Merge branch 'dpaa2-switch-add-support-for-lag-offload'

Ioana Ciornei says:

====================
dpaa2-switch: add support for LAG offload

This patch set adds support in dpaa2-switch for offloading upper bond
devices.

The first two patches remove the necessity to hold rtnl_lock during the
event processing workqueue by ensuring that all event were processed
before any changes in FDB layout happens.

Patch #3 updates the logic around choosing the FDB that should be used
on a switch port. This is necessary since with the addition of the LAG
offload, we need to take into account all ports which are under the same
bridge, even though not directly.

The next four patches clean up the FDB event by making them easier to
integrate with bond devices and also add the
dpaa2_switch_port_to_bridge_port() helper to be used in the LAG offload
support.

The 8th patch adds the necessary new APIs for the LAG configuration
while the next one uses them, both in the prechangeupper phase and the
changeupper one. Which ports can be part of the same LAG group is
configurable at boot time, thus we use the prechangeupper callback in
order to validate that a requested configuration can be offloaded or
not.

This set also extends the handling of FDBs and port objects so that they
are handled by the driver even on an offloaded bond device.

v3: https://lore.kernel.org/all/20260603143623.3712024-1-ioana.ciornei@nxp.com/
v2: https://lore.kernel.org/all/20260512131554.952971-1-ioana.ciornei@nxp.com/
v1: https://lore.kernel.org/all/20260506151540.1242997-1-ioana.ciornei@nxp.com/
====================

Link: https://patch.msgid.link/20260629112309.154328-1-ioana.ciornei@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

5 files changed, 948 insertions, 133 deletions

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index 858ba844ac51..8320b26c3f72 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -25,6 +25,9 @@
 
 #define DEFAULT_VLAN_ID			1
 
+static struct notifier_block dpaa2_switch_port_switchdev_nb;
+static struct notifier_block dpaa2_switch_port_switchdev_blocking_nb;
+
 static u16 dpaa2_switch_port_get_fdb_id(struct ethsw_port_priv *port_priv)
 {
 	return port_priv->fdb->fdb_id;
@@ -51,6 +54,17 @@ dpaa2_switch_filter_block_get_unused(struct ethsw_core *ethsw)
 	return NULL;
 }
 
+static struct dpaa2_switch_lag *
+dpaa2_switch_lag_get_unused(struct ethsw_core *ethsw)
+{
+	int i;
+
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+		if (!ethsw->lags[i].in_use)
+			return &ethsw->lags[i];
+	return NULL;
+}
+
 static bool dpaa2_switch_fdb_in_use_by_others(struct ethsw_core *ethsw,
 					      struct dpaa2_switch_fdb *fdb,
 					      struct ethsw_port_priv *except)
@@ -71,9 +85,9 @@ static struct dpaa2_switch_fdb *
 dpaa2_switch_fdb_for_join(struct ethsw_port_priv *port_priv,
 			  struct net_device *upper_dev)
 {
-	struct ethsw_port_priv *other_port_priv;
-	struct net_device *other_dev;
-	struct list_head *iter;
+	struct ethsw_port_priv *other_port_priv = NULL;
+	struct net_device *other_dev, *other_dev2;
+	struct list_head *iter, *iter2;
 
 	/* The below call to netdev_for_each_lower_dev() demands the RTNL lock
 	 * being held. Assert on it so that it's easier to catch new code
@@ -82,17 +96,32 @@ dpaa2_switch_fdb_for_join(struct ethsw_port_priv *port_priv,
 	ASSERT_RTNL();
 
 	/* If part of a bridge, use the FDB of the first dpaa2 switch interface
-	 * to be present in that bridge
+	 * to be present in that bridge. The search descends one level through
+	 * a bridged bond's lowers as well.
 	 */
 	netdev_for_each_lower_dev(upper_dev, other_dev, iter) {
-		if (!dpaa2_switch_port_dev_check(other_dev))
-			continue;
+		if (netif_is_lag_master(other_dev)) {
+			netdev_for_each_lower_dev(other_dev, other_dev2, iter2) {
+				if (!dpaa2_switch_port_dev_check(other_dev2))
+					continue;
 
-		if (other_dev == port_priv->netdev)
-			continue;
+				if (other_dev2 == port_priv->netdev)
+					continue;
 
-		other_port_priv = netdev_priv(other_dev);
-		return other_port_priv->fdb;
+				other_port_priv = netdev_priv(other_dev2);
+				break;
+			}
+		} else {
+			if (!dpaa2_switch_port_dev_check(other_dev))
+				continue;
+
+			if (other_dev == port_priv->netdev)
+				continue;
+
+			other_port_priv = netdev_priv(other_dev);
+		}
+		if (other_port_priv)
+			return other_port_priv->fdb;
 	}
 
 	return port_priv->fdb;
@@ -537,6 +566,103 @@ static int dpaa2_switch_port_fdb_del_mc(struct ethsw_port_priv *port_priv,
 	return err;
 }
 
+static int dpaa2_switch_port_fdb_add(struct ethsw_port_priv *port_priv,
+				     const unsigned char *addr)
+{
+	int err;
+
+	if (is_unicast_ether_addr(addr))
+		err = dpaa2_switch_port_fdb_add_uc(port_priv, addr);
+	else
+		err = dpaa2_switch_port_fdb_add_mc(port_priv, addr);
+
+	return err;
+}
+
+static int dpaa2_switch_port_fdb_del(struct ethsw_port_priv *port_priv,
+				     const unsigned char *addr)
+{
+	if (is_unicast_ether_addr(addr))
+		return dpaa2_switch_port_fdb_del_uc(port_priv, addr);
+	else
+		return dpaa2_switch_port_fdb_del_mc(port_priv, addr);
+}
+
+static struct dpaa2_mac_addr *
+dpaa2_switch_mac_addr_find(struct list_head *addr_list,
+			   const unsigned char *addr, u16 vid)
+{
+	struct dpaa2_mac_addr *a;
+
+	list_for_each_entry(a, addr_list, list)
+		if (ether_addr_equal(a->addr, addr) && a->vid == vid)
+			return a;
+
+	return NULL;
+}
+
+static int dpaa2_switch_lag_fdb_add(struct dpaa2_switch_lag *lag,
+				    const unsigned char *addr, u16 vid)
+{
+	struct ethsw_port_priv *port_priv = lag->primary;
+	struct dpaa2_mac_addr *a;
+	int err = 0;
+
+	mutex_lock(&lag->fdb_lock);
+
+	a = dpaa2_switch_mac_addr_find(&lag->fdbs, addr, vid);
+	if (a) {
+		refcount_inc(&a->refcount);
+		goto out;
+	}
+
+	a = kzalloc(sizeof(*a), GFP_KERNEL);
+	if (!a) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = dpaa2_switch_port_fdb_add(port_priv, addr);
+	if (err) {
+		kfree(a);
+		goto out;
+	}
+
+	ether_addr_copy(a->addr, addr);
+	a->vid = vid;
+	refcount_set(&a->refcount, 1);
+	list_add_tail(&a->list, &lag->fdbs);
+
+out:
+	mutex_unlock(&lag->fdb_lock);
+
+	return err;
+}
+
+static void dpaa2_switch_lag_fdb_del(struct dpaa2_switch_lag *lag,
+				     const unsigned char *addr, u16 vid)
+{
+	struct ethsw_port_priv *port_priv = lag->primary;
+	struct dpaa2_mac_addr *a;
+
+	mutex_lock(&lag->fdb_lock);
+
+	a = dpaa2_switch_mac_addr_find(&lag->fdbs, addr, vid);
+	if (!a)
+		goto out;
+
+	if (!refcount_dec_and_test(&a->refcount))
+		goto out;
+
+	list_del(&a->list);
+	kfree(a);
+
+	dpaa2_switch_port_fdb_del(port_priv, addr);
+
+out:
+	mutex_unlock(&lag->fdb_lock);
+}
+
 static void dpaa2_switch_port_get_stats(struct net_device *netdev,
 					struct rtnl_link_stats64 *stats)
 {
@@ -1485,6 +1611,33 @@ bool dpaa2_switch_port_dev_check(const struct net_device *netdev)
 	return netdev->netdev_ops == &dpaa2_switch_port_ops;
 }
 
