RFC 5927 states that the acceptable ICMP has seq in SND.UNA =< SEG.SEQ < SND.NXT: These implementations check that the TCP sequence number contained in the payload of the ICMP error message is within the range SND.UNA =< SEG.SEQ < SND.NXT. tcp_v4_err() and tcp_v6_err() accept packets if seq meets between(seq, snd_una, tp->snd_nxt) -> tp->snd_nxt - snd_una >= seq - snd_una , which includes both ends. This is fine once connection is established because tcp_acceptable_seq() uses SND_NXT for ACK and RST. However, we should not accept ICMP to SND_NXT for SYN_SENT. The minimal repro is: --ip_version=ipv4 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 fcntl(3, F_SETFL, O_RDWR|O_NONBLOCK) = 0 +0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress) +0 > S 0:0(0) <...> +0 < icmp unreachable host_unreachable [1:1(0)] +0 %{assert tcpi_state == TCP_SYN_SENT}% Let's fix off-by-one. Note that we need to check seq != snd_una because tp->snd_nxt is only advanced to tp->write_seq after tcp_transmit_skb(). Otherwise, ICMP for SYN could be dropped before tcp_connect() advances tp->snd_nxt. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima --- net/ipv4/tcp_ipv4.c | 9 ++++++--- net/ipv6/tcp_ipv6.c | 9 ++++++--- 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2fc92a7884fc..7d58f522068d 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -499,8 +499,8 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct request_sock *fastopen; + u32 seq, snd_una, snd_nxt; struct tcp_sock *tp; - u32 seq, snd_una; struct sock *sk; int err; @@ -555,9 +555,12 @@ int tcp_v4_err(struct sk_buff *skb, u32 info) tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); - snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : READ_ONCE(tp->snd_una); + snd_nxt = READ_ONCE(tp->snd_nxt); if (sk->sk_state != TCP_LISTEN && - !between(seq, snd_una, tp->snd_nxt)) { + (!between(seq, snd_una, snd_nxt) || + (sk->sk_state == TCP_SYN_SENT && + seq != snd_una && seq == snd_nxt))) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 5c7ed38f1f56..8691d220cf94 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -410,9 +410,9 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, const struct tcphdr *th = (struct tcphdr *)(skb->data+offset); struct net *net = dev_net_rcu(skb->dev); struct request_sock *fastopen; + __u32 seq, snd_una, snd_nxt; struct ipv6_pinfo *np; struct tcp_sock *tp; - __u32 seq, snd_una; struct sock *sk; bool fatal; int err; @@ -463,9 +463,12 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); - snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; + snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : READ_ONCE(tp->snd_una); + snd_nxt = READ_ONCE(tp->snd_nxt); if (sk->sk_state != TCP_LISTEN && - !between(seq, snd_una, tp->snd_nxt)) { + (!between(seq, snd_una, snd_nxt) || + (sk->sk_state == TCP_SYN_SENT && + seq != snd_una && seq == snd_nxt))) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } -- 2.56.0.679.gc527c65306-goog