Merge branch 'bonding-team-offload'

Jiri Pirko says:

====================
bonding/team offload + mlxsw implementation

This patchset introduces needed infrastructure for link aggregation
offload - for both team and bonding. It also implements the offload
in mlxsw driver.

Particulary, this patchset introduces possibility for upper driver
(bond/team/bridge/..) to pass type-specific info down to notifier listeners.
Info is passed along with NETDEV_CHANGEUPPER/NETDEV_PRECHANGEUPPER
notifiers. Listeners (drivers of netdevs being enslaved) can react
accordingly.

Other extension is for run-time use. This patchset introduces
new netdev notifier type - NETDEV_CHANGELOWERSTATE. Along with this
notification, the upper driver (bond/team/bridge/..) can pass some
information about lower device change, particulary link-up and
TX-enabled states. Listeners (drivers of netdevs being enslaved)
can react accordingly.

The last part of the patchset is implementation of LAG offload in mlxsw,
using both previously introduced infrastructre extensions.

Note that bond-speficic (and ugly) NETDEV_BONDING_INFO used by mlx4
can be removed and mlx4 can use the extensions this patchset adds.
I plan to convert it and get rid of NETDEV_BONDING_INFO in
a follow-up patchset.

v2->v3:
- one small fix in patch 1
v1->v2:
- added patch 1 and 2 per Andy's request
- couple of more or less cosmetic changes described in couple other patches
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/fault-injection/notifier-error-inject.txt

@@ -103,6 +103,7 @@ Netdevice notifier events which can be failed are:
  * NETDEV_POST_INIT
  * NETDEV_PRECHANGEMTU
  * NETDEV_PRECHANGEUPPER
+ * NETDEV_CHANGEUPPER
 
 Example: Inject netdevice mtu change error (-22 == -EINVAL)
 

drivers/net/bonding/bond_3ad.c

@@ -93,7 +93,8 @@ enum ad_link_speed_type {
 	AD_LINK_SPEED_10000MBPS,
 	AD_LINK_SPEED_20000MBPS,
 	AD_LINK_SPEED_40000MBPS,
-	AD_LINK_SPEED_56000MBPS
+	AD_LINK_SPEED_56000MBPS,
+	AD_LINK_SPEED_100000MBPS,
 };
 
 /* compare MAC addresses */
@@ -258,6 +259,7 @@ static inline int __check_agg_selection_timer(struct port *port)
  *     %AD_LINK_SPEED_20000MBPS
  *     %AD_LINK_SPEED_40000MBPS
  *     %AD_LINK_SPEED_56000MBPS
+ *     %AD_LINK_SPEED_100000MBPS
  */
 static u16 __get_link_speed(struct port *port)
 {
@@ -305,6 +307,10 @@ static u16 __get_link_speed(struct port *port)
 			speed = AD_LINK_SPEED_56000MBPS;
 			break;
 
+		case SPEED_100000:
+			speed = AD_LINK_SPEED_100000MBPS;
+			break;
+
 		default:
 			/* unknown speed value from ethtool. shouldn't happen */
 			speed = 0;
@@ -681,6 +687,9 @@ static u32 __get_agg_bandwidth(struct aggregator *aggregator)
 		case AD_LINK_SPEED_56000MBPS:
 			bandwidth = aggregator->num_of_ports * 56000;
 			break;
+		case AD_LINK_SPEED_100000MBPS:
+			bandwidth = aggregator->num_of_ports * 100000;
+			break;
 		default:
 			bandwidth = 0; /* to silence the compiler */
 		}

drivers/net/bonding/bond_main.c

@@ -830,7 +830,8 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active)
 			}
 
 			new_active->delay = 0;
-			bond_set_slave_link_state(new_active, BOND_LINK_UP);
+			bond_set_slave_link_state(new_active, BOND_LINK_UP,
+						  BOND_SLAVE_NOTIFY_NOW);
 
 			if (BOND_MODE(bond) == BOND_MODE_8023AD)
 				bond_3ad_handle_link_change(new_active, BOND_LINK_UP);
@@ -1198,26 +1199,43 @@ static rx_handler_result_t bond_handle_frame(struct sk_buff **pskb)
 	return ret;
 }
 
-static int bond_master_upper_dev_link(struct net_device *bond_dev,
-				      struct net_device *slave_dev,
-				      struct slave *slave)
+static enum netdev_lag_tx_type bond_lag_tx_type(struct bonding *bond)
 {
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_ROUNDROBIN:
+		return NETDEV_LAG_TX_TYPE_ROUNDROBIN;
+	case BOND_MODE_ACTIVEBACKUP:
+		return NETDEV_LAG_TX_TYPE_ACTIVEBACKUP;
+	case BOND_MODE_BROADCAST:
+		return NETDEV_LAG_TX_TYPE_BROADCAST;
+	case BOND_MODE_XOR:
+	case BOND_MODE_8023AD:
+		return NETDEV_LAG_TX_TYPE_HASH;
+	default:
+		return NETDEV_LAG_TX_TYPE_UNKNOWN;
+	}
+}
+
+static int bond_master_upper_dev_link(struct bonding *bond, struct slave *slave)
+{
+	struct netdev_lag_upper_info lag_upper_info;
 	int err;
 
-	err = netdev_master_upper_dev_link_private(slave_dev, bond_dev, slave);
+	lag_upper_info.tx_type = bond_lag_tx_type(bond);
+	err = netdev_master_upper_dev_link(slave->dev, bond->dev, slave,
+					   &lag_upper_info);
 	if (err)
 		return err;
-	slave_dev->flags |= IFF_SLAVE;
-	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
+	slave->dev->flags |= IFF_SLAVE;
+	rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
 	return 0;
 }
 
-static void bond_upper_dev_unlink(struct net_device *bond_dev,
-				  struct net_device *slave_dev)
+static void bond_upper_dev_unlink(struct bonding *bond, struct slave *slave)
 {
-	netdev_upper_dev_unlink(slave_dev, bond_dev);
-	slave_dev->flags &= ~IFF_SLAVE;
-	rtmsg_ifinfo(RTM_NEWLINK, slave_dev, IFF_SLAVE, GFP_KERNEL);
+	netdev_upper_dev_unlink(slave->dev, bond->dev);
+	slave->dev->flags &= ~IFF_SLAVE;
+	rtmsg_ifinfo(RTM_NEWLINK, slave->dev, IFF_SLAVE, GFP_KERNEL);
 }
 
 static struct slave *bond_alloc_slave(struct bonding *bond)
@@ -1299,6 +1317,16 @@ void bond_queue_slave_event(struct slave *slave)
 	queue_delayed_work(slave->bond->wq, &nnw->work, 0);
 }
 
+void bond_lower_state_changed(struct slave *slave)
+{
+	struct netdev_lag_lower_state_info info;
+
+	info.link_up = slave->link == BOND_LINK_UP ||
+		       slave->link == BOND_LINK_FAIL;
+	info.tx_enabled = bond_is_active_slave(slave);
+	netdev_lower_state_changed(slave->dev, &info);
+}
+
 /* enslave device <slave> to bond device <master> */
 int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 {
@@ -1563,21 +1591,26 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		if (bond_check_dev_link(bond, slave_dev, 0) == BMSR_LSTATUS) {
 			if (bond->params.updelay) {
 				bond_set_slave_link_state(new_slave,
-							  BOND_LINK_BACK);
+							  BOND_LINK_BACK,
+							  BOND_SLAVE_NOTIFY_NOW);
 				new_slave->delay = bond->params.updelay;
 			} else {
 				bond_set_slave_link_state(new_slave,
-							  BOND_LINK_UP);
+							  BOND_LINK_UP,
+							  BOND_SLAVE_NOTIFY_NOW);
 			}
 		} else {
-			bond_set_slave_link_state(new_slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(new_slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_NOW);
 		}
 	} else if (bond->params.arp_interval) {
 		bond_set_slave_link_state(new_slave,
 					  (netif_carrier_ok(slave_dev) ?
-					  BOND_LINK_UP : BOND_LINK_DOWN));
+					  BOND_LINK_UP : BOND_LINK_DOWN),
+					  BOND_SLAVE_NOTIFY_NOW);
 	} else {
-		bond_set_slave_link_state(new_slave, BOND_LINK_UP);
+		bond_set_slave_link_state(new_slave, BOND_LINK_UP,
+					  BOND_SLAVE_NOTIFY_NOW);
 	}
 
 	if (new_slave->link != BOND_LINK_DOWN)
@@ -1662,7 +1695,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 		goto err_detach;
 	}
 
-	res = bond_master_upper_dev_link(bond_dev, slave_dev, new_slave);
+	res = bond_master_upper_dev_link(bond, new_slave);
 	if (res) {
 		netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res);
 		goto err_unregister;
@@ -1698,7 +1731,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
 
 /* Undo stages on error */
 err_upper_unlink:
-	bond_upper_dev_unlink(bond_dev, slave_dev);
+	bond_upper_dev_unlink(bond, new_slave);
 
 err_unregister:
 	netdev_rx_handler_unregister(slave_dev);
@@ -1799,12 +1832,14 @@ static int __bond_release_one(struct net_device *bond_dev,
 		return -EINVAL;
 	}
 
+	bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW);
+
 	bond_sysfs_slave_del(slave);
 
 	/* recompute stats just before removing the slave */
 	bond_get_stats(bond->dev, &bond->bond_stats);
 
-	bond_upper_dev_unlink(bond_dev, slave_dev);
+	bond_upper_dev_unlink(bond, slave);
 	/* unregister rx_handler early so bond_handle_frame wouldn't be called
 	 * for this slave anymore.
 	 */
@@ -1996,7 +2031,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_FAIL);
+			bond_set_slave_link_state(slave, BOND_LINK_FAIL,
+						  BOND_SLAVE_NOTIFY_LATER);
 			slave->delay = bond->params.downdelay;
 			if (slave->delay) {
 				netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n",
@@ -2011,7 +2047,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_FAIL:
 			if (link_state) {
 				/* recovered before downdelay expired */
-				bond_set_slave_link_state(slave, BOND_LINK_UP);
+				bond_set_slave_link_state(slave, BOND_LINK_UP,
+							  BOND_SLAVE_NOTIFY_LATER);
 				slave->last_link_up = jiffies;
 				netdev_info(bond->dev, "link status up again after %d ms for interface %s\n",
 					    (bond->params.downdelay - slave->delay) *
@@ -2033,7 +2070,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 			if (!link_state)
 				continue;
 
-			bond_set_slave_link_state(slave, BOND_LINK_BACK);
+			bond_set_slave_link_state(slave, BOND_LINK_BACK,
+						  BOND_SLAVE_NOTIFY_LATER);
 			slave->delay = bond->params.updelay;
 
 			if (slave->delay) {
@@ -2047,7 +2085,8 @@ static int bond_miimon_inspect(struct bonding *bond)
 		case BOND_LINK_BACK:
 			if (!link_state) {
 				bond_set_slave_link_state(slave,
-							  BOND_LINK_DOWN);
+							  BOND_LINK_DOWN,
+							  BOND_SLAVE_NOTIFY_LATER);
 				netdev_info(bond->dev, "link status down again after %d ms for interface %s\n",
 					    (bond->params.updelay - slave->delay) *
 					    bond->params.miimon,
@@ -2085,7 +2124,8 @@ static void bond_miimon_commit(struct bonding *bond)
 			continue;
 
 		case BOND_LINK_UP:
-			bond_set_slave_link_state(slave, BOND_LINK_UP);
+			bond_set_slave_link_state(slave, BOND_LINK_UP,
+						  BOND_SLAVE_NOTIFY_NOW);
 			slave->last_link_up = jiffies;
 
 			primary = rtnl_dereference(bond->primary_slave);
@@ -2125,7 +2165,8 @@ static void bond_miimon_commit(struct bonding *bond)
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_NOW);
 
 			if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP ||
 			    BOND_MODE(bond) == BOND_MODE_8023AD)
@@ -2708,7 +2749,8 @@ static void bond_ab_arp_commit(struct bonding *bond)
 				struct slave *current_arp_slave;
 
 				current_arp_slave = rtnl_dereference(bond->current_arp_slave);
-				bond_set_slave_link_state(slave, BOND_LINK_UP);
+				bond_set_slave_link_state(slave, BOND_LINK_UP,
+							  BOND_SLAVE_NOTIFY_NOW);
 				if (current_arp_slave) {
 					bond_set_slave_inactive_flags(
 						current_arp_slave,
@@ -2731,7 +2773,8 @@ static void bond_ab_arp_commit(struct bonding *bond)
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
-			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_NOW);
 			bond_set_slave_inactive_flags(slave,
 						      BOND_SLAVE_NOTIFY_NOW);
 
