Merge mlx5-next into rdma for-next

From git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

Required for dependencies in the next patches.

Resolved the conflicts:
 - esw_destroy_offloads_acl_tables() use the newer mlx5_esw_for_all_vports()
   version
 - esw_offloads_steering_init() drop the cap test
 - esw_offloads_init() drop the extra function arguments

* branch 'mlx5-next': (39 commits)
  net/mlx5: Expose device definitions for object events
  net/mlx5: Report EQE data upon CQ completion
  net/mlx5: Report a CQ error event only when a handler was set
  net/mlx5: mlx5_core_create_cq() enhancements
  net/mlx5: Expose the API to register for ANY event
  net/mlx5: Use event mask based on device capabilities
  net/mlx5: Fix mlx5_core_destroy_cq() error flow
  net/mlx5: E-Switch, Handle UC address change in switchdev mode
  net/mlx5: E-Switch, Consider host PF for inline mode and vlan pop
  net/mlx5: E-Switch, Use iterator for vlan and min-inline setups
  net/mlx5: E-Switch, Reg/unreg function changed event at correct stage
  net/mlx5: E-Switch, Consolidate eswitch function number of VFs
  net/mlx5: E-Switch, Refactor eswitch SR-IOV interface
  net/mlx5: Handle host PF vport mac/guid for ECPF
  net/mlx5: E-Switch, Use correct flags when configuring vlan
  net/mlx5: Reduce dependency on enabled_vfs counter and num_vfs
  net/mlx5: Don't handle VF func change if host PF is disabled
  net/mlx5: Limit scope of mlx5_get_next_phys_dev() to PCI PF devices
  net/mlx5: Move pci status reg access mutex to mlx5_pci_init
  net/mlx5: Rename mlx5_pci_dev_type to mlx5_coredev_type
  ...

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

46 files changed, 1214 insertions, 536 deletions

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 22230fd7d741..45f48cde6b9d 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -37,7 +37,7 @@
 #include "mlx5_ib.h"
 #include "srq.h"
 
-static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq)
+static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe)
 {
 	struct ib_cq *ibcq = &to_mibcq(cq)->ibcq;
 
@@ -522,9 +522,9 @@ repoll:
 	case MLX5_CQE_SIG_ERR:
 		sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64;
 
-		read_lock(&dev->mdev->priv.mkey_table.lock);
-		mmkey = __mlx5_mr_lookup(dev->mdev,
-					 mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
+		xa_lock(&dev->mdev->priv.mkey_table);
+		mmkey = xa_load(&dev->mdev->priv.mkey_table,
+				mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
 		mr = to_mibmr(mmkey);
 		get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
 		mr->sig->sig_err_exists = true;
@@ -537,7 +537,7 @@ repoll:
 			     mr->sig->err_item.expected,
 			     mr->sig->err_item.actual);
 
-		read_unlock(&dev->mdev->priv.mkey_table.lock);
+		xa_unlock(&dev->mdev->priv.mkey_table);
 		goto repoll;
 	}
 
@@ -892,6 +892,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	int vector = attr->comp_vector;
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_ib_cq *cq = to_mcq(ibcq);
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	int uninitialized_var(index);
 	int uninitialized_var(inlen);
 	u32 *cqb = NULL;
@@ -954,7 +955,7 @@ int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	if (cq->create_flags & IB_UVERBS_CQ_FLAGS_IGNORE_OVERRUN)
 		MLX5_SET(cqc, cqc, oi, 1);
 
-	err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen);
+	err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen, out, sizeof(out));
 	if (err)
 		goto err_cqb;
 
diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 80b42d069328..931f587dfb8f 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -1043,13 +1043,10 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj,
 				     struct mlx5_ib_dev *dev,
 				     void *in, void *out)
 {
-	struct mlx5_mkey_table *table = &dev->mdev->priv.mkey_table;
 	struct mlx5_ib_devx_mr *devx_mr = &obj->devx_mr;
-	unsigned long flags;
 	struct mlx5_core_mkey *mkey;
 	void *mkc;
 	u8 key;
-	int err;
 
 	mkey = &devx_mr->mmkey;
 	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
@@ -1062,11 +1059,8 @@ static int devx_handle_mkey_indirect(struct devx_obj *obj,
 	mkey->pd = MLX5_GET(mkc, mkc, pd);
 	devx_mr->ndescs = MLX5_GET(mkc, mkc, translations_octword_size);
 
-	write_lock_irqsave(&table->lock, flags);
-	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mkey->key),
-				mkey);
-	write_unlock_irqrestore(&table->lock, flags);
-	return err;
+	return xa_err(xa_store(&dev->mdev->priv.mkey_table,
+			       mlx5_base_mkey(mkey->key), mkey, GFP_KERNEL));
 }
 
 static int devx_handle_mkey_create(struct mlx5_ib_dev *dev,
@@ -1117,12 +1111,8 @@ static void devx_free_indirect_mkey(struct rcu_head *rcu)
  */
 static void devx_cleanup_mkey(struct devx_obj *obj)
 {
-	struct mlx5_mkey_table *table = &obj->mdev->priv.mkey_table;
-	unsigned long flags;
-
-	write_lock_irqsave(&table->lock, flags);
-	radix_tree_delete(&table->tree, mlx5_base_mkey(obj->devx_mr.mmkey.key));
-	write_unlock_irqrestore(&table->lock, flags);
+	xa_erase(&obj->mdev->priv.mkey_table,
+		 mlx5_base_mkey(obj->devx_mr.mmkey.key));
 }
 
 static int devx_obj_cleanup(struct ib_uobject *uobject,
diff --git a/drivers/infiniband/hw/mlx5/flow.c b/drivers/infiniband/hw/mlx5/flow.c
index 1fc302d41a53..b8841355fcd5 100644
--- a/drivers/infiniband/hw/mlx5/flow.c
+++ b/drivers/infiniband/hw/mlx5/flow.c
@@ -65,11 +65,12 @@ static const struct uverbs_attr_spec mlx5_ib_flow_type[] = {
 static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 	struct uverbs_attr_bundle *attrs)
 {
-	struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
+	struct mlx5_flow_context flow_context = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
 	struct mlx5_ib_flow_handler *flow_handler;
 	struct mlx5_ib_flow_matcher *fs_matcher;
 	struct ib_uobject **arr_flow_actions;
 	struct ib_uflow_resources *uflow_res;
+	struct mlx5_flow_act flow_act = {};
 	void *devx_obj;
 	int dest_id, dest_type;
 	void *cmd_in;
@@ -172,17 +173,19 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_CREATE_FLOW)(
 				   arr_flow_actions[i]->object);
 	}
 
