Merge tag 'mlx5-updates-2021-04-21' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2021-04-21

devlink external port attribute for SF (Sub-Function) port flavour

This adds the support to instantiate Sub-Functions on external hosts
E.g when Eswitch manager is enabled on the ARM SmarNic SoC CPU, users
are now able to spawn new Sub-Functions on the Host server CPU.

Parav Pandit Says:
==================

This series introduces and uses external attribute for the SF port to
indicate that a SF port belongs to an external controller.

This is needed to generate unique phys_port_name when PF and SF numbers
are overlapping between local and external controllers.
For example two controllers 0 and 1, both of these controller have a SF.
having PF number 0, SF number 77. Here, phys_port_name has duplicate
entry which doesn't have controller number in it.

Hence, add controller number optionally when a SF port is for an
external controller. This extension is similar to existing PF and VF
eswitch ports of the external controller.

When a SF is for external controller an example view of external SF
port and config sequence:

On eswitch system:
$ devlink dev eswitch set pci/0033:01:00.0 mode switchdev

$ devlink port show
pci/0033:01:00.0/196607: type eth netdev enP51p1s0f0np0 flavour physical port 0 splittable false
pci/0033:01:00.0/131072: type eth netdev eth0 flavour pcipf controller 1 pfnum 0 external true splittable false
  function:
    hw_addr 00:00:00:00:00:00

$ devlink port add pci/0033:01:00.0 flavour pcisf pfnum 0 sfnum 77 controller 1
pci/0033:01:00.0/163840: type eth netdev eth1 flavour pcisf controller 1 pfnum 0 sfnum 77 splittable false
  function:
    hw_addr 00:00:00:00:00:00 state inactive opstate detached

phys_port_name construction:
$ cat /sys/class/net/eth1/phys_port_name
c1pf0sf77

Patch summary:
First 3 patches prepares the eswitch to handle vports in more generic
way using xarray to lookup vport from its unique vport number.
Patch-1 returns maximum eswitch ports only when eswitch is enabled
Patch-2 prepares eswitch to return eswitch max ports from a struct
Patch-3 uses xarray for vport and representor lookup
Patch-4 considers SF for an additioanl range of SF vports
Patch-5 relies on SF hw table to check SF support
Patch-6 extends SF devlink port attribute for external flag
Patch-7 stores the per controller SF allocation attributes
Patch-8 uses SF function id for filtering events
Patch-9 uses helper for allocation and free
Patch-10 splits hw table into per controller table and generic one
Patch-11 extends sf table for additional range

==================

====================

Signed-off-by: David S. Miller <davem@davemloft.net>

20 files changed, 724 insertions, 434 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
index 3e19b1721303..0399a396d166 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_lgcy.c
@@ -96,7 +96,7 @@ int esw_acl_egress_lgcy_setup(struct mlx5_eswitch *esw,
 	}
 
 	if (!vport->egress.acl) {
-		vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+		vport->egress.acl = esw_acl_table_create(esw, vport,
 							 MLX5_FLOW_NAMESPACE_ESW_EGRESS,
 							 table_size);
 		if (IS_ERR(vport->egress.acl)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
index 26b37a0f8762..505bf811984a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c
@@ -148,7 +148,7 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
 	esw_acl_egress_vlan_grp_destroy(vport);
 }
 
-static bool esw_acl_egress_needed(const struct mlx5_eswitch *esw, u16 vport_num)
+static bool esw_acl_egress_needed(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	return mlx5_eswitch_is_vf_vport(esw, vport_num) || mlx5_esw_is_sf_vport(esw, vport_num);
 }
@@ -171,7 +171,7 @@ int esw_acl_egress_ofld_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport
 		table_size++;
 	if (MLX5_CAP_GEN(esw->dev, prio_tag_required))
 		table_size++;
-	vport->egress.acl = esw_acl_table_create(esw, vport->vport,
+	vport->egress.acl = esw_acl_table_create(esw, vport,
 						 MLX5_FLOW_NAMESPACE_ESW_EGRESS, table_size);
 	if (IS_ERR(vport->egress.acl)) {
 		err = PTR_ERR(vport->egress.acl);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
index 4a369669e51e..45b839116212 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
@@ -6,14 +6,14 @@
 #include "helper.h"
 
 struct mlx5_flow_table *
-esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size)
+esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns, int size)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_namespace *root_ns;
 	struct mlx5_flow_table *acl;
 	int acl_supported;
-	int vport_index;
+	u16 vport_num;
 	int err;
 
 	acl_supported = (ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS) ?
@@ -23,11 +23,11 @@ esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size)
 	if (!acl_supported)
 		return ERR_PTR(-EOPNOTSUPP);
 
+	vport_num = vport->vport;
 	esw_debug(dev, "Create vport[%d] %s ACL table\n", vport_num,
 		  ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress");
 
-	vport_index = mlx5_eswitch_vport_num_to_index(esw, vport_num);
-	root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport_index);
+	root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport->index);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch root namespace for vport (%d)\n",
 			 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
index 8dc4cab66a71..a47063fab57e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.h
@@ -8,7 +8,7 @@
 
 /* General acl helper functions */
 struct mlx5_flow_table *
-esw_acl_table_create(struct mlx5_eswitch *esw, u16 vport_num, int ns, int size);
+esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns, int size);
 
 /* Egress acl helper functions */
 void esw_acl_egress_table_destroy(struct mlx5_vport *vport);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
index d64fad2823e7..f75b86abaf1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_lgcy.c
@@ -177,7 +177,7 @@ int esw_acl_ingress_lgcy_setup(struct mlx5_eswitch *esw,
 	}
 
 	if (!vport->ingress.acl) {
-		vport->ingress.acl = esw_acl_table_create(esw, vport->vport,
+		vport->ingress.acl = esw_acl_table_create(esw, vport,
 							  MLX5_FLOW_NAMESPACE_ESW_INGRESS,
 							  table_size);
 		if (IS_ERR(vport->ingress.acl)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
index 548c005ea633..39e948bc1204 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/ingress_ofld.c
@@ -7,7 +7,7 @@
 #include "ofld.h"
 
 static bool
-esw_acl_ingress_prio_tag_enabled(const struct mlx5_eswitch *esw,
+esw_acl_ingress_prio_tag_enabled(struct mlx5_eswitch *esw,
 				 const struct mlx5_vport *vport)
 {
 	return (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
@@ -255,7 +255,7 @@ int esw_acl_ingress_ofld_setup(struct mlx5_eswitch *esw,
 	if (esw_acl_ingress_prio_tag_enabled(esw, vport))
 		num_ftes++;
 
-	vport->ingress.acl = esw_acl_table_create(esw, vport->vport,
+	vport->ingress.acl = esw_acl_table_create(esw, vport,
 						  MLX5_FLOW_NAMESPACE_ESW_INGRESS,
 						  num_ftes);
 	if (IS_ERR(vport->ingress.acl)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 7bfc84238b3d..1703384eca95 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -14,8 +14,7 @@ mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_i
 	memcpy(ppid->id, &parent_id, sizeof(parent_id));
 }
 
-static bool
-mlx5_esw_devlink_port_supported(const struct mlx5_eswitch *esw, u16 vport_num)
+static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	return vport_num == MLX5_VPORT_UPLINK ||
 	       (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) ||
@@ -124,7 +123,7 @@ struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u1
 }
 
 int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 sfnum)
+				      u16 vport_num, u32 controller, u32 sfnum)
 {
 	struct mlx5_core_dev *dev = esw->dev;
 	struct netdev_phys_item_id ppid = {};
@@ -142,7 +141,7 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p
 	mlx5_esw_get_port_parent_id(dev, &ppid);
 	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 	dl_port->attrs.switch_id.id_len = ppid.id_len;
-	devlink_port_attrs_pci_sf_set(dl_port, 0, pfnum, sfnum);
+	devlink_port_attrs_pci_sf_set(dl_port, controller, pfnum, sfnum, !!controller);
 	devlink = priv_to_devlink(dev);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(dev, vport_num);
 	err = devlink_port_register(devlink, dl_port, dl_port_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 8ab1224653a4..d9041b16611d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -216,7 +216,8 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
 int esw_legacy_enable(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
-	int ret, i;
+	unsigned long i;
+	int ret;
 
 	ret = esw_create_legacy_table(esw);
 	if (ret)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 1bb229ecd43b..570f2280823c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -88,20 +88,17 @@ struct mlx5_eswitch *mlx5_devlink_eswitch_get(struct devlink *devlink)
 struct mlx5_vport *__must_check
 mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num)
 {
-	u16 idx;
+	struct mlx5_vport *vport;
 
 	if (!esw || !MLX5_CAP_GEN(esw->dev, vport_group_manager))
 		return ERR_PTR(-EPERM);
 
-	idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
-
-	if (idx > esw->total_vports - 1) {
-		esw_debug(esw->dev, "vport out of range: num(0x%x), idx(0x%x)\n",
-			  vport_num, idx);
+	vport = xa_load(&esw->vports, vport_num);
+	if (!vport) {
+		esw_debug(esw->dev, "vport out of range: num(0x%x)\n", vport_num);
 		return ERR_PTR(-EINVAL);
 	}
-
-	return &esw->vports[idx];
+	return vport;
 }
 
 static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
@@ -345,9 +342,10 @@ static void update_allmulti_vports(struct mlx5_eswitch *esw,
 {
 	u8 *mac = vaddr->node.addr;
 	struct mlx5_vport *vport;
-	u16 i, vport_num;
+	unsigned long i;
+	u16 vport_num;
 
-	mlx5_esw_for_all_vports(esw, i, vport) {
+	mlx5_esw_for_each_vport(esw, i, vport) {
 		struct hlist_head *vport_hash = vport->mc_list;
 		struct vport_addr *iter_vaddr =
 					l2addr_hash_find(vport_hash,
@@ -1175,7 +1173,7 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
 static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
-	int i;
+	unsigned long i;
 
 	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
 		memset(&vport->qos, 0, sizeof(vport->qos));
@@ -1213,20 +1211,25 @@ void mlx5_eswitch_unload_vport(struct mlx5_eswitch *esw, u16 vport_num)
 
 void mlx5_eswitch_unload_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs)
 {
-	int i;
+	struct mlx5_vport *vport;
+	unsigned long i;
 
