ipv6: route: purge exception on removal

[ Upstream commit f5b51fe804ec2a6edce0f8f6b11ea57283f5857b ]

When a netdevice is unregistered, we flush the relevant exception
via rt6_sync_down_dev() -> fib6_ifdown() -> fib6_del() -> fib6_del_route().

Finally, we end-up calling rt6_remove_exception(), where we release
the relevant dst, while we keep the references to the related fib6_info and
dev. Such references should be released later when the dst will be
destroyed.

There are a number of caches that can keep the exception around for an
unlimited amount of time - namely dst_cache, possibly even socket cache.
As a result device registration may hang, as demonstrated by this script:

ip netns add cl
ip netns add rt
ip netns add srv
ip netns exec rt sysctl -w net.ipv6.conf.all.forwarding=1

ip link add name cl_veth type veth peer name cl_rt_veth
ip link set dev cl_veth netns cl
ip -n cl link set dev cl_veth up
ip -n cl addr add dev cl_veth 2001::2/64
ip -n cl route add default via 2001::1

ip -n cl link add tunv6 type ip6tnl mode ip6ip6 local 2001::2 remote 2002::1 hoplimit 64 dev cl_veth
ip -n cl link set tunv6 up
ip -n cl addr add 2013::2/64 dev tunv6

ip link set dev cl_rt_veth netns rt
ip -n rt link set dev cl_rt_veth up
ip -n rt addr add dev cl_rt_veth 2001::1/64

ip link add name rt_srv_veth type veth peer name srv_veth
ip link set dev srv_veth netns srv
ip -n srv link set dev srv_veth up
ip -n srv addr add dev srv_veth 2002::1/64
ip -n srv route add default via 2002::2

ip -n srv link add tunv6 type ip6tnl mode ip6ip6 local 2002::1 remote 2001::2 hoplimit 64 dev srv_veth
ip -n srv link set tunv6 up
ip -n srv addr add 2013::1/64 dev tunv6

ip link set dev rt_srv_veth netns rt
ip -n rt link set dev rt_srv_veth up
ip -n rt addr add dev rt_srv_veth 2002::2/64

ip netns exec srv netserver & sleep 0.1
ip netns exec cl ping6 -c 4 2013::1
ip netns exec cl netperf -H 2013::1 -t TCP_STREAM -l 3 & sleep 1
ip -n rt link set dev rt_srv_veth mtu 1400
wait %2

ip -n cl link del cl_veth

This commit addresses the issue purging all the references held by the
exception at time, as we currently do for e.g. ipv6 pcpu dst entries.

v1 -> v2:
 - re-order the code to avoid accessing dst and net after dst_dev_put()

Fixes: 93531c67 ("net/ipv6: separate handling of FIB entries from dst based routes")
Signed-off-by: NPaolo Abeni <pabeni@redhat.com>
Reviewed-by: NDavid Ahern <dsahern@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

net/ipv6/route.c

@@ -1282,18 +1282,29 @@ static DEFINE_SPINLOCK(rt6_exception_lock);
 static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
 				 struct rt6_exception *rt6_ex)
 {
+	struct fib6_info *from;
 	struct net *net;
 
 	if (!bucket || !rt6_ex)
 		return;
 
 	net = dev_net(rt6_ex->rt6i->dst.dev);
+	net->ipv6.rt6_stats->fib_rt_cache--;
+
+	/* purge completely the exception to allow releasing the held resources:
+	 * some [sk] cache may keep the dst around for unlimited time
+	 */
+	from = rcu_dereference_protected(rt6_ex->rt6i->from,
+					 lockdep_is_held(&rt6_exception_lock));
+	rcu_assign_pointer(rt6_ex->rt6i->from, NULL);
+	fib6_info_release(from);
+	dst_dev_put(&rt6_ex->rt6i->dst);
+
 	hlist_del_rcu(&rt6_ex->hlist);
 	dst_release(&rt6_ex->rt6i->dst);
 	kfree_rcu(rt6_ex, rcu);
 	WARN_ON_ONCE(!bucket->depth);
 	bucket->depth--;
-	net->ipv6.rt6_stats->fib_rt_cache--;
 }
 
 /* Remove oldest rt6_ex in bucket and free the memory