Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:
 "Another merge window, another pull full of stuff:

   1) Support alternative names for network devices, from Jiri Pirko.

   2) Introduce per-netns netdev notifiers, also from Jiri Pirko.

   3) Support MSG_PEEK in vsock/virtio, from Matias Ezequiel Vara
      Larsen.

   4) Allow compiling out the TLS TOE code, from Jakub Kicinski.

   5) Add several new tracepoints to the kTLS code, also from Jakub.

   6) Support set channels ethtool callback in ena driver, from Sameeh
      Jubran.

   7) New SCTP events SCTP_ADDR_ADDED, SCTP_ADDR_REMOVED,
      SCTP_ADDR_MADE_PRIM, and SCTP_SEND_FAILED_EVENT. From Xin Long.

   8) Add XDP support to mvneta driver, from Lorenzo Bianconi.

   9) Lots of netfilter hw offload fixes, cleanups and enhancements,
      from Pablo Neira Ayuso.

  10) PTP support for aquantia chips, from Egor Pomozov.

  11) Add UDP segmentation offload support to igb, ixgbe, and i40e. From
      Josh Hunt.

  12) Add smart nagle to tipc, from Jon Maloy.

  13) Support L2 field rewrite by TC offloads in bnxt_en, from Venkat
      Duvvuru.

  14) Add a flow mask cache to OVS, from Tonghao Zhang.

  15) Add XDP support to ice driver, from Maciej Fijalkowski.

  16) Add AF_XDP support to ice driver, from Krzysztof Kazimierczak.

  17) Support UDP GSO offload in atlantic driver, from Igor Russkikh.

  18) Support it in stmmac driver too, from Jose Abreu.

  19) Support TIPC encryption and auth, from Tuong Lien.

  20) Introduce BPF trampolines, from Alexei Starovoitov.

  21) Make page_pool API more numa friendly, from Saeed Mahameed.

  22) Introduce route hints to ipv4 and ipv6, from Paolo Abeni.

  23) Add UDP segmentation offload to cxgb4, Rahul Lakkireddy"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1857 commits)
  libbpf: Fix usage of u32 in userspace code
  mm: Implement no-MMU variant of vmalloc_user_node_flags
  slip: Fix use-after-free Read in slip_open
  net: dsa: sja1105: fix sja1105_parse_rgmii_delays()
  macvlan: schedule bc_work even if error
  enetc: add support Credit Based Shaper(CBS) for hardware offload
  net: phy: add helpers phy_(un)lock_mdio_bus
  mdio_bus: don't use managed reset-controller
  ax88179_178a: add ethtool_op_get_ts_info()
  mlxsw: spectrum_router: Fix use of uninitialized adjacency index
  mlxsw: spectrum_router: After underlay moves, demote conflicting tunnels
  bpf: Simplify __bpf_arch_text_poke poke type handling
  bpf: Introduce BPF_TRACE_x helper for the tracing tests
  bpf: Add bpf_jit_blinding_enabled for !CONFIG_BPF_JIT
  bpf, testing: Add various tail call test cases
  bpf, x86: Emit patchable direct jump as tail call
  bpf: Constant map key tracking for prog array pokes
  bpf: Add poke dependency tracking for prog array maps
  bpf: Add initial poke descriptor table for jit images
  bpf: Move owner type, jited info into array auxiliary data
  ...

40 files changed, 1385 insertions, 929 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 5708fcc079ca..a6f390fdb971 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -70,7 +70,7 @@ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/t
 
 mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \
 					steering/dr_matcher.o steering/dr_rule.o \
-					steering/dr_icm_pool.o steering/dr_crc32.o \
+					steering/dr_icm_pool.o \
 					steering/dr_ste.o steering/dr_send.o \
 					steering/dr_cmd.o steering/dr_fw.o \
 					steering/dr_action.o steering/fs_dr.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index ea934cd02448..34cba97f7bf4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -866,7 +866,7 @@ static void cmd_work_handler(struct work_struct *work)
 	if (!ent->page_queue) {
 		alloc_ret = alloc_ent(cmd);
 		if (alloc_ret < 0) {
-			mlx5_core_err(dev, "failed to allocate command entry\n");
+			mlx5_core_err_rl(dev, "failed to allocate command entry\n");
 			if (ent->callback) {
 				ent->callback(-EAGAIN, ent->context);
 				mlx5_free_cmd_msg(dev, ent->out);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 381925c90d94..ac108f1e5bd6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -85,6 +85,22 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	return 0;
 }
 
+static int mlx5_devlink_reload_down(struct devlink *devlink, bool netns_change,
+				    struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	return mlx5_unload_one(dev, false);
+}
+
+static int mlx5_devlink_reload_up(struct devlink *devlink,
+				  struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+
+	return mlx5_load_one(dev, false);
+}
+
 static const struct devlink_ops mlx5_devlink_ops = {
 #ifdef CONFIG_MLX5_ESWITCH
 	.eswitch_mode_set = mlx5_devlink_eswitch_mode_set,
@@ -96,6 +112,8 @@ static const struct devlink_ops mlx5_devlink_ops = {
 #endif
 	.flash_update = mlx5_devlink_flash_update,
 	.info_get = mlx5_devlink_info_get,
+	.reload_down = mlx5_devlink_reload_down,
+	.reload_up = mlx5_devlink_reload_up,
 };
 
 struct devlink *mlx5_devlink_alloc(void)
@@ -177,12 +195,29 @@ enum mlx5_devlink_param_id {
 	MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
 };
 
+static int mlx5_devlink_enable_roce_validate(struct devlink *devlink, u32 id,
+					     union devlink_param_value val,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_core_dev *dev = devlink_priv(devlink);
+	bool new_state = val.vbool;
+
+	if (new_state && !MLX5_CAP_GEN(dev, roce)) {
+		NL_SET_ERR_MSG_MOD(extack, "Device doesn't support RoCE");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static const struct devlink_param mlx5_devlink_params[] = {
 	DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
 			     "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING,
 			     BIT(DEVLINK_PARAM_CMODE_RUNTIME),
 			     mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set,
 			     mlx5_devlink_fs_mode_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_ROCE, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx5_devlink_enable_roce_validate),
 };
 
 static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
@@ -197,6 +232,11 @@ static void mlx5_devlink_set_params_init_values(struct devlink *devlink)
 	devlink_param_driverinit_value_set(devlink,
 					   MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE,
 					   value);
+
+	value.vbool = MLX5_CAP_GEN(dev, roce);
+	devlink_param_driverinit_value_set(devlink,
+					   DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE,
+					   value);
 }
 
 int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
@@ -213,6 +253,7 @@ int mlx5_devlink_register(struct devlink *devlink, struct device *dev)
 		goto params_reg_err;
 	mlx5_devlink_set_params_init_values(devlink);
 	devlink_params_publish(devlink);
+	devlink_reload_enable(devlink);
 	return 0;
 
 params_reg_err:
@@ -222,6 +263,7 @@ params_reg_err:
 
 void mlx5_devlink_unregister(struct devlink *devlink)
 {
+	devlink_reload_disable(devlink);
 	devlink_params_unregister(devlink, mlx5_devlink_params,
 				  ARRAY_SIZE(mlx5_devlink_params));
 	devlink_unregister(devlink);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
index 633b117eb13e..7b672ada63a3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port_buffer.c
@@ -175,7 +175,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *	@port_buffer: <output> port receive buffer configuration
  *	@change: <output>
  *
- *	Update buffer configuration based on pfc configuraiton and
+ *	Update buffer configuration based on pfc configuration and
  *	priority to buffer mapping.
  *	Buffer's lossy bit is changed to:
  *		lossless if there is at least one PFC enabled priority
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index b860569d4247..6c72b592315b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -222,7 +222,8 @@ static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
 }
 
 static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter,
-				     void *context)
+				     void *context,
+				     struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_err_ctx *err_ctx = context;
@@ -301,7 +302,8 @@ static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq,
 }
 
 static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
-				      struct devlink_fmsg *fmsg)
+				      struct devlink_fmsg *fmsg,
+				      struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_params *params = &priv->channels.params;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index bfed558637c2..b468549e96ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -135,7 +135,8 @@ static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx)
 }
 
 static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter,
-				     void *context)
+				     void *context,
+				     struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_err_ctx *err_ctx = context;
@@ -205,7 +206,8 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg,
 }
 
 static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter,
-				      struct devlink_fmsg *fmsg)
+				      struct devlink_fmsg *fmsg,
+				      struct netlink_ext_ack *extack)
 {
 	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_txqsq *generic_sq = priv->txq2sq[0];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 745ab6cd7c30..784b1e26f414 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -77,8 +77,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   struct neighbour **out_n,
 				   u8 *out_ttl)
 {
+	struct neighbour *n;
 	struct rtable *rt;
-	struct neighbour *n = NULL;
 
 #if IS_ENABLED(CONFIG_INET)
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -138,10 +138,9 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 				   struct neighbour **out_n,
 				   u8 *out_ttl)
 {
-	struct neighbour *n = NULL;
 	struct dst_entry *dst;
+	struct neighbour *n;
 
-#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
 	int ret;
 
 	ret = ipv6_stub->ipv6_dst_lookup(dev_net(mirred_dev), NULL, &dst,
@@ -157,9 +156,6 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 		dst_release(dst);
 		return ret;
 	}
-#else
-	return -EOPNOTSUPP;
-#endif
 
 	n = dst_neigh_lookup(dst, &fl6->daddr);
 	dst_release(dst);
@@ -212,8 +208,8 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
 	struct net_device *out_dev, *route_dev;
-	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
+	struct neighbour *n;
 	int ipv4_encap_size;
 	char *encap_header;
 	u8 nud_state, ttl;
@@ -240,13 +236,13 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
 			       ipv4_encap_size, max_encap_size);
 		err = -EOPNOTSUPP;
-		goto out;
+		goto release_neigh;
 	}
 
 	encap_header = kzalloc(ipv4_encap_size, GFP_KERNEL);
 	if (!encap_header) {
 		err = -ENOMEM;
-		goto out;
+		goto release_neigh;
 	}
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
@@ -298,7 +294,7 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 		/* the encap entry will be made valid on neigh update event
 		 * and not used before that.
 		 */
-		goto out;
+		goto release_neigh;
 	}
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
 						     e->reformat_type,
@@ -318,9 +314,8 @@ destroy_neigh_entry:
 	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
 free_encap:
 	kfree(encap_header);
-out:
-	if (n)
-		neigh_release(n);
+release_neigh:
+	neigh_release(n);
 	return err;
 }
 
@@ -331,9 +326,9 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 	int max_encap_size = MLX5_CAP_ESW(priv->mdev, max_encap_header_size);
 	const struct ip_tunnel_key *tun_key = &e->tun_info->key;
 	struct net_device *out_dev, *route_dev;
-	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
 	struct ipv6hdr *ip6h;
+	struct neighbour *n;
 	int ipv6_encap_size;
 	char *encap_header;
 	u8 nud_state, ttl;
@@ -359,13 +354,13 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
 			       ipv6_encap_size, max_encap_size);
 		err = -EOPNOTSUPP;
-		goto out;
+		goto release_neigh;
 	}
 
 	encap_header = kzalloc(ipv6_encap_size, GFP_KERNEL);
 	if (!encap_header) {
 		err = -ENOMEM;
-		goto out;
+		goto release_neigh;
 	}
 
 	/* used by mlx5e_detach_encap to lookup a neigh hash table
@@ -416,7 +411,7 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 		/* the encap entry will be made valid on neigh update event
 		 * and not used before that.
 		 */
-		goto out;
+		goto release_neigh;
 	}
 
 	e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev,
@@ -437,9 +432,8 @@ destroy_neigh_entry:
 	mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e);
 free_encap:
 	kfree(encap_header);
-out:
-	if (n)
-		neigh_release(n);
+release_neigh:
+	neigh_release(n);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index c362b9225dc2..6f9a78c85ffd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -58,9 +58,16 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv,
 				    struct net_device *mirred_dev,
 				    struct mlx5e_encap_entry *e);
 
+#if IS_ENABLED(CONFIG_INET) && IS_ENABLED(CONFIG_IPV6)
 int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
 				    struct net_device *mirred_dev,
 				    struct mlx5e_encap_entry *e);
+#else
+static inline int
+mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv,
+				struct net_device *mirred_dev,
+				struct mlx5e_encap_entry *e) { return -EOPNOTSUPP; }
+#endif
 
 bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 				    struct net_device *netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2a56e66f58d8..09ed7f5f688b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -63,6 +63,7 @@
 #include "en/xsk/rx.h"
 #include "en/xsk/tx.h"
 #include "en/hv_vhca_stats.h"
+#include "lib/mlx5.h"
 
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
@@ -408,12 +409,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 		rq->stats = &c->priv->channel_stats[c->ix].rq;
 	INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work);
 
-	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
-	if (IS_ERR(rq->xdp_prog)) {
-		err = PTR_ERR(rq->xdp_prog);
-		rq->xdp_prog = NULL;
-		goto err_rq_wq_destroy;
-	}
+	if (params->xdp_prog)
+		bpf_prog_inc(params->xdp_prog);
+	rq->xdp_prog = params->xdp_prog;
 
 	rq_xdp_ix = rq->ix;
 	if (xsk)
@@ -4409,16 +4407,11 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	/* no need for full reset when exchanging programs */
 	reset = (!priv->channels.params.xdp_prog || !prog);
 
-	if (was_opened && !reset) {
+	if (was_opened && !reset)
 		/* num_channels is invariant here, so we can take the
 		 * batched reference right upfront.
 		 */
-		prog = bpf_prog_add(prog, priv->channels.num);
-		if (IS_ERR(prog)) {
-			err = PTR_ERR(prog);
-			goto unlock;
-		}
-	}
+		bpf_prog_add(prog, priv->channels.num);
 
 	if (was_opened && reset) {
 		struct mlx5e_channels new_channels = {};
@@ -5430,6 +5423,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 		return NULL;
 	}
 
+	dev_net_set(netdev, mlx5_core_net(mdev));
 	priv = netdev_priv(netdev);
 
 	err = mlx5e_attach(mdev, priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index cd9bb7c7b341..f175cb24bb67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -47,6 +47,7 @@
 #include "en/tc_tun.h"
 #include "fs_core.h"
 #include "lib/port_tun.h"
+#include "lib/mlx5.h"
 #define CREATE_TRACE_POINTS
 #include "diag/en_rep_tracepoint.h"
 
@@ -1243,21 +1244,60 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static LIST_HEAD(mlx5e_rep_block_cb_list);
+static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
+				 void *cb_priv)
+{
+	struct flow_cls_offload *f = type_data;
+	struct flow_cls_offload cls_flower;
+	struct mlx5e_priv *priv = cb_priv;
+	struct mlx5_eswitch *esw;
+	unsigned long flags;
+	int err;
+
+	flags = MLX5_TC_FLAG(INGRESS) |
+		MLX5_TC_FLAG(ESW_OFFLOAD) |
+		MLX5_TC_FLAG(FT_OFFLOAD);
+	esw = priv->mdev->priv.eswitch;
 
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		if (!mlx5_eswitch_prios_supported(esw) || f->common.chain_index)
+			return -EOPNOTSUPP;
+
+		/* Re-use tc offload path by moving the ft flow to the
+		 * reserved ft chain.
+		 */
+		memcpy(&cls_flower, f, sizeof(*f));
+		cls_flower.common.chain_index = FDB_FT_CHAIN;
+		err = mlx5e_rep_setup_tc_cls_flower(priv, &cls_flower, flags);
+		memcpy(&f->stats, &cls_flower.stats, sizeof(f->stats));
+		return err;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static LIST_HEAD(mlx5e_rep_block_tc_cb_list);
+static LIST_HEAD(mlx5e_rep_block_ft_cb_list);
 static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct flow_block_offload *f = type_data;
 
+	f->unlocked_driver_cb = true;
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		f->unlocked_driver_cb = true;
 		return flow_block_cb_setup_simple(type_data,
-						  &mlx5e_rep_block_cb_list,
+						  &mlx5e_rep_block_tc_cb_list,
 						  mlx5e_rep_setup_tc_cb,
 						  priv, priv, true);
+	case TC_SETUP_FT:
+		return flow_block_cb_setup_simple(type_data,
+						  &mlx5e_rep_block_ft_cb_list,
+						  mlx5e_rep_setup_ft_cb,
+						  priv, priv, true);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1877,6 +1917,7 @@ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		return -EINVAL;
 	}
 
+	dev_net_set(netdev, mlx5_core_net(dev));
 	rpriv->netdev = netdev;
 	rep->rep_data[REP_ETH].priv = rpriv;
 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 82cffb3a9964..9e9960146e5b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1386,6 +1386,9 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state)))
 		return 0;
 
+	if (rq->page_pool)
+		page_pool_nid_changed(rq->page_pool, numa_mem_id());
+
 	if (rq->cqd.left) {
 		work_done += mlx5e_decompress_cqes_cont(rq, cqwq, 0, budget);
 		if (rq->cqd.left || work_done >= budget)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index f90a9f8e0fc6..0d5d84b5fa23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -74,6 +74,7 @@ enum {
 	MLX5E_TC_FLOW_FLAG_INGRESS	= MLX5E_TC_FLAG_INGRESS_BIT,
 	MLX5E_TC_FLOW_FLAG_EGRESS	= MLX5E_TC_FLAG_EGRESS_BIT,
 	MLX5E_TC_FLOW_FLAG_ESWITCH	= MLX5E_TC_FLAG_ESW_OFFLOAD_BIT,
+	MLX5E_TC_FLOW_FLAG_FT		= MLX5E_TC_FLAG_FT_OFFLOAD_BIT,
 	MLX5E_TC_FLOW_FLAG_NIC		= MLX5E_TC_FLAG_NIC_OFFLOAD_BIT,
 	MLX5E_TC_FLOW_FLAG_OFFLOADED	= MLX5E_TC_FLOW_BASE,
 	MLX5E_TC_FLOW_FLAG_HAIRPIN	= MLX5E_TC_FLOW_BASE + 1,
@@ -276,6 +277,11 @@ static bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow)
 	return flow_flag_test(flow, ESWITCH);
 }
 
+static bool mlx5e_is_ft_flow(struct mlx5e_tc_flow *flow)
+{
+	return flow_flag_test(flow, FT);
+}
+
 static bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow)
 {
 	return flow_flag_test(flow, OFFLOADED);
@@ -1074,7 +1080,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw,
 	memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr));
 	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	slow_attr->split_count = 0;
-	slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN;
+	slow_attr->dest_chain = FDB_TC_SLOW_PATH_CHAIN;
 
 	rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr);
 	if (!IS_ERR(rule))
@@ -1091,7 +1097,7 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw,
 	memcpy(slow_attr, flow->esw_attr, sizeof(*slow_attr));
 	slow_attr->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	slow_attr->split_count = 0;
-	slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN;
+	slow_attr->dest_chain = FDB_TC_SLOW_PATH_CHAIN;
 	mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr);
 	flow_flag_clear(flow, SLOW);
 }
@@ -1168,7 +1174,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 		return -EOPNOTSUPP;
 	}
 
-	if (attr->chain > max_chain) {
+	/* We check chain range only for tc flows.
+	 * For ft flows, we checked attr->chain was originally 0 and set it to
+	 * FDB_FT_CHAIN which is outside tc range.
+	 * See mlx5e_rep_setup_ft_cb().
+	 */
+	if (!mlx5e_is_ft_flow(flow) && attr->chain > max_chain) {
 		NL_SET_ERR_MSG(extack, "Requested chain is out of supported range");
 		return -EOPNOTSUPP;
 	}
@@ -2241,13 +2252,14 @@ out_err:
 
 struct mlx5_fields {
 	u8  field;
-	u8  size;
+	u8  field_bsize;
+	u32 field_mask;
 	u32 offset;
 	u32 match_offset;
 };
 
