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 to093d04d
(ipv6: Change skb->data before using icmpv6_notify() to propagate redirect), but the origin of the bug comes fromec18d9a26
(ipv6: Add redirect support to all protocol icmp error handlers.). The bug simply did not trigger prior to093d04d
, 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>
This commit is contained in:
parent
53f63189b1
commit
50a75a8914
|
@ -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) {
|
||||
|
|
Loading…
Reference in New Issue