tcp: resets are misrouted

After commit e2446eaa ("tcp_v4_send_reset: binding oif to iif in no
sock case").. tcp resets are always lost, when routing is asymmetric.
Yes, backing out that patch will result in misrouting of resets for
dead connections which used interface binding when were alive, but we
actually cannot do anything here.  What's died that's died and correct
handling normal unbound connections is obviously a priority.

Comment to comment:
> This has few benefits:
>   1. tcp_v6_send_reset already did that.

It was done to route resets for IPv6 link local addresses. It was a
mistake to do so for global addresses. The patch fixes this as well.

Actually, the problem appears to be even more serious than guaranteed
loss of resets.  As reported by Sergey Soloviev <sol@eqv.ru>, those
misrouted resets create a lot of arp traffic and huge amount of
unresolved arp entires putting down to knees NAT firewalls which use
asymmetric routing.

Signed-off-by: Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 75735c9a6a9df2bf4026266c8c30d92bd474092c..ef998b008a570ba0976b911d85d0b98bb6d834fb 100644 (file)
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -708,10 +708,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
        arg.csumoffset = offsetof(struct tcphdr, check) / 2;
        arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
        /* When socket is gone, all binding information is lost.
-        * routing might fail in this case. using iif for oif to
-        * make sure we can deliver it
+        * routing might fail in this case. No choice here, if we choose to force
+        * input interface, we will misroute in case of asymmetric route.
         */
-       arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb);
+       if (sk)
+               arg.bound_dev_if = sk->sk_bound_dev_if;
 
        net = dev_net(skb_dst(skb)->dev);
        arg.tos = ip_hdr(skb)->tos;

diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 49c890386ce9ba6b76e401191d7d64484da7a238..26175bffbaa060ad8da6357330ff596a5391cef6 100644 (file)
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -877,7 +877,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
        __tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
 
        fl6.flowi6_proto = IPPROTO_TCP;
-       fl6.flowi6_oif = inet6_iif(skb);
+       if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
+               fl6.flowi6_oif = inet6_iif(skb);
        fl6.fl6_dport = t1->dest;
        fl6.fl6_sport = t1->source;
        security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));