+static bool dpaa2_switch_foreign_dev_check(const struct net_device *dev,
+					   const struct net_device *foreign_dev)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(dev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct ethsw_port_priv *other_port;
+	int i;
+
+	if (netif_is_bridge_master(foreign_dev))
+		if (port_priv->fdb->bridge_dev == foreign_dev)
+			return false;
+
+	if (netif_is_bridge_port(foreign_dev)) {
+		for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+			other_port = ethsw->ports[i];
+
+			if (!other_port)
+				continue;
+			if (dpaa2_switch_port_offloads_bridge_port(other_port,
+								   foreign_dev))
+				return false;
+		}
+	}
+
+	return true;
+}
+
 static int dpaa2_switch_port_connect_mac(struct ethsw_port_priv *port_priv)
 {
 	struct fsl_mc_device *dpsw_port_dev, *dpmac_dev;
@@ -1860,51 +2013,32 @@ int dpaa2_switch_port_vlans_add(struct net_device *netdev,
 					  vlan->changed);
 }
 
-static int dpaa2_switch_port_lookup_address(struct net_device *netdev, int is_uc,
-					    const unsigned char *addr)
-{
-	struct netdev_hw_addr_list *list = (is_uc) ? &netdev->uc : &netdev->mc;
-	struct netdev_hw_addr *ha;
-
-	netif_addr_lock_bh(netdev);
-	list_for_each_entry(ha, &list->list, list) {
-		if (ether_addr_equal(ha->addr, addr)) {
-			netif_addr_unlock_bh(netdev);
-			return 1;
-		}
-	}
-	netif_addr_unlock_bh(netdev);
-	return 0;
-}
-
 static int dpaa2_switch_port_mdb_add(struct net_device *netdev,
 				     const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
-	int err;
+	struct dpaa2_switch_lag *lag;
 
-	/* Check if address is already set on this port */
-	if (dpaa2_switch_port_lookup_address(netdev, 0, mdb->addr))
-		return -EEXIST;
-
-	err = dpaa2_switch_port_fdb_add_mc(port_priv, mdb->addr);
-	if (err)
-		return err;
-
-	err = dev_mc_add(netdev, mdb->addr);
-	if (err) {
-		netdev_err(netdev, "dev_mc_add err %d\n", err);
-		dpaa2_switch_port_fdb_del_mc(port_priv, mdb->addr);
-	}
-
-	return err;
+	lag = rtnl_dereference(port_priv->lag);
+	if (lag)
+		return dpaa2_switch_lag_fdb_add(lag, mdb->addr, mdb->vid);
+	else
+		return dpaa2_switch_port_fdb_add(port_priv, mdb->addr);
 }
 
-static int dpaa2_switch_port_obj_add(struct net_device *netdev,
-				     const struct switchdev_obj *obj)
+static int dpaa2_switch_port_obj_add(struct net_device *netdev, const void *ctx,
+				     const struct switchdev_obj *obj,
+				     struct netlink_ext_ack *extack)
 {
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	int err;
 
+	if (ctx && ctx != port_priv)
+		return 0;
+
+	if (!dpaa2_switch_port_offloads_bridge_port(port_priv, obj->orig_dev))
+		return -EOPNOTSUPP;
+
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		err = dpaa2_switch_port_vlans_add(netdev,
@@ -2000,29 +2134,29 @@ static int dpaa2_switch_port_mdb_del(struct net_device *netdev,
 				     const struct switchdev_obj_port_mdb *mdb)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
-	int err;
-
-	if (!dpaa2_switch_port_lookup_address(netdev, 0, mdb->addr))
-		return -ENOENT;
-
-	err = dpaa2_switch_port_fdb_del_mc(port_priv, mdb->addr);
-	if (err)
-		return err;
+	struct dpaa2_switch_lag *lag;
 
-	err = dev_mc_del(netdev, mdb->addr);
-	if (err) {
-		netdev_err(netdev, "dev_mc_del err %d\n", err);
-		return err;
-	}
+	lag = rtnl_dereference(port_priv->lag);
+	if (lag)
+		dpaa2_switch_lag_fdb_del(lag, mdb->addr, mdb->vid);
+	else
+		dpaa2_switch_port_fdb_del(port_priv, mdb->addr);
 
-	return err;
+	return 0;
 }
 
-static int dpaa2_switch_port_obj_del(struct net_device *netdev,
+static int dpaa2_switch_port_obj_del(struct net_device *netdev, const void *ctx,
 				     const struct switchdev_obj *obj)
 {
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	int err;
 
+	if (ctx && ctx != port_priv)
+		return 0;
+
+	if (!dpaa2_switch_port_offloads_bridge_port(port_priv, obj->orig_dev))
+		return -EOPNOTSUPP;
+
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_ID_PORT_VLAN:
 		err = dpaa2_switch_port_vlans_del(netdev, SWITCHDEV_OBJ_PORT_VLAN(obj));
@@ -2048,6 +2182,21 @@ static int dpaa2_switch_port_attr_set_event(struct net_device *netdev,
 	return notifier_from_errno(err);
 }
 
+static struct net_device *
+dpaa2_switch_port_to_bridge_port(struct ethsw_port_priv *port_priv)
+{
+	struct dpaa2_switch_lag *lag;
+
+	if (!port_priv->fdb->bridge_dev)
+		return NULL;
+
+	lag = rtnl_dereference(port_priv->lag);
+	if (lag)
+		return lag->bond_dev;
+
+	return port_priv->netdev;
+}
+
 static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 					 struct net_device *upper_dev,
 					 struct netlink_ext_ack *extack)
@@ -2055,6 +2204,7 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
 	struct dpaa2_switch_fdb *old_fdb = port_priv->fdb;
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *brport_dev;
 	bool learn_ena;
 	int err;
 
@@ -2066,7 +2216,8 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	dpaa2_switch_port_set_fdb(port_priv, upper_dev, true);
 
 	/* Inherit the initial bridge port learning state */
-	learn_ena = br_port_flag_is_set(netdev, BR_LEARNING);
+	brport_dev = dpaa2_switch_port_to_bridge_port(port_priv);
+	learn_ena = br_port_flag_is_set(brport_dev, BR_LEARNING);
 	err = dpaa2_switch_port_set_learning(port_priv, learn_ena);
 	port_priv->learn_ena = learn_ena;
 
@@ -2080,8 +2231,11 @@ static int dpaa2_switch_port_bridge_join(struct net_device *netdev,
 	if (err)
 		goto err_egress_flood;
 
-	err = switchdev_bridge_port_offload(netdev, netdev, NULL,
-					    NULL, NULL, false, extack);
+	brport_dev = dpaa2_switch_port_to_bridge_port(port_priv);
+	err = switchdev_bridge_port_offload(brport_dev, netdev, port_priv,
+					    &dpaa2_switch_port_switchdev_nb,
+					    &dpaa2_switch_port_switchdev_blocking_nb,
+					    false, extack);
 	if (err)
 		goto err_switchdev_offload;
 