-#define OFFLOAD(fw_field, size, field, off, match_field) \
-		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, size, \
+#define OFFLOAD(fw_field, field_bsize, field_mask, field, off, match_field) \
+		{MLX5_ACTION_IN_FIELD_OUT_ ## fw_field, field_bsize, field_mask, \
 		 offsetof(struct pedit_headers, field) + (off), \
 		 MLX5_BYTE_OFF(fte_match_set_lyr_2_4, match_field)}
 
@@ -2265,18 +2277,18 @@ struct mlx5_fields {
 })
 
 static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp,
-			 void *matchmaskp, int size)
+			 void *matchmaskp, u8 bsize)
 {
 	bool same = false;
 
-	switch (size) {
-	case sizeof(u8):
+	switch (bsize) {
+	case 8:
 		same = SAME_VAL_MASK(u8, valp, maskp, matchvalp, matchmaskp);
 		break;
-	case sizeof(u16):
+	case 16:
 		same = SAME_VAL_MASK(u16, valp, maskp, matchvalp, matchmaskp);
 		break;
-	case sizeof(u32):
+	case 32:
 		same = SAME_VAL_MASK(u32, valp, maskp, matchvalp, matchmaskp);
 		break;
 	}
@@ -2285,41 +2297,43 @@ static bool cmp_val_mask(void *valp, void *maskp, void *matchvalp,
 }
 
 static struct mlx5_fields fields[] = {
-	OFFLOAD(DMAC_47_16, 4, eth.h_dest[0], 0, dmac_47_16),
-	OFFLOAD(DMAC_15_0,  2, eth.h_dest[4], 0, dmac_15_0),
-	OFFLOAD(SMAC_47_16, 4, eth.h_source[0], 0, smac_47_16),
-	OFFLOAD(SMAC_15_0,  2, eth.h_source[4], 0, smac_15_0),
-	OFFLOAD(ETHERTYPE,  2, eth.h_proto, 0, ethertype),
-	OFFLOAD(FIRST_VID,  2, vlan.h_vlan_TCI, 0, first_vid),
-
-	OFFLOAD(IP_TTL, 1, ip4.ttl,   0, ttl_hoplimit),
-	OFFLOAD(SIPV4,  4, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4),
-	OFFLOAD(DIPV4,  4, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
-
-	OFFLOAD(SIPV6_127_96, 4, ip6.saddr.s6_addr32[0], 0,
+	OFFLOAD(DMAC_47_16, 32, U32_MAX, eth.h_dest[0], 0, dmac_47_16),
+	OFFLOAD(DMAC_15_0,  16, U16_MAX, eth.h_dest[4], 0, dmac_15_0),
+	OFFLOAD(SMAC_47_16, 32, U32_MAX, eth.h_source[0], 0, smac_47_16),
+	OFFLOAD(SMAC_15_0,  16, U16_MAX, eth.h_source[4], 0, smac_15_0),
+	OFFLOAD(ETHERTYPE,  16, U16_MAX, eth.h_proto, 0, ethertype),
+	OFFLOAD(FIRST_VID,  16, U16_MAX, vlan.h_vlan_TCI, 0, first_vid),
+
+	OFFLOAD(IP_DSCP, 8,    0xfc, ip4.tos,   0, ip_dscp),
+	OFFLOAD(IP_TTL,  8,  U8_MAX, ip4.ttl,   0, ttl_hoplimit),
+	OFFLOAD(SIPV4,  32, U32_MAX, ip4.saddr, 0, src_ipv4_src_ipv6.ipv4_layout.ipv4),
+	OFFLOAD(DIPV4,  32, U32_MAX, ip4.daddr, 0, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+
+	OFFLOAD(SIPV6_127_96, 32, U32_MAX, ip6.saddr.s6_addr32[0], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[0]),
-	OFFLOAD(SIPV6_95_64,  4, ip6.saddr.s6_addr32[1], 0,
+	OFFLOAD(SIPV6_95_64,  32, U32_MAX, ip6.saddr.s6_addr32[1], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[4]),
-	OFFLOAD(SIPV6_63_32,  4, ip6.saddr.s6_addr32[2], 0,
+	OFFLOAD(SIPV6_63_32,  32, U32_MAX, ip6.saddr.s6_addr32[2], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[8]),
-	OFFLOAD(SIPV6_31_0,   4, ip6.saddr.s6_addr32[3], 0,
+	OFFLOAD(SIPV6_31_0,   32, U32_MAX, ip6.saddr.s6_addr32[3], 0,
 		src_ipv4_src_ipv6.ipv6_layout.ipv6[12]),
-	OFFLOAD(DIPV6_127_96, 4, ip6.daddr.s6_addr32[0], 0,
+	OFFLOAD(DIPV6_127_96, 32, U32_MAX, ip6.daddr.s6_addr32[0], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[0]),
-	OFFLOAD(DIPV6_95_64,  4, ip6.daddr.s6_addr32[1], 0,
+	OFFLOAD(DIPV6_95_64,  32, U32_MAX, ip6.daddr.s6_addr32[1], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[4]),
-	OFFLOAD(DIPV6_63_32,  4, ip6.daddr.s6_addr32[2], 0,
+	OFFLOAD(DIPV6_63_32,  32, U32_MAX, ip6.daddr.s6_addr32[2], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[8]),
-	OFFLOAD(DIPV6_31_0,   4, ip6.daddr.s6_addr32[3], 0,
+	OFFLOAD(DIPV6_31_0,   32, U32_MAX, ip6.daddr.s6_addr32[3], 0,
 		dst_ipv4_dst_ipv6.ipv6_layout.ipv6[12]),
-	OFFLOAD(IPV6_HOPLIMIT, 1, ip6.hop_limit, 0, ttl_hoplimit),
+	OFFLOAD(IPV6_HOPLIMIT, 8,  U8_MAX, ip6.hop_limit, 0, ttl_hoplimit),
 
-	OFFLOAD(TCP_SPORT, 2, tcp.source,  0, tcp_sport),
-	OFFLOAD(TCP_DPORT, 2, tcp.dest,    0, tcp_dport),
-	OFFLOAD(TCP_FLAGS, 1, tcp.ack_seq, 5, tcp_flags),
+	OFFLOAD(TCP_SPORT, 16, U16_MAX, tcp.source,  0, tcp_sport),
+	OFFLOAD(TCP_DPORT, 16, U16_MAX, tcp.dest,    0, tcp_dport),
+	/* in linux iphdr tcp_flags is 8 bits long */
+	OFFLOAD(TCP_FLAGS,  8,  U8_MAX, tcp.ack_seq, 5, tcp_flags),
 
-	OFFLOAD(UDP_SPORT, 2, udp.source, 0, udp_sport),
-	OFFLOAD(UDP_DPORT, 2, udp.dest,   0, udp_dport),
+	OFFLOAD(UDP_SPORT, 16, U16_MAX, udp.source, 0, udp_sport),
+	OFFLOAD(UDP_DPORT, 16, U16_MAX, udp.dest,   0, udp_dport),
 };
 
 /* On input attr->max_mod_hdr_actions tells how many HW actions can be parsed at
@@ -2332,19 +2346,17 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 				struct netlink_ext_ack *extack)
 {
 	struct pedit_headers *set_masks, *add_masks, *set_vals, *add_vals;
-	void *headers_c = get_match_headers_criteria(*action_flags,
-						     &parse_attr->spec);
-	void *headers_v = get_match_headers_value(*action_flags,
-						  &parse_attr->spec);
 	int i, action_size, nactions, max_actions, first, last, next_z;
-	void *s_masks_p, *a_masks_p, *vals_p;
+	void *headers_c, *headers_v, *action, *vals_p;
+	u32 *s_masks_p, *a_masks_p, s_mask, a_mask;
 	struct mlx5_fields *f;
-	u8 cmd, field_bsize;
-	u32 s_mask, a_mask;
 	unsigned long mask;
 	__be32 mask_be32;
 	__be16 mask_be16;
-	void *action;
+	u8 cmd;
+
+	headers_c = get_match_headers_criteria(*action_flags, &parse_attr->spec);
+	headers_v = get_match_headers_value(*action_flags, &parse_attr->spec);
 
 	set_masks = &hdrs[0].masks;
 	add_masks = &hdrs[1].masks;
@@ -2369,8 +2381,8 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 		s_masks_p = (void *)set_masks + f->offset;
 		a_masks_p = (void *)add_masks + f->offset;
 
-		memcpy(&s_mask, s_masks_p, f->size);
-		memcpy(&a_mask, a_masks_p, f->size);
+		s_mask = *s_masks_p & f->field_mask;
+		a_mask = *a_masks_p & f->field_mask;
 
 		if (!s_mask && !a_mask) /* nothing to offload here */
 			continue;
@@ -2399,38 +2411,34 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 			vals_p = (void *)set_vals + f->offset;
 			/* don't rewrite if we have a match on the same value */
 			if (cmp_val_mask(vals_p, s_masks_p, match_val,
-					 match_mask, f->size))
+					 match_mask, f->field_bsize))
 				skip = true;
 			/* clear to denote we consumed this field */
-			memset(s_masks_p, 0, f->size);
+			*s_masks_p &= ~f->field_mask;
 		} else {
-			u32 zero = 0;
-
 			cmd  = MLX5_ACTION_TYPE_ADD;
 			mask = a_mask;
 			vals_p = (void *)add_vals + f->offset;
 			/* add 0 is no change */
-			if (!memcmp(vals_p, &zero, f->size))
+			if ((*(u32 *)vals_p & f->field_mask) == 0)
 				skip = true;
 			/* clear to denote we consumed this field */
-			memset(a_masks_p, 0, f->size);
+			*a_masks_p &= ~f->field_mask;
 		}
 		if (skip)
 			continue;
 
-		field_bsize = f->size * BITS_PER_BYTE;
-
-		if (field_bsize == 32) {
+		if (f->field_bsize == 32) {
 			mask_be32 = *(__be32 *)&mask;
 			mask = (__force unsigned long)cpu_to_le32(be32_to_cpu(mask_be32));
-		} else if (field_bsize == 16) {
+		} else if (f->field_bsize == 16) {
 			mask_be16 = *(__be16 *)&mask;
 			mask = (__force unsigned long)cpu_to_le16(be16_to_cpu(mask_be16));
 		}
 
-		first = find_first_bit(&mask, field_bsize);
-		next_z = find_next_zero_bit(&mask, field_bsize, first);
-		last  = find_last_bit(&mask, field_bsize);
+		first = find_first_bit(&mask, f->field_bsize);
+		next_z = find_next_zero_bit(&mask, f->field_bsize, first);
+		last  = find_last_bit(&mask, f->field_bsize);
 		if (first < next_z && next_z < last) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "rewrite of few sub-fields isn't supported");
@@ -2443,16 +2451,22 @@ static int offload_pedit_fields(struct pedit_headers_action *hdrs,
 		MLX5_SET(set_action_in, action, field, f->field);
 
 		if (cmd == MLX5_ACTION_TYPE_SET) {
-			MLX5_SET(set_action_in, action, offset, first);
+			int start;
+
+			/* if field is bit sized it can start not from first bit */
+			start = find_first_bit((unsigned long *)&f->field_mask,
+					       f->field_bsize);
+
+			MLX5_SET(set_action_in, action, offset, first - start);
 			/* length is num of bits to be written, zero means length of 32 */
 			MLX5_SET(set_action_in, action, length, (last - first + 1));
 		}
 
-		if (field_bsize == 32)
+		if (f->field_bsize == 32)
 			MLX5_SET(set_action_in, action, data, ntohl(*(__be32 *)vals_p) >> first);
-		else if (field_bsize == 16)
+		else if (f->field_bsize == 16)
 			MLX5_SET(set_action_in, action, data, ntohs(*(__be16 *)vals_p) >> first);
-		else if (field_bsize == 8)
+		else if (f->field_bsize == 8)
 			MLX5_SET(set_action_in, action, data, *(u8 *)vals_p >> first);
 
 		action += action_size;
@@ -3214,6 +3228,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 	struct mlx5e_tc_flow_parse_attr *parse_attr = attr->parse_attr;
 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
 	const struct ip_tunnel_info *info = NULL;
+	bool ft_flow = mlx5e_is_ft_flow(flow);
 	const struct flow_action_entry *act;
 	bool encap = false;
 	u32 action = 0;
@@ -3258,6 +3273,14 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 				return -EINVAL;
 			}
 
+			if (ft_flow && out_dev == priv->netdev) {
+				/* Ignore forward to self rules generated
+				 * by adding both mlx5 devs to the flow table
+				 * block on a normal nft offload setup.
+				 */
+				return -EOPNOTSUPP;
+			}
+
 			if (attr->out_count >= MLX5_MAX_FLOW_FWD_VPORTS) {
 				NL_SET_ERR_MSG_MOD(extack,
 						   "can't support more output ports, can't offload forwarding");
@@ -3382,6 +3405,10 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			u32 dest_chain = act->chain_index;
 			u32 max_chain = mlx5_eswitch_get_chain_range(esw);
 
+			if (ft_flow) {
+				NL_SET_ERR_MSG_MOD(extack, "Goto action is not supported");
+				return -EOPNOTSUPP;
+			}
 			if (dest_chain <= attr->chain) {
 				NL_SET_ERR_MSG(extack, "Goto earlier chain isn't supported");
 				return -EOPNOTSUPP;
@@ -3443,6 +3470,12 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 		attr->action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	}
 
+	if (!(attr->action &
+	      (MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_DROP))) {
+		NL_SET_ERR_MSG(extack, "Rule must have at least one forward/drop action");
+		return -EOPNOTSUPP;
+	}
+
 	if (attr->split_count > 0 && !mlx5_esw_has_fwd_fdb(priv->mdev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "current firmware doesn't support split rule for port mirroring");
@@ -3466,6 +3499,8 @@ static void get_flags(int flags, unsigned long *flow_flags)
 		__flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_ESWITCH);
 	if (flags & MLX5_TC_FLAG(NIC_OFFLOAD))
 		__flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_NIC);
+	if (flags & MLX5_TC_FLAG(FT_OFFLOAD))
+		__flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_FT);
 
 	*flow_flags = __flow_flags;
 }
@@ -3841,7 +3876,7 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 	int err;
 
 	rcu_read_lock();
-	flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params);
+	flow = rhashtable_lookup(tc_ht, &f->cookie, tc_ht_params);
 	if (!flow || !same_flow_direction(flow, flags)) {
 		err = -EINVAL;
 		goto errout;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 924c6ef86a14..262cdb7b69b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -44,7 +44,8 @@ enum {
 	MLX5E_TC_FLAG_EGRESS_BIT,
 	MLX5E_TC_FLAG_NIC_OFFLOAD_BIT,
 	MLX5E_TC_FLAG_ESW_OFFLOAD_BIT,
-	MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT,
+	MLX5E_TC_FLAG_FT_OFFLOAD_BIT,
+	MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_FT_OFFLOAD_BIT,
 };
 
 #define MLX5_TC_FLAG(flag) BIT(MLX5E_TC_FLAG_##flag##_BIT)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 67dc4f0921b6..66951ff975f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -461,8 +461,14 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 		if (unlikely(get_cqe_opcode(cqe) == MLX5_CQE_REQ_ERR)) {
 			if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING,
 					      &sq->state)) {
+				struct mlx5e_tx_wqe_info *wi;
+				u16 ci;
+
+				ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+				wi = &sq->db.wqe_info[ci];
 				mlx5e_dump_error_cqe(sq,
 						     (struct mlx5_err_cqe *)cqe);
+				mlx5_wq_cyc_wqe_dump(&sq->wq, ci, wi->num_wqebbs);
 				queue_work(cq->channel->priv->wq,
 					   &sq->recover_work);
 			}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 60fddf8afc99..2c965ad0d744 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -111,42 +111,32 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport,
 }
 
 /* E-Switch vport context HW commands */
-static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
-					void *in, int inlen)
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
+					  bool other_vport,
+					  void *in, int inlen)
 {
 	u32 out[MLX5_ST_SZ_DW(modify_esw_vport_context_out)] = {0};
 
 	MLX5_SET(modify_esw_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_MODIFY_ESW_VPORT_CONTEXT);
 	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
-	MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_esw_vport_context_in, in, other_vport, other_vport);
 	return mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
 }
 
-int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
-					  void *in, int inlen)
-{
-	return modify_esw_vport_context_cmd(esw->dev, vport, in, inlen);
-}
-
-static int query_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 vport,
-				       void *out, int outlen)
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
+					 bool other_vport,
+					 void *out, int outlen)
 {
 	u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {};
 
 	MLX5_SET(query_esw_vport_context_in, in, opcode,
 		 MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT);
 	MLX5_SET(modify_esw_vport_context_in, in, vport_number, vport);
-	MLX5_SET(modify_esw_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_esw_vport_context_in, in, other_vport, other_vport);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 
-int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
-					 void *out, int outlen)
-{
-	return query_esw_vport_context_cmd(esw->dev, vport, out, outlen);
-}
-
 static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 				  u16 vlan, u8 qos, u8 set_flags)
 {
@@ -179,7 +169,8 @@ static int modify_esw_vport_cvlan(struct mlx5_core_dev *dev, u16 vport,
 	MLX5_SET(modify_esw_vport_context_in, in,
 		 field_select.vport_cvlan_insert, 1);
 
-	return modify_esw_vport_context_cmd(dev, vport, in, sizeof(in));
+	return mlx5_eswitch_modify_esw_vport_context(dev, vport, true,
+						     in, sizeof(in));
 }
 
 /* E-Switch FDB */
@@ -452,6 +443,13 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw)
 	return err;
 }
 
+static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
+{
+	esw_cleanup_vepa_rules(esw);
+	esw_destroy_legacy_fdb_table(esw);
+	esw_destroy_legacy_vepa_table(esw);
+}
+
 #define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \
 					MLX5_VPORT_MC_ADDR_CHANGE | \
 					MLX5_VPORT_PROMISC_CHANGE)
@@ -464,15 +462,10 @@ static int esw_legacy_enable(struct mlx5_eswitch *esw)
 	if (ret)
 		return ret;
 
-	mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
-	return 0;
-}
-
-static void esw_destroy_legacy_table(struct mlx5_eswitch *esw)
-{
-	esw_cleanup_vepa_rules(esw);
-	esw_destroy_legacy_fdb_table(esw);
-	esw_destroy_legacy_vepa_table(esw);
+	ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS);
+	if (ret)
+		esw_destroy_legacy_table(esw);
+	return ret;
 }
 
 static void esw_legacy_disable(struct mlx5_eswitch *esw)
@@ -501,7 +494,7 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	/* Skip mlx5_mpfs_add_mac for eswitch_managers,
 	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (esw->manager_vport == vport)
+	if (mlx5_esw_is_manager_vport(esw, vport))
 		goto fdb_add;
 
 	err = mlx5_mpfs_add_mac(esw->dev, mac);
@@ -530,10 +523,10 @@ static int esw_del_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 	u16 vport = vaddr->vport;
 	int err = 0;
 
-	/* Skip mlx5_mpfs_del_mac for eswitch managerss,
+	/* Skip mlx5_mpfs_del_mac for eswitch managers,
 	 * it is already done by its netdev in mlx5e_execute_l2_action
 	 */
-	if (!vaddr->mpfs || esw->manager_vport == vport)
+	if (!vaddr->mpfs || mlx5_esw_is_manager_vport(esw, vport))
 		goto fdb_del;
 
 	err = mlx5_mpfs_del_mac(esw->dev, mac);
@@ -1040,14 +1033,15 @@ out:
 void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
 				    struct mlx5_vport *vport)
 {
-	if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan))
+	if (!IS_ERR_OR_NULL(vport->egress.allowed_vlan)) {
 		mlx5_del_flow_rules(vport->egress.allowed_vlan);
+		vport->egress.allowed_vlan = NULL;
+	}
 
