Merge branch 'mlxsw-Make-driver-more-robust'

Ido Schimmel says:

====================
mlxsw: Make driver more robust

In recent months we fixed several bugs in the driver that could have
been avoided by re-evaluating some of the involved code paths and by
introducing relevant and comprehensive test cases.

This patchset tries to do that by introducing a set of small and mostly
non-functional changes in addition to a new test. I have further
improvements in mind, but they can be done in a different set.

Patch #1 makes sure we correctly sanitize upper devices of a VLAN
interface.

Patch #2 removes an unexpected behavior from the driver, in which routes
configured on a VLAN interface will cease being offloaded after certain
operations.

Patch #3 is a small cleanup.

Patch #4 simplifies the driver by removing reference counting from VLAN
entries configured on a port.

Patches #5-#6 simplify linking/unlinking from a bridge, especially when
LAG and VLAN devices are involved. They make both operations symmetric
even when ports are unlinked from a bridged LAG device.

Patch #7-#9 make router interface (RIF) deletion more robust by removing
reliance on device chain to indicate whether a NETDEV_DOWN event in the
inet{,6}addr notification chains should be processed. This is due to the
fact that IP addresses can be flushed from a netdev after it was
unlinked from its lower device.

Patch #10 adds a new test to for valid and invalid configurations over
mlxsw ports. Some of the test cases are derived from recent fixes. I
expect that more test cases will be added over time.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -1141,16 +1141,20 @@ static void mlxsw_sp_port_vlan_flush(struct mlxsw_sp_port *mlxsw_sp_port)
 
 	list_for_each_entry_safe(mlxsw_sp_port_vlan, tmp,
 				 &mlxsw_sp_port->vlans_list, list)
-		mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+		mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 }
 
-static struct mlxsw_sp_port_vlan *
+struct mlxsw_sp_port_vlan *
 mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 {
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	bool untagged = vid == 1;
 	int err;
 
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
+	if (mlxsw_sp_port_vlan)
+		return ERR_PTR(-EEXIST);
+
 	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, true, untagged);
 	if (err)
 		return ERR_PTR(err);
@@ -1162,7 +1166,6 @@ mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 	}
 
 	mlxsw_sp_port_vlan->mlxsw_sp_port = mlxsw_sp_port;
-	mlxsw_sp_port_vlan->ref_count = 1;
 	mlxsw_sp_port_vlan->vid = vid;
 	list_add(&mlxsw_sp_port_vlan->list, &mlxsw_sp_port->vlans_list);
 
@@ -1173,44 +1176,19 @@ mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
 	return ERR_PTR(err);
 }
 
-static void
-mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
+void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
-	list_del(&mlxsw_sp_port_vlan->list);
-	kfree(mlxsw_sp_port_vlan);
-	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
-}
-
-struct mlxsw_sp_port_vlan *
-mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid)
-{
-	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
-
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
-	if (mlxsw_sp_port_vlan) {
-		mlxsw_sp_port_vlan->ref_count++;
-		return mlxsw_sp_port_vlan;
-	}
-
-	return mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid);
-}
-
-void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
-{
-	struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid;
-
-	if (--mlxsw_sp_port_vlan->ref_count != 0)
-		return;
-
 	if (mlxsw_sp_port_vlan->bridge_port)
 		mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
-	else if (fid)
+	else if (mlxsw_sp_port_vlan->fid)
 		mlxsw_sp_port_vlan_router_leave(mlxsw_sp_port_vlan);
 
-	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+	list_del(&mlxsw_sp_port_vlan->list);
+	kfree(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
 }
 
 static int mlxsw_sp_port_add_vid(struct net_device *dev,
@@ -1224,7 +1202,7 @@ static int mlxsw_sp_port_add_vid(struct net_device *dev,
 	if (!vid)
 		return 0;
 
-	return PTR_ERR_OR_ZERO(mlxsw_sp_port_vlan_get(mlxsw_sp_port, vid));
+	return PTR_ERR_OR_ZERO(mlxsw_sp_port_vlan_create(mlxsw_sp_port, vid));
 }
 
 static int mlxsw_sp_port_kill_vid(struct net_device *dev,
@@ -1242,7 +1220,7 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
 	if (!mlxsw_sp_port_vlan)
 		return 0;
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 
 	return 0;
 }
@@ -3198,12 +3176,12 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_nve_init;
 	}
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
 	if (IS_ERR(mlxsw_sp_port_vlan)) {
 		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to create VID 1\n",
 			mlxsw_sp_port->local_port);
 		err = PTR_ERR(mlxsw_sp_port_vlan);
-		goto err_port_vlan_get;
+		goto err_port_vlan_create;
 	}
 
 	mlxsw_sp_port_switchdev_init(mlxsw_sp_port);
@@ -3224,8 +3202,8 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 err_register_netdev:
 	mlxsw_sp->ports[local_port] = NULL;
 	mlxsw_sp_port_switchdev_fini(mlxsw_sp_port);
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
-err_port_vlan_get:
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
+err_port_vlan_create:
 	mlxsw_sp_port_nve_fini(mlxsw_sp_port);
 err_port_nve_init:
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
@@ -4520,6 +4498,25 @@ void mlxsw_sp_port_dev_put(struct mlxsw_sp_port *mlxsw_sp_port)
 	dev_put(mlxsw_sp_port->dev);
 }
 
+static void
+mlxsw_sp_port_lag_uppers_cleanup(struct mlxsw_sp_port *mlxsw_sp_port,
+				 struct net_device *lag_dev)
+{
+	struct net_device *br_dev = netdev_master_upper_dev_get(lag_dev);
+	struct net_device *upper_dev;
+	struct list_head *iter;
+
+	if (netif_is_bridge_port(lag_dev))
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, lag_dev, br_dev);
+
+	netdev_for_each_upper_dev_rcu(lag_dev, upper_dev, iter) {
+		if (!netif_is_bridge_port(upper_dev))
+			continue;
+		br_dev = netdev_master_upper_dev_get(upper_dev);
+		mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev, br_dev);
+	}
+}
+
 static int mlxsw_sp_lag_create(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
 {
 	char sldr_pl[MLXSW_REG_SLDR_LEN];
@@ -4712,6 +4709,10 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 
 	/* Any VLANs configured on the port are no longer valid */
 	mlxsw_sp_port_vlan_flush(mlxsw_sp_port);
+	/* Make the LAG and its directly linked uppers leave bridges they
+	 * are memeber in
+	 */
+	mlxsw_sp_port_lag_uppers_cleanup(mlxsw_sp_port, lag_dev);
 
 	if (lag->ref_count == 1)
 		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
@@ -4721,7 +4722,7 @@ static void mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port->lagged = 0;
 	lag->ref_count--;
 
