From 9cf7490360bf2c46a16b7525f899e4970c5fc144 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 2 Feb 2016 19:31:12 -0800 Subject: tcp: do not drop syn_recv on all icmp reports Petr Novopashenniy reported that ICMP redirects on SYN_RECV sockets were leading to RST. This is of course incorrect. A specific list of ICMP messages should be able to drop a SYN_RECV. For instance, a REDIRECT on SYN_RECV shall be ignored, as we do not hold a dst per SYN_RECV pseudo request. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111751 Fixes: 079096f103fa ("tcp/dccp: install syn_recv requests into ehash table") Reported-by: Petr Novopashenniy Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a4d5237..7f6ff03 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -311,7 +311,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk) /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ -void tcp_req_err(struct sock *sk, u32 seq) +void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); @@ -323,7 +323,7 @@ void tcp_req_err(struct sock *sk, u32 seq) if (seq != tcp_rsk(req)->snt_isn) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); - } else { + } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly @@ -383,7 +383,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) - return tcp_req_err(sk, seq); + return tcp_req_err(sk, seq, + type == ICMP_PARAMETERPROB || + type == ICMP_TIME_EXCEEDED || + (type == ICMP_DEST_UNREACH && + (code == ICMP_NET_UNREACH || + code == ICMP_HOST_UNREACH))); bh_lock_sock(sk); /* If too many ICMPs get dropped on busy -- cgit v1.1 From 729235554d805c63e5e274fcc6a98e71015dd847 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 11 Feb 2016 22:50:29 -0800 Subject: tcp: md5: release request socket instead of listener If tcp_v4_inbound_md5_hash() returns an error, we must release the refcount on the request socket, not on the listener. The bug was added for IPv4 only. Fixes: 079096f103fac ("tcp/dccp: install syn_recv requests into ehash table") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7f6ff03..c844779 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1600,8 +1600,10 @@ process: struct sock *nsk = NULL; sk = req->rsk_listener; - if (tcp_v4_inbound_md5_hash(sk, skb)) - goto discard_and_relse; + if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { + reqsk_put(req); + goto discard_it; + } if (likely(sk->sk_state == TCP_LISTEN)) { nsk = tcp_check_req(sk, skb, req, false); } else { -- cgit v1.1 From 7716682cc58e305e22207d5bb315f26af6b1e243 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Feb 2016 05:39:18 -0800 Subject: tcp/dccp: fix another race at listener dismantle Ilya reported following lockdep splat: kernel: ========================= kernel: [ BUG: held lock freed! ] kernel: 4.5.0-rc1-ceph-00026-g5e0a311 #1 Not tainted kernel: ------------------------- kernel: swapper/5/0 is freeing memory ffff880035c9d200-ffff880035c9dbff, with a lock still held there! kernel: (&(&queue->rskq_lock)->rlock){+.-...}, at: [] inet_csk_reqsk_queue_add+0x28/0xa0 kernel: 4 locks held by swapper/5/0: kernel: #0: (rcu_read_lock){......}, at: [] netif_receive_skb_internal+0x4b/0x1f0 kernel: #1: (rcu_read_lock){......}, at: [] ip_local_deliver_finish+0x3f/0x380 kernel: #2: (slock-AF_INET){+.-...}, at: [] sk_clone_lock+0x19b/0x440 kernel: #3: (&(&queue->rskq_lock)->rlock){+.-...}, at: [] inet_csk_reqsk_queue_add+0x28/0xa0 To properly fix this issue, inet_csk_reqsk_queue_add() needs to return to its callers if the child as been queued into accept queue. We also need to make sure listener is still there before calling sk->sk_data_ready(), by holding a reference on it, since the reference carried by the child can disappear as soon as the child is put on accept queue. Reported-by: Ilya Dryomov Fixes: ebb516af60e1 ("tcp/dccp: fix race at listener dismantle phase") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_ipv4.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net/ipv4/tcp_ipv4.c') diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index c844779..487ac67 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1597,30 +1597,30 @@ process: if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); - struct sock *nsk = NULL; + struct sock *nsk; sk = req->rsk_listener; if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { reqsk_put(req); goto discard_it; } - if (likely(sk->sk_state == TCP_LISTEN)) { - nsk = tcp_check_req(sk, skb, req, false); - } else { + if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } + sock_hold(sk); + nsk = tcp_check_req(sk, skb, req, false); if (!nsk) { reqsk_put(req); - goto discard_it; + goto discard_and_relse; } if (nsk == sk) { - sock_hold(sk); reqsk_put(req); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); - goto discard_it; + goto discard_and_relse; } else { + sock_put(sk); return 0; } } -- cgit v1.1