ipvlan: Support per-netns netdev unregistration.

When a lower device is unregistered, its upper ipvlan devices
must also be unregistered.  However, these upper devices may
reside in different netns than the lower device.

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

The new dying flag in struct ipvl_dev is used to avoid a race
that ipvlan_link_delete() is called while its lower device is
being removed in ipvlan_device_event().

If dying is true in ipvlan_link_delete(), the ipvlan device is
already destructed but not yet unregistered.  In this case,
unregistration will be done in __rtnl_net_unlock() of the
->dellink() caller.

Tested:

1. Create veth in ns1 and two ipvlan devices in ns2 and ns3.

  # ip netns add ns1
  # ip netns add ns2
  # ip netns add ns3
  # ip -n ns1 link add veth0 type veth peer veth1
  # ip -n ns2 link add ipvl2 link veth0 link-netns ns1 type ipvlan mode l2
  # ip -n ns3 link add ipvl3 link veth0 link-netns ns1 type ipvlan mode l2

2. Run bpftrace to check that veth is unregistered first but
   wait ipvlan to be unregistered

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

3. Remove the lower veth0 in ns1.

  # ip -n ns1 link del veth0

We can see that veth0 is freed after unregistering ipvl2 and ipvl3
in per-netns work because ipvl_port holds refcount of veth0.

  PID: 2010 | DEV: veth0
          veth_dellink+5
          rtnl_dellink+1213
          rtnetlink_rcv_msg+1791
  ...
  PID: 440 | DEV: ipvl2
          ipvlan_uninit+5
          unregister_netdevice_many_notify+7129
          unregister_netdevice_many_net+1050
          rtnl_net_work_func+136
          process_scheduled_works+2538
  ...
  PID: 440 | DEV: ipvl2
          free_netdev+5
          netdev_run_todo+4798
          process_scheduled_works+2538
  ...
  PID: 440 | DEV: ipvl3
          ipvlan_uninit+5
          unregister_netdevice_many_notify+7129
          unregister_netdevice_many_net+1050
          rtnl_net_work_func+136
          process_scheduled_works+2538
  ...
  PID: 2010 | DEV: veth0
          free_netdev+5
          netdev_run_todo+4798
          rtnl_dellink+1507
          rtnetlink_rcv_msg+1791
  ...
  PID: 440 | DEV: ipvl3
          free_netdev+5
          netdev_run_todo+4798
          process_scheduled_works+2538
  ...

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260703001009.1572444-15-kuniyu@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 23 insertions, 13 deletions

diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 9d3835c14e5e..8d05ad480438 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -69,6 +69,7 @@ struct ipvl_dev {
 	DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
 	netdev_features_t	sfeatures;
 	u32			msg_enable;
+	bool			dying;
 };
 
 struct ipvl_addr {
@@ -169,7 +170,8 @@ void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
 		     unsigned int len, bool success, bool mcast);
 int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 		    struct netlink_ext_ack *extack);
-void __ipvlan_link_delete(struct net_device *dev, struct list_head *head);
+void __ipvlan_link_delete(struct net *net, struct net_device *dev,
+			  struct list_head *head);
 void ipvlan_link_setup(struct net_device *dev);
 int ipvlan_link_register(struct rtnl_link_ops *ops);
 #ifdef CONFIG_IPVLAN_L3S
@@ -209,7 +211,7 @@ static inline bool netif_is_ipvlan_port(const struct net_device *dev)
 }
 
 #if IS_ENABLED(CONFIG_IPVTAP)
-extern void (*__ipvtap_dellink_ptr)(struct net_device *dev,
+extern void (*__ipvtap_dellink_ptr)(struct net *net, struct net_device *dev,
 				    struct list_head *head);
 #endif
 
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 6d7479a8a9c6..ee46a55f73d1 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -8,7 +8,7 @@
 #include "ipvlan.h"
 