-	mlx5_esw_for_each_vf_vport_num_reverse(esw, i, num_vfs)
-		mlx5_eswitch_unload_vport(esw, i);
+	mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
+		if (!vport->enabled)
+			continue;
+		mlx5_eswitch_unload_vport(esw, vport->vport);
+	}
 }
 
 int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 				enum mlx5_eswitch_vport_event enabled_events)
 {
+	struct mlx5_vport *vport;
+	unsigned long i;
 	int err;
-	int i;
 
-	mlx5_esw_for_each_vf_vport_num(esw, i, num_vfs) {
-		err = mlx5_eswitch_load_vport(esw, i, enabled_events);
+	mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
+		err = mlx5_eswitch_load_vport(esw, vport->vport, enabled_events);
 		if (err)
 			goto vf_err;
 	}
@@ -1234,7 +1237,7 @@ int mlx5_eswitch_load_vf_vports(struct mlx5_eswitch *esw, u16 num_vfs,
 	return 0;
 
 vf_err:
-	mlx5_eswitch_unload_vf_vports(esw, i - 1);
+	mlx5_eswitch_unload_vf_vports(esw, num_vfs);
 	return err;
 }
 
@@ -1563,24 +1566,161 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf)
 	up_write(&esw->mode_lock);
 }
 
+static int mlx5_query_hca_cap_host_pf(struct mlx5_core_dev *dev, void *out)
+{
+	u16 opmod = (MLX5_CAP_GENERAL << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01);
+	u8 in[MLX5_ST_SZ_BYTES(query_hca_cap_in)] = {};
+
+	MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP);
+	MLX5_SET(query_hca_cap_in, in, op_mod, opmod);
+	MLX5_SET(query_hca_cap_in, in, function_id, MLX5_VPORT_PF);
+	MLX5_SET(query_hca_cap_in, in, other_function, true);
+	return mlx5_cmd_exec_inout(dev, query_hca_cap, in, out);
+}
+
+int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *sf_base_id)
+
+{
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *query_ctx;
+	void *hca_caps;
+	int err;
+
+	if (!mlx5_core_is_ecpf(dev)) {
+		*max_sfs = 0;
+		return 0;
+	}
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx)
+		return -ENOMEM;
+
+	err = mlx5_query_hca_cap_host_pf(dev, query_ctx);
+	if (err)
+		goto out_free;
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	*max_sfs = MLX5_GET(cmd_hca_cap, hca_caps, max_num_sf);
+	*sf_base_id = MLX5_GET(cmd_hca_cap, hca_caps, sf_base_id);
+
+out_free:
+	kfree(query_ctx);
+	return err;
+}
+
+static int mlx5_esw_vport_alloc(struct mlx5_eswitch *esw, struct mlx5_core_dev *dev,
+				int index, u16 vport_num)
+{
+	struct mlx5_vport *vport;
+	int err;
+
+	vport = kzalloc(sizeof(*vport), GFP_KERNEL);
+	if (!vport)
+		return -ENOMEM;
+
+	vport->dev = esw->dev;
+	vport->vport = vport_num;
+	vport->index = index;
+	vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
+	INIT_WORK(&vport->vport_change_handler, esw_vport_change_handler);
+	err = xa_insert(&esw->vports, vport_num, vport, GFP_KERNEL);
+	if (err)
+		goto insert_err;
+
+	esw->total_vports++;
+	return 0;
+
+insert_err:
+	kfree(vport);
+	return err;
+}
+
+static void mlx5_esw_vport_free(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+	xa_erase(&esw->vports, vport->vport);
+	kfree(vport);
+}
+
+static void mlx5_esw_vports_cleanup(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+
+	mlx5_esw_for_each_vport(esw, i, vport)
+		mlx5_esw_vport_free(esw, vport);
+	xa_destroy(&esw->vports);
+}
+
+static int mlx5_esw_vports_init(struct mlx5_eswitch *esw)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	u16 max_host_pf_sfs;
+	u16 base_sf_num;
+	int idx = 0;
+	int err;
+	int i;
+
+	xa_init(&esw->vports);
+
+	err = mlx5_esw_vport_alloc(esw, dev, idx, MLX5_VPORT_PF);
+	if (err)
+		goto err;
+	if (esw->first_host_vport == MLX5_VPORT_PF)
+		xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_HOST_FN);
+	idx++;
+
+	for (i = 0; i < mlx5_core_max_vfs(dev); i++) {
+		err = mlx5_esw_vport_alloc(esw, dev, idx, idx);
+		if (err)
+			goto err;
+		xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_VF);
+		xa_set_mark(&esw->vports, idx, MLX5_ESW_VPT_HOST_FN);
+		idx++;
+	}
+	base_sf_num = mlx5_sf_start_function_id(dev);
+	for (i = 0; i < mlx5_sf_max_functions(dev); i++) {
+		err = mlx5_esw_vport_alloc(esw, dev, idx, base_sf_num + i);
+		if (err)
+			goto err;
+		xa_set_mark(&esw->vports, base_sf_num + i, MLX5_ESW_VPT_SF);
+		idx++;
+	}
+
+	err = mlx5_esw_sf_max_hpf_functions(dev, &max_host_pf_sfs, &base_sf_num);
+	if (err)
+		goto err;
+	for (i = 0; i < max_host_pf_sfs; i++) {
+		err = mlx5_esw_vport_alloc(esw, dev, idx, base_sf_num + i);
+		if (err)
+			goto err;
+		xa_set_mark(&esw->vports, base_sf_num + i, MLX5_ESW_VPT_SF);
+		idx++;
+	}
+
+	if (mlx5_ecpf_vport_exists(dev)) {
+		err = mlx5_esw_vport_alloc(esw, dev, idx, MLX5_VPORT_ECPF);
+		if (err)
+			goto err;
+		idx++;
+	}
+	err = mlx5_esw_vport_alloc(esw, dev, idx, MLX5_VPORT_UPLINK);
+	if (err)
+		goto err;
+	return 0;
+
+err:
+	mlx5_esw_vports_cleanup(esw);
+	return err;
+}
+
 int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_eswitch *esw;
-	struct mlx5_vport *vport;
-	int total_vports;
-	int err, i;
+	int err;
 
 	if (!MLX5_VPORT_MANAGER(dev))
 		return 0;
 
-	total_vports = mlx5_eswitch_get_total_vports(dev);
-
-	esw_info(dev,
-		 "Total vports %d, per vport: max uc(%d) max mc(%d)\n",
-		 total_vports,
-		 MLX5_MAX_UC_PER_VPORT(dev),
-		 MLX5_MAX_MC_PER_VPORT(dev));
-
 	esw = kzalloc(sizeof(*esw), GFP_KERNEL);
 	if (!esw)
 		return -ENOMEM;
@@ -1595,18 +1735,13 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		goto abort;
 	}
 
-	esw->vports = kcalloc(total_vports, sizeof(struct mlx5_vport),
-			      GFP_KERNEL);
-	if (!esw->vports) {
-		err = -ENOMEM;
+	err = mlx5_esw_vports_init(esw);
+	if (err)
 		goto abort;
-	}
-
-	esw->total_vports = total_vports;
 
 	err = esw_offloads_init_reps(esw);
 	if (err)
-		goto abort;
+		goto reps_err;
 
 	mutex_init(&esw->offloads.encap_tbl_lock);
 	hash_init(esw->offloads.encap_tbl);
@@ -1619,25 +1754,25 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	mutex_init(&esw->state_lock);
 	init_rwsem(&esw->mode_lock);
 
-	mlx5_esw_for_all_vports(esw, i, vport) {
-		vport->vport = mlx5_eswitch_index_to_vport_num(esw, i);
-		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
-		vport->dev = dev;
-		INIT_WORK(&vport->vport_change_handler,
-			  esw_vport_change_handler);
-	}
-
 	esw->enabled_vports = 0;
 	esw->mode = MLX5_ESWITCH_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
 
 	dev->priv.eswitch = esw;
 	BLOCKING_INIT_NOTIFIER_HEAD(&esw->n_head);
+
+	esw_info(dev,
+		 "Total vports %d, per vport: max uc(%d) max mc(%d)\n",
+		 esw->total_vports,
+		 MLX5_MAX_UC_PER_VPORT(dev),
+		 MLX5_MAX_MC_PER_VPORT(dev));
 	return 0;
+
+reps_err:
+	mlx5_esw_vports_cleanup(esw);
 abort:
 	if (esw->work_queue)
 		destroy_workqueue(esw->work_queue);
-	kfree(esw->vports);
 	kfree(esw);
 	return err;
 }
@@ -1659,7 +1794,7 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw)
 	mutex_destroy(&esw->offloads.encap_tbl_lock);
 	mutex_destroy(&esw->offloads.decap_tbl_lock);
 	esw_offloads_cleanup_reps(esw);
-	kfree(esw->vports);
+	mlx5_esw_vports_cleanup(esw);
 	kfree(esw);
 }
 
@@ -1718,8 +1853,29 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 	return err;
 }
 
+static bool mlx5_esw_check_port_type(struct mlx5_eswitch *esw, u16 vport_num, xa_mark_t mark)
+{
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return false;
+
+	return xa_get_mark(&esw->vports, vport_num, mark);
+}
+
+bool mlx5_eswitch_is_vf_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return mlx5_esw_check_port_type(esw, vport_num, MLX5_ESW_VPT_VF);
+}
+
+bool mlx5_esw_is_sf_vport(struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return mlx5_esw_check_port_type(esw, vport_num, MLX5_ESW_VPT_SF);
+}
+
 static bool
-is_port_function_supported(const struct mlx5_eswitch *esw, u16 vport_num)
+is_port_function_supported(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	return vport_num == MLX5_VPORT_PF ||
 	       mlx5_eswitch_is_vf_vport(esw, vport_num) ||
@@ -1891,9 +2047,9 @@ static u32 calculate_vports_min_rate_divider(struct mlx5_eswitch *esw)
 	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
 	struct mlx5_vport *evport;
 	u32 max_guarantee = 0;
-	int i;
+	unsigned long i;
 
