From bc8e4b954e463716a57d8113dd50ae9d47b682a7 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Wed, 21 Apr 2010 16:25:30 -0700 Subject: xfrm6: ensure to use the same dev when building a bundle When building a bundle, we set dst.dev and rt6.rt6i_idev. We must ensure to set the same device for both fields. Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/xfrm6_policy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index ae181651c75a..00bf7c962b7e 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -124,7 +124,7 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, xdst->u.dst.dev = dev; dev_hold(dev); - xdst->u.rt6.rt6i_idev = in6_dev_get(rt->u.dst.dev); + xdst->u.rt6.rt6i_idev = in6_dev_get(dev); if (!xdst->u.rt6.rt6i_idev) return -ENODEV; -- cgit From f2228f785a9d97307aa8ba709088cfda6c3df73f Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Sun, 18 Apr 2010 16:58:22 +0000 Subject: ipv6: allow to send packet after receiving ICMPv6 Too Big message with MTU field less than IPV6_MIN_MTU According to RFC2460, PMTU is set to the IPv6 Minimum Link MTU (1280) and a fragment header should always be included after a node receiving Too Big message reporting PMTU is less than the IPv6 Minimum Link MTU. After receiving a ICMPv6 Too Big message reporting PMTU is less than the IPv6 Minimum Link MTU, sctp *can't* send any data/control chunk that total length including IPv6 head and IPv6 extend head is less than IPV6_MIN_MTU(1280 bytes). The failure occured in p6_fragment(), about reason see following(take SHUTDOWN chunk for example): sctp_packet_transmit (SHUTDOWN chunk, len=16 byte) |------sctp_v6_xmit (local_df=0) |------ip6_xmit |------ip6_output (dst_allfrag is ture) |------ip6_fragment In ip6_fragment(), for local_df=0, drops the the packet and returns EMSGSIZE. The patch fixes it with adding check length of skb->len. In this case, Ipv6 not to fragment upper protocol data, just only add a fragment header before it. Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 65f9c379df38..75d5ef830097 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -629,7 +629,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) /* We must not fragment if the socket is set to force MTU discovery * or if the skb it not generated by a local socket. */ - if (!skb->local_df) { + if (!skb->local_df && skb->len > mtu) { skb->dev = skb_dst(skb)->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), -- cgit From f4f914b58019f0e50d521bbbadfaee260d766f95 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 20 Apr 2010 21:21:26 +0000 Subject: net: ipv6 bind to device issue The issue raises when having 2 NICs both assigned the same IPv6 global address. If a sender binds to a particular NIC (SO_BINDTODEVICE), the outgoing traffic is being sent via the first found. The bonded device is thus not taken into an account during the routing. From the ip6_route_output function: If the binding address is multicast, linklocal or loopback, the RT6_LOOKUP_F_IFACE bit is set, but not for global address. So binding global address will neglect SO_BINDTODEVICE-binded device, because the fib6_rule_lookup function path won't check for the flowi::oif field and take first route that fits. Signed-off-by: Jiri Olsa Signed-off-by: Scott Otto Signed-off-by: David S. Miller --- net/ipv6/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c2438e8cb9d0..05ebd7833043 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -815,7 +815,7 @@ struct dst_entry * ip6_route_output(struct net *net, struct sock *sk, { int flags = 0; - if (rt6_need_strict(&fl->fl6_dst)) + if (fl->oif || rt6_need_strict(&fl->fl6_dst)) flags |= RT6_LOOKUP_F_IFACE; if (!ipv6_addr_any(&fl->fl6_src)) -- cgit From fda48a0d7a8412cedacda46a9c0bf8ef9cd13559 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 21 Apr 2010 09:26:15 +0000 Subject: tcp: bind() fix when many ports are bound Port autoselection done by kernel only works when number of bound sockets is under a threshold (typically 30000). When this threshold is over, we must check if there is a conflict before exiting first loop in inet_csk_get_port() Change inet_csk_bind_conflict() to forbid two reuse-enabled sockets to bind on same (address,port) tuple (with a non ANY address) Same change for inet6_csk_bind_conflict() Reported-by: Gaspar Chilingarov Signed-off-by: Eric Dumazet Acked-by: Evgeniy Polyakov Signed-off-by: David S. Miller --- net/ipv6/inet6_connection_sock.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 628db24bcf22..b4b7d40a9c95 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 != sk2 && (!sk->sk_bound_dev_if || !sk2->sk_bound_dev_if || - sk->sk_bound_dev_if == sk2->sk_bound_dev_if) && - (!sk->sk_reuse || !sk2->sk_reuse || - sk2->sk_state == TCP_LISTEN) && - ipv6_rcv_saddr_equal(sk, sk2)) - break; + sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { + if ((!sk->sk_reuse || !sk2->sk_reuse || + sk2->sk_state == TCP_LISTEN) && + ipv6_rcv_saddr_equal(sk, sk2)) + break; + else if (sk->sk_reuse && sk2->sk_reuse && + !ipv6_addr_any(inet6_rcv_saddr(sk2)) && + ipv6_rcv_saddr_equal(sk, sk2)) + break; + } } return node != NULL; -- cgit From 6443bb1fc2050ca2b6585a3fa77f7833b55329ed Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 25 Apr 2010 15:09:42 -0700 Subject: 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 Tested-by: Michael S. Tsirkin Signed-off-by: David S. Miller --- net/ipv6/inet6_connection_sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index b4b7d40a9c95..3a4d92b5a83e 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; } -- cgit