@@ -2115,7 +2269,22 @@ static int dpaa2_switch_port_restore_rxvlan(struct net_device *vdev, int vid, vo
 
 static void dpaa2_switch_port_pre_bridge_leave(struct net_device *netdev)
 {
-	switchdev_bridge_port_unoffload(netdev, NULL, NULL, NULL);
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *brport_dev;
+
+	brport_dev = dpaa2_switch_port_to_bridge_port(port_priv);
+	if (!brport_dev)
+		return;
+
+	switchdev_bridge_port_unoffload(brport_dev, port_priv,
+					&dpaa2_switch_port_switchdev_nb,
+					&dpaa2_switch_port_switchdev_blocking_nb);
+
+	/* Make sure that any FDB add/del operations are completed before the
+	 * bridge layout changes
+	 */
+	flush_workqueue(ethsw->workqueue);
 }
 
 static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
@@ -2177,30 +2346,53 @@ static int dpaa2_switch_port_bridge_leave(struct net_device *netdev)
 					  false);
 }
 
+static int
+dpaa2_switch_have_vlan_upper(struct net_device *upper_dev,
+			     __always_unused struct netdev_nested_priv *priv)
+{
+	return is_vlan_dev(upper_dev);
+}
+
 static int dpaa2_switch_prevent_bridging_with_8021q_upper(struct net_device *netdev)
 {
-	struct net_device *upper_dev;
-	struct list_head *iter;
+	struct netdev_nested_priv priv = {};
 
 	/* RCU read lock not necessary because we have write-side protection
-	 * (rtnl_mutex), however a non-rcu iterator does not exist.
+	 * (rtnl_mutex), however a non-rcu iterator does not exist. Walk the
+	 * entire upper chain so that a VLAN device stacked on a intermediate
+	 * bond is caught too.
 	 */
-	netdev_for_each_upper_dev_rcu(netdev, upper_dev, iter)
-		if (is_vlan_dev(upper_dev))
-			return -EOPNOTSUPP;
+	if (netdev_walk_all_upper_dev_rcu(netdev, dpaa2_switch_have_vlan_upper,
+					  &priv))
+		return -EOPNOTSUPP;
 
 	return 0;
 }
 
+static int dpaa2_switch_check_dpsw_instance(struct net_device *dev,
+					    struct netdev_nested_priv *priv)
+{
+	struct ethsw_port_priv *port_priv = (struct ethsw_port_priv *)priv->data;
+	struct ethsw_port_priv *other_priv = netdev_priv(dev);
+
+	if (!dpaa2_switch_port_dev_check(dev))
+		return 0;
+
+	if (other_priv->ethsw_data == port_priv->ethsw_data)
+		return 0;
+
+	return 1;
+}
+
 static int
 dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 					  struct net_device *upper_dev,
 					  struct netlink_ext_ack *extack)
 {
 	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
-	struct ethsw_port_priv *other_port_priv;
-	struct net_device *other_dev;
-	struct list_head *iter;
+	struct netdev_nested_priv data = {
+		.data = (void *)port_priv,
+	};
 	int err;
 
 	if (!br_vlan_enabled(upper_dev)) {
@@ -2215,6 +2407,70 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 		return err;
 	}
 