-	mlx5_esw_for_all_vports(esw, i, evport) {
+	mlx5_esw_for_each_vport(esw, i, evport) {
 		if (!evport->enabled || evport->qos.min_rate < max_guarantee)
 			continue;
 		max_guarantee = evport->qos.min_rate;
@@ -1911,11 +2067,11 @@ static int normalize_vports_min_rate(struct mlx5_eswitch *esw)
 	struct mlx5_vport *evport;
 	u32 vport_max_rate;
 	u32 vport_min_rate;
+	unsigned long i;
 	u32 bw_share;
 	int err;
-	int i;
 
-	mlx5_esw_for_all_vports(esw, i, evport) {
+	mlx5_esw_for_each_vport(esw, i, evport) {
 		if (!evport->enabled)
 			continue;
 		vport_min_rate = evport->qos.min_rate;
@@ -2205,3 +2361,19 @@ void mlx5_esw_unlock(struct mlx5_eswitch *esw)
 {
 	up_write(&esw->mode_lock);
 }
+
+/**
+ * mlx5_eswitch_get_total_vports - Get total vports of the eswitch
+ *
+ * @dev: Pointer to core device
+ *
+ * mlx5_eswitch_get_total_vports returns total number of eswitch vports.
+ */
+u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev)
+{
+	struct mlx5_eswitch *esw;
+
+	esw = dev->priv.eswitch;
+	return mlx5_esw_allowed(esw) ? esw->total_vports : 0;
+}
+EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b289d756a7e4..64ccb2bc0b58 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -176,6 +176,7 @@ struct mlx5_vport {
 	u16 vport;
 	bool                    enabled;
 	enum mlx5_eswitch_vport_event enabled_events;
+	int index;
 	struct devlink_port *dl_port;
 };
 
@@ -228,7 +229,7 @@ struct mlx5_esw_offload {
 
 	struct mlx5_flow_table *ft_offloads;
 	struct mlx5_flow_group *vport_rx_group;
-	struct mlx5_eswitch_rep *vport_reps;
+	struct xarray vport_reps;
 	struct list_head peer_flows;
 	struct mutex peer_mutex;
 	struct mutex encap_tbl_lock; /* protects encap_tbl */
@@ -278,7 +279,7 @@ struct mlx5_eswitch {
 	struct esw_mc_addr mc_promisc;
 	/* end of legacy */
 	struct workqueue_struct *work_queue;
-	struct mlx5_vport       *vports;
+	struct xarray vports;
 	u32 flags;
 	int                     total_vports;
 	int                     enabled_vports;
@@ -545,94 +546,11 @@ static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev)
 		MLX5_VPORT_PF : MLX5_VPORT_FIRST_VF;
 }
 
-static inline int mlx5_esw_sf_start_idx(const struct mlx5_eswitch *esw)
-{
-	/* PF and VF vports indices start from 0 to max_vfs */
-	return MLX5_VPORT_PF_PLACEHOLDER + mlx5_core_max_vfs(esw->dev);
-}
-
-static inline int mlx5_esw_sf_end_idx(const struct mlx5_eswitch *esw)
-{
-	return mlx5_esw_sf_start_idx(esw) + mlx5_sf_max_functions(esw->dev);
-}
-
-static inline int
-mlx5_esw_sf_vport_num_to_index(const struct mlx5_eswitch *esw, u16 vport_num)
-{
-	return vport_num - mlx5_sf_start_function_id(esw->dev) +
-	       MLX5_VPORT_PF_PLACEHOLDER + mlx5_core_max_vfs(esw->dev);
-}
-
-static inline u16
-mlx5_esw_sf_vport_index_to_num(const struct mlx5_eswitch *esw, int idx)
-{
-	return mlx5_sf_start_function_id(esw->dev) + idx -
-	       (MLX5_VPORT_PF_PLACEHOLDER + mlx5_core_max_vfs(esw->dev));
-}
-
-static inline bool
-mlx5_esw_is_sf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
-{
-	return mlx5_sf_supported(esw->dev) &&
-	       vport_num >= mlx5_sf_start_function_id(esw->dev) &&
-	       (vport_num < (mlx5_sf_start_function_id(esw->dev) +
-			     mlx5_sf_max_functions(esw->dev)));
-}
-
 static inline bool mlx5_eswitch_is_funcs_handler(const struct mlx5_core_dev *dev)
 {
 	return mlx5_core_is_ecpf_esw_manager(dev);
 }
 
-static inline int mlx5_eswitch_uplink_idx(struct mlx5_eswitch *esw)
-{
-	/* Uplink always locate at the last element of the array.*/
-	return esw->total_vports - 1;
-}
-
-static inline int mlx5_eswitch_ecpf_idx(struct mlx5_eswitch *esw)
-{
-	return esw->total_vports - 2;
-}
-
-static inline int mlx5_eswitch_vport_num_to_index(struct mlx5_eswitch *esw,
-						  u16 vport_num)
-{
-	if (vport_num == MLX5_VPORT_ECPF) {
-		if (!mlx5_ecpf_vport_exists(esw->dev))
-			esw_warn(esw->dev, "ECPF vport doesn't exist!\n");
-		return mlx5_eswitch_ecpf_idx(esw);
-	}
-
-	if (vport_num == MLX5_VPORT_UPLINK)
-		return mlx5_eswitch_uplink_idx(esw);
-
-	if (mlx5_esw_is_sf_vport(esw, vport_num))
-		return mlx5_esw_sf_vport_num_to_index(esw, vport_num);
-
-	/* PF and VF vports start from 0 to max_vfs */
-	return vport_num;
-}
-
-static inline u16 mlx5_eswitch_index_to_vport_num(struct mlx5_eswitch *esw,
-						  int index)
-{
-	if (index == mlx5_eswitch_ecpf_idx(esw) &&
-	    mlx5_ecpf_vport_exists(esw->dev))
-		return MLX5_VPORT_ECPF;
-
-	if (index == mlx5_eswitch_uplink_idx(esw))
-		return MLX5_VPORT_UPLINK;
-
-	/* SF vports indices are after VFs and before ECPF */
-	if (mlx5_sf_supported(esw->dev) &&
-	    index > mlx5_core_max_vfs(esw->dev))
-		return mlx5_esw_sf_vport_index_to_num(esw, index);
-
-	/* PF and VF vports start from 0 to max_vfs */
-	return index;
-}
-
 static inline unsigned int
 mlx5_esw_vport_to_devlink_port_index(const struct mlx5_core_dev *dev,
 				     u16 vport_num)
@@ -649,82 +567,42 @@ mlx5_esw_devlink_port_index_to_vport_num(unsigned int dl_port_index)
 /* TODO: This mlx5e_tc function shouldn't be called by eswitch */
 void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
 
-/* The vport getter/iterator are only valid after esw->total_vports
- * and vport->vport are initialized in mlx5_eswitch_init.
+/* Each mark identifies eswitch vport type.
+ * MLX5_ESW_VPT_HOST_FN is used to identify both PF and VF ports using
+ * a single mark.
+ * MLX5_ESW_VPT_VF identifies a SRIOV VF vport.
+ * MLX5_ESW_VPT_SF identifies SF vport.
  */
-#define mlx5_esw_for_all_vports(esw, i, vport)		\
-	for ((i) = MLX5_VPORT_PF;			\
-	     (vport) = &(esw)->vports[i],		\
-	     (i) < (esw)->total_vports; (i)++)
-
-#define mlx5_esw_for_all_vports_reverse(esw, i, vport)	\
-	for ((i) = (esw)->total_vports - 1;		\
-	     (vport) = &(esw)->vports[i],		\
-	     (i) >= MLX5_VPORT_PF; (i)--)
-
-#define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)	\
-	for ((i) = MLX5_VPORT_FIRST_VF;			\
-	     (vport) = &(esw)->vports[(i)],		\
-	     (i) <= (nvfs); (i)++)
-
-#define mlx5_esw_for_each_vf_vport_reverse(esw, i, vport, nvfs)	\
-	for ((i) = (nvfs);					\
-	     (vport) = &(esw)->vports[(i)],			\
-	     (i) >= MLX5_VPORT_FIRST_VF; (i)--)
-
-/* The rep getter/iterator are only valid after esw->total_vports
- * and vport->vport are initialized in mlx5_eswitch_init.
+#define MLX5_ESW_VPT_HOST_FN XA_MARK_0
+#define MLX5_ESW_VPT_VF XA_MARK_1
+#define MLX5_ESW_VPT_SF XA_MARK_2
+
+/* The vport iterator is valid only after vport are initialized in mlx5_eswitch_init.
+ * Borrowed the idea from xa_for_each_marked() but with support for desired last element.
  */
-#define mlx5_esw_for_all_reps(esw, i, rep)			\
-	for ((i) = MLX5_VPORT_PF;				\
-	     (rep) = &(esw)->offloads.vport_reps[i],		\
-	     (i) < (esw)->total_vports; (i)++)
-
-#define mlx5_esw_for_each_vf_rep(esw, i, rep, nvfs)		\
-	for ((i) = MLX5_VPORT_FIRST_VF;				\
-	     (rep) = &(esw)->offloads.vport_reps[i],		\
-	     (i) <= (nvfs); (i)++)
-
-#define mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, nvfs)	\
-	for ((i) = (nvfs);					\
-	     (rep) = &(esw)->offloads.vport_reps[i],		\
-	     (i) >= MLX5_VPORT_FIRST_VF; (i)--)
-
-#define mlx5_esw_for_each_vf_vport_num(esw, vport, nvfs)	\
-	for ((vport) = MLX5_VPORT_FIRST_VF; (vport) <= (nvfs); (vport)++)
-
-#define mlx5_esw_for_each_vf_vport_num_reverse(esw, vport, nvfs)	\
-	for ((vport) = (nvfs); (vport) >= MLX5_VPORT_FIRST_VF; (vport)--)
-
-/* Includes host PF (vport 0) if it's not esw manager. */
-#define mlx5_esw_for_each_host_func_rep(esw, i, rep, nvfs)	\
-	for ((i) = (esw)->first_host_vport;			\
-	     (rep) = &(esw)->offloads.vport_reps[i],		\
-	     (i) <= (nvfs); (i)++)
-
-#define mlx5_esw_for_each_host_func_rep_reverse(esw, i, rep, nvfs)	\
-	for ((i) = (nvfs);						\
-	     (rep) = &(esw)->offloads.vport_reps[i],			\
-	     (i) >= (esw)->first_host_vport; (i)--)
-
-#define mlx5_esw_for_each_host_func_vport(esw, vport, nvfs)	\
-	for ((vport) = (esw)->first_host_vport;			\
-	     (vport) <= (nvfs); (vport)++)
-
-#define mlx5_esw_for_each_host_func_vport_reverse(esw, vport, nvfs)	\
-	for ((vport) = (nvfs);						\
-	     (vport) >= (esw)->first_host_vport; (vport)--)
-
-#define mlx5_esw_for_each_sf_rep(esw, i, rep)		\
-	for ((i) = mlx5_esw_sf_start_idx(esw);		\
-	     (rep) = &(esw)->offloads.vport_reps[(i)],	\
-	     (i) < mlx5_esw_sf_end_idx(esw); (i++))
+
+#define mlx5_esw_for_each_vport(esw, index, vport) \
+	xa_for_each(&((esw)->vports), index, vport)
+
+#define mlx5_esw_for_each_entry_marked(xa, index, entry, last, filter)	\
+	for (index = 0, entry = xa_find(xa, &index, last, filter); \
+	     entry; entry = xa_find_after(xa, &index, last, filter))
+
+#define mlx5_esw_for_each_vport_marked(esw, index, vport, last, filter)	\
+	mlx5_esw_for_each_entry_marked(&((esw)->vports), index, vport, last, filter)
+
+#define mlx5_esw_for_each_vf_vport(esw, index, vport, last)	\
+	mlx5_esw_for_each_vport_marked(esw, index, vport, last, MLX5_ESW_VPT_VF)
+
+#define mlx5_esw_for_each_host_func_vport(esw, index, vport, last)	\
+	mlx5_esw_for_each_vport_marked(esw, index, vport, last, MLX5_ESW_VPT_HOST_FN)
 