@@ -2810,7 +2853,8 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 		 * up when it is actually down
 		 */
 		if (!bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) {
-			bond_set_slave_link_state(slave, BOND_LINK_DOWN);
+			bond_set_slave_link_state(slave, BOND_LINK_DOWN,
+						  BOND_SLAVE_NOTIFY_LATER);
 			if (slave->link_failure_count < UINT_MAX)
 				slave->link_failure_count++;
 
@@ -2830,7 +2874,8 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 	if (!new_slave)
 		goto check_state;
 
-	bond_set_slave_link_state(new_slave, BOND_LINK_BACK);
+	bond_set_slave_link_state(new_slave, BOND_LINK_BACK,
+				  BOND_SLAVE_NOTIFY_LATER);
 	bond_set_slave_active_flags(new_slave, BOND_SLAVE_NOTIFY_LATER);
 	bond_arp_send_all(bond, new_slave);
 	new_slave->last_link_up = jiffies;
@@ -2838,7 +2883,7 @@ static bool bond_ab_arp_probe(struct bonding *bond)
 
 check_state:
 	bond_for_each_slave_rcu(bond, slave, iter) {
-		if (slave->should_notify) {
+		if (slave->should_notify || slave->should_notify_link) {
 			should_notify_rtnl = BOND_SLAVE_NOTIFY_NOW;
 			break;
 		}
@@ -2893,8 +2938,10 @@ static void bond_activebackup_arp_mon(struct work_struct *work)
 		if (should_notify_peers)
 			call_netdevice_notifiers(NETDEV_NOTIFY_PEERS,
 						 bond->dev);
-		if (should_notify_rtnl)
+		if (should_notify_rtnl) {
 			bond_slave_state_notify(bond);
+			bond_slave_link_notify(bond);
+		}
 
 		rtnl_unlock();
 	}

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

@@ -105,6 +105,9 @@ struct mlxsw_core {
 		struct debugfs_blob_wrapper vsd_blob;
 		struct debugfs_blob_wrapper psid_blob;
 	} dbg;
+	struct {
+		u8 *mapping; /* lag_id+port_index to local_port mapping */
+	} lag;
 	struct mlxsw_hwmon *hwmon;
 	unsigned long driver_priv[0];
 	/* driver_priv has to be always the last item */
@@ -815,6 +818,17 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 		goto err_alloc_stats;
 	}
 
+	if (mlxsw_driver->profile->used_max_lag &&
+	    mlxsw_driver->profile->used_max_port_per_lag) {
+		alloc_size = sizeof(u8) * mlxsw_driver->profile->max_lag *
+			     mlxsw_driver->profile->max_port_per_lag;
+		mlxsw_core->lag.mapping = kzalloc(alloc_size, GFP_KERNEL);
+		if (!mlxsw_core->lag.mapping) {
+			err = -ENOMEM;
+			goto err_alloc_lag_mapping;
+		}
+	}
+
 	err = mlxsw_bus->init(bus_priv, mlxsw_core, mlxsw_driver->profile);
 	if (err)
 		goto err_bus_init;
@@ -847,6 +861,8 @@ int mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info,
 err_emad_init:
 	mlxsw_bus->fini(bus_priv);
 err_bus_init:
+	kfree(mlxsw_core->lag.mapping);
+err_alloc_lag_mapping:
 	free_percpu(mlxsw_core->pcpu_stats);
 err_alloc_stats:
 	kfree(mlxsw_core);
@@ -865,6 +881,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core)
 	mlxsw_hwmon_fini(mlxsw_core->hwmon);
 	mlxsw_emad_fini(mlxsw_core);
 	mlxsw_core->bus->fini(mlxsw_core->bus_priv);
+	kfree(mlxsw_core->lag.mapping);
 	free_percpu(mlxsw_core->pcpu_stats);
 	kfree(mlxsw_core);
 	mlxsw_core_driver_put(device_kind);
@@ -1196,11 +1213,25 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 	struct mlxsw_rx_listener_item *rxl_item;
 	const struct mlxsw_rx_listener *rxl;
 	struct mlxsw_core_pcpu_stats *pcpu_stats;
-	u8 local_port = rx_info->sys_port;
+	u8 local_port;
 	bool found = false;
 
-	dev_dbg_ratelimited(mlxsw_core->bus_info->dev, "%s: sys_port = %d, trap_id = 0x%x\n",
-			    __func__, rx_info->sys_port, rx_info->trap_id);
+	if (rx_info->is_lag) {
+		dev_dbg_ratelimited(mlxsw_core->bus_info->dev, "%s: lag_id = %d, lag_port_index = 0x%x\n",
+				    __func__, rx_info->u.lag_id,
+				    rx_info->trap_id);
+		/* Upper layer does not care if the skb came from LAG or not,
+		 * so just get the local_port for the lag port and push it up.
+		 */
+		local_port = mlxsw_core_lag_mapping_get(mlxsw_core,
+							rx_info->u.lag_id,
+							rx_info->lag_port_index);
+	} else {
+		local_port = rx_info->u.sys_port;
+	}
+
+	dev_dbg_ratelimited(mlxsw_core->bus_info->dev, "%s: local_port = %d, trap_id = 0x%x\n",
+			    __func__, local_port, rx_info->trap_id);
 
 	if ((rx_info->trap_id >= MLXSW_TRAP_ID_MAX) ||
 	    (local_port >= MLXSW_PORT_MAX_PORTS))
@@ -1244,6 +1275,48 @@ void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(mlxsw_core_skb_receive);
 
+static int mlxsw_core_lag_mapping_index(struct mlxsw_core *mlxsw_core,
+					u16 lag_id, u8 port_index)
+{
+	return mlxsw_core->driver->profile->max_port_per_lag * lag_id +
+	       port_index;
+}
+
+void mlxsw_core_lag_mapping_set(struct mlxsw_core *mlxsw_core,
+				u16 lag_id, u8 port_index, u8 local_port)
+{
+	int index = mlxsw_core_lag_mapping_index(mlxsw_core,
+						 lag_id, port_index);
+
+	mlxsw_core->lag.mapping[index] = local_port;
+}
+EXPORT_SYMBOL(mlxsw_core_lag_mapping_set);
+
+u8 mlxsw_core_lag_mapping_get(struct mlxsw_core *mlxsw_core,
+			      u16 lag_id, u8 port_index)
+{
+	int index = mlxsw_core_lag_mapping_index(mlxsw_core,
+						 lag_id, port_index);
+
+	return mlxsw_core->lag.mapping[index];
+}
+EXPORT_SYMBOL(mlxsw_core_lag_mapping_get);
+
+void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
+				  u16 lag_id, u8 local_port)
+{
+	int i;
+
+	for (i = 0; i < mlxsw_core->driver->profile->max_port_per_lag; i++) {
+		int index = mlxsw_core_lag_mapping_index(mlxsw_core,
+							 lag_id, i);
+
+		if (mlxsw_core->lag.mapping[index] == local_port)
+			mlxsw_core->lag.mapping[index] = 0;
+	}
+}
+EXPORT_SYMBOL(mlxsw_core_lag_mapping_clear);
+
 int mlxsw_cmd_exec(struct mlxsw_core *mlxsw_core, u16 opcode, u8 opcode_mod,
 		   u32 in_mod, bool out_mbox_direct,
 		   char *in_mbox, size_t in_mbox_size,

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

@@ -112,13 +112,25 @@ int mlxsw_reg_write(struct mlxsw_core *mlxsw_core,
 		    const struct mlxsw_reg_info *reg, char *payload);
 
 struct mlxsw_rx_info {
+	bool is_lag;
+	union {
 		u16 sys_port;
+		u16 lag_id;
+	} u;
+	u8 lag_port_index;
 	int trap_id;
 };
 
 void mlxsw_core_skb_receive(struct mlxsw_core *mlxsw_core, struct sk_buff *skb,
 			    struct mlxsw_rx_info *rx_info);
 
+void mlxsw_core_lag_mapping_set(struct mlxsw_core *mlxsw_core,
+				u16 lag_id, u8 port_index, u8 local_port);
+u8 mlxsw_core_lag_mapping_get(struct mlxsw_core *mlxsw_core,
+			      u16 lag_id, u8 port_index);
+void mlxsw_core_lag_mapping_clear(struct mlxsw_core *mlxsw_core,
+				  u16 lag_id, u8 local_port);
+
 #define MLXSW_CONFIG_PROFILE_SWID_COUNT 8
 
 struct mlxsw_swid_config {

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

@@ -686,11 +686,15 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	if (q->consumer_counter++ != consumer_counter_limit)
 		dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n");
 
-	/* We do not support lag now */
-	if (mlxsw_pci_cqe_lag_get(cqe))
-		goto drop;
+	if (mlxsw_pci_cqe_lag_get(cqe)) {
+		rx_info.is_lag = true;
+		rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe);
+		rx_info.lag_port_index = mlxsw_pci_cqe_lag_port_index_get(cqe);
+	} else {
+		rx_info.is_lag = false;
+		rx_info.u.sys_port = mlxsw_pci_cqe_system_port_get(cqe);
+	}
 
-	rx_info.sys_port = mlxsw_pci_cqe_system_port_get(cqe);
 	rx_info.trap_id = mlxsw_pci_cqe_trap_id_get(cqe);
 
 	byte_count = mlxsw_pci_cqe_byte_count_get(cqe);
@@ -699,7 +703,6 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	skb_put(skb, byte_count);
 	mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info);
 
-put_new_skb:
 	memset(wqe, 0, q->elem_size);
 	err = mlxsw_pci_rdq_skb_alloc(mlxsw_pci, elem_info);
 	if (err)
@@ -708,10 +711,6 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci,
 	q->producer_counter++;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
 	return;
-
-drop:
-	dev_kfree_skb_any(skb);
-	goto put_new_skb;
 }
 
 static char *mlxsw_pci_cq_sw_cqe_get(struct mlxsw_pci_queue *q)

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

@@ -129,13 +129,15 @@ MLXSW_ITEM64_INDEXED(pci, wqe, address, 0x08, 0, 64, 0x8, 0x0, false);
  */
 MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1);
 
-/* pci_cqe_system_port
+/* pci_cqe_system_port/lag_id
  * When lag=0: System port on which the packet was received
  * When lag=1:
  * bits [15:4] LAG ID on which the packet was received
  * bits [3:0] sub_port on which the packet was received
  */
 MLXSW_ITEM32(pci, cqe, system_port, 0x00, 0, 16);
+MLXSW_ITEM32(pci, cqe, lag_id, 0x00, 4, 12);
+MLXSW_ITEM32(pci, cqe, lag_port_index, 0x00, 0, 4);
 
 /* pci_cqe_wqe_counter
  * WQE count of the WQEs completed on the associated dqn

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

@@ -286,6 +286,7 @@ MLXSW_ITEM32_INDEXED(reg, sfd, rec_swid, MLXSW_REG_SFD_BASE_LEN, 24, 8,
 
 enum mlxsw_reg_sfd_rec_type {
 	MLXSW_REG_SFD_REC_TYPE_UNICAST = 0x0,
+	MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG = 0x1,
 };
 
 /* reg_sfd_rec_type
@@ -376,24 +377,34 @@ MLXSW_ITEM32_INDEXED(reg, sfd, uc_fid_vid, MLXSW_REG_SFD_BASE_LEN, 0, 16,
 MLXSW_ITEM32_INDEXED(reg, sfd, uc_system_port, MLXSW_REG_SFD_BASE_LEN, 0, 16,
 		     MLXSW_REG_SFD_REC_LEN, 0x0C, false);
 