-	mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
 	/* Make sure untagged frames are allowed to ingress */
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
 }
@@ -5000,6 +5001,16 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 		} else if (netif_is_macvlan(upper_dev)) {
 			if (!info->linking)
 				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+		} else if (is_vlan_dev(upper_dev)) {
+			struct net_device *br_dev;
+
+			if (!netif_is_bridge_port(upper_dev))
+				break;
+			if (info->linking)
+				break;
+			br_dev = netdev_master_upper_dev_get(upper_dev);
+			mlxsw_sp_port_bridge_leave(mlxsw_sp_port, upper_dev,
+						   br_dev);
 		}
 		break;
 	}
@@ -5156,6 +5167,48 @@ static int mlxsw_sp_netdevice_lag_port_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static int mlxsw_sp_netdevice_bridge_vlan_event(struct net_device *vlan_dev,
+						struct net_device *br_dev,
+						unsigned long event, void *ptr,
+						u16 vid)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(vlan_dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+	struct net_device *upper_dev;
+
+	if (!mlxsw_sp)
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (!netif_is_macvlan(upper_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+			return -EOPNOTSUPP;
+		}
+		if (!info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case NETDEV_CHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev))
+			mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
+		break;
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 					 unsigned long event, void *ptr)
 {
@@ -5169,6 +5222,9 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 		return mlxsw_sp_netdevice_lag_port_vlan_event(vlan_dev,
 							      real_dev, event,
 							      ptr, vid);
+	else if (netif_is_bridge_master(real_dev))
+		return mlxsw_sp_netdevice_bridge_vlan_event(vlan_dev, real_dev,
+							    event, ptr, vid);
 
 	return 0;
 }
@@ -5358,18 +5414,10 @@ static struct notifier_block mlxsw_sp_inetaddr_valid_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inetaddr_valid_event,
 };
 
-static struct notifier_block mlxsw_sp_inetaddr_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_inetaddr_event,
-};
-
 static struct notifier_block mlxsw_sp_inet6addr_valid_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inet6addr_valid_event,
 };
 
-static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = {
-	.notifier_call = mlxsw_sp_inet6addr_event,
-};
-
 static const struct pci_device_id mlxsw_sp1_pci_id_table[] = {
 	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0},
 	{0, },
@@ -5395,9 +5443,7 @@ static int __init mlxsw_sp_module_init(void)
 	int err;
 
 	register_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
-	register_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 
 	err = mlxsw_core_driver_register(&mlxsw_sp1_driver);
 	if (err)
@@ -5424,9 +5470,7 @@ static int __init mlxsw_sp_module_init(void)
 err_sp2_core_driver_register:
 	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
 err_sp1_core_driver_register:
-	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 	return err;
 }
@@ -5437,9 +5481,7 @@ static void __exit mlxsw_sp_module_exit(void)
 	mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
 	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
 	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
-	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
-	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
 	unregister_inetaddr_validator_notifier(&mlxsw_sp_inetaddr_valid_nb);
 }
 

drivers/net/ethernet/mellanox/mlxsw/spectrum.h

@@ -190,7 +190,6 @@ struct mlxsw_sp_port_vlan {
 	struct list_head list;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct mlxsw_sp_fid *fid;
-	unsigned int ref_count;
 	u16 vid;
 	struct mlxsw_sp_bridge_port *bridge_port;
 	struct list_head bridge_vlan_node;
@@ -410,8 +409,8 @@ int mlxsw_sp_port_vid_learning_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid,
 				   bool learn_enable);
 int mlxsw_sp_port_pvid_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 struct mlxsw_sp_port_vlan *
-mlxsw_sp_port_vlan_get(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
-void mlxsw_sp_port_vlan_put(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
+mlxsw_sp_port_vlan_create(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
+void mlxsw_sp_port_vlan_destroy(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 int mlxsw_sp_port_vlan_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid_begin,
 			   u16 vid_end, bool is_member, bool untagged);
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
@@ -459,12 +458,8 @@ int mlxsw_sp_netdevice_router_port_event(struct net_device *dev,
 					 unsigned long event, void *ptr);
 void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 			      const struct net_device *macvlan_dev);
-int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
-			    unsigned long event, void *ptr);
 int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 				  unsigned long event, void *ptr);
-int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
-			     unsigned long event, void *ptr);
 int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 				   unsigned long event, void *ptr);
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
@@ -484,7 +479,6 @@ mlxsw_sp_netdevice_ipip_ul_event(struct mlxsw_sp *mlxsw_sp,
 				 struct netdev_notifier_info *info);
 void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
-void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
 				 struct net_device *dev);
 struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
@@ -785,10 +779,10 @@ int mlxsw_sp_fid_port_vid_map(struct mlxsw_sp_fid *fid,
 			      struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
 void mlxsw_sp_fid_port_vid_unmap(struct mlxsw_sp_fid *fid,
 				 struct mlxsw_sp_port *mlxsw_sp_port, u16 vid);
-enum mlxsw_sp_rif_type mlxsw_sp_fid_rif_type(const struct mlxsw_sp_fid *fid);
 u16 mlxsw_sp_fid_index(const struct mlxsw_sp_fid *fid);
 enum mlxsw_sp_fid_type mlxsw_sp_fid_type(const struct mlxsw_sp_fid *fid);
 void mlxsw_sp_fid_rif_set(struct mlxsw_sp_fid *fid, struct mlxsw_sp_rif *rif);
+struct mlxsw_sp_rif *mlxsw_sp_fid_rif(const struct mlxsw_sp_fid *fid);
 enum mlxsw_sp_rif_type
 mlxsw_sp_fid_type_rif_type(const struct mlxsw_sp *mlxsw_sp,
 			   enum mlxsw_sp_fid_type type);

drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c

@@ -349,11 +349,6 @@ void mlxsw_sp_fid_port_vid_unmap(struct mlxsw_sp_fid *fid,
 	fid->fid_family->ops->port_vid_unmap(fid, mlxsw_sp_port, vid);
 }
 
