diff options
| author | Christoph Paasch <christoph.paasch@uclouvain.be> | 2013-04-07 04:53:15 +0000 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2013-04-07 12:36:08 -0400 |
| commit | 50a75a8914539c5dcd441c5f54d237a666a426fd (patch) | |
| tree | 2635984dd1261e20a3c68b4170b8596a13c09174 | |
| parent | 53f63189b1110559dce8c1ee29e8abc3e31f7630 (diff) | |
| download | linux-50a75a8914539c5dcd441c5f54d237a666a426fd.tar.gz linux-50a75a8914539c5dcd441c5f54d237a666a426fd.tar.bz2 linux-50a75a8914539c5dcd441c5f54d237a666a426fd.zip | |
ipv6/tcp: Stop processing ICMPv6 redirect messages
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>
| -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 f6d629fd6aee..46a5be85be87 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) { |