-static inline void mlxsw_reg_sfd_uc_pack(char *payload, int rec_index,
+static inline void mlxsw_reg_sfd_rec_pack(char *payload, int rec_index,
+					  enum mlxsw_reg_sfd_rec_type rec_type,
 					  enum mlxsw_reg_sfd_rec_policy policy,
-					 const char *mac, u16 vid,
-					 enum mlxsw_reg_sfd_rec_action action,
-					 u8 local_port)
+					  const char *mac,
+					  enum mlxsw_reg_sfd_rec_action action)
 {
 	u8 num_rec = mlxsw_reg_sfd_num_rec_get(payload);
 
 	if (rec_index >= num_rec)
 		mlxsw_reg_sfd_num_rec_set(payload, rec_index + 1);
 	mlxsw_reg_sfd_rec_swid_set(payload, rec_index, 0);
-	mlxsw_reg_sfd_rec_type_set(payload, rec_index,
-				   MLXSW_REG_SFD_REC_TYPE_UNICAST);
+	mlxsw_reg_sfd_rec_type_set(payload, rec_index, rec_type);
 	mlxsw_reg_sfd_rec_policy_set(payload, rec_index, policy);
 	mlxsw_reg_sfd_rec_mac_memcpy_to(payload, rec_index, mac);
+	mlxsw_reg_sfd_rec_action_set(payload, rec_index, action);
+}
+
+static inline void mlxsw_reg_sfd_uc_pack(char *payload, int rec_index,
+					 enum mlxsw_reg_sfd_rec_policy policy,
+					 const char *mac, u16 vid,
+					 enum mlxsw_reg_sfd_rec_action action,
+					 u8 local_port)
+{
+	mlxsw_reg_sfd_rec_pack(payload, rec_index,
+			       MLXSW_REG_SFD_REC_TYPE_UNICAST,
+			       policy, mac, action);
 	mlxsw_reg_sfd_uc_sub_port_set(payload, rec_index, 0);
 	mlxsw_reg_sfd_uc_fid_vid_set(payload, rec_index, vid);
-	mlxsw_reg_sfd_rec_action_set(payload, rec_index, action);
 	mlxsw_reg_sfd_uc_system_port_set(payload, rec_index, local_port);
 }
 
@@ -406,6 +417,58 @@ static inline void mlxsw_reg_sfd_uc_unpack(char *payload, int rec_index,
 	*p_local_port = mlxsw_reg_sfd_uc_system_port_get(payload, rec_index);
 }
 
+/* reg_sfd_uc_lag_sub_port
+ * LAG sub port.
+ * Must be 0 if multichannel VEPA is not enabled.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, sfd, uc_lag_sub_port, MLXSW_REG_SFD_BASE_LEN, 16, 8,
+		     MLXSW_REG_SFD_REC_LEN, 0x08, false);
+
+/* reg_sfd_uc_lag_fid_vid
+ * Filtering ID or VLAN ID
+ * For SwitchX and SwitchX-2:
+ * - Dynamic entries (policy 2,3) use FID
+ * - Static entries (policy 0) use VID
+ * - When independent learning is configured, VID=FID
+ * For Spectrum: use FID for both Dynamic and Static entries.
+ * VID should not be used.
+ * Access: Index
+ */
+MLXSW_ITEM32_INDEXED(reg, sfd, uc_lag_fid_vid, MLXSW_REG_SFD_BASE_LEN, 0, 16,
+		     MLXSW_REG_SFD_REC_LEN, 0x08, false);
+
+/* reg_sfd_uc_lag_lag_id
+ * LAG Identifier - pointer into the LAG descriptor table.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, sfd, uc_lag_lag_id, MLXSW_REG_SFD_BASE_LEN, 0, 10,
+		     MLXSW_REG_SFD_REC_LEN, 0x0C, false);
+
+static inline void
+mlxsw_reg_sfd_uc_lag_pack(char *payload, int rec_index,
+			  enum mlxsw_reg_sfd_rec_policy policy,
+			  const char *mac, u16 vid,
+			  enum mlxsw_reg_sfd_rec_action action,
+			  u16 lag_id)
+{
+	mlxsw_reg_sfd_rec_pack(payload, rec_index,
+			       MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG,
+			       policy, mac, action);
+	mlxsw_reg_sfd_uc_lag_sub_port_set(payload, rec_index, 0);
+	mlxsw_reg_sfd_uc_lag_fid_vid_set(payload, rec_index, vid);
+	mlxsw_reg_sfd_uc_lag_lag_id_set(payload, rec_index, lag_id);
+}
+
+static inline void mlxsw_reg_sfd_uc_lag_unpack(char *payload, int rec_index,
+					       char *mac, u16 *p_vid,
+					       u16 *p_lag_id)
+{
+	mlxsw_reg_sfd_rec_mac_memcpy_from(payload, rec_index, mac);
+	*p_vid = mlxsw_reg_sfd_uc_lag_fid_vid_get(payload, rec_index);
+	*p_lag_id = mlxsw_reg_sfd_uc_lag_lag_id_get(payload, rec_index);
+}
+
 /* SFN - Switch FDB Notification Register
  * -------------------------------------------
  * The switch provides notifications on newly learned FDB entries and
@@ -456,8 +519,12 @@ MLXSW_ITEM32_INDEXED(reg, sfn, rec_swid, MLXSW_REG_SFN_BASE_LEN, 24, 8,
 enum mlxsw_reg_sfn_rec_type {
 	/* MAC addresses learned on a regular port. */
 	MLXSW_REG_SFN_REC_TYPE_LEARNED_MAC = 0x5,
-	/* Aged-out MAC address on a regular port */
+	/* MAC addresses learned on a LAG port. */
+	MLXSW_REG_SFN_REC_TYPE_LEARNED_MAC_LAG = 0x6,
+	/* Aged-out MAC address on a regular port. */
 	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC = 0x7,
+	/* Aged-out MAC address on a LAG port. */
+	MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC_LAG = 0x8,
 };
 
 /* reg_sfn_rec_type
@@ -505,6 +572,22 @@ static inline void mlxsw_reg_sfn_mac_unpack(char *payload, int rec_index,
 	*p_local_port = mlxsw_reg_sfn_mac_system_port_get(payload, rec_index);
 }
 
+/* reg_sfn_mac_lag_lag_id
+ * LAG ID (pointer into the LAG descriptor table).
+ * Access: RO
+ */
+MLXSW_ITEM32_INDEXED(reg, sfn, mac_lag_lag_id, MLXSW_REG_SFN_BASE_LEN, 0, 10,
+		     MLXSW_REG_SFN_REC_LEN, 0x0C, false);
+
+static inline void mlxsw_reg_sfn_mac_lag_unpack(char *payload, int rec_index,
+						char *mac, u16 *p_vid,
+						u16 *p_lag_id)
+{
+	mlxsw_reg_sfn_rec_mac_memcpy_from(payload, rec_index, mac);
+	*p_vid = mlxsw_reg_sfn_mac_fid_get(payload, rec_index);
+	*p_lag_id = mlxsw_reg_sfn_mac_lag_lag_id_get(payload, rec_index);
+}
+
 /* SPMS - Switch Port MSTP/RSTP State Register
  * -------------------------------------------
  * Configures the spanning tree state of a physical port.
@@ -865,6 +948,293 @@ static inline void mlxsw_reg_sftr_pack(char *payload,
 	mlxsw_reg_sftr_port_mask_set(payload, port, 1);
 }
 