-	if (!IS_ERR_OR_NULL(vport->egress.drop_rule))
-		mlx5_del_flow_rules(vport->egress.drop_rule);
-
-	vport->egress.allowed_vlan = NULL;
-	vport->egress.drop_rule = NULL;
+	if (!IS_ERR_OR_NULL(vport->egress.legacy.drop_rule)) {
+		mlx5_del_flow_rules(vport->egress.legacy.drop_rule);
+		vport->egress.legacy.drop_rule = NULL;
+	}
 }
 
 void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
@@ -1067,57 +1061,21 @@ void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
 	vport->egress.acl = NULL;
 }
 
-int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
-				 struct mlx5_vport *vport)
+static int
+esw_vport_create_legacy_ingress_acl_groups(struct mlx5_eswitch *esw,
+					   struct mlx5_vport *vport)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_core_dev *dev = esw->dev;
-	struct mlx5_flow_namespace *root_ns;
-	struct mlx5_flow_table *acl;
 	struct mlx5_flow_group *g;
 	void *match_criteria;
 	u32 *flow_group_in;
-	/* The ingress acl table contains 4 groups
-	 * (2 active rules at the same time -
-	 *      1 allow rule from one of the first 3 groups.
-	 *      1 drop rule from the last group):
-	 * 1)Allow untagged traffic with smac=original mac.
-	 * 2)Allow untagged traffic.
-	 * 3)Allow traffic with smac=original mac.
-	 * 4)Drop all other traffic.
-	 */
-	int table_size = 4;
-	int err = 0;
-
-	if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
-		return -EOPNOTSUPP;
-
-	if (!IS_ERR_OR_NULL(vport->ingress.acl))
-		return 0;
-
-	esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n",
-		  vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
-
-	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
-			mlx5_eswitch_vport_num_to_index(esw, vport->vport));
-	if (!root_ns) {
-		esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n", vport->vport);
-		return -EOPNOTSUPP;
-	}
+	int err;
 
 	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
-	if (IS_ERR(acl)) {
-		err = PTR_ERR(acl);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress flow Table, err(%d)\n",
-			 vport->vport, err);
-		goto out;
-	}
-	vport->ingress.acl = acl;
-
 	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
 
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
@@ -1127,14 +1085,14 @@ int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
 
-	g = mlx5_create_flow_group(acl, flow_group_in);
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
 	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged spoofchk flow group, err(%d)\n",
+		esw_warn(dev, "vport[%d] ingress create untagged spoofchk flow group, err(%d)\n",
 			 vport->vport, err);
-		goto out;
+		goto spoof_err;
 	}
-	vport->ingress.allow_untagged_spoofchk_grp = g;
+	vport->ingress.legacy.allow_untagged_spoofchk_grp = g;
 
 	memset(flow_group_in, 0, inlen);
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
@@ -1142,14 +1100,14 @@ int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 1);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 1);
 
-	g = mlx5_create_flow_group(acl, flow_group_in);
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
 	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress untagged flow group, err(%d)\n",
+		esw_warn(dev, "vport[%d] ingress create untagged flow group, err(%d)\n",
 			 vport->vport, err);
-		goto out;
+		goto untagged_err;
 	}
-	vport->ingress.allow_untagged_only_grp = g;
+	vport->ingress.legacy.allow_untagged_only_grp = g;
 
 	memset(flow_group_in, 0, inlen);
 	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable, MLX5_MATCH_OUTER_HEADERS);
@@ -1158,108 +1116,178 @@ int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 2);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 2);
 
-	g = mlx5_create_flow_group(acl, flow_group_in);
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
 	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress spoofchk flow group, err(%d)\n",
+		esw_warn(dev, "vport[%d] ingress create spoofchk flow group, err(%d)\n",
 			 vport->vport, err);
-		goto out;
+		goto allow_spoof_err;
 	}
-	vport->ingress.allow_spoofchk_only_grp = g;
+	vport->ingress.legacy.allow_spoofchk_only_grp = g;
 
 	memset(flow_group_in, 0, inlen);
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 3);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 3);
 
-	g = mlx5_create_flow_group(acl, flow_group_in);
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
 	if (IS_ERR(g)) {
 		err = PTR_ERR(g);
-		esw_warn(dev, "Failed to create E-Switch vport[%d] ingress drop flow group, err(%d)\n",
+		esw_warn(dev, "vport[%d] ingress create drop flow group, err(%d)\n",
 			 vport->vport, err);
-		goto out;
+		goto drop_err;
 	}
-	vport->ingress.drop_grp = g;
+	vport->ingress.legacy.drop_grp = g;
+	kvfree(flow_group_in);
+	return 0;
 
-out:
-	if (err) {
-		if (!IS_ERR_OR_NULL(vport->ingress.allow_spoofchk_only_grp))
-			mlx5_destroy_flow_group(
-					vport->ingress.allow_spoofchk_only_grp);
-		if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_only_grp))
-			mlx5_destroy_flow_group(
-					vport->ingress.allow_untagged_only_grp);
-		if (!IS_ERR_OR_NULL(vport->ingress.allow_untagged_spoofchk_grp))
-			mlx5_destroy_flow_group(
-				vport->ingress.allow_untagged_spoofchk_grp);
-		if (!IS_ERR_OR_NULL(vport->ingress.acl))
-			mlx5_destroy_flow_table(vport->ingress.acl);
+drop_err:
+	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_spoofchk_only_grp)) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp);
+		vport->ingress.legacy.allow_spoofchk_only_grp = NULL;
 	}
-
+allow_spoof_err:
+	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_only_grp)) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp);
+		vport->ingress.legacy.allow_untagged_only_grp = NULL;
+	}
+untagged_err:
+	if (!IS_ERR_OR_NULL(vport->ingress.legacy.allow_untagged_spoofchk_grp)) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp);
+		vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL;
+	}
+spoof_err:
 	kvfree(flow_group_in);
 	return err;
 }
 
+int esw_vport_create_ingress_acl_table(struct mlx5_eswitch *esw,
+				       struct mlx5_vport *vport, int table_size)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_namespace *root_ns;
+	struct mlx5_flow_table *acl;
+	int vport_index;
+	int err;
+
+	if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
+		return -EOPNOTSUPP;
+
+	esw_debug(dev, "Create vport[%d] ingress ACL log_max_size(%d)\n",
+		  vport->vport, MLX5_CAP_ESW_INGRESS_ACL(dev, log_max_ft_size));
+
+	vport_index = mlx5_eswitch_vport_num_to_index(esw, vport->vport);
+	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+						    vport_index);
+	if (!root_ns) {
+		esw_warn(dev, "Failed to get E-Switch ingress flow namespace for vport (%d)\n",
+			 vport->vport);
+		return -EOPNOTSUPP;
+	}
+
+	acl = mlx5_create_vport_flow_table(root_ns, 0, table_size, 0, vport->vport);
+	if (IS_ERR(acl)) {
+		err = PTR_ERR(acl);
+		esw_warn(dev, "vport[%d] ingress create flow Table, err(%d)\n",
+			 vport->vport, err);
+		return err;
+	}
+	vport->ingress.acl = acl;
+	return 0;
+}
+
+void esw_vport_destroy_ingress_acl_table(struct mlx5_vport *vport)
+{
+	if (!vport->ingress.acl)
+		return;
+
+	mlx5_destroy_flow_table(vport->ingress.acl);
+	vport->ingress.acl = NULL;
+}
+
 void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
 				     struct mlx5_vport *vport)
 {
-	if (!IS_ERR_OR_NULL(vport->ingress.drop_rule))
-		mlx5_del_flow_rules(vport->ingress.drop_rule);
+	if (vport->ingress.legacy.drop_rule) {
+		mlx5_del_flow_rules(vport->ingress.legacy.drop_rule);
+		vport->ingress.legacy.drop_rule = NULL;
+	}
 
-	if (!IS_ERR_OR_NULL(vport->ingress.allow_rule))
+	if (vport->ingress.allow_rule) {
 		mlx5_del_flow_rules(vport->ingress.allow_rule);
-
-	vport->ingress.drop_rule = NULL;
-	vport->ingress.allow_rule = NULL;
-
-	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
+		vport->ingress.allow_rule = NULL;
+	}
 }
 
-void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
-				   struct mlx5_vport *vport)
+static void esw_vport_disable_legacy_ingress_acl(struct mlx5_eswitch *esw,
+						 struct mlx5_vport *vport)
 {
-	if (IS_ERR_OR_NULL(vport->ingress.acl))
+	if (!vport->ingress.acl)
 		return;
 
 	esw_debug(esw->dev, "Destroy vport[%d] E-Switch ingress ACL\n", vport->vport);
 
 	esw_vport_cleanup_ingress_rules(esw, vport);
-	mlx5_destroy_flow_group(vport->ingress.allow_spoofchk_only_grp);
-	mlx5_destroy_flow_group(vport->ingress.allow_untagged_only_grp);
-	mlx5_destroy_flow_group(vport->ingress.allow_untagged_spoofchk_grp);
-	mlx5_destroy_flow_group(vport->ingress.drop_grp);
-	mlx5_destroy_flow_table(vport->ingress.acl);
-	vport->ingress.acl = NULL;
-	vport->ingress.drop_grp = NULL;
-	vport->ingress.allow_spoofchk_only_grp = NULL;
-	vport->ingress.allow_untagged_only_grp = NULL;
-	vport->ingress.allow_untagged_spoofchk_grp = NULL;
+	if (vport->ingress.legacy.allow_spoofchk_only_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_spoofchk_only_grp);
+		vport->ingress.legacy.allow_spoofchk_only_grp = NULL;
+	}
+	if (vport->ingress.legacy.allow_untagged_only_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_only_grp);
+		vport->ingress.legacy.allow_untagged_only_grp = NULL;
+	}
+	if (vport->ingress.legacy.allow_untagged_spoofchk_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.allow_untagged_spoofchk_grp);
+		vport->ingress.legacy.allow_untagged_spoofchk_grp = NULL;
+	}
+	if (vport->ingress.legacy.drop_grp) {
+		mlx5_destroy_flow_group(vport->ingress.legacy.drop_grp);
+		vport->ingress.legacy.drop_grp = NULL;
+	}
+	esw_vport_destroy_ingress_acl_table(vport);
 }
 
 static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 				    struct mlx5_vport *vport)
 {
-	struct mlx5_fc *counter = vport->ingress.drop_counter;
+	struct mlx5_fc *counter = vport->ingress.legacy.drop_counter;
 	struct mlx5_flow_destination drop_ctr_dst = {0};
 	struct mlx5_flow_destination *dst = NULL;
 	struct mlx5_flow_act flow_act = {0};
-	struct mlx5_flow_spec *spec;
+	struct mlx5_flow_spec *spec = NULL;
 	int dest_num = 0;
 	int err = 0;
 	u8 *smac_v;
 
+	/* The ingress acl table contains 4 groups
+	 * (2 active rules at the same time -
+	 *      1 allow rule from one of the first 3 groups.
+	 *      1 drop rule from the last group):
+	 * 1)Allow untagged traffic with smac=original mac.
+	 * 2)Allow untagged traffic.
+	 * 3)Allow traffic with smac=original mac.
+	 * 4)Drop all other traffic.
+	 */
+	int table_size = 4;
+
 	esw_vport_cleanup_ingress_rules(esw, vport);
 
 	if (!vport->info.vlan && !vport->info.qos && !vport->info.spoofchk) {
-		esw_vport_disable_ingress_acl(esw, vport);
+		esw_vport_disable_legacy_ingress_acl(esw, vport);
 		return 0;
 	}
 
-	err = esw_vport_enable_ingress_acl(esw, vport);
-	if (err) {
-		mlx5_core_warn(esw->dev,
-			       "failed to enable ingress acl (%d) on vport[%d]\n",
-			       err, vport->vport);
-		return err;
+	if (!vport->ingress.acl) {
+		err = esw_vport_create_ingress_acl_table(esw, vport, table_size);
+		if (err) {
+			esw_warn(esw->dev,
+				 "vport[%d] enable ingress acl err (%d)\n",
+				 err, vport->vport);
+			return err;
+		}
+
+		err = esw_vport_create_legacy_ingress_acl_groups(esw, vport);
+		if (err)
+			goto out;
 	}
 
 	esw_debug(esw->dev,
@@ -1309,21 +1337,59 @@ static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
 		dst = &drop_ctr_dst;
 		dest_num++;
 	}
-	vport->ingress.drop_rule =
+	vport->ingress.legacy.drop_rule =
 		mlx5_add_flow_rules(vport->ingress.acl, spec,
 				    &flow_act, dst, dest_num);
-	if (IS_ERR(vport->ingress.drop_rule)) {
-		err = PTR_ERR(vport->ingress.drop_rule);
+	if (IS_ERR(vport->ingress.legacy.drop_rule)) {
+		err = PTR_ERR(vport->ingress.legacy.drop_rule);
 		esw_warn(esw->dev,
 			 "vport[%d] configure ingress drop rule, err(%d)\n",
 			 vport->vport, err);
-		vport->ingress.drop_rule = NULL;
+		vport->ingress.legacy.drop_rule = NULL;
 		goto out;
 	}
+	kvfree(spec);
+	return 0;
 
 out:
-	if (err)
-		esw_vport_cleanup_ingress_rules(esw, vport);
+	esw_vport_disable_legacy_ingress_acl(esw, vport);
+	kvfree(spec);
+	return err;
+}
+
+int mlx5_esw_create_vport_egress_acl_vlan(struct mlx5_eswitch *esw,
+					  struct mlx5_vport *vport,
+					  u16 vlan_id, u32 flow_action)
+{
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	if (vport->egress.allowed_vlan)
+		return -EEXIST;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
+	MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vlan_id);
+
+	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
+	flow_act.action = flow_action;
+	vport->egress.allowed_vlan =
+		mlx5_add_flow_rules(vport->egress.acl, spec,
+				    &flow_act, NULL, 0);
+	if (IS_ERR(vport->egress.allowed_vlan)) {
+		err = PTR_ERR(vport->egress.allowed_vlan);
+		esw_warn(esw->dev,
+			 "vport[%d] configure egress vlan rule failed, err(%d)\n",
+			 vport->vport, err);
+		vport->egress.allowed_vlan = NULL;
+	}
+
 	kvfree(spec);
 	return err;
 }
@@ -1331,7 +1397,7 @@ out:
 static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 				   struct mlx5_vport *vport)
 {
-	struct mlx5_fc *counter = vport->egress.drop_counter;
+	struct mlx5_fc *counter = vport->egress.legacy.drop_counter;
 	struct mlx5_flow_destination drop_ctr_dst = {0};
 	struct mlx5_flow_destination *dst = NULL;
 	struct mlx5_flow_act flow_act = {0};
@@ -1358,34 +1424,17 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 		  "vport[%d] configure egress rules, vlan(%d) qos(%d)\n",
 		  vport->vport, vport->info.vlan, vport->info.qos);
 
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec) {
-		err = -ENOMEM;
-		goto out;
-	}
-
 	/* Allowed vlan rule */
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
-	MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, vport->info.vlan);
+	err = mlx5_esw_create_vport_egress_acl_vlan(esw, vport, vport->info.vlan,
+						    MLX5_FLOW_CONTEXT_ACTION_ALLOW);
+	if (err)
+		return err;
 
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-	vport->egress.allowed_vlan =
-		mlx5_add_flow_rules(vport->egress.acl, spec,
-				    &flow_act, NULL, 0);
-	if (IS_ERR(vport->egress.allowed_vlan)) {
-		err = PTR_ERR(vport->egress.allowed_vlan);
-		esw_warn(esw->dev,
-			 "vport[%d] configure egress allowed vlan rule failed, err(%d)\n",
-			 vport->vport, err);
-		vport->egress.allowed_vlan = NULL;
+	/* Drop others rule (star rule) */
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
 		goto out;
-	}
 
-	/* Drop others rule (star rule) */
-	memset(spec, 0, sizeof(*spec));
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP;
 
 	/* Attach egress drop flow counter */
@@ -1396,15 +1445,15 @@ static int esw_vport_egress_config(struct mlx5_eswitch *esw,
 		dst = &drop_ctr_dst;
 		dest_num++;
 	}
-	vport->egress.drop_rule =
+	vport->egress.legacy.drop_rule =
 		mlx5_add_flow_rules(vport->egress.acl, spec,
 				    &flow_act, dst, dest_num);
-	if (IS_ERR(vport->egress.drop_rule)) {
-		err = PTR_ERR(vport->egress.drop_rule);
+	if (IS_ERR(vport->egress.legacy.drop_rule)) {
+		err = PTR_ERR(vport->egress.legacy.drop_rule);
 		esw_warn(esw->dev,
 			 "vport[%d] configure egress drop rule failed, err(%d)\n",
 			 vport->vport, err);
-		vport->egress.drop_rule = NULL;
+		vport->egress.legacy.drop_rule = NULL;
 	}
 out:
 	kvfree(spec);
@@ -1619,7 +1668,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 	u16 vport_num = vport->vport;
 	int flags;
 
-	if (esw->manager_vport == vport_num)
+	if (mlx5_esw_is_manager_vport(esw, vport_num))
 		return;
 
 	mlx5_modify_vport_admin_state(esw->dev,
@@ -1639,66 +1688,112 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 		SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
 	modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos,
 			       flags);
-
-	/* Only legacy mode needs ACLs */
-	if (esw->mode == MLX5_ESWITCH_LEGACY) {
-		esw_vport_ingress_config(esw, vport);
-		esw_vport_egress_config(esw, vport);
-	}
 }
 
-static void esw_vport_create_drop_counters(struct mlx5_vport *vport)
+static int esw_vport_create_legacy_acl_tables(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport)
 {
-	struct mlx5_core_dev *dev = vport->dev;
+	int ret;
 
-	if (MLX5_CAP_ESW_INGRESS_ACL(dev, flow_counter)) {
-		vport->ingress.drop_counter = mlx5_fc_create(dev, false);
-		if (IS_ERR(vport->ingress.drop_counter)) {
-			esw_warn(dev,
+	/* Only non manager vports need ACL in legacy mode */
+	if (mlx5_esw_is_manager_vport(esw, vport->vport))
+		return 0;
+
+	if (!mlx5_esw_is_manager_vport(esw, vport->vport) &&
+	    MLX5_CAP_ESW_INGRESS_ACL(esw->dev, flow_counter)) {
+		vport->ingress.legacy.drop_counter = mlx5_fc_create(esw->dev, false);
+		if (IS_ERR(vport->ingress.legacy.drop_counter)) {
+			esw_warn(esw->dev,
 				 "vport[%d] configure ingress drop rule counter failed\n",
 				 vport->vport);
-			vport->ingress.drop_counter = NULL;
+			vport->ingress.legacy.drop_counter = NULL;
 		}
 	}
 
-	if (MLX5_CAP_ESW_EGRESS_ACL(dev, flow_counter)) {
-		vport->egress.drop_counter = mlx5_fc_create(dev, false);
-		if (IS_ERR(vport->egress.drop_counter)) {
-			esw_warn(dev,
+	ret = esw_vport_ingress_config(esw, vport);
+	if (ret)
+		goto ingress_err;
+
+	if (!mlx5_esw_is_manager_vport(esw, vport->vport) &&
+	    MLX5_CAP_ESW_EGRESS_ACL(esw->dev, flow_counter)) {
+		vport->egress.legacy.drop_counter = mlx5_fc_create(esw->dev, false);
+		if (IS_ERR(vport->egress.legacy.drop_counter)) {
+			esw_warn(esw->dev,
 				 "vport[%d] configure egress drop rule counter failed\n",
 				 vport->vport);
-			vport->egress.drop_counter = NULL;
+			vport->egress.legacy.drop_counter = NULL;
 		}
 	}
+
+	ret = esw_vport_egress_config(esw, vport);
+	if (ret)
+		goto egress_err;
+
+	return 0;
+
+egress_err:
+	esw_vport_disable_legacy_ingress_acl(esw, vport);
+	mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter);
+	vport->egress.legacy.drop_counter = NULL;
+
+ingress_err:
+	mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
+	vport->ingress.legacy.drop_counter = NULL;
+	return ret;
 }
 
