net: Call unregister_netdevice_many() per netns.

For per-netns device unregistration, the list passed to
unregister_netdevice_many() must contain devices from a single
netns only (once all callers are converted).

Let's move collected devices in the following functions to
net->dev_unreg_head and let __rtnl_net_unlock() pass them to
unregister_netdevice_many().

  * default_device_exit_batch()
  * ops_exit_rtnl_list()
  * __rtnl_kill_links()

This allows incremental conversion of each driver to support
per-netns device unregistration without affecting the normal
kernel where CONFIG_DEBUG_NET_SMALL_RTNL is disabled.

Note that this change unbatches synchronize_rcu() etc in
unregister_netdevice_many(), but we can later split it into
multiple stages to batch them again.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260703001009.1572444-8-kuniyu@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

4 files changed, 39 insertions, 1 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 108d8d7ea75b..8db25b79573e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3481,6 +3481,7 @@ static inline void unregister_netdevice(struct net_device *dev)
 void unregister_netdevice_queue_net(struct net *net, struct net_device *dev,
 				    struct list_head *head);
 void unregister_netdevice_many_net(struct net *net);
+void unregister_netdevice_queue_many_net(struct net *net, struct list_head *head);
 #else
 static inline void unregister_netdevice_queue_net(struct net *net,
 						  struct net_device *dev,
@@ -3488,6 +3489,11 @@ static inline void unregister_netdevice_queue_net(struct net *net,
 {
 	unregister_netdevice_queue(dev, head);
 }
+
+static inline void unregister_netdevice_queue_many_net(struct net *net,
+						       struct list_head *head)
+{
+}
 #endif
 
 int netdev_refcnt_read(const struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 7ec9af75d143..7c21bc0a1e34 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -12557,6 +12557,28 @@ void unregister_netdevice_queue_net(struct net *net, struct net_device *dev,
 }
 EXPORT_SYMBOL(unregister_netdevice_queue_net);
 
+void unregister_netdevice_queue_many_net(struct net *net, struct list_head *head)
+{
+	struct net_device *dev, *tmp;
+
+	spin_lock(&net->dev_unreg_lock);
+	list_for_each_entry_safe(dev, tmp, head, unreg_list) {
+		/* Once all cross-netns unregister_netdevice_queue() is
+		 * converted to _net() (or for debugging), remove this check.
+		 */
+		if (!net_eq(dev_net(dev), net))
+			continue;
+
+		DEBUG_NET_WARN_ONCE(!net_eq(dev_net(dev), net),
+				    "%s was unregistered from a different netns.\n",
+				    dev->name);
+
+		list_del_init(&dev->unreg_list);
+		list_move_tail(&dev->unreg_list_net, &net->dev_unreg_head);
+	}
+	spin_unlock(&net->dev_unreg_lock);
+}
+
 static void unregister_netdevice_move_net(struct net *net_old,
 					  struct net *net,
 					  struct net_device *dev)
@@ -13190,12 +13212,17 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list)
 	__rtnl_net_unlock(&init_net);
 
 	list_for_each_entry(net, net_list, exit_list) {
+		__rtnl_net_lock(net);
+
 		for_each_netdev_reverse(net, dev) {
 			if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink)
 				dev->rtnl_link_ops->dellink(dev, &dev_kill_list);
 			else
 				unregister_netdevice_queue(dev, &dev_kill_list);
 		}
+
+		unregister_netdevice_queue_many_net(net, &dev_kill_list);
+		__rtnl_net_unlock(net);
 	}
 	unregister_netdevice_many(&dev_kill_list);
 	rtnl_unlock();
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 578b48cf5318..a91d2b58aadd 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -181,6 +181,7 @@ static void ops_exit_rtnl_list(const struct list_head *ops_list,
 				ops->exit_rtnl(net, &dev_kill_list);
 		}
 
+		unregister_netdevice_queue_many_net(net, &dev_kill_list);
 		__rtnl_net_unlock(net);
 	}
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index cf2b7697a6e7..31c65a545a10 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -714,8 +714,12 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops)
 	down_write(&pernet_ops_rwsem);
 	rtnl_lock_unregistering_all();
 
-	for_each_net(net)
+	for_each_net(net) {
+		__rtnl_net_lock(net);
 		__rtnl_kill_links(net, ops, &dev_kill_list);
+		unregister_netdevice_queue_many_net(net, &dev_kill_list);
+		__rtnl_net_unlock(net);
+	}
 
 	unregister_netdevice_many(&dev_kill_list);