+/* SLDR - Switch LAG Descriptor Register
+ * -----------------------------------------
+ * The switch LAG descriptor register is populated by LAG descriptors.
+ * Each LAG descriptor is indexed by lag_id. The LAG ID runs from 0 to
+ * max_lag-1.
+ */
+#define MLXSW_REG_SLDR_ID 0x2014
+#define MLXSW_REG_SLDR_LEN 0x0C /* counting in only one port in list */
+
+static const struct mlxsw_reg_info mlxsw_reg_sldr = {
+	.id = MLXSW_REG_SLDR_ID,
+	.len = MLXSW_REG_SLDR_LEN,
+};
+
+enum mlxsw_reg_sldr_op {
+	/* Indicates a creation of a new LAG-ID, lag_id must be valid */
+	MLXSW_REG_SLDR_OP_LAG_CREATE,
+	MLXSW_REG_SLDR_OP_LAG_DESTROY,
+	/* Ports that appear in the list have the Distributor enabled */
+	MLXSW_REG_SLDR_OP_LAG_ADD_PORT_LIST,
+	/* Removes ports from the disributor list */
+	MLXSW_REG_SLDR_OP_LAG_REMOVE_PORT_LIST,
+};
+
+/* reg_sldr_op
+ * Operation.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sldr, op, 0x00, 29, 3);
+
+/* reg_sldr_lag_id
+ * LAG identifier. The lag_id is the index into the LAG descriptor table.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, sldr, lag_id, 0x00, 0, 10);
+
+static inline void mlxsw_reg_sldr_lag_create_pack(char *payload, u8 lag_id)
+{
+	MLXSW_REG_ZERO(sldr, payload);
+	mlxsw_reg_sldr_op_set(payload, MLXSW_REG_SLDR_OP_LAG_CREATE);
+	mlxsw_reg_sldr_lag_id_set(payload, lag_id);
+}
+
+static inline void mlxsw_reg_sldr_lag_destroy_pack(char *payload, u8 lag_id)
+{
+	MLXSW_REG_ZERO(sldr, payload);
+	mlxsw_reg_sldr_op_set(payload, MLXSW_REG_SLDR_OP_LAG_DESTROY);
+	mlxsw_reg_sldr_lag_id_set(payload, lag_id);
+}
+
+/* reg_sldr_num_ports
+ * The number of member ports of the LAG.
+ * Reserved for Create / Destroy operations
+ * For Add / Remove operations - indicates the number of ports in the list.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, sldr, num_ports, 0x04, 24, 8);
+
+/* reg_sldr_system_port
+ * System port.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, sldr, system_port, 0x08, 0, 16, 4, 0, false);
+
+static inline void mlxsw_reg_sldr_lag_add_port_pack(char *payload, u8 lag_id,
+						    u8 local_port)
+{
+	MLXSW_REG_ZERO(sldr, payload);
+	mlxsw_reg_sldr_op_set(payload, MLXSW_REG_SLDR_OP_LAG_ADD_PORT_LIST);
+	mlxsw_reg_sldr_lag_id_set(payload, lag_id);
+	mlxsw_reg_sldr_num_ports_set(payload, 1);
+	mlxsw_reg_sldr_system_port_set(payload, 0, local_port);
+}
+
+static inline void mlxsw_reg_sldr_lag_remove_port_pack(char *payload, u8 lag_id,
+						       u8 local_port)
+{
+	MLXSW_REG_ZERO(sldr, payload);
+	mlxsw_reg_sldr_op_set(payload, MLXSW_REG_SLDR_OP_LAG_REMOVE_PORT_LIST);
+	mlxsw_reg_sldr_lag_id_set(payload, lag_id);
+	mlxsw_reg_sldr_num_ports_set(payload, 1);
+	mlxsw_reg_sldr_system_port_set(payload, 0, local_port);
+}
+
+/* SLCR - Switch LAG Configuration 2 Register
+ * -------------------------------------------
+ * The Switch LAG Configuration register is used for configuring the
+ * LAG properties of the switch.
+ */
+#define MLXSW_REG_SLCR_ID 0x2015
+#define MLXSW_REG_SLCR_LEN 0x10
+
+static const struct mlxsw_reg_info mlxsw_reg_slcr = {
+	.id = MLXSW_REG_SLCR_ID,
+	.len = MLXSW_REG_SLCR_LEN,
+};
+
+enum mlxsw_reg_slcr_pp {
+	/* Global Configuration (for all ports) */
+	MLXSW_REG_SLCR_PP_GLOBAL,
+	/* Per port configuration, based on local_port field */
+	MLXSW_REG_SLCR_PP_PER_PORT,
+};
+
+/* reg_slcr_pp
+ * Per Port Configuration
+ * Note: Reading at Global mode results in reading port 1 configuration.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, slcr, pp, 0x00, 24, 1);
+
+/* reg_slcr_local_port
+ * Local port number
+ * Supported from CPU port
+ * Not supported from router port
+ * Reserved when pp = Global Configuration
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, slcr, local_port, 0x00, 16, 8);
+
+enum mlxsw_reg_slcr_type {
+	MLXSW_REG_SLCR_TYPE_CRC, /* default */
+	MLXSW_REG_SLCR_TYPE_XOR,
+	MLXSW_REG_SLCR_TYPE_RANDOM,
+};
+
+/* reg_slcr_type
+ * Hash type
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, slcr, type, 0x00, 0, 4);
+
+/* Ingress port */
+#define MLXSW_REG_SLCR_LAG_HASH_IN_PORT		BIT(0)
+/* SMAC - for IPv4 and IPv6 packets */
+#define MLXSW_REG_SLCR_LAG_HASH_SMAC_IP		BIT(1)
+/* SMAC - for non-IP packets */
+#define MLXSW_REG_SLCR_LAG_HASH_SMAC_NONIP	BIT(2)
+#define MLXSW_REG_SLCR_LAG_HASH_SMAC \
+	(MLXSW_REG_SLCR_LAG_HASH_SMAC_IP | \
+	 MLXSW_REG_SLCR_LAG_HASH_SMAC_NONIP)
+/* DMAC - for IPv4 and IPv6 packets */
+#define MLXSW_REG_SLCR_LAG_HASH_DMAC_IP		BIT(3)
+/* DMAC - for non-IP packets */
+#define MLXSW_REG_SLCR_LAG_HASH_DMAC_NONIP	BIT(4)
+#define MLXSW_REG_SLCR_LAG_HASH_DMAC \
+	(MLXSW_REG_SLCR_LAG_HASH_DMAC_IP | \
+	 MLXSW_REG_SLCR_LAG_HASH_DMAC_NONIP)
+/* Ethertype - for IPv4 and IPv6 packets */
+#define MLXSW_REG_SLCR_LAG_HASH_ETHERTYPE_IP	BIT(5)
+/* Ethertype - for non-IP packets */
+#define MLXSW_REG_SLCR_LAG_HASH_ETHERTYPE_NONIP	BIT(6)
+#define MLXSW_REG_SLCR_LAG_HASH_ETHERTYPE \
+	(MLXSW_REG_SLCR_LAG_HASH_ETHERTYPE_IP | \
+	 MLXSW_REG_SLCR_LAG_HASH_ETHERTYPE_NONIP)
+/* VLAN ID - for IPv4 and IPv6 packets */
+#define MLXSW_REG_SLCR_LAG_HASH_VLANID_IP	BIT(7)
+/* VLAN ID - for non-IP packets */
+#define MLXSW_REG_SLCR_LAG_HASH_VLANID_NONIP	BIT(8)
+#define MLXSW_REG_SLCR_LAG_HASH_VLANID \
+	(MLXSW_REG_SLCR_LAG_HASH_VLANID_IP | \
+	 MLXSW_REG_SLCR_LAG_HASH_VLANID_NONIP)
+/* Source IP address (can be IPv4 or IPv6) */
+#define MLXSW_REG_SLCR_LAG_HASH_SIP		BIT(9)
+/* Destination IP address (can be IPv4 or IPv6) */
+#define MLXSW_REG_SLCR_LAG_HASH_DIP		BIT(10)
+/* TCP/UDP source port */
+#define MLXSW_REG_SLCR_LAG_HASH_SPORT		BIT(11)
+/* TCP/UDP destination port*/
+#define MLXSW_REG_SLCR_LAG_HASH_DPORT		BIT(12)
+/* IPv4 Protocol/IPv6 Next Header */
+#define MLXSW_REG_SLCR_LAG_HASH_IPPROTO		BIT(13)
+/* IPv6 Flow label */
+#define MLXSW_REG_SLCR_LAG_HASH_FLOWLABEL	BIT(14)
+/* SID - FCoE source ID */
+#define MLXSW_REG_SLCR_LAG_HASH_FCOE_SID	BIT(15)
+/* DID - FCoE destination ID */
+#define MLXSW_REG_SLCR_LAG_HASH_FCOE_DID	BIT(16)
+/* OXID - FCoE originator exchange ID */
+#define MLXSW_REG_SLCR_LAG_HASH_FCOE_OXID	BIT(17)
+/* Destination QP number - for RoCE packets */
+#define MLXSW_REG_SLCR_LAG_HASH_ROCE_DQP	BIT(19)
+
+/* reg_slcr_lag_hash
+ * LAG hashing configuration. This is a bitmask, in which each set
+ * bit includes the corresponding item in the LAG hash calculation.
+ * The default lag_hash contains SMAC, DMAC, VLANID and
+ * Ethertype (for all packet types).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, slcr, lag_hash, 0x04, 0, 20);
+
+static inline void mlxsw_reg_slcr_pack(char *payload, u16 lag_hash)
+{
+	MLXSW_REG_ZERO(slcr, payload);
+	mlxsw_reg_slcr_pp_set(payload, MLXSW_REG_SLCR_PP_GLOBAL);
+	mlxsw_reg_slcr_type_set(payload, MLXSW_REG_SLCR_TYPE_XOR);
+	mlxsw_reg_slcr_lag_hash_set(payload, lag_hash);
+}
+
+/* SLCOR - Switch LAG Collector Register
+ * -------------------------------------
+ * The Switch LAG Collector register controls the Local Port membership
+ * in a LAG and enablement of the collector.
+ */
+#define MLXSW_REG_SLCOR_ID 0x2016
+#define MLXSW_REG_SLCOR_LEN 0x10
+
+static const struct mlxsw_reg_info mlxsw_reg_slcor = {
+	.id = MLXSW_REG_SLCOR_ID,
+	.len = MLXSW_REG_SLCOR_LEN,
+};
+
+enum mlxsw_reg_slcor_col {
+	/* Port is added with collector disabled */
+	MLXSW_REG_SLCOR_COL_LAG_ADD_PORT,
+	MLXSW_REG_SLCOR_COL_LAG_COLLECTOR_ENABLED,
+	MLXSW_REG_SLCOR_COL_LAG_COLLECTOR_DISABLED,
+	MLXSW_REG_SLCOR_COL_LAG_REMOVE_PORT,
+};
+
+/* reg_slcor_col
+ * Collector configuration
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, slcor, col, 0x00, 30, 2);
+
+/* reg_slcor_local_port
+ * Local port number
+ * Not supported for CPU port
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, slcor, local_port, 0x00, 16, 8);
+
+/* reg_slcor_lag_id
+ * LAG Identifier. Index into the LAG descriptor table.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, slcor, lag_id, 0x00, 0, 10);
+
+/* reg_slcor_port_index
+ * Port index in the LAG list. Only valid on Add Port to LAG col.
+ * Valid range is from 0 to cap_max_lag_members-1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, slcor, port_index, 0x04, 0, 10);
+
+static inline void mlxsw_reg_slcor_pack(char *payload,
+					u8 local_port, u16 lag_id,
+					enum mlxsw_reg_slcor_col col)
+{
+	MLXSW_REG_ZERO(slcor, payload);
+	mlxsw_reg_slcor_col_set(payload, col);
+	mlxsw_reg_slcor_local_port_set(payload, local_port);
+	mlxsw_reg_slcor_lag_id_set(payload, lag_id);
+}
+
+static inline void mlxsw_reg_slcor_port_add_pack(char *payload,
+						 u8 local_port, u16 lag_id,
+						 u8 port_index)
+{
+	mlxsw_reg_slcor_pack(payload, local_port, lag_id,
+			     MLXSW_REG_SLCOR_COL_LAG_ADD_PORT);
+	mlxsw_reg_slcor_port_index_set(payload, port_index);
+}
+
+static inline void mlxsw_reg_slcor_port_remove_pack(char *payload,
+						    u8 local_port, u16 lag_id)
+{
+	mlxsw_reg_slcor_pack(payload, local_port, lag_id,
+			     MLXSW_REG_SLCOR_COL_LAG_REMOVE_PORT);
+}
+
+static inline void mlxsw_reg_slcor_col_enable_pack(char *payload,
+						   u8 local_port, u16 lag_id)
+{
+	mlxsw_reg_slcor_pack(payload, local_port, lag_id,
+			     MLXSW_REG_SLCOR_COL_LAG_COLLECTOR_ENABLED);
+}
+
+static inline void mlxsw_reg_slcor_col_disable_pack(char *payload,
+						    u8 local_port, u16 lag_id)
+{
+	mlxsw_reg_slcor_pack(payload, local_port, lag_id,
+			     MLXSW_REG_SLCOR_COL_LAG_COLLECTOR_ENABLED);
+}
+
 /* SPMLR - Switch Port MAC Learning Register
  * -----------------------------------------
  * Controls the Switch MAC learning policy per port.
@@ -2653,6 +3023,12 @@ static inline const char *mlxsw_reg_id_str(u16 reg_id)
 		return "SFGC";
 	case MLXSW_REG_SFTR_ID:
 		return "SFTR";
+	case MLXSW_REG_SLDR_ID:
+		return "SLDR";
+	case MLXSW_REG_SLCR_ID:
+		return "SLCR";
+	case MLXSW_REG_SLCOR_ID:
+		return "SLCOR";
 	case MLXSW_REG_SPMLR_ID:
 		return "SPMLR";
 	case MLXSW_REG_SVFA_ID:

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

@@ -417,6 +417,10 @@ static netdev_tx_t mlxsw_sp_port_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static void mlxsw_sp_set_rx_mode(struct net_device *dev)
+{
+}
+
 static int mlxsw_sp_port_set_mac_address(struct net_device *dev, void *p)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
@@ -725,6 +729,7 @@ static const struct net_device_ops mlxsw_sp_port_netdev_ops = {
 	.ndo_open		= mlxsw_sp_port_open,
 	.ndo_stop		= mlxsw_sp_port_stop,
 	.ndo_start_xmit		= mlxsw_sp_port_xmit,
+	.ndo_set_rx_mode	= mlxsw_sp_set_rx_mode,
 	.ndo_set_mac_address	= mlxsw_sp_port_set_mac_address,
 	.ndo_change_mtu		= mlxsw_sp_port_change_mtu,
 	.ndo_get_stats64	= mlxsw_sp_port_get_stats64,
@@ -1707,6 +1712,22 @@ static int mlxsw_sp_flood_init(struct mlxsw_sp *mlxsw_sp)
 	return 0;
 }
 
+static int mlxsw_sp_lag_init(struct mlxsw_sp *mlxsw_sp)
+{
+	char slcr_pl[MLXSW_REG_SLCR_LEN];
+
+	mlxsw_reg_slcr_pack(slcr_pl, MLXSW_REG_SLCR_LAG_HASH_SMAC |
+				     MLXSW_REG_SLCR_LAG_HASH_DMAC |
+				     MLXSW_REG_SLCR_LAG_HASH_ETHERTYPE |
+				     MLXSW_REG_SLCR_LAG_HASH_VLANID |
+				     MLXSW_REG_SLCR_LAG_HASH_SIP |
+				     MLXSW_REG_SLCR_LAG_HASH_DIP |
+				     MLXSW_REG_SLCR_LAG_HASH_SPORT |
+				     MLXSW_REG_SLCR_LAG_HASH_DPORT |
+				     MLXSW_REG_SLCR_LAG_HASH_IPPROTO);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(slcr), slcr_pl);
+}
+
 static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core,
 			 const struct mlxsw_bus_info *mlxsw_bus_info)
 {
@@ -1752,6 +1773,12 @@ static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core,
 		goto err_buffers_init;
 	}
 
