summary | shortlog | log | commit | commitdiff | tree
raw | patch | inline | side by side (parent: 1f451b6)
raw | patch | inline | side by side (parent: 1f451b6)
author | Christoph Paasch <christoph.paasch@uclouvain.be> | |
Sun, 7 Apr 2013 04:53:15 +0000 (04:53 +0000) | ||
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | |
Wed, 1 May 2013 16:46:18 +0000 (09:46 -0700) |
[ 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>
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>
net/ipv6/tcp_ipv6.c | patch | blob | history |
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8d19346b7a31e66b70e12c98db406c23573d6e8b..89dfeddb026922d02ae1c382d4e9b3413d2ce5dc 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
if (dst)
dst->ops->redirect(dst, sk, skb);
+ goto out;
}
if (type == ICMPV6_PKT_TOOBIG) {