-	ret = uverbs_copy_from(&flow_act.flow_tag, attrs,
+	ret = uverbs_copy_from(&flow_context.flow_tag, attrs,
 			       MLX5_IB_ATTR_CREATE_FLOW_TAG);
 	if (!ret) {
-		if (flow_act.flow_tag >= BIT(24)) {
+		if (flow_context.flow_tag >= BIT(24)) {
 			ret = -EINVAL;
 			goto err_out;
 		}
-		flow_act.flags |= FLOW_ACT_HAS_TAG;
+		flow_context.flags |= FLOW_CONTEXT_HAS_TAG;
 	}
 
-	flow_handler = mlx5_ib_raw_fs_rule_add(dev, fs_matcher, &flow_act,
+	flow_handler = mlx5_ib_raw_fs_rule_add(dev, fs_matcher,
+					       &flow_context,
+					       &flow_act,
 					       counter_id,
 					       cmd_in, inlen,
 					       dest_id, dest_type);
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index aa9acebfcc23..f30e0d881368 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -14,9 +14,10 @@ mlx5_ib_set_vport_rep(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	int vport_index;
 
 	ibdev = mlx5_ib_get_uplink_ibdev(dev->priv.eswitch);
-	vport_index = ibdev->free_port++;
+	vport_index = rep->vport_index;
 
 	ibdev->port[vport_index].rep = rep;
+	rep->rep_data[REP_IB].priv = ibdev;
 	write_lock(&ibdev->port[vport_index].roce.netdev_lock);
 	ibdev->port[vport_index].roce.netdev =
 		mlx5_ib_get_rep_netdev(dev->priv.eswitch, rep->vport);
@@ -50,7 +51,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	}
 
 	ibdev->is_rep = true;
-	vport_index = ibdev->free_port++;
+	vport_index = rep->vport_index;
 	ibdev->port[vport_index].rep = rep;
 	ibdev->port[vport_index].roce.netdev =
 		mlx5_ib_get_rep_netdev(dev->priv.eswitch, rep->vport);
@@ -68,15 +69,18 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 static void
 mlx5_ib_vport_rep_unload(struct mlx5_eswitch_rep *rep)
 {
-	struct mlx5_ib_dev *dev;
-
-	if (!rep->rep_data[REP_IB].priv ||
-	    rep->vport != MLX5_VPORT_UPLINK)
-		return;
+	struct mlx5_ib_dev *dev = mlx5_ib_rep_to_dev(rep);
+	struct mlx5_ib_port *port;
 
-	dev = mlx5_ib_rep_to_dev(rep);
-	__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
+	port = &dev->port[rep->vport_index];
+	write_lock(&port->roce.netdev_lock);
+	port->roce.netdev = NULL;
+	write_unlock(&port->roce.netdev_lock);
 	rep->rep_data[REP_IB].priv = NULL;
+	port->rep = NULL;
+
+	if (rep->vport == MLX5_VPORT_UPLINK)
+		__mlx5_ib_remove(dev, dev->profile, MLX5_IB_STAGE_MAX);
 }
 
 static void *mlx5_ib_vport_get_proto_dev(struct mlx5_eswitch_rep *rep)
diff --git a/drivers/infiniband/hw/mlx5/ib_rep.h b/drivers/infiniband/hw/mlx5/ib_rep.h
index 7a917e6d5c09..de43b423bafc 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.h
+++ b/drivers/infiniband/hw/mlx5/ib_rep.h
@@ -28,7 +28,7 @@ struct net_device *mlx5_ib_get_rep_netdev(struct mlx5_eswitch *esw,
 #else /* CONFIG_MLX5_ESWITCH */
 static inline u8 mlx5_ib_eswitch_mode(struct mlx5_eswitch *esw)
 {
-	return SRIOV_NONE;
+	return MLX5_ESWITCH_NONE;
 }
 
 static inline
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 05d2bfcb3d60..9db8c06aa01e 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2669,11 +2669,15 @@ int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
 	}
 }
 
-static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
-			   u32 *match_v, const union ib_flow_spec *ib_spec,
+static int parse_flow_attr(struct mlx5_core_dev *mdev,
+			   struct mlx5_flow_spec *spec,
+			   const union ib_flow_spec *ib_spec,
 			   const struct ib_flow_attr *flow_attr,
 			   struct mlx5_flow_act *action, u32 prev_type)
 {
+	struct mlx5_flow_context *flow_context = &spec->flow_context;
+	u32 *match_c = spec->match_criteria;
+	u32 *match_v = spec->match_value;
 	void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c,
 					   misc_parameters);
 	void *misc_params_v = MLX5_ADDR_OF(fte_match_param, match_v,
@@ -2992,8 +2996,8 @@ static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c,
 		if (ib_spec->flow_tag.tag_id >= BIT(24))
 			return -EINVAL;
 
-		action->flow_tag = ib_spec->flow_tag.tag_id;
-		action->flags |= FLOW_ACT_HAS_TAG;
+		flow_context->flow_tag = ib_spec->flow_tag.tag_id;
+		flow_context->flags |= FLOW_CONTEXT_HAS_TAG;
 		break;
 	case IB_FLOW_SPEC_ACTION_DROP:
 		if (FIELDS_NOT_SUPPORTED(ib_spec->drop,
@@ -3087,7 +3091,8 @@ is_valid_esp_aes_gcm(struct mlx5_core_dev *mdev,
 		return VALID_SPEC_NA;
 
 	return is_crypto && is_ipsec &&
-		(!egress || (!is_drop && !(flow_act->flags & FLOW_ACT_HAS_TAG))) ?
+		(!egress || (!is_drop &&
+			     !(spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG))) ?
 		VALID_SPEC_VALID : VALID_SPEC_INVALID;
 }
 