+	err = netdev_walk_all_lower_dev(upper_dev,
+					dpaa2_switch_check_dpsw_instance,
+					&data);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Interface from a different DPSW is in the bridge already");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int dpaa2_switch_pre_lag_join(struct net_device *netdev,
+				     struct net_device *upper_dev,
+				     struct netdev_lag_upper_info *info,
+				     struct netlink_ext_ack *extack)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct ethsw_port_priv *other_port_priv;
+	struct dpaa2_switch_lag *lag = NULL;
+	struct dpsw_lag_cfg cfg = {0};
+	struct net_device *other_dev;
+	int i, num_ifs = 0, err;
+	struct list_head *iter;
+
+	if (!(ethsw->features & ETHSW_FEATURE_LAG_OFFLOAD)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "LAG offload is supported only for DPSW >= v8.13");
+		return -EOPNOTSUPP;
+	}
+
+	if (info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Can only offload LAG using hash TX type");
+		return -EOPNOTSUPP;
+	}
+
+	if (info->hash_type != NETDEV_LAG_HASH_L23) {
+		NL_SET_ERR_MSG_MOD(extack, "Can only offload L2+L3 Tx hash");
+		return -EOPNOTSUPP;
+	}
+
+	if (!dpaa2_switch_port_has_mac(port_priv)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Only switch interfaces connected to MACs can be under a LAG");
+		return -EINVAL;
+	}
+
+	if (vlan_uses_dev(upper_dev)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot join a LAG upper that has a VLAN");
+		return -EOPNOTSUPP;
+	}
+
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+		if (!ethsw->lags[i].in_use)
+			continue;
+		if (ethsw->lags[i].bond_dev != upper_dev)
+			continue;
+		lag = &ethsw->lags[i];
+		break;
+	}
+
 	netdev_for_each_lower_dev(upper_dev, other_dev, iter) {
 		if (!dpaa2_switch_port_dev_check(other_dev))
 			continue;
@@ -2222,9 +2478,248 @@ dpaa2_switch_prechangeupper_sanity_checks(struct net_device *netdev,
 		other_port_priv = netdev_priv(other_dev);
 		if (other_port_priv->ethsw_data != port_priv->ethsw_data) {
 			NL_SET_ERR_MSG_MOD(extack,
-					   "Interface from a different DPSW is in the bridge already");
+					   "Interface from a different DPSW is in the bond already");
 			return -EINVAL;
 		}
+
+		cfg.if_id[num_ifs++] = other_port_priv->idx;
+
+		if (num_ifs >= DPSW_MAX_LAG_IFS) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Cannot add more than 8 DPAA2 switch ports under the same bond");
+			return -EINVAL;
+		}
+	}
+
+	if (lag) {
+		cfg.group_id = lag->id;
+		cfg.if_id[num_ifs++] = port_priv->idx;
+		cfg.num_ifs = num_ifs;
+		cfg.phase = DPSW_LAG_SET_PHASE_CHECK;
+
+		err = dpsw_lag_set(ethsw->mc_io, 0, ethsw->dpsw_handle, &cfg);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Cannot offload LAG configuration");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	return 0;
+}
+
+static void dpaa2_switch_port_set_lag_group(struct ethsw_port_priv *port_priv,
+					    struct net_device *bond_dev)
+{
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct ethsw_port_priv *other_port_priv = NULL;
+	struct dpaa2_switch_lag *lag = NULL;
+	struct dpaa2_switch_lag *other_lag;
+	struct net_device *other_dev;
+	struct list_head *iter;
+
+	netdev_for_each_lower_dev(bond_dev, other_dev, iter) {
+		if (!dpaa2_switch_port_dev_check(other_dev))
+			continue;
+
+		other_port_priv = netdev_priv(other_dev);
+		other_lag = rtnl_dereference(other_port_priv->lag);
+		if (!other_lag)
+			continue;
+
+		if (other_lag->bond_dev == bond_dev) {
+			rcu_assign_pointer(port_priv->lag, other_lag);
+			return;
+		}
+	}
+
+	/* This is the first interface to be added under a bond device. Find an
+	 * unused LAG group. No need to check for NULL since there are the same
+	 * amount of DPSW ports as LAG groups, meaning that each port can have
+	 * its own LAG group.
+	 */
+	lag = dpaa2_switch_lag_get_unused(ethsw);
+	lag->in_use = true;
+	lag->bond_dev = bond_dev;
+	lag->primary = port_priv;
+	rcu_assign_pointer(port_priv->lag, lag);
+}
+
+static bool dpaa2_switch_port_in_lag(struct ethsw_port_priv *port_priv,
+				     struct net_device *bond_dev)
+{
+	struct dpaa2_switch_lag *lag;
+
+	if (!port_priv)
+		return false;
+
+	lag = rtnl_dereference(port_priv->lag);
+	return lag && lag->bond_dev == bond_dev;
+}
+
+static int dpaa2_switch_set_lag_cfg(struct net_device *bond_dev, u8 lag_id,
+				    struct ethsw_core *ethsw)
+{
+	struct dpaa2_switch_lag *lag = &ethsw->lags[lag_id - 1];
+	struct ethsw_port_priv *primary, *port_priv;
+	struct ethsw_port_priv *new_primary = NULL;
+	struct dpsw_lag_cfg cfg = {0};
+	struct dpaa2_mac_addr *a;
+	u8 num_ifs = 0;
+	int err, i;
+
+	cfg.group_id = lag_id;
+
+	/* Determine the primary port. The caller clears ->lag on the port that
+	 * is leaving, so a NULL ->lag on the current primary means it is the
+	 * one leaving: elect the first remaining member as the new primary.
+	 * Otherwise keep the current primary.
+	 */
+	if (rtnl_dereference(lag->primary->lag)) {
+		primary = lag->primary;
+	} else {
+		primary = NULL;
+		for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+			if (dpaa2_switch_port_in_lag(ethsw->ports[i], bond_dev)) {
+				new_primary = ethsw->ports[i];
+				primary = new_primary;
+				break;
+			}
+		}
+	}
+
+	/* Build the interface list, always placing the primary first */
+	if (primary)
+		cfg.if_id[num_ifs++] = primary->idx;
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+		port_priv = ethsw->ports[i];
+		if (port_priv == primary)
+			continue;
+		if (!dpaa2_switch_port_in_lag(port_priv, bond_dev))
+			continue;
+
+		cfg.if_id[num_ifs++] = port_priv->idx;
+	}
+	cfg.num_ifs = num_ifs;
+
+	/* No more interfaces under this LAG group, mark it as not in use. Wait
+	 * for a grace period so that any readers of the lag structure finished.
+	 */
+	if (!num_ifs) {
+		synchronize_net();
+
+		lag->bond_dev = NULL;
+		lag->primary = NULL;
+		lag->in_use = false;
+	}
+
+	/* When the primary changes, migrate the FDB entries from the old
+	 * primary to the new one: remove them before reconfiguring the LAG in
+	 * hardware and re-add them on the new primary afterwards. We do not
+	 * touch any refcounting since the intention is to change the HW entry,
+	 * not the parallel software tracking.
+	 */
+	if (new_primary) {
+		mutex_lock(&lag->fdb_lock);
+		list_for_each_entry(a, &lag->fdbs, list)
+			dpaa2_switch_port_fdb_del(lag->primary, a->addr);
+		mutex_unlock(&lag->fdb_lock);
+	}
+
+	err = dpsw_lag_set(ethsw->mc_io, 0, ethsw->dpsw_handle, &cfg);
+	if (err)
+		return err;
+
+	if (new_primary) {
+		mutex_lock(&lag->fdb_lock);
+		list_for_each_entry(a, &lag->fdbs, list) {
+			err = dpaa2_switch_port_fdb_add(new_primary, a->addr);
+			if (err)
+				netdev_err(new_primary->netdev, "Unable to migrate FDB\n");
+		}
+		mutex_unlock(&lag->fdb_lock);
+
+		synchronize_net();
+		lag->primary = new_primary;
+	}
+
+	return 0;
+}
+
+static int dpaa2_switch_port_bond_join(struct net_device *netdev,
+				       struct net_device *bond_dev,
+				       struct netdev_lag_upper_info *info,
+				       struct netlink_ext_ack *extack)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *bridge_dev;
+	struct dpaa2_switch_lag *lag;
+	int err = 0;
+	u8 lag_id;
+
+	/* Setup the port_priv->lag pointer for this switch port */
+	dpaa2_switch_port_set_lag_group(port_priv, bond_dev);
+
+	/* Create the LAG configuration and apply it in MC */
+	lag = rtnl_dereference(port_priv->lag);
+	lag_id = lag->id;
+	err = dpaa2_switch_set_lag_cfg(bond_dev, lag_id, ethsw);
+	if (err)
+		goto err_lag_cfg;
+
+	/* If the bond device is a switch port, join the bridge as well */
+	bridge_dev = netdev_master_upper_dev_get(bond_dev);
+	if (!bridge_dev || !netif_is_bridge_master(bridge_dev))
+		return 0;
+
+	err = dpaa2_switch_port_bridge_join(netdev, bridge_dev, extack);
+	if (err)
+		goto err_lag_cfg;
+
+	return err;
+
+err_lag_cfg:
+	rcu_assign_pointer(port_priv->lag, NULL);
+	dpaa2_switch_set_lag_cfg(bond_dev, lag_id, ethsw);
+
+	return err;
+}
+
+static int dpaa2_switch_port_bond_leave(struct net_device *netdev,
+					struct net_device *bond_dev)
+{
+	struct net_device *bridge_dev = netdev_master_upper_dev_get(bond_dev);
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct dpaa2_switch_lag *lag = rtnl_dereference(port_priv->lag);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	struct net_device *brpdev;
+	bool learn_ena;
+	int err;
+
+	if (!lag)
+		return 0;
+
+	/* Recreate the LAG configuration for the LAG group that we left. */
+	rcu_assign_pointer(port_priv->lag, NULL);
+	dpaa2_switch_set_lag_cfg(bond_dev, lag->id, ethsw);
+
+	if (bridge_dev && netif_is_bridge_master(bridge_dev)) {
+		/* Make sure that the new primary inherits the learning state */
+		if (lag->primary) {
+			brpdev = dpaa2_switch_port_to_bridge_port(lag->primary);
+			learn_ena = br_port_flag_is_set(brpdev, BR_LEARNING);
+			err = dpaa2_switch_port_set_learning(lag->primary,
+							     learn_ena);
+			if (err)
+				return err;
+			lag->primary->learn_ena = learn_ena;
+		}
+
+		/* In case the bond is a bridge port, leave the upper bridge as
+		 * well.
+		 */
+		return dpaa2_switch_port_bridge_leave(netdev);
 	}
 
 	return 0;
@@ -2234,8 +2729,8 @@ static int dpaa2_switch_port_prechangeupper(struct net_device *netdev,
 					    struct netdev_notifier_changeupper_info *info)
 {
 	struct ethsw_port_priv *port_priv;
+	struct net_device *upper_dev, *br;
 	struct netlink_ext_ack *extack;
-	struct net_device *upper_dev;
 	int err;
 
 	if (!dpaa2_switch_port_dev_check(netdev))
@@ -2252,6 +2747,24 @@ static int dpaa2_switch_port_prechangeupper(struct net_device *netdev,
 