-enum mlxsw_sp_rif_type mlxsw_sp_fid_rif_type(const struct mlxsw_sp_fid *fid)
-{
-	return fid->fid_family->rif_type;
-}
-
 u16 mlxsw_sp_fid_index(const struct mlxsw_sp_fid *fid)
 {
 	return fid->fid_index;
@@ -369,6 +364,11 @@ void mlxsw_sp_fid_rif_set(struct mlxsw_sp_fid *fid, struct mlxsw_sp_rif *rif)
 	fid->rif = rif;
 }
 
+struct mlxsw_sp_rif *mlxsw_sp_fid_rif(const struct mlxsw_sp_fid *fid)
+{
+	return fid->rif;
+}
+
 enum mlxsw_sp_rif_type
 mlxsw_sp_fid_type_rif_type(const struct mlxsw_sp *mlxsw_sp,
 			   enum mlxsw_sp_fid_type type)
@@ -1083,12 +1083,9 @@ void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid)
 	struct mlxsw_sp_fid_family *fid_family = fid->fid_family;
 	struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp;
 
-	if (--fid->ref_count == 1 && fid->rif) {
-		/* Destroy the associated RIF and let it drop the last
-		 * reference on the FID.
-		 */
-		return mlxsw_sp_rif_destroy(fid->rif);
-	} else if (fid->ref_count == 0) {
+	if (--fid->ref_count != 0)
+		return;
+
 	list_del(&fid->list);
 	rhashtable_remove_fast(&mlxsw_sp->fid_core->fid_ht,
 			       &fid->ht_node, mlxsw_sp_fid_ht_params);
@@ -1096,7 +1093,6 @@ void mlxsw_sp_fid_put(struct mlxsw_sp_fid *fid)
 	__clear_bit(fid->fid_index - fid_family->start_index,
 		    fid_family->fids_bitmap);
 	kfree(fid);
-	}
 }
 
 struct mlxsw_sp_fid *mlxsw_sp_fid_8021q_get(struct mlxsw_sp *mlxsw_sp, u16 vid)

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c

@@ -15,6 +15,7 @@
 #include <linux/gcd.h>
 #include <linux/random.h>
 #include <linux/if_macvlan.h>
+#include <linux/refcount.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
@@ -70,6 +71,8 @@ struct mlxsw_sp_router {
 	bool aborted;
 	struct notifier_block fib_nb;
 	struct notifier_block netevent_nb;
+	struct notifier_block inetaddr_nb;
+	struct notifier_block inet6addr_nb;
 	const struct mlxsw_sp_rif_ops **rif_ops_arr;
 	const struct mlxsw_sp_ipip_ops **ipip_ops_arr;
 };
@@ -104,6 +107,7 @@ struct mlxsw_sp_rif_params {
 
 struct mlxsw_sp_rif_subport {
 	struct mlxsw_sp_rif common;
+	refcount_t ref_count;
 	union {
 		u16 system_port;
 		u16 lag_id;
@@ -136,6 +140,7 @@ struct mlxsw_sp_rif_ops {
 	void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
 };
 
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
 static void mlxsw_sp_lpm_tree_put(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_lpm_tree *lpm_tree);
@@ -6297,6 +6302,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		err = -ENOMEM;
 		goto err_rif_alloc;
 	}
+	dev_hold(rif->dev);
 	rif->mlxsw_sp = mlxsw_sp;
 	rif->ops = ops;
 
@@ -6335,6 +6341,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	if (fid)
 		mlxsw_sp_fid_put(fid);
 err_fid_get:
+	dev_put(rif->dev);
 	kfree(rif);
 err_rif_alloc:
 err_rif_index_alloc:
@@ -6343,7 +6350,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	return ERR_PTR(err);
 }
 
-void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
+static void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 {
 	const struct mlxsw_sp_rif_ops *ops = rif->ops;
 	struct mlxsw_sp *mlxsw_sp = rif->mlxsw_sp;
@@ -6362,6 +6369,7 @@ void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif)
 	if (fid)
 		/* Loopback RIFs are not associated with a FID. */
 		mlxsw_sp_fid_put(fid);
+	dev_put(rif->dev);
 	kfree(rif);
 	vr->rif_count--;
 	mlxsw_sp_vr_put(mlxsw_sp, vr);
@@ -6392,6 +6400,40 @@ mlxsw_sp_rif_subport_params_init(struct mlxsw_sp_rif_params *params,
 		params->system_port = mlxsw_sp_port->local_port;
 }
 
+static struct mlxsw_sp_rif_subport *
+mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
+{
+	return container_of(rif, struct mlxsw_sp_rif_subport, common);
+}
+
+static struct mlxsw_sp_rif *
+mlxsw_sp_rif_subport_get(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp_rif_params *params,
+			 struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, params->dev);
+	if (!rif)
+		return mlxsw_sp_rif_create(mlxsw_sp, params, extack);
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_inc(&rif_subport->ref_count);
+	return rif;
+}
+
+static void mlxsw_sp_rif_subport_put(struct mlxsw_sp_rif *rif)
+{
+	struct mlxsw_sp_rif_subport *rif_subport;
+
+	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	if (!refcount_dec_and_test(&rif_subport->ref_count))
+		return;
+
+	mlxsw_sp_rif_destroy(rif);
+}
+
 static int
 mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 			       struct net_device *l3_dev,
@@ -6399,22 +6441,18 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_rif_params params = {
+		.dev = l3_dev,
+	};
 	u16 vid = mlxsw_sp_port_vlan->vid;
 	struct mlxsw_sp_rif *rif;
 	struct mlxsw_sp_fid *fid;
 	int err;
 
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
-	if (!rif) {
-		struct mlxsw_sp_rif_params params = {
-			.dev = l3_dev,
-		};
-
 	mlxsw_sp_rif_subport_params_init(&params, mlxsw_sp_port_vlan);
-		rif = mlxsw_sp_rif_create(mlxsw_sp, &params, extack);
+	rif = mlxsw_sp_rif_subport_get(mlxsw_sp, &params, extack);
 	if (IS_ERR(rif))
 		return PTR_ERR(rif);
-	}
 