+	err = mlxsw_sp_lag_init(mlxsw_sp);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize LAG\n");
+		goto err_lag_init;
+	}
+
 	err = mlxsw_sp_switchdev_init(mlxsw_sp);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize switchdev\n");
@@ -1761,6 +1788,7 @@ static int mlxsw_sp_init(void *priv, struct mlxsw_core *mlxsw_core,
 	return 0;
 
 err_switchdev_init:
+err_lag_init:
 err_buffers_init:
 err_flood_init:
 	mlxsw_sp_traps_fini(mlxsw_sp);
@@ -1788,9 +1816,9 @@ static struct mlxsw_config_profile mlxsw_sp_config_profile = {
 	.used_max_vepa_channels		= 1,
 	.max_vepa_channels		= 0,
 	.used_max_lag			= 1,
-	.max_lag			= 64,
+	.max_lag			= MLXSW_SP_LAG_MAX,
 	.used_max_port_per_lag		= 1,
-	.max_port_per_lag		= 16,
+	.max_port_per_lag		= MLXSW_SP_PORT_PER_LAG_MAX,
 	.used_max_mid			= 1,
 	.max_mid			= 7000,
 	.used_max_pgt			= 1,
@@ -1889,19 +1917,245 @@ static void mlxsw_sp_master_bridge_dec(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp->master_bridge.dev = NULL;
 }
 
-static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
+static int mlxsw_sp_lag_create(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
+{
+	char sldr_pl[MLXSW_REG_SLDR_LEN];
+
+	mlxsw_reg_sldr_lag_create_pack(sldr_pl, lag_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl);
+}
+
+static int mlxsw_sp_lag_destroy(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
+{
+	char sldr_pl[MLXSW_REG_SLDR_LEN];
+
+	mlxsw_reg_sldr_lag_destroy_pack(sldr_pl, lag_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl);
+}
+
+static int mlxsw_sp_lag_col_port_add(struct mlxsw_sp_port *mlxsw_sp_port,
+				     u16 lag_id, u8 port_index)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char slcor_pl[MLXSW_REG_SLCOR_LEN];
+
+	mlxsw_reg_slcor_port_add_pack(slcor_pl, mlxsw_sp_port->local_port,
+				      lag_id, port_index);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(slcor), slcor_pl);
+}
+
+static int mlxsw_sp_lag_col_port_remove(struct mlxsw_sp_port *mlxsw_sp_port,
+					u16 lag_id)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char slcor_pl[MLXSW_REG_SLCOR_LEN];
+
+	mlxsw_reg_slcor_port_remove_pack(slcor_pl, mlxsw_sp_port->local_port,
+					 lag_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(slcor), slcor_pl);
+}
+
+static int mlxsw_sp_lag_col_port_enable(struct mlxsw_sp_port *mlxsw_sp_port,
+					u16 lag_id)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char slcor_pl[MLXSW_REG_SLCOR_LEN];
+
+	mlxsw_reg_slcor_col_enable_pack(slcor_pl, mlxsw_sp_port->local_port,
+					lag_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(slcor), slcor_pl);
+}
+
+static int mlxsw_sp_lag_col_port_disable(struct mlxsw_sp_port *mlxsw_sp_port,
+					 u16 lag_id)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char slcor_pl[MLXSW_REG_SLCOR_LEN];
+
+	mlxsw_reg_slcor_col_disable_pack(slcor_pl, mlxsw_sp_port->local_port,
+					 lag_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(slcor), slcor_pl);
+}
+
+static int mlxsw_sp_lag_index_get(struct mlxsw_sp *mlxsw_sp,
+				  struct net_device *lag_dev,
+				  u16 *p_lag_id)
+{
+	struct mlxsw_sp_upper *lag;
+	int free_lag_id = -1;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_LAG_MAX; i++) {
+		lag = mlxsw_sp_lag_get(mlxsw_sp, i);
+		if (lag->ref_count) {
+			if (lag->dev == lag_dev) {
+				*p_lag_id = i;
+				return 0;
+			}
+		} else if (free_lag_id < 0) {
+			free_lag_id = i;
+		}
+	}
+	if (free_lag_id < 0)
+		return -EBUSY;
+	*p_lag_id = free_lag_id;
+	return 0;
+}
+
+static bool
+mlxsw_sp_master_lag_check(struct mlxsw_sp *mlxsw_sp,
+			  struct net_device *lag_dev,
+			  struct netdev_lag_upper_info *lag_upper_info)
+{
+	u16 lag_id;
+
+	if (mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id) != 0)
+		return false;
+	if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH)
+		return false;
+	return true;
+}
+
+static int mlxsw_sp_port_lag_index_get(struct mlxsw_sp *mlxsw_sp,
+				       u16 lag_id, u8 *p_port_index)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP_PORT_PER_LAG_MAX; i++) {
+		if (!mlxsw_sp_port_lagged_get(mlxsw_sp, lag_id, i)) {
+			*p_port_index = i;
+			return 0;
+		}
+	}
+	return -EBUSY;
+}
+
+static int mlxsw_sp_port_lag_join(struct mlxsw_sp_port *mlxsw_sp_port,
+				  struct net_device *lag_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_upper *lag;
+	u16 lag_id;
+	u8 port_index;
+	int err;
+
+	err = mlxsw_sp_lag_index_get(mlxsw_sp, lag_dev, &lag_id);
+	if (err)
+		return err;
+	lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id);
+	if (!lag->ref_count) {
+		err = mlxsw_sp_lag_create(mlxsw_sp, lag_id);
+		if (err)
+			return err;
+		lag->dev = lag_dev;
+	}
+
+	err = mlxsw_sp_port_lag_index_get(mlxsw_sp, lag_id, &port_index);
+	if (err)
+		return err;
+	err = mlxsw_sp_lag_col_port_add(mlxsw_sp_port, lag_id, port_index);
+	if (err)
+		goto err_col_port_add;
+	err = mlxsw_sp_lag_col_port_enable(mlxsw_sp_port, lag_id);
+	if (err)
+		goto err_col_port_enable;
+
+	mlxsw_core_lag_mapping_set(mlxsw_sp->core, lag_id, port_index,
+				   mlxsw_sp_port->local_port);
+	mlxsw_sp_port->lag_id = lag_id;
+	mlxsw_sp_port->lagged = 1;
+	lag->ref_count++;
+	return 0;
+
+err_col_port_add:
+	if (!lag->ref_count)
+		mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
+err_col_port_enable:
+	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
+	return err;
+}
+
+static int mlxsw_sp_port_lag_leave(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct net_device *lag_dev)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	struct mlxsw_sp_upper *lag;
+	u16 lag_id = mlxsw_sp_port->lag_id;
+	int err;
+
+	if (!mlxsw_sp_port->lagged)
+		return 0;
+	lag = mlxsw_sp_lag_get(mlxsw_sp, lag_id);
+	WARN_ON(lag->ref_count == 0);
+
+	err = mlxsw_sp_lag_col_port_disable(mlxsw_sp_port, lag_id);
+	if (err)
+		return err;
+	mlxsw_sp_lag_col_port_remove(mlxsw_sp_port, lag_id);
+	if (err)
+		return err;
+
+	if (lag->ref_count == 1) {
+		err = mlxsw_sp_lag_destroy(mlxsw_sp, lag_id);
+		if (err)
+			return err;
+	}
+
+	mlxsw_core_lag_mapping_clear(mlxsw_sp->core, lag_id,
+				     mlxsw_sp_port->local_port);
+	mlxsw_sp_port->lagged = 0;
+	lag->ref_count--;
+	return 0;
+}
+
+static int mlxsw_sp_lag_dist_port_add(struct mlxsw_sp_port *mlxsw_sp_port,
+				      u16 lag_id)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char sldr_pl[MLXSW_REG_SLDR_LEN];
+
+	mlxsw_reg_sldr_lag_add_port_pack(sldr_pl, lag_id,
+					 mlxsw_sp_port->local_port);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl);
+}
+
+static int mlxsw_sp_lag_dist_port_remove(struct mlxsw_sp_port *mlxsw_sp_port,
+					 u16 lag_id)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char sldr_pl[MLXSW_REG_SLDR_LEN];
+
+	mlxsw_reg_sldr_lag_remove_port_pack(sldr_pl, lag_id,
+					    mlxsw_sp_port->local_port);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sldr), sldr_pl);
+}
+
+static int mlxsw_sp_port_lag_tx_en_set(struct mlxsw_sp_port *mlxsw_sp_port,
+				       bool lag_tx_enabled)
+{
+	if (lag_tx_enabled)
+		return mlxsw_sp_lag_dist_port_add(mlxsw_sp_port,
+						  mlxsw_sp_port->lag_id);
+	else
+		return mlxsw_sp_lag_dist_port_remove(mlxsw_sp_port,
+						     mlxsw_sp_port->lag_id);
+}
+
+static int mlxsw_sp_port_lag_changed(struct mlxsw_sp_port *mlxsw_sp_port,
+				     struct netdev_lag_lower_state_info *info)
+{
+	return mlxsw_sp_port_lag_tx_en_set(mlxsw_sp_port, info->tx_enabled);
+}
+
+static int mlxsw_sp_netdevice_port_upper_event(struct net_device *dev,
 					       unsigned long event, void *ptr)
 {
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct netdev_notifier_changeupper_info *info;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct net_device *upper_dev;
 	struct mlxsw_sp *mlxsw_sp;
 	int err;
 
-	if (!mlxsw_sp_port_dev_check(dev))
-		return NOTIFY_DONE;
-
 	mlxsw_sp_port = netdev_priv(dev);
 	mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	info = ptr;
@@ -1909,16 +2163,22 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
+		if (!info->master || !info->linking)
+			break;
 		/* HW limitation forbids to put ports to multiple bridges. */
-		if (info->master && info->linking &&
-		    netif_is_bridge_master(upper_dev) &&
+		if (netif_is_bridge_master(upper_dev) &&
 		    !mlxsw_sp_master_bridge_check(mlxsw_sp, upper_dev))
 			return NOTIFY_BAD;
+		if (netif_is_lag_master(upper_dev) &&
+		    !mlxsw_sp_master_lag_check(mlxsw_sp, upper_dev,
+					       info->upper_info))
+			return NOTIFY_BAD;
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (info->master &&
-		    netif_is_bridge_master(upper_dev)) {
+		if (!info->master)
+			break;
+		if (netif_is_bridge_master(upper_dev)) {
 			if (info->linking) {
 				err = mlxsw_sp_port_bridge_join(mlxsw_sp_port);
 				if (err)
@@ -1932,6 +2192,22 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 				mlxsw_sp_port->bridged = 0;
 				mlxsw_sp_master_bridge_dec(mlxsw_sp, upper_dev);
 			}
+		} else if (netif_is_lag_master(upper_dev)) {
+			if (info->linking) {
+				err = mlxsw_sp_port_lag_join(mlxsw_sp_port,
+							     upper_dev);
+				if (err) {
+					netdev_err(dev, "Failed to join link aggregation\n");
+					return NOTIFY_BAD;
+				}
+			} else {
+				err = mlxsw_sp_port_lag_leave(mlxsw_sp_port,
+							      upper_dev);
+				if (err) {
+					netdev_err(dev, "Failed to leave link aggregation\n");
+					return NOTIFY_BAD;
+				}
+			}
 		}
 		break;
 	}
@@ -1939,6 +2215,76 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 	return NOTIFY_DONE;
 }
 
