Fix for GRE tunnel running in IPSec (rhbz 1272571)

1 files changed, 91 insertions, 0 deletions

diff --git a/0001-ipv6-Avoid-creating-RTF_CACHE-from-a-rt-that-is-not-.patch b/0001-ipv6-Avoid-creating-RTF_CACHE-from-a-rt-that-is-not-.patch
new file mode 100644
index 000000000..3390024d2
--- /dev/null
+++ b/0001-ipv6-Avoid-creating-RTF_CACHE-from-a-rt-that-is-not-.patch
@@ -0,0 +1,91 @@
+From 0d3f6d297bfb7af24d0508460fdb3d1ec4903fa3 Mon Sep 17 00:00:00 2001
+From: Martin KaFai Lau <kafai@fb.com>
+Date: Wed, 11 Nov 2015 11:51:06 -0800
+Subject: [PATCH] ipv6: Avoid creating RTF_CACHE from a rt that is not managed
+ by fib6 tree
+
+The original bug report:
+https://bugzilla.redhat.com/show_bug.cgi?id=1272571
+
+The setup has a IPv4 GRE tunnel running in a IPSec.  The bug
+happens when ndisc starts sending router solicitation at the gre
+interface.  The simplified oops stack is like:
+
+__lock_acquire+0x1b2/0x1c30
+lock_acquire+0xb9/0x140
+_raw_write_lock_bh+0x3f/0x50
+__ip6_ins_rt+0x2e/0x60
+ip6_ins_rt+0x49/0x50
+~~~~~~~~
+__ip6_rt_update_pmtu.part.54+0x145/0x250
+ip6_rt_update_pmtu+0x2e/0x40
+~~~~~~~~
+ip_tunnel_xmit+0x1f1/0xf40
+__gre_xmit+0x7a/0x90
+ipgre_xmit+0x15a/0x220
+dev_hard_start_xmit+0x2bd/0x480
+__dev_queue_xmit+0x696/0x730
+dev_queue_xmit+0x10/0x20
+neigh_direct_output+0x11/0x20
+ip6_finish_output2+0x21f/0x770
+ip6_finish_output+0xa7/0x1d0
+ip6_output+0x56/0x190
+~~~~~~~~
+ndisc_send_skb+0x1d9/0x400
+ndisc_send_rs+0x88/0xc0
+~~~~~~~~
+
+The rt passed to ip6_rt_update_pmtu() is created by
+icmp6_dst_alloc() and it is not managed by the fib6 tree,
+so its rt6i_table == NULL.  When __ip6_rt_update_pmtu() creates
+a RTF_CACHE clone, the newly created clone also has rt6i_table == NULL
+and it causes the ip6_ins_rt() oops.
+
+During pmtu update, we only want to create a RTF_CACHE clone
+from a rt which is currently managed (or owned) by the
+fib6 tree.  It means either rt->rt6i_node != NULL or
+rt is a RTF_PCPU clone.
+
+It is worth to note that rt6i_table may not be NULL even it is
+not (yet) managed by the fib6 tree (e.g. addrconf_dst_alloc()).
+Hence, rt6i_node is a better check instead of rt6i_table.
+
+Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu")
+Signed-off-by: Martin KaFai Lau <kafai@fb.com>
+Reported-by: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
+Cc: Chris Siebenmann <cks-rhbugzilla@cs.toronto.edu>
+Cc: Hannes Frederic Sowa <hannes@stressinduktion.org>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+---
+ net/ipv6/route.c | 8 +++++++-
+ 1 file changed, 7 insertions(+), 1 deletion(-)
+
+diff --git a/net/ipv6/route.c b/net/ipv6/route.c
+index c8bc9b4..74907c5 100644
+--- a/net/ipv6/route.c
++++ b/net/ipv6/route.c
+@@ -1322,6 +1322,12 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
+ 	rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+ }
+
++static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
++{
++	return !(rt->rt6i_flags & RTF_CACHE) &&
++		(rt->rt6i_flags & RTF_PCPU || rt->rt6i_node);
++}
++
+ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
+ 				 const struct ipv6hdr *iph, u32 mtu)
+ {
+@@ -1335,7 +1341,7 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
+ 	if (mtu >= dst_mtu(dst))
+ 		return;
+
+-	if (rt6->rt6i_flags & RTF_CACHE) {
++	if (!rt6_cache_allowed_for_pmtu(rt6)) {
+ 		rt6_do_update_pmtu(rt6, mtu);
+ 	} else {
+ 		const struct in6_addr *daddr, *saddr;
+-- 
+2.5.0
+