* [PATCH 4.14 095/126] inet: frags: Convert timers to use timer_setup()
[not found] <20180917211703.481236999@linuxfoundation.org>
@ 2018-09-17 22:42 ` Greg Kroah-Hartman
2018-09-17 22:42 ` [PATCH 4.14 098/126] ipv6: export ip6 fragments sysctl to unprivileged users Greg Kroah-Hartman
` (5 subsequent siblings)
6 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2018-09-17 22:42 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable, Alexander Aring, Stefan Schmidt,
David S. Miller, Alexey Kuznetsov, Hideaki YOSHIFUJI,
Pablo Neira Ayuso, Jozsef Kadlecsik, Florian Westphal, linux-wpan,
netdev, netfilter-devel, coreteam, Kees Cook
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kees Cook <keescook@chromium.org>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Stefan Schmidt <stefan@osg.samsung.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: Pablo Neira Ayuso <pablo@netfilter.org>
Cc: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Cc: Florian Westphal <fw@strlen.de>
Cc: linux-wpan@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: netfilter-devel@vger.kernel.org
Cc: coreteam@netfilter.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Stefan Schmidt <stefan@osg.samsung.com> # for ieee802154
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 78802011fbe34331bdef6f2dfb1634011f0e4c32)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
include/net/inet_frag.h | 2 +-
net/ieee802154/6lowpan/reassembly.c | 5 +++--
net/ipv4/inet_fragment.c | 4 ++--
net/ipv4/ip_fragment.c | 5 +++--
net/ipv6/netfilter/nf_conntrack_reasm.c | 5 +++--
net/ipv6/reassembly.c | 5 +++--
6 files changed, 15 insertions(+), 11 deletions(-)
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -97,7 +97,7 @@ struct inet_frags {
void (*constructor)(struct inet_frag_queue *q,
const void *arg);
void (*destructor)(struct inet_frag_queue *);
- void (*frag_expire)(unsigned long data);
+ void (*frag_expire)(struct timer_list *t);
struct kmem_cache *frags_cachep;
const char *frags_cache_name;
};
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -80,12 +80,13 @@ static void lowpan_frag_init(struct inet
fq->daddr = *arg->dst;
}
-static void lowpan_frag_expire(unsigned long data)
+static void lowpan_frag_expire(struct timer_list *t)
{
+ struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct frag_queue *fq;
struct net *net;
- fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+ fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags);
spin_lock(&fq->q.lock);
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -150,7 +150,7 @@ inet_evict_bucket(struct inet_frags *f,
spin_unlock(&hb->chain_lock);
hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
- f->frag_expire((unsigned long) fq);
+ f->frag_expire(&fq->timer);
return evicted;
}
@@ -367,7 +367,7 @@ static struct inet_frag_queue *inet_frag
f->constructor(q, arg);
add_frag_mem_limit(nf, f->qsize);
- setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
+ timer_setup(&q->timer, f->frag_expire, 0);
spin_lock_init(&q->lock);
refcount_set(&q->refcnt, 1);
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -191,12 +191,13 @@ static bool frag_expire_skip_icmp(u32 us
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
-static void ip_expire(unsigned long arg)
+static void ip_expire(struct timer_list *t)
{
+ struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct ipq *qp;
struct net *net;
- qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
+ qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
rcu_read_lock();
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -169,12 +169,13 @@ static unsigned int nf_hashfn(const stru
return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr);
}
-static void nf_ct_frag6_expire(unsigned long data)
+static void nf_ct_frag6_expire(struct timer_list *t)
{
+ struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct frag_queue *fq;
struct net *net;
- fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+ fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, nf_frag.frags);
ip6_expire_frag_queue(net, fq);
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -169,12 +169,13 @@ out:
}
EXPORT_SYMBOL(ip6_expire_frag_queue);
-static void ip6_frag_expire(unsigned long data)
+static void ip6_frag_expire(struct timer_list *t)
{
+ struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct frag_queue *fq;
struct net *net;
- fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+ fq = container_of(frag, struct frag_queue, q);
net = container_of(fq->q.net, struct net, ipv6.frags);
ip6_expire_frag_queue(net, fq);
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH 4.14 098/126] ipv6: export ip6 fragments sysctl to unprivileged users
[not found] <20180917211703.481236999@linuxfoundation.org>