 	/* FID was already created, just take a reference */
 	fid = rif->ops->fid_get(rif, extack);
@@ -6441,6 +6479,7 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
 err_fid_port_vid_map:
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 	return err;
 }
 
@@ -6449,6 +6488,7 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = mlxsw_sp_port_vlan->mlxsw_sp_port;
 	struct mlxsw_sp_fid *fid = mlxsw_sp_port_vlan->fid;
+	struct mlxsw_sp_rif *rif = mlxsw_sp_fid_rif(fid);
 	u16 vid = mlxsw_sp_port_vlan->vid;
 
 	if (WARN_ON(mlxsw_sp_fid_type(fid) != MLXSW_SP_FID_TYPE_RFID))
@@ -6458,10 +6498,8 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan)
 	mlxsw_sp_port_vid_stp_set(mlxsw_sp_port, vid, BR_STATE_BLOCKING);
 	mlxsw_sp_port_vid_learning_set(mlxsw_sp_port, vid, true);
 	mlxsw_sp_fid_port_vid_unmap(fid, mlxsw_sp_port, vid);
-	/* If router port holds the last reference on the rFID, then the
-	 * associated Sub-port RIF will be destroyed.
-	 */
 	mlxsw_sp_fid_put(fid);
+	mlxsw_sp_rif_subport_put(rif);
 }
 
 static int mlxsw_sp_inetaddr_port_vlan_event(struct net_device *l3_dev,
@@ -6535,11 +6573,11 @@ static int mlxsw_sp_inetaddr_lag_event(struct net_device *lag_dev,
 					     extack);
 }
 
-static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
+static int mlxsw_sp_inetaddr_bridge_event(struct mlxsw_sp *mlxsw_sp,
+					  struct net_device *l3_dev,
 					  unsigned long event,
 					  struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
 	struct mlxsw_sp_rif_params params = {
 		.dev = l3_dev,
 	};
@@ -6560,7 +6598,8 @@ static int mlxsw_sp_inetaddr_bridge_event(struct net_device *l3_dev,
 	return 0;
 }
 
-static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
+static int mlxsw_sp_inetaddr_vlan_event(struct mlxsw_sp *mlxsw_sp,
+					struct net_device *vlan_dev,
 					unsigned long event,
 					struct netlink_ext_ack *extack)
 {
@@ -6577,7 +6616,8 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 		return __mlxsw_sp_inetaddr_lag_event(vlan_dev, real_dev, event,
 						     vid, extack);
 	else if (netif_is_bridge_master(real_dev) && br_vlan_enabled(real_dev))
-		return mlxsw_sp_inetaddr_bridge_event(vlan_dev, event, extack);
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, vlan_dev, event,
+						      extack);
 
 	return 0;
 }
@@ -6678,16 +6718,11 @@ void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 			    mlxsw_sp_fid_index(rif->fid), false);
 }
 
-static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
+static int mlxsw_sp_inetaddr_macvlan_event(struct mlxsw_sp *mlxsw_sp,
+					   struct net_device *macvlan_dev,
 					   unsigned long event,
 					   struct netlink_ext_ack *extack)
 {
-	struct mlxsw_sp *mlxsw_sp;
-
-	mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
-	if (!mlxsw_sp)
-		return 0;
-
 	switch (event) {
 	case NETDEV_UP:
 		return mlxsw_sp_rif_macvlan_add(mlxsw_sp, macvlan_dev, extack);
@@ -6726,7 +6761,8 @@ static int mlxsw_sp_router_port_check_rif_addr(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
+static int __mlxsw_sp_inetaddr_event(struct mlxsw_sp *mlxsw_sp,
+				     struct net_device *dev,
 				     unsigned long event,
 				     struct netlink_ext_ack *extack)
 {
@@ -6735,21 +6771,24 @@ static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 	else if (netif_is_lag_master(dev))
 		return mlxsw_sp_inetaddr_lag_event(dev, event, extack);
 	else if (netif_is_bridge_master(dev))
-		return mlxsw_sp_inetaddr_bridge_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_bridge_event(mlxsw_sp, dev, event,
+						      extack);
 	else if (is_vlan_dev(dev))
-		return mlxsw_sp_inetaddr_vlan_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_vlan_event(mlxsw_sp, dev, event,
+						    extack);
 	else if (netif_is_macvlan(dev))
-		return mlxsw_sp_inetaddr_macvlan_event(dev, event, extack);
+		return mlxsw_sp_inetaddr_macvlan_event(mlxsw_sp, dev, event,
+						       extack);
 	else
 		return 0;
 }
 
-int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
+static int mlxsw_sp_inetaddr_event(struct notifier_block *nb,
 				   unsigned long event, void *ptr)
 {
 	struct in_ifaddr *ifa = (struct in_ifaddr *) ptr;
 	struct net_device *dev = ifa->ifa_dev->dev;
-	struct mlxsw_sp *mlxsw_sp;
+	struct mlxsw_sp_router *router;
 	struct mlxsw_sp_rif *rif;
 	int err = 0;
 
@@ -6757,15 +6796,12 @@ int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 	if (event == NETDEV_UP)
 		goto out;
 
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
-
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
+	router = container_of(nb, struct mlxsw_sp_router, inetaddr_nb);
+	rif = mlxsw_sp_rif_find_by_dev(router->mlxsw_sp, dev);
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, NULL);
+	err = __mlxsw_sp_inetaddr_event(router->mlxsw_sp, dev, event, NULL);
 out:
 	return notifier_from_errno(err);
 }
@@ -6792,13 +6828,14 @@ int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
 	if (err)
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, ivi->extack);
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, ivi->extack);
 out:
 	return notifier_from_errno(err);
 }
 
 struct mlxsw_sp_inet6addr_event_work {
 	struct work_struct work;
+	struct mlxsw_sp *mlxsw_sp;
 	struct net_device *dev;
 	unsigned long event;
 };
@@ -6807,21 +6844,18 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 {
 	struct mlxsw_sp_inet6addr_event_work *inet6addr_work =
 		container_of(work, struct mlxsw_sp_inet6addr_event_work, work);
+	struct mlxsw_sp *mlxsw_sp = inet6addr_work->mlxsw_sp;
 	struct net_device *dev = inet6addr_work->dev;
 	unsigned long event = inet6addr_work->event;
-	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_sp_rif *rif;
 
 	rtnl_lock();
-	mlxsw_sp = mlxsw_sp_lower_get(dev);
-	if (!mlxsw_sp)
-		goto out;
 