+static int mlxsw_sp_netdevice_port_lower_event(struct net_device *dev,
+					       unsigned long event, void *ptr)
+{
+	struct netdev_notifier_changelowerstate_info *info;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	int err;
+
+	mlxsw_sp_port = netdev_priv(dev);
+	info = ptr;
+
+	switch (event) {
+	case NETDEV_CHANGELOWERSTATE:
+		if (netif_is_lag_port(dev) && mlxsw_sp_port->lagged) {
+			err = mlxsw_sp_port_lag_changed(mlxsw_sp_port,
+							info->lower_state_info);
+			if (err)
+				netdev_err(dev, "Failed to reflect link aggregation lower state change\n");
+		}
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int mlxsw_sp_netdevice_port_event(struct net_device *dev,
+					 unsigned long event, void *ptr)
+{
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+	case NETDEV_CHANGEUPPER:
+		return mlxsw_sp_netdevice_port_upper_event(dev, event, ptr);
+	case NETDEV_CHANGELOWERSTATE:
+		return mlxsw_sp_netdevice_port_lower_event(dev, event, ptr);
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int mlxsw_sp_netdevice_lag_event(struct net_device *lag_dev,
+					unsigned long event, void *ptr)
+{
+	struct net_device *dev;
+	struct list_head *iter;
+	int ret;
+
+	netdev_for_each_lower_dev(lag_dev, dev, iter) {
+		if (mlxsw_sp_port_dev_check(dev)) {
+			ret = mlxsw_sp_netdevice_port_event(dev, event, ptr);
+			if (ret == NOTIFY_BAD)
+				return ret;
+		}
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
+				    unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (mlxsw_sp_port_dev_check(dev))
+		return mlxsw_sp_netdevice_port_event(dev, event, ptr);
+
+	if (netif_is_lag_master(dev))
+		return mlxsw_sp_netdevice_lag_event(dev, event, ptr);
+
+	return NOTIFY_DONE;
+}
+
 static struct notifier_block mlxsw_sp_netdevice_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_netdevice_event,
 };

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

@@ -46,9 +46,16 @@
 #include "core.h"
 
 #define MLXSW_SP_VFID_BASE VLAN_N_VID
+#define MLXSW_SP_LAG_MAX 64
+#define MLXSW_SP_PORT_PER_LAG_MAX 16
 
 struct mlxsw_sp_port;
 
+struct mlxsw_sp_upper {
+	struct net_device *dev;
+	unsigned int ref_count;
+};
+
 struct mlxsw_sp {
 	unsigned long active_vfids[BITS_TO_LONGS(VLAN_N_VID)];
 	unsigned long active_fids[BITS_TO_LONGS(VLAN_N_VID)];
@@ -63,12 +70,16 @@ struct mlxsw_sp {
 	} fdb_notify;
 #define MLXSW_SP_DEFAULT_AGEING_TIME 300
 	u32 ageing_time;
-	struct {
-		struct net_device *dev;
-		unsigned int ref_count;
-	} master_bridge;
+	struct mlxsw_sp_upper master_bridge;
+	struct mlxsw_sp_upper lags[MLXSW_SP_LAG_MAX];
 };
 
+static inline struct mlxsw_sp_upper *
+mlxsw_sp_lag_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id)
+{
+	return &mlxsw_sp->lags[lag_id];
+}
+
 struct mlxsw_sp_port_pcpu_stats {
 	u64			rx_packets;
 	u64			rx_bytes;
@@ -87,8 +98,10 @@ struct mlxsw_sp_port {
 	u8 learning:1,
 	   learning_sync:1,
 	   uc_flood:1,
-	   bridged:1;
+	   bridged:1,
+	   lagged:1;
 	u16 pvid;
+	u16 lag_id;
 	/* 802.1Q bridge VLANs */
 	unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)];
 	/* VLAN interfaces */
@@ -96,6 +109,18 @@ struct mlxsw_sp_port {
 	u16 nr_vfids;
 };
 
+static inline struct mlxsw_sp_port *
+mlxsw_sp_port_lagged_get(struct mlxsw_sp *mlxsw_sp, u16 lag_id, u8 port_index)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	u8 local_port;
+
+	local_port = mlxsw_core_lag_mapping_get(mlxsw_sp->core,
+						lag_id, port_index);
+	mlxsw_sp_port = mlxsw_sp->ports[local_port];
+	return mlxsw_sp_port && mlxsw_sp_port->lagged ? mlxsw_sp_port : NULL;
+}
+
 enum mlxsw_sp_flood_table {
 	MLXSW_SP_FLOOD_TABLE_UC,
 	MLXSW_SP_FLOOD_TABLE_BM,

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

@@ -490,32 +490,56 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 					 untagged_flag, pvid_flag);
 }
 
-static int mlxsw_sp_port_fdb_op(struct mlxsw_sp_port *mlxsw_sp_port,
+static enum mlxsw_reg_sfd_rec_policy mlxsw_sp_sfd_rec_policy(bool dynamic)
+{
+	return dynamic ? MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_INGRESS :
+			 MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY;
+}
+
+static enum mlxsw_reg_sfd_op mlxsw_sp_sfd_op(bool adding)
+{
+	return adding ? MLXSW_REG_SFD_OP_WRITE_EDIT :
+			MLXSW_REG_SFD_OP_WRITE_REMOVE;
+}
+
+static int mlxsw_sp_port_fdb_uc_op(struct mlxsw_sp_port *mlxsw_sp_port,
 				   const char *mac, u16 vid, bool adding,
 				   bool dynamic)
 {
-	enum mlxsw_reg_sfd_rec_policy policy;
-	enum mlxsw_reg_sfd_op op;
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char *sfd_pl;
 	int err;
 
-	if (!vid)
-		vid = mlxsw_sp_port->pvid;
-
 	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
 	if (!sfd_pl)
 		return -ENOMEM;
 
-	policy = dynamic ? MLXSW_REG_SFD_REC_POLICY_DYNAMIC_ENTRY_INGRESS :
-			   MLXSW_REG_SFD_REC_POLICY_STATIC_ENTRY;
-	op = adding ? MLXSW_REG_SFD_OP_WRITE_EDIT :
-		      MLXSW_REG_SFD_OP_WRITE_REMOVE;
-	mlxsw_reg_sfd_pack(sfd_pl, op, 0);
-	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, policy,
+	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
+	mlxsw_reg_sfd_uc_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
 			      mac, vid, MLXSW_REG_SFD_REC_ACTION_NOP,
 			      mlxsw_sp_port->local_port);
-	err = mlxsw_reg_write(mlxsw_sp_port->mlxsw_sp->core, MLXSW_REG(sfd),
-			      sfd_pl);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
+	kfree(sfd_pl);
+
+	return err;
+}
+
+static int mlxsw_sp_port_fdb_uc_lag_op(struct mlxsw_sp *mlxsw_sp, u16 lag_id,
+				       const char *mac, u16 vid, bool adding,
+				       bool dynamic)
+{
+	char *sfd_pl;
+	int err;
+
+	sfd_pl = kmalloc(MLXSW_REG_SFD_LEN, GFP_KERNEL);
+	if (!sfd_pl)
+		return -ENOMEM;
+
+	mlxsw_reg_sfd_pack(sfd_pl, mlxsw_sp_sfd_op(adding), 0);
+	mlxsw_reg_sfd_uc_lag_pack(sfd_pl, 0, mlxsw_sp_sfd_rec_policy(dynamic),
+				  mac, vid, MLXSW_REG_SFD_REC_ACTION_NOP,
+				  lag_id);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
 	kfree(sfd_pl);
 
 	return err;
@@ -526,11 +550,21 @@ mlxsw_sp_port_fdb_static_add(struct mlxsw_sp_port *mlxsw_sp_port,
 			     const struct switchdev_obj_port_fdb *fdb,
 			     struct switchdev_trans *trans)
 {
+	u16 vid = fdb->vid;
+
 	if (switchdev_trans_ph_prepare(trans))
 		return 0;
 
-	return mlxsw_sp_port_fdb_op(mlxsw_sp_port, fdb->addr, fdb->vid,
-				    true, false);
+	if (!vid)
+		vid = mlxsw_sp_port->pvid;
+
+	if (!mlxsw_sp_port->lagged)
+		return mlxsw_sp_port_fdb_uc_op(mlxsw_sp_port,
+					       fdb->addr, vid, true, false);
+	else
+		return mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp_port->mlxsw_sp,
+						   mlxsw_sp_port->lag_id,
+						   fdb->addr, vid, true, false);
 }
 
 static int mlxsw_sp_port_obj_add(struct net_device *dev,
@@ -645,7 +679,14 @@ static int
 mlxsw_sp_port_fdb_static_del(struct mlxsw_sp_port *mlxsw_sp_port,
 			     const struct switchdev_obj_port_fdb *fdb)
 {
-	return mlxsw_sp_port_fdb_op(mlxsw_sp_port, fdb->addr, fdb->vid,
+	if (!mlxsw_sp_port->lagged)
+		return mlxsw_sp_port_fdb_uc_op(mlxsw_sp_port,
+					       fdb->addr, fdb->vid,
+					       false, false);
+	else
+		return mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp_port->mlxsw_sp,
+						   mlxsw_sp_port->lag_id,
+						   fdb->addr, fdb->vid,
 						   false, false);
 }
 
@@ -672,14 +713,30 @@ static int mlxsw_sp_port_obj_del(struct net_device *dev,
 	return err;
 }
 
+static struct mlxsw_sp_port *mlxsw_sp_lag_rep_port(struct mlxsw_sp *mlxsw_sp,
+						   u16 lag_id)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	int i;
+
+	for (i = 0; i < MLXSW_SP_PORT_PER_LAG_MAX; i++) {
+		mlxsw_sp_port = mlxsw_sp_port_lagged_get(mlxsw_sp, lag_id, i);
+		if (mlxsw_sp_port)
+			return mlxsw_sp_port;
+	}
+	return NULL;
+}
+
 static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port,
 				  struct switchdev_obj_port_fdb *fdb,
 				  switchdev_obj_dump_cb_t *cb)
 {
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	char *sfd_pl;
 	char mac[ETH_ALEN];
 	u16 vid;
 	u8 local_port;
+	u16 lag_id;
 	u8 num_rec;
 	int stored_err = 0;
 	int i;
@@ -692,8 +749,7 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_reg_sfd_pack(sfd_pl, MLXSW_REG_SFD_OP_QUERY_DUMP, 0);
 	do {
 		mlxsw_reg_sfd_num_rec_set(sfd_pl, MLXSW_REG_SFD_REC_MAX_COUNT);
-		err = mlxsw_reg_query(mlxsw_sp_port->mlxsw_sp->core,
-				      MLXSW_REG(sfd), sfd_pl);
+		err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(sfd), sfd_pl);
 		if (err)
 			goto out;
 
@@ -718,6 +774,20 @@ static int mlxsw_sp_port_fdb_dump(struct mlxsw_sp_port *mlxsw_sp_port,
 					if (err)
 						stored_err = err;
 				}
+				break;
+			case MLXSW_REG_SFD_REC_TYPE_UNICAST_LAG:
+				mlxsw_reg_sfd_uc_lag_unpack(sfd_pl, i,
+							    mac, &vid, &lag_id);
+				if (mlxsw_sp_port ==
+				    mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id)) {
+					ether_addr_copy(fdb->addr, mac);
+					fdb->ndm_state = NUD_REACHABLE;
+					fdb->vid = vid;
+					err = cb(&fdb->obj);
+					if (err)
+						stored_err = err;
+				}
+				break;
 			}
 		}
 	} while (num_rec == MLXSW_REG_SFD_REC_MAX_COUNT);
@@ -779,6 +849,21 @@ static const struct switchdev_ops mlxsw_sp_port_switchdev_ops = {
 	.switchdev_port_obj_dump	= mlxsw_sp_port_obj_dump,
 };
 
+static void mlxsw_sp_fdb_call_notifiers(bool learning, bool learning_sync,
+					bool adding, char *mac, u16 vid,
+					struct net_device *dev)
+{
+	struct switchdev_notifier_fdb_info info;
+	unsigned long notifier_type;
+
+	if (learning && learning_sync) {
+		info.addr = mac;
+		info.vid = vid;
+		notifier_type = adding ? SWITCHDEV_FDB_ADD : SWITCHDEV_FDB_DEL;
+		call_switchdev_notifiers(notifier_type, dev, &info.info);
+	}
+}
+
 static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 					    char *sfn_pl, int rec_index,
 					    bool adding)
@@ -796,7 +881,7 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 		return;
 	}
 
-	err = mlxsw_sp_port_fdb_op(mlxsw_sp_port, mac, vid,
+	err = mlxsw_sp_port_fdb_uc_op(mlxsw_sp_port, mac, vid,
 				      adding && mlxsw_sp_port->learning, true);
 	if (err) {
 		if (net_ratelimit())
@@ -804,16 +889,41 @@ static void mlxsw_sp_fdb_notify_mac_process(struct mlxsw_sp *mlxsw_sp,
 		return;
 	}
 