2018-09-17 22:42 ` [PATCH 4.14 095/126] inet: frags: Convert timers to use timer_setup() Greg Kroah-Hartman
@ 2018-09-17 22:42 ` Greg Kroah-Hartman
2018-09-17 22:42 ` Greg Kroah-Hartman
` (4 subsequent siblings)
6 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2018-09-17 22:42 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable,
netdev@vger.kernel.org, stable@vger.kernel.org, edumazet@google.com, Nikolay Borisov,
Eric Dumazet, David S. Miller, Nikolay Borisov
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <edumazet@google.com>
IPv4 was changed in commit 52a773d645e9 ("net: Export ip fragment
sysctl to unprivileged users")
The only sysctl that is not per-netns is not used :
ip6frag_secret_interval
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Nikolay Borisov <kernel@kyup.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 18dcbe12fe9fca0ab825f7eff993060525ac2503)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv6/reassembly.c | 4 ----
1 file changed, 4 deletions(-)
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -649,10 +649,6 @@ static int __net_init ip6_frags_ns_sysct
table[1].data = &net->ipv6.frags.low_thresh;
table[1].extra2 = &net->ipv6.frags.high_thresh;
table[2].data = &net->ipv6.frags.timeout;
-
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- table[0].procname = NULL;
}
hdr = register_net_sysctl(net, "net/ipv6", table);
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH 4.14 098/126] ipv6: export ip6 fragments sysctl to unprivileged users
[not found] <20180917211703.481236999@linuxfoundation.org>
2018-09-17 22:42 ` [PATCH 4.14 095/126] inet: frags: Convert timers to use timer_setup() Greg Kroah-Hartman
2018-09-17 22:42 ` [PATCH 4.14 098/126] ipv6: export ip6 fragments sysctl to unprivileged users Greg Kroah-Hartman
@ 2018-09-17 22:42 ` Greg Kroah-Hartman
2018-09-17 22:42 ` [PATCH 4.14 118/126] ipv4: frags: precedence bug in ip_expire() Greg Kroah-Hartman
` (3 subsequent siblings)
6 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2018-09-17 22:42 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable,
netdev@vger.kernel.org, stable@vger.kernel.org, edumazet@google.com, Nikolay Borisov,
Eric Dumazet, David S. Miller, Nikolay Borisov
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <edumazet@google.com>
IPv4 was changed in commit 52a773d645e9 ("net: Export ip fragment
sysctl to unprivileged users")
The only sysctl that is not per-netns is not used :
ip6frag_secret_interval
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Nikolay Borisov <kernel@kyup.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 18dcbe12fe9fca0ab825f7eff993060525ac2503)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv6/reassembly.c | 4 ----
1 file changed, 4 deletions(-)
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -649,10 +649,6 @@ static int __net_init ip6_frags_ns_sysct
table[1].data = &net->ipv6.frags.low_thresh;
table[1].extra2 = &net->ipv6.frags.high_thresh;
table[2].data = &net->ipv6.frags.timeout;
-
- /* Don't export sysctls to unprivileged users */
- if (net->user_ns != &init_user_ns)
- table[0].procname = NULL;
}
hdr = register_net_sysctl(net, "net/ipv6", table);
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH 4.14 118/126] ipv4: frags: precedence bug in ip_expire()
[not found] <20180917211703.481236999@linuxfoundation.org>
` (2 preceding siblings ...)
2018-09-17 22:42 ` Greg Kroah-Hartman
@ 2018-09-17 22:42 ` Greg Kroah-Hartman
2018-09-17 22:42 ` Greg Kroah-Hartman
` (2 subsequent siblings)
6 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2018-09-17 22:42 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable,
netdev@vger.kernel.org, stable@vger.kernel.org, edumazet@google.com, Dan Carpenter,
David S. Miller, Dan Carpenter
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dan Carpenter <dan.carpenter@oracle.com>
We accidentally removed the parentheses here, but they are required
because '!' has higher precedence than '&'.
Fixes: fa0f527358bd ("ip: use rb trees for IP frag queue.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 70837ffe3085c9a91488b52ca13ac84424da1042)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv4/ip_fragment.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -154,7 +154,7 @@ static void ip_expire(struct timer_list
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
- if (!qp->q.flags & INET_FRAG_FIRST_IN)
+ if (!(qp->q.flags & INET_FRAG_FIRST_IN))
goto out;
/* sk_buff::dev and sk_buff::rbnode are unionized. So we
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH 4.14 118/126] ipv4: frags: precedence bug in ip_expire()
[not found] <20180917211703.481236999@linuxfoundation.org>
` (3 preceding siblings ...)