 		if (!info->linking)
 			dpaa2_switch_port_pre_bridge_leave(netdev);
+	} else if (netif_is_lag_master(upper_dev)) {
+		if (!info->linking) {
+			if (netif_is_bridge_port(upper_dev))
+				dpaa2_switch_port_pre_bridge_leave(netdev);
+			return 0;
+		}
+
+		if (netif_is_bridge_port(upper_dev)) {
+			br = netdev_master_upper_dev_get(upper_dev);
+			err = dpaa2_switch_prechangeupper_sanity_checks(netdev,
+									br,
+									extack);
+			if (err)
+				return err;
+		}
+
+		return dpaa2_switch_pre_lag_join(netdev, upper_dev,
+						 info->upper_info, extack);
 	} else if (is_vlan_dev(upper_dev)) {
 		port_priv = netdev_priv(netdev);
 		if (port_priv->fdb->bridge_dev) {
@@ -2283,6 +2796,80 @@ static int dpaa2_switch_port_changeupper(struct net_device *netdev,
 							     extack);
 		else
 			return dpaa2_switch_port_bridge_leave(netdev);
+	} else if (netif_is_lag_master(upper_dev)) {
+		if (info->linking)
+			return dpaa2_switch_port_bond_join(netdev, upper_dev,
+							   info->upper_info,
+							   extack);
+		else
+			return dpaa2_switch_port_bond_leave(netdev, upper_dev);
+	}
+
+	return 0;
+}
+
+static int
+dpaa2_switch_lag_prechangeupper(struct net_device *netdev,
+				struct netdev_notifier_changeupper_info *info)
+{
+	struct net_device *lower;
+	struct list_head *iter;
+	int err = 0;
+
+	if (!netif_is_lag_master(netdev))
+		return 0;
+
+	netdev_for_each_lower_dev(netdev, lower, iter) {
+		if (!dpaa2_switch_port_dev_check(lower))
+			continue;
+
+		err = dpaa2_switch_port_prechangeupper(lower, info);
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+static int
+dpaa2_switch_lag_changeupper(struct net_device *netdev,
+			     struct netdev_notifier_changeupper_info *info)
+{
+	struct net_device *lower;
+	struct list_head *iter;
+	int err = 0;
+
+	if (!netif_is_lag_master(netdev))
+		return 0;
+
+	netdev_for_each_lower_dev(netdev, lower, iter) {
+		if (!dpaa2_switch_port_dev_check(lower))
+			continue;
+
+		err = dpaa2_switch_port_changeupper(lower, info);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int
+dpaa2_switch_port_changelowerstate(struct net_device *netdev,
+				   struct netdev_lag_lower_state_info *linfo)
+{
+	struct ethsw_port_priv *port_priv = netdev_priv(netdev);
+	struct ethsw_core *ethsw = port_priv->ethsw_data;
+	int err;
+
+	if (!rtnl_dereference(port_priv->lag))
+		return 0;
+
+	err = dpsw_if_set_lag_state(ethsw->mc_io, 0, ethsw->dpsw_handle,
+				    port_priv->idx, linfo->tx_enabled ? 1 : 0);
+	if (err) {
+		netdev_err(netdev, "dpsw_if_set_lag_state() = %d\n", err);
+		return err;
 	}
 
 	return 0;
@@ -2292,6 +2879,7 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
 					     unsigned long event, void *ptr)
 {
 	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_changelowerstate_info *info;
 	int err = 0;
 
 	switch (event) {
@@ -2300,13 +2888,29 @@ static int dpaa2_switch_port_netdevice_event(struct notifier_block *nb,
 		if (err)
 			return notifier_from_errno(err);
 
+		err = dpaa2_switch_lag_prechangeupper(netdev, ptr);
+		if (err)
+			return notifier_from_errno(err);
+
 		break;
 	case NETDEV_CHANGEUPPER:
 		err = dpaa2_switch_port_changeupper(netdev, ptr);
 		if (err)
 			return notifier_from_errno(err);
 
+		err = dpaa2_switch_lag_changeupper(netdev, ptr);
+		if (err)
+			return notifier_from_errno(err);
+
 		break;
+	case NETDEV_CHANGELOWERSTATE:
+		info = ptr;
+		if (!dpaa2_switch_port_dev_check(netdev))
+			break;
+
+		err = dpaa2_switch_port_changelowerstate(netdev,
+							 info->lower_state_info);
+		return notifier_from_errno(err);
 	}
 
 	return NOTIFY_DONE;
@@ -2316,80 +2920,97 @@ struct ethsw_switchdev_event_work {
 	struct work_struct work;
 	struct switchdev_notifier_fdb_info fdb_info;
 	struct net_device *dev;
+	struct net_device *orig_dev;
 	unsigned long event;
+	u16 vid;
 };
 
 static void dpaa2_switch_event_work(struct work_struct *work)
 {
 	struct ethsw_switchdev_event_work *switchdev_work =
 		container_of(work, struct ethsw_switchdev_event_work, work);
+	struct net_device *orig_dev = switchdev_work->orig_dev;
 	struct net_device *dev = switchdev_work->dev;
+	struct ethsw_port_priv *port_priv = netdev_priv(dev);
 	struct switchdev_notifier_fdb_info *fdb_info;
+	struct dpaa2_switch_lag *lag;
 	int err;
 
-	rtnl_lock();
 	fdb_info = &switchdev_work->fdb_info;
 
+	/* The lag structures are freed only from dpaa2_switch_remove(), which
+	 * first flushes this workqueue, so the pointer stays valid for the
+	 * lifetime of the work item. Only the dereference needs the RCU
+	 * read-side lock; the FDB helpers below can sleep and must run outside
+	 * of it.
+	 */
+	rcu_read_lock();
+	lag = rcu_dereference(port_priv->lag);
+	rcu_read_unlock();
+
 	switch (switchdev_work->event) {
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
-		if (!fdb_info->added_by_user || fdb_info->is_local)
-			break;
-		if (is_unicast_ether_addr(fdb_info->addr))
-			err = dpaa2_switch_port_fdb_add_uc(netdev_priv(dev),
-							   fdb_info->addr);
+		if (lag)
+			err = dpaa2_switch_lag_fdb_add(lag, fdb_info->addr,
+						       switchdev_work->vid);
 		else
-			err = dpaa2_switch_port_fdb_add_mc(netdev_priv(dev),
-							   fdb_info->addr);
+			err = dpaa2_switch_port_fdb_add(port_priv,
+							fdb_info->addr);
 		if (err)
 			break;
 		fdb_info->offloaded = true;
-		call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev,
+		call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, orig_dev,
 					 &fdb_info->info, NULL);
 		break;
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
-		if (!fdb_info->added_by_user || fdb_info->is_local)
-			break;
-		if (is_unicast_ether_addr(fdb_info->addr))
-			dpaa2_switch_port_fdb_del_uc(netdev_priv(dev), fdb_info->addr);
+		if (lag)
+			dpaa2_switch_lag_fdb_del(lag, fdb_info->addr,
+						 switchdev_work->vid);
 		else
-			dpaa2_switch_port_fdb_del_mc(netdev_priv(dev), fdb_info->addr);
+			dpaa2_switch_port_fdb_del(port_priv, fdb_info->addr);
 		break;
 	}
 
-	rtnl_unlock();
 	kfree(switchdev_work->fdb_info.addr);
 	kfree(switchdev_work);
 	dev_put(dev);
+	dev_put(orig_dev);
 }
 
-/* Called under rcu_read_lock() */
-static int dpaa2_switch_port_event(struct notifier_block *nb,
-				   unsigned long event, void *ptr)
+static int
+dpaa2_switch_port_fdb_event(struct net_device *dev,
+			    struct net_device *orig_dev,
+			    unsigned long event, const void *ctx,
+			    const struct switchdev_notifier_fdb_info *fdb_info)
 {
-	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
 	struct ethsw_port_priv *port_priv = netdev_priv(dev);
 	struct ethsw_switchdev_event_work *switchdev_work;
-	struct switchdev_notifier_fdb_info *fdb_info = ptr;
 	struct ethsw_core *ethsw = port_priv->ethsw_data;
 