 struct mlx5_eswitch *mlx5_devlink_eswitch_get(struct devlink *devlink);
 struct mlx5_vport *__must_check
 mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num);
 
-bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num);
+bool mlx5_eswitch_is_vf_vport(struct mlx5_eswitch *esw, u16 vport_num);
+bool mlx5_esw_is_sf_vport(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data);
 
@@ -784,12 +662,13 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
 struct devlink_port *mlx5_esw_offloads_devlink_port(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 sfnum);
+				      u16 vport_num, u32 controller, u32 sfnum);
 void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num);
 
 int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 sfnum);
+				      u16 vport_num, u32 controller, u32 sfnum);
 void mlx5_esw_offloads_sf_vport_disable(struct mlx5_eswitch *esw, u16 vport_num);
+int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *sf_base_id);
 
 int mlx5_esw_vport_vhca_id_set(struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_esw_vport_vhca_id_clear(struct mlx5_eswitch *esw, u16 vport_num);
@@ -816,6 +695,8 @@ void mlx5_esw_unlock(struct mlx5_eswitch *esw);
 
 void esw_vport_change_handle_locked(struct mlx5_vport *vport);
 
+bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 controller);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index bbb707117296..db1e74280e57 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -49,6 +49,16 @@
 #include "en_tc.h"
 #include "en/mapping.h"
 
+#define mlx5_esw_for_each_rep(esw, i, rep) \
+	xa_for_each(&((esw)->offloads.vport_reps), i, rep)
+
+#define mlx5_esw_for_each_sf_rep(esw, i, rep) \
+	xa_for_each_marked(&((esw)->offloads.vport_reps), i, rep, MLX5_ESW_VPT_SF)
+
+#define mlx5_esw_for_each_vf_rep(esw, index, rep)	\
+	mlx5_esw_for_each_entry_marked(&((esw)->offloads.vport_reps), index, \
+				       rep, (esw)->esw_funcs.num_vfs, MLX5_ESW_VPT_VF)
+
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
  */
@@ -67,10 +77,7 @@ static const struct esw_vport_tbl_namespace mlx5_esw_vport_tbl_mirror_ns = {
 static struct mlx5_eswitch_rep *mlx5_eswitch_get_rep(struct mlx5_eswitch *esw,
 						     u16 vport_num)
 {
-	int idx = mlx5_eswitch_vport_num_to_index(esw, vport_num);
-
-	WARN_ON(idx > esw->total_vports - 1);
-	return &esw->offloads.vport_reps[idx];
+	return xa_load(&esw->offloads.vport_reps, vport_num);
 }
 
 static void
@@ -720,10 +727,11 @@ mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
 static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 {
 	struct mlx5_eswitch_rep *rep;
-	int i, err = 0;
+	unsigned long i;
+	int err = 0;
 
 	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
-	mlx5_esw_for_each_host_func_rep(esw, i, rep, esw->esw_funcs.num_vfs) {
+	mlx5_esw_for_each_host_func_vport(esw, i, rep, esw->esw_funcs.num_vfs) {
 		if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
 			continue;
 
@@ -972,13 +980,13 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
 static void mlx5_eswitch_del_send_to_vport_meta_rules(struct mlx5_eswitch *esw)
 {
 	struct mlx5_flow_handle **flows = esw->fdb_table.offloads.send_to_vport_meta_rules;
-	int i = 0, num_vfs = esw->esw_funcs.num_vfs, vport_num;
+	int i = 0, num_vfs = esw->esw_funcs.num_vfs;
 
 	if (!num_vfs || !flows)
 		return;
 
-	mlx5_esw_for_each_vf_vport_num(esw, vport_num, num_vfs)
-		mlx5_del_flow_rules(flows[i++]);
+	for (i = 0; i < num_vfs; i++)
+		mlx5_del_flow_rules(flows[i]);
 
 	kvfree(flows);
 }
@@ -992,6 +1000,8 @@ mlx5_eswitch_add_send_to_vport_meta_rules(struct mlx5_eswitch *esw)
 	struct mlx5_flow_handle *flow_rule;
 	struct mlx5_flow_handle **flows;
 	struct mlx5_flow_spec *spec;
+	struct mlx5_vport *vport;
+	unsigned long i;
 	u16 vport_num;
 
 	num_vfs = esw->esw_funcs.num_vfs;
@@ -1016,7 +1026,8 @@ mlx5_eswitch_add_send_to_vport_meta_rules(struct mlx5_eswitch *esw)
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 
-	mlx5_esw_for_each_vf_vport_num(esw, vport_num, num_vfs) {
+	mlx5_esw_for_each_vf_vport(esw, i, vport, num_vfs) {
+		vport_num = vport->vport;
 		MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_0,
 			 mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num));
 		dest.vport.num = vport_num;
@@ -1158,12 +1169,14 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	struct mlx5_flow_destination dest = {};
 	struct mlx5_flow_act flow_act = {0};
 	struct mlx5_flow_handle **flows;
-	struct mlx5_flow_handle *flow;
-	struct mlx5_flow_spec *spec;
 	/* total vports is the same for both e-switches */
 	int nvports = esw->total_vports;
+	struct mlx5_flow_handle *flow;
+	struct mlx5_flow_spec *spec;
+	struct mlx5_vport *vport;
+	unsigned long i;
 	void *misc;
-	int err, i;
+	int err;
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
@@ -1182,6 +1195,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			    misc_parameters);
 
 	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
 		esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
 						   spec, MLX5_VPORT_PF);
 
@@ -1191,10 +1205,11 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_pf_flow_err;
 		}
-		flows[MLX5_VPORT_PF] = flow;
+		flows[vport->index] = flow;
 	}
 
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
 		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_ECPF);
 		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 					   spec, &flow_act, &dest, 1);
@@ -1202,13 +1217,13 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_ecpf_flow_err;
 		}
-		flows[mlx5_eswitch_ecpf_idx(esw)] = flow;
+		flows[vport->index] = flow;
 	}
 
-	mlx5_esw_for_each_vf_vport_num(esw, i, mlx5_core_max_vfs(esw->dev)) {
+	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) {
 		esw_set_peer_miss_rule_source_port(esw,
 						   peer_dev->priv.eswitch,
-						   spec, i);
+						   spec, vport->vport);
 
 		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 					   spec, &flow_act, &dest, 1);
@@ -1216,7 +1231,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			err = PTR_ERR(flow);
 			goto add_vf_flow_err;
 		}
-		flows[i] = flow;
+		flows[vport->index] = flow;
 	}
 
 	esw->fdb_table.offloads.peer_miss_rules = flows;
@@ -1225,15 +1240,20 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	return 0;
 
 add_vf_flow_err:
-	nvports = --i;
-	mlx5_esw_for_each_vf_vport_num_reverse(esw, i, nvports)
-		mlx5_del_flow_rules(flows[i]);
-
-	if (mlx5_ecpf_vport_exists(esw->dev))
-		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev)) {
+		if (!flows[vport->index])
+			continue;
+		mlx5_del_flow_rules(flows[vport->index]);
+	}
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+		mlx5_del_flow_rules(flows[vport->index]);
+	}
 add_ecpf_flow_err:
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
-		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
+		mlx5_del_flow_rules(flows[vport->index]);
+	}
 add_pf_flow_err:
 	esw_warn(esw->dev, "FDB: Failed to add peer miss flow rule err %d\n", err);
 	kvfree(flows);
@@ -1245,20 +1265,23 @@ alloc_flows_err:
 static void esw_del_fdb_peer_miss_rules(struct mlx5_eswitch *esw)
 {
 	struct mlx5_flow_handle **flows;
-	int i;
+	struct mlx5_vport *vport;
+	unsigned long i;
 
 	flows = esw->fdb_table.offloads.peer_miss_rules;
 
-	mlx5_esw_for_each_vf_vport_num_reverse(esw, i,
-					       mlx5_core_max_vfs(esw->dev))
-		mlx5_del_flow_rules(flows[i]);
-
-	if (mlx5_ecpf_vport_exists(esw->dev))
-		mlx5_del_flow_rules(flows[mlx5_eswitch_ecpf_idx(esw)]);
+	mlx5_esw_for_each_vf_vport(esw, i, vport, mlx5_core_max_vfs(esw->dev))
+		mlx5_del_flow_rules(flows[vport->index]);
 
-	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
-		mlx5_del_flow_rules(flows[MLX5_VPORT_PF]);
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+		mlx5_del_flow_rules(flows[vport->index]);
+	}
 
