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, 14 insertions, 53 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index e59f6025067c..d426c1beeb76 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9593,14 +9593,14 @@ static void dev_change_rx_flags(struct net_device *dev, int flags)
 		ops->ndo_change_rx_flags(dev, flags);
 }
 
-static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
+int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
 {
 	unsigned int old_flags = dev->flags;
 	unsigned int promiscuity, flags;
 	kuid_t uid;
 	kgid_t gid;
 
-	ASSERT_RTNL();
+	netdev_ops_assert_locked(dev);
 
 	promiscuity = dev->promiscuity + inc;
 	if (promiscuity == 0) {
@@ -9636,16 +9636,8 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
 
 		dev_change_rx_flags(dev, IFF_PROMISC);
 	}
-	if (notify) {
-		/* The ops lock is only required to ensure consistent locking
-		 * for `NETDEV_CHANGE` notifiers. This function is sometimes
-		 * called without the lock, even for devices that are ops
-		 * locked, such as in `dev_uc_sync_multiple` when using
-		 * bonding or teaming.
-		 */
-		netdev_ops_assert_locked(dev);
+	if (notify)
 		__dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL);
-	}
 	return 0;
 }
 
@@ -9667,7 +9659,7 @@ int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
 	unsigned int old_flags = dev->flags, old_gflags = dev->gflags;
 	unsigned int allmulti, flags;
 
-	ASSERT_RTNL();
+	netdev_ops_assert_locked(dev);
 
 	allmulti = dev->allmulti + inc;
 	if (allmulti == 0) {
@@ -9697,46 +9689,6 @@ int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
 	return 0;
 }
 
-/*
- *	Upload unicast and multicast address lists to device and
- *	configure RX filtering. When the device doesn't support unicast
- *	filtering it is put in promiscuous mode while unicast addresses
- *	are present.
- */
-void __dev_set_rx_mode(struct net_device *dev)
-{
-	const struct net_device_ops *ops = dev->netdev_ops;
-
-	/* dev_open will call this function so the list will stay sane. */
-	if (!(dev->flags&IFF_UP))
-		return;
-
-	if (!netif_device_present(dev))
-		return;
-
-	if (!(dev->priv_flags & IFF_UNICAST_FLT)) {
-		/* Unicast addresses changes may only happen under the rtnl,
-		 * therefore calling __dev_set_promiscuity here is safe.
-		 */
-		if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
-			__dev_set_promiscuity(dev, 1, false);
-			dev->uc_promisc = true;
-		} else if (netdev_uc_empty(dev) && dev->uc_promisc) {
-			__dev_set_promiscuity(dev, -1, false);
-			dev->uc_promisc = false;
-		}
-	}
-
-	if (ops->ndo_set_rx_mode)
-		ops->ndo_set_rx_mode(dev);
-}
-
-void dev_set_rx_mode(struct net_device *dev)
-{
-	netif_addr_lock_bh(dev);
-	__dev_set_rx_mode(dev);
-	netif_addr_unlock_bh(dev);
-}
 
 /**
  * netif_get_flags() - get flags reported to userspace
@@ -9775,7 +9727,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags,
 	unsigned int old_flags = dev->flags;
 	int ret;
 
-	ASSERT_RTNL();
+	netdev_ops_assert_locked(dev);
 
 	/*
 	 *	Set the flags on our device.
@@ -11408,6 +11360,11 @@ int register_netdevice(struct net_device *dev)
 		goto err_uninit;
 	}
 
+	if (netdev_need_ops_lock(dev) &&
+	    dev->netdev_ops->ndo_set_rx_mode &&
+	    !dev->netdev_ops->ndo_set_rx_mode_async)
+		netdev_WARN(dev, "ops-locked drivers should use ndo_set_rx_mode_async\n");
+
 	ret = netdev_do_alloc_pcpu_stats(dev);
 	if (ret)
 		goto err_uninit;
@@ -12127,6 +12084,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 #endif
 
 	mutex_init(&dev->lock);
+	INIT_LIST_HEAD(&dev->rx_mode_node);
+	__hw_addr_init(&dev->rx_mode_addr_cache);
 
 	dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM;
 	setup(dev);
@@ -12231,6 +12190,8 @@ void free_netdev(struct net_device *dev)
 
 	kfree(rcu_dereference_protected(dev->ingress_queue, 1));
 
+	__hw_addr_flush(&dev->rx_mode_addr_cache);
+
 	/* Flush device addresses */
 	dev_addr_flush(dev);