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
 	if (!mlxsw_sp_rif_should_config(rif, dev, event))
 		goto out;
 
-	__mlxsw_sp_inetaddr_event(dev, event, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, NULL);
 out:
 	rtnl_unlock();
 	dev_put(dev);
@@ -6829,25 +6863,25 @@ static void mlxsw_sp_inet6addr_event_work(struct work_struct *work)
 }
 
 /* Called with rcu_read_lock() */
-int mlxsw_sp_inet6addr_event(struct notifier_block *unused,
+static int mlxsw_sp_inet6addr_event(struct notifier_block *nb,
 				    unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *if6 = (struct inet6_ifaddr *) ptr;
 	struct mlxsw_sp_inet6addr_event_work *inet6addr_work;
 	struct net_device *dev = if6->idev->dev;
+	struct mlxsw_sp_router *router;
 
 	/* NETDEV_UP event is handled by mlxsw_sp_inet6addr_valid_event */
 	if (event == NETDEV_UP)
 		return NOTIFY_DONE;
 
-	if (!mlxsw_sp_port_dev_lower_find_rcu(dev))
-		return NOTIFY_DONE;
-
 	inet6addr_work = kzalloc(sizeof(*inet6addr_work), GFP_ATOMIC);
 	if (!inet6addr_work)
 		return NOTIFY_BAD;
 
+	router = container_of(nb, struct mlxsw_sp_router, inet6addr_nb);
 	INIT_WORK(&inet6addr_work->work, mlxsw_sp_inet6addr_event_work);
+	inet6addr_work->mlxsw_sp = router->mlxsw_sp;
 	inet6addr_work->dev = dev;
 	inet6addr_work->event = event;
 	dev_hold(dev);
@@ -6878,7 +6912,7 @@ int mlxsw_sp_inet6addr_valid_event(struct notifier_block *unused,
 	if (err)
 		goto out;
 
-	err = __mlxsw_sp_inetaddr_event(dev, event, i6vi->extack);
+	err = __mlxsw_sp_inetaddr_event(mlxsw_sp, dev, event, i6vi->extack);
 out:
 	return notifier_from_errno(err);
 }
@@ -6997,9 +7031,10 @@ static int mlxsw_sp_port_vrf_join(struct mlxsw_sp *mlxsw_sp,
 	 */
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (rif)
-		__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, extack);
+		__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN,
+					  extack);
 
-	return __mlxsw_sp_inetaddr_event(l3_dev, NETDEV_UP, extack);
+	return __mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_UP, extack);
 }
 
 static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
@@ -7010,7 +7045,7 @@ static void mlxsw_sp_port_vrf_leave(struct mlxsw_sp *mlxsw_sp,
 	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, l3_dev);
 	if (!rif)
 		return;
-	__mlxsw_sp_inetaddr_event(l3_dev, NETDEV_DOWN, NULL);
+	__mlxsw_sp_inetaddr_event(mlxsw_sp, l3_dev, NETDEV_DOWN, NULL);
 }
 
 int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
@@ -7064,18 +7099,13 @@ static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
 					     __mlxsw_sp_rif_macvlan_flush, rif);
 }
 
-static struct mlxsw_sp_rif_subport *
-mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
-{
-	return container_of(rif, struct mlxsw_sp_rif_subport, common);
-}
-
 static void mlxsw_sp_rif_subport_setup(struct mlxsw_sp_rif *rif,
 				       const struct mlxsw_sp_rif_params *params)
 {
 	struct mlxsw_sp_rif_subport *rif_subport;
 
 	rif_subport = mlxsw_sp_rif_subport_rif(rif);
+	refcount_set(&rif_subport->ref_count, 1);
 	rif_subport->vid = params->vid;
 	rif_subport->lag = params->lag;
 	if (params->lag)
@@ -7627,6 +7657,16 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp->router = router;
 	router->mlxsw_sp = mlxsw_sp;
 
+	router->inetaddr_nb.notifier_call = mlxsw_sp_inetaddr_event;
+	err = register_inetaddr_notifier(&router->inetaddr_nb);
+	if (err)
+		goto err_register_inetaddr_notifier;
+
+	router->inet6addr_nb.notifier_call = mlxsw_sp_inet6addr_event;
+	err = register_inet6addr_notifier(&router->inet6addr_nb);
+	if (err)
+		goto err_register_inet6addr_notifier;
+
 	INIT_LIST_HEAD(&mlxsw_sp->router->nexthop_neighs_list);
 	err = __mlxsw_sp_router_init(mlxsw_sp);
 	if (err)
@@ -7712,6 +7752,10 @@ int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 err_rifs_init:
 	__mlxsw_sp_router_fini(mlxsw_sp);
 err_router_init:
+	unregister_inet6addr_notifier(&router->inet6addr_nb);
+err_register_inet6addr_notifier:
+	unregister_inetaddr_notifier(&router->inetaddr_nb);
+err_register_inetaddr_notifier:
 	kfree(mlxsw_sp->router);
 	return err;
 }
@@ -7729,5 +7773,7 @@ void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp)
 	mlxsw_sp_ipips_fini(mlxsw_sp);
 	mlxsw_sp_rifs_fini(mlxsw_sp);
 	__mlxsw_sp_router_fini(mlxsw_sp);
+	unregister_inet6addr_notifier(&mlxsw_sp->router->inet6addr_nb);
+	unregister_inetaddr_notifier(&mlxsw_sp->router->inetaddr_nb);
 	kfree(mlxsw_sp->router);
 }

drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c

@@ -290,30 +290,6 @@ mlxsw_sp_bridge_port_destroy(struct mlxsw_sp_bridge_port *bridge_port)
 	kfree(bridge_port);
 }
 
