Merge tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from Jakub Kicinski:
 "Core:

   - Enable memcg accounting for various networking objects.

  BPF:

   - Introduce bpf timers.

   - Add perf link and opaque bpf_cookie which the program can read out
     again, to be used in libbpf-based USDT library.

   - Add bpf_task_pt_regs() helper to access user space pt_regs in
     kprobes, to help user space stack unwinding.

   - Add support for UNIX sockets for BPF sockmap.

   - Extend BPF iterator support for UNIX domain sockets.

   - Allow BPF TCP congestion control progs and bpf iterators to call
     bpf_setsockopt(), e.g. to switch to another congestion control
     algorithm.

  Protocols:

   - Support IOAM Pre-allocated Trace with IPv6.

   - Support Management Component Transport Protocol.

   - bridge: multicast: add vlan support.

   - netfilter: add hooks for the SRv6 lightweight tunnel driver.

   - tcp:
       - enable mid-stream window clamping (by user space or BPF)
       - allow data-less, empty-cookie SYN with TFO_SERVER_COOKIE_NOT_REQD
       - more accurate DSACK processing for RACK-TLP

   - mptcp:
       - add full mesh path manager option
       - add partial support for MP_FAIL
       - improve use of backup subflows
       - optimize option processing

   - af_unix: add OOB notification support.

   - ipv6: add IFLA_INET6_RA_MTU to expose MTU value advertised by the
     router.

   - mac80211: Target Wake Time support in AP mode.

   - can: j1939: extend UAPI to notify about RX status.

  Driver APIs:

   - Add page frag support in page pool API.

   - Many improvements to the DSA (distributed switch) APIs.

   - ethtool: extend IRQ coalesce uAPI with timer reset modes.

   - devlink: control which auxiliary devices are created.

   - Support CAN PHYs via the generic PHY subsystem.

   - Proper cross-chip support for tag_8021q.

   - Allow TX forwarding for the software bridge data path to be
     offloaded to capable devices.

  Drivers:

   - veth: more flexible channels number configuration.

   - openvswitch: introduce per-cpu upcall dispatch.

   - Add internet mix (IMIX) mode to pktgen.

   - Transparently handle XDP operations in the bonding driver.

   - Add LiteETH network driver.

   - Renesas (ravb):
       - support Gigabit Ethernet IP

   - NXP Ethernet switch (sja1105):
       - fast aging support
       - support for "H" switch topologies
       - traffic termination for ports under VLAN-aware bridge

   - Intel 1G Ethernet
       - support getcrosststamp() with PCIe PTM (Precision Time
         Measurement) for better time sync
       - support Credit-Based Shaper (CBS) offload, enabling HW traffic
         prioritization and bandwidth reservation

   - Broadcom Ethernet (bnxt)
       - support pulse-per-second output
       - support larger Rx rings

   - Mellanox Ethernet (mlx5)
       - support ethtool RSS contexts and MQPRIO channel mode
       - support LAG offload with bridging
       - support devlink rate limit API
       - support packet sampling on tunnels

   - Huawei Ethernet (hns3):
       - basic devlink support
       - add extended IRQ coalescing support
       - report extended link state

   - Netronome Ethernet (nfp):
       - add conntrack offload support

   - Broadcom WiFi (brcmfmac):
       - add WPA3 Personal with FT to supported cipher suites
       - support 43752 SDIO device

   - Intel WiFi (iwlwifi):
       - support scanning hidden 6GHz networks
       - support for a new hardware family (Bz)

   - Xen pv driver:
       - harden netfront against malicious backends

   - Qualcomm mobile
       - ipa: refactor power management and enable automatic suspend
       - mhi: move MBIM to WWAN subsystem interfaces

  Refactor:

   - Ambient BPF run context and cgroup storage cleanup.

   - Compat rework for ndo_ioctl.

  Old code removal:

   - prism54 remove the obsoleted driver, deprecated by the p54 driver.

   - wan: remove sbni/granch driver"

* tag 'net-next-5.15' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1715 commits)
  net: Add depends on OF_NET for LiteX's LiteETH
  ipv6: seg6: remove duplicated include
  net: hns3: remove unnecessary spaces
  net: hns3: add some required spaces
  net: hns3: clean up a type mismatch warning
  net: hns3: refine function hns3_set_default_feature()
  ipv6: remove duplicated 'net/lwtunnel.h' include
  net: w5100: check return value after calling platform_get_resource()
  net/mlxbf_gige: Make use of devm_platform_ioremap_resourcexxx()
  net: mdio: mscc-miim: Make use of the helper function devm_platform_ioremap_resource()
  net: mdio-ipq4019: Make use of devm_platform_ioremap_resource()
  fou: remove sparse errors
  ipv4: fix endianness issue in inet_rtm_getroute_build_skb()
  octeontx2-af: Set proper errorcode for IPv4 checksum errors
  octeontx2-af: Fix static code analyzer reported issues
  octeontx2-af: Fix mailbox errors in nix_rss_flowkey_cfg
  octeontx2-af: Fix loop in free and unmap counter
  af_unix: fix potential NULL deref in unix_dgram_connect()
  dpaa2-eth: Replace strlcpy with strscpy
  octeontx2-af: Use NDC TX for transmit packet data
  ...

13 files changed, 1380 insertions, 767 deletions

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 505bf811984a..2e504c7461c6 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
@@ -15,6 +15,15 @@ static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport)
 	vport->egress.offloads.fwd_rule = NULL;
 }
 
+static void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport)
+{
+	if (!vport->egress.offloads.bounce_rule)
+		return;
+
+	mlx5_del_flow_rules(vport->egress.offloads.bounce_rule);
+	vport->egress.offloads.bounce_rule = NULL;
+}
+
 static int esw_acl_egress_ofld_fwd2vport_create(struct mlx5_eswitch *esw,
 						struct mlx5_vport *vport,
 						struct mlx5_flow_destination *fwd_dest)
@@ -87,6 +96,7 @@ static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport)
 {
 	esw_acl_egress_vlan_destroy(vport);
 	esw_acl_egress_ofld_fwd2vport_destroy(vport);
+	esw_acl_egress_ofld_bounce_rule_destroy(vport);
 }
 
 static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw,
@@ -145,6 +155,12 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
 		mlx5_destroy_flow_group(vport->egress.offloads.fwd_grp);
 		vport->egress.offloads.fwd_grp = NULL;
 	}
+
+	if (!IS_ERR_OR_NULL(vport->egress.offloads.bounce_grp)) {
+		mlx5_destroy_flow_group(vport->egress.offloads.bounce_grp);
+		vport->egress.offloads.bounce_grp = NULL;
+	}
+
 	esw_acl_egress_vlan_grp_destroy(vport);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 69a3630818d7..7e221038df8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -5,6 +5,7 @@
 #include <linux/notifier.h>
 #include <net/netevent.h>
 #include <net/switchdev.h>
+#include "lib/devcom.h"
 #include "bridge.h"
 #include "eswitch.h"
 #include "bridge_priv.h"
@@ -56,7 +57,6 @@ struct mlx5_esw_bridge {
 
 	struct list_head fdb_list;
 	struct rhashtable fdb_ht;
-	struct xarray vports;
 
 	struct mlx5_flow_table *egress_ft;
 	struct mlx5_flow_group *egress_vlan_fg;
@@ -77,6 +77,15 @@ mlx5_esw_bridge_fdb_offload_notify(struct net_device *dev, const unsigned char *
 	call_switchdev_notifiers(val, dev, &send_info.info, NULL);
 }
 
+static void
+mlx5_esw_bridge_fdb_del_notify(struct mlx5_esw_bridge_fdb_entry *entry)
+{
+	if (!(entry->flags & (MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER | MLX5_ESW_BRIDGE_FLAG_PEER)))
+		mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
+						   entry->key.vid,
+						   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+}
+
 static struct mlx5_flow_table *
 mlx5_esw_bridge_table_create(int max_fte, u32 level, struct mlx5_eswitch *esw)
 {
@@ -400,9 +409,10 @@ mlx5_esw_bridge_egress_table_cleanup(struct mlx5_esw_bridge *bridge)
 }
 
 static struct mlx5_flow_handle *
-mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
-				    struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
-				    struct mlx5_esw_bridge *bridge)
+mlx5_esw_bridge_ingress_flow_with_esw_create(u16 vport_num, const unsigned char *addr,
+					     struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+					     struct mlx5_esw_bridge *bridge,
+					     struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_bridge_offloads *br_offloads = bridge->br_offloads;
 	struct mlx5_flow_act flow_act = {
@@ -430,7 +440,7 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
 	MLX5_SET(fte_match_param, rule_spec->match_criteria,
 		 misc_parameters_2.metadata_reg_c_0, mlx5_eswitch_get_vport_metadata_mask());
 	MLX5_SET(fte_match_param, rule_spec->match_value, misc_parameters_2.metadata_reg_c_0,
-		 mlx5_eswitch_get_vport_metadata_for_match(br_offloads->esw, vport_num));
+		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport_num));
 
 	if (vlan && vlan->pkt_reformat_push) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT;
@@ -459,6 +469,35 @@ mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
 }
 
 static struct mlx5_flow_handle *
+mlx5_esw_bridge_ingress_flow_create(u16 vport_num, const unsigned char *addr,
+				    struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+				    struct mlx5_esw_bridge *bridge)
+{
+	return mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+							    bridge, bridge->br_offloads->esw);
+}
+
+static struct mlx5_flow_handle *
+mlx5_esw_bridge_ingress_flow_peer_create(u16 vport_num, const unsigned char *addr,
+					 struct mlx5_esw_bridge_vlan *vlan, u32 counter_id,
+					 struct mlx5_esw_bridge *bridge)
+{
+	struct mlx5_devcom *devcom = bridge->br_offloads->esw->dev->priv.devcom;
+	static struct mlx5_flow_handle *handle;
+	struct mlx5_eswitch *peer_esw;
+
+	peer_esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	if (!peer_esw)
+		return ERR_PTR(-ENODEV);
+
+	handle = mlx5_esw_bridge_ingress_flow_with_esw_create(vport_num, addr, vlan, counter_id,
+							      bridge, peer_esw);
+
+	mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+	return handle;
+}
+
+static struct mlx5_flow_handle *
 mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *addr,
 					   struct mlx5_esw_bridge *bridge)
 {
@@ -505,7 +544,7 @@ mlx5_esw_bridge_ingress_filter_flow_create(u16 vport_num, const unsigned char *a
 }
 
 static struct mlx5_flow_handle *
-mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr,
+mlx5_esw_bridge_egress_flow_create(u16 vport_num, u16 esw_owner_vhca_id, const unsigned char *addr,
 				   struct mlx5_esw_bridge_vlan *vlan,
 				   struct mlx5_esw_bridge *bridge)
 {
@@ -550,6 +589,10 @@ mlx5_esw_bridge_egress_flow_create(u16 vport_num, const unsigned char *addr,
 			 vlan->vid);
 	}
 
+	if (MLX5_CAP_ESW(bridge->br_offloads->esw->dev, merged_eswitch)) {
+		dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
+		dest.vport.vhca_id = esw_owner_vhca_id;
+	}
 	handle = mlx5_add_flow_rules(bridge->egress_ft, rule_spec, &flow_act, &dest, 1);
 
 	kvfree(rule_spec);
@@ -576,7 +619,6 @@ static struct mlx5_esw_bridge *mlx5_esw_bridge_create(int ifindex,
 		goto err_fdb_ht;
 
 	INIT_LIST_HEAD(&bridge->fdb_list);
-	xa_init(&bridge->vports);
 	bridge->ifindex = ifindex;
 	bridge->refcnt = 1;
 	bridge->ageing_time = clock_t_to_jiffies(BR_DEFAULT_AGEING_TIME);
@@ -603,7 +645,6 @@ static void mlx5_esw_bridge_put(struct mlx5_esw_bridge_offloads *br_offloads,
 		return;
 
 	mlx5_esw_bridge_egress_table_cleanup(bridge);
-	WARN_ON(!xa_empty(&bridge->vports));
 	list_del(&bridge->list);
 	rhashtable_destroy(&bridge->fdb_ht);
 	kvfree(bridge);
@@ -639,30 +680,40 @@ mlx5_esw_bridge_lookup(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads
 	return bridge;
 }
 