@@ -3470,6 +3475,37 @@ free:
 	return ret;
 }
 
+static void mlx5_ib_set_rule_source_port(struct mlx5_ib_dev *dev,
+					 struct mlx5_flow_spec *spec,
+					 struct mlx5_eswitch_rep *rep)
+{
+	struct mlx5_eswitch *esw = dev->mdev->priv.eswitch;
+	void *misc;
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters_2);
+
+		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(esw,
+								   rep->vport));
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters_2);
+
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
+
+		MLX5_SET(fte_match_set_misc, misc, source_port, rep->vport);
+
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+	}
+}
+
 static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 						      struct mlx5_ib_flow_prio *ft_prio,
 						      const struct ib_flow_attr *flow_attr,
@@ -3479,7 +3515,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 {
 	struct mlx5_flow_table	*ft = ft_prio->flow_table;
 	struct mlx5_ib_flow_handler *handler;
-	struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG};
+	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_spec *spec;
 	struct mlx5_flow_destination dest_arr[2] = {};
 	struct mlx5_flow_destination *rule_dst = dest_arr;
@@ -3510,8 +3546,7 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	}
 
 	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
-		err = parse_flow_attr(dev->mdev, spec->match_criteria,
-				      spec->match_value,
+		err = parse_flow_attr(dev->mdev, spec,
 				      ib_flow, flow_attr, &flow_act,
 				      prev_type);
 		if (err < 0)
@@ -3525,19 +3560,15 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 		set_underlay_qp(dev, spec, underlay_qpn);
 
 	if (dev->is_rep) {
-		void *misc;
+		struct mlx5_eswitch_rep *rep;
 
-		if (!dev->port[flow_attr->port - 1].rep) {
+		rep = dev->port[flow_attr->port - 1].rep;
+		if (!rep) {
 			err = -EINVAL;
 			goto free;
 		}
-		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-				    misc_parameters);
-		MLX5_SET(fte_match_set_misc, misc, source_port,
-			 dev->port[flow_attr->port - 1].rep->vport);
-		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    misc_parameters);
-		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+		mlx5_ib_set_rule_source_port(dev, spec, rep);
 	}
 
 	spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria);
@@ -3578,11 +3609,11 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 					MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO;
 	}
 
-	if ((flow_act.flags & FLOW_ACT_HAS_TAG)  &&
+	if ((spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG)  &&
 	    (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT ||
 	     flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) {
 		mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n",
-			     flow_act.flow_tag, flow_attr->type);
+			     spec->flow_context.flow_tag, flow_attr->type);
 		err = -EINVAL;
 		goto free;
 	}
@@ -3962,6 +3993,7 @@ _create_raw_flow_rule(struct mlx5_ib_dev *dev,
 		      struct mlx5_ib_flow_prio *ft_prio,
 		      struct mlx5_flow_destination *dst,
 		      struct mlx5_ib_flow_matcher  *fs_matcher,
+		      struct mlx5_flow_context *flow_context,
 		      struct mlx5_flow_act *flow_act,
 		      void *cmd_in, int inlen,
 		      int dst_num)
@@ -3984,6 +4016,7 @@ _create_raw_flow_rule(struct mlx5_ib_dev *dev,
 	memcpy(spec->match_criteria, fs_matcher->matcher_mask.match_params,
 	       fs_matcher->mask_len);
 	spec->match_criteria_enable = fs_matcher->match_criteria_enable;
+	spec->flow_context = *flow_context;
 
 	handler->rule = mlx5_add_flow_rules(ft, spec,
 					    flow_act, dst, dst_num);
@@ -4048,6 +4081,7 @@ static bool raw_fs_is_multicast(struct mlx5_ib_flow_matcher *fs_matcher,
 struct mlx5_ib_flow_handler *
 mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
 			struct mlx5_ib_flow_matcher *fs_matcher,
+			struct mlx5_flow_context *flow_context,
 			struct mlx5_flow_act *flow_act,
 			u32 counter_id,
 			void *cmd_in, int inlen, int dest_id,
@@ -4100,7 +4134,8 @@ mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev,
 		dst_num++;
 	}
 
-	handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, flow_act,
+	handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher,
+					flow_context, flow_act,
 					cmd_in, inlen, dst_num);
 
 	if (IS_ERR(handler)) {
@@ -4472,7 +4507,7 @@ static void mlx5_ib_handle_internal_error(struct mlx5_ib_dev *ibdev)
 	 * lock/unlock above locks Now need to arm all involved CQs.
 	 */
 	list_for_each_entry(mcq, &cq_armed_list, reset_notify) {
-		mcq->comp(mcq);
+		mcq->comp(mcq, NULL);
 	}
 	spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags);
 }
@@ -6802,7 +6837,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	printk_once(KERN_INFO "%s", mlx5_version);
 
 	if (MLX5_ESWITCH_MANAGER(mdev) &&
-	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+	    mlx5_ib_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) {
 		if (!mlx5_core_mp_enabled(mdev))
 			mlx5_ib_register_vport_reps(mdev);
 		return mdev;
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bdb83fc85f94..305d26cdf7f3 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -985,7 +985,6 @@ struct mlx5_ib_dev {
 	u16			devx_whitelist_uid;
 	struct mlx5_srq_table   srq_table;
 	struct mlx5_async_ctx   async_ctx;
-	int			free_port;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
@@ -1330,6 +1329,7 @@ extern const struct uapi_definition mlx5_ib_devx_defs[];
 extern const struct uapi_definition mlx5_ib_flow_defs[];
 struct mlx5_ib_flow_handler *mlx5_ib_raw_fs_rule_add(
 	struct mlx5_ib_dev *dev, struct mlx5_ib_flow_matcher *fs_matcher,
+	struct mlx5_flow_context *flow_context,
 	struct mlx5_flow_act *flow_act, u32 counter_id,
 	void *cmd_in, int inlen, int dest_id, int dest_type);
 bool mlx5_ib_devx_is_flow_dest(void *obj, int *dest_id, int *dest_type);
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 6ac77e09a34a..20ece6e0b2fc 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -130,7 +130,7 @@ static void reg_mr_callback(int status, struct mlx5_async_work *context)
 	struct mlx5_cache_ent *ent = &cache->ent[c];
 	u8 key;
 	unsigned long flags;
-	struct mlx5_mkey_table *table = &dev->mdev->priv.mkey_table;
+	struct xarray *mkeys = &dev->mdev->priv.mkey_table;
 	int err;
 
 	spin_lock_irqsave(&ent->lock, flags);
@@ -158,12 +158,12 @@ static void reg_mr_callback(int status, struct mlx5_async_work *context)
 	ent->size++;
 	spin_unlock_irqrestore(&ent->lock, flags);
 