-static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport)
+static int esw_vport_setup_acl(struct mlx5_eswitch *esw,
+			       struct mlx5_vport *vport)
 {
-	struct mlx5_core_dev *dev = vport->dev;
+	if (esw->mode == MLX5_ESWITCH_LEGACY)
+		return esw_vport_create_legacy_acl_tables(esw, vport);
+	else
+		return esw_vport_create_offloads_acl_tables(esw, vport);
+}
+
+static void esw_vport_destroy_legacy_acl_tables(struct mlx5_eswitch *esw,
+						struct mlx5_vport *vport)
 
-	if (vport->ingress.drop_counter)
-		mlx5_fc_destroy(dev, vport->ingress.drop_counter);
-	if (vport->egress.drop_counter)
-		mlx5_fc_destroy(dev, vport->egress.drop_counter);
+{
+	if (mlx5_esw_is_manager_vport(esw, vport->vport))
+		return;
+
+	esw_vport_disable_egress_acl(esw, vport);
+	mlx5_fc_destroy(esw->dev, vport->egress.legacy.drop_counter);
+	vport->egress.legacy.drop_counter = NULL;
+
+	esw_vport_disable_legacy_ingress_acl(esw, vport);
+	mlx5_fc_destroy(esw->dev, vport->ingress.legacy.drop_counter);
+	vport->ingress.legacy.drop_counter = NULL;
 }
 
-static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
-			     enum mlx5_eswitch_vport_event enabled_events)
+static void esw_vport_cleanup_acl(struct mlx5_eswitch *esw,
+				  struct mlx5_vport *vport)
+{
+	if (esw->mode == MLX5_ESWITCH_LEGACY)
+		esw_vport_destroy_legacy_acl_tables(esw, vport);
+	else
+		esw_vport_destroy_offloads_acl_tables(esw, vport);
+}
+
+static int esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
+			    enum mlx5_eswitch_vport_event enabled_events)
 {
 	u16 vport_num = vport->vport;
+	int ret;
 
 	mutex_lock(&esw->state_lock);
 	WARN_ON(vport->enabled);
 
 	esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
 
-	/* Create steering drop counters for ingress and egress ACLs */
-	if (vport_num && esw->mode == MLX5_ESWITCH_LEGACY)
-		esw_vport_create_drop_counters(vport);
-
 	/* Restore old vport configuration */
 	esw_apply_vport_conf(esw, vport);
 
+	ret = esw_vport_setup_acl(esw, vport);
+	if (ret)
+		goto done;
+
 	/* Attach vport to the eswitch rate limiter */
 	if (esw_vport_enable_qos(esw, vport, vport->info.max_rate,
 				 vport->qos.bw_share))
@@ -1711,7 +1806,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 	/* Esw manager is trusted by default. Host PF (vport 0) is trusted as well
 	 * in smartNIC as it's a vport group manager.
 	 */
-	if (esw->manager_vport == vport_num ||
+	if (mlx5_esw_is_manager_vport(esw, vport_num) ||
 	    (!vport_num && mlx5_core_is_ecpf(esw->dev)))
 		vport->info.trusted = true;
 
@@ -1719,7 +1814,9 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 
 	esw->enabled_vports++;
 	esw_debug(esw->dev, "Enabled VPORT(%d)\n", vport_num);
+done:
 	mutex_unlock(&esw->state_lock);
+	return ret;
 }
 
 static void esw_disable_vport(struct mlx5_eswitch *esw,
@@ -1727,18 +1824,16 @@ static void esw_disable_vport(struct mlx5_eswitch *esw,
 {
 	u16 vport_num = vport->vport;
 
+	mutex_lock(&esw->state_lock);
 	if (!vport->enabled)
-		return;
+		goto done;
 
 	esw_debug(esw->dev, "Disabling vport(%d)\n", vport_num);
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	/* Wait for current already scheduled events to complete */
-	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */
 	arm_vport_context_events_cmd(esw->dev, vport->vport, 0);
-	mutex_lock(&esw->state_lock);
 	/* We don't assume VFs will cleanup after themselves.
 	 * Calling vport change handler while vport is disabled will cleanup
 	 * the vport resources.
@@ -1746,17 +1841,18 @@ static void esw_disable_vport(struct mlx5_eswitch *esw,
 	esw_vport_change_handle_locked(vport);
 	vport->enabled_events = 0;
 	esw_vport_disable_qos(esw, vport);
-	if (esw->manager_vport != vport_num &&
-	    esw->mode == MLX5_ESWITCH_LEGACY) {
+
+	if (!mlx5_esw_is_manager_vport(esw, vport->vport) &&
+	    esw->mode == MLX5_ESWITCH_LEGACY)
 		mlx5_modify_vport_admin_state(esw->dev,
 					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					      vport_num, 1,
 					      MLX5_VPORT_ADMIN_STATE_DOWN);
-		esw_vport_disable_egress_acl(esw, vport);
-		esw_vport_disable_ingress_acl(esw, vport);
-		esw_vport_destroy_drop_counters(vport);
-	}
+
+	esw_vport_cleanup_acl(esw, vport);
 	esw->enabled_vports--;
+
+done:
 	mutex_unlock(&esw->state_lock);
 }
 
@@ -1770,12 +1866,8 @@ static int eswitch_vport_event(struct notifier_block *nb,
 
 	vport_num = be16_to_cpu(eqe->data.vport_change.vport_num);
 	vport = mlx5_eswitch_get_vport(esw, vport_num);
-	if (IS_ERR(vport))
-		return NOTIFY_OK;
-
-	if (vport->enabled)
+	if (!IS_ERR(vport))
 		queue_work(esw->work_queue, &vport->vport_change_handler);
-
 	return NOTIFY_OK;
 }
 
@@ -1831,32 +1923,66 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
 	flush_workqueue(esw->work_queue);
 }
 
+static void mlx5_eswitch_clear_vf_vports_info(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	int i;
+
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
+		memset(&vport->info, 0, sizeof(vport->info));
+}
+
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
 /* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs
  * whichever are present on the eswitch.
  */
-void
+int
 mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 				 enum mlx5_eswitch_vport_event enabled_events)
 {
 	struct mlx5_vport *vport;
+	int num_vfs;
+	int ret;
 	int i;
 
 	/* Enable PF vport */
 	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
-	esw_enable_vport(esw, vport, enabled_events);
+	ret = esw_enable_vport(esw, vport, enabled_events);
+	if (ret)
+		return ret;
 
-	/* Enable ECPF vports */
+	/* Enable ECPF vport */
 	if (mlx5_ecpf_vport_exists(esw->dev)) {
 		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
-		esw_enable_vport(esw, vport, enabled_events);
+		ret = esw_enable_vport(esw, vport, enabled_events);
+		if (ret)
+			goto ecpf_err;
 	}
 
 	/* Enable VF vports */
-	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
-		esw_enable_vport(esw, vport, enabled_events);
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) {
+		ret = esw_enable_vport(esw, vport, enabled_events);
+		if (ret)
+			goto vf_err;
+	}
+	return 0;
+
+vf_err:
+	num_vfs = i - 1;
+	mlx5_esw_for_each_vf_vport_reverse(esw, i, vport, num_vfs)
+		esw_disable_vport(esw, vport);
+
+	if (mlx5_ecpf_vport_exists(esw->dev)) {
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF);
+		esw_disable_vport(esw, vport);
+	}
+
+ecpf_err:
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
+	esw_disable_vport(esw, vport);
+	return ret;
 }
 
 /* mlx5_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs
@@ -1923,7 +2049,7 @@ abort:
 	return err;
 }
 
-void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf)
 {
 	int old_mode;
 
@@ -1952,6 +2078,8 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 	}
+	if (clear_vf)
+		mlx5_eswitch_clear_vf_vports_info(esw);
 }
 
 int mlx5_eswitch_init(struct mlx5_core_dev *dev)
@@ -2474,12 +2602,12 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
 	if (!vport->enabled || esw->mode != MLX5_ESWITCH_LEGACY)
 		return 0;
 
-	if (vport->egress.drop_counter)
-		mlx5_fc_query(dev, vport->egress.drop_counter,
+	if (vport->egress.legacy.drop_counter)
+		mlx5_fc_query(dev, vport->egress.legacy.drop_counter,
 			      &stats->rx_dropped, &bytes);
 
-	if (vport->ingress.drop_counter)
-		mlx5_fc_query(dev, vport->ingress.drop_counter,
+	if (vport->ingress.legacy.drop_counter)
+		mlx5_fc_query(dev, vport->ingress.legacy.drop_counter,
 			      &stats->tx_dropped, &bytes);
 
 	if (!MLX5_CAP_GEN(dev, receive_discard_vport_down) &&
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index 6bd6f5895244..962888a7c3c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -43,6 +43,16 @@
 #include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
 
+#define FDB_TC_MAX_CHAIN 3
+#define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1)
+#define FDB_TC_SLOW_PATH_CHAIN (FDB_FT_CHAIN + 1)
+
+/* The index of the last real chain (FT) + 1 as chain zero is valid as well */
+#define FDB_NUM_CHAINS (FDB_FT_CHAIN + 1)
+
+#define FDB_TC_MAX_PRIO 16
+#define FDB_TC_LEVELS_PER_PRIO 2
+
 #ifdef CONFIG_MLX5_ESWITCH
 
 #define MLX5_MAX_UC_PER_VPORT(dev) \
@@ -59,21 +69,22 @@
 #define mlx5_esw_has_fwd_fdb(dev) \
 	MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table)
 
-#define FDB_MAX_CHAIN 3
-#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1)
-#define FDB_MAX_PRIO 16
-
 struct vport_ingress {
 	struct mlx5_flow_table *acl;
-	struct mlx5_flow_group *allow_untagged_spoofchk_grp;
-	struct mlx5_flow_group *allow_spoofchk_only_grp;
-	struct mlx5_flow_group *allow_untagged_only_grp;
-	struct mlx5_flow_group *drop_grp;
-	struct mlx5_modify_hdr   *modify_metadata;
-	struct mlx5_flow_handle  *modify_metadata_rule;
-	struct mlx5_flow_handle  *allow_rule;
-	struct mlx5_flow_handle  *drop_rule;
-	struct mlx5_fc           *drop_counter;
+	struct mlx5_flow_handle *allow_rule;
+	struct {
+		struct mlx5_flow_group *allow_spoofchk_only_grp;
+		struct mlx5_flow_group *allow_untagged_spoofchk_grp;
+		struct mlx5_flow_group *allow_untagged_only_grp;
+		struct mlx5_flow_group *drop_grp;
+		struct mlx5_flow_handle *drop_rule;
+		struct mlx5_fc *drop_counter;
+	} legacy;
+	struct {
+		struct mlx5_flow_group *metadata_grp;
+		struct mlx5_modify_hdr *modify_metadata;
+		struct mlx5_flow_handle *modify_metadata_rule;
+	} offloads;
 };
 
 struct vport_egress {
@@ -81,8 +92,10 @@ struct vport_egress {
 	struct mlx5_flow_group *allowed_vlans_grp;
 	struct mlx5_flow_group *drop_grp;
 	struct mlx5_flow_handle  *allowed_vlan;
-	struct mlx5_flow_handle  *drop_rule;
-	struct mlx5_fc           *drop_counter;
+	struct {
+		struct mlx5_flow_handle *drop_rule;
+		struct mlx5_fc *drop_counter;
+	} legacy;
 };
 
 struct mlx5_vport_drop_stats {
@@ -139,7 +152,6 @@ enum offloads_fdb_flags {
 
 extern const unsigned int ESW_POOLS[4];
 
-#define PRIO_LEVELS 2
 struct mlx5_eswitch_fdb {
 	union {
 		struct legacy_fdb {
@@ -166,7 +178,7 @@ struct mlx5_eswitch_fdb {
 			struct {
 				struct mlx5_flow_table *fdb;
 				u32 num_rules;
-			} fdb_prio[FDB_MAX_CHAIN + 1][FDB_MAX_PRIO + 1][PRIO_LEVELS];
+			} fdb_prio[FDB_NUM_CHAINS][FDB_TC_MAX_PRIO + 1][FDB_TC_LEVELS_PER_PRIO];
 			/* Protects fdb_prio table */
 			struct mutex fdb_prio_lock;
 
@@ -217,8 +229,8 @@ enum {
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
 	struct mlx5_nb          nb;
-	/* legacy data structures */
 	struct mlx5_eswitch_fdb fdb_table;
+	/* legacy data structures */
 	struct hlist_head       mc_table[MLX5_L2_ADDR_HASH_SIZE];
 	struct esw_mc_addr mc_promisc;
 	/* end of legacy */
@@ -251,18 +263,16 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw);
 int esw_offloads_init_reps(struct mlx5_eswitch *esw);
 void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
 				     struct mlx5_vport *vport);
-int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
-				 struct mlx5_vport *vport);
+int esw_vport_create_ingress_acl_table(struct mlx5_eswitch *esw,
+				       struct mlx5_vport *vport,
+				       int table_size);
+void esw_vport_destroy_ingress_acl_table(struct mlx5_vport *vport);
 void esw_vport_cleanup_egress_rules(struct mlx5_eswitch *esw,
 				    struct mlx5_vport *vport);
 int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 				struct mlx5_vport *vport);
 void esw_vport_disable_egress_acl(struct mlx5_eswitch *esw,
 				  struct mlx5_vport *vport);
-void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
-				   struct mlx5_vport *vport);
-void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
-					       struct mlx5_vport *vport);
 int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 			       u32 rate_mbps);
 
@@ -270,7 +280,7 @@ int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num,
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
 int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode);
-void mlx5_eswitch_disable(struct mlx5_eswitch *esw);
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf);
 int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 			       u16 vport, u8 mac[ETH_ALEN]);
 int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
@@ -292,9 +302,11 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw,
 				 struct ifla_vf_stats *vf_stats);
 void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule);
 
-int mlx5_eswitch_modify_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+int mlx5_eswitch_modify_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
+					  bool other_vport,
 					  void *in, int inlen);
-int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_core_dev *dev, u16 vport,
+					 bool other_vport,
 					 void *out, int outlen);
 
 struct mlx5_flow_spec;
@@ -421,6 +433,10 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  u16 vport, u16 vlan, u8 qos, u8 set_flags);
 
+int mlx5_esw_create_vport_egress_acl_vlan(struct mlx5_eswitch *esw,
+					  struct mlx5_vport *vport,
+					  u16 vlan_id, u32 flow_action);
+
 static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
 						       u8 vlan_depth)
 {
@@ -459,6 +475,12 @@ static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
 		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
 }
 
+static inline bool
+mlx5_esw_is_manager_vport(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return esw->manager_vport == vport_num;
+}
+
 static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev)
 {
 	return mlx5_core_is_ecpf_esw_manager(dev) ?
@@ -593,17 +615,24 @@ bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num);
 void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs);
 int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data);
 
-void
+int
 mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw,
 				 enum mlx5_eswitch_vport_event enabled_events);
 void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw);
 
+int
+esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
+				     struct mlx5_vport *vport);
+void
+esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
+				      struct mlx5_vport *vport);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
 static inline void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) {}
 static inline int  mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) { return 0; }
-static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw) {}
+static inline void mlx5_eswitch_disable(struct mlx5_eswitch *esw, bool clear_vf) {}
 static inline bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1) { return true; }
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev) { return false; }
 static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
@@ -613,10 +642,6 @@ static inline const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev)
 
 static inline void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs) {}
 
-#define FDB_MAX_CHAIN 1
-#define FDB_SLOW_PATH_CHAIN (FDB_MAX_CHAIN + 1)
-#define FDB_MAX_PRIO 1
-
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 9004a07e457a..8ba59a21a163 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -75,7 +75,7 @@ bool mlx5_eswitch_prios_supported(struct mlx5_eswitch *esw)
 u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw)
 {
 	if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
-		return FDB_MAX_CHAIN;
+		return FDB_TC_MAX_CHAIN;
 
 	return 0;
 }
@@ -83,7 +83,7 @@ u32 mlx5_eswitch_get_chain_range(struct mlx5_eswitch *esw)
 u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw)
 {
 	if (esw->fdb_table.flags & ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED)
-		return FDB_MAX_PRIO;
+		return FDB_TC_MAX_PRIO;
 
 	return 1;
 }
@@ -599,7 +599,7 @@ static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable)
 	if (!mlx5_eswitch_vport_match_metadata_enabled(esw))
 		return 0;
 
-	err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+	err = mlx5_eswitch_query_esw_vport_context(esw->dev, 0, false,
 						   out, sizeof(out));
 	if (err)
 		return err;
@@ -618,7 +618,7 @@ static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable)
 	MLX5_SET(modify_esw_vport_context_in, in,
 		 field_select.fdb_to_vport_reg_c_id, 1);
 
-	return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport,
+	return mlx5_eswitch_modify_esw_vport_context(esw->dev, 0, false,
 						     in, sizeof(in));
 }
 
@@ -927,7 +927,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
 	int table_prio, l = 0;
 	u32 flags = 0;
 
-	if (chain == FDB_SLOW_PATH_CHAIN)
+	if (chain == FDB_TC_SLOW_PATH_CHAIN)
 		return esw->fdb_table.offloads.slow_fdb;
 
 	mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);
@@ -952,7 +952,7 @@ esw_get_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
 		flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 			  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	table_prio = (chain * FDB_MAX_PRIO) + prio - 1;
+	table_prio = prio - 1;
 
 	/* create earlier levels for correct fs_core lookup when
 	 * connecting tables
@@ -989,7 +989,7 @@ esw_put_prio_table(struct mlx5_eswitch *esw, u32 chain, u16 prio, int level)
 {
 	int l;
 
-	if (chain == FDB_SLOW_PATH_CHAIN)
+	if (chain == FDB_TC_SLOW_PATH_CHAIN)
 		return;
 
 	mutex_lock(&esw->fdb_table.offloads.fdb_prio_lock);
@@ -1369,7 +1369,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable(esw);
+	mlx5_eswitch_disable(esw, false);
 	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {
@@ -1777,9 +1777,9 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
 	flow_act.vlan[0].vid = 0;
 	flow_act.vlan[0].prio = 0;
 
-	if (vport->ingress.modify_metadata_rule) {
+	if (vport->ingress.offloads.modify_metadata_rule) {
 		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
-		flow_act.modify_hdr = vport->ingress.modify_metadata;
+		flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
 	}
 
 	vport->ingress.allow_rule =
@@ -1815,11 +1815,11 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 	MLX5_SET(set_action_in, action, data,
 		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));
 
-	vport->ingress.modify_metadata =
+	vport->ingress.offloads.modify_metadata =
 		mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
 					 1, action);
-	if (IS_ERR(vport->ingress.modify_metadata)) {
-		err = PTR_ERR(vport->ingress.modify_metadata);
+	if (IS_ERR(vport->ingress.offloads.modify_metadata)) {
+		err = PTR_ERR(vport->ingress.offloads.modify_metadata);
 		esw_warn(esw->dev,
 			 "failed to alloc modify header for vport %d ingress acl (%d)\n",
 			 vport->vport, err);
@@ -1827,100 +1827,76 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
 	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-	flow_act.modify_hdr = vport->ingress.modify_metadata;
-	vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl,
-								  &spec, &flow_act, NULL, 0);
-	if (IS_ERR(vport->ingress.modify_metadata_rule)) {
-		err = PTR_ERR(vport->ingress.modify_metadata_rule);
+	flow_act.modify_hdr = vport->ingress.offloads.modify_metadata;
+	vport->ingress.offloads.modify_metadata_rule =
+				mlx5_add_flow_rules(vport->ingress.acl,
+						    &spec, &flow_act, NULL, 0);
+	if (IS_ERR(vport->ingress.offloads.modify_metadata_rule)) {
+		err = PTR_ERR(vport->ingress.offloads.modify_metadata_rule);
 		esw_warn(esw->dev,
 			 "failed to add setting metadata rule for vport %d ingress acl, err(%d)\n",
 			 vport->vport, err);
-		vport->ingress.modify_metadata_rule = NULL;
+		vport->ingress.offloads.modify_metadata_rule = NULL;
 		goto out;
 	}
 
 out:
 	if (err)
-		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata);
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);
 	return err;
 }
 