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
+		mlx5_del_flow_rules(flows[vport->index]);
+	}
 	kvfree(flows);
 }
 
@@ -1402,11 +1425,11 @@ static void esw_vport_tbl_put(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport_tbl_attr attr;
 	struct mlx5_vport *vport;
-	int i;
+	unsigned long i;
 
 	attr.chain = 0;
 	attr.prio = 1;
-	mlx5_esw_for_all_vports(esw, i, vport) {
+	mlx5_esw_for_each_vport(esw, i, vport) {
 		attr.vport = vport->vport;
 		attr.vport_ns = &mlx5_esw_vport_tbl_mirror_ns;
 		mlx5_esw_vporttbl_put(esw, &attr);
@@ -1418,11 +1441,11 @@ static int esw_vport_tbl_get(struct mlx5_eswitch *esw)
 	struct mlx5_vport_tbl_attr attr;
 	struct mlx5_flow_table *fdb;
 	struct mlx5_vport *vport;
-	int i;
+	unsigned long i;
 
 	attr.chain = 0;
 	attr.prio = 1;
-	mlx5_esw_for_all_vports(esw, i, vport) {
+	mlx5_esw_for_each_vport(esw, i, vport) {
 		attr.vport = vport->vport;
 		attr.vport_ns = &mlx5_esw_vport_tbl_mirror_ns;
 		fdb = mlx5_esw_vporttbl_get(esw, &attr);
@@ -1910,12 +1933,12 @@ out:
 	return flow_rule;
 }
 
-
-static int mlx5_eswitch_inline_mode_get(const struct mlx5_eswitch *esw, u8 *mode)
+static int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, u8 *mode)
 {
 	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
 	struct mlx5_core_dev *dev = esw->dev;
-	int vport;
+	struct mlx5_vport *vport;
+	unsigned long i;
 
 	if (!MLX5_CAP_GEN(dev, vport_group_manager))
 		return -EOPNOTSUPP;
@@ -1936,8 +1959,8 @@ static int mlx5_eswitch_inline_mode_get(const struct mlx5_eswitch *esw, u8 *mode
 
 query_vports:
 	mlx5_query_nic_vport_min_inline(dev, esw->first_host_vport, &prev_mlx5_mode);
-	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
-		mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
+	mlx5_esw_for_each_host_func_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+		mlx5_query_nic_vport_min_inline(dev, vport->vport, &mlx5_mode);
 		if (prev_mlx5_mode != mlx5_mode)
 			return -EINVAL;
 		prev_mlx5_mode = mlx5_mode;
@@ -2080,34 +2103,82 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 	return err;
 }
 
-void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
+static void mlx5_esw_offloads_rep_mark_set(struct mlx5_eswitch *esw,
+					   struct mlx5_eswitch_rep *rep,
+					   xa_mark_t mark)
 {
-	kfree(esw->offloads.vport_reps);
+	bool mark_set;
+
+	/* Copy the mark from vport to its rep */
+	mark_set = xa_get_mark(&esw->vports, rep->vport, mark);
+	if (mark_set)
+		xa_set_mark(&esw->offloads.vport_reps, rep->vport, mark);
 }
 
-int esw_offloads_init_reps(struct mlx5_eswitch *esw)
+static int mlx5_esw_offloads_rep_init(struct mlx5_eswitch *esw, const struct mlx5_vport *vport)
 {
-	int total_vports = esw->total_vports;
 	struct mlx5_eswitch_rep *rep;
-	int vport_index;
-	u8 rep_type;
+	int rep_type;
+	int err;
 
-	esw->offloads.vport_reps = kcalloc(total_vports,
-					   sizeof(struct mlx5_eswitch_rep),
-					   GFP_KERNEL);
-	if (!esw->offloads.vport_reps)
+	rep = kzalloc(sizeof(*rep), GFP_KERNEL);
+	if (!rep)
 		return -ENOMEM;
 
-	mlx5_esw_for_all_reps(esw, vport_index, rep) {
-		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index);
-		rep->vport_index = vport_index;
+	rep->vport = vport->vport;
+	rep->vport_index = vport->index;
+	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
+		atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
 
-		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
-			atomic_set(&rep->rep_data[rep_type].state,
-				   REP_UNREGISTERED);
-	}
+	err = xa_insert(&esw->offloads.vport_reps, rep->vport, rep, GFP_KERNEL);
+	if (err)
+		goto insert_err;
 
+	mlx5_esw_offloads_rep_mark_set(esw, rep, MLX5_ESW_VPT_HOST_FN);
+	mlx5_esw_offloads_rep_mark_set(esw, rep, MLX5_ESW_VPT_VF);
+	mlx5_esw_offloads_rep_mark_set(esw, rep, MLX5_ESW_VPT_SF);
 	return 0;
+
+insert_err:
+	kfree(rep);
+	return err;
+}
+
+static void mlx5_esw_offloads_rep_cleanup(struct mlx5_eswitch *esw,
+					  struct mlx5_eswitch_rep *rep)
+{
+	xa_erase(&esw->offloads.vport_reps, rep->vport);
+	kfree(rep);
+}
+
+void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw)
+{
+	struct mlx5_eswitch_rep *rep;
+	unsigned long i;
+
+	mlx5_esw_for_each_rep(esw, i, rep)
+		mlx5_esw_offloads_rep_cleanup(esw, rep);
+	xa_destroy(&esw->offloads.vport_reps);
+}
+
+int esw_offloads_init_reps(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+	int err;
+
+	xa_init(&esw->offloads.vport_reps);
+
+	mlx5_esw_for_each_vport(esw, i, vport) {
+		err = mlx5_esw_offloads_rep_init(esw, vport);
+		if (err)
+			goto err;
+	}
+	return 0;
+
+err:
+	esw_offloads_cleanup_reps(esw);
+	return err;
 }
 
 static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
@@ -2121,7 +2192,7 @@ static void __esw_offloads_unload_rep(struct mlx5_eswitch *esw,
 static void __unload_reps_sf_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int i;
+	unsigned long i;
 
 	mlx5_esw_for_each_sf_rep(esw, i, rep)
 		__esw_offloads_unload_rep(esw, rep, rep_type);
@@ -2130,11 +2201,11 @@ static void __unload_reps_sf_vport(struct mlx5_eswitch *esw, u8 rep_type)
 static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int i;
+	unsigned long i;
 
 	__unload_reps_sf_vport(esw, rep_type);
 
-	mlx5_esw_for_each_vf_rep_reverse(esw, i, rep, esw->esw_funcs.num_vfs)
+	mlx5_esw_for_each_vf_rep(esw, i, rep)
 		__esw_offloads_unload_rep(esw, rep, rep_type);
 
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
@@ -2421,25 +2492,25 @@ static void esw_offloads_vport_metadata_cleanup(struct mlx5_eswitch *esw,
 static void esw_offloads_metadata_uninit(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
-	int i;
+	unsigned long i;
 
 	if (!mlx5_eswitch_vport_match_metadata_enabled(esw))
 		return;
 
-	mlx5_esw_for_all_vports_reverse(esw, i, vport)
+	mlx5_esw_for_each_vport(esw, i, vport)
 		esw_offloads_vport_metadata_cleanup(esw, vport);
 }
 
 static int esw_offloads_metadata_init(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
+	unsigned long i;
 	int err;
-	int i;
 
 	if (!mlx5_eswitch_vport_match_metadata_enabled(esw))
 		return 0;
 
-	mlx5_esw_for_all_vports(esw, i, vport) {
+	mlx5_esw_for_each_vport(esw, i, vport) {
 		err = esw_offloads_vport_metadata_setup(esw, vport);
 		if (err)
 			goto metadata_err;
@@ -2676,11 +2747,25 @@ static int mlx5_esw_host_number_init(struct mlx5_eswitch *esw)
 	return 0;
 }
 
+bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 controller)
+{
+	/* Local controller is always valid */
+	if (controller == 0)
+		return true;
+
+	if (!mlx5_core_is_ecpf_esw_manager(esw->dev))
+		return false;
+
+	/* External host number starts with zero in device */
+	return (controller == esw->offloads.host_number + 1);
+}
+
 int esw_offloads_enable(struct mlx5_eswitch *esw)
 {
 	struct mapping_ctx *reg_c0_obj_pool;
 	struct mlx5_vport *vport;
-	int err, i;
+	unsigned long i;
+	int err;
 
 	if (MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, reformat) &&
 	    MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, decap))
@@ -2926,13 +3011,44 @@ unlock:
 	return err;
 }
 
+static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_vport *vport;
+	u16 err_vport_num = 0;
+	unsigned long i;
+	int err = 0;
+
+	mlx5_esw_for_each_host_func_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+		err = mlx5_modify_nic_vport_min_inline(dev, vport->vport, mlx5_mode);
+		if (err) {
+			err_vport_num = vport->vport;
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Failed to set min inline on vport");
+			goto revert_inline_mode;
+		}
+	}
+	return 0;
+
+revert_inline_mode:
+	mlx5_esw_for_each_host_func_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+		if (vport->vport == err_vport_num)
+			break;
+		mlx5_modify_nic_vport_min_inline(dev,
+						 vport->vport,
+						 esw->offloads.inline_mode);
+	}
+	return err;
+}
+
 int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 					 struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
-	int err, vport, num_vport;
 	struct mlx5_eswitch *esw;
 	u8 mlx5_mode;
+	int err;
 
 	esw = mlx5_devlink_eswitch_get(devlink);
 	if (IS_ERR(esw))
@@ -2967,25 +3083,14 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	if (err)
 		goto out;
 
-	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
-		err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode);
-		if (err) {
-			NL_SET_ERR_MSG_MOD(extack,
-					   "Failed to set min inline on vport");
-			goto revert_inline_mode;
-		}
-	}
+	err = mlx5_esw_vports_inline_set(esw, mlx5_mode, extack);
+	if (err)
+		goto out;
 
 	esw->offloads.inline_mode = mlx5_mode;
 	up_write(&esw->mode_lock);
 	return 0;
 