-	write_lock_irqsave(&table->lock, flags);
-	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->mmkey.key),
-				&mr->mmkey);
+	xa_lock_irqsave(mkeys, flags);
+	err = xa_err(__xa_store(mkeys, mlx5_base_mkey(mr->mmkey.key),
+				&mr->mmkey, GFP_ATOMIC));
+	xa_unlock_irqrestore(mkeys, flags);
 	if (err)
 		pr_err("Error inserting to mkey tree. 0x%x\n", -err);
-	write_unlock_irqrestore(&table->lock, flags);
 
 	if (!completion_done(&ent->compl))
 		complete(&ent->compl);
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 3d18b6ea9efa..5b642d81e617 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -765,7 +765,7 @@ static int pagefault_single_data_segment(struct mlx5_ib_dev *dev,
 	bcnt -= *bytes_committed;
 
 next_mr:
-	mmkey = __mlx5_mr_lookup(dev->mdev, mlx5_base_mkey(key));
+	mmkey = xa_load(&dev->mdev->priv.mkey_table, mlx5_base_mkey(key));
 	if (!mkey_is_eq(mmkey, key)) {
 		mlx5_ib_dbg(dev, "failed to find mkey %x\n", key);
 		ret = -EFAULT;
@@ -1555,9 +1555,9 @@ mlx5_ib_create_pf_eq(struct mlx5_ib_dev *dev, struct mlx5_ib_pf_eq *eq)
 	eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int;
 	param = (struct mlx5_eq_param) {
 		.irq_index = 0,
-		.mask = 1 << MLX5_EVENT_TYPE_PAGE_FAULT,
 		.nent = MLX5_IB_NUM_PF_EQE,
 	};
+	param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT;
 	eq->core = mlx5_eq_create_generic(dev->mdev, &param);
 	if (IS_ERR(eq->core)) {
 		err = PTR_ERR(eq->core);
@@ -1683,8 +1683,8 @@ static void num_pending_prefetch_dec(struct mlx5_ib_dev *dev,
 		struct mlx5_core_mkey *mmkey;
 		struct mlx5_ib_mr *mr;
 
-		mmkey = __mlx5_mr_lookup(dev->mdev,
-					 mlx5_base_mkey(sg_list[i].lkey));
+		mmkey = xa_load(&dev->mdev->priv.mkey_table,
+				mlx5_base_mkey(sg_list[i].lkey));
 		mr = container_of(mmkey, struct mlx5_ib_mr, mmkey);
 		atomic_dec(&mr->num_pending_prefetch);
 	}
@@ -1703,8 +1703,8 @@ static bool num_pending_prefetch_inc(struct ib_pd *pd,
 		struct mlx5_core_mkey *mmkey;
 		struct mlx5_ib_mr *mr;
 
-		mmkey = __mlx5_mr_lookup(dev->mdev,
-					 mlx5_base_mkey(sg_list[i].lkey));
+		mmkey = xa_load(&dev->mdev->priv.mkey_table,
+				mlx5_base_mkey(sg_list[i].lkey));
 		if (!mmkey || mmkey->key != sg_list[i].lkey) {
 			ret = false;
 			break;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 4fbf60fed374..8b7a60ada92c 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -6365,7 +6365,7 @@ static void handle_drain_completion(struct ib_cq *cq,
 		/* Run the CQ handler - this makes sure that the drain WR will
 		 * be processed if wasn't processed yet.
 		 */
-		mcq->mcq.comp(&mcq->mcq);
+		mcq->mcq.comp(&mcq->mcq, NULL);
 	}
 
 	wait_for_completion(&sdrain->done);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cq.c b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
index 713a17ee3751..818edc63e428 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cq.c
@@ -58,7 +58,7 @@ void mlx5_cq_tasklet_cb(unsigned long data)
 	list_for_each_entry_safe(mcq, temp, &ctx->process_list,
 				 tasklet_ctx.list) {
 		list_del_init(&mcq->tasklet_ctx.list);
-		mcq->tasklet_ctx.comp(mcq);
+		mcq->tasklet_ctx.comp(mcq, NULL);
 		mlx5_cq_put(mcq);
 		if (time_after(jiffies, end))
 			break;
@@ -68,7 +68,8 @@ void mlx5_cq_tasklet_cb(unsigned long data)
 		tasklet_schedule(&ctx->task);
 }
 
-static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq)
+static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq,
+				   struct mlx5_eqe *eqe)
 {
 	unsigned long flags;
 	struct mlx5_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
@@ -87,11 +88,10 @@ static void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq)
 }
 
 int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
-			u32 *in, int inlen)
+			u32 *in, int inlen, u32 *out, int outlen)
 {
 	int eqn = MLX5_GET(cqc, MLX5_ADDR_OF(create_cq_in, in, cq_context), c_eqn);
 	u32 dout[MLX5_ST_SZ_DW(destroy_cq_out)];
-	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	u32 din[MLX5_ST_SZ_DW(destroy_cq_in)];
 	struct mlx5_eq_comp *eq;
 	int err;
@@ -100,9 +100,9 @@ int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 	if (IS_ERR(eq))
 		return PTR_ERR(eq);
 
-	memset(out, 0, sizeof(out));
+	memset(out, 0, outlen);
 	MLX5_SET(create_cq_in, in, opcode, MLX5_CMD_OP_CREATE_CQ);
-	err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out));
+	err = mlx5_cmd_exec(dev, in, inlen, out, outlen);
 	if (err)
 		return err;
 