+static unsigned long mlx5_esw_bridge_port_key_from_data(u16 vport_num, u16 esw_owner_vhca_id)
+{
+	return vport_num | (unsigned long)esw_owner_vhca_id << sizeof(vport_num) * BITS_PER_BYTE;
+}
+
+static unsigned long mlx5_esw_bridge_port_key(struct mlx5_esw_bridge_port *port)
+{
+	return mlx5_esw_bridge_port_key_from_data(port->vport_num, port->esw_owner_vhca_id);
+}
+
 static int mlx5_esw_bridge_port_insert(struct mlx5_esw_bridge_port *port,
-				       struct mlx5_esw_bridge *bridge)
+				       struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	return xa_insert(&bridge->vports, port->vport_num, port, GFP_KERNEL);
+	return xa_insert(&br_offloads->ports, mlx5_esw_bridge_port_key(port), port, GFP_KERNEL);
 }
 
 static struct mlx5_esw_bridge_port *
-mlx5_esw_bridge_port_lookup(u16 vport_num, struct mlx5_esw_bridge *bridge)
+mlx5_esw_bridge_port_lookup(u16 vport_num, u16 esw_owner_vhca_id,
+			    struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	return xa_load(&bridge->vports, vport_num);
+	return xa_load(&br_offloads->ports, mlx5_esw_bridge_port_key_from_data(vport_num,
+									       esw_owner_vhca_id));
 }
 
 static void mlx5_esw_bridge_port_erase(struct mlx5_esw_bridge_port *port,
-				       struct mlx5_esw_bridge *bridge)
+				       struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	xa_erase(&bridge->vports, port->vport_num);
+	xa_erase(&br_offloads->ports, mlx5_esw_bridge_port_key(port));
 }
 
-static void mlx5_esw_bridge_fdb_entry_refresh(unsigned long lastuse,
-					      struct mlx5_esw_bridge_fdb_entry *entry)
+static void mlx5_esw_bridge_fdb_entry_refresh(struct mlx5_esw_bridge_fdb_entry *entry)
 {
 	trace_mlx5_esw_bridge_fdb_entry_refresh(entry);
 
-	entry->lastuse = lastuse;
 	mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
 					   entry->key.vid,
 					   SWITCHDEV_FDB_ADD_TO_BRIDGE);
@@ -690,10 +741,7 @@ static void mlx5_esw_bridge_fdb_flush(struct mlx5_esw_bridge *bridge)
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
 
 	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list) {
-		if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
-			mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
-							   entry->key.vid,
-							   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+		mlx5_esw_bridge_fdb_del_notify(entry);
 		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 	}
 }
@@ -841,10 +889,7 @@ static void mlx5_esw_bridge_vlan_flush(struct mlx5_esw_bridge_vlan *vlan,
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
 
 	list_for_each_entry_safe(entry, tmp, &vlan->fdb_list, vlan_list) {
-		if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
-			mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
-							   entry->key.vid,
-							   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+		mlx5_esw_bridge_fdb_del_notify(entry);
 		mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 	}
 
@@ -875,13 +920,13 @@ static void mlx5_esw_bridge_port_vlans_flush(struct mlx5_esw_bridge_port *port,
 }
 
 static struct mlx5_esw_bridge_vlan *
-mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge *bridge,
-				 struct mlx5_eswitch *esw)
+mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge *bridge, struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge_vlan *vlan;
 
-	port = mlx5_esw_bridge_port_lookup(vport_num, bridge);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, bridge->br_offloads);
 	if (!port) {
 		/* FDB is added asynchronously on wq while port might have been deleted
 		 * concurrently. Report on 'info' logging level and skip the FDB offload.
@@ -904,24 +949,23 @@ mlx5_esw_bridge_port_vlan_lookup(u16 vid, u16 vport_num, struct mlx5_esw_bridge
 }
 
 static struct mlx5_esw_bridge_fdb_entry *
-mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsigned char *addr,
-			       u16 vid, bool added_by_user, struct mlx5_eswitch *esw,
-			       struct mlx5_esw_bridge *bridge)
+mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+			       const unsigned char *addr, u16 vid, bool added_by_user, bool peer,
+			       struct mlx5_eswitch *esw, struct mlx5_esw_bridge *bridge)
 {
 	struct mlx5_esw_bridge_vlan *vlan = NULL;
 	struct mlx5_esw_bridge_fdb_entry *entry;
 	struct mlx5_flow_handle *handle;
 	struct mlx5_fc *counter;
-	struct mlx5e_priv *priv;
 	int err;
 
 	if (bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG && vid) {
-		vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, bridge, esw);
+		vlan = mlx5_esw_bridge_port_vlan_lookup(vid, vport_num, esw_owner_vhca_id, bridge,
+							esw);
 		if (IS_ERR(vlan))
 			return ERR_CAST(vlan);
 	}
 
-	priv = netdev_priv(dev);
 	entry = kvzalloc(sizeof(*entry), GFP_KERNEL);
 	if (!entry)
 		return ERR_PTR(-ENOMEM);
@@ -930,19 +974,25 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsi
 	entry->key.vid = vid;
 	entry->dev = dev;
 	entry->vport_num = vport_num;
+	entry->esw_owner_vhca_id = esw_owner_vhca_id;
 	entry->lastuse = jiffies;
 	if (added_by_user)
 		entry->flags |= MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER;
+	if (peer)
+		entry->flags |= MLX5_ESW_BRIDGE_FLAG_PEER;
 
-	counter = mlx5_fc_create(priv->mdev, true);
+	counter = mlx5_fc_create(esw->dev, true);
 	if (IS_ERR(counter)) {
 		err = PTR_ERR(counter);
 		goto err_ingress_fc_create;
 	}
 	entry->ingress_counter = counter;
 
-	handle = mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan, mlx5_fc_id(counter),
-						     bridge);
+	handle = peer ?
+		mlx5_esw_bridge_ingress_flow_peer_create(vport_num, addr, vlan,
+							 mlx5_fc_id(counter), bridge) :
+		mlx5_esw_bridge_ingress_flow_create(vport_num, addr, vlan,
+						    mlx5_fc_id(counter), bridge);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		esw_warn(esw->dev, "Failed to create ingress flow(vport=%u,err=%d)\n",
@@ -962,7 +1012,8 @@ mlx5_esw_bridge_fdb_entry_init(struct net_device *dev, u16 vport_num, const unsi
 		entry->filter_handle = handle;
 	}
 
-	handle = mlx5_esw_bridge_egress_flow_create(vport_num, addr, vlan, bridge);
+	handle = mlx5_esw_bridge_egress_flow_create(vport_num, esw_owner_vhca_id, addr, vlan,
+						    bridge);
 	if (IS_ERR(handle)) {
 		err = PTR_ERR(handle);
 		esw_warn(esw->dev, "Failed to create egress flow(vport=%u,err=%d)\n",
@@ -994,32 +1045,37 @@ err_egress_flow_create:
 err_ingress_filter_flow_create:
 	mlx5_del_flow_rules(entry->ingress_handle);
 err_ingress_flow_create:
-	mlx5_fc_destroy(priv->mdev, entry->ingress_counter);
+	mlx5_fc_destroy(esw->dev, entry->ingress_counter);
 err_ingress_fc_create:
 	kvfree(entry);
 	return ERR_PTR(err);
 }
 
-int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport)
+int mlx5_esw_bridge_ageing_time_set(u16 vport_num, u16 esw_owner_vhca_id, unsigned long ageing_time,
+				    struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	if (!vport->bridge)
+	struct mlx5_esw_bridge_port *port;
+
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
 		return -EINVAL;
 
-	vport->bridge->ageing_time = clock_t_to_jiffies(ageing_time);
+	port->bridge->ageing_time = clock_t_to_jiffies(ageing_time);
 	return 0;
 }
 
-int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
-				       struct mlx5_vport *vport)
+int mlx5_esw_bridge_vlan_filtering_set(u16 vport_num, u16 esw_owner_vhca_id, bool enable,
+				       struct mlx5_esw_bridge_offloads *br_offloads)
 {
+	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge *bridge;
 	bool filtering;
 
-	if (!vport->bridge)
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
 		return -EINVAL;
 
-	bridge = vport->bridge;
+	bridge = port->bridge;
 	filtering = bridge->flags & MLX5_ESW_BRIDGE_VLAN_FILTERING_FLAG;
 	if (filtering == enable)
 		return 0;
@@ -1033,114 +1089,143 @@ int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
 	return 0;
 }
 
-static int mlx5_esw_bridge_vport_init(struct mlx5_esw_bridge_offloads *br_offloads,
-				      struct mlx5_esw_bridge *bridge,
-				      struct mlx5_vport *vport)
+static int mlx5_esw_bridge_vport_init(u16 vport_num, u16 esw_owner_vhca_id, u16 flags,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct mlx5_esw_bridge *bridge)
 {
 	struct mlx5_eswitch *esw = br_offloads->esw;
 	struct mlx5_esw_bridge_port *port;
 	int err;
 
 	port = kvzalloc(sizeof(*port), GFP_KERNEL);
-	if (!port) {
-		err = -ENOMEM;
-		goto err_port_alloc;
-	}
+	if (!port)
+		return -ENOMEM;
 
-	port->vport_num = vport->vport;
+	port->vport_num = vport_num;
+	port->esw_owner_vhca_id = esw_owner_vhca_id;
+	port->bridge = bridge;
+	port->flags |= flags;
 	xa_init(&port->vlans);
-	err = mlx5_esw_bridge_port_insert(port, bridge);
+	err = mlx5_esw_bridge_port_insert(port, br_offloads);
 	if (err) {
-		esw_warn(esw->dev, "Failed to insert port metadata (vport=%u,err=%d)\n",
-			 vport->vport, err);
+		esw_warn(esw->dev,
+			 "Failed to insert port metadata (vport=%u,esw_owner_vhca_id=%u,err=%d)\n",
+			 port->vport_num, port->esw_owner_vhca_id, err);
 		goto err_port_insert;
 	}
 	trace_mlx5_esw_bridge_vport_init(port);
 
-	vport->bridge = bridge;
 	return 0;
 
 err_port_insert:
 	kvfree(port);
-err_port_alloc:
-	mlx5_esw_bridge_put(br_offloads, bridge);
 	return err;
 }
 
 static int mlx5_esw_bridge_vport_cleanup(struct mlx5_esw_bridge_offloads *br_offloads,
-					 struct mlx5_vport *vport)
+					 struct mlx5_esw_bridge_port *port)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
+	u16 vport_num = port->vport_num, esw_owner_vhca_id = port->esw_owner_vhca_id;
+	struct mlx5_esw_bridge *bridge = port->bridge;
 	struct mlx5_esw_bridge_fdb_entry *entry, *tmp;
-	struct mlx5_esw_bridge_port *port;
 
 	list_for_each_entry_safe(entry, tmp, &bridge->fdb_list, list)
-		if (entry->vport_num == vport->vport)
+		if (entry->vport_num == vport_num && entry->esw_owner_vhca_id == esw_owner_vhca_id)
 			mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 
-	port = mlx5_esw_bridge_port_lookup(vport->vport, bridge);
-	if (!port) {
-		WARN(1, "Vport %u metadata not found on bridge", vport->vport);
-		return -EINVAL;
-	}
-
 	trace_mlx5_esw_bridge_vport_cleanup(port);
 	mlx5_esw_bridge_port_vlans_flush(port, bridge);
-	mlx5_esw_bridge_port_erase(port, bridge);
+	mlx5_esw_bridge_port_erase(port, br_offloads);
 	kvfree(port);
 	mlx5_esw_bridge_put(br_offloads, bridge);
-	vport->bridge = NULL;
 	return 0;
 }
 
-int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-			       struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+static int mlx5_esw_bridge_vport_link_with_flags(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+						 u16 flags,
+						 struct mlx5_esw_bridge_offloads *br_offloads,
+						 struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_bridge *bridge;
 	int err;
 
-	WARN_ON(vport->bridge);
-
 	bridge = mlx5_esw_bridge_lookup(ifindex, br_offloads);
 	if (IS_ERR(bridge)) {
 		NL_SET_ERR_MSG_MOD(extack, "Error checking for existing bridge with same ifindex");
 		return PTR_ERR(bridge);
 	}
 
