[PATCH AUTOSEL 4.19 05/49] netfilter: nf_queue: fix reinject verdict handling

[PATCH AUTOSEL 4.19 05/49] netfilter: nf_queue: fix reinject verdict handling

[Sasha Levin]

From: Jagdish Motwani <jagdish.motwani@sophos.com>

[ Upstream commit 946c0d8e6ed43dae6527e878d0077c1e11015db0 ]

This patch fixes netfilter hook traversal when there are more than 1 hooks
returning NF_QUEUE verdict. When the first queue reinjects the packet,
'nf_reinject' starts traversing hooks with a proper hook_index. However,
if it again receives a NF_QUEUE verdict (by some other netfilter hook), it
queues the packet with a wrong hook_index. So, when the second queue
reinjects the packet, it re-executes hooks in between.

Fixes: 960632ece694 ("netfilter: convert hook list to an array")
Signed-off-by: Jagdish Motwani <jagdish.motwani@sophos.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_queue.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index d67a96a25a68..7569ba00e732 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -238,6 +238,7 @@ static unsigned int nf_iterate(struct sk_buff *skb,
 repeat:
 		verdict = nf_hook_entry_hookfn(hook, skb, state);
 		if (verdict != NF_ACCEPT) {
+			*index = i;
 			if (verdict != NF_REPEAT)
 				return verdict;
 			goto repeat;
-- 
2.20.1

[PATCH AUTOSEL 4.19 06/49] ipvs: Fix use-after-free in ip_vs_in

[Sasha Levin]

From: YueHaibing <yuehaibing@huawei.com>

[ Upstream commit 719c7d563c17b150877cee03a4b812a424989dfa ]

BUG: KASAN: use-after-free in ip_vs_in.part.29+0xe8/0xd20 [ip_vs]
Read of size 4 at addr ffff8881e9b26e2c by task sshd/5603

CPU: 0 PID: 5603 Comm: sshd Not tainted 4.19.39+ #30
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
Call Trace:
 dump_stack+0x71/0xab
 print_address_description+0x6a/0x270
 kasan_report+0x179/0x2c0
 ip_vs_in.part.29+0xe8/0xd20 [ip_vs]
 ip_vs_in+0xd8/0x170 [ip_vs]
 nf_hook_slow+0x5f/0xe0
 __ip_local_out+0x1d5/0x250
 ip_local_out+0x19/0x60
 __tcp_transmit_skb+0xba1/0x14f0
 tcp_write_xmit+0x41f/0x1ed0
 ? _copy_from_iter_full+0xca/0x340
 __tcp_push_pending_frames+0x52/0x140
 tcp_sendmsg_locked+0x787/0x1600
 ? tcp_sendpage+0x60/0x60
 ? inet_sk_set_state+0xb0/0xb0
 tcp_sendmsg+0x27/0x40
 sock_sendmsg+0x6d/0x80
 sock_write_iter+0x121/0x1c0
 ? sock_sendmsg+0x80/0x80
 __vfs_write+0x23e/0x370
 vfs_write+0xe7/0x230
 ksys_write+0xa1/0x120
 ? __ia32_sys_read+0x50/0x50
 ? __audit_syscall_exit+0x3ce/0x450
 do_syscall_64+0x73/0x200
 entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7ff6f6147c60
Code: 73 01 c3 48 8b 0d 28 12 2d 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 5d 73 2d 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83
RSP: 002b:00007ffd772ead18 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000034 RCX: 00007ff6f6147c60
RDX: 0000000000000034 RSI: 000055df30a31270 RDI: 0000000000000003
RBP: 000055df30a31270 R08: 0000000000000000 R09: 0000000000000000
R10: 00007ffd772ead70 R11: 0000000000000246 R12: 00007ffd772ead74
R13: 00007ffd772eae20 R14: 00007ffd772eae24 R15: 000055df2f12ddc0

Allocated by task 6052:
 kasan_kmalloc+0xa0/0xd0
 __kmalloc+0x10a/0x220
 ops_init+0x97/0x190
 register_pernet_operations+0x1ac/0x360
 register_pernet_subsys+0x24/0x40
 0xffffffffc0ea016d
 do_one_initcall+0x8b/0x253
 do_init_module+0xe3/0x335
 load_module+0x2fc0/0x3890
 __do_sys_finit_module+0x192/0x1c0
 do_syscall_64+0x73/0x200
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Freed by task 6067:
 __kasan_slab_free+0x130/0x180
 kfree+0x90/0x1a0
 ops_free_list.part.7+0xa6/0xc0
 unregister_pernet_operations+0x18b/0x1f0
 unregister_pernet_subsys+0x1d/0x30
 ip_vs_cleanup+0x1d/0xd2f [ip_vs]
 __x64_sys_delete_module+0x20c/0x300
 do_syscall_64+0x73/0x200
 entry_SYSCALL_64_after_hwframe+0x44/0xa9

