From 84581bdae9587023cea1d139523f0ef0f28bd88d Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 27 Aug 2018 18:41:32 +0800 Subject: erspan: set erspan_ver to 1 by default when adding an erspan dev After erspan_ver is introudced, if erspan_ver is not set in iproute, its value will be left 0 by default. Since Commit 02f99df1875c ("erspan: fix invalid erspan version."), it has broken the traffic due to the version check in erspan_xmit if users are not aware of 'erspan_ver' param, like using an old version of iproute. To fix this compatibility problem, it sets erspan_ver to 1 by default when adding an erspan dev in erspan_setup. Note that we can't do it in ipgre_netlink_parms, as this function is also used by ipgre_changelink. Fixes: 02f99df1875c ("erspan: fix invalid erspan version.") Reported-by: Jianlin Shi 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 18a3794b0f52..e493b041d4ac 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1778,6 +1778,7 @@ static void ip6gre_netlink_parms(struct nlattr *data[], if (data[IFLA_GRE_COLLECT_METADATA]) parms->collect_md = true; + parms->erspan_ver = 1; if (data[IFLA_GRE_ERSPAN_VER]) parms->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); -- cgit v1.2.3 From 9f2895461439fda2801a7906fb4c5fb3dbb37a0a Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Thu, 23 Aug 2018 19:49:54 +0300 Subject: vti6: remove !skb->ignore_df check from vti6_xmit() Before the commit d6990976af7c ("vti6: fix PMTU caching and reporting on xmit") '!skb->ignore_df' check was always true because the function skb_scrub_packet() was called before it, resetting ignore_df to zero. In the commit, skb_scrub_packet() was moved below, and now this check can be false for the packet, e.g. when sending it in the two fragments, this prevents successful PMTU updates in such case. The next attempts to send the packet lead to the same tx error. Moreover, vti6 initial MTU value relies on PMTU adjustments. This issue can be reproduced with the following LTP test script: udp_ipsec_vti.sh -6 -p ah -m tunnel -s 2000 Fixes: ccd740cbc6e0 ("vti6: Add pmtu handling to vti6_xmit.") Signed-off-by: Alexey Kodanev Acked-by: Steffen Klassert Signed-off-by: David S. Miller --- net/ipv6/ip6_vti.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 5095367c7204..eeaf7455d51e 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -481,7 +481,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) } mtu = dst_mtu(dst); - if (!skb->ignore_df && skb->len > mtu) { + if (skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { -- cgit v1.2.3 From afe49de44c27a89e8e9631c44b5ffadf6ace65e2 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 28 Aug 2018 13:40:51 +0200 Subject: ipv6: fix cleanup ordering for ip6_mr failure Commit 15e668070a64 ("ipv6: reorder icmpv6_init() and ip6_mr_init()") moved the cleanup label for ipmr_fail, but should have changed the contents of the cleanup labels as well. Now we can end up cleaning up icmpv6 even though it hasn't been initialized (jump to icmp_fail or ipmr_fail). Simply undo things in the reverse order of their initialization. Example of panic (triggered by faking a failure of icmpv6_init): kasan: GPF could be caused by NULL-ptr deref or user memory access general protection fault: 0000 [#1] PREEMPT SMP KASAN PTI [...] RIP: 0010:__list_del_entry_valid+0x79/0x160 [...] Call Trace: ? lock_release+0x8a0/0x8a0 unregister_pernet_operations+0xd4/0x560 ? ops_free_list+0x480/0x480 ? down_write+0x91/0x130 ? unregister_pernet_subsys+0x15/0x30 ? down_read+0x1b0/0x1b0 ? up_read+0x110/0x110 ? kmem_cache_create_usercopy+0x1b4/0x240 unregister_pernet_subsys+0x1d/0x30 icmpv6_cleanup+0x1d/0x30 inet6_init+0x1b5/0x23f Fixes: 15e668070a64 ("ipv6: reorder icmpv6_init() and ip6_mr_init()") Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- net/ipv6/af_inet6.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 673bba31eb18..e5da133c6932 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -1113,11 +1113,11 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: - ip6_mr_cleanup(); + icmpv6_cleanup(); icmp_fail: - unregister_pernet_subsys(&inet6_net_ops); + ip6_mr_cleanup(); ipmr_fail: - icmpv6_cleanup(); + unregister_pernet_subsys(&inet6_net_ops); register_pernet_fail: sock_unregister(PF_INET6); rtnl_unregister_all(PF_INET6); -- cgit v1.2.3 From a03dc36bdca6b614651fedfcd8559cf914d2d21d Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Tue, 28 Aug 2018 13:40:52 +0200 Subject: ipv6: fix cleanup ordering for pingv6 registration Commit 6d0bfe226116 ("net: ipv6: Add IPv6 support to the ping socket.") contains an error in the cleanup path of inet6_init(): when proto_register(&pingv6_prot, 1) fails, we try to unregister &pingv6_prot. When rawv6_init() fails, we skip unregistering &pingv6_prot. Example of panic (triggered by faking a failure of proto_register(&pingv6_prot, 1)): general protection fault: 0000 [#1] PREEMPT SMP KASAN PTI [...] RIP: 0010:__list_del_entry_valid+0x79/0x160 [...] Call Trace: proto_unregister+0xbb/0x550 ? trace_preempt_on+0x6f0/0x6f0 ? sock_no_shutdown+0x10/0x10 inet6_init+0x153/0x1b8 Fixes: 6d0bfe226116 ("net: ipv6: Add IPv6 support to the ping socket.") Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- net/ipv6/af_inet6.