From 588753f1eb18978512b1c9b85fddb457d46f9033 Mon Sep 17 00:00:00 2001 From: Brendan McGrath Date: Wed, 13 Dec 2017 22:14:57 +1100 Subject: ipv6: icmp6: Allow icmp messages to be looped back One example of when an ICMPv6 packet is required to be looped back is when a host acts as both a Multicast Listener and a Multicast Router. A Multicast Router will listen on address ff02::16 for MLDv2 messages. Currently, MLDv2 messages originating from a Multicast Listener running on the same host as the Multicast Router are not being delivered to the Multicast Router. This is due to dst.input being assigned the default value of dst_discard. This results in the packet being looped back but discarded before being delivered to the Multicast Router. This patch sets dst.input to ip6_input to ensure a looped back packet is delivered to the Multicast Router. Signed-off-by: Brendan McGrath Signed-off-by: David S. Miller --- net/ipv6/route.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv6') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 7a8d1500d374..2bc91c349273 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2336,6 +2336,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, } rt->dst.flags |= DST_HOST; + rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_gateway = fl6->daddr; rt->rt6i_dst.addr = fl6->daddr; -- cgit v1.2.3-59-g8ed1b From 2c52129a7d74d017320804c6928de770815c5f4a Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:25:09 +0800 Subject: ip6_gre: remove the incorrect mtu limit for ipgre tap The same fix as the patch "ip_gre: remove the incorrect mtu limit for ipgre tap" is also needed for ip6_gre. Fixes: 61e84623ace3 ("net: centralize net_device min/max MTU checking") Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4cfd8e0696fe..416c8913f132 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1308,6 +1308,7 @@ static void ip6gre_tap_setup(struct net_device *dev) ether_setup(dev); + dev->max_mtu = 0; dev->netdev_ops = &ip6gre_tap_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; -- cgit v1.2.3-59-g8ed1b From c9fefa08190fc879fb2e681035d7774e0a8c5170 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 18 Dec 2017 14:26:21 +0800 Subject: ip6_tunnel: get the min mtu properly in ip6_tnl_xmit Now it's using IPV6_MIN_MTU as the min mtu in ip6_tnl_xmit, but IPV6_MIN_MTU actually only works when the inner packet is ipv6. With IPV6_MIN_MTU for ipv4 packets, the new pmtu for inner dst couldn't be set less than 1280. It would cause tx_err and the packet to be dropped when the outer dst pmtu is close to 1280. Jianlin found it by running ipv4 traffic with the topo: (client) gre6 <---> eth1 (route) eth2 <---> gre6 (server) After changing eth2 mtu to 1300, the performance became very low, or the connection was even broken. The issue also affects ip4ip6 and ip6ip6 tunnels. So if the inner packet is ipv4, 576 should be considered as the min mtu. Note that for ip4ip6 and ip6ip6 tunnels, the inner packet can only be ipv4 or ipv6, but for gre6 tunnel, it may also be ARP. This patch using 576 as the min mtu for non-ipv6 packet works for all those cases. Reported-by: Jianlin Shi Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index db84f523656d..931c38f6ff4a 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1123,8 +1123,13 @@ route_lookup: max_headroom += 8; mtu -= 8; } - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; + if (skb->protocol == htons(ETH_P_IPV6)) { + if (mtu < IPV6_MIN_MTU) + mtu = IPV6_MIN_MTU; + } else if (mtu < 576) { + mtu = 576; + } + if (skb_dst(skb) && !t->parms.collect_md) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { -- cgit v1.2.3-59-g8ed1b From 58acfd714e6b02e8617448b431c2b64a2f1f0792 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 20 Dec 2017 12:28:25 +0200 Subject: ipv6: Honor specified parameters in fibmatch lookup Currently, parameters such as oif and source address are not taken into account during fibmatch lookup. Example (IPv4 for reference) before patch: $ ip -4 route show 192.0.2.0/24 dev dummy0 proto kernel scope link src 192.0.2.1 198.51.100.0/24 dev dummy1 proto kernel scope link src 198.51.100.1 $ ip -6 route show 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium 2001:db8:2::/64 dev dummy1 proto kernel metric 256 pref medium fe80::/64 dev dummy0 proto kernel metric 256 pref medium fe80::/64 dev dummy1 proto kernel metric 256 pref medium $ ip -4 route get fibmatch 192.0.2.2 oif dummy0 192.0.2.0/24 dev dummy0 proto kernel scope link src 192.0.2.1 $ ip -4 route get fibmatch 192.0.2.2 oif dummy1 RTNETLINK answers: No route to host $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy0 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy1 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium After: $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy0 2001:db8:1::/64 dev dummy0 proto kernel metric 256 pref medium $ ip -6 route get fibmatch 2001:db8:1::2 oif dummy1 RTNETLINK answers: Network is unreachable The problem stems from the fact that the necessary route lookup flags are not set based on these parameters. Instead of duplicating the same logic for fibmatch, we can simply resolve the original route from its copy and dump it instead. Fixes: 18c3a61c4264 ("net: ipv6: RTM_GETROUTE: return matched fib result when