@@ -158,13 +158,8 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq)
 	u32 in[MLX5_ST_SZ_DW(destroy_cq_in)] = {0};
 	int err;
 
-	err = mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
-	if (err)
-		return err;
-
-	err = mlx5_eq_del_cq(&cq->eq->core, cq);
-	if (err)
-		return err;
+	mlx5_eq_del_cq(mlx5_get_async_eq(dev), cq);
+	mlx5_eq_del_cq(&cq->eq->core, cq);
 
 	MLX5_SET(destroy_cq_in, in, opcode, MLX5_CMD_OP_DESTROY_CQ);
 	MLX5_SET(destroy_cq_in, in, cqn, cq->cqn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
index f6b1da99e6c2..5bb6a26ea267 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c
@@ -311,13 +311,20 @@ static u32 mlx5_gen_pci_id(struct mlx5_core_dev *dev)
 /* Must be called with intf_mutex held */
 struct mlx5_core_dev *mlx5_get_next_phys_dev(struct mlx5_core_dev *dev)
 {
-	u32 pci_id = mlx5_gen_pci_id(dev);
 	struct mlx5_core_dev *res = NULL;
 	struct mlx5_core_dev *tmp_dev;
 	struct mlx5_priv *priv;
+	u32 pci_id;
 
+	if (!mlx5_core_is_pf(dev))
+		return NULL;
+
+	pci_id = mlx5_gen_pci_id(dev);
 	list_for_each_entry(priv, &mlx5_dev_list, dev_list) {
 		tmp_dev = container_of(priv, struct mlx5_core_dev, priv);
+		if (!mlx5_core_is_pf(tmp_dev))
+			continue;
+
 		if ((dev != tmp_dev) && (mlx5_gen_pci_id(tmp_dev) == pci_id)) {
 			res = tmp_dev;
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
index a4cf123e3f17..ddf1b87f1bc0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fs_tracepoint.h
@@ -187,6 +187,7 @@ TRACE_EVENT(mlx5_fs_set_fte,
 		__field(u32, index)
 		__field(u32, action)
 		__field(u32, flow_tag)
+		__field(u32, flow_source)
 		__field(u8,  mask_enable)
 		__field(int, new_fte)
 		__array(u32, mask_outer, MLX5_ST_SZ_DW(fte_match_set_lyr_2_4))
@@ -204,7 +205,8 @@ TRACE_EVENT(mlx5_fs_set_fte,
 			   __entry->index = fte->index;
 			   __entry->action = fte->action.action;
 			   __entry->mask_enable = __entry->fg->mask.match_criteria_enable;
-			   __entry->flow_tag = fte->action.flow_tag;
+			   __entry->flow_tag = fte->flow_context.flow_tag;
+			   __entry->flow_source = fte->flow_context.flow_source;
 			   memcpy(__entry->mask_outer,
 				  MLX5_ADDR_OF(fte_match_param,
 					       &__entry->fg->mask.match_criteria,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index cc6797e24571..c97036792f4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -781,7 +781,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi, bool xmit_more);
 
 void mlx5e_trigger_irq(struct mlx5e_icosq *sq);
-void mlx5e_completion_event(struct mlx5_core_cq *mcq);
+void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe);
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
index 554672edf8c3..8dd31b5c740c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c
@@ -680,7 +680,7 @@ static void mlx5e_dcbnl_getpermhwaddr(struct net_device *netdev,
 
 	memset(perm_addr, 0xff, MAX_ADDR_LEN);
 
-	mlx5_query_nic_vport_mac_address(priv->mdev, 0, perm_addr);
+	mlx5_query_mac_address(priv->mdev, perm_addr);
 }
 
 static void mlx5e_dcbnl_setpgtccfgtx(struct net_device *netdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 4421c10f58ae..839662644ed3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -426,7 +426,7 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv,
 	}
 
 	spec->match_criteria_enable = (!outer_header_zero(spec->match_criteria));
-	flow_act.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
+	spec->flow_context.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG;
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dst, dst ? 1 : 0);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a8e8350b38aa..2c5275b46797 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1518,6 +1518,7 @@ static void mlx5e_free_cq(struct mlx5e_cq *cq)
 
 static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 {
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	struct mlx5_core_dev *mdev = cq->mdev;
 	struct mlx5_core_cq *mcq = &cq->mcq;
 
@@ -1552,7 +1553,7 @@ static int mlx5e_create_cq(struct mlx5e_cq *cq, struct mlx5e_cq_param *param)
 					    MLX5_ADAPTER_PAGE_SHIFT);
 	MLX5_SET64(cqc, cqc, dbr_addr,      cq->wq_ctrl.db.dma);
 
-	err = mlx5_core_create_cq(mdev, mcq, in, inlen);
+	err = mlx5_core_create_cq(mdev, mcq, in, inlen, out, sizeof(out));
 
 	kvfree(in);
 
@@ -4590,7 +4591,7 @@ static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	mlx5_query_nic_vport_mac_address(priv->mdev, 0, netdev->dev_addr);
+	mlx5_query_mac_address(priv->mdev, netdev->dev_addr);
 	if (is_zero_ether_addr(netdev->dev_addr) &&
 	    !MLX5_CAP_GEN(priv->mdev, vport_group_manager)) {
 		eth_hw_addr_random(netdev);
@@ -5133,7 +5134,7 @@ static void *mlx5e_add(struct mlx5_core_dev *mdev)
 
 #ifdef CONFIG_MLX5_ESWITCH
 	if (MLX5_ESWITCH_MANAGER(mdev) &&
-	    mlx5_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) {
+	    mlx5_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) {
 		mlx5e_rep_register_vport_reps(mdev);
 		return mdev;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 51066f27ef1e..dfd8c5726871 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -408,7 +408,7 @@ static int mlx5e_rep_get_port_parent_id(struct net_device *dev,
 	struct mlx5e_priv *uplink_priv = NULL;
 	struct net_device *uplink_dev;
 
-	if (esw->mode == SRIOV_NONE)
+	if (esw->mode == MLX5_ESWITCH_NONE)
 		return -EOPNOTSUPP;
 
 	uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH);
@@ -436,7 +436,7 @@ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw,
 	struct mlx5e_rep_sq *rep_sq, *tmp;
 	struct mlx5e_rep_priv *rpriv;
 