-static bool
-mlxsw_sp_bridge_port_should_destroy(const struct mlxsw_sp_bridge_port *
-				    bridge_port)
-{
-	struct net_device *dev = bridge_port->dev;
-	struct mlxsw_sp *mlxsw_sp;
-
-	if (is_vlan_dev(dev))
-		mlxsw_sp = mlxsw_sp_lower_get(vlan_dev_real_dev(dev));
-	else
-		mlxsw_sp = mlxsw_sp_lower_get(dev);
-
-	/* In case ports were pulled from out of a bridged LAG, then
-	 * it's possible the reference count isn't zero, yet the bridge
-	 * port should be destroyed, as it's no longer an upper of ours.
-	 */
-	if (!mlxsw_sp && list_empty(&bridge_port->vlans_list))
-		return true;
-	else if (bridge_port->ref_count == 0)
-		return true;
-	else
-		return false;
-}
-
 static struct mlxsw_sp_bridge_port *
 mlxsw_sp_bridge_port_get(struct mlxsw_sp_bridge *bridge,
 			 struct net_device *brport_dev)
@@ -351,8 +327,7 @@ static void mlxsw_sp_bridge_port_put(struct mlxsw_sp_bridge *bridge,
 {
 	struct mlxsw_sp_bridge_device *bridge_device;
 
-	bridge_port->ref_count--;
-	if (!mlxsw_sp_bridge_port_should_destroy(bridge_port))
+	if (--bridge_port->ref_count != 0)
 		return;
 	bridge_device = bridge_port->bridge_device;
 	mlxsw_sp_bridge_port_destroy(bridge_port);
@@ -1021,10 +996,8 @@ mlxsw_sp_port_vlan_bridge_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	int err;
 
 	/* No need to continue if only VLAN flags were changed */
-	if (mlxsw_sp_port_vlan->bridge_port) {
-		mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	if (mlxsw_sp_port_vlan->bridge_port)
 		return 0;
-	}
 
 	err = mlxsw_sp_port_vlan_fid_join(mlxsw_sp_port_vlan, bridge_port,
 					  extack);
@@ -1105,16 +1078,32 @@ static int
 mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			      struct mlxsw_sp_bridge_port *bridge_port,
 			      u16 vid, bool is_untagged, bool is_pvid,
-			      struct netlink_ext_ack *extack)
+			      struct netlink_ext_ack *extack,
+			      struct switchdev_trans *trans)
 {
 	u16 pvid = mlxsw_sp_port_pvid_determine(mlxsw_sp_port, vid, is_pvid);
 	struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan;
 	u16 old_pvid = mlxsw_sp_port->pvid;
 	int err;
 
-	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_get(mlxsw_sp_port, vid);
+	/* The only valid scenario in which a port-vlan already exists, is if
+	 * the VLAN flags were changed and the port-vlan is associated with the
+	 * correct bridge port
+	 */
+	mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_find_by_vid(mlxsw_sp_port, vid);
+	if (mlxsw_sp_port_vlan &&
+	    mlxsw_sp_port_vlan->bridge_port != bridge_port)
+		return -EEXIST;
+
+	if (switchdev_trans_ph_prepare(trans))
+		return 0;
+
+	if (!mlxsw_sp_port_vlan) {
+		mlxsw_sp_port_vlan = mlxsw_sp_port_vlan_create(mlxsw_sp_port,
+							       vid);
 		if (IS_ERR(mlxsw_sp_port_vlan))
 			return PTR_ERR(mlxsw_sp_port_vlan);
+	}
 
 	err = mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, true,
 				     is_untagged);
@@ -1137,7 +1126,7 @@ mlxsw_sp_bridge_port_vlan_add(struct mlxsw_sp_port *mlxsw_sp_port,
 err_port_pvid_set:
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
 err_port_vlan_set:
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 	return err;
 }
 
@@ -1199,9 +1188,6 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 		return err;
 	}
 
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
-
 	bridge_port = mlxsw_sp_bridge_port_find(mlxsw_sp->bridge, orig_dev);
 	if (WARN_ON(!bridge_port))
 		return -EINVAL;
@@ -1214,7 +1200,7 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 
 		err = mlxsw_sp_bridge_port_vlan_add(mlxsw_sp_port, bridge_port,
 						    vid, flag_untagged,
-						    flag_pvid, extack);
+						    flag_pvid, extack, trans);
 		if (err)
 			return err;
 	}
@@ -1832,7 +1818,7 @@ mlxsw_sp_bridge_port_vlan_del(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_port_vlan_bridge_leave(mlxsw_sp_port_vlan);
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, pvid);
 	mlxsw_sp_port_vlan_set(mlxsw_sp_port, vid, vid, false, false);
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 }
 
 static int mlxsw_sp_port_vlans_del(struct mlxsw_sp_port *mlxsw_sp_port,
@@ -2000,7 +1986,7 @@ mlxsw_sp_bridge_8021q_port_join(struct mlxsw_sp_bridge_device *bridge_device,
 		return -EINVAL;
 
 	/* Let VLAN-aware bridge take care of its own VLANs */
-	mlxsw_sp_port_vlan_put(mlxsw_sp_port_vlan);
+	mlxsw_sp_port_vlan_destroy(mlxsw_sp_port_vlan);
 
 	return 0;
 }
@@ -2010,7 +1996,7 @@ mlxsw_sp_bridge_8021q_port_leave(struct mlxsw_sp_bridge_device *bridge_device,
 				 struct mlxsw_sp_bridge_port *bridge_port,
 				 struct mlxsw_sp_port *mlxsw_sp_port)
 {
-	mlxsw_sp_port_vlan_get(mlxsw_sp_port, 1);
+	mlxsw_sp_port_vlan_create(mlxsw_sp_port, 1);
 	/* Make sure untagged frames are allowed to ingress */
 	mlxsw_sp_port_pvid_set(mlxsw_sp_port, 1);
 }

tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh

@@ -13,9 +13,23 @@ ALL_TESTS="
 	rif_set_addr_test
 	rif_inherit_bridge_addr_test
 	rif_non_inherit_bridge_addr_test
+	vlan_interface_deletion_test
+	bridge_deletion_test
+	bridge_vlan_flags_test
+	vlan_1_test
+	lag_bridge_upper_test
+	duplicate_vlans_test
+	vlan_rif_refcount_test
+	subport_rif_refcount_test
+	vlan_dev_deletion_test
+	lag_unlink_slaves_test
+	lag_dev_deletion_test
+	vlan_interface_uppers_test
+	devlink_reload_test
 "
 NUM_NETIFS=2
 source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
 
 setup_prepare()
 {
@@ -160,6 +174,384 @@ rif_non_inherit_bridge_addr_test()
 	ip addr del dev $swp1 192.0.2.1/28
 }
 