requested") Signed-off-by: Ido Schimmel Acked-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/route.c | 19 +++++++++++-------- 1 file changed, 11 insertions(+), 8 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 2bc91c349273..0458b761f3c5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4298,19 +4298,13 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, if (!ipv6_addr_any(&fl6.saddr)) flags |= RT6_LOOKUP_F_HAS_SADDR; - if (!fibmatch) - dst = ip6_route_input_lookup(net, dev, &fl6, flags); - else - dst = ip6_route_lookup(net, &fl6, 0); + dst = ip6_route_input_lookup(net, dev, &fl6, flags); rcu_read_unlock(); } else { fl6.flowi6_oif = oif; - if (!fibmatch) - dst = ip6_route_output(net, NULL, &fl6); - else - dst = ip6_route_lookup(net, &fl6, 0); + dst = ip6_route_output(net, NULL, &fl6); } @@ -4327,6 +4321,15 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout; } + if (fibmatch && rt->dst.from) { + struct rt6_info *ort = container_of(rt->dst.from, + struct rt6_info, dst); + + dst_hold(&ort->dst); + ip6_rt_put(rt); + rt = ort; + } + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); -- cgit v1.2.3-59-g8ed1b From 513674b5a2c9c7a67501506419da5c3c77ac6f08 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 20 Dec 2017 12:10:21 -0800 Subject: net: reevalulate autoflowlabel setting after sysctl setting sysctl.ip6.auto_flowlabels is default 1. In our hosts, we set it to 2. If sockopt doesn't set autoflowlabel, outcome packets from the hosts are supposed to not include flowlabel. This is true for normal packet, but not for reset packet. The reason is ipv6_pinfo.autoflowlabel is set in sock creation. Later if we change sysctl.ip6.auto_flowlabels, the ipv6_pinfo.autoflowlabel isn't changed, so the sock will keep the old behavior in terms of auto flowlabel. Reset packet is suffering from this problem, because reset packet is sent from a special control socket, which is created at boot time. Since sysctl.ipv6.auto_flowlabels is 1 by default, the control socket will always have its ipv6_pinfo.autoflowlabel set, even after user set sysctl.ipv6.auto_flowlabels to 1, so reset packset will always have flowlabel. Normal sock created before sysctl setting suffers from the same issue. We can't even turn off autoflowlabel unless we kill all socks in the hosts. To fix this, if IPV6_AUTOFLOWLABEL sockopt is used, we use the autoflowlabel setting from user, otherwise we always call ip6_default_np_autolabel() which has the new settings of sysctl. Note, this changes behavior a little bit. Before commit 42240901f7c4 (ipv6: Implement different admin modes for automatic flow labels), the autoflowlabel behavior of a sock isn't sticky, eg, if sysctl changes, existing connection will change autoflowlabel behavior. After that commit, autoflowlabel behavior is sticky in the whole life of the sock. With this patch, the behavior isn't sticky again. Cc: Martin KaFai Lau Cc: Eric Dumazet Cc: Tom Herbert Signed-off-by: Shaohua Li Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 ++- net/ipv6/af_inet6.c | 1 - net/ipv6/ip6_output.c | 12 ++++++++++-- net/ipv6/ipv6_sockglue.c | 1 + 4 files changed, 13 insertions(+), 4 deletions(-) (limited to 'net/ipv6') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index cb18c6290ca8..8415bf1a9776 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -273,7 +273,8 @@ struct ipv6_pinfo { * 100: prefer care-of address */ dontfrag:1, - autoflowlabel:1; + autoflowlabel:1, + autoflowlabel_set:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index c26f71234b9c..c9441ca45399 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -210,7 +210,6 @@ lookup_protocol: np->mcast_hops = IPV6_DEFAULT_MCASTHOPS; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->autoflowlabel = ip6_default_np_autolabel(net); np->repflow = net->ipv6.sysctl.flowlabel_reflect; sk->sk_ipv6only = net->ipv6.sysctl.bindv6only; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 5110a418cc4d..f7dd51c42314 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -166,6 +166,14 @@ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb) !(IP6CB(skb)->flags & IP6SKB_REROUTED)); } +static bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np) +{ + if (!np->autoflowlabel_set) + return ip6_default_np_autolabel(net); + else + return np->autoflowlabel; +} + /* * xmit an sk_buff (used by TCP, SCTP and DCCP) * Note : socket lock is not held for SYNACK packets, but might be modified @@ -230,7 +238,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, hlimit = ip6_dst_hoplimit(dst); ip6_flow_hdr(hdr, tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->payload_len = htons(seg_len); hdr->nexthdr = proto; @@ -1626,7 +1634,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, ip6_flow_hdr(hdr, v6_cork->tclass, ip6_make_flowlabel(net, skb, fl6->flowlabel, - np->autoflowlabel, fl6)); + ip6_autoflowlabel(net, np), fl6)); hdr->hop_limit = v6_cork->hop_limit; hdr->nexthdr = proto; hdr->saddr = fl6->saddr; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index b9404feabd78..2d4680e0376f 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -886,6 +886,7 @@ pref_skip_coa: break; case IPV6_AUTOFLOWLABEL: np->autoflowlabel = valbool; + np->autoflowlabel_set = 1; retv = 0; break; case IPV6_RECVFRAGSIZE: -- cgit v1.2.3-59-g8ed1b