net: make netdev_lock() protect netdev->reg_state

Protect writes to netdev->reg_state with netdev_lock().
From now on holding netdev_lock() is sufficient to prevent
the net_device from getting unregistered, so code which
wants to hold just a single netdev around no longer needs
to hold rtnl_lock.

We do not protect the NETREG_UNREGISTERED -> NETREG_RELEASED
transition. We'd need to move mutex_destroy(netdev->lock)
to .release, but the real reason is that trying to stop
the unregistration process mid-way would be unsafe / crazy.
Taking references on such devices is not safe, either.
So the intended semantics are to lock REGISTERED devices.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250115035319.559603-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/netdevice.h

@@ -2448,7 +2448,7 @@ struct net_device {
 	 * Should always be taken using netdev_lock() / netdev_unlock() helpers.
 	 * Drivers are free to use it for other protection.
 	 *
-	 * Protects: @net_shaper_hierarchy.
+	 * Protects: @reg_state, @net_shaper_hierarchy.
 	 * Ordering: take after rtnl_lock.
 	 */
 	struct mutex		lock;

net/core/dev.c

@@ -10695,7 +10695,9 @@ int register_netdevice(struct net_device *dev)
 
 	ret = netdev_register_kobject(dev);
 
+	netdev_lock(dev);
 	WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED);
+	netdev_unlock(dev);
 
 	if (ret)
 		goto err_uninit_notify;
@@ -10969,7 +10971,9 @@ void netdev_run_todo(void)
 			continue;
 		}
 
+		netdev_lock(dev);
 		WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED);
+		netdev_unlock(dev);
 		linkwatch_sync_dev(dev);
 	}
 
@@ -11575,7 +11579,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
 	list_for_each_entry(dev, head, unreg_list) {
 		/* And unlink it from device chain. */
 		unlist_netdevice(dev);
+		netdev_lock(dev);
 		WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING);
+		netdev_unlock(dev);
 	}
 	flush_all_backlogs();