+vlan_interface_deletion_test()
+{
+	# Test that when a VLAN interface is deleted, its associated router
+	# interface (RIF) is correctly deleted and not leaked. See commit
+	# c360867ec46a ("mlxsw: spectrum: Delete RIF when VLAN device is
+	# removed") for more details
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	ip link add link br0 name br0.10 type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+	ip link del dev br0.10
+
+	# If we leaked the previous RIF, then this should produce a trace
+	ip link add link br0 name br0.20 type vlan id 20
+	ip -6 address add 2001:db8:1::1/64 dev br0.20
+	ip link del dev br0.20
+
+	log_test "vlan interface deletion"
+
+	ip link del dev br0
+}
+
+bridge_deletion_test()
+{
+	# Test that when a bridge with VLAN interfaces is deleted, we correctly
+	# delete the associated RIFs. See commit 602b74eda813 ("mlxsw:
+	# spectrum_switchdev: Do not leak RIFs when removing bridge") for more
+	# details
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+	ip -6 address add 2001:db8::1/64 dev br0
+
+	ip link add link br0 name br0.10 type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+
+	ip link add link br0 name br0.20 type vlan id 20
+	ip -6 address add 2001:db8:2::1/64 dev br0.20
+
+	ip link del dev br0
+
+	# If we leaked previous RIFs, then this should produce a trace
+	ip -6 address add 2001:db8:1::1/64 dev $swp1
+	ip -6 address del 2001:db8:1::1/64 dev $swp1
+
+	log_test "bridge deletion"
+}
+
+bridge_vlan_flags_test()
+{
+	# Test that when bridge VLAN flags are toggled, we do not take
+	# unnecessary references on related structs. See commit 9e25826ffc94
+	# ("mlxsw: spectrum_switchdev: Fix port_vlan refcounting") for more
+	# details
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	bridge vlan add vid 10 dev $swp1 pvid untagged
+	bridge vlan add vid 10 dev $swp1 untagged
+	bridge vlan add vid 10 dev $swp1 pvid
+	bridge vlan add vid 10 dev $swp1
+	ip link del dev br0
+
+	# If we did not handle references correctly, then this should produce a
+	# trace
+	devlink dev reload "$DEVLINK_DEV"
+
+	# Allow netdevices to be re-created following the reload
+	sleep 20
+
+	log_test "bridge vlan flags"
+}
+
+vlan_1_test()
+{
+	# Test that VLAN 1 cannot be configured, as it is used internally for
+	# untagged traffic. See commit 47bf9df2e820 ("mlxsw: spectrum: Forbid
+	# creation of VLAN 1 over port/LAG") for more details
+	RET=0
+
+	ip link add link $swp1 name $swp1.1 type vlan id 1 &> /dev/null
+	check_fail $? "managed to create vlan 1 when should not"
+
+	log_test "vlan 1"
+}
+
+lag_bridge_upper_test()
+{
+	# Test that ports cannot be enslaved to LAG devices that have uppers
+	# and that failure is handled gracefully. See commit b3529af6bb0d
+	# ("spectrum: Reference count VLAN entries") for more details
+	RET=0
+
+	ip link add name bond1 type bond mode 802.3ad
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev bond1 master br0
+
+	ip link set dev $swp1 down
+	ip link set dev $swp1 master bond1 &> /dev/null
+	check_fail $? "managed to enslave port to lag when should not"
+
+	# This might generate a trace, if we did not handle the failure
+	# correctly
+	ip -6 address add 2001:db8:1::1/64 dev $swp1
+	ip -6 address del 2001:db8:1::1/64 dev $swp1
+
+	log_test "lag with bridge upper"
+
+	ip link del dev br0
+	ip link del dev bond1
+}
+
+duplicate_vlans_test()
+{
+	# Test that on a given port a VLAN is only used once. Either as VLAN
+	# in a VLAN-aware bridge or as a VLAN device
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+	bridge vlan add vid 10 dev $swp1
+
+	ip link add link $swp1 name $swp1.10 type vlan id 10 &> /dev/null
+	check_fail $? "managed to create vlan device when should not"
+
+	bridge vlan del vid 10 dev $swp1
+	ip link add link $swp1 name $swp1.10 type vlan id 10
+	check_err $? "did not manage to create vlan device when should"
+	bridge vlan add vid 10 dev $swp1 &> /dev/null
+	check_fail $? "managed to add bridge vlan when should not"
+
+	log_test "duplicate vlans"
+
+	ip link del dev $swp1.10
+	ip link del dev br0
+}
+
+vlan_rif_refcount_test()
+{
+	# Test that RIFs representing VLAN interfaces are not affected from
+	# ports member in the VLAN. We use the offload indication on routes
+	# configured on the RIF to understand if it was created / destroyed
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	ip link set dev $swp1 up
+	ip link set dev br0 up
+
+	ip link add link br0 name br0.10 up type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_err $? "vlan rif was not created before adding port to vlan"
+
+	bridge vlan add vid 10 dev $swp1
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_err $? "vlan rif was destroyed after adding port to vlan"
+
+	bridge vlan del vid 10 dev $swp1
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_err $? "vlan rif was destroyed after removing port from vlan"
+
+	ip link set dev $swp1 nomaster
+	ip -6 route get fibmatch 2001:db8:1::2 dev br0.10 | grep -q offload
+	check_fail $? "vlan rif was not destroyed after unlinking port from bridge"
+
+	log_test "vlan rif refcount"
+
+	ip link del dev br0.10
+	ip link set dev $swp1 down
+	ip link del dev br0
+}
+
+subport_rif_refcount_test()
+{
+	# Test that RIFs representing upper devices of physical ports are
+	# reference counted correctly and destroyed when should. We use the
+	# offload indication on routes configured on the RIF to understand if
+	# it was created / destroyed
+	RET=0
+
+	ip link add name bond1 type bond mode 802.3ad
