Merge branch 'net-sleepable-ndo_set_rx_mode'

Stanislav Fomichev says:

====================
net: sleepable ndo_set_rx_mode

This series adds a new ndo_set_rx_mode_async callback that enables
drivers to handle address list updates in a sleepable context. The
current ndo_set_rx_mode is called under the netif_addr_lock spinlock
with BHs disabled, which prevents drivers from sleeping. This is
problematic for ops-locked drivers that need to sleep.

The approach:
1. Add snapshot/reconcile infrastructure for address lists
2. Introduce dev_rx_mode_work that takes snapshots under the lock,
   drops the lock, calls the driver, then reconciles changes back
3. Move promiscuity handling into the scheduled work as well
4. Convert existing ops-locked drivers to ndo_set_rx_mode_async
5. Add a warning for ops-locked drivers still using ndo_set_rx_mode
6. Add a selftest exercising the team+bridge+macvlan topology that
   triggers the addr_lock -> ops_lock ordering issue
====================

Link: https://patch.msgid.link/20260416185712.2155425-1-sdf@fomichev.me
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 28 insertions, 0 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7969fcdd5ac4..97b435da5771 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1119,6 +1119,16 @@ struct netdev_net_notifier {
  *	This function is called device changes address list filtering.
  *	If driver handles unicast address filtering, it should set
  *	IFF_UNICAST_FLT in its priv_flags.
+ *	Cannot sleep, called with netif_addr_lock_bh held.
+ *	Deprecated in favor of ndo_set_rx_mode_async.
+ *
+ * void (*ndo_set_rx_mode_async)(struct net_device *dev,
+ *				 struct netdev_hw_addr_list *uc,
+ *				 struct netdev_hw_addr_list *mc);
+ *	Async version of ndo_set_rx_mode which runs in process context
+ *	with rtnl_lock and netdev_lock_ops(dev) held. The uc/mc parameters
+ *	are snapshots of the address lists - iterate with
+ *	netdev_hw_addr_list_for_each(ha, uc).
  *
  * int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
  *	This function  is called when the Media Access Control address
@@ -1439,6 +1449,10 @@ struct net_device_ops {
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
 	void			(*ndo_set_rx_mode)(struct net_device *dev);
+	void			(*ndo_set_rx_mode_async)(
+					struct net_device *dev,
+					struct netdev_hw_addr_list *uc,
+					struct netdev_hw_addr_list *mc);
 	int			(*ndo_set_mac_address)(struct net_device *dev,
 						       void *addr);
 	int			(*ndo_validate_addr)(struct net_device *dev);
@@ -1903,6 +1917,9 @@ enum netdev_reg_state {
  *				has been enabled due to the need to listen to
  *				additional unicast addresses in a device that
  *				does not implement ndo_set_rx_mode()
+ *	@rx_mode_node:		List entry for rx_mode work processing
+ *	@rx_mode_tracker:	Refcount tracker for rx_mode work
+ *	@rx_mode_addr_cache:	Recycled snapshot entries for rx_mode work
  *	@uc:			unicast mac addresses
  *	@mc:			multicast mac addresses
  *	@dev_addrs:		list of device hw addresses
@@ -2294,6 +2311,9 @@ struct net_device {
 	unsigned int		promiscuity;
 	unsigned int		allmulti;
 	bool			uc_promisc;
+	struct list_head	rx_mode_node;
+	netdevice_tracker	rx_mode_tracker;
+	struct netdev_hw_addr_list	rx_mode_addr_cache;
 #ifdef CONFIG_LOCKDEP
 	unsigned char		nested_level;
 #endif
@@ -5004,6 +5024,14 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
 			  int (*unsync)(struct net_device *,
 					const unsigned char *));
 void __hw_addr_init(struct netdev_hw_addr_list *list);
+void __hw_addr_flush(struct netdev_hw_addr_list *list);
+int __hw_addr_list_snapshot(struct netdev_hw_addr_list *snap,
+			    const struct netdev_hw_addr_list *list,
+			    int addr_len, struct netdev_hw_addr_list *cache);
+void __hw_addr_list_reconcile(struct netdev_hw_addr_list *real_list,
+			      struct netdev_hw_addr_list *work,
+			      struct netdev_hw_addr_list *ref, int addr_len,
+			      struct netdev_hw_addr_list *cache);
 
 /* Functions used for device addresses handling */
 void dev_addr_mod(struct net_device *dev, unsigned int offset,