-	if (event == SWITCHDEV_PORT_ATTR_SET)
-		return dpaa2_switch_port_attr_set_event(dev, ptr);
+	if (ctx && ctx != port_priv)
+		return 0;
 
-	if (!dpaa2_switch_port_dev_check(dev))
-		return NOTIFY_DONE;
+	/* For the moment, do nothing with entries towards foreign devices */
+	if (dpaa2_switch_foreign_dev_check(dev, orig_dev))
+		return 0;
+
+	if (!fdb_info->added_by_user || fdb_info->is_local)
+		return 0;
 
 	switchdev_work = kzalloc_obj(*switchdev_work, GFP_ATOMIC);
 	if (!switchdev_work)
-		return NOTIFY_BAD;
+		return -ENOMEM;
 
 	INIT_WORK(&switchdev_work->work, dpaa2_switch_event_work);
 	switchdev_work->dev = dev;
 	switchdev_work->event = event;
+	switchdev_work->orig_dev = orig_dev;
+	switchdev_work->vid = fdb_info->vid;
 
 	switch (event) {
 	case SWITCHDEV_FDB_ADD_TO_DEVICE:
 	case SWITCHDEV_FDB_DEL_TO_DEVICE:
-		memcpy(&switchdev_work->fdb_info, ptr,
+		memcpy(&switchdev_work->fdb_info, fdb_info,
 		       sizeof(switchdev_work->fdb_info));
 		switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC);
 		if (!switchdev_work->fdb_info.addr)
@@ -2400,52 +3021,61 @@ static int dpaa2_switch_port_event(struct notifier_block *nb,
 
 		/* Take a reference on the device to avoid being freed. */
 		dev_hold(dev);
+		dev_hold(orig_dev);
 		break;
 	default:
 		kfree(switchdev_work);
-		return NOTIFY_DONE;
+		return 0;
 	}
 
 	queue_work(ethsw->workqueue, &switchdev_work->work);
 
-	return NOTIFY_DONE;
+	return 0;
 
 err_addr_alloc:
 	kfree(switchdev_work);
-	return NOTIFY_BAD;
+	return -ENOMEM;
 }
 
-static int dpaa2_switch_port_obj_event(unsigned long event,
-				       struct net_device *netdev,
-				       struct switchdev_notifier_port_obj_info *port_obj_info)
+/* Called under rcu_read_lock() */
+static int dpaa2_switch_port_event(struct notifier_block *nb,
+				   unsigned long event, void *ptr)
 {
-	int err = -EOPNOTSUPP;
-
-	if (!dpaa2_switch_port_dev_check(netdev))
-		return NOTIFY_DONE;
+	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
 
 	switch (event) {
-	case SWITCHDEV_PORT_OBJ_ADD:
-		err = dpaa2_switch_port_obj_add(netdev, port_obj_info->obj);
-		break;
-	case SWITCHDEV_PORT_OBJ_DEL:
-		err = dpaa2_switch_port_obj_del(netdev, port_obj_info->obj);
-		break;
+	case SWITCHDEV_PORT_ATTR_SET:
+		return dpaa2_switch_port_attr_set_event(dev, ptr);
+	case SWITCHDEV_FDB_ADD_TO_DEVICE:
+	case SWITCHDEV_FDB_DEL_TO_DEVICE:
+		err = switchdev_handle_fdb_event_to_device(dev, event, ptr,
+							   dpaa2_switch_port_dev_check,
+							   dpaa2_switch_foreign_dev_check,
+							   dpaa2_switch_port_fdb_event);
+		return notifier_from_errno(err);
+	default:
+		return NOTIFY_DONE;
 	}
-
-	port_obj_info->handled = true;
-	return notifier_from_errno(err);
 }
 
 static int dpaa2_switch_port_blocking_event(struct notifier_block *nb,
 					    unsigned long event, void *ptr)
 {
 	struct net_device *dev = switchdev_notifier_info_to_dev(ptr);
+	int err;
 
 	switch (event) {
 	case SWITCHDEV_PORT_OBJ_ADD:
+		err = switchdev_handle_port_obj_add(dev, ptr,
+						    dpaa2_switch_port_dev_check,
+						    dpaa2_switch_port_obj_add);
+		return notifier_from_errno(err);
 	case SWITCHDEV_PORT_OBJ_DEL:
-		return dpaa2_switch_port_obj_event(event, dev, ptr);
+		err = switchdev_handle_port_obj_del(dev, ptr,
+						    dpaa2_switch_port_dev_check,
+						    dpaa2_switch_port_obj_del);
+		return notifier_from_errno(err);
 	case SWITCHDEV_PORT_ATTR_SET:
 		return dpaa2_switch_port_attr_set_event(dev, ptr);
 	}
@@ -2490,19 +3120,22 @@ static void dpaa2_switch_rx(struct dpaa2_switch_fq *fq,
 	dma_addr_t addr = dpaa2_fd_get_addr(fd);
 	struct ethsw_core *ethsw = fq->ethsw;
 	struct ethsw_port_priv *port_priv;
+	struct dpaa2_switch_lag *lag;
 	struct net_device *netdev;
 	struct vlan_ethhdr *hdr;
 	struct sk_buff *skb;
 	u16 vlan_tci, vid;
 	int if_id, err;
 	void *vaddr;
+	u64 flc;
 
 	vaddr = dpaa2_iova_to_virt(ethsw->iommu_domain, addr);
 	dma_unmap_page(ethsw->dev, addr, DPAA2_SWITCH_RX_BUF_SIZE,
 		       DMA_FROM_DEVICE);
 
 	/* get switch ingress interface ID */
-	if_id = upper_32_bits(dpaa2_fd_get_flc(fd)) & 0x0000FFFF;
+	flc = dpaa2_fd_get_flc(fd);
+	if_id = DPAA2_ETHSW_FLC_IF_ID(flc);
 	if (if_id >= ethsw->sw_attr.num_ifs) {
 		dev_err(ethsw->dev, "Frame received from unknown interface!\n");
 		goto err_free_fd;
@@ -2541,12 +3174,20 @@ static void dpaa2_switch_rx(struct dpaa2_switch_fq *fq,
 		}
 	}
 
-	skb->dev = netdev;
+	rcu_read_lock();
+
+	lag = rcu_dereference(port_priv->lag);
+	if (DPAA2_ETHSW_FLC_IMPRECISE_IF_ID(flc) && lag)
+		skb->dev = lag->bond_dev;
+	else
+		skb->dev = netdev;
 	skb->protocol = eth_type_trans(skb, skb->dev);
 
 	/* Setup the offload_fwd_mark only if the port is under a bridge */
 	skb->offload_fwd_mark = !!(port_priv->fdb->bridge_dev);
 
+	rcu_read_unlock();
+
 	netif_receive_skb(skb);
 
 	return;
@@ -2561,6 +3202,9 @@ static void dpaa2_switch_detect_features(struct ethsw_core *ethsw)
 
 	if (ethsw->major > 8 || (ethsw->major == 8 && ethsw->minor >= 6))
 		ethsw->features |= ETHSW_FEATURE_MAC_ADDR;
+
+	if (ethsw->major > 8 || (ethsw->major == 8 && ethsw->minor >= 13))
+		ethsw->features |= ETHSW_FEATURE_LAG_OFFLOAD;
 }
 
 static int dpaa2_switch_setup_fqs(struct ethsw_core *ethsw)
@@ -3195,17 +3839,15 @@ err_close:
 	return err;
 }
 