-void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
-					       struct mlx5_vport *vport)
+static void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+						      struct mlx5_vport *vport)
 {
-	if (vport->ingress.modify_metadata_rule) {
-		mlx5_del_flow_rules(vport->ingress.modify_metadata_rule);
-		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata);
+	if (vport->ingress.offloads.modify_metadata_rule) {
+		mlx5_del_flow_rules(vport->ingress.offloads.modify_metadata_rule);
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.offloads.modify_metadata);
 
-		vport->ingress.modify_metadata_rule = NULL;
+		vport->ingress.offloads.modify_metadata_rule = NULL;
 	}
 }
 
-static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
-					    struct mlx5_vport *vport)
+static int esw_vport_create_ingress_acl_group(struct mlx5_eswitch *esw,
+					      struct mlx5_vport *vport)
 {
-	struct mlx5_flow_act flow_act = {0};
-	struct mlx5_flow_spec *spec;
-	int err = 0;
-
-	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
-		return 0;
-
-	/* For prio tag mode, there is only 1 FTEs:
-	 * 1) prio tag packets - pop the prio tag VLAN, allow
-	 * Unmatched traffic is allowed by default
-	 */
-
-	esw_vport_cleanup_egress_rules(esw, vport);
-
-	err = esw_vport_enable_egress_acl(esw, vport);
-	if (err) {
-		mlx5_core_warn(esw->dev,
-			       "failed to enable egress acl (%d) on vport[%d]\n",
-			       err, vport->vport);
-		return err;
-	}
-
-	esw_debug(esw->dev,
-		  "vport[%d] configure prio tag egress rules\n", vport->vport);
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_group *g;
+	u32 *flow_group_in;
+	int ret = 0;
 
-	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
-	if (!spec) {
-		err = -ENOMEM;
-		goto out_no_mem;
-	}
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
 
-	/* prio tag vlan rule - pop it so VF receives untagged packets */
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_value, outer_headers.cvlan_tag);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, outer_headers.first_vid);
-	MLX5_SET(fte_match_param, spec->match_value, outer_headers.first_vid, 0);
+	memset(flow_group_in, 0, inlen);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
 
-	spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS;
-	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
-			  MLX5_FLOW_CONTEXT_ACTION_ALLOW;
-	vport->egress.allowed_vlan =
-		mlx5_add_flow_rules(vport->egress.acl, spec,
-				    &flow_act, NULL, 0);
-	if (IS_ERR(vport->egress.allowed_vlan)) {
-		err = PTR_ERR(vport->egress.allowed_vlan);
+	g = mlx5_create_flow_group(vport->ingress.acl, flow_group_in);
+	if (IS_ERR(g)) {
+		ret = PTR_ERR(g);
 		esw_warn(esw->dev,
-			 "vport[%d] configure egress pop prio tag vlan rule failed, err(%d)\n",
-			 vport->vport, err);
-		vport->egress.allowed_vlan = NULL;
-		goto out;
+			 "Failed to create vport[%d] ingress metadata group, err(%d)\n",
+			 vport->vport, ret);
+		goto grp_err;
 	}
+	vport->ingress.offloads.metadata_grp = g;
+grp_err:
+	kvfree(flow_group_in);
+	return ret;
+}
 
-out:
-	kvfree(spec);
-out_no_mem:
-	if (err)
-		esw_vport_cleanup_egress_rules(esw, vport);
-	return err;
+static void esw_vport_destroy_ingress_acl_group(struct mlx5_vport *vport)
+{
+	if (vport->ingress.offloads.metadata_grp) {
+		mlx5_destroy_flow_group(vport->ingress.offloads.metadata_grp);
+		vport->ingress.offloads.metadata_grp = NULL;
+	}
 }
 
-static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
-					   struct mlx5_vport *vport)
+static int esw_vport_ingress_config(struct mlx5_eswitch *esw,
+				    struct mlx5_vport *vport)
 {
 	int err;
 
@@ -1929,8 +1905,7 @@ static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
 		return 0;
 
 	esw_vport_cleanup_ingress_rules(esw, vport);
-
-	err = esw_vport_enable_ingress_acl(esw, vport);
+	err = esw_vport_create_ingress_acl_table(esw, vport, 1);
 	if (err) {
 		esw_warn(esw->dev,
 			 "failed to enable ingress acl (%d) on vport[%d]\n",
@@ -1938,25 +1913,65 @@ static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
 		return err;
 	}
 
+	err = esw_vport_create_ingress_acl_group(esw, vport);
+	if (err)
+		goto group_err;
+
 	esw_debug(esw->dev,
 		  "vport[%d] configure ingress rules\n", vport->vport);
 
 	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
 		err = esw_vport_add_ingress_acl_modify_metadata(esw, vport);
 		if (err)
-			goto out;
+			goto metadata_err;
 	}
 
 	if (MLX5_CAP_GEN(esw->dev, prio_tag_required) &&
 	    mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
 		err = esw_vport_ingress_prio_tag_config(esw, vport);
 		if (err)
-			goto out;
+			goto prio_tag_err;
 	}
+	return 0;
 
-out:
+prio_tag_err:
+	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
+metadata_err:
+	esw_vport_cleanup_ingress_rules(esw, vport);
+	esw_vport_destroy_ingress_acl_group(vport);
+group_err:
+	esw_vport_destroy_ingress_acl_table(vport);
+	return err;
+}
+
+static int esw_vport_egress_config(struct mlx5_eswitch *esw,
+				   struct mlx5_vport *vport)
+{
+	int err;
+
+	if (!MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		return 0;
+
+	esw_vport_cleanup_egress_rules(esw, vport);
+
+	err = esw_vport_enable_egress_acl(esw, vport);
+	if (err)
+		return err;
+
+	/* For prio tag mode, there is only 1 FTEs:
+	 * 1) prio tag packets - pop the prio tag VLAN, allow
+	 * Unmatched traffic is allowed by default
+	 */
+	esw_debug(esw->dev,
+		  "vport[%d] configure prio tag egress rules\n", vport->vport);
+
+	/* prio tag vlan rule - pop it so VF receives untagged packets */
+	err = mlx5_esw_create_vport_egress_acl_vlan(esw, vport, 0,
+						    MLX5_FLOW_CONTEXT_ACTION_VLAN_POP |
+						    MLX5_FLOW_CONTEXT_ACTION_ALLOW);
 	if (err)
-		esw_vport_disable_ingress_acl(esw, vport);
+		esw_vport_disable_egress_acl(esw, vport);
+
 	return err;
 }
 
@@ -1980,54 +1995,59 @@ esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
 	return true;
 }
 
-static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
+int
+esw_vport_create_offloads_acl_tables(struct mlx5_eswitch *esw,
+				     struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport;
-	int i, j;
 	int err;
 
-	if (esw_check_vport_match_metadata_supported(esw))
-		esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
-
-	mlx5_esw_for_all_vports(esw, i, vport) {
-		err = esw_vport_ingress_common_config(esw, vport);
-		if (err)
-			goto err_ingress;
+	err = esw_vport_ingress_config(esw, vport);
+	if (err)
+		return err;
 
-		if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
-			err = esw_vport_egress_prio_tag_config(esw, vport);
-			if (err)
-				goto err_egress;
+	if (mlx5_eswitch_is_vf_vport(esw, vport->vport)) {
+		err = esw_vport_egress_config(esw, vport);
+		if (err) {
+			esw_vport_del_ingress_acl_modify_metadata(esw, vport);
+			esw_vport_cleanup_ingress_rules(esw, vport);
+			esw_vport_destroy_ingress_acl_table(vport);
 		}
 	}
+	return err;
+}
 
-	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
-		esw_info(esw->dev, "Use metadata reg_c as source vport to match\n");
+void
+esw_vport_destroy_offloads_acl_tables(struct mlx5_eswitch *esw,
+				      struct mlx5_vport *vport)
+{
+	esw_vport_disable_egress_acl(esw, vport);
+	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
+	esw_vport_cleanup_ingress_rules(esw, vport);
+	esw_vport_destroy_ingress_acl_group(vport);
+	esw_vport_destroy_ingress_acl_table(vport);
+}
 
-	return 0;
+static int esw_create_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
+{
+	struct mlx5_vport *vport;
+	int err;
 
-err_egress:
-	esw_vport_disable_ingress_acl(esw, vport);
-err_ingress:
-	for (j = MLX5_VPORT_PF; j < i; j++) {
-		vport = &esw->vports[j];
-		esw_vport_disable_egress_acl(esw, vport);
-		esw_vport_disable_ingress_acl(esw, vport);
-	}
+	if (esw_check_vport_match_metadata_supported(esw))
+		esw->flags |= MLX5_ESWITCH_VPORT_MATCH_METADATA;
 
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+	err = esw_vport_create_offloads_acl_tables(esw, vport);
+	if (err)
+		esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
 	return err;
 }
 
-static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
+static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
-	int i;
-
-	mlx5_esw_for_all_vports(esw, i, vport) {
-		esw_vport_disable_egress_acl(esw, vport);
-		esw_vport_disable_ingress_acl(esw, vport);
-	}
 
+	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+	esw_vport_destroy_offloads_acl_tables(esw, vport);
 	esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
 }
 
@@ -2045,7 +2065,7 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
 	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
 
-	err = esw_create_offloads_acl_tables(esw);
+	err = esw_create_uplink_offloads_acl_tables(esw);
 	if (err)
 		return err;
 
@@ -2070,7 +2090,7 @@ create_ft_err:
 	esw_destroy_offloads_fdb_tables(esw);
 
 create_fdb_err:
-	esw_destroy_offloads_acl_tables(esw);
+	esw_destroy_uplink_offloads_acl_tables(esw);
 
 	return err;
 }
@@ -2080,7 +2100,7 @@ static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw)
 	esw_destroy_vport_rx_group(esw);
 	esw_destroy_offloads_table(esw);
 	esw_destroy_offloads_fdb_tables(esw);
-	esw_destroy_offloads_acl_tables(esw);
+	esw_destroy_uplink_offloads_acl_tables(esw);
 }
 
 static void
@@ -2169,7 +2189,9 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	if (err)
 		goto err_vport_metadata;
 
-	mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE);
+	err = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE);
+	if (err)
+		goto err_vports;
 
 	err = esw_offloads_load_all_reps(esw);
 	if (err)
@@ -2182,6 +2204,7 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 
 err_reps:
 	mlx5_eswitch_disable_pf_vf_vports(esw);
+err_vports:
 	esw_set_passing_vport_metadata(esw, false);
 err_vport_metadata:
 	esw_offloads_steering_cleanup(esw);
@@ -2195,7 +2218,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 {
 	int err, err1;
 
-	mlx5_eswitch_disable(esw);
+	mlx5_eswitch_disable(esw, false);
 	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
index eb8b0fe0b4e1..11621d265d7e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/cmd.h
@@ -35,11 +35,11 @@
 
 #include <linux/mlx5/driver.h>
 
-enum mlx5_fpga_device_id {
-	MLX5_FPGA_DEVICE_UNKNOWN = 0,
-	MLX5_FPGA_DEVICE_KU040 = 1,
-	MLX5_FPGA_DEVICE_KU060 = 2,
-	MLX5_FPGA_DEVICE_KU060_2 = 3,
+enum mlx5_fpga_id {
+	MLX5_FPGA_NEWTON = 0,
+	MLX5_FPGA_EDISON = 1,
+	MLX5_FPGA_MORSE = 2,
+	MLX5_FPGA_MORSEQ = 3,
 };
 
 enum mlx5_fpga_image {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
index d046d1ec2a86..2ce4241459ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.c
@@ -81,19 +81,28 @@ static const char *mlx5_fpga_image_name(enum mlx5_fpga_image image)
 	}
 }
 
-static const char *mlx5_fpga_device_name(u32 device)
+static const char *mlx5_fpga_name(u32 fpga_id)
 {
-	switch (device) {
-	case MLX5_FPGA_DEVICE_KU040:
-		return "ku040";
-	case MLX5_FPGA_DEVICE_KU060:
-		return "ku060";
-	case MLX5_FPGA_DEVICE_KU060_2:
-		return "ku060_2";
-	case MLX5_FPGA_DEVICE_UNKNOWN:
-	default:
-		return "unknown";
+	static char ret[32];
+
+	switch (fpga_id) {
+	case MLX5_FPGA_NEWTON:
+		return "Newton";
+	case MLX5_FPGA_EDISON:
+		return "Edison";
+	case MLX5_FPGA_MORSE:
+		return "Morse";
+	case MLX5_FPGA_MORSEQ:
+		return "MorseQ";
 	}
+
+	snprintf(ret, sizeof(ret), "Unknown %d", fpga_id);
+	return ret;
+}
+
+static int mlx5_is_fpga_lookaside(u32 fpga_id)
+{
+	return fpga_id != MLX5_FPGA_NEWTON && fpga_id != MLX5_FPGA_EDISON;
 }
 
 static int mlx5_fpga_device_load_check(struct mlx5_fpga_device *fdev)
@@ -110,8 +119,12 @@ static int mlx5_fpga_device_load_check(struct mlx5_fpga_device *fdev)
 	fdev->last_admin_image = query.admin_image;
 	fdev->last_oper_image = query.oper_image;
 
-	mlx5_fpga_dbg(fdev, "Status %u; Admin image %u; Oper image %u\n",
-		      query.status, query.admin_image, query.oper_image);
+	mlx5_fpga_info(fdev, "Status %u; Admin image %u; Oper image %u\n",
+		       query.status, query.admin_image, query.oper_image);
+
+	/* for FPGA lookaside projects FPGA load status is not important */
+	if (mlx5_is_fpga_lookaside(MLX5_CAP_FPGA(fdev->mdev, fpga_id)))
+		return 0;
 
 	if (query.status != MLX5_FPGA_STATUS_SUCCESS) {
 		mlx5_fpga_err(fdev, "%s image failed to load; status %u\n",
@@ -167,25 +180,30 @@ int mlx5_fpga_device_start(struct mlx5_core_dev *mdev)
 	struct mlx5_fpga_device *fdev = mdev->fpga;
 	unsigned int max_num_qps;
 	unsigned long flags;
-	u32 fpga_device_id;
+	u32 fpga_id;
 	int err;
 
 	if (!fdev)
 		return 0;
 
-	err = mlx5_fpga_device_load_check(fdev);
+	err = mlx5_fpga_caps(fdev->mdev);
 	if (err)
 		goto out;
 
-	err = mlx5_fpga_caps(fdev->mdev);
+	err = mlx5_fpga_device_load_check(fdev);
 	if (err)
 		goto out;
 
-	fpga_device_id = MLX5_CAP_FPGA(fdev->mdev, fpga_device);
-	mlx5_fpga_info(fdev, "%s:%u; %s image, version %u; SBU %06x:%04x version %d\n",
-		       mlx5_fpga_device_name(fpga_device_id),
-		       fpga_device_id,
+	fpga_id = MLX5_CAP_FPGA(fdev->mdev, fpga_id);
+	mlx5_fpga_info(fdev, "FPGA card %s:%u\n", mlx5_fpga_name(fpga_id), fpga_id);
+
+	/* No QPs if FPGA does not participate in net processing */
+	if (mlx5_is_fpga_lookaside(fpga_id))
+		goto out;
+
+	mlx5_fpga_info(fdev, "%s(%d): image, version %u; SBU %06x:%04x version %d\n",
 		       mlx5_fpga_image_name(fdev->last_oper_image),
+		       fdev->last_oper_image,
 		       MLX5_CAP_FPGA(fdev->mdev, image_version),
 		       MLX5_CAP_FPGA(fdev->mdev, ieee_vendor_id),
 		       MLX5_CAP_FPGA(fdev->mdev, sandbox_product_id),
@@ -264,6 +282,9 @@ void mlx5_fpga_device_stop(struct mlx5_core_dev *mdev)
 	if (!fdev)
 		return;
 
+	if (mlx5_is_fpga_lookaside(MLX5_CAP_FPGA(fdev->mdev, fpga_id)))
+		return;
+
 	spin_lock_irqsave(&fdev->state_lock, flags);
 	if (fdev->state != MLX5_FPGA_STATUS_SUCCESS) {
 		spin_unlock_irqrestore(&fdev->state_lock, flags);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 791e14ac26f4..d60577484567 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -531,9 +531,16 @@ static void del_hw_fte(struct fs_node *node)
 	}
 }
 
+static void del_sw_fte_rcu(struct rcu_head *head)
+{
+	struct fs_fte *fte = container_of(head, struct fs_fte, rcu);
+	struct mlx5_flow_steering *steering = get_steering(&fte->node);
+
+	kmem_cache_free(steering->ftes_cache, fte);
+}
+
 static void del_sw_fte(struct fs_node *node)
 {
-	struct mlx5_flow_steering *steering = get_steering(node);
 	struct mlx5_flow_group *fg;
 	struct fs_fte *fte;
 	int err;
@@ -546,7 +553,8 @@ static void del_sw_fte(struct fs_node *node)
 				     rhash_fte);
 	WARN_ON(err);
 	ida_simple_remove(&fg->fte_allocator, fte->index - fg->start_index);
-	kmem_cache_free(steering->ftes_cache, fte);
+
+	call_rcu(&fte->rcu, del_sw_fte_rcu);
 }
 
 static void del_hw_flow_group(struct fs_node *node)
@@ -1625,22 +1633,47 @@ static u64 matched_fgs_get_version(struct list_head *match_head)
 }
 
 static struct fs_fte *
-lookup_fte_locked(struct mlx5_flow_group *g,
-		  const u32 *match_value,
-		  bool take_write)
+lookup_fte_for_write_locked(struct mlx5_flow_group *g, const u32 *match_value)
 {
 	struct fs_fte *fte_tmp;
 
-	if (take_write)
-		nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
-	else
-		nested_down_read_ref_node(&g->node, FS_LOCK_PARENT);
-	fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value,
-					 rhash_fte);
+	nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
+
+	fte_tmp = rhashtable_lookup_fast(&g->ftes_hash, match_value, rhash_fte);
+	if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
+		fte_tmp = NULL;
+		goto out;
+	}
+
+	if (!fte_tmp->node.active) {
+		tree_put_node(&fte_tmp->node, false);
+		fte_tmp = NULL;
+		goto out;
+	}
+	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+
+out:
+	up_write_ref_node(&g->node, false);
+	return fte_tmp;
+}
+
+static struct fs_fte *
+lookup_fte_for_read_locked(struct mlx5_flow_group *g, const u32 *match_value)
+{
+	struct fs_fte *fte_tmp;
+
+	if (!tree_get_node(&g->node))
+		return NULL;
+
+	rcu_read_lock();
+	fte_tmp = rhashtable_lookup(&g->ftes_hash, match_value, rhash_fte);
 	if (!fte_tmp || !tree_get_node(&fte_tmp->node)) {
+		rcu_read_unlock();
 		fte_tmp = NULL;
 		goto out;
 	}
+	rcu_read_unlock();
+
 	if (!fte_tmp->node.active) {
 		tree_put_node(&fte_tmp->node, false);
 		fte_tmp = NULL;
@@ -1648,14 +1681,21 @@ lookup_fte_locked(struct mlx5_flow_group *g,
 	}
 
 	nested_down_write_ref_node(&fte_tmp->node, FS_LOCK_CHILD);
+
 out:
-	if (take_write)
-		up_write_ref_node(&g->node, false);
-	else
-		up_read_ref_node(&g->node);
+	tree_put_node(&g->node, false);
 	return fte_tmp;
 }
 