-	if (esw->mode != SRIOV_OFFLOADS)
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return;
 
 	rpriv = mlx5e_rep_to_rep_priv(rep);
@@ -457,7 +457,7 @@ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
 	int err;
 	int i;
 
-	if (esw->mode != SRIOV_OFFLOADS)
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return 0;
 
 	rpriv = mlx5e_rep_to_rep_priv(rep);
@@ -1412,7 +1412,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev)
 		SET_NETDEV_DEV(netdev, mdev->device);
 		netdev->netdev_ops = &mlx5e_netdev_ops_uplink_rep;
 		/* we want a persistent mac for the uplink rep */
-		mlx5_query_nic_vport_mac_address(mdev, 0, netdev->dev_addr);
+		mlx5_query_mac_address(mdev, netdev->dev_addr);
 		netdev->ethtool_ops = &mlx5e_uplink_rep_ethtool_ops;
 #ifdef CONFIG_MLX5_CORE_EN_DCB
 		if (MLX5_CAP_GEN(mdev, qos))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index e40c60d1631f..af91b0f904b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -716,19 +716,22 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv,
 		      struct mlx5e_tc_flow *flow,
 		      struct netlink_ext_ack *extack)
 {
+	struct mlx5_flow_context *flow_context = &parse_attr->spec.flow_context;
 	struct mlx5_nic_flow_attr *attr = flow->nic_attr;
 	struct mlx5_core_dev *dev = priv->mdev;
 	struct mlx5_flow_destination dest[2] = {};
 	struct mlx5_flow_act flow_act = {
 		.action = attr->action,
-		.flow_tag = attr->flow_tag,
 		.reformat_id = 0,
-		.flags    = FLOW_ACT_HAS_TAG | FLOW_ACT_NO_APPEND,
+		.flags    = FLOW_ACT_NO_APPEND,
 	};
 	struct mlx5_fc *counter = NULL;
 	bool table_created = false;
 	int err, dest_ix = 0;
 
+	flow_context->flags |= FLOW_CONTEXT_HAS_TAG;
+	flow_context->flow_tag = attr->flow_tag;
+
 	if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) {
 		err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack);
 		if (err) {
@@ -3349,7 +3352,7 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 	if (!tc_can_offload_extack(priv->netdev, f->common.extack))
 		return -EOPNOTSUPP;
 
-	if (esw && esw->mode == SRIOV_OFFLOADS)
+	if (esw && esw->mode == MLX5_ESWITCH_OFFLOADS)
 		err = mlx5e_add_fdb_flow(priv, f, flow_flags,
 					 filter_dev, flow);
 	else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index f9862bf75491..c665ae0f22bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -136,7 +136,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-void mlx5e_completion_event(struct mlx5_core_cq *mcq)
+void mlx5e_completion_event(struct mlx5_core_cq *mcq, struct mlx5_eqe *eqe)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 58fff2f39b38..41f25ea2e8d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -153,7 +153,7 @@ static int mlx5_eq_comp_int(struct notifier_block *nb,
 		cq = mlx5_eq_cq_get(eq, cqn);
 		if (likely(cq)) {
 			++cq->arm_sn;
-			cq->comp(cq);
+			cq->comp(cq, eqe);
 			mlx5_cq_put(cq);
 		} else {
 			mlx5_core_warn(eq->dev, "Completion event for bogus CQ 0x%x\n", cqn);
@@ -256,6 +256,7 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	int inlen;
 	u32 *in;
 	int err;
+	int i;
 
 	/* Init CQ table */
 	memset(cq_table, 0, sizeof(*cq_table));
@@ -283,10 +284,12 @@ create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
 	mlx5_fill_page_array(&eq->buf, pas);
 
 	MLX5_SET(create_eq_in, in, opcode, MLX5_CMD_OP_CREATE_EQ);
-	if (!param->mask && MLX5_CAP_GEN(dev, log_max_uctx))
+	if (!param->mask[0] && MLX5_CAP_GEN(dev, log_max_uctx))
 		MLX5_SET(create_eq_in, in, uid, MLX5_SHARED_RESOURCE_UID);
 
-	MLX5_SET64(create_eq_in, in, event_bitmask, param->mask);
+	for (i = 0; i < 4; i++)
+		MLX5_ARRAY_SET64(create_eq_in, in, event_bitmask, i,
+				 param->mask[i]);
 
 	eqc = MLX5_ADDR_OF(create_eq_in, in, eq_context_entry);
 	MLX5_SET(eqc, eqc, log_eq_size, ilog2(eq->nent));
@@ -389,7 +392,7 @@ int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	return err;
 }
 
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
+void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 {
 	struct mlx5_cq_table *table = &eq->cq_table;
 	struct mlx5_core_cq *tmp;
@@ -399,16 +402,14 @@ int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq)
 	spin_unlock(&table->lock);
 
 	if (!tmp) {
-		mlx5_core_warn(eq->dev, "cq 0x%x not found in eq 0x%x tree\n", eq->eqn, cq->cqn);
-		return -ENOENT;
-	}
-
-	if (tmp != cq) {
-		mlx5_core_warn(eq->dev, "corruption on cqn 0x%x in eq 0x%x\n", eq->eqn, cq->cqn);
-		return -EINVAL;
+		mlx5_core_dbg(eq->dev, "cq 0x%x not found in eq 0x%x tree\n",
+			      eq->eqn, cq->cqn);
+		return;
 	}
 
-	return 0;
+	if (tmp != cq)
+		mlx5_core_dbg(eq->dev, "corruption on cqn 0x%x in eq 0x%x\n",
+			      eq->eqn, cq->cqn);
 }
 
 int mlx5_eq_table_init(struct mlx5_core_dev *dev)
@@ -502,14 +503,31 @@ static int cq_err_event_notifier(struct notifier_block *nb,
 		return NOTIFY_OK;
 	}
 
