From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: PROBLEM: Linux kernel 2.6.31 IPv4 TCP fails to open huge amount of outgoing connections (unable to bind ... ) Date: Sun, 25 Apr 2010 18:21:00 +0200 Message-ID: <1272212460.2069.9.camel@edumazet-laptop> References: <1271828799.7895.1287.camel@edumazet-laptop> <20100421082559.GA32475@ioremap.net> <1271840535.7895.1612.camel@edumazet-laptop> <20100421095812.GA14778@ioremap.net> <1271849253.7895.1929.camel@edumazet-laptop> <20100421182723.GA17202@ioremap.net> <1271875416.7895.3033.camel@edumazet-laptop> <20100421185837.GB21249@ioremap.net> <1271877975.7895.3171.camel@edumazet-laptop> <20100425142642.GA11411@redhat.com> <20100425155600.GA13319@ioremap.net> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: "Michael S. Tsirkin" , Ben Greear , David Miller , Gaspar Chilingarov , netdev To: Evgeniy Polyakov Return-path: Received: from mail-bw0-f219.google.com ([209.85.218.219]:35796 "EHLO mail-bw0-f219.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753461Ab0DYQVH (ORCPT ); Sun, 25 Apr 2010 12:21:07 -0400 Received: by bwz19 with SMTP id 19so633765bwz.21 for ; Sun, 25 Apr 2010 09:21:04 -0700 (PDT) In-Reply-To: <20100425155600.GA13319@ioremap.net> Sender: netdev-owner@vger.kernel.org List-ID: Le dimanche 25 avril 2010 =C3=A0 19:56 +0400, Evgeniy Polyakov a =C3=A9= crit : > On Sun, Apr 25, 2010 at 05:26:42PM +0300, Michael S. Tsirkin (mst@red= hat.com) wrote: >=20 > > > diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_co= nnection_sock.c > > > index 0c5e3c3..fb6959c 100644 > > > --- a/net/ipv6/inet6_connection_sock.c > > > +++ b/net/ipv6/inet6_connection_sock.c > > > @@ -42,11 +42,16 @@ int inet6_csk_bind_conflict(const struct sock= *sk, > > > if (sk !=3D sk2 && > > > (!sk->sk_bound_dev_if || > > > !sk2->sk_bound_dev_if || > > > - sk->sk_bound_dev_if =3D=3D sk2->sk_bound_dev_if) && > > > - (!sk->sk_reuse || !sk2->sk_reuse || > > > - sk2->sk_state =3D=3D TCP_LISTEN) && > > > - ipv6_rcv_saddr_equal(sk, sk2)) > > > - break; > > > + sk->sk_bound_dev_if =3D=3D sk2->sk_bound_dev_if)) { > > > + if ((!sk->sk_reuse || !sk2->sk_reuse || > > > + sk2->sk_state =3D=3D TCP_LISTEN) && > > > + ipv6_rcv_saddr_equal(sk, sk2)) > > > + break; > > > + else if (sk->sk_reuse && sk2->sk_reuse && > > > + !ipv6_addr_any(inet6_rcv_saddr(sk2)) && >=20 > I suppose above line is guilty when inet6_rcv_saddr() returns NULL? >=20 Sorry, I cant test this at this moment (I am travelling) Evgeniy, David could you double check ? Michael, could you test this patch ? Thanks ! [PATCH] ipv6: Fix inet6_csk_bind_conflict() Commit fda48a0d7a84 (tcp: bind() fix when many ports are bound) introduced a bug on IPV6 part. We should not call ipv6_addr_any(inet6_rcv_saddr(sk2)) but ipv6_addr_any(inet6_rcv_saddr(sk)) because sk2 can be IPV4, while sk is IPV6. Reported-by: Michael S. Tsirkin Signed-off-by: Eric Dumazet --- diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connecti= on_sock.c index b4b7d40..3a4d92b 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -48,7 +48,7 @@ int inet6_csk_bind_conflict(const struct sock *sk, ipv6_rcv_saddr_equal(sk, sk2)) break; else if (sk->sk_reuse && sk2->sk_reuse && - !ipv6_addr_any(inet6_rcv_saddr(sk2)) && + !ipv6_addr_any(inet6_rcv_saddr(sk)) && ipv6_rcv_saddr_equal(sk, sk2)) break; }