-revert_inline_mode:
-	num_vport = --vport;
-	mlx5_esw_for_each_host_func_vport_reverse(esw, vport, num_vport)
-		mlx5_modify_nic_vport_min_inline(dev,
-						 vport,
-						 esw->offloads.inline_mode);
 out:
 	up_write(&esw->mode_lock);
 	return err;
@@ -3116,11 +3221,11 @@ void mlx5_eswitch_register_vport_reps(struct mlx5_eswitch *esw,
 {
 	struct mlx5_eswitch_rep_data *rep_data;
 	struct mlx5_eswitch_rep *rep;
-	int i;
+	unsigned long i;
 
 	esw->offloads.rep_ops[rep_type] = ops;
-	mlx5_esw_for_all_reps(esw, i, rep) {
-		if (likely(mlx5_eswitch_vport_has_rep(esw, i))) {
+	mlx5_esw_for_each_rep(esw, i, rep) {
+		if (likely(mlx5_eswitch_vport_has_rep(esw, rep->vport))) {
 			rep->esw = esw;
 			rep_data = &rep->rep_data[rep_type];
 			atomic_set(&rep_data->state, REP_REGISTERED);
@@ -3132,12 +3237,12 @@ EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
 void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 {
 	struct mlx5_eswitch_rep *rep;
-	int i;
+	unsigned long i;
 
 	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
 		__unload_reps_all_vport(esw, rep_type);
 
-	mlx5_esw_for_all_reps(esw, i, rep)
+	mlx5_esw_for_each_rep(esw, i, rep)
 		atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
 }
 EXPORT_SYMBOL(mlx5_eswitch_unregister_vport_reps);
@@ -3178,12 +3283,6 @@ struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
 }
 EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
 
-bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
-{
-	return vport_num >= MLX5_VPORT_FIRST_VF &&
-	       vport_num <= esw->dev->priv.sriov.max_vfs;
-}
-
 bool mlx5_eswitch_reg_c1_loopback_enabled(const struct mlx5_eswitch *esw)
 {
 	return !!(esw->flags & MLX5_ESWITCH_REG_C1_LOOPBACK_ENABLED);
@@ -3209,7 +3308,7 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw,
 EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
 
 int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_port *dl_port,
-				      u16 vport_num, u32 sfnum)
+				      u16 vport_num, u32 controller, u32 sfnum)
 {
 	int err;
 
@@ -3217,7 +3316,7 @@ int mlx5_esw_offloads_sf_vport_enable(struct mlx5_eswitch *esw, struct devlink_p
 	if (err)
 		return err;
 
-	err = mlx5_esw_devlink_sf_port_register(esw, dl_port, vport_num, sfnum);
+	err = mlx5_esw_devlink_sf_port_register(esw, dl_port, vport_num, controller, sfnum);
 	if (err)
 		goto devlink_err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
index 90b524c59f3c..6a0c6f965ad1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/dev.c
@@ -148,9 +148,19 @@ mlx5_sf_dev_state_change_handler(struct notifier_block *nb, unsigned long event_
 	struct mlx5_sf_dev_table *table = container_of(nb, struct mlx5_sf_dev_table, nb);
 	const struct mlx5_vhca_state_event *event = data;
 	struct mlx5_sf_dev *sf_dev;
+	u16 max_functions;
 	u16 sf_index;
+	u16 base_id;
+
+	max_functions = mlx5_sf_max_functions(table->dev);
+	if (!max_functions)
+		return 0;
+
+	base_id = MLX5_CAP_GEN(table->dev, sf_base_id);
+	if (event->function_id < base_id || event->function_id >= (base_id + max_functions))
+		return 0;
 
-	sf_index = event->function_id - MLX5_CAP_GEN(table->dev, sf_base_id);
+	sf_index = event->function_id - base_id;
 	sf_dev = xa_load(&table->devices, sf_index);
 	switch (event->new_vhca_state) {
 	case MLX5_VHCA_STATE_ALLOCATED:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index 52226d9b9a6d..a8e73c9ed1ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -12,6 +12,7 @@
 struct mlx5_sf {
 	struct devlink_port dl_port;
 	unsigned int port_index;
+	u32 controller;
 	u16 id;
 	u16 hw_fn_id;
 	u16 hw_state;
@@ -58,7 +59,8 @@ static void mlx5_sf_id_erase(struct mlx5_sf_table *table, struct mlx5_sf *sf)
 }
 
 static struct mlx5_sf *
-mlx5_sf_alloc(struct mlx5_sf_table *table, u32 sfnum, struct netlink_ext_ack *extack)
+mlx5_sf_alloc(struct mlx5_sf_table *table, struct mlx5_eswitch *esw,
+	      u32 controller, u32 sfnum, struct netlink_ext_ack *extack)
 {
 	unsigned int dl_port_index;
 	struct mlx5_sf *sf;
@@ -66,7 +68,12 @@ mlx5_sf_alloc(struct mlx5_sf_table *table, u32 sfnum, struct netlink_ext_ack *ex
 	int id_err;
 	int err;
 
-	id_err = mlx5_sf_hw_table_sf_alloc(table->dev, sfnum);
+	if (!mlx5_esw_offloads_controller_valid(esw, controller)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid controller number");
+		return ERR_PTR(-EINVAL);
+	}
+
+	id_err = mlx5_sf_hw_table_sf_alloc(table->dev, controller, sfnum);
 	if (id_err < 0) {
 		err = id_err;
 		goto id_err;
@@ -78,11 +85,12 @@ mlx5_sf_alloc(struct mlx5_sf_table *table, u32 sfnum, struct netlink_ext_ack *ex
 		goto alloc_err;
 	}
 	sf->id = id_err;
-	hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, sf->id);
+	hw_fn_id = mlx5_sf_sw_to_hw_id(table->dev, controller, sf->id);
 	dl_port_index = mlx5_esw_vport_to_devlink_port_index(table->dev, hw_fn_id);
 	sf->port_index = dl_port_index;
 	sf->hw_fn_id = hw_fn_id;
 	sf->hw_state = MLX5_VHCA_STATE_ALLOCATED;
+	sf->controller = controller;
 
 	err = mlx5_sf_id_insert(table, sf);
 	if (err)
@@ -93,7 +101,7 @@ mlx5_sf_alloc(struct mlx5_sf_table *table, u32 sfnum, struct netlink_ext_ack *ex
 insert_err:
 	kfree(sf);
 alloc_err:
-	mlx5_sf_hw_table_sf_free(table->dev, id_err);
+	mlx5_sf_hw_table_sf_free(table->dev, controller, id_err);
 id_err:
 	if (err == -EEXIST)
 		NL_SET_ERR_MSG_MOD(extack, "SF already exist. Choose different sfnum");
@@ -103,7 +111,7 @@ id_err:
 static void mlx5_sf_free(struct mlx5_sf_table *table, struct mlx5_sf *sf)
 {
 	mlx5_sf_id_erase(table, sf);
-	mlx5_sf_hw_table_sf_free(table->dev, sf->id);
+	mlx5_sf_hw_table_sf_free(table->dev, sf->controller, sf->id);
 	kfree(sf);
 }
 
@@ -272,12 +280,12 @@ static int mlx5_sf_add(struct mlx5_core_dev *dev, struct mlx5_sf_table *table,
 	struct mlx5_sf *sf;
 	int err;
 
-	sf = mlx5_sf_alloc(table, new_attr->sfnum, extack);
+	sf = mlx5_sf_alloc(table, esw, new_attr->controller, new_attr->sfnum, extack);
 	if (IS_ERR(sf))
 		return PTR_ERR(sf);
 
 	err = mlx5_esw_offloads_sf_vport_enable(esw, &sf->dl_port, sf->hw_fn_id,
-						new_attr->sfnum);
+						new_attr->controller, new_attr->sfnum);
 	if (err)
 		goto esw_err;
 	*new_port_index = sf->port_index;
@@ -306,7 +314,8 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_
 				   "User must provide unique sfnum. Driver does not support auto assignment");
 		return -EOPNOTSUPP;
 	}
-	if (new_attr->controller_valid && new_attr->controller) {
+	if (new_attr->controller_valid && new_attr->controller &&
+	    !mlx5_core_is_ecpf_esw_manager(dev)) {
 		NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported");
 		return -EOPNOTSUPP;
 	}
@@ -352,10 +361,10 @@ static void mlx5_sf_dealloc(struct mlx5_sf_table *table, struct mlx5_sf *sf)
 		 * firmware gives confirmation that it is detached by the driver.
 		 */
 		mlx5_cmd_sf_disable_hca(table->dev, sf->hw_fn_id);
-		mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->id);
+		mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->controller, sf->id);
 		kfree(sf);
 	} else {
-		mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->id);
+		mlx5_sf_hw_table_sf_deferred_free(table->dev, sf->controller, sf->id);
 		kfree(sf);
 	}
 }
@@ -437,9 +446,6 @@ sf_err:
 
 static void mlx5_sf_table_enable(struct mlx5_sf_table *table)
 {
-	if (!mlx5_sf_max_functions(table->dev))
-		return;
-
 	init_completion(&table->disable_complete);
 	refcount_set(&table->refcount, 1);
 }
@@ -462,9 +468,6 @@ static void mlx5_sf_deactivate_all(struct mlx5_sf_table *table)
 
 static void mlx5_sf_table_disable(struct mlx5_sf_table *table)
 {
-	if (!mlx5_sf_max_functions(table->dev))
-		return;
-
 	if (!refcount_read(&table->refcount))
 		return;
 
@@ -498,7 +501,8 @@ static int mlx5_sf_esw_event(struct notifier_block *nb, unsigned long event, voi
 
 static bool mlx5_sf_table_supported(const struct mlx5_core_dev *dev)
 {
-	return dev->priv.eswitch && MLX5_ESWITCH_MANAGER(dev) && mlx5_sf_supported(dev);
+	return dev->priv.eswitch && MLX5_ESWITCH_MANAGER(dev) &&
+	       mlx5_sf_hw_table_supported(dev);
 }
 
 int mlx5_sf_table_init(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
index ec53c11c8344..ef5f892aafad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/hw_table.c
@@ -8,6 +8,7 @@
 #include "ecpf.h"
 #include "vhca_event.h"
 #include "mlx5_core.h"
+#include "eswitch.h"
 
 struct mlx5_sf_hw {
 	u32 usr_sfnum;
@@ -15,59 +16,113 @@ struct mlx5_sf_hw {
 	u8 pending_delete: 1;
 };
 