+	ip link set dev $swp1 down
+	ip link set dev $swp2 down
+	ip link set dev $swp1 master bond1
+	ip link set dev $swp2 master bond1
+
+	ip link set dev bond1 up
+	ip link add link bond1 name bond1.10 up type vlan id 10
+	ip -6 address add 2001:db8:1::1/64 dev bond1
+	ip -6 address add 2001:db8:2::1/64 dev bond1.10
+
+	ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+	check_err $? "subport rif was not created on lag device"
+	ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+	check_err $? "subport rif was not created on vlan device"
+
+	ip link set dev $swp1 nomaster
+	ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+	check_err $? "subport rif of lag device was destroyed when should not"
+	ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+	check_err $? "subport rif of vlan device was destroyed when should not"
+
+	ip link set dev $swp2 nomaster
+	ip -6 route get fibmatch 2001:db8:1::2 dev bond1 | grep -q offload
+	check_fail $? "subport rif of lag device was not destroyed when should"
+	ip -6 route get fibmatch 2001:db8:2::2 dev bond1.10 | grep -q offload
+	check_fail $? "subport rif of vlan device was not destroyed when should"
+
+	log_test "subport rif refcount"
+
+	ip link del dev bond1.10
+	ip link del dev bond1
+}
+
+vlan_dev_deletion_test()
+{
+	# Test that VLAN devices are correctly deleted / unlinked when enslaved
+	# to bridge
+	RET=0
+
+	ip link add name br10 type bridge
+	ip link add name br20 type bridge
+	ip link add name br30 type bridge
+	ip link add link $swp1 name $swp1.10 type vlan id 10
+	ip link add link $swp1 name $swp1.20 type vlan id 20
+	ip link add link $swp1 name $swp1.30 type vlan id 30
+	ip link set dev $swp1.10 master br10
+	ip link set dev $swp1.20 master br20
+	ip link set dev $swp1.30 master br30
+
+	# If we did not handle the situation correctly, then these operations
+	# might produce a trace
+	ip link set dev $swp1.30 nomaster
+	ip link del dev $swp1.20
+	# Deletion via ioctl uses different code paths from netlink
+	vconfig rem $swp1.10 &> /dev/null
+
+	log_test "vlan device deletion"
+
+	ip link del dev $swp1.30
+	ip link del dev br30
+	ip link del dev br20
+	ip link del dev br10
+}
+
+lag_create()
+{
+	ip link add name bond1 type bond mode 802.3ad
+	ip link set dev $swp1 down
+	ip link set dev $swp2 down
+	ip link set dev $swp1 master bond1
+	ip link set dev $swp2 master bond1
+
+	ip link add link bond1 name bond1.10 type vlan id 10
+	ip link add link bond1 name bond1.20 type vlan id 20
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev bond1 master br0
+
+	ip link add name br10 type bridge
+	ip link set dev bond1.10 master br10
+
+	ip link add name br20 type bridge
+	ip link set dev bond1.20 master br20
+}
+
+lag_unlink_slaves_test()
+{
+	# Test that ports are correctly unlinked from their LAG master, when
+	# the LAG and its VLAN uppers are enslaved to bridges
+	RET=0
+
+	lag_create
+
+	ip link set dev $swp1 nomaster
+	check_err $? "lag slave $swp1 was not unlinked from master"
+	ip link set dev $swp2 nomaster
+	check_err $? "lag slave $swp2 was not unlinked from master"
+
+	# Try to configure corresponding VLANs as router interfaces
+	ip -6 address add 2001:db8:1::1/64 dev $swp1
+	check_err $? "failed to configure ip address on $swp1"
+
+	ip link add link $swp1 name $swp1.10 type vlan id 10
+	ip -6 address add 2001:db8:10::1/64 dev $swp1.10
+	check_err $? "failed to configure ip address on $swp1.10"
+
+	ip link add link $swp1 name $swp1.20 type vlan id 20
+	ip -6 address add 2001:db8:20::1/64 dev $swp1.20
+	check_err $? "failed to configure ip address on $swp1.20"
+
+	log_test "lag slaves unlinking"
+
+	ip link del dev $swp1.20
+	ip link del dev $swp1.10
+	ip address flush dev $swp1
+
+	ip link del dev br20
+	ip link del dev br10
+	ip link del dev br0
+	ip link del dev bond1
+}
+
+lag_dev_deletion_test()
+{
+	# Test that LAG device is correctly deleted, when the LAG and its VLAN
+	# uppers are enslaved to bridges
+	RET=0
+
+	lag_create
+
+	ip link del dev bond1
+
+	log_test "lag device deletion"
+
+	ip link del dev br20
+	ip link del dev br10
+	ip link del dev br0
+}
+
+vlan_interface_uppers_test()
+{
+	# Test that uppers of a VLAN interface are correctly sanitized
+	RET=0
+
+	ip link add name br0 type bridge vlan_filtering 1
+	ip link set dev $swp1 master br0
+
+	ip link add link br0 name br0.10 type vlan id 10
+	ip link add link br0.10 name macvlan0 \
+		type macvlan mode private &> /dev/null
+	check_fail $? "managed to create a macvlan when should not"
+
+	ip -6 address add 2001:db8:1::1/64 dev br0.10
+	ip link add link br0.10 name macvlan0 type macvlan mode private
+	check_err $? "did not manage to create a macvlan when should"
+
+	ip link del dev macvlan0
+
+	ip link add name vrf-test type vrf table 10
+	ip link set dev br0.10 master vrf-test
+	check_err $? "did not manage to enslave vlan interface to vrf"
+	ip link del dev vrf-test
+
+	ip link add name br-test type bridge
+	ip link set dev br0.10 master br-test &> /dev/null
+	check_fail $? "managed to enslave vlan interface to bridge when should not"
+	ip link del dev br-test
+
+	log_test "vlan interface uppers"
+
+	ip link del dev br0
+}
+
+devlink_reload_test()
+{
+	# Test that after executing all the above configuration tests, a
+	# devlink reload can be performed without errors
+	RET=0
+
+	devlink dev reload "$DEVLINK_DEV"
+	check_err $? "devlink reload failed"
+
+	log_test "devlink reload - last test"
+
+	sleep 20
+}
+
 trap cleanup EXIT
 
 setup_prepare