+static struct fs_fte *
+lookup_fte_locked(struct mlx5_flow_group *g, const u32 *match_value, bool write)
+{
+	if (write)
+		return lookup_fte_for_write_locked(g, match_value);
+	else
+		return lookup_fte_for_read_locked(g, match_value);
+}
+
 static struct mlx5_flow_handle *
 try_add_to_existing_fg(struct mlx5_flow_table *ft,
 		       struct list_head *match_head,
@@ -1816,6 +1856,13 @@ search_again_locked:
 		return rule;
 	}
 
+	fte = alloc_fte(ft, spec, flow_act);
+	if (IS_ERR(fte)) {
+		up_write_ref_node(&ft->node, false);
+		err = PTR_ERR(fte);
+		goto err_alloc_fte;
+	}
+
 	nested_down_write_ref_node(&g->node, FS_LOCK_PARENT);
 	up_write_ref_node(&ft->node, false);
 
@@ -1823,17 +1870,9 @@ search_again_locked:
 	if (err)
 		goto err_release_fg;
 
-	fte = alloc_fte(ft, spec, flow_act);
-	if (IS_ERR(fte)) {
-		err = PTR_ERR(fte);
-		goto err_release_fg;
-	}
-
 	err = insert_fte(g, fte);
-	if (err) {
-		kmem_cache_free(steering->ftes_cache, fte);
+	if (err)
 		goto err_release_fg;
-	}
 
 	nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
 	up_write_ref_node(&g->node, false);
@@ -1845,6 +1884,8 @@ search_again_locked:
 
 err_release_fg:
 	up_write_ref_node(&g->node, false);
+	kmem_cache_free(steering->ftes_cache, fte);
+err_alloc_fte:
 	tree_put_node(&g->node, false);
 	return ERR_PTR(err);
 }
@@ -2361,9 +2402,17 @@ static void set_prio_attrs_in_prio(struct fs_prio *prio, int acc_level)
 	int acc_level_ns = acc_level;
 
 	prio->start_level = acc_level;
-	fs_for_each_ns(ns, prio)
+	fs_for_each_ns(ns, prio) {
 		/* This updates start_level and num_levels of ns's priority descendants */
 		acc_level_ns = set_prio_attrs_in_ns(ns, acc_level);
+
+		/* If this a prio with chains, and we can jump from one chain
+		 * (namepsace) to another, so we accumulate the levels
+		 */
+		if (prio->node.type == FS_TYPE_PRIO_CHAINS)
+			acc_level = acc_level_ns;
+	}
+
 	if (!prio->num_levels)
 		prio->num_levels = acc_level_ns - prio->start_level;
 	WARN_ON(prio->num_levels < acc_level_ns - prio->start_level);
@@ -2552,58 +2601,109 @@ out_err:
 	steering->rdma_rx_root_ns = NULL;
 	return err;
 }
-static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
+
+/* FT and tc chains are stored in the same array so we can re-use the
+ * mlx5_get_fdb_sub_ns() and tc api for FT chains.
+ * When creating a new ns for each chain store it in the first available slot.
+ * Assume tc chains are created and stored first and only then the FT chain.
+ */
+static void store_fdb_sub_ns_prio_chain(struct mlx5_flow_steering *steering,
+					struct mlx5_flow_namespace *ns)
+{
+	int chain = 0;
+
+	while (steering->fdb_sub_ns[chain])
+		++chain;
+
+	steering->fdb_sub_ns[chain] = ns;
+}
+
+static int create_fdb_sub_ns_prio_chain(struct mlx5_flow_steering *steering,
+					struct fs_prio *maj_prio)
 {
 	struct mlx5_flow_namespace *ns;
-	struct fs_prio *maj_prio;
 	struct fs_prio *min_prio;
+	int prio;
+
+	ns = fs_create_namespace(maj_prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF);
+	if (IS_ERR(ns))
+		return PTR_ERR(ns);
+
+	for (prio = 0; prio < FDB_TC_MAX_PRIO; prio++) {
+		min_prio = fs_create_prio(ns, prio, FDB_TC_LEVELS_PER_PRIO);
+		if (IS_ERR(min_prio))
+			return PTR_ERR(min_prio);
+	}
+
+	store_fdb_sub_ns_prio_chain(steering, ns);
+
+	return 0;
+}
+
+static int create_fdb_chains(struct mlx5_flow_steering *steering,
+			     int fs_prio,
+			     int chains)
+{
+	struct fs_prio *maj_prio;
 	int levels;
 	int chain;
-	int prio;
 	int err;
 
-	steering->fdb_root_ns = create_root_ns(steering, FS_FT_FDB);
-	if (!steering->fdb_root_ns)
-		return -ENOMEM;
+	levels = FDB_TC_LEVELS_PER_PRIO * FDB_TC_MAX_PRIO * chains;
+	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns,
+					  fs_prio,
+					  levels);
+	if (IS_ERR(maj_prio))
+		return PTR_ERR(maj_prio);
+
+	for (chain = 0; chain < chains; chain++) {
+		err = create_fdb_sub_ns_prio_chain(steering, maj_prio);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int create_fdb_fast_path(struct mlx5_flow_steering *steering)
+{
+	int err;
 
-	steering->fdb_sub_ns = kzalloc(sizeof(steering->fdb_sub_ns) *
-				       (FDB_MAX_CHAIN + 1), GFP_KERNEL);
+	steering->fdb_sub_ns = kcalloc(FDB_NUM_CHAINS,
+				       sizeof(*steering->fdb_sub_ns),
+				       GFP_KERNEL);
 	if (!steering->fdb_sub_ns)
 		return -ENOMEM;
 
+	err = create_fdb_chains(steering, FDB_TC_OFFLOAD, FDB_TC_MAX_CHAIN + 1);
+	if (err)
+		return err;
+
+	err = create_fdb_chains(steering, FDB_FT_OFFLOAD, 1);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int init_fdb_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct fs_prio *maj_prio;
+	int err;
+
+	steering->fdb_root_ns = create_root_ns(steering, FS_FT_FDB);
+	if (!steering->fdb_root_ns)
+		return -ENOMEM;
+
 	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_BYPASS_PATH,
 				  1);
 	if (IS_ERR(maj_prio)) {
 		err = PTR_ERR(maj_prio);
 		goto out_err;
 	}
-
-	levels = 2 * FDB_MAX_PRIO * (FDB_MAX_CHAIN + 1);
-	maj_prio = fs_create_prio_chained(&steering->fdb_root_ns->ns,
-					  FDB_FAST_PATH,
-					  levels);
-	if (IS_ERR(maj_prio)) {
-		err = PTR_ERR(maj_prio);
+	err = create_fdb_fast_path(steering);
+	if (err)
 		goto out_err;
-	}
-
-	for (chain = 0; chain <= FDB_MAX_CHAIN; chain++) {
-		ns = fs_create_namespace(maj_prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF);
-		if (IS_ERR(ns)) {
-			err = PTR_ERR(ns);
-			goto out_err;
-		}
-
-		for (prio = 0; prio < FDB_MAX_PRIO * (chain + 1); prio++) {
-			min_prio = fs_create_prio(ns, prio, 2);
-			if (IS_ERR(min_prio)) {
-				err = PTR_ERR(min_prio);
-				goto out_err;
-			}
-		}
-
-		steering->fdb_sub_ns[chain] = ns;
-	}
 
 	maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_SLOW_PATH, 1);
 	if (IS_ERR(maj_prio)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index c2621b911563..e8cd997f413e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -203,6 +203,7 @@ struct fs_fte {
 	enum fs_fte_status		status;
 	struct mlx5_fc			*counter;
 	struct rhash_head		hash;
+	struct rcu_head	rcu;
 	int				modify_mask;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index c07f3154437c..d9f4e8c59c1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -390,7 +390,8 @@ static void print_health_info(struct mlx5_core_dev *dev)
 
 static int
 mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter,
-			  struct devlink_fmsg *fmsg)
+			  struct devlink_fmsg *fmsg,
+			  struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
 	struct mlx5_core_health *health = &dev->priv.health;
@@ -491,7 +492,8 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev,
 
 static int
 mlx5_fw_reporter_dump(struct devlink_health_reporter *reporter,
-		      struct devlink_fmsg *fmsg, void *priv_ctx)
+		      struct devlink_fmsg *fmsg, void *priv_ctx,
+		      struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
 	int err;
@@ -545,23 +547,22 @@ static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
 
 static int
 mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
-			       void *priv_ctx)
+			       void *priv_ctx,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
 
 	return mlx5_health_try_recover(dev);
 }
 
-#define MLX5_CR_DUMP_CHUNK_SIZE 256
 static int
 mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
-			    struct devlink_fmsg *fmsg, void *priv_ctx)
+			    struct devlink_fmsg *fmsg, void *priv_ctx,
+			    struct netlink_ext_ack *extack)
 {
 	struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter);
 	u32 crdump_size = dev->priv.health.crdump_size;
 	u32 *cr_data;
-	u32 data_size;
-	u32 offset;
 	int err;
 
 	if (!mlx5_core_is_pf(dev))
@@ -582,20 +583,7 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter,
 			goto free_data;
 	}
 
-	err = devlink_fmsg_arr_pair_nest_start(fmsg, "crdump_data");
-	if (err)
-		goto free_data;
-	for (offset = 0; offset < crdump_size; offset += data_size) {
-		if (crdump_size - offset < MLX5_CR_DUMP_CHUNK_SIZE)
-			data_size = crdump_size - offset;
-		else
-			data_size = MLX5_CR_DUMP_CHUNK_SIZE;
-		err = devlink_fmsg_binary_put(fmsg, (char *)cr_data + offset,
-					      data_size);
-		if (err)
-			goto free_data;
-	}
-	err = devlink_fmsg_arr_pair_nest_end(fmsg);
+	err = devlink_fmsg_binary_pair_put(fmsg, "crdump_data", cr_data, crdump_size);
 
 free_data:
 	kvfree(cr_data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index c5ef2ff26465..fc0d9583475d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -145,34 +145,35 @@ static void mlx5_infer_tx_affinity_mapping(struct lag_tracker *tracker,
 {
 	*port1 = 1;
 	*port2 = 2;
-	if (!tracker->netdev_state[0].tx_enabled ||
-	    !tracker->netdev_state[0].link_up) {
+	if (!tracker->netdev_state[MLX5_LAG_P1].tx_enabled ||
+	    !tracker->netdev_state[MLX5_LAG_P1].link_up) {
 		*port1 = 2;
 		return;
 	}
 
-	if (!tracker->netdev_state[1].tx_enabled ||
-	    !tracker->netdev_state[1].link_up)
+	if (!tracker->netdev_state[MLX5_LAG_P2].tx_enabled ||
+	    !tracker->netdev_state[MLX5_LAG_P2].link_up)
 		*port2 = 1;
 }
 
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	u8 v2p_port1, v2p_port2;
 	int err;
 
 	mlx5_infer_tx_affinity_mapping(tracker, &v2p_port1,
 				       &v2p_port2);
 
-	if (v2p_port1 != ldev->v2p_map[0] ||
-	    v2p_port2 != ldev->v2p_map[1]) {
-		ldev->v2p_map[0] = v2p_port1;
-		ldev->v2p_map[1] = v2p_port2;
+	if (v2p_port1 != ldev->v2p_map[MLX5_LAG_P1] ||
+	    v2p_port2 != ldev->v2p_map[MLX5_LAG_P2]) {
+		ldev->v2p_map[MLX5_LAG_P1] = v2p_port1;
+		ldev->v2p_map[MLX5_LAG_P2] = v2p_port2;
 
 		mlx5_core_info(dev0, "modify lag map port 1:%d port 2:%d",
-			       ldev->v2p_map[0], ldev->v2p_map[1]);
+			       ldev->v2p_map[MLX5_LAG_P1],
+			       ldev->v2p_map[MLX5_LAG_P2]);
 
 		err = mlx5_cmd_modify_lag(dev0, v2p_port1, v2p_port2);
 		if (err)
@@ -185,16 +186,17 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 static int mlx5_create_lag(struct mlx5_lag *ldev,
 			   struct lag_tracker *tracker)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	int err;
 
-	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[0],
-				       &ldev->v2p_map[1]);
+	mlx5_infer_tx_affinity_mapping(tracker, &ldev->v2p_map[MLX5_LAG_P1],
+				       &ldev->v2p_map[MLX5_LAG_P2]);
 
 	mlx5_core_info(dev0, "lag map port 1:%d port 2:%d",
-		       ldev->v2p_map[0], ldev->v2p_map[1]);
+		       ldev->v2p_map[MLX5_LAG_P1], ldev->v2p_map[MLX5_LAG_P2]);
 
-	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[0], ldev->v2p_map[1]);
+	err = mlx5_cmd_create_lag(dev0, ldev->v2p_map[MLX5_LAG_P1],
+				  ldev->v2p_map[MLX5_LAG_P2]);
 	if (err)
 		mlx5_core_err(dev0,
 			      "Failed to create LAG (%d)\n",
@@ -207,7 +209,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 		      u8 flags)
 {
 	bool roce_lag = !!(flags & MLX5_LAG_FLAG_ROCE);
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	int err;
 
 	err = mlx5_create_lag(ldev, tracker);
@@ -229,7 +231,7 @@ int mlx5_activate_lag(struct mlx5_lag *ldev,
 
 static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
 	bool roce_lag = __mlx5_lag_is_roce(ldev);
 	int err;
 
@@ -252,14 +254,15 @@ static int mlx5_deactivate_lag(struct mlx5_lag *ldev)
 
 static bool mlx5_lag_check_prereq(struct mlx5_lag *ldev)
 {
-	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
+	if (!ldev->pf[MLX5_LAG_P1].dev || !ldev->pf[MLX5_LAG_P2].dev)
 		return false;
 
 #ifdef CONFIG_MLX5_ESWITCH
-	return mlx5_esw_lag_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+	return mlx5_esw_lag_prereq(ldev->pf[MLX5_LAG_P1].dev,
+				   ldev->pf[MLX5_LAG_P2].dev);
 #else
-	return (!mlx5_sriov_is_enabled(ldev->pf[0].dev) &&
-		!mlx5_sriov_is_enabled(ldev->pf[1].dev));
+	return (!mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P1].dev) &&
+		!mlx5_sriov_is_enabled(ldev->pf[MLX5_LAG_P2].dev));
 #endif
 }
 
@@ -285,8 +288,8 @@ static void mlx5_lag_remove_ib_devices(struct mlx5_lag *ldev)
 
 static void mlx5_do_bond(struct mlx5_lag *ldev)
 {
-	struct mlx5_core_dev *dev0 = ldev->pf[0].dev;
-	struct mlx5_core_dev *dev1 = ldev->pf[1].dev;
+	struct mlx5_core_dev *dev0 = ldev->pf[MLX5_LAG_P1].dev;
+	struct mlx5_core_dev *dev1 = ldev->pf[MLX5_LAG_P2].dev;
 	struct lag_tracker tracker;
 	bool do_bond, roce_lag;
 	int err;
@@ -692,10 +695,11 @@ struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
 		goto unlock;
 
 	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
-		ndev = ldev->tracker.netdev_state[0].tx_enabled ?
-		       ldev->pf[0].netdev : ldev->pf[1].netdev;
+		ndev = ldev->tracker.netdev_state[MLX5_LAG_P1].tx_enabled ?
+		       ldev->pf[MLX5_LAG_P1].netdev :
+		       ldev->pf[MLX5_LAG_P2].netdev;
 	} else {
-		ndev = ldev->pf[0].netdev;
+		ndev = ldev->pf[MLX5_LAG_P1].netdev;
 	}
 	if (ndev)
 		dev_hold(ndev);
@@ -717,7 +721,8 @@ bool mlx5_lag_intf_add(struct mlx5_interface *intf, struct mlx5_priv *priv)
 		return true;
 
 	ldev = mlx5_lag_dev_get(dev);
-	if (!ldev || !__mlx5_lag_is_roce(ldev) || ldev->pf[0].dev == dev)
+	if (!ldev || !__mlx5_lag_is_roce(ldev) ||
+	    ldev->pf[MLX5_LAG_P1].dev == dev)
 		return true;
 
 	/* If bonded, we do not add an IB device for PF1. */
@@ -746,11 +751,11 @@ int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 	ldev = mlx5_lag_dev_get(dev);
 	if (ldev && __mlx5_lag_is_roce(ldev)) {
 		num_ports = MLX5_MAX_PORTS;
-		mdev[0] = ldev->pf[0].dev;
-		mdev[1] = ldev->pf[1].dev;
+		mdev[MLX5_LAG_P1] = ldev->pf[MLX5_LAG_P1].dev;
+		mdev[MLX5_LAG_P2] = ldev->pf[MLX5_LAG_P2].dev;
 	} else {
 		num_ports = 1;
-		mdev[0] = dev;
+		mdev[MLX5_LAG_P1] = dev;
 	}
 
 	for (i = 0; i < num_ports; ++i) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
index 1dea0b1c9826..f1068aac6406 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.h
@@ -8,6 +8,11 @@
 #include "lag_mp.h"
 
 enum {
+	MLX5_LAG_P1,
+	MLX5_LAG_P2,
+};
+
+enum {
 	MLX5_LAG_FLAG_ROCE   = 1 << 0,
 	MLX5_LAG_FLAG_SRIOV  = 1 << 1,
 	MLX5_LAG_FLAG_MULTIPATH = 1 << 2,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
index 5d20d615663e..b70afa310ad2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c
@@ -11,10 +11,11 @@
 
 static bool mlx5_lag_multipath_check_prereq(struct mlx5_lag *ldev)
 {
-	if (!ldev->pf[0].dev || !ldev->pf[1].dev)
+	if (!ldev->pf[MLX5_LAG_P1].dev || !ldev->pf[MLX5_LAG_P2].dev)
 		return false;
 
-	return mlx5_esw_multipath_prereq(ldev->pf[0].dev, ldev->pf[1].dev);
+	return mlx5_esw_multipath_prereq(ldev->pf[MLX5_LAG_P1].dev,
+					 ldev->pf[MLX5_LAG_P2].dev);
 }
 
 static bool __mlx5_lag_is_multipath(struct mlx5_lag *ldev)
@@ -43,7 +44,8 @@ bool mlx5_lag_is_multipath(struct mlx5_core_dev *dev)
  *     2 - set affinity to port 2.
  *
  **/
-static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port)
+static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev,
+				       enum mlx5_lag_port_affinity port)
 {
 	struct lag_tracker tracker;
 