-	cq->event(cq, type);
+	if (cq->event)
+		cq->event(cq, type);
 
 	mlx5_cq_put(cq);
 
 	return NOTIFY_OK;
 }
 
-static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
+static void gather_user_async_events(struct mlx5_core_dev *dev, u64 mask[4])
+{
+	__be64 *user_unaffiliated_events;
+	__be64 *user_affiliated_events;
+	int i;
+
+	user_affiliated_events =
+		MLX5_CAP_DEV_EVENT(dev, user_affiliated_events);
+	user_unaffiliated_events =
+		MLX5_CAP_DEV_EVENT(dev, user_unaffiliated_events);
+
+	for (i = 0; i < 4; i++)
+		mask[i] |= be64_to_cpu(user_affiliated_events[i] |
+				       user_unaffiliated_events[i]);
+}
+
+static void gather_async_events_mask(struct mlx5_core_dev *dev, u64 mask[4])
 {
 	u64 async_event_mask = MLX5_ASYNC_EVENT_MASK;
 
@@ -546,7 +564,10 @@ static u64 gather_async_events_mask(struct mlx5_core_dev *dev)
 		async_event_mask |=
 			(1ull << MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED);
 
-	return async_event_mask;
+	mask[0] = async_event_mask;
+
+	if (MLX5_CAP_GEN(dev, event_cap))
+		gather_user_async_events(dev, mask);
 }
 
 static int create_async_eqs(struct mlx5_core_dev *dev)
@@ -561,9 +582,10 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	table->cmd_eq.irq_nb.notifier_call = mlx5_eq_async_int;
 	param = (struct mlx5_eq_param) {
 		.irq_index = 0,
-		.mask = 1ull << MLX5_EVENT_TYPE_CMD,
 		.nent = MLX5_NUM_CMD_EQE,
 	};
+
+	param.mask[0] = 1ull << MLX5_EVENT_TYPE_CMD;
 	err = create_async_eq(dev, &table->cmd_eq.core, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
@@ -579,9 +601,10 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	table->async_eq.irq_nb.notifier_call = mlx5_eq_async_int;
 	param = (struct mlx5_eq_param) {
 		.irq_index = 0,
-		.mask = gather_async_events_mask(dev),
 		.nent = MLX5_NUM_ASYNC_EQE,
 	};
+
+	gather_async_events_mask(dev, param.mask);
 	err = create_async_eq(dev, &table->async_eq.core, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
@@ -597,9 +620,10 @@ static int create_async_eqs(struct mlx5_core_dev *dev)
 	table->pages_eq.irq_nb.notifier_call = mlx5_eq_async_int;
 	param = (struct mlx5_eq_param) {
 		.irq_index = 0,
-		.mask =  1 << MLX5_EVENT_TYPE_PAGE_REQUEST,
 		.nent = /* TODO: sriov max_vf + */ 1,
 	};
+
+	param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_REQUEST;
 	err = create_async_eq(dev, &table->pages_eq.core, &param);
 	if (err) {
 		mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
@@ -791,7 +815,6 @@ static int create_comp_eqs(struct mlx5_core_dev *dev)
 		eq->irq_nb.notifier_call = mlx5_eq_comp_int;
 		param = (struct mlx5_eq_param) {
 			.irq_index = vecidx,
-			.mask = 0,
 			.nent = nent,
 		};
 		err = create_map_eq(dev, &eq->core, &param);
@@ -927,6 +950,7 @@ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 
 	return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb);
 }
+EXPORT_SYMBOL(mlx5_eq_notifier_register);
 
 int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 {
@@ -937,3 +961,4 @@ int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb)
 
 	return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb);
 }
+EXPORT_SYMBOL(mlx5_eq_notifier_unregister);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index ea4c8dc93ce4..c53020605b0d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -134,6 +134,30 @@ static int modify_esw_vport_context_cmd(struct mlx5_core_dev *dev, u16 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)
+{
+	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);
+	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)
 {
@@ -473,7 +497,7 @@ static int esw_add_uc_addr(struct mlx5_eswitch *esw, struct vport_addr *vaddr)
 
 fdb_add:
 	/* SRIOV is enabled: Forward UC MAC to vport */
-	if (esw->fdb_table.legacy.fdb && esw->mode == SRIOV_LEGACY)
+	if (esw->fdb_table.legacy.fdb && esw->mode == MLX5_ESWITCH_LEGACY)
 		vaddr->flow_rule = esw_fdb_set_vport_rule(esw, mac, vport);
 
 	esw_debug(esw->dev, "\tADDED UC MAC: vport[%d] %pM fr(%p)\n",
@@ -873,7 +897,7 @@ static void esw_vport_change_handle_locked(struct mlx5_vport *vport)
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
 	u8 mac[ETH_ALEN];
 
-	mlx5_query_nic_vport_mac_address(dev, vport->vport, mac);
+	mlx5_query_nic_vport_mac_address(dev, vport->vport, true, mac);
 	esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n",
 		  vport->vport, mac);
 
@@ -939,7 +963,7 @@ int esw_vport_enable_egress_acl(struct mlx5_eswitch *esw,
 		  vport->vport, MLX5_CAP_ESW_EGRESS_ACL(dev, log_max_ft_size));
 
 	root_ns = mlx5_get_flow_vport_acl_namespace(dev, MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-						    vport->vport);
+			mlx5_eswitch_vport_num_to_index(esw, vport->vport));
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch egress flow namespace for vport (%d)\n", vport->vport);
 		return -EOPNOTSUPP;
@@ -1057,7 +1081,7 @@ int esw_vport_enable_ingress_acl(struct mlx5_eswitch *esw,
 		  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,
-						    vport->vport);
+			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;
@@ -1168,6 +1192,8 @@ void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw,
 
 	vport->ingress.drop_rule = NULL;
 	vport->ingress.allow_rule = NULL;
+
+	esw_vport_del_ingress_acl_modify_metadata(esw, vport);
 }
 
 void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw,
@@ -1527,6 +1553,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 				 struct mlx5_vport *vport)
 {
 	u16 vport_num = vport->vport;
+	int flags;
 
 	if (esw->manager_vport == vport_num)
 		return;
@@ -1544,11 +1571,13 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 						vport->info.node_guid);
 	}
 
+	flags = (vport->info.vlan || vport->info.qos) ?
+		SET_VLAN_STRIP | SET_VLAN_INSERT : 0;
 	modify_esw_vport_cvlan(esw->dev, vport_num, vport->info.vlan, vport->info.qos,
-			       (vport->info.vlan || vport->info.qos));
+			       flags);
 