2018-09-17 22:42 ` [PATCH 4.14 118/126] ipv4: frags: precedence bug in ip_expire() Greg Kroah-Hartman
@ 2018-09-17 22:42 ` Greg Kroah-Hartman
2018-09-17 22:42 ` [PATCH 4.14 121/126] ip: frags: fix crash in ip_do_fragment() Greg Kroah-Hartman
2018-09-17 22:42 ` Greg Kroah-Hartman
6 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2018-09-17 22:42 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable,
netdev@vger.kernel.org, stable@vger.kernel.org, edumazet@google.com, Dan Carpenter,
David S. Miller, Dan Carpenter
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dan Carpenter <dan.carpenter@oracle.com>
We accidentally removed the parentheses here, but they are required
because '!' has higher precedence than '&'.
Fixes: fa0f527358bd ("ip: use rb trees for IP frag queue.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
(cherry picked from commit 70837ffe3085c9a91488b52ca13ac84424da1042)
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv4/ip_fragment.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -154,7 +154,7 @@ static void ip_expire(struct timer_list
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
- if (!qp->q.flags & INET_FRAG_FIRST_IN)
+ if (!(qp->q.flags & INET_FRAG_FIRST_IN))
goto out;
/* sk_buff::dev and sk_buff::rbnode are unionized. So we
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH 4.14 121/126] ip: frags: fix crash in ip_do_fragment()
[not found] <20180917211703.481236999@linuxfoundation.org>
` (4 preceding siblings ...)
2018-09-17 22:42 ` Greg Kroah-Hartman
@ 2018-09-17 22:42 ` Greg Kroah-Hartman
2018-09-17 22:42 ` Greg Kroah-Hartman
6 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2018-09-17 22:42 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable,
netdev@vger.kernel.org, stable@vger.kernel.org, edumazet@google.com, Taehee Yoo,
Eric Dumazet, David S. Miller, Taehee Yoo
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Taehee Yoo <ap420073@gmail.com>
commit 5d407b071dc369c26a38398326ee2be53651cfe4 upstream
A kernel crash occurrs when defragmented packet is fragmented
in ip_do_fragment().
In defragment routine, skb_orphan() is called and
skb->ip_defrag_offset is set. but skb->sk and
skb->ip_defrag_offset are same union member. so that
frag->sk is not NULL.
Hence crash occurrs in skb->sk check routine in ip_do_fragment() when
defragmented packet is fragmented.
test commands:
%iptables -t nat -I POSTROUTING -j MASQUERADE
%hping3 192.168.4.2 -s 1000 -p 2000 -d 60000
splat looks like:
[ 261.069429] kernel BUG at net/ipv4/ip_output.c:636!
[ 261.075753] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 261.083854] CPU: 1 PID: 1349 Comm: hping3 Not tainted 4.19.0-rc2+ #3
[ 261.100977] RIP: 0010:ip_do_fragment+0x1613/0x2600
[ 261.106945] Code: e8 e2 38 e3 fe 4c 8b 44 24 18 48 8b 74 24 08 e9 92 f6 ff ff 80 3c 02 00 0f 85 da 07 00 00 48 8b b5 d0 00 00 00 e9 25 f6 ff ff <0f> 0b 0f 0b 44 8b 54 24 58 4c 8b 4c 24 18 4c 8b 5c 24 60 4c 8b 6c
[ 261.127015] RSP: 0018:ffff8801031cf2c0 EFLAGS: 00010202
[ 261.134156] RAX: 1ffff1002297537b RBX: ffffed0020639e6e RCX: 0000000000000004
[ 261.142156] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880114ba9bd8
[ 261.150157] RBP: ffff880114ba8a40 R08: ffffed0022975395 R09: ffffed0022975395
[ 261.158157] R10: 0000000000000001 R11: ffffed0022975394 R12: ffff880114ba9ca4
[ 261.166159] R13: 0000000000000010 R14: ffff880114ba9bc0 R15: dffffc0000000000
[ 261.174169] FS: 00007fbae2199700(0000) GS:ffff88011b400000(0000) knlGS:0000000000000000
[ 261.183012] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 261.189013] CR2: 00005579244fe000 CR3: 0000000119bf4000 CR4: 00000000001006e0