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e5da133c6932..9a4261e50272 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -938,14 +938,14 @@ static int __init inet6_init(void) err = proto_register(&pingv6_prot, 1); if (err) - goto out_unregister_ping_proto; + goto out_unregister_raw_proto; /* We MUST register RAW sockets before we create the ICMP6, * IGMP6, or NDISC control sockets. */ err = rawv6_init(); if (err) - goto out_unregister_raw_proto; + goto out_unregister_ping_proto; /* Register the family here so that the init calls below will * be able to create sockets. (?? is this dangerous ??) -- cgit v1.2.3 From 93bbadd6e0a2a58e49d265b9b1aa58e621b60a26 Mon Sep 17 00:00:00 2001 From: Alexey Kodanev Date: Thu, 30 Aug 2018 19:11:24 +0300 Subject: ipv6: don't get lwtstate twice in ip6_rt_copy_init() Commit 80f1a0f4e0cd ("net/ipv6: Put lwtstate when destroying fib6_info") partially fixed the kmemleak [1], lwtstate can be copied from fib6_info, with ip6_rt_copy_init(), and it should be done only once there. rt->dst.lwtstate is set by ip6_rt_init_dst(), at the start of the function ip6_rt_copy_init(), so there is no need to get it again at the end. With this patch, lwtstate also isn't copied from RTF_REJECT routes. [1]: unreferenced object 0xffff880b6aaa14e0 (size 64): comm "ip", pid 10577, jiffies 4295149341 (age 1273.903s) hex dump (first 32 bytes): 01 00 04 00 04 00 00 00 10 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<0000000018664623>] lwtunnel_build_state+0x1bc/0x420 [<00000000b73aa29a>] ip6_route_info_create+0x9f7/0x1fd0 [<00000000ee2c5d1f>] ip6_route_add+0x14/0x70 [<000000008537b55c>] inet6_rtm_newroute+0xd9/0xe0 [<000000002acc50f5>] rtnetlink_rcv_msg+0x66f/0x8e0 [<000000008d9cd381>] netlink_rcv_skb+0x268/0x3b0 [<000000004c893c76>] netlink_unicast+0x417/0x5a0 [<00000000f2ab1afb>] netlink_sendmsg+0x70b/0xc30 [<00000000890ff0aa>] sock_sendmsg+0xb1/0xf0 [<00000000a2e7b66f>] ___sys_sendmsg+0x659/0x950 [<000000001e7426c8>] __sys_sendmsg+0xde/0x170 [<00000000fe411443>] do_syscall_64+0x9f/0x4a0 [<000000001be7b28b>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000006d21f353>] 0xffffffffffffffff Fixes: 6edb3c96a5f0 ("net/ipv6: Defer initialization of dst to data path") Signed-off-by: Alexey Kodanev Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/route.c | 1 - 1 file changed, 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c4ea13e8360b..18e00ce1719a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -996,7 +996,6 @@ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) rt->rt6i_src = ort->fib6_src; #endif rt->rt6i_prefsrc = ort->fib6_prefsrc; - rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); } static struct fib6_node* fib6_backtrack(struct fib6_node *fn, -- cgit v1.2.3 From 15a81b418e22a9aa4a0504471fdcb0f4ebf69b96 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Thu, 30 Aug 2018 14:15:43 -0700 Subject: net/ipv6: Only update MTU metric if it set Jan reported a regression after an update to 4.18.5. In this case ipv6 default route is setup by systemd-networkd based on data from an RA. The RA contains an MTU of 1492 which is used when the route is first inserted but then systemd-networkd pushes down updates to the default route without the mtu set. Prior to the change to fib6_info, metrics such as MTU were held in the dst_entry and rt6i_pmtu in rt6_info contained an update to the mtu if any. ip6_mtu would look at rt6i_pmtu first and use it if set. If not, the value from the metrics is used if it is set and finally falling back to the idev value. After the fib6_info change metrics are contained in the fib6_info struct and there is no equivalent to rt6i_pmtu. To maintain consistency with the old behavior the new code should only reset the MTU in the metrics if the route update has it set. Fixes: d4ead6b34b67 ("net/ipv6: move metrics from dst to rt6_info") Reported-by: Jan Janssen Signed-off-by: David Ahern Signed-off-by: David S. Miller --- net/ipv6/ip6_fib.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index c861a6d4671d..5516f55e214b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -989,7 +989,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_clean_expires(iter); else fib6_set_expires(iter, rt->expires); - fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); + + if (rt->fib6_pmtu) + fib6_metric_set(iter, RTAX_MTU, + rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, -- cgit v1.2.3 From 36feaac35405e932ad9c321d7a2db8a7e4a4d7ca Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Fri, 31 Aug 2018 16:52:01 +0800 Subject: ip6_tunnel: respect ttl inherit for ip6tnl man ip-tunnel ttl section says: 0 is a special value meaning that packets inherit the TTL value. IPv4 tunnel respect this in ip_tunnel_xmit(), but IPv6 tunnel has not implement it yet. To make IPv6 behave consistently with IP tunnel, add ipv6 tunnel inherit support. Signed-off-by: Hangbin Liu Signed-off-by: David S. Miller --- net/ipv6/ip6_tunnel.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5df2a58d945c..419960b0ba16 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1188,7 +1188,15 @@ route_lookup: init_tel_txopt(&opt, encap_limit); ipv6_push_frag_opts(skb, &opt.ops, &proto); } - hop_limit = hop_limit ? : ip6_dst_hoplimit(dst); + + if (hop_limit == 0) { + if (skb->protocol == htons(ETH_P_IP)) + hop_limit = ip_hdr(skb)->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + hop_limit = ipv6_hdr(skb)->hop_limit; + else + hop_limit = ip6_dst_hoplimit(dst); + } /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. -- cgit v1.2.3