-	if (mlxsw_sp_port->learning && mlxsw_sp_port->learning_sync) {
-		struct switchdev_notifier_fdb_info info;
-		unsigned long notifier_type;
+	mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning,
+				    mlxsw_sp_port->learning_sync,
+				    adding, mac, vid, mlxsw_sp_port->dev);
+}
 
-		info.addr = mac;
-		info.vid = vid;
-		notifier_type = adding ? SWITCHDEV_FDB_ADD : SWITCHDEV_FDB_DEL;
-		call_switchdev_notifiers(notifier_type, mlxsw_sp_port->dev,
-					 &info.info);
+static void mlxsw_sp_fdb_notify_mac_lag_process(struct mlxsw_sp *mlxsw_sp,
+						char *sfn_pl, int rec_index,
+						bool adding)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	char mac[ETH_ALEN];
+	u16 lag_id;
+	u16 vid;
+	int err;
+
+	mlxsw_reg_sfn_mac_lag_unpack(sfn_pl, rec_index, mac, &vid, &lag_id);
+	mlxsw_sp_port = mlxsw_sp_lag_rep_port(mlxsw_sp, lag_id);
+	if (!mlxsw_sp_port) {
+		dev_err_ratelimited(mlxsw_sp->bus_info->dev, "Cannot find port representor for LAG\n");
+		return;
 	}
+
+	err = mlxsw_sp_port_fdb_uc_lag_op(mlxsw_sp, lag_id, mac, vid,
+					  adding && mlxsw_sp_port->learning,
+					  true);
+	if (err) {
+		if (net_ratelimit())
+			netdev_err(mlxsw_sp_port->dev, "Failed to set FDB entry\n");
+		return;
+	}
+
+	mlxsw_sp_fdb_call_notifiers(mlxsw_sp_port->learning,
+				    mlxsw_sp_port->learning_sync,
+				    adding, mac, vid,
+				    mlxsw_sp_lag_get(mlxsw_sp, lag_id)->dev);
 }
 
 static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp,
@@ -828,6 +938,14 @@ static void mlxsw_sp_fdb_notify_rec_process(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_fdb_notify_mac_process(mlxsw_sp, sfn_pl,
 						rec_index, false);
 		break;
+	case MLXSW_REG_SFN_REC_TYPE_LEARNED_MAC_LAG:
+		mlxsw_sp_fdb_notify_mac_lag_process(mlxsw_sp, sfn_pl,
+						    rec_index, true);
+		break;
+	case MLXSW_REG_SFN_REC_TYPE_AGED_OUT_MAC_LAG:
+		mlxsw_sp_fdb_notify_mac_lag_process(mlxsw_sp, sfn_pl,
+						    rec_index, false);
+		break;
 	}
 }
 

drivers/net/team/team.c

@@ -91,10 +91,24 @@ void team_modeop_port_change_dev_addr(struct team *team,
 }
 EXPORT_SYMBOL(team_modeop_port_change_dev_addr);
 
+static void team_lower_state_changed(struct team_port *port)
+{
+	struct netdev_lag_lower_state_info info;
+
+	info.link_up = port->linkup;
+	info.tx_enabled = team_port_enabled(port);
+	netdev_lower_state_changed(port->dev, &info);
+}
+
 static void team_refresh_port_linkup(struct team_port *port)
 {
-	port->linkup = port->user.linkup_enabled ? port->user.linkup :
+	bool new_linkup = port->user.linkup_enabled ? port->user.linkup :
 						      port->state.linkup;
+
+	if (port->linkup != new_linkup) {
+		port->linkup = new_linkup;
+		team_lower_state_changed(port);
+	}
 }
 
 
@@ -932,6 +946,7 @@ static void team_port_enable(struct team *team,
 		team->ops.port_enabled(team, port);
 	team_notify_peers(team);
 	team_mcast_rejoin(team);
+	team_lower_state_changed(port);
 }
 
 static void __reconstruct_port_hlist(struct team *team, int rm_index)
@@ -963,6 +978,7 @@ static void team_port_disable(struct team *team,
 	team_adjust_ops(team);
 	team_notify_peers(team);
 	team_mcast_rejoin(team);
+	team_lower_state_changed(port);
 }
 
 #define TEAM_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \
@@ -1078,23 +1094,24 @@ static void team_port_disable_netpoll(struct team_port *port)
 }
 #endif
 
-static int team_upper_dev_link(struct net_device *dev,
-			       struct net_device *port_dev)
+static int team_upper_dev_link(struct team *team, struct team_port *port)
 {
+	struct netdev_lag_upper_info lag_upper_info;
 	int err;
 
-	err = netdev_master_upper_dev_link(port_dev, dev);
+	lag_upper_info.tx_type = team->mode->lag_tx_type;
+	err = netdev_master_upper_dev_link(port->dev, team->dev, NULL,
+					   &lag_upper_info);
 	if (err)
 		return err;
-	port_dev->priv_flags |= IFF_TEAM_PORT;
+	port->dev->priv_flags |= IFF_TEAM_PORT;
 	return 0;
 }
 
-static void team_upper_dev_unlink(struct net_device *dev,
-				  struct net_device *port_dev)
+static void team_upper_dev_unlink(struct team *team, struct team_port *port)
 {
-	netdev_upper_dev_unlink(port_dev, dev);
-	port_dev->priv_flags &= ~IFF_TEAM_PORT;
+	netdev_upper_dev_unlink(port->dev, team->dev);
+	port->dev->priv_flags &= ~IFF_TEAM_PORT;
 }
 
 static void __team_port_change_port_added(struct team_port *port, bool linkup);
@@ -1194,7 +1211,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 		goto err_handler_register;
 	}
 
-	err = team_upper_dev_link(dev, port_dev);
+	err = team_upper_dev_link(team, port);
 	if (err) {
 		netdev_err(dev, "Device %s failed to set upper link\n",
 			   portname);
@@ -1220,7 +1237,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev)
 	return 0;
 
 err_option_port_add:
-	team_upper_dev_unlink(dev, port_dev);
+	team_upper_dev_unlink(team, port);
 
 err_set_upper_link:
 	netdev_rx_handler_unregister(port_dev);
@@ -1264,7 +1281,7 @@ static int team_port_del(struct team *team, struct net_device *port_dev)
 
 	team_port_disable(team, port);
 	list_del_rcu(&port->list);
-	team_upper_dev_unlink(dev, port_dev);
+	team_upper_dev_unlink(team, port);
 	netdev_rx_handler_unregister(port_dev);
 	team_port_disable_netpoll(port);
 	vlan_vids_del_by_dev(port_dev, dev);
@@ -2054,6 +2071,7 @@ static void team_setup(struct net_device *dev)
 	dev->flags |= IFF_MULTICAST;
 	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
 	dev->priv_flags |= IFF_NO_QUEUE;
+	dev->priv_flags |= IFF_TEAM;
 
 	/*
 	 * Indicate we support unicast address filtering. That way core won't
@@ -2420,9 +2438,13 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 	struct nlattr *nl_option;
 	LIST_HEAD(opt_inst_list);
 
+	rtnl_lock();
+
 	team = team_nl_team_get(info);
-	if (!team)
-		return -EINVAL;
+	if (!team) {
+		err = -EINVAL;
+		goto rtnl_unlock;
+	}
 
 	err = -EINVAL;
 	if (!info->attrs[TEAM_ATTR_LIST_OPTION]) {
@@ -2549,7 +2571,8 @@ static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
 
 team_put:
 	team_nl_team_put(team);
-
+rtnl_unlock:
+	rtnl_unlock();
 	return err;
 }
 

drivers/net/team/team_mode_activebackup.c

@@ -127,6 +127,7 @@ static const struct team_mode ab_mode = {
 	.owner		= THIS_MODULE,
 	.priv_size	= sizeof(struct ab_priv),
 	.ops		= &ab_mode_ops,
+	.lag_tx_type	= NETDEV_LAG_TX_TYPE_ACTIVEBACKUP,
 };
 
 static int __init ab_init_module(void)

drivers/net/team/team_mode_broadcast.c

@@ -56,6 +56,7 @@ static const struct team_mode bc_mode = {
 	.kind		= "broadcast",
 	.owner		= THIS_MODULE,
 	.ops		= &bc_mode_ops,
+	.lag_tx_type	= NETDEV_LAG_TX_TYPE_BROADCAST,
 };
 
 static int __init bc_init_module(void)

drivers/net/team/team_mode_loadbalance.c

@@ -661,6 +661,7 @@ static const struct team_mode lb_mode = {
 	.priv_size	= sizeof(struct lb_priv),
 	.port_priv_size	= sizeof(struct lb_port_priv),
 	.ops		= &lb_mode_ops,
+	.lag_tx_type	= NETDEV_LAG_TX_TYPE_HASH,
 };
 
 static int __init lb_init_module(void)

drivers/net/team/team_mode_random.c

@@ -46,6 +46,7 @@ static const struct team_mode rnd_mode = {
 	.kind		= "random",
 	.owner		= THIS_MODULE,
 	.ops		= &rnd_mode_ops,
+	.lag_tx_type	= NETDEV_LAG_TX_TYPE_RANDOM,
 };
 
 static int __init rnd_init_module(void)

drivers/net/team/team_mode_roundrobin.c

@@ -58,6 +58,7 @@ static const struct team_mode rr_mode = {
 	.owner		= THIS_MODULE,
 	.priv_size	= sizeof(struct rr_priv),
 	.ops		= &rr_mode_ops,
+	.lag_tx_type	= NETDEV_LAG_TX_TYPE_ROUNDROBIN,
 };
 
 static int __init rr_init_module(void)

drivers/net/vrf.c

@@ -624,7 +624,7 @@ static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev)
 		goto out_fail;
 	}
 
-	ret = netdev_master_upper_dev_link(port_dev, dev);
+	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
 	if (ret < 0)
 		goto out_unregister;
 

include/linux/if_team.h

@@ -164,6 +164,7 @@ struct team_mode {
 	size_t priv_size;
 	size_t port_priv_size;
 	const struct team_mode_ops *ops;
+	enum netdev_lag_tx_type lag_tx_type;
 };
 
 #define TEAM_PORT_HASHBITS 4

include/linux/netdevice.h

@@ -1273,6 +1273,7 @@ struct net_device_ops {
  * @IFF_NO_QUEUE: device can run without qdisc attached
  * @IFF_OPENVSWITCH: device is a Open vSwitch master
  * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device
+ * @IFF_TEAM: device is a team device
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1299,6 +1300,7 @@ enum netdev_priv_flags {
 	IFF_NO_QUEUE			= 1<<21,
 	IFF_OPENVSWITCH			= 1<<22,
 	IFF_L3MDEV_SLAVE		= 1<<23,
+	IFF_TEAM			= 1<<24,
 };
 
 #define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
@@ -1325,6 +1327,7 @@ enum netdev_priv_flags {
 #define IFF_NO_QUEUE			IFF_NO_QUEUE
 #define IFF_OPENVSWITCH			IFF_OPENVSWITCH
 #define IFF_L3MDEV_SLAVE		IFF_L3MDEV_SLAVE
+#define IFF_TEAM			IFF_TEAM
 
 /**
  *	struct net_device - The DEVICE structure.
@@ -2107,6 +2110,24 @@ struct pcpu_sw_netstats {
 #define netdev_alloc_pcpu_stats(type)					\
 	__netdev_alloc_pcpu_stats(type, GFP_KERNEL);
 
+enum netdev_lag_tx_type {
+	NETDEV_LAG_TX_TYPE_UNKNOWN,
+	NETDEV_LAG_TX_TYPE_RANDOM,
+	NETDEV_LAG_TX_TYPE_BROADCAST,
+	NETDEV_LAG_TX_TYPE_ROUNDROBIN,
+	NETDEV_LAG_TX_TYPE_ACTIVEBACKUP,
+	NETDEV_LAG_TX_TYPE_HASH,
+};
+
+struct netdev_lag_upper_info {
+	enum netdev_lag_tx_type tx_type;
+};
+
+struct netdev_lag_lower_state_info {
+	u8 link_up : 1,
+	   tx_enabled : 1;
+};
+
 #include <linux/notifier.h>
 