[ 261.198158] Call Trace:
[ 261.199018] ? dst_output+0x180/0x180
[ 261.205011] ? save_trace+0x300/0x300
[ 261.209018] ? ip_copy_metadata+0xb00/0xb00
[ 261.213034] ? sched_clock_local+0xd4/0x140
[ 261.218158] ? kill_l4proto+0x120/0x120 [nf_conntrack]
[ 261.223014] ? rt_cpu_seq_stop+0x10/0x10
[ 261.227014] ? find_held_lock+0x39/0x1c0
[ 261.233008] ip_finish_output+0x51d/0xb50
[ 261.237006] ? ip_fragment.constprop.56+0x220/0x220
[ 261.243011] ? nf_ct_l4proto_register_one+0x5b0/0x5b0 [nf_conntrack]
[ 261.250152] ? rcu_is_watching+0x77/0x120
[ 261.255010] ? nf_nat_ipv4_out+0x1e/0x2b0 [nf_nat_ipv4]
[ 261.261033] ? nf_hook_slow+0xb1/0x160
[ 261.265007] ip_output+0x1c7/0x710
[ 261.269005] ? ip_mc_output+0x13f0/0x13f0
[ 261.273002] ? __local_bh_enable_ip+0xe9/0x1b0
[ 261.278152] ? ip_fragment.constprop.56+0x220/0x220
[ 261.282996] ? nf_hook_slow+0xb1/0x160
[ 261.287007] raw_sendmsg+0x21f9/0x4420
[ 261.291008] ? dst_output+0x180/0x180
[ 261.297003] ? sched_clock_cpu+0x126/0x170
[ 261.301003] ? find_held_lock+0x39/0x1c0
[ 261.306155] ? stop_critical_timings+0x420/0x420
[ 261.311004] ? check_flags.part.36+0x450/0x450
[ 261.315005] ? _raw_spin_unlock_irq+0x29/0x40
[ 261.320995] ? _raw_spin_unlock_irq+0x29/0x40
[ 261.326142] ? cyc2ns_read_end+0x10/0x10
[ 261.330139] ? raw_bind+0x280/0x280
[ 261.334138] ? sched_clock_cpu+0x126/0x170
[ 261.338995] ? check_flags.part.36+0x450/0x450
[ 261.342991] ? __lock_acquire+0x4500/0x4500
[ 261.348994] ? inet_sendmsg+0x11c/0x500
[ 261.352989] ? dst_output+0x180/0x180
[ 261.357012] inet_sendmsg+0x11c/0x500
[ ... ]
v2:
- clear skb->sk at reassembly routine.(Eric Dumarzet)
Fixes: fa0f527358bd ("ip: use rb trees for IP frag queue.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv4/ip_fragment.c | 1 +
net/ipv6/netfilter/nf_conntrack_reasm.c | 1 +
2 files changed, 2 insertions(+)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -599,6 +599,7 @@ static int ip_frag_reasm(struct ipq *qp,
nextp = &fp->next;
fp->prev = NULL;
memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+ fp->sk = NULL;
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -453,6 +453,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq,
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
+ fp->sk = NULL;
}
sub_frag_mem_limit(fq->q.net, head->truesize);
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH 4.14 121/126] ip: frags: fix crash in ip_do_fragment()
[not found] <20180917211703.481236999@linuxfoundation.org>
` (5 preceding siblings ...)
2018-09-17 22:42 ` [PATCH 4.14 121/126] ip: frags: fix crash in ip_do_fragment() Greg Kroah-Hartman
@ 2018-09-17 22:42 ` Greg Kroah-Hartman
6 siblings, 0 replies; 7+ messages in thread
From: Greg Kroah-Hartman @ 2018-09-17 22:42 UTC (permalink / raw)
To: linux-kernel
Cc: Greg Kroah-Hartman, stable,
netdev@vger.kernel.org, stable@vger.kernel.org, edumazet@google.com, Taehee Yoo,
Eric Dumazet, David S. Miller, Taehee Yoo
4.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Taehee Yoo <ap420073@gmail.com>
commit 5d407b071dc369c26a38398326ee2be53651cfe4 upstream
A kernel crash occurrs when defragmented packet is fragmented
in ip_do_fragment().
In defragment routine, skb_orphan() is called and
skb->ip_defrag_offset is set. but skb->sk and
skb->ip_defrag_offset are same union member. so that
frag->sk is not NULL.
Hence crash occurrs in skb->sk check routine in ip_do_fragment() when
defragmented packet is fragmented.
test commands:
%iptables -t nat -I POSTROUTING -j MASQUERADE
%hping3 192.168.4.2 -s 1000 -p 2000 -d 60000
splat looks like:
[ 261.069429] kernel BUG at net/ipv4/ip_output.c:636!
