xfrm: reuse uncached_list to track xdsts

In early time, when freeing a xdst, it would be inserted into
dst_garbage.list first. Then if it's refcnt was still held
somewhere, later it would be put into dst_busy_list in
dst_gc_task().

When one dev was being unregistered, the dev of these dsts in
dst_busy_list would be set with loopback_dev and put this dev.
So that this dev's removal wouldn't get blocked, and avoid the
kmsg warning:

  kernel:unregister_netdevice: waiting for veth0 to become \
  free. Usage count = 2

However after Commit 52df157f17e5 ("xfrm: take refcnt of dst
when creating struct xfrm_dst bundle"), the xdst will not be
freed with dst gc, and this warning happens.

To fix it, we need to find these xdsts that are still held by
others when removing the dev, and free xdst's dev and set it
with loopback_dev.

But unfortunately after flow_cache for xfrm was deleted, no
list tracks them anymore. So we need to save these xdsts
somewhere to release the xdst's dev later.

To make this easier, this patch is to reuse uncached_list to
track xdsts, so that the dev refcnt can be released in the
event NETDEV_UNREGISTER process of fib_netdev_notifier.

Thanks to Florian, we could move forward this fix quickly.

Fixes: 52df157f17e5 ("xfrm: take refcnt of dst when creating struct xfrm_dst bundle")
Reported-by: Jianlin Shi <jishi@redhat.com>
Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Tested-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

2 files changed, 7 insertions, 2 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fb2d251c0500..38b75e9d6eae 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -128,7 +128,7 @@ struct uncached_list {
 
 static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt6_uncached_list);
 
-static void rt6_uncached_list_add(struct rt6_info *rt)
+void rt6_uncached_list_add(struct rt6_info *rt)
 {
 	struct uncached_list *ul = raw_cpu_ptr(&rt6_uncached_list);
 
@@ -139,7 +139,7 @@ static void rt6_uncached_list_add(struct rt6_info *rt)
 	spin_unlock_bh(&ul->lock);
 }
 
-static void rt6_uncached_list_del(struct rt6_info *rt)
+void rt6_uncached_list_del(struct rt6_info *rt)
 {
 	if (!list_empty(&rt->rt6i_uncached)) {
 		struct uncached_list *ul = rt->rt6i_uncached_list;
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 09fb44ee3b45..416fe67271a9 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -113,6 +113,9 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 	xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
 	xdst->u.rt6.rt6i_dst = rt->rt6i_dst;
 	xdst->u.rt6.rt6i_src = rt->rt6i_src;
+	INIT_LIST_HEAD(&xdst->u.rt6.rt6i_uncached);
+	rt6_uncached_list_add(&xdst->u.rt6);
+	atomic_inc(&dev_net(dev)->ipv6.rt6_stats->fib_rt_uncache);
 
 	return 0;
 }
@@ -244,6 +247,8 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
 	if (likely(xdst->u.rt6.rt6i_idev))
 		in6_dev_put(xdst->u.rt6.rt6i_idev);
 	dst_destroy_metrics_generic(dst);
+	if (xdst->u.rt6.rt6i_uncached_list)
+		rt6_uncached_list_del(&xdst->u.rt6);
 	xfrm_dst_destroy(xdst);
 }