The CI is hitting some aperiodic hangup at device removal time in the
pmtu.sh self-test:
unregister_netdevice: waiting for veth_A-R1 to become free. Usage count = 6
ref_tracker: veth_A-R1@ffff888013df15d8 has 1/5 users at
dst_init+0x84/0x4a0
dst_alloc+0x97/0x150
ip6_dst_alloc+0x23/0x90
ip6_rt_pcpu_alloc+0x1e6/0x520
ip6_pol_route+0x56f/0x840
fib6_rule_lookup+0x334/0x630
ip6_route_output_flags+0x259/0x480
ip6_dst_lookup_tail.constprop.0+0x5c2/0x940
ip6_dst_lookup_flow+0x88/0x190
udp_tunnel6_dst_lookup+0x2a7/0x4c0
vxlan_xmit_one+0xbde/0x4a50 [vxlan]
vxlan_xmit+0x9ad/0xf20 [vxlan]
dev_hard_start_xmit+0x10e/0x360
__dev_queue_xmit+0xf95/0x18c0
arp_solicit+0x4a2/0xe00
neigh_probe+0xaa/0xf0
While the first suspect is the dst_cache, explicitly tracking the dst
owing the last device reference via probes proved such dst is held by
the nexthop in the originating fib6_info.
Similar to commit f5b51fe804ec ("ipv6: route: purge exception on
removal"), we need to explicitly release the originating fib info when
disconnecting a to-be-removed device from a live ipv6 dst: move the
fib6_info cleanup into ip6_dst_ifdown().
Tested running:
./pmtu.sh cleanup_ipv6_exception
in a tight loop for more than 400 iterations with no spat, running an
unpatched kernel I observed a splat every ~10 iterations.
Fixes: f88d8ea67fbd ("ipv6: Plumb support for nexthop object in a fib6_info")
Signed-off-by: Paolo Abeni <pabeni@xxxxxxxxxx>
---
v1 -> v2:
- dropped unintended whitespace change
---
net/ipv6/route.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d7ce5cf2017a..038c1eeef0be 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -374,6 +374,7 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
{
struct rt6_info *rt = dst_rt6_info(dst);
struct inet6_dev *idev = rt->rt6i_idev;
+ struct fib6_info *from;
if (idev && idev->dev != blackhole_netdev) {
struct inet6_dev *blackhole_idev = in6_dev_get(blackhole_netdev);
@@ -383,6 +384,8 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev)
in6_dev_put(idev);
}
}
+ from = unrcu_pointer(xchg(&rt->from, NULL));
+ fib6_info_release(from);
}
static bool __rt6_check_expired(const struct rt6_info *rt)
@@ -1455,7 +1458,6 @@ 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)
@@ -1467,8 +1469,6 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
/* purge completely the exception to allow releasing the held resources:
* some [sk] cache may keep the dst around for unlimited time
*/
- from = unrcu_pointer(xchg(&rt6_ex->rt6i->from, NULL));
- fib6_info_release(from);
dst_dev_put(&rt6_ex->rt6i->dst);
hlist_del_rcu(&rt6_ex->hlist);
--
2.45.2