The buggy address belongs to the object at ffff8881e9b26600 which belongs to the cache kmalloc-4096 of size 4096
The buggy address is located 2092 bytes inside of 4096-byte region [ffff8881e9b26600, ffff8881e9b27600)
The buggy address belongs to the page:
page:ffffea0007a6c800 count:1 mapcount:0 mapping:ffff888107c0e600 index:0x0 compound_mapcount: 0
flags: 0x17ffffc0008100(slab|head)
raw: 0017ffffc0008100 dead000000000100 dead000000000200 ffff888107c0e600
raw: 0000000000000000 0000000080070007 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

while unregistering ipvs module, ops_free_list calls
__ip_vs_cleanup, then nf_unregister_net_hooks be called to
do remove nf hook entries. It need a RCU period to finish,
however net->ipvs is set to NULL immediately, which will
trigger NULL pointer dereference when a packet is hooked
and handled by ip_vs_in where net->ipvs is dereferenced.

Another scene is ops_free_list call ops_free to free the
net_generic directly while __ip_vs_cleanup finished, then
calling ip_vs_in will triggers use-after-free.

This patch moves nf_unregister_net_hooks from __ip_vs_cleanup()
to __ip_vs_dev_cleanup(),  where rcu_barrier() is called by
unregister_pernet_device -> unregister_pernet_operations,
that will do the needed grace period.

Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: efe41606184e ("ipvs: convert to use pernet nf_hook api")
Suggested-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/ipvs/ip_vs_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index a42c1bc7c698..62c0e80dcd71 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2280,7 +2280,6 @@ static void __net_exit __ip_vs_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
-	nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	ip_vs_service_net_cleanup(ipvs);	/* ip_vs_flush() with locks */
 	ip_vs_conn_net_cleanup(ipvs);
 	ip_vs_app_net_cleanup(ipvs);
@@ -2295,6 +2294,7 @@ static void __net_exit __ip_vs_dev_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
 	EnterFunction(2);
+	nf_unregister_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
 	ipvs->enable = 0;	/* Disable packet reception */
 	smp_wmb();
 	ip_vs_sync_net_cleanup(ipvs);
-- 
2.20.1

[PATCH AUTOSEL 4.19 11/49] mISDN: make sure device name is NUL terminated

[Sasha Levin]

From: Dan Carpenter <dan.carpenter@oracle.com>

[ Upstream commit ccfb62f27beb295103e9392462b20a6ed807d0ea ]

The user can change the device_name with the IMSETDEVNAME ioctl, but we
need to ensure that the user's name is NUL terminated.  Otherwise it
could result in a buffer overflow when we copy the name back to the user
with IMGETDEVINFO ioctl.

I also changed two strcpy() calls which handle the name to strscpy().
Hopefully, there aren't any other ways to create a too long name, but
it's nice to do this as a kernel hardening measure.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/isdn/mISDN/socket.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c
index b2abc44fa5cb..a73337b74f41 100644
--- a/drivers/isdn/mISDN/socket.c
+++ b/drivers/isdn/mISDN/socket.c
@@ -394,7 +394,7 @@ data_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			memcpy(di.channelmap, dev->channelmap,
 			       sizeof(di.channelmap));
 			di.nrbchan = dev->nrbchan;
-			strcpy(di.name, dev_name(&dev->dev));
+			strscpy(di.name, dev_name(&dev->dev), sizeof(di.name));
 			if (copy_to_user((void __user *)arg, &di, sizeof(di)))
 				err = -EFAULT;
 		} else
@@ -677,7 +677,7 @@ base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			memcpy(di.channelmap, dev->channelmap,
 			       sizeof(di.channelmap));
 			di.nrbchan = dev->nrbchan;
-			strcpy(di.name, dev_name(&dev->dev));
+			strscpy(di.name, dev_name(&dev->dev), sizeof(di.name));
 			if (copy_to_user((void __user *)arg, &di, sizeof(di)))
 				err = -EFAULT;
 		} else
@@ -691,6 +691,7 @@ base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 			err = -EFAULT;
 			break;
 		}
+		dn.name[sizeof(dn.name) - 1] = '\0';
 		dev = get_mdevice(dn.id);
 		if (dev)
 			err = device_rename(&dev->dev, dn.name);
-- 
2.20.1

[PATCH AUTOSEL 4.19 18/49] net: stmmac: update rx tail pointer register to fix rx dma hang issue.