@@ -51,37 +53,37 @@ static void mlx5_lag_set_port_affinity(struct mlx5_lag *ldev, int port)
 		return;
 
 	switch (port) {
-	case 0:
-		tracker.netdev_state[0].tx_enabled = true;
-		tracker.netdev_state[1].tx_enabled = true;
-		tracker.netdev_state[0].link_up = true;
-		tracker.netdev_state[1].link_up = true;
+	case MLX5_LAG_NORMAL_AFFINITY:
+		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P1].link_up = true;
+		tracker.netdev_state[MLX5_LAG_P2].link_up = true;
 		break;
-	case 1:
-		tracker.netdev_state[0].tx_enabled = true;
-		tracker.netdev_state[0].link_up = true;
-		tracker.netdev_state[1].tx_enabled = false;
-		tracker.netdev_state[1].link_up = false;
+	case MLX5_LAG_P1_AFFINITY:
+		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P1].link_up = true;
+		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = false;
+		tracker.netdev_state[MLX5_LAG_P2].link_up = false;
 		break;
-	case 2:
-		tracker.netdev_state[0].tx_enabled = false;
-		tracker.netdev_state[0].link_up = false;
-		tracker.netdev_state[1].tx_enabled = true;
-		tracker.netdev_state[1].link_up = true;
+	case MLX5_LAG_P2_AFFINITY:
+		tracker.netdev_state[MLX5_LAG_P1].tx_enabled = false;
+		tracker.netdev_state[MLX5_LAG_P1].link_up = false;
+		tracker.netdev_state[MLX5_LAG_P2].tx_enabled = true;
+		tracker.netdev_state[MLX5_LAG_P2].link_up = true;
 		break;
 	default:
-		mlx5_core_warn(ldev->pf[0].dev, "Invalid affinity port %d",
-			       port);
+		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
+			       "Invalid affinity port %d", port);
 		return;
 	}
 
-	if (tracker.netdev_state[0].tx_enabled)
-		mlx5_notifier_call_chain(ldev->pf[0].dev->priv.events,
+	if (tracker.netdev_state[MLX5_LAG_P1].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P1].dev->priv.events,
 					 MLX5_DEV_EVENT_PORT_AFFINITY,
 					 (void *)0);
 
-	if (tracker.netdev_state[1].tx_enabled)
-		mlx5_notifier_call_chain(ldev->pf[1].dev->priv.events,
+	if (tracker.netdev_state[MLX5_LAG_P2].tx_enabled)
+		mlx5_notifier_call_chain(ldev->pf[MLX5_LAG_P2].dev->priv.events,
 					 MLX5_DEV_EVENT_PORT_AFFINITY,
 					 (void *)0);
 
@@ -141,11 +143,12 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 	/* Verify next hops are ports of the same hca */
 	fib_nh0 = fib_info_nh(fi, 0);
 	fib_nh1 = fib_info_nh(fi, 1);
-	if (!(fib_nh0->fib_nh_dev == ldev->pf[0].netdev &&
-	      fib_nh1->fib_nh_dev == ldev->pf[1].netdev) &&
-	    !(fib_nh0->fib_nh_dev == ldev->pf[1].netdev &&
-	      fib_nh1->fib_nh_dev == ldev->pf[0].netdev)) {
-		mlx5_core_warn(ldev->pf[0].dev, "Multipath offload require two ports of the same HCA\n");
+	if (!(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev) &&
+	    !(fib_nh0->fib_nh_dev == ldev->pf[MLX5_LAG_P2].netdev &&
+	      fib_nh1->fib_nh_dev == ldev->pf[MLX5_LAG_P1].netdev)) {
+		mlx5_core_warn(ldev->pf[MLX5_LAG_P1].dev,
+			       "Multipath offload require two ports of the same HCA\n");
 		return;
 	}
 
@@ -157,7 +160,7 @@ static void mlx5_lag_fib_route_event(struct mlx5_lag *ldev,
 		mlx5_activate_lag(ldev, &tracker, MLX5_LAG_FLAG_MULTIPATH);
 	}
 
-	mlx5_lag_set_port_affinity(ldev, 0);
+	mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY);
 	mp->mfi = fi;
 }
 
@@ -182,7 +185,7 @@ static void mlx5_lag_fib_nexthop_event(struct mlx5_lag *ldev,
 		}
 	} else if (event == FIB_EVENT_NH_ADD &&
 		   fib_info_num_path(fi) == 2) {
-		mlx5_lag_set_port_affinity(ldev, 0);
+		mlx5_lag_set_port_affinity(ldev, MLX5_LAG_NORMAL_AFFINITY);
 	}
 }
 
@@ -248,9 +251,6 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
 	struct net_device *fib_dev;
 	struct fib_info *fi;
 
-	if (!net_eq(info->net, &init_net))
-		return NOTIFY_DONE;
-
 	if (info->family != AF_INET)
 		return NOTIFY_DONE;
 
@@ -270,8 +270,8 @@ static int mlx5_lag_fib_event(struct notifier_block *nb,
 			return notifier_from_errno(-EINVAL);
 		}
 		fib_dev = fib_info_nh(fen_info->fi, 0)->fib_nh_dev;
-		if (fib_dev != ldev->pf[0].netdev &&
-		    fib_dev != ldev->pf[1].netdev) {
+		if (fib_dev != ldev->pf[MLX5_LAG_P1].netdev &&
+		    fib_dev != ldev->pf[MLX5_LAG_P2].netdev) {
 			return NOTIFY_DONE;
 		}
 		fib_work = mlx5_lag_init_fib_work(ldev, event);
@@ -311,8 +311,8 @@ int mlx5_lag_mp_init(struct mlx5_lag *ldev)
 		return 0;
 
 	mp->fib_nb.notifier_call = mlx5_lag_fib_event;
-	err = register_fib_notifier(&mp->fib_nb,
-				    mlx5_lag_fib_event_flush);
+	err = register_fib_notifier(&init_net, &mp->fib_nb,
+				    mlx5_lag_fib_event_flush, NULL);
 	if (err)
 		mp->fib_nb.notifier_call = NULL;
 
@@ -326,6 +326,6 @@ void mlx5_lag_mp_cleanup(struct mlx5_lag *ldev)
 	if (!mp->fib_nb.notifier_call)
 		return;
 
-	unregister_fib_notifier(&mp->fib_nb);
+	unregister_fib_notifier(&init_net, &mp->fib_nb);
 	mp->fib_nb.notifier_call = NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
index 6d14b1100be9..79be89e9c7a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.h
@@ -7,6 +7,12 @@
 #include "lag.h"
 #include "mlx5_core.h"
 
+enum mlx5_lag_port_affinity {
+	MLX5_LAG_NORMAL_AFFINITY,
+	MLX5_LAG_P1_AFFINITY,
+	MLX5_LAG_P2_AFFINITY,
+};
+
 struct lag_mp {
 	struct notifier_block     fib_nb;
 	struct fib_info           *mfi; /* used in tracking fib events */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index b99d469e4e64..249539247e2e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -84,4 +84,9 @@ int mlx5_create_encryption_key(struct mlx5_core_dev *mdev,
 			       void *key, u32 sz_bytes, u32 *p_key_id);
 void mlx5_destroy_encryption_key(struct mlx5_core_dev *mdev, u32 key_id);
 
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 50ab88d80033..584074bbf669 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1168,7 +1168,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_put_uars_page(dev, dev->priv.uar);
 }
 
-static int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
+int mlx5_load_one(struct mlx5_core_dev *dev, bool boot)
 {
 	int err = 0;
 
@@ -1226,10 +1226,8 @@ function_teardown:
 	return err;
 }
 
-static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
+int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 {
-	int err = 0;
-
 	if (cleanup) {
 		mlx5_unregister_device(dev);
 		mlx5_drain_health_wq(dev);
@@ -1257,7 +1255,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup)
 	mlx5_function_teardown(dev, cleanup);
 out:
 	mutex_unlock(&dev->intf_state_mutex);
-	return err;
+	return 0;
 }
 
 static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index b100489dc85c..da67b28d6e23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -243,4 +243,7 @@ enum {
 
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev);
 void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state);
+
+int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup);
+int mlx5_load_one(struct mlx5_core_dev *dev, bool boot);
 #endif /* __MLX5_CORE_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 61fcfd8b39b4..03f037811f1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -108,10 +108,10 @@ enable_vfs_hca:
 	return 0;
 }
 
-static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
+static void
+mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
-	int num_vfs = pci_num_vf(dev->pdev);
 	int err;
 	int vf;
 
@@ -127,7 +127,7 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 	}
 
 	if (MLX5_ESWITCH_MANAGER(dev))
-		mlx5_eswitch_disable(dev->priv.eswitch);
+		mlx5_eswitch_disable(dev->priv.eswitch, clear_vf);
 
 	if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
@@ -147,7 +147,7 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 	err = pci_enable_sriov(pdev, num_vfs);
 	if (err) {
 		mlx5_core_warn(dev, "pci_enable_sriov failed : %d\n", err);
-		mlx5_device_disable_sriov(dev);
+		mlx5_device_disable_sriov(dev, num_vfs, true);
 	}
 	return err;
 }
@@ -155,9 +155,10 @@ static int mlx5_sriov_enable(struct pci_dev *pdev, int num_vfs)
 static void mlx5_sriov_disable(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev  = pci_get_drvdata(pdev);
+	int num_vfs = pci_num_vf(dev->pdev);
 
 	pci_disable_sriov(pdev);
-	mlx5_device_disable_sriov(dev);
+	mlx5_device_disable_sriov(dev, num_vfs, true);
 }
 
 int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs)
@@ -192,7 +193,7 @@ void mlx5_sriov_detach(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_pf(dev))
 		return;
 
-	mlx5_device_disable_sriov(dev);
+	mlx5_device_disable_sriov(dev, pci_num_vf(dev->pdev), false);
 }
 
 static u16 mlx5_get_max_vfs(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
deleted file mode 100644
index 9e2eccbb1eb8..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c
+++ /dev/null
@@ -1,98 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
-/* Copyright (c) 2019 Mellanox Technologies. */
-
-/* Copyright (c) 2011-2015 Stephan Brumme. All rights reserved.
- * Slicing-by-16 contributed by Bulat Ziganshin
- *
- * This software is provided 'as-is', without any express or implied warranty.
- * In no event will the author be held liable for any damages arising from the
- * of this software.
- *
- * Permission is granted to anyone to use this software for any purpose,
- * including commercial applications, and to alter it and redistribute it
- * freely, subject to the following restrictions:
- *
- * 1. The origin of this software must not be misrepresented; you must not
- *    claim that you wrote the original software.
- * 2. If you use this software in a product, an acknowledgment in the product
- *    documentation would be appreciated but is not required.
- * 3. Altered source versions must be plainly marked as such, and must not be
- *    misrepresented as being the original software.
- *
- * Taken from http://create.stephan-brumme.com/crc32/ and adapted.
- */
-
-#include "dr_types.h"
-
-#define DR_STE_CRC_POLY 0xEDB88320L
-
-static u32 dr_ste_crc_tab32[8][256];
-
-static void dr_crc32_calc_lookup_entry(u32 (*tbl)[256], u8 i, u8 j)
-{
-	tbl[i][j] = (tbl[i - 1][j] >> 8) ^ tbl[0][tbl[i - 1][j] & 0xff];
-}
-
-void mlx5dr_crc32_init_table(void)
-{
-	u32 crc, i, j;
-
-	for (i = 0; i < 256; i++) {
-		crc = i;
-		for (j = 0; j < 8; j++) {
-			if (crc & 0x00000001L)
-				crc = (crc >> 1) ^ DR_STE_CRC_POLY;
-			else
-				crc = crc >> 1;
-		}
-		dr_ste_crc_tab32[0][i] = crc;
-	}
-
-	/* Init CRC lookup tables according to crc_slice_8 algorithm */
-	for (i = 0; i < 256; i++) {
-		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 1, i);
-		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 2, i);
-		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 3, i);
-		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 4, i);
-		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 5, i);
-		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 6, i);
-		dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 7, i);
-	}
-}
-
-/* Compute CRC32 (Slicing-by-8 algorithm) */
-u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length)
-{
-	const u32 *curr = (const u32 *)input_data;
-	const u8 *curr_char;
-	u32 crc = 0, one, two;
-
-	if (!input_data)
-		return 0;
-
-	/* Process eight bytes at once (Slicing-by-8) */
-	while (length >= 8) {
-		one = *curr++ ^ crc;
-		two = *curr++;
-
-		crc = dr_ste_crc_tab32[0][(two >> 24) & 0xff]
-			^ dr_ste_crc_tab32[1][(two >> 16) & 0xff]
-			^ dr_ste_crc_tab32[2][(two >> 8) & 0xff]
-			^ dr_ste_crc_tab32[3][two & 0xff]
-			^ dr_ste_crc_tab32[4][(one >> 24) & 0xff]
-			^ dr_ste_crc_tab32[5][(one >> 16) & 0xff]
-			^ dr_ste_crc_tab32[6][(one >> 8) & 0xff]
-			^ dr_ste_crc_tab32[7][one & 0xff];
-
-		length -= 8;
-	}
-
-	curr_char = (const u8 *)curr;
-	/* Remaining 1 to 7 bytes (standard algorithm) */
-	while (length-- != 0)
-		crc = (crc >> 8) ^ dr_ste_crc_tab32[0][(crc & 0xff)
-			^ *curr_char++];
-
-	return ((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) |
-		((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000);
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
index 5b24732b18c0..a9da961d4d2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c
@@ -326,9 +326,6 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
 		goto uninit_resourses;
 	}
 
-	/* Init CRC table for htbl CRC calculation */
-	mlx5dr_crc32_init_table();
-
 	return dmn;
 
 uninit_resourses:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
index 67dea7698fc9..c6dbd856df94 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c
@@ -102,13 +102,52 @@ static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc)
 	DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \
 	DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp))
 
-static bool dr_mask_is_flex_parser_tnl_set(struct mlx5dr_match_misc3 *misc3)
+static bool
+dr_mask_is_misc3_vxlan_gpe_set(struct mlx5dr_match_misc3 *misc3)
 {
 	return (misc3->outer_vxlan_gpe_vni ||
 		misc3->outer_vxlan_gpe_next_protocol ||
 		misc3->outer_vxlan_gpe_flags);
 }
 
+static bool
+dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_cmd_caps *caps)
+{
+	return caps->flex_protocols &
+	       MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
+}
+
+static bool
+dr_mask_is_flex_parser_tnl_vxlan_gpe_set(struct mlx5dr_match_param *mask,
+					 struct mlx5dr_domain *dmn)
+{
+	return dr_mask_is_misc3_vxlan_gpe_set(&mask->misc3) &&
+	       dr_matcher_supp_flex_parser_vxlan_gpe(&dmn->info.caps);
+}
+
+static bool dr_mask_is_misc_geneve_set(struct mlx5dr_match_misc *misc)
+{
+	return misc->geneve_vni ||
+	       misc->geneve_oam ||
+	       misc->geneve_protocol_type ||
+	       misc->geneve_opt_len;
+}
+
+static bool
+dr_matcher_supp_flex_parser_geneve(struct mlx5dr_cmd_caps *caps)
+{
+	return caps->flex_protocols &
+	       MLX5_FLEX_PARSER_GENEVE_ENABLED;
+}
+
+static bool
+dr_mask_is_flex_parser_tnl_geneve_set(struct mlx5dr_match_param *mask,
+				      struct mlx5dr_domain *dmn)
+{
+	return dr_mask_is_misc_geneve_set(&mask->misc) &&
+	       dr_matcher_supp_flex_parser_geneve(&dmn->info.caps);
+}
+
 static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3)
 {
 	return (misc3->icmpv6_type || misc3->icmpv6_code ||
@@ -137,24 +176,15 @@ static bool dr_mask_is_gvmi_or_qpn_set(struct mlx5dr_match_misc *misc)
 	return (misc->source_sqn || misc->source_port);
 }
 
-static bool
-dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn)
-{
-	return dmn->info.caps.flex_protocols &
-	       MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED;
-}
-
 int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
 				   struct mlx5dr_matcher_rx_tx *nic_matcher,
-				   bool ipv6)
+				   enum mlx5dr_ipv outer_ipv,
+				   enum mlx5dr_ipv inner_ipv)
 {
-	if (ipv6) {
-		nic_matcher->ste_builder = nic_matcher->ste_builder6;
-		nic_matcher->num_of_builders = nic_matcher->num_of_builders6;
-	} else {
-		nic_matcher->ste_builder = nic_matcher->ste_builder4;
-		nic_matcher->num_of_builders = nic_matcher->num_of_builders4;
-	}
+	nic_matcher->ste_builder =
+		nic_matcher->ste_builder_arr[outer_ipv][inner_ipv];
+	nic_matcher->num_of_builders =
+		nic_matcher->num_of_builders_arr[outer_ipv][inner_ipv];
 
 	if (!nic_matcher->num_of_builders) {
 		mlx5dr_dbg(matcher->tbl->dmn,
@@ -167,26 +197,19 @@ int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
 
 static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 				       struct mlx5dr_matcher_rx_tx *nic_matcher,
-				       bool ipv6)
+				       enum mlx5dr_ipv outer_ipv,
+				       enum mlx5dr_ipv inner_ipv)
 {
 	struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn;
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
 	struct mlx5dr_match_param mask = {};
 	struct mlx5dr_match_misc3 *misc3;
 	struct mlx5dr_ste_build *sb;
-	u8 *num_of_builders;
 	bool inner, rx;
 	int idx = 0;
 	int ret, i;
 
-	if (ipv6) {
-		sb = nic_matcher->ste_builder6;
-		num_of_builders = &nic_matcher->num_of_builders6;
-	} else {
-		sb = nic_matcher->ste_builder4;
-		num_of_builders = &nic_matcher->num_of_builders4;
-	}
-
+	sb = nic_matcher->ste_builder_arr[outer_ipv][inner_ipv];
 	rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX;
 
 	/* Create a temporary mask to track and clear used mask fields */
@@ -249,7 +272,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 		if (DR_MASK_IS_L2_DST(mask.outer, mask.misc, outer))
 			mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
 
-		if (ipv6) {
+		if (outer_ipv == DR_RULE_IPV6) {
 			if (dr_mask_is_dst_addr_set(&mask.outer))
 				mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
 								 inner, rx);
@@ -271,10 +294,14 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 								  inner, rx);
 		}
 
-		if (dr_mask_is_flex_parser_tnl_set(&mask.misc3) &&
-		    dr_matcher_supp_flex_parser_vxlan_gpe(dmn))
-			mlx5dr_ste_build_flex_parser_tnl(&sb[idx++], &mask,
-							 inner, rx);
+		if (dr_mask_is_flex_parser_tnl_vxlan_gpe_set(&mask, dmn))
+			mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(&sb[idx++],
+								   &mask,
+								   inner, rx);
+		else if (dr_mask_is_flex_parser_tnl_geneve_set(&mask, dmn))
+			mlx5dr_ste_build_flex_parser_tnl_geneve(&sb[idx++],
+								&mask,
+								inner, rx);
 
 		if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer))
 			mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx);
@@ -325,7 +352,7 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 		if (DR_MASK_IS_L2_DST(mask.inner, mask.misc, inner))
 			mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx);
 
-		if (ipv6) {
+		if (inner_ipv == DR_RULE_IPV6) {
 			if (dr_mask_is_dst_addr_set(&mask.inner))
 				mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask,
 								 inner, rx);
@@ -373,7 +400,8 @@ static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher,
 		}
 	}
 
-	*num_of_builders = idx;
+	nic_matcher->ste_builder = sb;
+	nic_matcher->num_of_builders_arr[outer_ipv][inner_ipv] = idx;
 
 	return 0;
 }
@@ -524,24 +552,33 @@ static void dr_matcher_uninit(struct mlx5dr_matcher *matcher)
 	}
 }
 
-static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher,
-			       struct mlx5dr_matcher_rx_tx *nic_matcher)
+static int dr_matcher_set_all_ste_builders(struct mlx5dr_matcher *matcher,
+					   struct mlx5dr_matcher_rx_tx *nic_matcher)
 {
 	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
-	int ret, ret_v4, ret_v6;
 
-	ret_v4 = dr_matcher_set_ste_builders(matcher, nic_matcher, false);
-	ret_v6 = dr_matcher_set_ste_builders(matcher, nic_matcher, true);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV4, DR_RULE_IPV4);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV4, DR_RULE_IPV6);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV6, DR_RULE_IPV4);
+	dr_matcher_set_ste_builders(matcher, nic_matcher, DR_RULE_IPV6, DR_RULE_IPV6);
 