-/* Add an ACL to redirect frames with specific destination MAC address to
- * control interface
- */
+/* Add an ACL to redirect frames to control interface based on the dst MAC */
 static int dpaa2_switch_port_trap_mac_addr(struct ethsw_port_priv *port_priv,
-					   const char *mac)
+					   const u8 *mac, const u8 *mask)
 {
 	struct dpaa2_switch_acl_entry acl_entry = {0};
 
 	/* Match on the destination MAC address */
 	ether_addr_copy(acl_entry.key.match.l2_dest_mac, mac);
-	eth_broadcast_addr(acl_entry.key.mask.l2_dest_mac);
+	ether_addr_copy(acl_entry.key.mask.l2_dest_mac, mask);
 
 	/* Trap to CPU */
 	acl_entry.cfg.precedence = 0;
@@ -3216,7 +3858,8 @@ static int dpaa2_switch_port_trap_mac_addr(struct ethsw_port_priv *port_priv,
 
 static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
 {
-	const char stpa[ETH_ALEN] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
+	const u8 ll_mac[ETH_ALEN] = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x00};
+	const u8 ll_mask[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xf0};
 	struct switchdev_obj_port_vlan vlan = {
 		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
 		.vid = DEFAULT_VLAN_ID,
@@ -3291,7 +3934,7 @@ static int dpaa2_switch_port_init(struct ethsw_port_priv *port_priv, u16 port)
 	if (err)
 		return err;
 
-	err = dpaa2_switch_port_trap_mac_addr(port_priv, stpa);
+	err = dpaa2_switch_port_trap_mac_addr(port_priv, ll_mac, ll_mask);
 	if (err)
 		return err;
 
@@ -3331,6 +3974,9 @@ static void dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 	dev = &sw_dev->dev;
 	ethsw = dev_get_drvdata(dev);
 
+	/* Make sure that all events were handled before we kfree anything */
+	flush_workqueue(ethsw->workqueue);
+
 	dpaa2_switch_teardown_irqs(sw_dev);
 
 	dpsw_disable(ethsw->mc_io, 0, ethsw->dpsw_handle);
@@ -3344,12 +3990,15 @@ static void dpaa2_switch_remove(struct fsl_mc_device *sw_dev)
 	for (i = 0; i < DPAA2_SWITCH_RX_NUM_FQS; i++)
 		netif_napi_del(&ethsw->fq[i].napi);
 
-	for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
 		dpaa2_switch_remove_port(ethsw, i);
+		mutex_destroy(&ethsw->lags[i].fdb_lock);
+	}
 
 	kfree(ethsw->fdbs);
 	kfree(ethsw->filter_blocks);
 	kfree(ethsw->ports);
+	kfree(ethsw->lags);
 
 	dpaa2_switch_teardown(sw_dev);
 
@@ -3377,6 +4026,7 @@ static int dpaa2_switch_probe_port(struct ethsw_core *ethsw,
 	port_priv = netdev_priv(port_netdev);
 	port_priv->netdev = port_netdev;
 	port_priv->ethsw_data = ethsw;
+	rcu_assign_pointer(port_priv->lag, NULL);
 
 	mutex_init(&port_priv->mac_lock);
 
@@ -3484,6 +4134,21 @@ static int dpaa2_switch_probe(struct fsl_mc_device *sw_dev)
 		goto err_free_fdbs;
 	}
 
+	ethsw->lags = kcalloc(ethsw->sw_attr.num_ifs, sizeof(*ethsw->lags),
+			      GFP_KERNEL);
+	if (!ethsw->lags) {
+		err = -ENOMEM;
+		goto err_free_filter;
+	}
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
+		ethsw->lags[i].bond_dev = NULL;
+		ethsw->lags[i].ethsw = ethsw;
+		ethsw->lags[i].id = i + 1;
+		ethsw->lags[i].in_use = 0;
+		mutex_init(&ethsw->lags[i].fdb_lock);
+		INIT_LIST_HEAD(&ethsw->lags[i].fdbs);
+	}
+
 	for (i = 0; i < ethsw->sw_attr.num_ifs; i++) {
 		err = dpaa2_switch_probe_port(ethsw, i);
 		if (err)
@@ -3530,6 +4195,10 @@ err_stop:
 err_free_netdev:
 	for (i--; i >= 0; i--)
 		dpaa2_switch_remove_port(ethsw, i);
+	for (i = 0; i < ethsw->sw_attr.num_ifs; i++)
+		mutex_destroy(&ethsw->lags[i].fdb_lock);
+	kfree(ethsw->lags);
+err_free_filter:
 	kfree(ethsw->filter_blocks);
 err_free_fdbs:
 	kfree(ethsw->fdbs);
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
index 42b3ca73f55d..63b702b0000c 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.h
@@ -41,7 +41,8 @@
 #define ETHSW_MAX_FRAME_LENGTH	(DPAA2_MFL - VLAN_ETH_HLEN - ETH_FCS_LEN)
 #define ETHSW_L2_MAX_FRM(mtu)	((mtu) + VLAN_ETH_HLEN + ETH_FCS_LEN)
 
-#define ETHSW_FEATURE_MAC_ADDR	BIT(0)
+#define ETHSW_FEATURE_MAC_ADDR		BIT(0)
+#define ETHSW_FEATURE_LAG_OFFLOAD	BIT(1)
 
 /* Number of receive queues (one RX and one TX_CONF) */
 #define DPAA2_SWITCH_RX_NUM_FQS	2
@@ -86,6 +87,9 @@
 
 #define DPAA2_ETHSW_PORT_ACL_CMD_BUF_SIZE	256
 
+#define DPAA2_ETHSW_FLC_IF_ID(flc)		(((flc) >> 32) & GENMASK(15, 0))
+#define DPAA2_ETHSW_FLC_IMPRECISE_IF_ID(flc)	((flc) & BIT_ULL(63))
+
 extern const struct ethtool_ops dpaa2_switch_port_ethtool_ops;
 
 struct ethsw_core;
@@ -99,12 +103,30 @@ struct dpaa2_switch_fq {
 	u32 fqid;
 };
 
+struct dpaa2_mac_addr {
+	unsigned char addr[ETH_ALEN];
+	u16 vid;
+	refcount_t refcount;
+	struct list_head list;
+};
+
 struct dpaa2_switch_fdb {
 	struct net_device	*bridge_dev;
 	u16			fdb_id;
 	bool			in_use;
 };
 
+struct dpaa2_switch_lag {
+	struct ethsw_core	*ethsw;
+	struct net_device	*bond_dev;
+	bool			in_use;
+	u8			id;
+	struct ethsw_port_priv	*primary;
+	/* Protects the list of fdbs installed on this LAG */
+	struct mutex		fdb_lock;
+	struct list_head	fdbs;
+};
+
 struct dpaa2_switch_acl_entry {
 	struct list_head	list;
 	u16			prio;
@@ -163,6 +185,8 @@ struct ethsw_port_priv {
 	struct dpaa2_mac	*mac;
 	/* Protects against changes to port_priv->mac */
 	struct mutex		mac_lock;
+
+	struct dpaa2_switch_lag __rcu *lag;
 };
 