[ 261.075753] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI
[ 261.083854] CPU: 1 PID: 1349 Comm: hping3 Not tainted 4.19.0-rc2+ #3
[ 261.100977] RIP: 0010:ip_do_fragment+0x1613/0x2600
[ 261.106945] Code: e8 e2 38 e3 fe 4c 8b 44 24 18 48 8b 74 24 08 e9 92 f6 ff ff 80 3c 02 00 0f 85 da 07 00 00 48 8b b5 d0 00 00 00 e9 25 f6 ff ff <0f> 0b 0f 0b 44 8b 54 24 58 4c 8b 4c 24 18 4c 8b 5c 24 60 4c 8b 6c
[ 261.127015] RSP: 0018:ffff8801031cf2c0 EFLAGS: 00010202
[ 261.134156] RAX: 1ffff1002297537b RBX: ffffed0020639e6e RCX: 0000000000000004
[ 261.142156] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880114ba9bd8
[ 261.150157] RBP: ffff880114ba8a40 R08: ffffed0022975395 R09: ffffed0022975395
[ 261.158157] R10: 0000000000000001 R11: ffffed0022975394 R12: ffff880114ba9ca4
[ 261.166159] R13: 0000000000000010 R14: ffff880114ba9bc0 R15: dffffc0000000000
[ 261.174169] FS: 00007fbae2199700(0000) GS:ffff88011b400000(0000) knlGS:0000000000000000
[ 261.183012] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 261.189013] CR2: 00005579244fe000 CR3: 0000000119bf4000 CR4: 00000000001006e0
[ 261.198158] Call Trace:
[ 261.199018] ? dst_output+0x180/0x180
[ 261.205011] ? save_trace+0x300/0x300
[ 261.209018] ? ip_copy_metadata+0xb00/0xb00
[ 261.213034] ? sched_clock_local+0xd4/0x140
[ 261.218158] ? kill_l4proto+0x120/0x120 [nf_conntrack]
[ 261.223014] ? rt_cpu_seq_stop+0x10/0x10
[ 261.227014] ? find_held_lock+0x39/0x1c0
[ 261.233008] ip_finish_output+0x51d/0xb50
[ 261.237006] ? ip_fragment.constprop.56+0x220/0x220
[ 261.243011] ? nf_ct_l4proto_register_one+0x5b0/0x5b0 [nf_conntrack]
[ 261.250152] ? rcu_is_watching+0x77/0x120
[ 261.255010] ? nf_nat_ipv4_out+0x1e/0x2b0 [nf_nat_ipv4]
[ 261.261033] ? nf_hook_slow+0xb1/0x160
[ 261.265007] ip_output+0x1c7/0x710
[ 261.269005] ? ip_mc_output+0x13f0/0x13f0
[ 261.273002] ? __local_bh_enable_ip+0xe9/0x1b0
[ 261.278152] ? ip_fragment.constprop.56+0x220/0x220
[ 261.282996] ? nf_hook_slow+0xb1/0x160
[ 261.287007] raw_sendmsg+0x21f9/0x4420
[ 261.291008] ? dst_output+0x180/0x180
[ 261.297003] ? sched_clock_cpu+0x126/0x170
[ 261.301003] ? find_held_lock+0x39/0x1c0
[ 261.306155] ? stop_critical_timings+0x420/0x420
[ 261.311004] ? check_flags.part.36+0x450/0x450
[ 261.315005] ? _raw_spin_unlock_irq+0x29/0x40
[ 261.320995] ? _raw_spin_unlock_irq+0x29/0x40
[ 261.326142] ? cyc2ns_read_end+0x10/0x10
[ 261.330139] ? raw_bind+0x280/0x280
[ 261.334138] ? sched_clock_cpu+0x126/0x170
[ 261.338995] ? check_flags.part.36+0x450/0x450
[ 261.342991] ? __lock_acquire+0x4500/0x4500
[ 261.348994] ? inet_sendmsg+0x11c/0x500
[ 261.352989] ? dst_output+0x180/0x180
[ 261.357012] inet_sendmsg+0x11c/0x500
[ ... ]
v2:
- clear skb->sk at reassembly routine.(Eric Dumarzet)
Fixes: fa0f527358bd ("ip: use rb trees for IP frag queue.")
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
net/ipv4/ip_fragment.c | 1 +
net/ipv6/netfilter/nf_conntrack_reasm.c | 1 +
2 files changed, 2 insertions(+)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -599,6 +599,7 @@ static int ip_frag_reasm(struct ipq *qp,
nextp = &fp->next;
fp->prev = NULL;
memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+ fp->sk = NULL;
head->data_len += fp->len;
head->len += fp->len;
if (head->ip_summed != fp->ip_summed)
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -453,6 +453,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq,
else if (head->ip_summed == CHECKSUM_COMPLETE)
head->csum = csum_add(head->csum, fp->csum);
head->truesize += fp->truesize;
+ fp->sk = NULL;
}
sub_frag_mem_limit(fq->q.net, head->truesize);
^ permalink raw reply [flat|nested] 7+ messages in thread