diff options
| author | Christoph Paasch <christoph.paasch@uclouvain.be> | 2013-04-07 04:53:15 +0000 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2013-05-01 09:46:18 -0700 |
| commit | c642a760c494c82e7e415e14c5de4be3bf260056 (patch) | |
| tree | ba07ed952731951292682cb95348487a02a69024 /net | |
| parent | 1f451b69be3f3705018b314be47c832e5a53a1f6 (diff) | |
ipv6/tcp: Stop processing ICMPv6 redirect messages
[ Upstream commit 50a75a8914539c5dcd441c5f54d237a666a426fd ]
Tetja Rediske found that if the host receives an ICMPv6 redirect message
after sending a SYN+ACK, the connection will be reset.
He bisected it down to 093d04d (ipv6: Change skb->data before using
icmpv6_notify() to propagate redirect), but the origin of the bug comes
from ec18d9a26 (ipv6: Add redirect support to all protocol icmp error
handlers.). The bug simply did not trigger prior to 093d04d, because
skb->data did not point to the inner IP header and thus icmpv6_notify
did not call the correct err_handler.
This patch adds the missing "goto out;" in tcp_v6_err. After receiving
an ICMPv6 Redirect, we should not continue processing the ICMP in
tcp_v6_err, as this may trigger the removal of request-socks or setting
sk_err(_soft).
Reported-by: Tetja Rediske <tetja@tetja.de>
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'net')
| -rw-r--r-- | net/ipv6/tcp_ipv6.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 8d19346b7a3..89dfeddb026 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -386,6 +386,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (dst) dst->ops->redirect(dst, sk, skb); + goto out; } if (type == ICMPV6_PKT_TOOBIG) { |