+struct mlx5_sf_hwc_table {
+	struct mlx5_sf_hw *sfs;
+	int max_fn;
+	u16 start_fn_id;
+};
+
+enum mlx5_sf_hwc_index {
+	MLX5_SF_HWC_LOCAL,
+	MLX5_SF_HWC_EXTERNAL,
+	MLX5_SF_HWC_MAX,
+};
+
 struct mlx5_sf_hw_table {
 	struct mlx5_core_dev *dev;
-	struct mlx5_sf_hw *sfs;
-	int max_local_functions;
 	struct mutex table_lock; /* Serializes sf deletion and vhca state change handler. */
 	struct notifier_block vhca_nb;
+	struct mlx5_sf_hwc_table hwc[MLX5_SF_HWC_MAX];
 };
 
-u16 mlx5_sf_sw_to_hw_id(const struct mlx5_core_dev *dev, u16 sw_id)
+static struct mlx5_sf_hwc_table *
+mlx5_sf_controller_to_hwc(struct mlx5_core_dev *dev, u32 controller)
 {
-	return sw_id + mlx5_sf_start_function_id(dev);
+	int idx = !!controller;
+
+	return &dev->priv.sf_hw_table->hwc[idx];
 }
 
-static u16 mlx5_sf_hw_to_sw_id(const struct mlx5_core_dev *dev, u16 hw_id)
+u16 mlx5_sf_sw_to_hw_id(struct mlx5_core_dev *dev, u32 controller, u16 sw_id)
 {
-	return hw_id - mlx5_sf_start_function_id(dev);
+	struct mlx5_sf_hwc_table *hwc;
+
+	hwc = mlx5_sf_controller_to_hwc(dev, controller);
+	return hwc->start_fn_id + sw_id;
 }
 
-int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum)
+static u16 mlx5_sf_hw_to_sw_id(struct mlx5_sf_hwc_table *hwc, u16 hw_id)
+{
+	return hw_id - hwc->start_fn_id;
+}
+
+static struct mlx5_sf_hwc_table *
+mlx5_sf_table_fn_to_hwc(struct mlx5_sf_hw_table *table, u16 fn_id)
 {
-	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
-	int sw_id = -ENOSPC;
-	u16 hw_fn_id;
-	int err;
 	int i;
 
-	if (!table->max_local_functions)
-		return -EOPNOTSUPP;
+	for (i = 0; i < ARRAY_SIZE(table->hwc); i++) {
+		if (table->hwc[i].max_fn &&
+		    fn_id >= table->hwc[i].start_fn_id &&
+		    fn_id < (table->hwc[i].start_fn_id + table->hwc[i].max_fn))
+			return &table->hwc[i];
+	}
+	return NULL;
+}
+
+static int mlx5_sf_hw_table_id_alloc(struct mlx5_sf_hw_table *table, u32 controller,
+				     u32 usr_sfnum)
+{
+	struct mlx5_sf_hwc_table *hwc;
+	int i;
+
+	hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+	if (!hwc->sfs)
+		return -ENOSPC;
 
-	mutex_lock(&table->table_lock);
 	/* Check if sf with same sfnum already exists or not. */
-	for (i = 0; i < table->max_local_functions; i++) {
-		if (table->sfs[i].allocated && table->sfs[i].usr_sfnum == usr_sfnum) {
-			err = -EEXIST;
-			goto exist_err;
-		}
+	for (i = 0; i < hwc->max_fn; i++) {
+		if (hwc->sfs[i].allocated && hwc->sfs[i].usr_sfnum == usr_sfnum)
+			return -EEXIST;
 	}
-
 	/* Find the free entry and allocate the entry from the array */
-	for (i = 0; i < table->max_local_functions; i++) {
-		if (!table->sfs[i].allocated) {
-			table->sfs[i].usr_sfnum = usr_sfnum;
-			table->sfs[i].allocated = true;
-			sw_id = i;
-			break;
+	for (i = 0; i < hwc->max_fn; i++) {
+		if (!hwc->sfs[i].allocated) {
+			hwc->sfs[i].usr_sfnum = usr_sfnum;
+			hwc->sfs[i].allocated = true;
+			return i;
 		}
 	}
-	if (sw_id == -ENOSPC) {
-		err = -ENOSPC;
+	return -ENOSPC;
+}
+
+static void mlx5_sf_hw_table_id_free(struct mlx5_sf_hw_table *table, u32 controller, int id)
+{
+	struct mlx5_sf_hwc_table *hwc;
+
+	hwc = mlx5_sf_controller_to_hwc(table->dev, controller);
+	hwc->sfs[id].allocated = false;
+	hwc->sfs[id].pending_delete = false;
+}
+
+int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr_sfnum)
+{
+	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
+	u16 hw_fn_id;
+	int sw_id;
+	int err;
+
+	if (!table)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&table->table_lock);
+	sw_id = mlx5_sf_hw_table_id_alloc(table, controller, usr_sfnum);
+	if (sw_id < 0) {
+		err = sw_id;
 		goto exist_err;
 	}
 
-	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, sw_id);
+	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, sw_id);
 	err = mlx5_cmd_alloc_sf(dev, hw_fn_id);
 	if (err)
 		goto err;
@@ -76,47 +131,58 @@ int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum)
 	if (err)
 		goto vhca_err;
 
+	if (controller) {
+		/* If this SF is for external controller, SF manager
+		 * needs to arm firmware to receive the events.
+		 */
+		err = mlx5_vhca_event_arm(dev, hw_fn_id);
+		if (err)
+			goto vhca_err;
+	}
+
 	mutex_unlock(&table->table_lock);
 	return sw_id;
 
 vhca_err:
 	mlx5_cmd_dealloc_sf(dev, hw_fn_id);
 err:
-	table->sfs[i].allocated = false;
+	mlx5_sf_hw_table_id_free(table, controller, sw_id);
 exist_err:
 	mutex_unlock(&table->table_lock);
 	return err;
 }
 
-static void _mlx5_sf_hw_id_free(struct mlx5_core_dev *dev, u16 id)
+void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u32 controller, u16 id)
 {
 	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
 	u16 hw_fn_id;
 
-	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, id);
+	mutex_lock(&table->table_lock);
+	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, id);
 	mlx5_cmd_dealloc_sf(dev, hw_fn_id);
-	table->sfs[id].allocated = false;
-	table->sfs[id].pending_delete = false;
+	mlx5_sf_hw_table_id_free(table, controller, id);
+	mutex_unlock(&table->table_lock);
 }
 
-void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u16 id)
+static void mlx5_sf_hw_table_hwc_sf_free(struct mlx5_core_dev *dev,
+					 struct mlx5_sf_hwc_table *hwc, int idx)
 {
-	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
-
-	mutex_lock(&table->table_lock);
-	_mlx5_sf_hw_id_free(dev, id);
-	mutex_unlock(&table->table_lock);
+	mlx5_cmd_dealloc_sf(dev, hwc->start_fn_id + idx);
+	hwc->sfs[idx].allocated = false;
+	hwc->sfs[idx].pending_delete = false;
 }
 
-void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id)
+void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller, u16 id)
 {
 	struct mlx5_sf_hw_table *table = dev->priv.sf_hw_table;
 	u32 out[MLX5_ST_SZ_DW(query_vhca_state_out)] = {};
+	struct mlx5_sf_hwc_table *hwc;
 	u16 hw_fn_id;
 	u8 state;
 	int err;
 
-	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, id);
+	hw_fn_id = mlx5_sf_sw_to_hw_id(dev, controller, id);
+	hwc = mlx5_sf_controller_to_hwc(dev, controller);
 	mutex_lock(&table->table_lock);
 	err = mlx5_cmd_query_vhca_state(dev, hw_fn_id, out, sizeof(out));
 	if (err)
@@ -124,53 +190,102 @@ void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id)
 	state = MLX5_GET(query_vhca_state_out, out, vhca_state_context.vhca_state);
 	if (state == MLX5_VHCA_STATE_ALLOCATED) {
 		mlx5_cmd_dealloc_sf(dev, hw_fn_id);
-		table->sfs[id].allocated = false;
+		hwc->sfs[id].allocated = false;
 	} else {
-		table->sfs[id].pending_delete = true;
+		hwc->sfs[id].pending_delete = true;
 	}
 err:
 	mutex_unlock(&table->table_lock);
 }
 
-static void mlx5_sf_hw_dealloc_all(struct mlx5_sf_hw_table *table)
+static void mlx5_sf_hw_table_hwc_dealloc_all(struct mlx5_core_dev *dev,
+					     struct mlx5_sf_hwc_table *hwc)
 {
 	int i;
 
-	for (i = 0; i < table->max_local_functions; i++) {
-		if (table->sfs[i].allocated)
-			_mlx5_sf_hw_id_free(table->dev, i);
+	for (i = 0; i < hwc->max_fn; i++) {
+		if (hwc->sfs[i].allocated)
+			mlx5_sf_hw_table_hwc_sf_free(dev, hwc, i);
 	}
 }
 
+static void mlx5_sf_hw_table_dealloc_all(struct mlx5_sf_hw_table *table)
+{
+	mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_EXTERNAL]);
+	mlx5_sf_hw_table_hwc_dealloc_all(table->dev, &table->hwc[MLX5_SF_HWC_LOCAL]);
+}
+
+static int mlx5_sf_hw_table_hwc_init(struct mlx5_sf_hwc_table *hwc, u16 max_fn, u16 base_id)
+{
+	struct mlx5_sf_hw *sfs;
+
+	if (!max_fn)
+		return 0;
+
+	sfs = kcalloc(max_fn, sizeof(*sfs), GFP_KERNEL);
+	if (!sfs)
+		return -ENOMEM;
+
+	hwc->sfs = sfs;
+	hwc->max_fn = max_fn;
+	hwc->start_fn_id = base_id;
+	return 0;
+}
+
+static void mlx5_sf_hw_table_hwc_cleanup(struct mlx5_sf_hwc_table *hwc)
+{
+	kfree(hwc->sfs);
+}
+
 int mlx5_sf_hw_table_init(struct mlx5_core_dev *dev)
 {
 	struct mlx5_sf_hw_table *table;
-	struct mlx5_sf_hw *sfs;
-	int max_functions;
+	u16 max_ext_fn = 0;
+	u16 ext_base_id;
+	u16 max_fn = 0;
+	u16 base_id;
+	int err;
 