 /* netdevice notifier chain. Please remember to update the rtnetlink
@@ -2142,6 +2163,7 @@ struct pcpu_sw_netstats {
 #define NETDEV_CHANGEINFODATA	0x0018
 #define NETDEV_BONDING_INFO	0x0019
 #define NETDEV_PRECHANGEUPPER	0x001A
+#define NETDEV_CHANGELOWERSTATE	0x001B
 
 int register_netdevice_notifier(struct notifier_block *nb);
 int unregister_netdevice_notifier(struct notifier_block *nb);
@@ -2160,6 +2182,12 @@ struct netdev_notifier_changeupper_info {
 	struct net_device *upper_dev; /* new upper dev */
 	bool master; /* is upper dev master */
 	bool linking; /* is the nofication for link or unlink */
+	void *upper_info; /* upper dev info */
+};
+
+struct netdev_notifier_changelowerstate_info {
+	struct netdev_notifier_info info; /* must be first */
+	void *lower_state_info; /* is lower dev state */
 };
 
 static inline void netdev_notifier_info_init(struct netdev_notifier_info *info,
@@ -3616,15 +3644,15 @@ struct net_device *netdev_master_upper_dev_get(struct net_device *dev);
 struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev);
 int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev);
 int netdev_master_upper_dev_link(struct net_device *dev,
-				 struct net_device *upper_dev);
-int netdev_master_upper_dev_link_private(struct net_device *dev,
 				 struct net_device *upper_dev,
-					 void *private);
+				 void *upper_priv, void *upper_info);
 void netdev_upper_dev_unlink(struct net_device *dev,
 			     struct net_device *upper_dev);
 void netdev_adjacent_rename_links(struct net_device *dev, char *oldname);
 void *netdev_lower_dev_get_private(struct net_device *dev,
 				   struct net_device *lower_dev);
+void netdev_lower_state_changed(struct net_device *lower_dev,
+				void *lower_state_info);
 
 /* RSS keys are 40 or 52 bytes long */
 #define NETDEV_RSS_KEY_LEN 52
@@ -3889,6 +3917,26 @@ static inline bool netif_is_ovs_master(const struct net_device *dev)
 	return dev->priv_flags & IFF_OPENVSWITCH;
 }
 
+static inline bool netif_is_team_master(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_TEAM;
+}
+
+static inline bool netif_is_team_port(struct net_device *dev)
+{
+	return dev->priv_flags & IFF_TEAM_PORT;
+}
+
+static inline bool netif_is_lag_master(struct net_device *dev)
+{
+	return netif_is_bond_master(dev) || netif_is_team_master(dev);
+}
+
+static inline bool netif_is_lag_port(struct net_device *dev)
+{
+	return netif_is_bond_slave(dev) || netif_is_team_port(dev);
+}
+
 /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */
 static inline void netif_keep_dst(struct net_device *dev)
 {

include/net/bonding.h

@@ -165,7 +165,8 @@ struct slave {
 	u8     backup:1,   /* indicates backup slave. Value corresponds with
 			      BOND_STATE_ACTIVE and BOND_STATE_BACKUP */
 	       inactive:1, /* indicates inactive slave */
-	       should_notify:1; /* indicateds whether the state changed */
+	       should_notify:1, /* indicates whether the state changed */
+	       should_notify_link:1; /* indicates whether the link changed */
 	u8     duplex;
 	u32    original_mtu;
 	u32    link_failure_count;
@@ -246,6 +247,7 @@ struct bonding {
 	((struct slave *) rtnl_dereference(dev->rx_handler_data))
 
 void bond_queue_slave_event(struct slave *slave);
+void bond_lower_state_changed(struct slave *slave);
 
 struct bond_vlan_tag {
 	__be16		vlan_proto;
@@ -327,6 +329,7 @@ static inline void bond_set_active_slave(struct slave *slave)
 	if (slave->backup) {
 		slave->backup = 0;
 		bond_queue_slave_event(slave);
+		bond_lower_state_changed(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
@@ -336,6 +339,7 @@ static inline void bond_set_backup_slave(struct slave *slave)
 	if (!slave->backup) {
 		slave->backup = 1;
 		bond_queue_slave_event(slave);
+		bond_lower_state_changed(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 	}
 }
@@ -348,6 +352,7 @@ static inline void bond_set_slave_state(struct slave *slave,
 
 	slave->backup = slave_state;
 	if (notify) {
+		bond_lower_state_changed(slave);
 		rtmsg_ifinfo(RTM_NEWLINK, slave->dev, 0, GFP_ATOMIC);
 		bond_queue_slave_event(slave);
 		slave->should_notify = 0;
@@ -379,6 +384,7 @@ static inline void bond_slave_state_notify(struct bonding *bond)
 
 	bond_for_each_slave(bond, tmp, iter) {
 		if (tmp->should_notify) {
+			bond_lower_state_changed(tmp);
 			rtmsg_ifinfo(RTM_NEWLINK, tmp->dev, 0, GFP_ATOMIC);
 			tmp->should_notify = 0;
 		}
@@ -504,10 +510,37 @@ static inline bool bond_is_slave_inactive(struct slave *slave)
 	return slave->inactive;
 }
 
-static inline void bond_set_slave_link_state(struct slave *slave, int state)
+static inline void bond_set_slave_link_state(struct slave *slave, int state,
+					     bool notify)
 {
+	if (slave->link == state)
+		return;
+
 	slave->link = state;
+	if (notify) {
 		bond_queue_slave_event(slave);
+		bond_lower_state_changed(slave);
+		slave->should_notify_link = 0;
+	} else {
+		if (slave->should_notify_link)
+			slave->should_notify_link = 0;
+		else
+			slave->should_notify_link = 1;
+	}
+}
+
+static inline void bond_slave_link_notify(struct bonding *bond)
+{
+	struct list_head *iter;
+	struct slave *tmp;
+
+	bond_for_each_slave(bond, tmp, iter) {
+		if (tmp->should_notify_link) {
+			bond_queue_slave_event(tmp);
+			bond_lower_state_changed(tmp);
+			tmp->should_notify_link = 0;
+		}
+	}
 }
 
 static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be32 local)

lib/netdev-notifier-error-inject.c

@@ -18,6 +18,7 @@ static struct notifier_err_inject netdev_notifier_err_inject = {
 		{ NOTIFIER_ERR_INJECT_ACTION(NETDEV_POST_INIT) },
 		{ NOTIFIER_ERR_INJECT_ACTION(NETDEV_PRECHANGEMTU) },
 		{ NOTIFIER_ERR_INJECT_ACTION(NETDEV_PRECHANGEUPPER) },
+		{ NOTIFIER_ERR_INJECT_ACTION(NETDEV_CHANGEUPPER) },
 		{}
 	}
 };

net/batman-adv/hard-interface.c

@@ -464,7 +464,8 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	hard_iface->soft_iface = soft_iface;
 	bat_priv = netdev_priv(hard_iface->soft_iface);
 
-	ret = netdev_master_upper_dev_link(hard_iface->net_dev, soft_iface);
+	ret = netdev_master_upper_dev_link(hard_iface->net_dev,
+					   soft_iface, NULL, NULL);
 	if (ret)
 		goto err_dev;
 

net/bridge/br_if.c

@@ -493,7 +493,7 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
 
 	dev->priv_flags |= IFF_BRIDGE_PORT;
 
-	err = netdev_master_upper_dev_link(dev, br->dev);
+	err = netdev_master_upper_dev_link(dev, br->dev, NULL, NULL);
 	if (err)
 		goto err5;
 

net/core/dev.c

@@ -5421,7 +5421,7 @@ static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev,
 
 static int __netdev_upper_dev_link(struct net_device *dev,
 				   struct net_device *upper_dev, bool master,
-				   void *private)
+				   void *upper_priv, void *upper_info)
 {
 	struct netdev_notifier_changeupper_info changeupper_info;
 	struct netdev_adjacent *i, *j, *to_i, *to_j;
@@ -5445,6 +5445,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	changeupper_info.upper_dev = upper_dev;
 	changeupper_info.master = master;
 	changeupper_info.linking = true;
+	changeupper_info.upper_info = upper_info;
 
 	ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, dev,
 					    &changeupper_info.info);
@@ -5452,7 +5453,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 	if (ret)
 		return ret;
 
-	ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, private,
+	ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv,
 						   master);
 	if (ret)
 		return ret;
@@ -5490,8 +5491,12 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 			goto rollback_lower_mesh;
 	}
 
-	call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
+	ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, dev,
 					    &changeupper_info.info);
+	ret = notifier_to_errno(ret);
+	if (ret)
+		goto rollback_lower_mesh;
+
 	return 0;
 
 rollback_lower_mesh:
@@ -5545,7 +5550,7 @@ static int __netdev_upper_dev_link(struct net_device *dev,
 int netdev_upper_dev_link(struct net_device *dev,
 			  struct net_device *upper_dev)
 {
-	return __netdev_upper_dev_link(dev, upper_dev, false, NULL);
+	return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL);
 }
 EXPORT_SYMBOL(netdev_upper_dev_link);
 
@@ -5553,6 +5558,8 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
  * netdev_master_upper_dev_link - Add a master link to the upper device
  * @dev: device
  * @upper_dev: new upper device
+ * @upper_priv: upper device private
+ * @upper_info: upper info to be passed down via notifier
  *
  * Adds a link to device which is upper to this one. In this case, only
  * one master upper device can be linked, although other non-master devices
@@ -5561,19 +5568,13 @@ EXPORT_SYMBOL(netdev_upper_dev_link);
  * counts are adjusted and the function returns zero.
  */
 int netdev_master_upper_dev_link(struct net_device *dev,
-				 struct net_device *upper_dev)
-{
-	return __netdev_upper_dev_link(dev, upper_dev, true, NULL);
-}
-EXPORT_SYMBOL(netdev_master_upper_dev_link);
-
-int netdev_master_upper_dev_link_private(struct net_device *dev,
 				 struct net_device *upper_dev,
-					 void *private)
+				 void *upper_priv, void *upper_info)
 {
-	return __netdev_upper_dev_link(dev, upper_dev, true, private);
+	return __netdev_upper_dev_link(dev, upper_dev, true,
+				       upper_priv, upper_info);
 }
-EXPORT_SYMBOL(netdev_master_upper_dev_link_private);
+EXPORT_SYMBOL(netdev_master_upper_dev_link);
 
 /**
  * netdev_upper_dev_unlink - Removes a link to upper device
@@ -5755,6 +5756,26 @@ int dev_get_nest_level(struct net_device *dev,
 }
 EXPORT_SYMBOL(dev_get_nest_level);
 
+/**
+ * netdev_lower_change - Dispatch event about lower device state change
+ * @lower_dev: device
+ * @lower_state_info: state to dispatch
+ *
+ * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info.
+ * The caller must hold the RTNL lock.
+ */
+void netdev_lower_state_changed(struct net_device *lower_dev,
+				void *lower_state_info)
+{
+	struct netdev_notifier_changelowerstate_info changelowerstate_info;
+
+	ASSERT_RTNL();
+	changelowerstate_info.lower_state_info = lower_state_info;
+	call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, lower_dev,
+				      &changelowerstate_info.info);
+}
+EXPORT_SYMBOL(netdev_lower_state_changed);
+
 static void dev_change_rx_flags(struct net_device *dev, int flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;

net/openvswitch/vport-netdev.c

@@ -105,7 +105,7 @@ struct vport *ovs_netdev_link(struct vport *vport, const char *name)
 
 	rtnl_lock();
 	err = netdev_master_upper_dev_link(vport->dev,
-					   get_dpdev(vport->dp));
+					   get_dpdev(vport->dp), NULL, NULL);
 	if (err)
 		goto error_unlock;