-	err = mlx5_esw_bridge_vport_init(br_offloads, bridge, vport);
-	if (err)
+	err = mlx5_esw_bridge_vport_init(vport_num, esw_owner_vhca_id, flags, br_offloads, bridge);
+	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Error initializing port");
+		goto err_vport;
+	}
+	return 0;
+
+err_vport:
+	mlx5_esw_bridge_put(br_offloads, bridge);
 	return err;
 }
 
-int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-				 struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+			       struct mlx5_esw_bridge_offloads *br_offloads,
+			       struct netlink_ext_ack *extack)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
+	return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id, 0,
+						     br_offloads, extack);
+}
+
+int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge_offloads *br_offloads,
+				 struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_bridge_port *port;
 	int err;
 
-	if (!bridge) {
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port) {
 		NL_SET_ERR_MSG_MOD(extack, "Port is not attached to any bridge");
 		return -EINVAL;
 	}
-	if (bridge->ifindex != ifindex) {
+	if (port->bridge->ifindex != ifindex) {
 		NL_SET_ERR_MSG_MOD(extack, "Port is attached to another bridge");
 		return -EINVAL;
 	}
 
-	err = mlx5_esw_bridge_vport_cleanup(br_offloads, vport);
+	err = mlx5_esw_bridge_vport_cleanup(br_offloads, port);
 	if (err)
 		NL_SET_ERR_MSG_MOD(extack, "Port cleanup failed");
 	return err;
 }
 
-int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport, struct netlink_ext_ack *extack)
+int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				    struct mlx5_esw_bridge_offloads *br_offloads,
+				    struct netlink_ext_ack *extack)
+{
+	if (!MLX5_CAP_ESW(br_offloads->esw->dev, merged_eswitch))
+		return 0;
+
+	return mlx5_esw_bridge_vport_link_with_flags(ifindex, vport_num, esw_owner_vhca_id,
+						     MLX5_ESW_BRIDGE_PORT_FLAG_PEER,
+						     br_offloads, extack);
+}
+
+int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct netlink_ext_ack *extack)
+{
+	return mlx5_esw_bridge_vport_unlink(ifindex, vport_num, esw_owner_vhca_id, br_offloads,
+					    extack);
+}
+
+int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags,
+				  struct mlx5_esw_bridge_offloads *br_offloads,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge_vlan *vlan;
 
-	port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
 	if (!port)
 		return -EINVAL;
 
@@ -1148,10 +1233,10 @@ int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
 	if (vlan) {
 		if (vlan->flags == flags)
 			return 0;
-		mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge);
+		mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge);
 	}
 
-	vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, esw);
+	vlan = mlx5_esw_bridge_vlan_create(vid, flags, port, br_offloads->esw);
 	if (IS_ERR(vlan)) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to create VLAN entry");
 		return PTR_ERR(vlan);
@@ -1159,62 +1244,93 @@ int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
 	return 0;
 }
 
-void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+void mlx5_esw_bridge_port_vlan_del(u16 vport_num, u16 esw_owner_vhca_id, u16 vid,
+				   struct mlx5_esw_bridge_offloads *br_offloads)
 {
 	struct mlx5_esw_bridge_port *port;
 	struct mlx5_esw_bridge_vlan *vlan;
 
-	port = mlx5_esw_bridge_port_lookup(vport->vport, vport->bridge);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
 	if (!port)
 		return;
 
 	vlan = mlx5_esw_bridge_vlan_lookup(vid, port);
 	if (!vlan)
 		return;
-	mlx5_esw_bridge_vlan_cleanup(port, vlan, vport->bridge);
+	mlx5_esw_bridge_vlan_cleanup(port, vlan, port->bridge);
 }
 
-void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
-				struct switchdev_notifier_fdb_info *fdb_info)
+void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				     struct mlx5_esw_bridge_offloads *br_offloads,
+				     struct switchdev_notifier_fdb_info *fdb_info)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
 	struct mlx5_esw_bridge_fdb_entry *entry;
-	u16 vport_num = vport->vport;
+	struct mlx5_esw_bridge_fdb_key key;
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge *bridge;
 
-	if (!bridge) {
-		esw_info(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port || port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER)
+		return;
+
+	bridge = port->bridge;
+	ether_addr_copy(key.addr, fdb_info->addr);
+	key.vid = fdb_info->vid;
+	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
+	if (!entry) {
+		esw_debug(br_offloads->esw->dev,
+			  "FDB entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n",
+			  key.addr, key.vid, vport_num);
 		return;
 	}
 
-	entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, fdb_info->addr, fdb_info->vid,
-					       fdb_info->added_by_user, esw, bridge);
+	entry->lastuse = jiffies;
+}
+
+void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
+				struct switchdev_notifier_fdb_info *fdb_info)
+{
+	struct mlx5_esw_bridge_fdb_entry *entry;
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge *bridge;
+
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
+		return;
+
+	bridge = port->bridge;
+	entry = mlx5_esw_bridge_fdb_entry_init(dev, vport_num, esw_owner_vhca_id, fdb_info->addr,
+					       fdb_info->vid, fdb_info->added_by_user,
+					       port->flags & MLX5_ESW_BRIDGE_PORT_FLAG_PEER,
+					       br_offloads->esw, bridge);
 	if (IS_ERR(entry))
 		return;
 
 	if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER)
 		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
 						   SWITCHDEV_FDB_OFFLOADED);
-	else
+	else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER))
 		/* Take over dynamic entries to prevent kernel bridge from aging them out. */
 		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
 						   SWITCHDEV_FDB_ADD_TO_BRIDGE);
 }
 
-void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
+void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info)
 {
-	struct mlx5_esw_bridge *bridge = vport->bridge;
+	struct mlx5_eswitch *esw = br_offloads->esw;
 	struct mlx5_esw_bridge_fdb_entry *entry;
 	struct mlx5_esw_bridge_fdb_key key;
-	u16 vport_num = vport->vport;
+	struct mlx5_esw_bridge_port *port;
+	struct mlx5_esw_bridge *bridge;
 
-	if (!bridge) {
-		esw_warn(esw->dev, "Vport is not assigned to bridge (vport=%u)\n", vport_num);
+	port = mlx5_esw_bridge_port_lookup(vport_num, esw_owner_vhca_id, br_offloads);
+	if (!port)
 		return;
-	}
 
+	bridge = port->bridge;
 	ether_addr_copy(key.addr, fdb_info->addr);
 	key.vid = fdb_info->vid;
 	entry = rhashtable_lookup_fast(&bridge->fdb_ht, &key, fdb_ht_params);
@@ -1225,9 +1341,7 @@ void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw
 		return;
 	}
 
-	if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER))
-		mlx5_esw_bridge_fdb_offload_notify(dev, entry->key.addr, entry->key.vid,
-						   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+	mlx5_esw_bridge_fdb_del_notify(entry);
 	mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 }
 
@@ -1245,11 +1359,10 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
 				continue;
 
 			if (time_after(lastuse, entry->lastuse)) {
-				mlx5_esw_bridge_fdb_entry_refresh(lastuse, entry);
-			} else if (time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) {
-				mlx5_esw_bridge_fdb_offload_notify(entry->dev, entry->key.addr,
-								   entry->key.vid,
-								   SWITCHDEV_FDB_DEL_TO_BRIDGE);
+				mlx5_esw_bridge_fdb_entry_refresh(entry);
+			} else if (!(entry->flags & MLX5_ESW_BRIDGE_FLAG_PEER) &&
+				   time_is_before_jiffies(entry->lastuse + bridge->ageing_time)) {
+				mlx5_esw_bridge_fdb_del_notify(entry);
 				mlx5_esw_bridge_fdb_entry_cleanup(entry, bridge);
 			}
 		}
@@ -1258,13 +1371,11 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads)
 
 static void mlx5_esw_bridge_flush(struct mlx5_esw_bridge_offloads *br_offloads)
 {
-	struct mlx5_eswitch *esw = br_offloads->esw;
-	struct mlx5_vport *vport;
+	struct mlx5_esw_bridge_port *port;
 	unsigned long i;
 
-	mlx5_esw_for_each_vport(esw, i, vport)
-		if (vport->bridge)
-			mlx5_esw_bridge_vport_cleanup(br_offloads, vport);
+	xa_for_each(&br_offloads->ports, i, port)
+		mlx5_esw_bridge_vport_cleanup(br_offloads, port);
 
 	WARN_ONCE(!list_empty(&br_offloads->bridges),
 		  "Cleaning up bridge offloads while still having bridges attached\n");
@@ -1279,6 +1390,7 @@ struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw)
 		return ERR_PTR(-ENOMEM);
 
 	INIT_LIST_HEAD(&br_offloads->bridges);
+	xa_init(&br_offloads->ports);
 	br_offloads->esw = esw;
 	esw->br_offloads = br_offloads;
 
@@ -1293,6 +1405,7 @@ void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw)
 		return;
 
 	mlx5_esw_bridge_flush(br_offloads);
+	WARN_ON(!xa_empty(&br_offloads->ports));
 
 	esw->br_offloads = NULL;
 	kvfree(br_offloads);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
index d826942b27fc..efc39975226e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h
@@ -7,6 +7,7 @@
 #include <linux/notifier.h>
 #include <linux/list.h>
 #include <linux/workqueue.h>
+#include <linux/xarray.h>
 #include "eswitch.h"
 
 struct mlx5_flow_table;
@@ -15,6 +16,8 @@ struct mlx5_flow_group;
 struct mlx5_esw_bridge_offloads {
 	struct mlx5_eswitch *esw;
 	struct list_head bridges;
+	struct xarray ports;
+
 	struct notifier_block netdev_nb;
 	struct notifier_block nb_blk;
 	struct notifier_block nb;
@@ -31,23 +34,36 @@ struct mlx5_esw_bridge_offloads {
 
 struct mlx5_esw_bridge_offloads *mlx5_esw_bridge_init(struct mlx5_eswitch *esw);
 void mlx5_esw_bridge_cleanup(struct mlx5_eswitch *esw);
-int mlx5_esw_bridge_vport_link(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-			       struct mlx5_vport *vport, struct netlink_ext_ack *extack);
-int mlx5_esw_bridge_vport_unlink(int ifindex, struct mlx5_esw_bridge_offloads *br_offloads,
-				 struct mlx5_vport *vport, struct netlink_ext_ack *extack);
-void mlx5_esw_bridge_fdb_create(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
+int mlx5_esw_bridge_vport_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+			       struct mlx5_esw_bridge_offloads *br_offloads,
+			       struct netlink_ext_ack *extack);
+int mlx5_esw_bridge_vport_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				 struct mlx5_esw_bridge_offloads *br_offloads,
+				 struct netlink_ext_ack *extack);
+int mlx5_esw_bridge_vport_peer_link(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				    struct mlx5_esw_bridge_offloads *br_offloads,
+				    struct netlink_ext_ack *extack);
+int mlx5_esw_bridge_vport_peer_unlink(int ifindex, u16 vport_num, u16 esw_owner_vhca_id,
+				      struct mlx5_esw_bridge_offloads *br_offloads,
+				      struct netlink_ext_ack *extack);
+void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				     struct mlx5_esw_bridge_offloads *br_offloads,
+				     struct switchdev_notifier_fdb_info *fdb_info);
+void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info);
-void mlx5_esw_bridge_fdb_remove(struct net_device *dev, struct mlx5_eswitch *esw,
-				struct mlx5_vport *vport,
+void mlx5_esw_bridge_fdb_remove(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id,
+				struct mlx5_esw_bridge_offloads *br_offloads,
 				struct switchdev_notifier_fdb_info *fdb_info);
 void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads);
-int mlx5_esw_bridge_ageing_time_set(unsigned long ageing_time, struct mlx5_eswitch *esw,
-				    struct mlx5_vport *vport);
-int mlx5_esw_bridge_vlan_filtering_set(bool enable, struct mlx5_eswitch *esw,
-				       struct mlx5_vport *vport);
-int mlx5_esw_bridge_port_vlan_add(u16 vid, u16 flags, struct mlx5_eswitch *esw,
-				  struct mlx5_vport *vport, struct netlink_ext_ack *extack);
-void mlx5_esw_bridge_port_vlan_del(u16 vid, struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+int mlx5_esw_bridge_ageing_time_set(u16 vport_num, u16 esw_owner_vhca_id, unsigned long ageing_time,
+				    struct mlx5_esw_bridge_offloads *br_offloads);
+int mlx5_esw_bridge_vlan_filtering_set(u16 vport_num, u16 esw_owner_vhca_id, bool enable,
+				       struct mlx5_esw_bridge_offloads *br_offloads);
+int mlx5_esw_bridge_port_vlan_add(u16 vport_num, u16 esw_owner_vhca_id, u16 vid, u16 flags,
+				  struct mlx5_esw_bridge_offloads *br_offloads,
+				  struct netlink_ext_ack *extack);
+void mlx5_esw_bridge_port_vlan_del(u16 vport_num, u16 esw_owner_vhca_id, u16 vid,
+				   struct mlx5_esw_bridge_offloads *br_offloads);
 