 #if IS_ENABLED(CONFIG_IPVTAP)
-void (*__ipvtap_dellink_ptr)(struct net_device *dev,
+void (*__ipvtap_dellink_ptr)(struct net *net, struct net_device *dev,
 			     struct list_head *head);
 EXPORT_SYMBOL(__ipvtap_dellink_ptr);
 #endif
@@ -706,7 +706,8 @@ unregister_netdev:
 }
 EXPORT_SYMBOL_GPL(ipvlan_link_new);
 
-void __ipvlan_link_delete(struct net_device *dev, struct list_head *head)
+void __ipvlan_link_delete(struct net *net, struct net_device *dev,
+			  struct list_head *head)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_addr *addr, *next;
@@ -721,7 +722,7 @@ void __ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 
 	ida_free(&ipvlan->port->ida, dev->dev_id);
 	list_del_rcu(&ipvlan->pnode);
-	unregister_netdevice_queue(dev, head);
+	unregister_netdevice_queue_net(net, dev, head);
 	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
 }
 EXPORT_SYMBOL(__ipvlan_link_delete);
@@ -731,7 +732,8 @@ static void ipvlan_link_delete(struct net_device *dev, struct list_head *head)
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
 	mutex_lock(&ipvlan->port->pnodes_lock);
-	__ipvlan_link_delete(dev, head);
+	if (!ipvlan->dying)
+		__ipvlan_link_delete(dev_net(dev), dev, head);
 	mutex_unlock(&ipvlan->port->pnodes_lock);
 }
 
@@ -827,22 +829,26 @@ static int ipvlan_device_event(struct notifier_block *unused,
 			ipvlan_migrate_l3s_hook(oldnet, newnet);
 		break;
 	}
-	case NETDEV_UNREGISTER:
+	case NETDEV_UNREGISTER: {
+		struct net *net = dev_net(dev);
+
 		if (dev->reg_state != NETREG_UNREGISTERING)
 			break;
 
 		list_for_each_entry_safe(ipvlan, next, &port->ipvlans, pnode) {
+			ipvlan->dying = true;
+
 #if IS_ENABLED(CONFIG_IPVTAP)
 			if (ipvlan->dev->rtnl_link_ops != &ipvlan_link_ops)
-				__ipvtap_dellink_ptr(ipvlan->dev, &lst_kill);
+				__ipvtap_dellink_ptr(net, ipvlan->dev, &lst_kill);
 			else
 #endif
-				__ipvlan_link_delete(ipvlan->dev, &lst_kill);
+				__ipvlan_link_delete(net, ipvlan->dev, &lst_kill);
 		}
 
 		unregister_netdevice_many(&lst_kill);
 		break;
-
+	}
 	case NETDEV_FEAT_CHANGE:
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
 			netif_inherit_tso_max(ipvlan->dev, dev);
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 99eaa29057b4..66c949d94261 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -109,13 +109,14 @@ static int ipvtap_newlink(struct net_device *dev,
 	return err;
 }
 
-static void __ipvtap_dellink(struct net_device *dev, struct list_head *head)
+static void __ipvtap_dellink(struct net *net, struct net_device *dev,
+			     struct list_head *head)
 {
 	struct ipvtap_dev *vlantap = netdev_priv(dev);
 
 	netdev_rx_handler_unregister(dev);
 	tap_del_queues(&vlantap->tap);
-	__ipvlan_link_delete(dev, head);
+	__ipvlan_link_delete(net, dev, head);
 }
 
 static void ipvtap_dellink(struct net_device *dev,
@@ -125,7 +126,8 @@ static void ipvtap_dellink(struct net_device *dev,
 	struct ipvl_port *port = vlantap->vlan.port;
 
 	mutex_lock(&port->pnodes_lock);
-	__ipvtap_dellink(dev, head);
+	if (!vlantap->vlan.dying)
+		__ipvtap_dellink(dev_net(dev), dev, head);
 	mutex_unlock(&port->pnodes_lock);
 }