 /* Switch data */
@@ -190,6 +214,8 @@ struct ethsw_core {
 	struct dpaa2_switch_fdb		*fdbs;
 	struct dpaa2_switch_filter_block *filter_blocks;
 	u16				mirror_port;
+
+	struct dpaa2_switch_lag		*lags;
 };
 
 static inline int dpaa2_switch_get_index(struct ethsw_core *ethsw,
@@ -274,4 +300,18 @@ int dpaa2_switch_block_offload_mirror(struct dpaa2_switch_filter_block *block,
 
 int dpaa2_switch_block_unoffload_mirror(struct dpaa2_switch_filter_block *block,
 					struct ethsw_port_priv *port_priv);
+
+static inline bool
+dpaa2_switch_port_offloads_bridge_port(struct ethsw_port_priv *port_priv,
+				       const struct net_device *dev)
+{
+	struct dpaa2_switch_lag *lag = rcu_dereference_rtnl(port_priv->lag);
+
+	if (lag && lag->bond_dev == dev)
+		return true;
+	if (port_priv->netdev == dev)
+		return true;
+	return false;
+}
+
 #endif	/* __ETHSW_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
index 397d55f2bd99..9a2055c64983 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw-cmd.h
@@ -12,7 +12,7 @@
 
 /* DPSW Version */
 #define DPSW_VER_MAJOR		8
-#define DPSW_VER_MINOR		9
+#define DPSW_VER_MINOR		13
 
 #define DPSW_CMD_BASE_VERSION	1
 #define DPSW_CMD_VERSION_2	2
@@ -92,11 +92,14 @@
 #define DPSW_CMDID_CTRL_IF_SET_POOLS        DPSW_CMD_ID(0x0A1)
 #define DPSW_CMDID_CTRL_IF_ENABLE           DPSW_CMD_ID(0x0A2)
 #define DPSW_CMDID_CTRL_IF_DISABLE          DPSW_CMD_ID(0x0A3)
+#define DPSW_CMDID_SET_LAG                  DPSW_CMD_V2(0x0A4)
 #define DPSW_CMDID_CTRL_IF_SET_QUEUE        DPSW_CMD_ID(0x0A6)
 
 #define DPSW_CMDID_SET_EGRESS_FLOOD         DPSW_CMD_ID(0x0AC)
 #define DPSW_CMDID_IF_SET_LEARNING_MODE     DPSW_CMD_ID(0x0AD)
 
+#define DPSW_CMDID_IF_SET_LAG_STATE         DPSW_CMD_ID(0x0B0)
+
 /* Macros for accessing command fields smaller than 1byte */
 #define DPSW_MASK(field)        \
 	GENMASK(DPSW_##field##_SHIFT + DPSW_##field##_SIZE - 1, \
@@ -552,5 +555,18 @@ struct dpsw_cmd_if_reflection {
 	/* only 2 bits from the LSB */
 	u8 filter;
 };
+
+struct dpsw_cmd_lag {
+	u8 group_id;
+	u8 num_ifs;
+	u8 pad[6];
+	u8 if_id[DPSW_MAX_LAG_IFS];
+	u8 phase;
+};
+
+struct dpsw_cmd_if_set_lag_state {
+	__le16 if_id;
+	u8 tx_enabled;
+};
 #pragma pack(pop)
 #endif /* __FSL_DPSW_CMD_H */
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.c b/drivers/net/ethernet/freescale/dpaa2/dpsw.c
index ab921d75deb2..f75cbdce42ba 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.c
@@ -1659,3 +1659,63 @@ int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 
 	return mc_send_command(mc_io, &cmd);
 }
+
+/**
+ * dpsw_lag_set() - Set LAG configuration
+ * @mc_io:	Pointer to MC portal's I/O object
+ * @cmd_flags:	Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:	Token of DPSW object
+ * @cfg:	pointer to LAG configuration
+ *
+ * Return:   '0' on Success; Error code otherwise.
+ */
+int dpsw_lag_set(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+		 const struct dpsw_lag_cfg *cfg)
+{
+	struct fsl_mc_command cmd = { 0 };
+	struct dpsw_cmd_lag *cmd_params;
+	int i = 0;
+
+	cmd.header = mc_encode_cmd_header(DPSW_CMDID_SET_LAG, cmd_flags, token);
+
+	if (cfg->num_ifs > DPSW_MAX_LAG_IFS)
+		return -EOPNOTSUPP;
+
+	cmd_params = (struct dpsw_cmd_lag *)cmd.params;
+	cmd_params->group_id = cfg->group_id;
+	cmd_params->num_ifs = cfg->num_ifs;
+	cmd_params->phase = cfg->phase;
+
+	for (i = 0; i < cfg->num_ifs; i++)
+		cmd_params->if_id[i] = cfg->if_id[i];
+
+	return mc_send_command(mc_io, &cmd);
+}
+
+/**
+ * dpsw_if_set_lag_state() - Change per port LAG state
+ * @mc_io:      Pointer to MC portal's I/O object
+ * @cmd_flags:  Command flags; one or more of 'MC_CMD_FLAG_'
+ * @token:      Token of DPSW object
+ * @if_id:      ID of the switch interface
+ * @tx_enabled: Value of the per port LAG state
+ *     - 0 if the interface will not be active as part of the LAG group
+ *     - 1 if the interface will be active in the LAG group
+ *
+ * Return:   '0' on Success; Error code otherwise.
+ */
+int dpsw_if_set_lag_state(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			  u16 if_id, u8 tx_enabled)
+{
+	struct dpsw_cmd_if_set_lag_state *cmd_params;
+	struct fsl_mc_command cmd = { 0 };
+
+	cmd.header = mc_encode_cmd_header(DPSW_CMDID_IF_SET_LAG_STATE,
+					  cmd_flags, token);
+
+	cmd_params = (struct dpsw_cmd_if_set_lag_state *)cmd.params;
+	cmd_params->if_id = cpu_to_le16(if_id);
+	cmd_params->tx_enabled = tx_enabled;
+
+	return mc_send_command(mc_io, &cmd);
+}
diff --git a/drivers/net/ethernet/freescale/dpaa2/dpsw.h b/drivers/net/ethernet/freescale/dpaa2/dpsw.h
index b90bd363f47a..89f0267de8e9 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpsw.h
+++ b/drivers/net/ethernet/freescale/dpaa2/dpsw.h
@@ -20,6 +20,8 @@ struct fsl_mc_io;
 
 #define DPSW_MAX_IF		64
 
+#define DPSW_MAX_LAG_IFS	8
+
 int dpsw_open(struct fsl_mc_io *mc_io, u32 cmd_flags, int dpsw_id, u16 *token);
 
 int dpsw_close(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token);
@@ -788,4 +790,32 @@ int dpsw_if_add_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 
 int dpsw_if_remove_reflection(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
 			      u16 if_id, const struct dpsw_reflection_cfg *cfg);
+
+/* Link Aggregation Group configuration */
+
+#define DPSW_LAG_SET_PHASE_APPLY 0
+#define DPSW_LAG_SET_PHASE_CHECK 1
+
+/**
+ * struct dpsw_lag_cfg - Configuration structure for a LAG group
+ * @group_id: Link aggregation group ID. Valid values are in the
+ * [1, DPSW_MAX_LAG_IFS] range.
+ * @num_ifs: Number of interfaces in this LAG group, valid range is
+ * [0, DPSW_MAX_LAG_IFS].
+ * @if_id: Array containing the interface IDs of the ports part of a LAG group
+ * @phase: Use DPSW_LAG_SET_PHASE_APPLY for LAG configuration processing or
+ * DPSW_LAG_SET_PHASE_CHECK for LAG configuration validation.
+ */
+struct dpsw_lag_cfg {
+	u8 group_id;
+	u8 num_ifs;
+	u8 if_id[DPSW_MAX_LAG_IFS];
+	u8 phase;
+};
+
+int dpsw_lag_set(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+		 const struct dpsw_lag_cfg *cfg);
+
+int dpsw_if_set_lag_state(struct fsl_mc_io *mc_io, u32 cmd_flags, u16 token,
+			  u16 if_id, u8 tx_enabled);
 #endif /* __FSL_DPSW_H */