-	if (ret_v4 && ret_v6) {
+	if (!nic_matcher->ste_builder) {
 		mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n");
 		return -EINVAL;
 	}
 
-	if (!ret_v4)
-		nic_matcher->ste_builder = nic_matcher->ste_builder4;
-	else
-		nic_matcher->ste_builder = nic_matcher->ste_builder6;
+	return 0;
+}
+
+static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher,
+			       struct mlx5dr_matcher_rx_tx *nic_matcher)
+{
+	struct mlx5dr_domain *dmn = matcher->tbl->dmn;
+	int ret;
+
+	ret = dr_matcher_set_all_ste_builders(matcher, nic_matcher);
+	if (ret)
+		return ret;
 
 	nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool,
 						      DR_CHUNK_SIZE_1,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
index bd1699e62142..32e94d2ee5e4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
@@ -969,12 +969,12 @@ static int dr_rule_destroy_rule(struct mlx5dr_rule *rule)
 	return 0;
 }
 
-static bool dr_rule_is_ipv6(struct mlx5dr_match_param *param)
+static enum mlx5dr_ipv dr_rule_get_ipv(struct mlx5dr_match_spec *spec)
 {
-	return (param->outer.ip_version == 6 ||
-		param->inner.ip_version == 6 ||
-		param->outer.ethertype == ETH_P_IPV6 ||
-		param->inner.ethertype == ETH_P_IPV6);
+	if (spec->ip_version == 6 || spec->ethertype == ETH_P_IPV6)
+		return DR_RULE_IPV6;
+
+	return DR_RULE_IPV4;
 }
 
 static bool dr_rule_skip(enum mlx5dr_domain_type domain,
@@ -1038,7 +1038,8 @@ dr_rule_create_rule_nic(struct mlx5dr_rule *rule,
 
 	ret = mlx5dr_matcher_select_builders(matcher,
 					     nic_matcher,
-					     dr_rule_is_ipv6(param));
+					     dr_rule_get_ipv(&param->outer),
+					     dr_rule_get_ipv(&param->inner));
 	if (ret)
 		goto out_err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
index 3cbf74b44d1f..a5a266983dd3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Mellanox Technologies. */
 
 #include <linux/types.h>
+#include <linux/crc32.h>
 #include "dr_types.h"
 
 #define DR_STE_CRC_POLY 0xEDB88320L
@@ -107,6 +108,13 @@ struct dr_hw_ste_format {
 	u8 mask[DR_STE_SIZE_MASK];
 };
 
+static u32 dr_ste_crc32_calc(const void *input_data, size_t length)
+{
+	u32 crc = crc32(0, input_data, length);
+
+	return htonl(crc);
+}
+
 u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl)
 {
 	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
@@ -128,7 +136,7 @@ u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl)
 		bit = bit >> 1;
 	}
 
-	crc32 = mlx5dr_crc32_slice8_calc(masked, DR_STE_SIZE_TAG);
+	crc32 = dr_ste_crc32_calc(masked, DR_STE_SIZE_TAG);
 	index = crc32 & (htbl->chunk->num_of_entries - 1);
 
 	return index;
@@ -2075,68 +2083,110 @@ void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb,
 	sb->ste_build_tag_func = &dr_ste_build_eth_l4_misc_tag;
 }
 
-static void dr_ste_build_flex_parser_tnl_bit_mask(struct mlx5dr_match_param *value,
-						  bool inner, u8 *bit_mask)
+static void
+dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(struct mlx5dr_match_param *value,
+						bool inner, u8 *bit_mask)
 {
 	struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3;
 
-	if (misc_3_mask->outer_vxlan_gpe_flags ||
-	    misc_3_mask->outer_vxlan_gpe_next_protocol) {
-		MLX5_SET(ste_flex_parser_tnl, bit_mask,
-			 flex_parser_tunneling_header_63_32,
-			 (misc_3_mask->outer_vxlan_gpe_flags << 24) |
-			 (misc_3_mask->outer_vxlan_gpe_next_protocol));
-		misc_3_mask->outer_vxlan_gpe_flags = 0;
-		misc_3_mask->outer_vxlan_gpe_next_protocol = 0;
-	}
-
-	if (misc_3_mask->outer_vxlan_gpe_vni) {
-		MLX5_SET(ste_flex_parser_tnl, bit_mask,
-			 flex_parser_tunneling_header_31_0,
-			 misc_3_mask->outer_vxlan_gpe_vni << 8);
-		misc_3_mask->outer_vxlan_gpe_vni = 0;
-	}
+	DR_STE_SET_MASK_V(flex_parser_tnl_vxlan_gpe, bit_mask,
+			  outer_vxlan_gpe_flags,
+			  misc_3_mask, outer_vxlan_gpe_flags);
+	DR_STE_SET_MASK_V(flex_parser_tnl_vxlan_gpe, bit_mask,
+			  outer_vxlan_gpe_next_protocol,
+			  misc_3_mask, outer_vxlan_gpe_next_protocol);
+	DR_STE_SET_MASK_V(flex_parser_tnl_vxlan_gpe, bit_mask,
+			  outer_vxlan_gpe_vni,
+			  misc_3_mask, outer_vxlan_gpe_vni);
 }
 
-static int dr_ste_build_flex_parser_tnl_tag(struct mlx5dr_match_param *value,
-					    struct mlx5dr_ste_build *sb,
-					    u8 *hw_ste_p)
+static int
+dr_ste_build_flex_parser_tnl_vxlan_gpe_tag(struct mlx5dr_match_param *value,
+					   struct mlx5dr_ste_build *sb,
+					   u8 *hw_ste_p)
 {
 	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
 	struct mlx5dr_match_misc3 *misc3 = &value->misc3;
 	u8 *tag = hw_ste->tag;
 
-	if (misc3->outer_vxlan_gpe_flags ||
-	    misc3->outer_vxlan_gpe_next_protocol) {
-		MLX5_SET(ste_flex_parser_tnl, tag,
-			 flex_parser_tunneling_header_63_32,
-			 (misc3->outer_vxlan_gpe_flags << 24) |
-			 (misc3->outer_vxlan_gpe_next_protocol));
-		misc3->outer_vxlan_gpe_flags = 0;
-		misc3->outer_vxlan_gpe_next_protocol = 0;
-	}
-
-	if (misc3->outer_vxlan_gpe_vni) {
-		MLX5_SET(ste_flex_parser_tnl, tag,
-			 flex_parser_tunneling_header_31_0,
-			 misc3->outer_vxlan_gpe_vni << 8);
-		misc3->outer_vxlan_gpe_vni = 0;
-	}
+	DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag,
+		       outer_vxlan_gpe_flags, misc3,
+		       outer_vxlan_gpe_flags);
+	DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag,
+		       outer_vxlan_gpe_next_protocol, misc3,
+		       outer_vxlan_gpe_next_protocol);
+	DR_STE_SET_TAG(flex_parser_tnl_vxlan_gpe, tag,
+		       outer_vxlan_gpe_vni, misc3,
+		       outer_vxlan_gpe_vni);
 
 	return 0;
 }
 
-void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb,
-				      struct mlx5dr_match_param *mask,
-				      bool inner, bool rx)
+void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb,
+						struct mlx5dr_match_param *mask,
+						bool inner, bool rx)
+{
+	dr_ste_build_flex_parser_tnl_vxlan_gpe_bit_mask(mask, inner,
+							sb->bit_mask);
+
+	sb->rx = rx;
+	sb->inner = inner;
+	sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER;
+	sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
+	sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_vxlan_gpe_tag;
+}
+
+static void
+dr_ste_build_flex_parser_tnl_geneve_bit_mask(struct mlx5dr_match_param *value,
+					     u8 *bit_mask)
 {
-	dr_ste_build_flex_parser_tnl_bit_mask(mask, inner, sb->bit_mask);
+	struct mlx5dr_match_misc *misc_mask = &value->misc;
 
+	DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask,
+			  geneve_protocol_type,
+			  misc_mask, geneve_protocol_type);
+	DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask,
+			  geneve_oam,
+			  misc_mask, geneve_oam);
+	DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask,
+			  geneve_opt_len,
+			  misc_mask, geneve_opt_len);
+	DR_STE_SET_MASK_V(flex_parser_tnl_geneve, bit_mask,
+			  geneve_vni,
+			  misc_mask, geneve_vni);
+}
+
+static int
+dr_ste_build_flex_parser_tnl_geneve_tag(struct mlx5dr_match_param *value,
+					struct mlx5dr_ste_build *sb,
+					u8 *hw_ste_p)
+{
+	struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p;
+	struct mlx5dr_match_misc *misc = &value->misc;
+	u8 *tag = hw_ste->tag;
+
+	DR_STE_SET_TAG(flex_parser_tnl_geneve, tag,
+		       geneve_protocol_type, misc, geneve_protocol_type);
+	DR_STE_SET_TAG(flex_parser_tnl_geneve, tag,
+		       geneve_oam, misc, geneve_oam);
+	DR_STE_SET_TAG(flex_parser_tnl_geneve, tag,
+		       geneve_opt_len, misc, geneve_opt_len);
+	DR_STE_SET_TAG(flex_parser_tnl_geneve, tag,
+		       geneve_vni, misc, geneve_vni);
+
+	return 0;
+}
+
+void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb,
+					     struct mlx5dr_match_param *mask,
+					     bool inner, bool rx)
+{
+	dr_ste_build_flex_parser_tnl_geneve_bit_mask(mask, sb->bit_mask);
 	sb->rx = rx;
 	sb->inner = inner;
 	sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER;
 	sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask);
-	sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_tag;
+	sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_geneve_tag;
 }
 
 static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
index 1cb3769d4e3c..290fe61c33d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h
@@ -106,6 +106,12 @@ enum mlx5dr_action_type {
 	DR_ACTION_TYP_MAX,
 };
 
+enum mlx5dr_ipv {
+	DR_RULE_IPV4,
+	DR_RULE_IPV6,
+	DR_RULE_IPV_MAX,
+};
+
 struct mlx5dr_icm_pool;
 struct mlx5dr_icm_chunk;
 struct mlx5dr_icm_bucket;
@@ -319,9 +325,12 @@ int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb,
 				   struct mlx5dr_match_param *mask,
 				   struct mlx5dr_cmd_caps *caps,
 				   bool inner, bool rx);
-void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb,
-				      struct mlx5dr_match_param *mask,
-				      bool inner, bool rx);
+void mlx5dr_ste_build_flex_parser_tnl_vxlan_gpe(struct mlx5dr_ste_build *sb,
+						struct mlx5dr_match_param *mask,
+						bool inner, bool rx);
+void mlx5dr_ste_build_flex_parser_tnl_geneve(struct mlx5dr_ste_build *sb,
+					     struct mlx5dr_match_param *mask,
+					     bool inner, bool rx);
 void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb,
 				      struct mlx5dr_match_param *mask,
 				      bool inner, bool rx);
@@ -679,11 +688,11 @@ struct mlx5dr_matcher_rx_tx {
 	struct mlx5dr_ste_htbl *s_htbl;
 	struct mlx5dr_ste_htbl *e_anchor;
 	struct mlx5dr_ste_build *ste_builder;
-	struct mlx5dr_ste_build ste_builder4[DR_RULE_MAX_STES];
-	struct mlx5dr_ste_build ste_builder6[DR_RULE_MAX_STES];
+	struct mlx5dr_ste_build ste_builder_arr[DR_RULE_IPV_MAX]
+					       [DR_RULE_IPV_MAX]
+					       [DR_RULE_MAX_STES];
 	u8 num_of_builders;
-	u8 num_of_builders4;
-	u8 num_of_builders6;
+	u8 num_of_builders_arr[DR_RULE_IPV_MAX][DR_RULE_IPV_MAX];
 	u64 default_icm_addr;
 	struct mlx5dr_table_rx_tx *nic_tbl;
 };
@@ -812,7 +821,8 @@ mlx5dr_matcher_supp_flex_parser_icmp_v6(struct mlx5dr_cmd_caps *caps)
 
 int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher,
 				   struct mlx5dr_matcher_rx_tx *nic_matcher,
-				   bool ipv6);
+				   enum mlx5dr_ipv outer_ipv,
+				   enum mlx5dr_ipv inner_ipv);
 
 static inline u32
 mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size)
@@ -962,9 +972,6 @@ void mlx5dr_ste_copy_param(u8 match_criteria,
 			   struct mlx5dr_match_param *set_param,
 			   struct mlx5dr_match_parameters *mask);
 
-void mlx5dr_crc32_init_table(void);
-u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length);
-
 struct mlx5dr_qp {
 	struct mlx5_core_dev *mdev;
 	struct mlx5_wq_qp wq;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
index 596c927220d9..1722f4668269 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h
@@ -548,6 +548,30 @@ struct mlx5_ifc_ste_flex_parser_tnl_bits {
 	u8         reserved_at_40[0x40];
 };
 
+struct mlx5_ifc_ste_flex_parser_tnl_vxlan_gpe_bits {
+	u8         outer_vxlan_gpe_flags[0x8];
+	u8         reserved_at_8[0x10];
+	u8         outer_vxlan_gpe_next_protocol[0x8];
+
+	u8         outer_vxlan_gpe_vni[0x18];
+	u8         reserved_at_38[0x8];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_ste_flex_parser_tnl_geneve_bits {
+	u8         reserved_at_0[0x2];
+	u8         geneve_opt_len[0x6];
+	u8         geneve_oam[0x1];
+	u8         reserved_at_9[0x7];
+	u8         geneve_protocol_type[0x10];
+
+	u8         geneve_vni[0x18];
+	u8         reserved_at_38[0x8];
+
+	u8         reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_ste_general_purpose_bits {
 	u8         general_purpose_lookup_field[0x20];
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 30f7848a6f88..1faac31f74d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -1064,26 +1064,13 @@ int mlx5_core_modify_hca_vport_context(struct mlx5_core_dev *dev,
 
 	ctx = MLX5_ADDR_OF(modify_hca_vport_context_in, in, hca_vport_context);
 	MLX5_SET(hca_vport_context, ctx, field_select, req->field_select);
-	MLX5_SET(hca_vport_context, ctx, sm_virt_aware, req->sm_virt_aware);
-	MLX5_SET(hca_vport_context, ctx, has_smi, req->has_smi);
-	MLX5_SET(hca_vport_context, ctx, has_raw, req->has_raw);
-	MLX5_SET(hca_vport_context, ctx, vport_state_policy, req->policy);
-	MLX5_SET(hca_vport_context, ctx, port_physical_state, req->phys_state);
-	MLX5_SET(hca_vport_context, ctx, vport_state, req->vport_state);
-	MLX5_SET64(hca_vport_context, ctx, port_guid, req->port_guid);
-	MLX5_SET64(hca_vport_context, ctx, node_guid, req->node_guid);
-	MLX5_SET(hca_vport_context, ctx, cap_mask1, req->cap_mask1);
-	MLX5_SET(hca_vport_context, ctx, cap_mask1_field_select, req->cap_mask1_perm);
-	MLX5_SET(hca_vport_context, ctx, cap_mask2, req->cap_mask2);
-	MLX5_SET(hca_vport_context, ctx, cap_mask2_field_select, req->cap_mask2_perm);
-	MLX5_SET(hca_vport_context, ctx, lid, req->lid);
-	MLX5_SET(hca_vport_context, ctx, init_type_reply, req->init_type_reply);
-	MLX5_SET(hca_vport_context, ctx, lmc, req->lmc);
-	MLX5_SET(hca_vport_context, ctx, subnet_timeout, req->subnet_timeout);
-	MLX5_SET(hca_vport_context, ctx, sm_lid, req->sm_lid);
-	MLX5_SET(hca_vport_context, ctx, sm_sl, req->sm_sl);
-	MLX5_SET(hca_vport_context, ctx, qkey_violation_counter, req->qkey_violation_counter);
-	MLX5_SET(hca_vport_context, ctx, pkey_violation_counter, req->pkey_violation_counter);
+	if (req->field_select & MLX5_HCA_VPORT_SEL_STATE_POLICY)
+		MLX5_SET(hca_vport_context, ctx, vport_state_policy,
+			 req->policy);
+	if (req->field_select & MLX5_HCA_VPORT_SEL_PORT_GUID)
+		MLX5_SET64(hca_vport_context, ctx, port_guid, req->port_guid);
+	if (req->field_select & MLX5_HCA_VPORT_SEL_NODE_GUID)
+		MLX5_SET64(hca_vport_context, ctx, node_guid, req->node_guid);
 	err = mlx5_cmd_exec(dev, in, in_sz, out, sizeof(out));
 ex:
 	kfree(in);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
index dd2315ce4441..f2a0e72285ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c
@@ -34,26 +34,6 @@
 #include "wq.h"
 #include "mlx5_core.h"
 
-u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
-{
-	return (u32)wq->fbc.sz_m1 + 1;
-}
-
-u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
-{
-	return wq->fbc.sz_m1 + 1;
-}
-
-u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq)
-{
-	return wq->fbc.log_stride;
-}
-
-u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
-{
-	return (u32)wq->fbc.sz_m1 + 1;
-}
-
 static u32 wq_get_byte_sz(u8 log_sz, u8 log_stride)
 {
 	return ((u32)1 << log_sz) << log_stride;
@@ -96,6 +76,24 @@ err_db_free:
 	return err;
 }
 
+void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides)
+{
+	size_t len;
+	void *wqe;
+
+	if (!net_ratelimit())
+		return;
+
+	nstrides = max_t(u8, nstrides, 1);
+
+	len = nstrides << wq->fbc.log_stride;
+	wqe = mlx5_wq_cyc_get_wqe(wq, ix);
+
+	pr_info("WQE DUMP: WQ size %d WQ cur size %d, WQE index 0x%x, len: %ld\n",
+		mlx5_wq_cyc_get_size(wq), wq->cur_sz, ix, len);
+	print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false);
+}
+
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 55791f71a778..d9a94bc223c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -79,7 +79,7 @@ struct mlx5_wq_ll {
 int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		       void *wqc, struct mlx5_wq_cyc *wq,
 		       struct mlx5_wq_ctrl *wq_ctrl);
-u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq);
+void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides);
 
 int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *qpc, struct mlx5_wq_qp *wq,
@@ -88,16 +88,18 @@ int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		     void *cqc, struct mlx5_cqwq *wq,
 		     struct mlx5_wq_ctrl *wq_ctrl);
-u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq);
-u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq);
 
 int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param,
 		      void *wqc, struct mlx5_wq_ll *wq,
 		      struct mlx5_wq_ctrl *wq_ctrl);
-u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq);
 
 void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl);
 
+static inline u32 mlx5_wq_cyc_get_size(struct mlx5_wq_cyc *wq)
+{
+	return (u32)wq->fbc.sz_m1 + 1;
+}
+
 static inline int mlx5_wq_cyc_is_full(struct mlx5_wq_cyc *wq)
 {
 	return wq->cur_sz == wq->sz;
@@ -168,6 +170,16 @@ static inline int mlx5_wq_cyc_cc_bigger(u16 cc1, u16 cc2)
 	return !equal && !smaller;
 }
 
+static inline u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq)
+{
+	return wq->fbc.sz_m1 + 1;
+}
+
+static inline u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq)
+{
+	return wq->fbc.log_stride;
+}
+
 static inline u32 mlx5_cqwq_ctr2ix(struct mlx5_cqwq *wq, u32 ctr)
 {
 	return ctr & wq->fbc.sz_m1;
@@ -224,6 +236,11 @@ static inline struct mlx5_cqe64 *mlx5_cqwq_get_cqe(struct mlx5_cqwq *wq)
 	return cqe;
 }
 
+static inline u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq)
+{
+	return (u32)wq->fbc.sz_m1 + 1;
+}
+
 static inline int mlx5_wq_ll_is_full(struct mlx5_wq_ll *wq)
 {
 	return wq->cur_sz == wq->fbc.sz_m1;