[Sasha Levin]

From: Biao Huang <biao.huang@mediatek.com>

[ Upstream commit 4523a5611526709ec9b4e2574f1bb7818212651e ]

Currently we will not update the receive descriptor tail pointer in
stmmac_rx_refill. Rx dma will think no available descriptors and stop
once received packets exceed DMA_RX_SIZE, so that the rx only test will fail.

Update the receive tail pointer in stmmac_rx_refill to add more descriptors
to the rx channel, so packets can be received continually

Fixes: 54139cf3bb33 ("net: stmmac: adding multiple buffers for rx")
Signed-off-by: Biao Huang <biao.huang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 50c00822b2d8..45e64d71a93f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3319,6 +3319,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue)
 		entry = STMMAC_GET_ENTRY(entry, DMA_RX_SIZE);
 	}
 	rx_q->dirty_rx = entry;
+	stmmac_set_rx_tail_ptr(priv, priv->ioaddr, rx_q->rx_tail_addr, queue);
 }
 
 /**
-- 
2.20.1

[PATCH AUTOSEL 4.19 19/49] net: tulip: de4x5: Drop redundant MODULE_DEVICE_TABLE()

[Sasha Levin]

From: Kees Cook <keescook@chromium.org>

[ Upstream commit 3e66b7cc50ef921121babc91487e1fb98af1ba6e ]

Building with Clang reports the redundant use of MODULE_DEVICE_TABLE():

drivers/net/ethernet/dec/tulip/de4x5.c:2110:1: error: redefinition of '__mod_eisa__de4x5_eisa_ids_device_table'
MODULE_DEVICE_TABLE(eisa, de4x5_eisa_ids);
^
./include/linux/module.h:229:21: note: expanded from macro 'MODULE_DEVICE_TABLE'
extern typeof(name) __mod_##type##__##name##_device_table               \
                    ^
<scratch space>:90:1: note: expanded from here
__mod_eisa__de4x5_eisa_ids_device_table
^
drivers/net/ethernet/dec/tulip/de4x5.c:2100:1: note: previous definition is here
MODULE_DEVICE_TABLE(eisa, de4x5_eisa_ids);
^
./include/linux/module.h:229:21: note: expanded from macro 'MODULE_DEVICE_TABLE'
extern typeof(name) __mod_##type##__##name##_device_table               \
                    ^
<scratch space>:85:1: note: expanded from here
__mod_eisa__de4x5_eisa_ids_device_table
^

This drops the one further from the table definition to match the common
use of MODULE_DEVICE_TABLE().

Fixes: 07563c711fbc ("EISA bus MODALIAS attributes support")
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/dec/tulip/de4x5.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index 66535d1653f6..f16853c3c851 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -2107,7 +2107,6 @@ static struct eisa_driver de4x5_eisa_driver = {
 		.remove  = de4x5_eisa_remove,
         }
 };
-MODULE_DEVICE_TABLE(eisa, de4x5_eisa_ids);
 #endif
 
 #ifdef CONFIG_PCI
-- 
2.20.1

[PATCH AUTOSEL 4.19 24/49] net: aquantia: tx clean budget logic error

[Sasha Levin]

From: Igor Russkikh <Igor.Russkikh@aquantia.com>

[ Upstream commit 31bafc49a7736989e4c2d9f7280002c66536e590 ]

In case no other traffic happening on the ring, full tx cleanup
may not be completed. That may cause socket buffer to overflow
and tx traffic to stuck until next activity on the ring happens.

This is due to logic error in budget variable decrementor.
Variable is compared with zero, and then post decremented,
causing it to become MAX_INT. Solution is remove decrementor
from the `for` statement and rewrite it in a clear way.

