[PATCH net-next v5 03/14] net: move promiscuity handling into netdev_rx_mode_work

[Stanislav Fomichev <sdf@fomichev.me>]

Move unicast promiscuity tracking into netdev_rx_mode_work so it runs
under netdev_ops_lock instead of under the addr_lock spinlock. This
is required because __dev_set_promiscuity calls dev_change_rx_flags
and __dev_notify_flags, both of which may need to sleep.

Change ASSERT_RTNL() to netdev_ops_assert_locked() in
__dev_set_promiscuity, netif_set_allmulti and __dev_change_flags
since these are now called from the work queue under the ops lock.

Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
---
 Documentation/networking/netdevices.rst |  4 ++
 net/core/dev.c                          | 16 ++---
 net/core/dev_addr_lists.c               | 82 ++++++++++++++++++-------
 3 files changed, 68 insertions(+), 34 deletions(-)

diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index 8a488c21fd7c..390537323457 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -299,6 +299,10 @@ struct net_device synchronization rules
 	Notes: Async version of ndo_set_rx_mode which runs in process
 	context. Receives snapshots of the unicast and multicast address lists.
 
+ndo_change_rx_flags:
+	Synchronization: rtnl_lock() semaphore. In addition, netdev instance
+	lock if the driver implements queue management or shaper API.
+
 ndo_setup_tc:
 	``TC_SETUP_BLOCK`` and ``TC_SETUP_FT`` are running under NFT locks
 	(i.e. no ``rtnl_lock`` and no device instance lock). The rest of
diff --git a/net/core/dev.c b/net/core/dev.c
index b9f9e6a30963..ae1fd30d1ef9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9581,7 +9581,7 @@ int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
 	kuid_t uid;
 	kgid_t gid;
 
-	ASSERT_RTNL();
+	netdev_ops_assert_locked(dev);
 
 	promiscuity = dev->promiscuity + inc;
 	if (promiscuity == 0) {
@@ -9617,16 +9617,8 @@ 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;
 }
 
@@ -9648,7 +9640,7 @@ 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) {
@@ -9716,7 +9708,7 @@ 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.
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index a05db3ac43ea..61589537b2d3 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -1204,10 +1204,34 @@ static void netif_addr_lists_reconcile(struct net_device *dev,
 	__hw_addr_list_reconcile(&dev->mc, mc_snap, mc_ref, dev->addr_len);
 }
 
+/**
+ * netif_uc_promisc_update() - evaluate whether uc_promisc should be toggled.
+ * @dev: device
+ *
+ * Must be called under netif_addr_lock_bh.
+ * Return: +1 to enter promisc, -1 to leave, 0 for no change.
+ */
+static int netif_uc_promisc_update(struct net_device *dev)
+{
+	if (dev->priv_flags & IFF_UNICAST_FLT)
+		return 0;
+
+	if (!netdev_uc_empty(dev) && !dev->uc_promisc) {
+		dev->uc_promisc = true;
+		return 1;
+	}
+	if (netdev_uc_empty(dev) && dev->uc_promisc) {
+		dev->uc_promisc = false;
+		return -1;
+	}
+	return 0;
+}
+
 static void netif_rx_mode_run(struct net_device *dev)
 {
 	struct netdev_hw_addr_list uc_snap, mc_snap, uc_ref, mc_ref;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int promisc_inc;
 	int err;
 
 	might_sleep();
@@ -1221,22 +1245,39 @@ static void netif_rx_mode_run(struct net_device *dev)
 	if (!(dev->flags & IFF_UP) || !netif_device_present(dev))
 		return;
 
-	netif_addr_lock_bh(dev);
-	err = netif_addr_lists_snapshot(dev, &uc_snap, &mc_snap,
-					&uc_ref, &mc_ref);
-	if (err) {
-		netdev_WARN(dev, "failed to sync uc/mc addresses\n");
+	if (ops->ndo_set_rx_mode_async) {
+		netif_addr_lock_bh(dev);
+		err = netif_addr_lists_snapshot(dev, &uc_snap, &mc_snap,
+						&uc_ref, &mc_ref);
+		if (err) {
+			netdev_WARN(dev, "failed to sync uc/mc addresses\n");
+			netif_addr_unlock_bh(dev);
+			return;
+		}
+
+		promisc_inc = netif_uc_promisc_update(dev);
+		netif_addr_unlock_bh(dev);
+	} else {
+		netif_addr_lock_bh(dev);
+		promisc_inc = netif_uc_promisc_update(dev);
 		netif_addr_unlock_bh(dev);
-		return;
 	}
-	netif_addr_unlock_bh(dev);
 
-	ops->ndo_set_rx_mode_async(dev, &uc_snap, &mc_snap);
+	if (promisc_inc)
+		__dev_set_promiscuity(dev, promisc_inc, false);
 
-	netif_addr_lock_bh(dev);
-	netif_addr_lists_reconcile(dev, &uc_snap, &mc_snap,
-				   &uc_ref, &mc_ref);
-	netif_addr_unlock_bh(dev);
+	if (ops->ndo_set_rx_mode_async) {
+		ops->ndo_set_rx_mode_async(dev, &uc_snap, &mc_snap);
+
+		netif_addr_lock_bh(dev);
+		netif_addr_lists_reconcile(dev, &uc_snap, &mc_snap,
+					   &uc_ref, &mc_ref);
+		netif_addr_unlock_bh(dev);
+	} else if (ops->ndo_set_rx_mode) {
+		netif_addr_lock_bh(dev);
+		ops->ndo_set_rx_mode(dev);
+		netif_addr_unlock_bh(dev);
+	}
 }
 
 static void netdev_rx_mode_work(struct work_struct *work)
@@ -1287,6 +1328,7 @@ static void netif_rx_mode_queue(struct net_device *dev)
 void __dev_set_rx_mode(struct net_device *dev)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int promisc_inc;
 
 	/* dev_open will call this function so the list will stay sane. */
 	if (!(dev->flags & IFF_UP))
@@ -1295,20 +1337,16 @@ void __dev_set_rx_mode(struct net_device *dev)
 	if (!netif_device_present(dev))
 		return;
 
-	if (ops->ndo_set_rx_mode_async) {
+	if (ops->ndo_set_rx_mode_async || ops->ndo_change_rx_flags) {
 		netif_rx_mode_queue(dev);
 		return;
 	}
 
-	if (!(dev->priv_flags & IFF_UNICAST_FLT)) {
-		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;
-		}
-	}
+	/* Legacy path for non-ops-locked HW devices. */
+
+	promisc_inc = netif_uc_promisc_update(dev);
+	if (promisc_inc)
+		__dev_set_promiscuity(dev, promisc_inc, false);
 
 	if (ops->ndo_set_rx_mode)
 		ops->ndo_set_rx_mode(dev);
-- 
2.53.0