[PATCH v2 net-next 08/14] veth: Support per-netns device unregistration.

[Kuniyuki Iwashima <kuniyu@google.com>]

Currently, veth_dellink() unregisters both local and peer devices
synchronously under RTNL.

Once RTNL is removed, it can be called concurrently from different
netns.

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

This way, each device is queued for destruction only once by
the winner of the race.

Note that the extra netdev_hold() ensures that @peer obtained by
the first xchg() is not freed during the subsequent access to
netdev_priv(peer).  The 2nd xchg() overwrites @dev to balance
the refcount.

Tested:

1. Create two veth pairs (veth1-2, veth3-4) between two netns
   (ns1 & ns2).

  # ip netns add ns1
  # ip netns add ns2
  # ip -n ns1 link add veth1 type veth peer veth2 netns ns2
  # ip -n ns1 link add veth3 type veth peer veth4 netns ns2

2. Run bpftrace to check if the same process does NOT
   unregister the paired veth devices

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

3. Remove veth2 in ns2 and check bpftrace output

  # ip -n ns2 link del veth2

  PID: 2194 | DEV: veth2
          free_netdev+5
          netdev_run_todo+4798
          rtnl_dellink+1507
          rtnetlink_rcv_msg+1791
  ...
  PID: 448 | DEV: veth1
          free_netdev+5
          netdev_run_todo+4798
          process_scheduled_works+2538
  ...

4. Remove ns2 (thus veth4) and check bpftrace output

  # ip netns del ns2

  PID: 571 | DEV: veth4
          free_netdev+5
          netdev_run_todo+4798
          default_device_exit_batch+2271
          ops_undo_list+993
          cleanup_net+1122
          process_scheduled_works+2538
  ...
  PID: 441 | DEV: veth3
          free_netdev+5
          netdev_run_todo+4798
          process_scheduled_works+2538
  ...

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 drivers/net/veth.c | 34 +++++++++++++++++++++-------------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 1c5142149175..8170bf33ccf9 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -77,6 +77,7 @@ struct veth_priv {
 	struct bpf_prog		*_xdp_prog;
 	struct veth_rq		*rq;
 	unsigned int		requested_headroom;
+	netdevice_tracker	peer_tracker;
 };
 
 struct veth_xdp_tx_bq {
@@ -1901,15 +1902,17 @@ static int veth_newlink(struct net_device *dev,
 
 	priv = netdev_priv(dev);
 	rcu_assign_pointer(priv->peer, peer);
+	netdev_hold(peer, &priv->peer_tracker, GFP_KERNEL);
 	err = veth_init_queues(dev, tb);
 	if (err)
 		goto err_queues;
 
 	priv = netdev_priv(peer);
 	rcu_assign_pointer(priv->peer, dev);
+	netdev_hold(dev, &priv->peer_tracker, GFP_KERNEL);
 	err = veth_init_queues(peer, tb);
 	if (err)
-		goto err_queues;
+		goto err_peer_queues;
 
 	veth_disable_gro(dev);
 	/* update XDP supported features */
@@ -1918,7 +1921,11 @@ static int veth_newlink(struct net_device *dev,
 
 	return 0;
 
+err_peer_queues:
+	netdev_put(dev, &priv->peer_tracker);
+	priv = netdev_priv(dev);
 err_queues:
+	netdev_put(peer, &priv->peer_tracker);
 	unregister_netdevice(dev);
 err_register_dev:
 	/* nothing to do */
@@ -1933,24 +1940,25 @@ static int veth_newlink(struct net_device *dev,
 
 static void veth_dellink(struct net_device *dev, struct list_head *head)
 {
-	struct veth_priv *priv;
+	netdevice_tracker *peer_tracker;
 	struct net_device *peer;
+	struct veth_priv *priv;
 
 	priv = netdev_priv(dev);
-	peer = rtnl_dereference(priv->peer);
+	peer_tracker = &priv->peer_tracker;
+	peer = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (!peer)
+		return;
 
-	/* Note : dellink() is called from default_device_exit_batch(),
-	 * before a rcu_synchronize() point. The devices are guaranteed
-	 * not being freed before one RCU grace period.
-	 */
-	RCU_INIT_POINTER(priv->peer, NULL);
 	unregister_netdevice_queue(dev, head);
 
-	if (peer) {
-		priv = netdev_priv(peer);
-		RCU_INIT_POINTER(priv->peer, NULL);
-		unregister_netdevice_queue(peer, head);
-	}
+	priv = netdev_priv(peer);
+	dev = unrcu_pointer(xchg(&priv->peer, NULL));
+	if (dev)
+		unregister_netdevice_queue_net(dev_net(dev), peer, head);
+
+	netdev_put(peer, peer_tracker);
+	netdev_put(dev, &priv->peer_tracker);
 }
 
 static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = {
-- 
2.55.0.rc0.799.gd6f94ed593-goog