 #endif /* __MLX5_ESW_BRIDGE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
index d9ab2e8bc2cb..52964a82d6a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h
@@ -19,6 +19,11 @@ struct mlx5_esw_bridge_fdb_key {
 
 enum {
 	MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0),
+	MLX5_ESW_BRIDGE_FLAG_PEER = BIT(1),
+};
+
+enum {
+	MLX5_ESW_BRIDGE_PORT_FLAG_PEER = BIT(0),
 };
 
 struct mlx5_esw_bridge_fdb_entry {
@@ -28,6 +33,7 @@ struct mlx5_esw_bridge_fdb_entry {
 	struct list_head list;
 	struct list_head vlan_list;
 	u16 vport_num;
+	u16 esw_owner_vhca_id;
 	u16 flags;
 
 	struct mlx5_flow_handle *ingress_handle;
@@ -47,6 +53,9 @@ struct mlx5_esw_bridge_vlan {
 
 struct mlx5_esw_bridge_port {
 	u16 vport_num;
+	u16 esw_owner_vhca_id;
+	u16 flags;
+	struct mlx5_esw_bridge *bridge;
 	struct xarray vlans;
 };
 
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 1703384eca95..20af557ae30c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -91,9 +91,15 @@ int mlx5_esw_offloads_devlink_port_register(struct mlx5_eswitch *esw, u16 vport_
 	if (err)
 		goto reg_err;
 
+	err = devlink_rate_leaf_create(dl_port, vport);
+	if (err)
+		goto rate_err;
+
 	vport->dl_port = dl_port;
 	return 0;
 
+rate_err:
+	devlink_port_unregister(dl_port);
 reg_err:
 	mlx5_esw_dl_port_free(dl_port);
 	return err;
@@ -109,6 +115,12 @@ void mlx5_esw_offloads_devlink_port_unregister(struct mlx5_eswitch *esw, u16 vpo
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport))
 		return;
+
+	if (vport->dl_port->devlink_rate) {
+		mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
+		devlink_rate_leaf_destroy(vport->dl_port);
+	}
+
 	devlink_port_unregister(vport->dl_port);
 	mlx5_esw_dl_port_free(vport->dl_port);
 	vport->dl_port = NULL;
@@ -148,8 +160,16 @@ int mlx5_esw_devlink_sf_port_register(struct mlx5_eswitch *esw, struct devlink_p
 	if (err)
 		return err;
 
+	err = devlink_rate_leaf_create(dl_port, vport);
+	if (err)
+		goto rate_err;
+
 	vport->dl_port = dl_port;
 	return 0;
+
+rate_err:
+	devlink_port_unregister(dl_port);
+	return err;
 }
 
 void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num)
@@ -159,6 +179,12 @@ void mlx5_esw_devlink_sf_port_unregister(struct mlx5_eswitch *esw, u16 vport_num
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
 	if (IS_ERR(vport))
 		return;
+
+	if (vport->dl_port->devlink_rate) {
+		mlx5_esw_qos_vport_update_group(esw, vport, NULL, NULL);
+		devlink_rate_leaf_destroy(vport->dl_port);
+	}
+
 	devlink_port_unregister(vport->dl_port);
 	vport->dl_port = NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
index 227964b7d3b9..3401188e0a60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/bridge_tracepoint.h
@@ -85,11 +85,18 @@ DECLARE_EVENT_CLASS(mlx5_esw_bridge_port_template,
 		    TP_ARGS(port),
 		    TP_STRUCT__entry(
 			    __field(u16, vport_num)
+			    __field(u16, esw_owner_vhca_id)
+			    __field(u16, flags)
 			    ),
 		    TP_fast_assign(
 			    __entry->vport_num = port->vport_num;
+			    __entry->esw_owner_vhca_id = port->esw_owner_vhca_id;
+			    __entry->flags = port->flags;
 			    ),
-		    TP_printk("vport_num=%hu", __entry->vport_num)
+		    TP_printk("vport_num=%hu esw_owner_vhca_id=%hu flags=%hx",
+			      __entry->vport_num,
+			      __entry->esw_owner_vhca_id,
+			      __entry->flags)
 	);
 
 DEFINE_EVENT(mlx5_esw_bridge_port_template,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h
new file mode 100644
index 000000000000..458baf0c6415
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/diag/qos_tracepoint.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+#if !defined(_MLX5_ESW_TP_) || defined(TRACE_HEADER_MULTI_READ)
+#define _MLX5_ESW_TP_
+
+#include <linux/tracepoint.h>
+#include "eswitch.h"
+
+TRACE_EVENT(mlx5_esw_vport_qos_destroy,
+	    TP_PROTO(const struct mlx5_vport *vport),
+	    TP_ARGS(vport),
+	    TP_STRUCT__entry(__string(devname, dev_name(vport->dev->device))
+			     __field(unsigned short, vport_id)
+			     __field(unsigned int,   tsar_ix)
+			     ),
+	    TP_fast_assign(__assign_str(devname, dev_name(vport->dev->device));
+		    __entry->vport_id = vport->vport;
+		    __entry->tsar_ix = vport->qos.esw_tsar_ix;
+	    ),
+	    TP_printk("(%s) vport=%hu tsar_ix=%u\n",
+		      __get_str(devname), __entry->vport_id, __entry->tsar_ix
+		      )
+);
+
+DECLARE_EVENT_CLASS(mlx5_esw_vport_qos_template,
+		    TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate),
+		    TP_ARGS(vport, bw_share, max_rate),
+		    TP_STRUCT__entry(__string(devname, dev_name(vport->dev->device))
+				     __field(unsigned short, vport_id)
+				     __field(unsigned int, tsar_ix)
+				     __field(unsigned int, bw_share)
+				     __field(unsigned int, max_rate)
+				     __field(void *, group)
+				     ),
+		    TP_fast_assign(__assign_str(devname, dev_name(vport->dev->device));
+			    __entry->vport_id = vport->vport;
+			    __entry->tsar_ix = vport->qos.esw_tsar_ix;
+			    __entry->bw_share = bw_share;
+			    __entry->max_rate = max_rate;
+			    __entry->group = vport->qos.group;
+		    ),
+		    TP_printk("(%s) vport=%hu tsar_ix=%u bw_share=%u, max_rate=%u group=%p\n",
+			      __get_str(devname), __entry->vport_id, __entry->tsar_ix,
+			      __entry->bw_share, __entry->max_rate, __entry->group
+			      )
+);
+
+DEFINE_EVENT(mlx5_esw_vport_qos_template, mlx5_esw_vport_qos_create,
+	     TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate),
+	     TP_ARGS(vport, bw_share, max_rate)
+	     );
+
+DEFINE_EVENT(mlx5_esw_vport_qos_template, mlx5_esw_vport_qos_config,
+	     TP_PROTO(const struct mlx5_vport *vport, u32 bw_share, u32 max_rate),
+	     TP_ARGS(vport, bw_share, max_rate)
+	     );
+
+DECLARE_EVENT_CLASS(mlx5_esw_group_qos_template,
+		    TP_PROTO(const struct mlx5_core_dev *dev,
+			     const struct mlx5_esw_rate_group *group,
+			     unsigned int tsar_ix),
+		    TP_ARGS(dev, group, tsar_ix),
+		    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+				     __field(const void *, group)
+				     __field(unsigned int, tsar_ix)
+				     ),
+		    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+			    __entry->group = group;
+			    __entry->tsar_ix = tsar_ix;
+		    ),
+		    TP_printk("(%s) group=%p tsar_ix=%u\n",
+			      __get_str(devname), __entry->group, __entry->tsar_ix
+			      )
+);
+
+DEFINE_EVENT(mlx5_esw_group_qos_template, mlx5_esw_group_qos_create,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      const struct mlx5_esw_rate_group *group,
+		      unsigned int tsar_ix),
+	     TP_ARGS(dev, group, tsar_ix)
+	     );
+
+DEFINE_EVENT(mlx5_esw_group_qos_template, mlx5_esw_group_qos_destroy,
+	     TP_PROTO(const struct mlx5_core_dev *dev,
+		      const struct mlx5_esw_rate_group *group,
+		      unsigned int tsar_ix),
+	     TP_ARGS(dev, group, tsar_ix)
+	     );
+
+TRACE_EVENT(mlx5_esw_group_qos_config,
+	    TP_PROTO(const struct mlx5_core_dev *dev,
+		     const struct mlx5_esw_rate_group *group,
+		     unsigned int tsar_ix, u32 bw_share, u32 max_rate),
+	    TP_ARGS(dev, group, tsar_ix, bw_share, max_rate),
+	    TP_STRUCT__entry(__string(devname, dev_name(dev->device))
+			     __field(const void *, group)
+			     __field(unsigned int, tsar_ix)
+			     __field(unsigned int, bw_share)
+			     __field(unsigned int, max_rate)
+			     ),
+	    TP_fast_assign(__assign_str(devname, dev_name(dev->device));
+		    __entry->group = group;
+		    __entry->tsar_ix = tsar_ix;
+		    __entry->bw_share = bw_share;
+		    __entry->max_rate = max_rate;
+	    ),
+	    TP_printk("(%s) group=%p tsar_ix=%u bw_share=%u max_rate=%u\n",
+		      __get_str(devname), __entry->group, __entry->tsar_ix,
+		      __entry->bw_share, __entry->max_rate
+		      )
+);
+#endif /* _MLX5_ESW_TP_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH esw/diag
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE qos_tracepoint
+#include <trace/define_trace.h>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
index 3da7becc1069..425c91814b34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/indir_table.c
@@ -364,6 +364,7 @@ static int mlx5_create_indir_fwd_group(struct mlx5_eswitch *esw,
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest.vport.num = e->vport;
 	dest.vport.vhca_id = MLX5_CAP_GEN(esw->dev, vhca_id);
+	dest.vport.flags = MLX5_FLOW_DEST_VPORT_VHCA_ID;
 	e->fwd_rule = mlx5_add_flow_rules(e->ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(e->fwd_rule)) {
 		mlx5_destroy_flow_group(e->fwd_grp);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index d9041b16611d..df277a6cddc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -11,6 +11,7 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "fs_core.h"
+#include "esw/qos.h"
 
