[PATCH v1] vxcan: Support per-netns device unregistration.

[Kuniyuki Iwashima <kuniyu@google.com>]

Currently, vxcan_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 vxcan pairs (vxcan1-2, vxcan3-4) between two netns
   (ns1 & ns2).

  # ip netns add ns1
  # ip netns add ns2
  # ip -n ns1 link add vxcan1 type vxcan peer vxcan2 netns ns2
  # ip -n ns1 link add vxcan3 type vxcan peer vxcan4 netns ns2

2. Run bpftrace to check if the same process does NOT
   unregister the paired vxcan 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 vxcan2 in ns2 and check bpftrace output

  # ip -n ns2 link del vxcan2

  PID: 1524 | DEV: vxcan2
          free_netdev+5
          netdev_run_todo+4798
          rtnl_dellink+1507
          rtnetlink_rcv_msg+1791
          netlink_rcv_skb+504
  ...
  PID: 453 | DEV: vxcan1
          free_netdev+5
          netdev_run_todo+4798
          process_scheduled_works+2538
          worker_thread+1906
          kthread+806
          ret_from_fork+805
          ret_from_fork_asm+17

4. Remove ns2 (thus vxcan4) and check bpftrace output

  # ip netns del ns2

  PID: 12 | DEV: vxcan4
          free_netdev+5
          netdev_run_todo+4798
          default_device_exit_batch+2271
          ops_undo_list+993
          cleanup_net+1122
          process_scheduled_works+2538
          worker_thread+1906
          kthread+806
          ret_from_fork+805
          ret_from_fork_asm+17
  ...
  PID: 462 | DEV: vxcan3
          free_netdev+5
          netdev_run_todo+4798
          process_scheduled_works+2538
          worker_thread+1906
          kthread+806
          ret_from_fork+805
          ret_from_fork_asm+17

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
This mirros commit d7fda2c776b2 ("veth: Support per-netns device
unregistration.").

The patch is based on net-next.git because it seems both main/master
of linux-can.git and linux-can-next.git are not synced with net-next.
71ac90cca6d8 is needed to verify the test output.
---
 drivers/net/can/vxcan.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index e882250180ef..b7efed1226d8 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -33,6 +33,7 @@ MODULE_ALIAS_RTNL_LINK(DRV_NAME);
 
 struct vxcan_priv {
 	struct net_device __rcu	*peer;
+	netdevice_tracker	peer_tracker;
 };
 
 static netdev_tx_t vxcan_xmit(struct sk_buff *oskb, struct net_device *dev)
@@ -268,9 +269,11 @@ static int vxcan_newlink(struct net_device *dev,
 	/* cross link the device pair */
 	priv = netdev_priv(dev);
 	rcu_assign_pointer(priv->peer, peer);
+	netdev_hold(peer, &priv->peer_tracker, GFP_KERNEL);
 
 	priv = netdev_priv(peer);
 	rcu_assign_pointer(priv->peer, dev);
+	netdev_hold(dev, &priv->peer_tracker, GFP_KERNEL);
 
 	return 0;
 
@@ -281,24 +284,25 @@ static int vxcan_newlink(struct net_device *dev,
 
 static void vxcan_dellink(struct net_device *dev, struct list_head *head)
 {
+	netdevice_tracker *peer_tracker;
 	struct vxcan_priv *priv;
 	struct net_device *peer;
 
 	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 vxcan_policy[VXCAN_INFO_MAX + 1] = {
-- 
2.55.0.795.g602f6c329a-goog