From 1b8e6a01e19f001e9f93b39c32387961c91ed3cc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 18 Nov 2015 12:40:13 -0800 Subject: tcp: md5: fix lockdep annotation When a passive TCP is created, we eventually call tcp_md5_do_add() with sk pointing to the child. It is not owner by the user yet (we will add this socket into listener accept queue a bit later anyway) But we do own the spinlock, so amend the lockdep annotation to avoid following splat : [ 8451.090932] net/ipv4/tcp_ipv4.c:923 suspicious rcu_dereference_protected() usage! [ 8451.090932] [ 8451.090932] other info that might help us debug this: [ 8451.090932] [ 8451.090934] [ 8451.090934] rcu_scheduler_active = 1, debug_locks = 1 [ 8451.090936] 3 locks held by socket_sockopt_/214795: [ 8451.090936] #0: (rcu_read_lock){.+.+..}, at: [] __netif_receive_skb_core+0x151/0xe90 [ 8451.090947] #1: (rcu_read_lock){.+.+..}, at: [] ip_local_deliver_finish+0x43/0x2b0 [ 8451.090952] #2: (slock-AF_INET){+.-...}, at: [] sk_clone_lock+0x1c5/0x500 [ 8451.090958] [ 8451.090958] stack backtrace: [ 8451.090960] CPU: 7 PID: 214795 Comm: socket_sockopt_ [ 8451.091215] Call Trace: [ 8451.091216] [] dump_stack+0x55/0x76 [ 8451.091229] [] lockdep_rcu_suspicious+0xeb/0x110 [ 8451.091235] [] tcp_md5_do_add+0x1bf/0x1e0 [ 8451.091239] [] tcp_v4_syn_recv_sock+0x1f1/0x4c0 [ 8451.091242] [] ? tcp_v4_md5_hash_skb+0x167/0x190 [ 8451.091246] [] tcp_check_req+0x3c8/0x500 [ 8451.091249] [] ? tcp_v4_inbound_md5_hash+0x11e/0x190 [ 8451.091253] [] tcp_v4_rcv+0x3c0/0x9f0 [ 8451.091256] [] ? ip_local_deliver_finish+0x43/0x2b0 [ 8451.091260] [] ip_local_deliver_finish+0xb6/0x2b0 [ 8451.091263] [] ? ip_local_deliver_finish+0x43/0x2b0 [ 8451.091267] [] ip_local_deliver+0x48/0x80 [ 8451.091270] [] ip_rcv_finish+0x160/0x700 [ 8451.091273] [] ip_rcv+0x29e/0x3d0 [ 8451.091277] [] __netif_receive_skb_core+0xb47/0xe90 Fixes: a8afca0329988 ("tcp: md5: protects md5sig_info with RCU") Signed-off-by: Eric Dumazet Reported-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ba09016d1bfd..db003438aaf5 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -921,7 +921,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, } md5sig = rcu_dereference_protected(tp->md5sig_info, - sock_owned_by_user(sk)); + sock_owned_by_user(sk) || + lockdep_is_held(&sk->sk_lock.slock)); if (!md5sig) { md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) -- cgit v1.2.3 From 5037e9ef9454917b047f9f3a19b4dd179fbf7cd4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 14 Dec 2015 14:08:53 -0800 Subject: net: fix IP early demux races David Wilder reported crashes caused by dst reuse. I am seeing a crash on a distro V4.2.3 kernel caused by a double release of a dst_entry. In ipv4_dst_destroy() the call to list_empty() finds a poisoned next pointer, indicating the dst_entry has already been removed from the list and freed. The crash occurs 18 to 24 hours into a run of a network stress exerciser. Thanks to his detailed report and analysis, we were able to understand the core issue. IP early demux can associate a dst to skb, after a lookup in TCP/UDP sockets. When socket cache is not properly set, we want to store into sk->sk_dst_cache the dst for future IP early demux lookups, by acquiring a stable refcount on the dst. Problem is this acquisition is simply using an atomic_inc(), which works well, unless the dst was queued for destruction from dst_release() noticing dst refcount went to zero, if DST_NOCACHE was set on dst. We need to make sure current refcount is not zero before incrementing it, or risk double free as David reported. This patch, being a stable candidate, adds two new helpers, and use them only from IP early demux problematic paths. It might be possible to merge in net-next skb_dst_force() and skb_dst_force_safe(), but I prefer having the smallest patch for stable kernels : Maybe some skb_dst_force() callers do not expect skb->dst can suddenly be cleared. Can probably be backported back to linux-3.6 kernels Reported-by: David J. Wilder Tested-by: David J. Wilder Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/dst.h | 33 +++++++++++++++++++++++++++++++++ include/net/sock.h | 2 +- net/ipv4/tcp_ipv4.c | 5 ++--- net/ipv6/tcp_ipv6.c | 3 +-- 4 files changed, 37 insertions(+), 6 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/include/net/dst.h b/include/net/dst.h index 1279f9b09791..c7329dcd90cc 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -322,6 +322,39 @@ static inline void skb_dst_force(struct sk_buff *skb) } } +/** + * dst_hold_safe - Take a reference on a dst if possible + * @dst: pointer to dst entry + * + * This helper returns false if it could not safely + * take a reference on a dst. + */ +static inline bool dst_hold_safe(struct dst_entry *dst) +{ + if (dst->flags & DST_NOCACHE) + return atomic_inc_not_zero(&dst->__refcnt); + dst_hold(dst); + return true; +} + +/** + * skb_dst_force_safe - makes sure skb dst is refcounted + * @skb: buffer + * + * If dst is not yet refcounted and not destroyed, grab a ref on it. + */ +static inline void skb_dst_force_safe(struct sk_buff *skb) +{ + if (skb_dst_is_noref(skb)) { + struct dst_entry *dst = skb_dst(skb); + + if (!dst_hold_safe(dst)) + dst = NULL; + + skb->_skb_refdst = (unsigned long)dst; + } +} + /** * __skb_tunnel_rx - prepare skb for rx reinsert diff --git a/include/net/sock.h b/include/net/sock.h index c4205e0a3a2d..28790fe18206 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -817,7 +817,7 @@ void sk_stream_write_space(struct sock *sk); static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { /* dont let skb dst not refcounted, we are going to leave rcu lock */ - skb_dst_force(skb); + skb_dst_force_safe(skb); if (!sk->sk_backlog.tail) sk->sk_backlog.head = skb; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index db003438aaf5..d8841a2f1569 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1493,7 +1493,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb) if (likely(sk->sk_rx_dst)) skb_dst_drop(skb); else - skb_dst_force(skb); + skb_dst_force_safe(skb); __skb_queue_tail(&tp->ucopy.prequeue, skb); tp->ucopy.memory += skb->truesize; @@ -1721,8 +1721,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { - dst_hold(dst); + if (dst && dst_hold_safe(dst)) { sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index e7aab561b7b4..6b8a8a9091fa 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -93,10 +93,9 @@ static void inet6_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - if (dst) { + if (dst && dst_hold_safe(dst)) { const struct rt6_info *rt = (const struct rt6_info *)dst; - dst_hold(dst); sk->sk_rx_dst = dst; inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; inet6_sk(sk)->rx_dst_cookie = rt6_get_cookie(rt); -- cgit v1.2.3