 enum {
 	LEGACY_VEPA_PRIO = 0,
@@ -508,3 +509,22 @@ unlock:
 	mutex_unlock(&esw->state_lock);
 	return err;
 }
+
+int mlx5_eswitch_set_vport_rate(struct mlx5_eswitch *esw, u16 vport,
+				u32 max_rate, u32 min_rate)
+{
+	struct mlx5_vport *evport = mlx5_eswitch_get_vport(esw, vport);
+	int err;
+
+	if (!mlx5_esw_allowed(esw))
+		return -EPERM;
+	if (IS_ERR(evport))
+		return PTR_ERR(evport);
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_esw_qos_set_vport_min_rate(esw, evport, min_rate, NULL);
+	if (!err)
+		err = mlx5_esw_qos_set_vport_max_rate(esw, evport, max_rate, NULL);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
new file mode 100644
index 000000000000..985e305179d1
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -0,0 +1,869 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#include "eswitch.h"
+#include "esw/qos.h"
+#include "en/port.h"
+#define CREATE_TRACE_POINTS
+#include "diag/qos_tracepoint.h"
+
+/* Minimum supported BW share value by the HW is 1 Mbit/sec */
+#define MLX5_MIN_BW_SHARE 1
+
+#define MLX5_RATE_TO_BW_SHARE(rate, divider, limit) \
+	min_t(u32, max_t(u32, DIV_ROUND_UP(rate, divider), MLX5_MIN_BW_SHARE), limit)
+
+struct mlx5_esw_rate_group {
+	u32 tsar_ix;
+	u32 max_rate;
+	u32 min_rate;
+	u32 bw_share;
+	struct list_head list;
+};
+
+static int esw_qos_tsar_config(struct mlx5_core_dev *dev, u32 *sched_ctx,
+			       u32 parent_ix, u32 tsar_ix,
+			       u32 max_rate, u32 bw_share)
+{
+	u32 bitmask = 0;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+		return -EOPNOTSUPP;
+
+	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_ix);
+	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate);
+	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
+	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
+	bitmask |= MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_BW_SHARE;
+
+	return mlx5_modify_scheduling_element_cmd(dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  sched_ctx,
+						  tsar_ix,
+						  bitmask);
+}
+
+static int esw_qos_group_config(struct mlx5_eswitch *esw, struct mlx5_esw_rate_group *group,
+				u32 max_rate, u32 bw_share, struct netlink_ext_ack *extack)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_core_dev *dev = esw->dev;
+	int err;
+
+	err = esw_qos_tsar_config(dev, sched_ctx,
+				  esw->qos.root_tsar_ix, group->tsar_ix,
+				  max_rate, bw_share);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch modify group TSAR element failed");
+
+	trace_mlx5_esw_group_qos_config(dev, group, group->tsar_ix, bw_share, max_rate);
+
+	return err;
+}
+
+static int esw_qos_vport_config(struct mlx5_eswitch *esw,
+				struct mlx5_vport *vport,
+				u32 max_rate, u32 bw_share,
+				struct netlink_ext_ack *extack)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_esw_rate_group *group = vport->qos.group;
+	struct mlx5_core_dev *dev = esw->dev;
+	u32 parent_tsar_ix;
+	void *vport_elem;
+	int err;
+
+	if (!vport->qos.enabled)
+		return -EIO;
+
+	parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
+	MLX5_SET(scheduling_context, sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx,
+				  element_attributes);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
+
+	err = esw_qos_tsar_config(dev, sched_ctx, parent_tsar_ix, vport->qos.esw_tsar_ix,
+				  max_rate, bw_share);
+	if (err) {
+		esw_warn(esw->dev,
+			 "E-Switch modify TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport->vport, err);
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch modify TSAR vport element failed");
+		return err;
+	}
+
+	trace_mlx5_esw_vport_qos_config(vport, bw_share, max_rate);
+
+	return 0;
+}
+
+static u32 esw_qos_calculate_min_rate_divider(struct mlx5_eswitch *esw,
+					      struct mlx5_esw_rate_group *group,
+					      bool group_level)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	struct mlx5_vport *evport;
+	u32 max_guarantee = 0;
+	unsigned long i;
+
+	if (group_level) {
+		struct mlx5_esw_rate_group *group;
+
+		list_for_each_entry(group, &esw->qos.groups, list) {
+			if (group->min_rate < max_guarantee)
+				continue;
+			max_guarantee = group->min_rate;
+		}
+	} else {
+		mlx5_esw_for_each_vport(esw, i, evport) {
+			if (!evport->enabled || !evport->qos.enabled ||
+			    evport->qos.group != group || evport->qos.min_rate < max_guarantee)
+				continue;
+			max_guarantee = evport->qos.min_rate;
+		}
+	}
+
+	if (max_guarantee)
+		return max_t(u32, max_guarantee / fw_max_bw_share, 1);
+
+	/* If vports min rate divider is 0 but their group has bw_share configured, then
+	 * need to set bw_share for vports to minimal value.
+	 */
+	if (!group_level && !max_guarantee && group->bw_share)
+		return 1;
+	return 0;
+}
+
+static u32 esw_qos_calc_bw_share(u32 min_rate, u32 divider, u32 fw_max)
+{
+	if (divider)
+		return MLX5_RATE_TO_BW_SHARE(min_rate, divider, fw_max);
+
+	return 0;
+}
+
+static int esw_qos_normalize_vports_min_rate(struct mlx5_eswitch *esw,
+					     struct mlx5_esw_rate_group *group,
+					     struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	u32 divider = esw_qos_calculate_min_rate_divider(esw, group, false);
+	struct mlx5_vport *evport;
+	unsigned long i;
+	u32 bw_share;
+	int err;
+
+	mlx5_esw_for_each_vport(esw, i, evport) {
+		if (!evport->enabled || !evport->qos.enabled || evport->qos.group != group)
+			continue;
+		bw_share = esw_qos_calc_bw_share(evport->qos.min_rate, divider, fw_max_bw_share);
+
+		if (bw_share == evport->qos.bw_share)
+			continue;
+
+		err = esw_qos_vport_config(esw, evport, evport->qos.max_rate, bw_share, extack);
+		if (err)
+			return err;
+
+		evport->qos.bw_share = bw_share;
+	}
+
+	return 0;
+}
+
+static int esw_qos_normalize_groups_min_rate(struct mlx5_eswitch *esw, u32 divider,
+					     struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	struct mlx5_esw_rate_group *group;
+	u32 bw_share;
+	int err;
+
+	list_for_each_entry(group, &esw->qos.groups, list) {
+		bw_share = esw_qos_calc_bw_share(group->min_rate, divider, fw_max_bw_share);
+
+		if (bw_share == group->bw_share)
+			continue;
+
+		err = esw_qos_group_config(esw, group, group->max_rate, bw_share, extack);
+		if (err)
+			return err;
+
+		group->bw_share = bw_share;
+
+		/* All the group's vports need to be set with default bw_share
+		 * to enable them with QOS
+		 */
+		err = esw_qos_normalize_vports_min_rate(esw, group, extack);
+
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int mlx5_esw_qos_set_vport_min_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 min_rate,
+				    struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share, previous_min_rate;
+	bool min_rate_supported;
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	min_rate_supported = MLX5_CAP_QOS(esw->dev, esw_bw_share) &&
+				fw_max_bw_share >= MLX5_MIN_BW_SHARE;
+	if (min_rate && !min_rate_supported)
+		return -EOPNOTSUPP;
+	if (min_rate == evport->qos.min_rate)
+		return 0;
+
+	previous_min_rate = evport->qos.min_rate;
+	evport->qos.min_rate = min_rate;
+	err = esw_qos_normalize_vports_min_rate(esw, evport->qos.group, extack);
+	if (err)
+		evport->qos.min_rate = previous_min_rate;
+
+	return err;
+}
+
+int mlx5_esw_qos_set_vport_max_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 max_rate,
+				    struct netlink_ext_ack *extack)
+{
+	u32 act_max_rate = max_rate;
+	bool max_rate_supported;
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	max_rate_supported = MLX5_CAP_QOS(esw->dev, esw_rate_limit);
+
+	if (max_rate && !max_rate_supported)
+		return -EOPNOTSUPP;
+	if (max_rate == evport->qos.max_rate)
+		return 0;
+
+	/* If parent group has rate limit need to set to group
+	 * value when new max rate is 0.
+	 */
+	if (evport->qos.group && !max_rate)
+		act_max_rate = evport->qos.group->max_rate;
+
+	err = esw_qos_vport_config(esw, evport, act_max_rate, evport->qos.bw_share, extack);
+
+	if (!err)
+		evport->qos.max_rate = max_rate;
+
+	return err;
+}
+
+static int esw_qos_set_group_min_rate(struct mlx5_eswitch *esw, struct mlx5_esw_rate_group *group,
+				      u32 min_rate, struct netlink_ext_ack *extack)
+{
+	u32 fw_max_bw_share = MLX5_CAP_QOS(esw->dev, max_tsar_bw_share);
+	struct mlx5_core_dev *dev = esw->dev;
+	u32 previous_min_rate, divider;
+	int err;
+
+	if (!(MLX5_CAP_QOS(dev, esw_bw_share) && fw_max_bw_share >= MLX5_MIN_BW_SHARE))
+		return -EOPNOTSUPP;
+
+	if (min_rate == group->min_rate)
+		return 0;
+
+	previous_min_rate = group->min_rate;
+	group->min_rate = min_rate;
+	divider = esw_qos_calculate_min_rate_divider(esw, group, true);
+	err = esw_qos_normalize_groups_min_rate(esw, divider, extack);
+	if (err) {
+		group->min_rate = previous_min_rate;
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch group min rate setting failed");
+
+		/* Attempt restoring previous configuration */
+		divider = esw_qos_calculate_min_rate_divider(esw, group, true);
+		if (esw_qos_normalize_groups_min_rate(esw, divider, extack))
+			NL_SET_ERR_MSG_MOD(extack, "E-Switch BW share restore failed");
+	}
+
+	return err;
+}
+
+static int esw_qos_set_group_max_rate(struct mlx5_eswitch *esw,
+				      struct mlx5_esw_rate_group *group,
+				      u32 max_rate, struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport;
+	unsigned long i;
+	int err;
+
+	if (group->max_rate == max_rate)
+		return 0;
+
+	err = esw_qos_group_config(esw, group, max_rate, group->bw_share, extack);
+	if (err)
+		return err;
+
+	group->max_rate = max_rate;
+
+	/* Any unlimited vports in the group should be set
+	 * with the value of the group.
+	 */
+	mlx5_esw_for_each_vport(esw, i, vport) {
+		if (!vport->enabled || !vport->qos.enabled ||
+		    vport->qos.group != group || vport->qos.max_rate)
+			continue;
+
+		err = esw_qos_vport_config(esw, vport, max_rate, vport->qos.bw_share, extack);
+		if (err)
+			NL_SET_ERR_MSG_MOD(extack,
+					   "E-Switch vport implicit rate limit setting failed");
+	}
+
+	return err;
+}
+
+static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport,
+					      u32 max_rate, u32 bw_share)
+{
+	u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_esw_rate_group *group = vport->qos.group;
+	struct mlx5_core_dev *dev = esw->dev;
+	u32 parent_tsar_ix;
+	void *vport_elem;
+	int err;
+
+	parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
+	MLX5_SET(scheduling_context, sched_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+	vport_elem = MLX5_ADDR_OF(scheduling_context, sched_ctx, element_attributes);
+	MLX5_SET(vport_element, vport_elem, vport_number, vport->vport);
+	MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_tsar_ix);
+	MLX5_SET(scheduling_context, sched_ctx, max_average_bw, max_rate);
+	MLX5_SET(scheduling_context, sched_ctx, bw_share, bw_share);
+
+	err = mlx5_create_scheduling_element_cmd(dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 sched_ctx,
+						 &vport->qos.esw_tsar_ix);
+	if (err) {
+		esw_warn(esw->dev, "E-Switch create TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport->vport, err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int esw_qos_update_group_scheduling_element(struct mlx5_eswitch *esw,
+						   struct mlx5_vport *vport,
+						   struct mlx5_esw_rate_group *curr_group,
+						   struct mlx5_esw_rate_group *new_group,
+						   struct netlink_ext_ack *extack)
+{
+	u32 max_rate;
+	int err;
