bareudp: Support per-netns netdev unregistration.

bareudp_exit_rtnl_net() iterates bareudp devices whose sockets
are in the dying netns and queues them for destruction.

So the devices may reside in different netns.

Let's use unregister_netdevice_queue_net() to support per-netns
device unregistration.

list_del() is changed to list_del_init() to avoid queueing the
same device twice.

Even after bareudp_exit_rtnl_net() queues a cross-netns bareudp
device, bareudp_dellink() could be called concurrently for it
(once RTNL is removed).  In such a case, __rtnl_net_unlock() will
perform the unregistration.

Note that bareudp uses register_pernet_subsys() instead of _device(),
so default_device_exit_batch() guarantees that the async per-netns
works are flushed before ->exit().

Tested:

1. Create bareudp device across two netns.

  # ip netns add ns1
  # ip netns add ns2
  # ip -n ns1 link add bareudp0 link-netns ns2 type bareudp \
    dstport 9292 ethertype ipv4

2. Run bpftrace to check that bareudp_uninit() is called between
   ->exit_rtnl() and ->exit().

  # bpftrace -e '#include <linux/netdevice.h>
  kprobe:bareudp_uninit {
      $dev = (struct net_device *)arg0;
      printf("PID: %d | DEV: %s%s\n", pid, $dev->name, kstack());
  }
  kprobe:bareudp_exit_rtnl_net,
  kprobe:bareudp_exit_net {
      printf("PID: %d%s\n", pid, kstack());
  }'

3. Remove the netns where the bareudp socket resides

  # ip netns del ns2

Now, we can see bareudp0 is unregistered by per-netns work
instead of cleanup_net() and it finishes before ->exit() to
avoid WARN_ON_ONCE(!list_empty(&bn->bareudp_list)) there.

  PID: 576
          bareudp_exit_rtnl_net+5
          ops_undo_list+702
          cleanup_net+1122
          process_scheduled_works+2538
  ...
  PID: 470 | DEV: bareudp0
          bareudp_uninit+5
          unregister_netdevice_many_notify+7129
          unregister_netdevice_many_net+1050
          rtnl_net_work_func+136
          process_scheduled_works+2538
  ...
  PID: 576
          bareudp_exit_net+5
          ops_undo_list+1064
          cleanup_net+1122
          process_scheduled_works+2538

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260703001009.1572444-11-kuniyu@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 15 insertions, 5 deletions

diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 7dedf4867e7b..c3b5ed52d877 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -701,12 +701,13 @@ static int bareudp_link_config(struct net_device *dev,
 	return 0;
 }
 
-static void __bareudp_dellink(struct net_device *dev, struct list_head *head)
+static void __bareudp_dellink(struct net *net, struct net_device *dev,
+			      struct list_head *head)
 {
 	struct bareudp_dev *bareudp = netdev_priv(dev);
 
-	list_del(&bareudp->next);
-	unregister_netdevice_queue(dev, head);
+	list_del_init(&bareudp->next);
+	unregister_netdevice_queue_net(net, dev, head);
 }
 
 static void bareudp_dellink(struct net_device *dev, struct list_head *head)
@@ -717,7 +718,8 @@ static void bareudp_dellink(struct net_device *dev, struct list_head *head)
 	bn = net_generic(bareudp->net, bareudp_net_id);
 
 	mutex_lock(&bn->lock);
-	__bareudp_dellink(dev, head);
+	if (!list_empty(&bareudp->next))
+		__bareudp_dellink(dev_net(dev), dev, head);
 	mutex_unlock(&bn->lock);
 }
 
@@ -811,14 +813,22 @@ static void __net_exit bareudp_exit_rtnl_net(struct net *net,
 	mutex_lock(&bn->lock);
 
 	list_for_each_entry_safe(bareudp, next, &bn->bareudp_list, next)
-		__bareudp_dellink(bareudp->dev, dev_kill_list);
+		__bareudp_dellink(net, bareudp->dev, dev_kill_list);
 
 	mutex_unlock(&bn->lock);
 }
 
+static void __net_exit bareudp_exit_net(struct net *net)
+{
+	struct bareudp_net *bn = net_generic(net, bareudp_net_id);
+
+	WARN_ON_ONCE(!list_empty(&bn->bareudp_list));
+}
+
 static struct pernet_operations bareudp_net_ops = {
 	.init = bareudp_init_net,
 	.exit_rtnl = bareudp_exit_rtnl_net,
+	.exit = bareudp_exit_net,
 	.id   = &bareudp_net_id,
 	.size = sizeof(struct bareudp_net),
 };