-	if (!mlx5_sf_supported(dev) || !mlx5_vhca_event_supported(dev))
+	if (!mlx5_vhca_event_supported(dev))
+		return 0;
+
+	if (mlx5_sf_supported(dev))
+		max_fn = mlx5_sf_max_functions(dev);
+
+	err = mlx5_esw_sf_max_hpf_functions(dev, &max_ext_fn, &ext_base_id);
+	if (err)
+		return err;
+
+	if (!max_fn && !max_ext_fn)
 		return 0;
 
-	max_functions = mlx5_sf_max_functions(dev);
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
 	if (!table)
 		return -ENOMEM;
 
-	sfs = kcalloc(max_functions, sizeof(*sfs), GFP_KERNEL);
-	if (!sfs)
-		goto table_err;
-
 	mutex_init(&table->table_lock);
 	table->dev = dev;
-	table->sfs = sfs;
-	table->max_local_functions = max_functions;
 	dev->priv.sf_hw_table = table;
-	mlx5_core_dbg(dev, "SF HW table: max sfs = %d\n", max_functions);
+
+	base_id = mlx5_sf_start_function_id(dev);
+	err = mlx5_sf_hw_table_hwc_init(&table->hwc[MLX5_SF_HWC_LOCAL], max_fn, base_id);
+	if (err)
+		goto table_err;
+
+	err = mlx5_sf_hw_table_hwc_init(&table->hwc[MLX5_SF_HWC_EXTERNAL],
+					max_ext_fn, ext_base_id);
+	if (err)
+		goto ext_err;
+
+	mlx5_core_dbg(dev, "SF HW table: max sfs = %d, ext sfs = %d\n", max_fn, max_ext_fn);
 	return 0;
 
+ext_err:
+	mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]);
 table_err:
+	mutex_destroy(&table->table_lock);
 	kfree(table);
-	return -ENOMEM;
+	return err;
 }
 
 void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
@@ -181,7 +296,8 @@ void mlx5_sf_hw_table_cleanup(struct mlx5_core_dev *dev)
 		return;
 
 	mutex_destroy(&table->table_lock);
-	kfree(table->sfs);
+	mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_EXTERNAL]);
+	mlx5_sf_hw_table_hwc_cleanup(&table->hwc[MLX5_SF_HWC_LOCAL]);
 	kfree(table);
 }
 
@@ -189,21 +305,26 @@ static int mlx5_sf_hw_vhca_event(struct notifier_block *nb, unsigned long opcode
 {
 	struct mlx5_sf_hw_table *table = container_of(nb, struct mlx5_sf_hw_table, vhca_nb);
 	const struct mlx5_vhca_state_event *event = data;
+	struct mlx5_sf_hwc_table *hwc;
 	struct mlx5_sf_hw *sf_hw;
 	u16 sw_id;
 
 	if (event->new_vhca_state != MLX5_VHCA_STATE_ALLOCATED)
 		return 0;
 
-	sw_id = mlx5_sf_hw_to_sw_id(table->dev, event->function_id);
-	sf_hw = &table->sfs[sw_id];
+	hwc = mlx5_sf_table_fn_to_hwc(table, event->function_id);
+	if (!hwc)
+		return 0;
+
+	sw_id = mlx5_sf_hw_to_sw_id(hwc, event->function_id);
+	sf_hw = &hwc->sfs[sw_id];
 
 	mutex_lock(&table->table_lock);
 	/* SF driver notified through firmware that SF is finally detached.
 	 * Hence recycle the sf hardware id for reuse.
 	 */
 	if (sf_hw->allocated && sf_hw->pending_delete)
-		_mlx5_sf_hw_id_free(table->dev, sw_id);
+		mlx5_sf_hw_table_hwc_sf_free(table->dev, hwc, sw_id);
 	mutex_unlock(&table->table_lock);
 	return 0;
 }
@@ -228,5 +349,10 @@ void mlx5_sf_hw_table_destroy(struct mlx5_core_dev *dev)
 
 	mlx5_vhca_event_notifier_unregister(dev, &table->vhca_nb);
 	/* Dealloc SFs whose firmware event has been missed. */
-	mlx5_sf_hw_dealloc_all(table);
+	mlx5_sf_hw_table_dealloc_all(table);
+}
+
+bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev)
+{
+	return !!dev->priv.sf_hw_table;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h
index cb02a51d0986..7114f3fc335f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/priv.h
@@ -12,10 +12,11 @@ int mlx5_cmd_dealloc_sf(struct mlx5_core_dev *dev, u16 function_id);
 int mlx5_cmd_sf_enable_hca(struct mlx5_core_dev *dev, u16 func_id);
 int mlx5_cmd_sf_disable_hca(struct mlx5_core_dev *dev, u16 func_id);
 
-u16 mlx5_sf_sw_to_hw_id(const struct mlx5_core_dev *dev, u16 sw_id);
+u16 mlx5_sf_sw_to_hw_id(struct mlx5_core_dev *dev, u32 controller, u16 sw_id);
 
-int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 usr_sfnum);
-void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u16 id);
-void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u16 id);
+int mlx5_sf_hw_table_sf_alloc(struct mlx5_core_dev *dev, u32 controller, u32 usr_sfnum);
+void mlx5_sf_hw_table_sf_free(struct mlx5_core_dev *dev, u32 controller, u16 id);
+void mlx5_sf_hw_table_sf_deferred_free(struct mlx5_core_dev *dev, u32 controller, u16 id);
+bool mlx5_sf_hw_table_supported(const struct mlx5_core_dev *dev);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index e05c5c0f3ae1..457ad42eaa2a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -1151,20 +1151,6 @@ u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid);
 
-/**
- * mlx5_eswitch_get_total_vports - Get total vports of the eswitch
- *
- * @dev:	Pointer to core device
- *
- * mlx5_eswitch_get_total_vports returns total number of vports for
- * the eswitch.
- */
-u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev)
-{
-	return MLX5_SPECIAL_VPORTS(dev) + mlx5_core_max_vfs(dev) + mlx5_sf_max_functions(dev);
-}
-EXPORT_SYMBOL_GPL(mlx5_eswitch_get_total_vports);
-
 int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out)
 {
 	u16 opmod = (MLX5_CAP_GENERAL << 1) | (HCA_CAP_OPMOD_GET_MAX & 0x01);
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index 9cf1da2883c6..17109b65c1ac 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -65,8 +65,6 @@ struct mlx5_flow_handle *
 mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw,
 				    struct mlx5_eswitch_rep *rep, u32 sqn);
 
-u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
-
 #ifdef CONFIG_MLX5_ESWITCH
 enum devlink_eswitch_encap_mode
 mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev);
@@ -126,6 +124,8 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 #define ESW_TUN_SLOW_TABLE_GOTO_VPORT_MARK ESW_TUN_OPTS_MASK
 
 u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev);
+u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 
 static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev)
@@ -162,10 +162,17 @@ mlx5_eswitch_get_vport_metadata_mask(void)
 {
 	return 0;
 }
+
+static inline u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MLX5_ESWITCH */
 
 static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev)
 {
 	return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS;
 }
+
 #endif
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 4db87bcfce7b..aad53cb72f17 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -36,14 +36,6 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/device.h>
 
-#define MLX5_VPORT_PF_PLACEHOLDER		(1u)
-#define MLX5_VPORT_UPLINK_PLACEHOLDER		(1u)
-#define MLX5_VPORT_ECPF_PLACEHOLDER(mdev)	(mlx5_ecpf_vport_exists(mdev))
-
-#define MLX5_SPECIAL_VPORTS(mdev) (MLX5_VPORT_PF_PLACEHOLDER +		\
-				   MLX5_VPORT_UPLINK_PLACEHOLDER +	\
-				   MLX5_VPORT_ECPF_PLACEHOLDER(mdev))
-
 #define MLX5_VPORT_MANAGER(mdev)					\
 	(MLX5_CAP_GEN(mdev, vport_group_manager) &&			\
 	 (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&	\
diff --git a/include/net/devlink.h b/include/net/devlink.h
index 853420db5d32..7c984cadfec4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -98,11 +98,13 @@ struct devlink_port_pci_vf_attrs {
  * @controller: Associated controller number
  * @sf: Associated PCI SF for of the PCI PF for this port.
  * @pf: Associated PCI PF number for this port.
+ * @external: when set, indicates if a port is for an external controller
  */
 struct devlink_port_pci_sf_attrs {
 	u32 controller;
 	u32 sf;
 	u16 pf;
+	u8 external:1;
 };
 
 /**
@@ -1508,7 +1510,8 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 contro
 void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
 				   u16 pf, u16 vf, bool external);
 void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port,
-				   u32 controller, u16 pf, u32 sf);
+				   u32 controller, u16 pf, u32 sf,
+				   bool external);
 int devlink_sb_register(struct devlink *devlink, unsigned int sb_index,
 			u32 size, u16 ingress_pools_count,
 			u16 egress_pools_count, u16 ingress_tc_count,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 737b61c2976e..4eb969518ee0 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -8599,9 +8599,10 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set);
  *	@controller: associated controller number for the devlink port instance
  *	@pf: associated PF for the devlink port instance
  *	@sf: associated SF of a PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
  */
 void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 controller,
-				   u16 pf, u32 sf)
+				   u16 pf, u32 sf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
@@ -8615,6 +8616,7 @@ void devlink_port_attrs_pci_sf_set(struct devlink_port *devlink_port, u32 contro
 	attrs->pci_sf.controller = controller;
 	attrs->pci_sf.pf = pf;
 	attrs->pci_sf.sf = sf;
+	attrs->pci_sf.external = external;
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_sf_set);
 
@@ -8667,6 +8669,13 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 			     attrs->pci_vf.pf, attrs->pci_vf.vf);
 		break;
 	case DEVLINK_PORT_FLAVOUR_PCI_SF:
+		if (attrs->pci_sf.external) {
+			n = snprintf(name, len, "c%u", attrs->pci_sf.controller);
+			if (n >= len)
+				return -EINVAL;
+			len -= n;
+			name += n;
+		}
 		n = snprintf(name, len, "pf%usf%u", attrs->pci_sf.pf,
 			     attrs->pci_sf.sf);
 		break;