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  vport->qos.esw_tsar_ix);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR vport element failed");
+		return err;
+	}
+
+	vport->qos.group = new_group;
+	max_rate = vport->qos.max_rate ? vport->qos.max_rate : new_group->max_rate;
+
+	/* If vport is unlimited, we set the group's value.
+	 * Therefore, if the group is limited it will apply to
+	 * the vport as well and if not, vport will remain unlimited.
+	 */
+	err = esw_qos_vport_create_sched_element(esw, vport, max_rate, vport->qos.bw_share);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch vport group set failed.");
+		goto err_sched;
+	}
+
+	return 0;
+
+err_sched:
+	vport->qos.group = curr_group;
+	max_rate = vport->qos.max_rate ? vport->qos.max_rate : curr_group->max_rate;
+	if (esw_qos_vport_create_sched_element(esw, vport, max_rate, vport->qos.bw_share))
+		esw_warn(esw->dev, "E-Switch vport group restore failed (vport=%d)\n",
+			 vport->vport);
+
+	return err;
+}
+
+static int esw_qos_vport_update_group(struct mlx5_eswitch *esw,
+				      struct mlx5_vport *vport,
+				      struct mlx5_esw_rate_group *group,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_rate_group *new_group, *curr_group;
+	int err;
+
+	if (!vport->enabled)
+		return -EINVAL;
+
+	curr_group = vport->qos.group;
+	new_group = group ?: esw->qos.group0;
+	if (curr_group == new_group)
+		return 0;
+
+	err = esw_qos_update_group_scheduling_element(esw, vport, curr_group, new_group, extack);
+	if (err)
+		return err;
+
+	/* Recalculate bw share weights of old and new groups */
+	if (vport->qos.bw_share) {
+		esw_qos_normalize_vports_min_rate(esw, curr_group, extack);
+		esw_qos_normalize_vports_min_rate(esw, new_group, extack);
+	}
+
+	return 0;
+}
+
+static struct mlx5_esw_rate_group *
+esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_esw_rate_group *group;
+	u32 divider;
+	int err;
+
+	if (!MLX5_CAP_QOS(esw->dev, log_esw_max_sched_depth))
+		return ERR_PTR(-EOPNOTSUPP);
+
+	group = kzalloc(sizeof(*group), GFP_KERNEL);
+	if (!group)
+		return ERR_PTR(-ENOMEM);
+
+	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
+		 esw->qos.root_tsar_ix);
+	err = mlx5_create_scheduling_element_cmd(esw->dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 tsar_ctx,
+						 &group->tsar_ix);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for group failed");
+		goto err_sched_elem;
+	}
+
+	list_add_tail(&group->list, &esw->qos.groups);
+
+	divider = esw_qos_calculate_min_rate_divider(esw, group, true);
+	if (divider) {
+		err = esw_qos_normalize_groups_min_rate(esw, divider, extack);
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "E-Switch groups normalization failed");
+			goto err_min_rate;
+		}
+	}
+	trace_mlx5_esw_group_qos_create(esw->dev, group, group->tsar_ix);
+
+	return group;
+
+err_min_rate:
+	list_del(&group->list);
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  group->tsar_ix);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR for group failed");
+err_sched_elem:
+	kfree(group);
+	return ERR_PTR(err);
+}
+
+static int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw,
+				      struct mlx5_esw_rate_group *group,
+				      struct netlink_ext_ack *extack)
+{
+	u32 divider;
+	int err;
+
+	list_del(&group->list);
+
+	divider = esw_qos_calculate_min_rate_divider(esw, NULL, true);
+	err = esw_qos_normalize_groups_min_rate(esw, divider, extack);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch groups' normalization failed");
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  group->tsar_ix);
+	if (err)
+		NL_SET_ERR_MSG_MOD(extack, "E-Switch destroy TSAR_ID failed");
+
+	trace_mlx5_esw_group_qos_destroy(esw->dev, group, group->tsar_ix);
+	kfree(group);
+	return err;
+}
+
+static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type)
+{
+	switch (type) {
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_TASR;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_VPORT_TC;
+	case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
+		return MLX5_CAP_QOS(dev, esw_element_type) &
+		       ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
+	}
+	return false;
+}
+
+void mlx5_esw_qos_create(struct mlx5_eswitch *esw)
+{
+	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_core_dev *dev = esw->dev;
+	__be32 *attr;
+	int err;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+		return;
+
+	if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
+		return;
+
+	mutex_lock(&esw->state_lock);
+	if (esw->qos.enabled)
+		goto unlock;
+
+	MLX5_SET(scheduling_context, tsar_ctx, element_type,
+		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+
+	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
+	*attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
+
+	err = mlx5_create_scheduling_element_cmd(dev,
+						 SCHEDULING_HIERARCHY_E_SWITCH,
+						 tsar_ctx,
+						 &esw->qos.root_tsar_ix);
+	if (err) {
+		esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err);
+		goto unlock;
+	}
+
+	INIT_LIST_HEAD(&esw->qos.groups);
+	if (MLX5_CAP_QOS(dev, log_esw_max_sched_depth)) {
+		esw->qos.group0 = esw_qos_create_rate_group(esw, NULL);
+		if (IS_ERR(esw->qos.group0)) {
+			esw_warn(dev, "E-Switch create rate group 0 failed (%ld)\n",
+				 PTR_ERR(esw->qos.group0));
+			goto err_group0;
+		}
+	}
+	esw->qos.enabled = true;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return;
+
+err_group0:
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  esw->qos.root_tsar_ix);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err);
+	mutex_unlock(&esw->state_lock);
+}
+
+void mlx5_esw_qos_destroy(struct mlx5_eswitch *esw)
+{
+	struct devlink *devlink = priv_to_devlink(esw->dev);
+	int err;
+
+	devlink_rate_nodes_destroy(devlink);
+	mutex_lock(&esw->state_lock);
+	if (!esw->qos.enabled)
+		goto unlock;
+
+	if (esw->qos.group0)
+		esw_qos_destroy_rate_group(esw, esw->qos.group0, NULL);
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  esw->qos.root_tsar_ix);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy root TSAR failed (%d)\n", err);
+
+	esw->qos.enabled = false;
+unlock:
+	mutex_unlock(&esw->state_lock);
+}
+
+int mlx5_esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+			      u32 max_rate, u32 bw_share)
+{
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	if (!esw->qos.enabled)
+		return 0;
+
+	if (vport->qos.enabled)
+		return -EEXIST;
+
+	vport->qos.group = esw->qos.group0;
+
+	err = esw_qos_vport_create_sched_element(esw, vport, max_rate, bw_share);
+	if (!err) {
+		vport->qos.enabled = true;
+		trace_mlx5_esw_vport_qos_create(vport, bw_share, max_rate);
+	}
+
+	return err;
+}
+
+void mlx5_esw_qos_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport)
+{
+	int err;
+
+	lockdep_assert_held(&esw->state_lock);
+	if (!esw->qos.enabled || !vport->qos.enabled)
+		return;
+	WARN(vport->qos.group && vport->qos.group != esw->qos.group0,
+	     "Disabling QoS on port before detaching it from group");
+
+	err = mlx5_destroy_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  vport->qos.esw_tsar_ix);
+	if (err)
+		esw_warn(esw->dev, "E-Switch destroy TSAR vport element failed (vport=%d,err=%d)\n",
+			 vport->vport, err);
+
+	vport->qos.enabled = false;
+	trace_mlx5_esw_vport_qos_destroy(vport);
+}
+
+int mlx5_esw_qos_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, u32 rate_mbps)
+{
+	u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+	struct mlx5_vport *vport;
+	u32 bitmask;
+
+	vport = mlx5_eswitch_get_vport(esw, vport_num);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	if (!vport->qos.enabled)
+		return -EOPNOTSUPP;
+
+	MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps);
+	bitmask = MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW;
+
+	return mlx5_modify_scheduling_element_cmd(esw->dev,
+						  SCHEDULING_HIERARCHY_E_SWITCH,
+						  ctx,
+						  vport->qos.esw_tsar_ix,
+						  bitmask);
+}
+
+#define MLX5_LINKSPEED_UNIT 125000 /* 1Mbps in Bps */
+
+/* Converts bytes per second value passed in a pointer into megabits per
+ * second, rewriting last. If converted rate exceed link speed or is not a
+ * fraction of Mbps - returns error.
+ */
+static int esw_qos_devlink_rate_to_mbps(struct mlx5_core_dev *mdev, const char *name,
+					u64 *rate, struct netlink_ext_ack *extack)
+{
+	u32 link_speed_max, reminder;
+	u64 value;
+	int err;
+
+	err = mlx5e_port_max_linkspeed(mdev, &link_speed_max);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to get link maximum speed");
+		return err;
+	}
+
+	value = div_u64_rem(*rate, MLX5_LINKSPEED_UNIT, &reminder);
+	if (reminder) {
+		pr_err("%s rate value %lluBps not in link speed units of 1Mbps.\n",
+		       name, *rate);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value not in link speed units of 1Mbps");
+		return -EINVAL;
+	}
+
+	if (value > link_speed_max) {
+		pr_err("%s rate value %lluMbps exceed link maximum speed %u.\n",
+		       name, value, link_speed_max);
+		NL_SET_ERR_MSG_MOD(extack, "TX rate value exceed link maximum speed");
+		return -EINVAL;
+	}
+
+	*rate = value;
+	return 0;
+}
+
+/* Eswitch devlink rate API */
+
+int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport = priv;
+	struct mlx5_eswitch *esw;
+	int err;
+
+	esw = vport->dev->priv.eswitch;
+	if (!mlx5_esw_allowed(esw))
+		return -EPERM;
+
+	err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_esw_qos_set_vport_min_rate(esw, vport, tx_share, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct mlx5_vport *vport = priv;
+	struct mlx5_eswitch *esw;
+	int err;
+
+	esw = vport->dev->priv.eswitch;
+	if (!mlx5_esw_allowed(esw))
+		return -EPERM;
+
+	err = esw_qos_devlink_rate_to_mbps(vport->dev, "tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = mlx5_esw_qos_set_vport_max_rate(esw, vport, tx_max, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(rate_node->devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	struct mlx5_esw_rate_group *group = priv;
+	int err;
+
+	err = esw_qos_devlink_rate_to_mbps(dev, "tx_share", &tx_share, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_set_group_min_rate(esw, group, tx_share, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(rate_node->devlink);
+	struct mlx5_eswitch *esw = dev->priv.eswitch;
+	struct mlx5_esw_rate_group *group = priv;
+	int err;
+
+	err = esw_qos_devlink_rate_to_mbps(dev, "tx_max", &tx_max, extack);
+	if (err)
+		return err;
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_set_group_max_rate(esw, group, tx_max, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
+				   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_rate_group *group;
+	struct mlx5_eswitch *esw;
+	int err = 0;
+
+	esw = mlx5_devlink_eswitch_get(rate_node->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	mutex_lock(&esw->state_lock);
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Rate node creation supported only in switchdev mode");
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	group = esw_qos_create_rate_group(esw, extack);
+	if (IS_ERR(group)) {
+		err = PTR_ERR(group);
+		goto unlock;
+	}
+
+	*priv = group;
+unlock:
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv,
+				   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_rate_group *group = priv;
+	struct mlx5_eswitch *esw;
+	int err;
+
+	esw = mlx5_devlink_eswitch_get(rate_node->devlink);
+	if (IS_ERR(esw))