Fixes: b647d3980948e ("net: aquantia: Add tx clean budget and valid budget handling logic")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/aq_ring.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
index 6f3312350cac..b3c7994d73eb 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c
@@ -139,10 +139,10 @@ void aq_ring_queue_stop(struct aq_ring_s *ring)
 bool aq_ring_tx_clean(struct aq_ring_s *self)
 {
 	struct device *dev = aq_nic_get_dev(self->aq_nic);
-	unsigned int budget = AQ_CFG_TX_CLEAN_BUDGET;
+	unsigned int budget;
 
-	for (; self->sw_head != self->hw_head && budget--;
-		self->sw_head = aq_ring_next_dx(self, self->sw_head)) {
+	for (budget = AQ_CFG_TX_CLEAN_BUDGET;
+	     budget && self->sw_head != self->hw_head; budget--) {
 		struct aq_ring_buff_s *buff = &self->buff_ring[self->sw_head];
 
 		if (likely(buff->is_mapped)) {
@@ -167,6 +167,7 @@ bool aq_ring_tx_clean(struct aq_ring_s *self)
 
 		buff->pa = 0U;
 		buff->eop_index = 0xffffU;
+		self->sw_head = aq_ring_next_dx(self, self->sw_head);
 	}
 
 	return !!budget;
-- 
2.20.1

[PATCH AUTOSEL 4.19 25/49] net: aquantia: fix LRO with FCS error

[Sasha Levin]

From: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>

[ Upstream commit eaeb3b7494ba9159323814a8ce8af06a9277d99b ]

Driver stops producing skbs on ring if a packet with FCS error
was coalesced into LRO session. Ring gets hang forever.

Thats a logical error in driver processing descriptors:
When rx_stat indicates MAC Error, next pointer and eop flags
are not filled. This confuses driver so it waits for descriptor 0
to be filled by HW.

Solution is fill next pointer and eop flag even for packets with FCS error.

Fixes: bab6de8fd180b ("net: ethernet: aquantia: Atlantic A0 and B0 specific functions.")
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: Dmitry Bogdanov <dmitry.bogdanov@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../aquantia/atlantic/hw_atl/hw_atl_b0.c      | 61 ++++++++++---------
 1 file changed, 32 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 56363ff5c891..51cd1f98bcf0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -695,38 +695,41 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self,
 		if ((rx_stat & BIT(0)) || rxd_wb->type & 0x1000U) {
 			/* MAC error or DMA error */
 			buff->is_error = 1U;
-		} else {
-			if (self->aq_nic_cfg->is_rss) {
-				/* last 4 byte */
-				u16 rss_type = rxd_wb->type & 0xFU;
-
-				if (rss_type && rss_type < 0x8U) {
-					buff->is_hash_l4 = (rss_type == 0x4 ||
-					rss_type == 0x5);
-					buff->rss_hash = rxd_wb->rss_hash;
-				}
+		}
+		if (self->aq_nic_cfg->is_rss) {
+			/* last 4 byte */
+			u16 rss_type = rxd_wb->type & 0xFU;
+
+			if (rss_type && rss_type < 0x8U) {
+				buff->is_hash_l4 = (rss_type == 0x4 ||
+				rss_type == 0x5);
+				buff->rss_hash = rxd_wb->rss_hash;
 			}
+		}
 
-			if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
-				buff->len = rxd_wb->pkt_len %
-					AQ_CFG_RX_FRAME_MAX;
-				buff->len = buff->len ?
-					buff->len : AQ_CFG_RX_FRAME_MAX;
-				buff->next = 0U;
-				buff->is_eop = 1U;
+		if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) {
+			buff->len = rxd_wb->pkt_len %
+				AQ_CFG_RX_FRAME_MAX;
+			buff->len = buff->len ?
+				buff->len : AQ_CFG_RX_FRAME_MAX;
+			buff->next = 0U;
+			buff->is_eop = 1U;
+		} else {
+			buff->len =
+				rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ?
+				AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len;
+
+			if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
+				rxd_wb->status) {
+				/* LRO */
+				buff->next = rxd_wb->next_desc_ptr;
+				++ring->stats.rx.lro_packets;
 			} else {
-				if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT &
-					rxd_wb->status) {
-					/* LRO */
-					buff->next = rxd_wb->next_desc_ptr;
-					++ring->stats.rx.lro_packets;
-				} else {
-					/* jumbo */
-					buff->next =
-						aq_ring_next_dx(ring,
-								ring->hw_head);
-					++ring->stats.rx.jumbo_packets;
-				}
+				/* jumbo */
+				buff->next =
+					aq_ring_next_dx(ring,
+							ring->hw_head);
+				++ring->stats.rx.jumbo_packets;
 			}
 		}
 	}
-- 
2.20.1