+		return PTR_ERR(esw);
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_destroy_rate_group(esw, group, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_qos_vport_update_group(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport,
+				    struct mlx5_esw_rate_group *group,
+				    struct netlink_ext_ack *extack)
+{
+	int err;
+
+	mutex_lock(&esw->state_lock);
+	err = esw_qos_vport_update_group(esw, vport, group, extack);
+	mutex_unlock(&esw->state_lock);
+	return err;
+}
+
+int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
+				     struct devlink_rate *parent,
+				     void *priv, void *parent_priv,
+				     struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_rate_group *group;
+	struct mlx5_vport *vport = priv;
+
+	if (!parent)
+		return mlx5_esw_qos_vport_update_group(vport->dev->priv.eswitch,
+						       vport, NULL, extack);
+
+	group = parent_priv;
+	return mlx5_esw_qos_vport_update_group(vport->dev->priv.eswitch, vport, group, extack);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
new file mode 100644
index 000000000000..28451abe2d2f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
+
+#ifndef __MLX5_ESW_QOS_H__
+#define __MLX5_ESW_QOS_H__
+
+#ifdef CONFIG_MLX5_ESWITCH
+
+int mlx5_esw_qos_set_vport_min_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 min_rate,
+				    struct netlink_ext_ack *extack);
+int mlx5_esw_qos_set_vport_max_rate(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *evport,
+				    u32 max_rate,
+				    struct netlink_ext_ack *extack);
+void mlx5_esw_qos_create(struct mlx5_eswitch *esw);
+void mlx5_esw_qos_destroy(struct mlx5_eswitch *esw);
+int mlx5_esw_qos_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+			      u32 max_rate, u32 bw_share);
+void mlx5_esw_qos_vport_disable(struct mlx5_eswitch *esw, struct mlx5_vport *vport);
+
+int mlx5_esw_devlink_rate_leaf_tx_share_set(struct devlink_rate *rate_leaf, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_leaf_tx_max_set(struct devlink_rate *rate_leaf, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_tx_share_set(struct devlink_rate *rate_node, void *priv,
+					    u64 tx_share, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_tx_max_set(struct devlink_rate *rate_node, void *priv,
+					  u64 tx_max, struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
+				   struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv,
+				   struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
+				     struct devlink_rate *parent,
+				     void *priv, void *parent_priv,
+				     struct netlink_ext_ack *extack);
+#endif
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c
deleted file mode 100644
index d3ad78aa9d45..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.c
+++ /dev/null
@@ -1,586 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-/* Copyright (c) 2021 Mellanox Technologies. */
-
-#include <linux/skbuff.h>
-#include <net/psample.h>
-#include "en/mapping.h"
-#include "esw/sample.h"
-#include "eswitch.h"
-#include "en_tc.h"
-#include "fs_core.h"
-
-#define MLX5_ESW_VPORT_TBL_SIZE_SAMPLE (64 * 1024)
-
-static const struct esw_vport_tbl_namespace mlx5_esw_vport_tbl_sample_ns = {
-	.max_fte = MLX5_ESW_VPORT_TBL_SIZE_SAMPLE,
-	.max_num_groups = 0,    /* default num of groups */
-	.flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | MLX5_FLOW_TABLE_TUNNEL_EN_DECAP,
-};
-
-struct mlx5_esw_psample {
-	struct mlx5e_priv *priv;
-	struct mlx5_flow_table *termtbl;
-	struct mlx5_flow_handle *termtbl_rule;
-	DECLARE_HASHTABLE(hashtbl, 8);
-	struct mutex ht_lock; /* protect hashtbl */
-	DECLARE_HASHTABLE(restore_hashtbl, 8);
-	struct mutex restore_lock; /* protect restore_hashtbl */
-};
-
-struct mlx5_sampler {
-	struct hlist_node hlist;
-	u32 sampler_id;
-	u32 sample_ratio;
-	u32 sample_table_id;
-	u32 default_table_id;
-	int count;
-};
-
-struct mlx5_sample_flow {
-	struct mlx5_sampler *sampler;
-	struct mlx5_sample_restore *restore;
-	struct mlx5_flow_attr *pre_attr;
-	struct mlx5_flow_handle *pre_rule;
-	struct mlx5_flow_handle *rule;
-};
-
-struct mlx5_sample_restore {
-	struct hlist_node hlist;
-	struct mlx5_modify_hdr *modify_hdr;
-	struct mlx5_flow_handle *rule;
-	u32 obj_id;
-	int count;
-};
-
-static int
-sampler_termtbl_create(struct mlx5_esw_psample *esw_psample)
-{
-	struct mlx5_core_dev *dev = esw_psample->priv->mdev;
-	struct mlx5_eswitch *esw = dev->priv.eswitch;
-	struct mlx5_flow_table_attr ft_attr = {};
-	struct mlx5_flow_destination dest = {};
-	struct mlx5_flow_namespace *root_ns;
-	struct mlx5_flow_act act = {};
-	int err;
-
-	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(dev, termination_table))  {
-		mlx5_core_warn(dev, "termination table is not supported\n");
-		return -EOPNOTSUPP;
-	}
-
-	root_ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_FDB);
-	if (!root_ns) {
-		mlx5_core_warn(dev, "failed to get FDB flow namespace\n");
-		return -EOPNOTSUPP;
-	}
-
-	ft_attr.flags = MLX5_FLOW_TABLE_TERMINATION | MLX5_FLOW_TABLE_UNMANAGED;
-	ft_attr.autogroup.max_num_groups = 1;
-	ft_attr.prio = FDB_SLOW_PATH;
-	ft_attr.max_fte = 1;
-	ft_attr.level = 1;
-	esw_psample->termtbl = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr);
-	if (IS_ERR(esw_psample->termtbl)) {
-		err = PTR_ERR(esw_psample->termtbl);
-		mlx5_core_warn(dev, "failed to create termtbl, err: %d\n", err);
-		return err;
-	}
-
-	act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
-	dest.vport.num = esw->manager_vport;
-	esw_psample->termtbl_rule = mlx5_add_flow_rules(esw_psample->termtbl, NULL, &act, &dest, 1);
-	if (IS_ERR(esw_psample->termtbl_rule)) {
-		err = PTR_ERR(esw_psample->termtbl_rule);
-		mlx5_core_warn(dev, "failed to create termtbl rule, err: %d\n", err);
-		mlx5_destroy_flow_table(esw_psample->termtbl);
-		return err;
-	}
-
-	return 0;
-}
-
-static void
-sampler_termtbl_destroy(struct mlx5_esw_psample *esw_psample)
-{
-	mlx5_del_flow_rules(esw_psample->termtbl_rule);
-	mlx5_destroy_flow_table(esw_psample->termtbl);
-}
-
-static int
-sampler_obj_create(struct mlx5_core_dev *mdev, struct mlx5_sampler *sampler)
-{
-	u32 in[MLX5_ST_SZ_DW(create_sampler_obj_in)] = {};
-	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
-	u64 general_obj_types;
-	void *obj;
-	int err;
-
-	general_obj_types = MLX5_CAP_GEN_64(mdev, general_obj_types);
-	if (!(general_obj_types & MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER))
-		return -EOPNOTSUPP;
-	if (!MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
-		return -EOPNOTSUPP;
-
-	obj = MLX5_ADDR_OF(create_sampler_obj_in, in, sampler_object);
-	MLX5_SET(sampler_obj, obj, table_type, FS_FT_FDB);
-	MLX5_SET(sampler_obj, obj, ignore_flow_level, 1);
-	MLX5_SET(sampler_obj, obj, level, 1);
-	MLX5_SET(sampler_obj, obj, sample_ratio, sampler->sample_ratio);
-	MLX5_SET(sampler_obj, obj, sample_table_id, sampler->sample_table_id);
-	MLX5_SET(sampler_obj, obj, default_table_id, sampler->default_table_id);
-	MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
-	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_GENERAL_OBJECT_TYPES_SAMPLER);
-
-	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-	if (!err)
-		sampler->sampler_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
-
-	return err;
-}
-
-static void
-sampler_obj_destroy(struct mlx5_core_dev *mdev, u32 sampler_id)
-{
-	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
-	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
-
-	MLX5_SET(general_obj_in_cmd_hdr, in, opcode, MLX5_CMD_OP_DESTROY_GENERAL_OBJECT);
-	MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_GENERAL_OBJECT_TYPES_SAMPLER);
-	MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, sampler_id);
-
-	mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-}
-
-static u32
-sampler_hash(u32 sample_ratio, u32 default_table_id)
-{
-	return jhash_2words(sample_ratio, default_table_id, 0);
-}
-
-static int
-sampler_cmp(u32 sample_ratio1, u32 default_table_id1, u32 sample_ratio2, u32 default_table_id2)
-{
-	return sample_ratio1 != sample_ratio2 || default_table_id1 != default_table_id2;
-}
-
-static struct mlx5_sampler *
-sampler_get(struct mlx5_esw_psample *esw_psample, u32 sample_ratio, u32 default_table_id)
-{
-	struct mlx5_sampler *sampler;
-	u32 hash_key;
-	int err;
-
-	mutex_lock(&esw_psample->ht_lock);
-	hash_key = sampler_hash(sample_ratio, default_table_id);
-	hash_for_each_possible(esw_psample->hashtbl, sampler, hlist, hash_key)
-		if (!sampler_cmp(sampler->sample_ratio, sampler->default_table_id,
-				 sample_ratio, default_table_id))
-			goto add_ref;
-
-	sampler = kzalloc(sizeof(*sampler), GFP_KERNEL);
-	if (!sampler) {
-		err = -ENOMEM;
-		goto err_alloc;
-	}
-
-	sampler->sample_table_id = esw_psample->termtbl->id;
-	sampler->default_table_id = default_table_id;
-	sampler->sample_ratio = sample_ratio;
-
-	err = sampler_obj_create(esw_psample->priv->mdev, sampler);
-	if (err)
-		goto err_create;
-
-	hash_add(esw_psample->hashtbl, &sampler->hlist, hash_key);
-
-add_ref:
-	sampler->count++;
-	mutex_unlock(&esw_psample->ht_lock);
-	return sampler;
-
-err_create:
-	kfree(sampler);
-err_alloc:
-	mutex_unlock(&esw_psample->ht_lock);
-	return ERR_PTR(err);
-}
-
-static void
-sampler_put(struct mlx5_esw_psample *esw_psample, struct mlx5_sampler *sampler)
-{
-	mutex_lock(&esw_psample->ht_lock);
-	if (--sampler->count == 0) {
-		hash_del(&sampler->hlist);
-		sampler_obj_destroy(esw_psample->priv->mdev, sampler->sampler_id);
-		kfree(sampler);
-	}
-	mutex_unlock(&esw_psample->ht_lock);
-}
-
-static struct mlx5_modify_hdr *
-sample_metadata_rule_get(struct mlx5_core_dev *mdev, u32 obj_id)
-{
-	struct mlx5e_tc_mod_hdr_acts mod_acts = {};
-	struct mlx5_modify_hdr *modify_hdr;
-	int err;
-
-	err = mlx5e_tc_match_to_reg_set(mdev, &mod_acts, MLX5_FLOW_NAMESPACE_FDB,
-					CHAIN_TO_REG, obj_id);
-	if (err)
-		goto err_set_regc0;
-
-	modify_hdr = mlx5_modify_header_alloc(mdev, MLX5_FLOW_NAMESPACE_FDB,
-					      mod_acts.num_actions,
-					      mod_acts.actions);
-	if (IS_ERR(modify_hdr)) {
-		err = PTR_ERR(modify_hdr);
-		goto err_modify_hdr;
-	}
-
-	dealloc_mod_hdr_actions(&mod_acts);
-	return modify_hdr;
-
-err_modify_hdr:
-	dealloc_mod_hdr_actions(&mod_acts);
-err_set_regc0:
-	return ERR_PTR(err);
-}
-
-static struct mlx5_sample_restore *
-sample_restore_get(struct mlx5_esw_psample *esw_psample, u32 obj_id)
-{
-	struct mlx5_core_dev *mdev = esw_psample->priv->mdev;
-	struct mlx5_eswitch *esw = mdev->priv.eswitch;
-	struct mlx5_sample_restore *restore;
-	struct mlx5_modify_hdr *modify_hdr;
-	int err;
-
-	mutex_lock(&esw_psample->restore_lock);
-	hash_for_each_possible(esw_psample->restore_hashtbl, restore, hlist, obj_id)
-		if (restore->obj_id == obj_id)
-			goto add_ref;
-
-	restore = kzalloc(sizeof(*restore), GFP_KERNEL);
-	if (!restore) {
-		err = -ENOMEM;
-		goto err_alloc;
-	}
-	restore->obj_id = obj_id;
-
-	modify_hdr = sample_metadata_rule_get(mdev, obj_id);
-	if (IS_ERR(modify_hdr)) {
-		err = PTR_ERR(modify_hdr);
-		goto err_modify_hdr;
-	}
-	restore->modify_hdr = modify_hdr;
-
-	restore->rule = esw_add_restore_rule(esw, obj_id);
-	if (IS_ERR(restore->rule)) {
-		err = PTR_ERR(restore->rule);
-		goto err_restore;
-	}
-
-	hash_add(esw_psample->restore_hashtbl, &restore->hlist, obj_id);
-add_ref:
-	restore->count++;
-	mutex_unlock(&esw_psample->restore_lock);
-	return restore;
-
-err_restore:
-	mlx5_modify_header_dealloc(mdev, restore->modify_hdr);
-err_modify_hdr:
-	kfree(restore);
-err_alloc:
-	mutex_unlock(&esw_psample->restore_lock);
-	return ERR_PTR(err);
-}
-
-static void
-sample_restore_put(struct mlx5_esw_psample *esw_psample, struct mlx5_sample_restore *restore)
-{
-	mutex_lock(&esw_psample->restore_lock);
-	if (--restore->count == 0)
-		hash_del(&restore->hlist);
-	mutex_unlock(&esw_psample->restore_lock);
-
-	if (!restore->count) {
-		mlx5_del_flow_rules(restore->rule);
-		mlx5_modify_header_dealloc(esw_psample->priv->mdev, restore->modify_hdr);
-		kfree(restore);
-	}
-}
-
-void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj)
-{
-	u32 trunc_size = mapped_obj->sample.trunc_size;
-	struct psample_group psample_group = {};
-	struct psample_metadata md = {};
-
-	md.trunc_size = trunc_size ? min(trunc_size, skb->len) : skb->len;
-	md.in_ifindex = skb->dev->ifindex;
-	psample_group.group_num = mapped_obj->sample.group_id;
-	psample_group.net = &init_net;
-	skb_push(skb, skb->mac_len);
-
-	psample_sample_packet(&psample_group, skb, mapped_obj->sample.rate, &md);
-}
-
-/* For the following typical flow table:
- *
- * +-------------------------------+
- * +       original flow table     +
- * +-------------------------------+
- * +         original match        +
- * +-------------------------------+
- * + sample action + other actions +
- * +-------------------------------+
- *
- * We translate the tc filter with sample action to the following HW model:
- *
- *         +---------------------+
- *         + original flow table +
- *         +---------------------+
- *         +   original match    +
- *         +---------------------+
- *                    |
- *                    v
- * +------------------------------------------------+
- * +                Flow Sampler Object             +
- * +------------------------------------------------+
- * +                    sample ratio                +
- * +------------------------------------------------+
- * +    sample table id    |    default table id    +
- * +------------------------------------------------+
- *            |                            |
- *            v                            v
- * +-----------------------------+  +----------------------------------------+
- * +        sample table         +  + default table per <vport, chain, prio> +
- * +-----------------------------+  +----------------------------------------+
- * + forward to management vport +  +            original match              +
- * +-----------------------------+  +----------------------------------------+
- *                                  +            other actions               +
- *                                  +----------------------------------------+
- */
-struct mlx5_flow_handle *
-mlx5_esw_sample_offload(struct mlx5_esw_psample *esw_psample,
-			struct mlx5_flow_spec *spec,
-			struct mlx5_flow_attr *attr)
-{
-	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
-	struct mlx5_vport_tbl_attr per_vport_tbl_attr;
-	struct mlx5_esw_flow_attr *pre_esw_attr;
-	struct mlx5_mapped_obj restore_obj = {};
-	struct mlx5_sample_flow *sample_flow;
-	struct mlx5_sample_attr *sample_attr;
-	struct mlx5_flow_table *default_tbl;
-	struct mlx5_flow_attr *pre_attr;
-	struct mlx5_eswitch *esw;
-	u32 obj_id;
-	int err;
-
-	if (IS_ERR_OR_NULL(esw_psample))
-		return ERR_PTR(-EOPNOTSUPP);
-
-	/* If slow path flag is set, eg. when the neigh is invalid for encap,
-	 * don't offload sample action.
-	 */
-	esw = esw_psample->priv->mdev->priv.eswitch;
-	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH)
-		return mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
-
-	sample_flow = kzalloc(sizeof(*sample_flow), GFP_KERNEL);
-	if (!sample_flow)
-		return ERR_PTR(-ENOMEM);
-	esw_attr->sample->sample_flow = sample_flow;
-
-	/* Allocate default table per vport, chain and prio. Otherwise, there is
-	 * only one default table for the same sampler object. Rules with different
-	 * prio and chain may overlap. For CT sample action, per vport default
-	 * table is needed to resotre the metadata.
-	 */
-	per_vport_tbl_attr.chain = attr->chain;
-	per_vport_tbl_attr.prio = attr->prio;
-	per_vport_tbl_attr.vport = esw_attr->in_rep->vport;
-	per_vport_tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
-	default_tbl = mlx5_esw_vporttbl_get(esw, &per_vport_tbl_attr);
-	if (IS_ERR(default_tbl)) {
-		err = PTR_ERR(default_tbl);
-		goto err_default_tbl;
-	}
-
-	/* Perform the original matches on the default table.
-	 * Offload all actions except the sample action.
-	 */
-	esw_attr->sample->sample_default_tbl = default_tbl;
-	/* When offloading sample and encap action, if there is no valid
-	 * neigh data struct, a slow path rule is offloaded first. Source
-	 * port metadata match is set at that time. A per vport table is
-	 * already allocated. No need to match it again. So clear the source
-	 * port metadata match.
-	 */
-	mlx5_eswitch_clear_rule_source_port(esw, spec);
-	sample_flow->rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
-	if (IS_ERR(sample_flow->rule)) {
-		err = PTR_ERR(sample_flow->rule);
-		goto err_offload_rule;
-	}
-
-	/* Create sampler object. */
-	sample_flow->sampler = sampler_get(esw_psample, esw_attr->sample->rate, default_tbl->id);
-	if (IS_ERR(sample_flow->sampler)) {
-		err = PTR_ERR(sample_flow->sampler);
-		goto err_sampler;
-	}
-
-	/* Create an id mapping reg_c0 value to sample object. */
-	restore_obj.type = MLX5_MAPPED_OBJ_SAMPLE;
-	restore_obj.sample.group_id = esw_attr->sample->group_num;
-	restore_obj.sample.rate = esw_attr->sample->rate;
-	restore_obj.sample.trunc_size = esw_attr->sample->trunc_size;
-	err = mapping_add(esw->offloads.reg_c0_obj_pool, &restore_obj, &obj_id);
-	if (err)
-		goto err_obj_id;
-	esw_attr->sample->restore_obj_id = obj_id;
-
-	/* Create sample restore context. */
-	sample_flow->restore = sample_restore_get(esw_psample, obj_id);
-	if (IS_ERR(sample_flow->restore)) {
-		err = PTR_ERR(sample_flow->restore);
-		goto err_sample_restore;
-	}
-
-	/* Perform the original matches on the original table. Offload the
-	 * sample action. The destination is the sampler object.
-	 */
-	pre_attr = mlx5_alloc_flow_attr(MLX5_FLOW_NAMESPACE_FDB);
-	if (!pre_attr) {
-		err = -ENOMEM;
-		goto err_alloc_flow_attr;
-	}
-	sample_attr = kzalloc(sizeof(*sample_attr), GFP_KERNEL);
-	if (!sample_attr) {
-		err = -ENOMEM;
-		goto err_alloc_sample_attr;
-	}
-	pre_esw_attr = pre_attr->esw_attr;
-	pre_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-	pre_attr->modify_hdr = sample_flow->restore->modify_hdr;
-	pre_attr->flags = MLX5_ESW_ATTR_FLAG_SAMPLE;
-	pre_attr->chain = attr->chain;
-	pre_attr->prio = attr->prio;
-	pre_esw_attr->sample = sample_attr;
-	pre_esw_attr->sample->sampler_id = sample_flow->sampler->sampler_id;
-	pre_esw_attr->in_mdev = esw_attr->in_mdev;
-	pre_esw_attr->in_rep = esw_attr->in_rep;
-	sample_flow->pre_rule = mlx5_eswitch_add_offloaded_rule(esw, spec, pre_attr);
-	if (IS_ERR(sample_flow->pre_rule)) {
-		err = PTR_ERR(sample_flow->pre_rule);
-		goto err_pre_offload_rule;
-	}
-	sample_flow->pre_attr = pre_attr;
-
-	return sample_flow->rule;
-
-err_pre_offload_rule:
-	kfree(sample_attr);
-err_alloc_sample_attr:
-	kfree(pre_attr);
-err_alloc_flow_attr:
-	sample_restore_put(esw_psample, sample_flow->restore);
-err_sample_restore:
-	mapping_remove(esw->offloads.reg_c0_obj_pool, obj_id);
-err_obj_id:
-	sampler_put(esw_psample, sample_flow->sampler);
-err_sampler:
-	/* For sample offload, rule is added in default_tbl. No need to call
-	 * mlx5_esw_chains_put_table()
-	 */
-	attr->prio = 0;
-	attr->chain = 0;
-	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->rule, attr);
-err_offload_rule:
-	mlx5_esw_vporttbl_put(esw, &per_vport_tbl_attr);
-err_default_tbl:
-	kfree(sample_flow);
-	return ERR_PTR(err);
-}
-
-void
-mlx5_esw_sample_unoffload(struct mlx5_esw_psample *esw_psample,
-			  struct mlx5_flow_handle *rule,
-			  struct mlx5_flow_attr *attr)
-{
-	struct mlx5_esw_flow_attr *esw_attr = attr->esw_attr;
-	struct mlx5_sample_flow *sample_flow;
-	struct mlx5_vport_tbl_attr tbl_attr;
-	struct mlx5_flow_attr *pre_attr;
-	struct mlx5_eswitch *esw;
-
-	if (IS_ERR_OR_NULL(esw_psample))
-		return;
-
-	/* If slow path flag is set, sample action is not offloaded.
-	 * No need to delete sample rule.
-	 */
-	esw = esw_psample->priv->mdev->priv.eswitch;
-	if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) {
-		mlx5_eswitch_del_offloaded_rule(esw, rule, attr);
-		return;
-	}
-
-	sample_flow = esw_attr->sample->sample_flow;
-	pre_attr = sample_flow->pre_attr;
-	memset(pre_attr, 0, sizeof(*pre_attr));
-	esw = esw_psample->priv->mdev->priv.eswitch;
-	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->pre_rule, pre_attr);
-	mlx5_eswitch_del_offloaded_rule(esw, sample_flow->rule, attr);
-
-	sample_restore_put(esw_psample, sample_flow->restore);
-	mapping_remove(esw->offloads.reg_c0_obj_pool, esw_attr->sample->restore_obj_id);
-	sampler_put(esw_psample, sample_flow->sampler);
-	tbl_attr.chain = attr->chain;
-	tbl_attr.prio = attr->prio;
-	tbl_attr.vport = esw_attr->in_rep->vport;
-	tbl_attr.vport_ns = &mlx5_esw_vport_tbl_sample_ns;
-	mlx5_esw_vporttbl_put(esw, &tbl_attr);
-
-	kfree(pre_attr->esw_attr->sample);
-	kfree(pre_attr);
-	kfree(sample_flow);
-}
-
-struct mlx5_esw_psample *
-mlx5_esw_sample_init(struct mlx5e_priv *priv)
-{
-	struct mlx5_esw_psample *esw_psample;
-	int err;
-
-	esw_psample = kzalloc(sizeof(*esw_psample), GFP_KERNEL);
-	if (!esw_psample)
-		return ERR_PTR(-ENOMEM);
-	esw_psample->priv = priv;
-	err = sampler_termtbl_create(esw_psample);
-	if (err)
-		goto err_termtbl;
-
-	mutex_init(&esw_psample->ht_lock);
-	mutex_init(&esw_psample->restore_lock);
-
-	return esw_psample;
-
-err_termtbl:
-	kfree(esw_psample);
-	return ERR_PTR(err);
-}
-
-void
-mlx5_esw_sample_cleanup(struct mlx5_esw_psample *esw_psample)
-{
-	if (IS_ERR_OR_NULL(esw_psample))
-		return;
-
-	mutex_destroy(&esw_psample->restore_lock);
-	mutex_destroy(&esw_psample->ht_lock);
-	sampler_termtbl_destroy(esw_psample);
-	kfree(esw_psample);
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h
deleted file mode 100644
index 2a3f4be10030..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/sample.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2021 Mellanox Technologies. */
-
-#ifndef __MLX5_EN_TC_SAMPLE_H__
-#define __MLX5_EN_TC_SAMPLE_H__
-
-#include "en.h"
-#include "eswitch.h"
-
-struct mlx5e_priv;
-struct mlx5_flow_attr;
-struct mlx5_esw_psample;
-
-struct mlx5_sample_attr {
-	u32 group_num;
-	u32 rate;
-	u32 trunc_size;
-	u32 restore_obj_id;
-	u32 sampler_id;
-	struct mlx5_flow_table *sample_default_tbl;
-	struct mlx5_sample_flow *sample_flow;
-};
-
-void mlx5_esw_sample_skb(struct sk_buff *skb, struct mlx5_mapped_obj *mapped_obj);
-
-struct mlx5_flow_handle *
-mlx5_esw_sample_offload(struct mlx5_esw_psample *sample_priv,
-			struct mlx5_flow_spec *spec,
-			struct mlx5_flow_attr *attr);
-
-void
-mlx5_esw_sample_unoffload(struct mlx5_esw_psample *sample_priv,
-			  struct mlx5_flow_handle *rule,
-			  struct mlx5_flow_attr *attr);
-
-struct mlx5_esw_psample *
-mlx5_esw_sample_init(struct mlx5e_priv *priv);
-
-void
-mlx5_esw_sample_cleanup(struct mlx5_esw_psample *esw_psample);
-
-#endif /* __MLX5_EN_TC_SAMPLE_H__ */