 	/* Only legacy mode needs ACLs */
-	if (esw->mode == SRIOV_LEGACY) {
+	if (esw->mode == MLX5_ESWITCH_LEGACY) {
 		esw_vport_ingress_config(esw, vport);
 		esw_vport_egress_config(esw, vport);
 	}
@@ -1600,7 +1629,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport,
 	esw_debug(esw->dev, "Enabling VPORT(%d)\n", vport_num);
 
 	/* Create steering drop counters for ingress and egress ACLs */
-	if (vport_num && esw->mode == SRIOV_LEGACY)
+	if (vport_num && esw->mode == MLX5_ESWITCH_LEGACY)
 		esw_vport_create_drop_counters(vport);
 
 	/* Restore old vport configuration */
@@ -1654,7 +1683,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw,
 	vport->enabled_events = 0;
 	esw_vport_disable_qos(esw, vport);
 	if (esw->manager_vport != vport_num &&
-	    esw->mode == SRIOV_LEGACY) {
+	    esw->mode == MLX5_ESWITCH_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
 					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					      vport_num, 1,
@@ -1696,49 +1725,61 @@ int mlx5_esw_query_functions(struct mlx5_core_dev *dev, u32 *out, int outlen)
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen);
 }
 
+static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw)
+{
+	MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
+	mlx5_eq_notifier_register(esw->dev, &esw->nb);
+
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) {
+		MLX5_NB_INIT(&esw->esw_funcs.nb, mlx5_esw_funcs_changed_handler,
+			     ESW_FUNCTIONS_CHANGED);
+		mlx5_eq_notifier_register(esw->dev, &esw->esw_funcs.nb);
+	}
+}
+
+static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw)
+{
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev))
+		mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
+
+	mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+
+	flush_workqueue(esw->work_queue);
+}
+
 /* Public E-Switch API */
 #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev))
 
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
+int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode)
 {
 	struct mlx5_vport *vport;
-	int total_nvports = 0;
 	int err;
 	int i, enabled_events;
 
 	if (!ESW_ALLOWED(esw) ||
 	    !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) {
-		esw_warn(esw->dev, "E-Switch FDB is not supported, aborting ...\n");
+		esw_warn(esw->dev, "FDB is not supported, aborting ...\n");
 		return -EOPNOTSUPP;
 	}
 
 	if (!MLX5_CAP_ESW_INGRESS_ACL(esw->dev, ft_support))
-		esw_warn(esw->dev, "E-Switch ingress ACL is not supported by FW\n");
+		esw_warn(esw->dev, "ingress ACL is not supported by FW\n");
 
 	if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support))
-		esw_warn(esw->dev, "E-Switch engress ACL is not supported by FW\n");
-
-	esw_info(esw->dev, "E-Switch enable SRIOV: nvfs(%d) mode (%d)\n", nvfs, mode);
-
-	if (mode == SRIOV_OFFLOADS) {
-		if (mlx5_core_is_ecpf_esw_manager(esw->dev))
-			total_nvports = esw->total_vports;
-		else
-			total_nvports = nvfs + MLX5_SPECIAL_VPORTS(esw->dev);
-	}
+		esw_warn(esw->dev, "engress ACL is not supported by FW\n");
 
 	esw->mode = mode;
 
 	mlx5_lag_update(esw->dev);
 
-	if (mode == SRIOV_LEGACY) {
+	if (mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_create_legacy_table(esw);
 		if (err)
 			goto abort;
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
-		err = esw_offloads_init(esw, nvfs, total_nvports);
+		err = esw_offloads_init(esw);
 	}
 
 	if (err)
@@ -1748,11 +1789,8 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	if (err)
 		esw_warn(esw->dev, "Failed to create eswitch TSAR");
 
-	/* Don't enable vport events when in SRIOV_OFFLOADS mode, since:
-	 * 1. L2 table (MPFS) is programmed by PF/VF representors netdevs set_rx_mode
-	 * 2. FDB/Eswitch is programmed by user space tools
-	 */
-	enabled_events = (mode == SRIOV_LEGACY) ? SRIOV_VPORT_EVENTS : 0;
+	enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS :
+		UC_ADDR_CHANGE;
 
 	/* Enable PF vport */
 	vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF);
@@ -1765,22 +1803,21 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	}
 
 	/* Enable VF vports */
-	mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs)
+	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs)
 		esw_enable_vport(esw, vport, enabled_events);
 
-	if (mode == SRIOV_LEGACY) {
-		MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE);
-		mlx5_eq_notifier_register(esw->dev, &esw->nb);
-	}
+	mlx5_eswitch_event_handlers_register(esw);
+
+	esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n",
+		 mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+		 esw->esw_funcs.num_vfs, esw->enabled_vports);
 
-	esw_info(esw->dev, "SRIOV enabled: active vports(%d)\n",
-		 esw->enabled_vports);
 	return 0;
 
 abort:
-	esw->mode = SRIOV_NONE;
+	esw->mode = MLX5_ESWITCH_NONE;
 
-	if (mode == SRIOV_OFFLOADS) {
+	if (mode == MLX5_ESWITCH_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 	}
@@ -1788,23 +1825,22 @@ abort:
 	return err;
 }
 
-void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw)
 {
 	struct esw_mc_addr *mc_promisc;
 	struct mlx5_vport *vport;
 	int old_mode;
 	int i;
 
-	if (!ESW_ALLOWED(esw) || esw->mode == SRIOV_NONE)
+	if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE)
 		return;
 
-	esw_info(esw->dev, "disable SRIOV: active vports(%d) mode(%d)\n",
-		 esw->enabled_vports, esw->mode);
+	esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), active vports(%d)\n",
+		 esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS",
+		 esw->esw_funcs.num_vfs, esw->enabled_vports);
 
 	mc_promisc = &esw->mc_promisc;
-
-	if (esw->mode == SRIOV_LEGACY)
-		mlx5_eq_notifier_unregister(esw->dev, &esw->nb);
+	mlx5_eswitch_event_handlers_unregister(esw);
 
 	mlx5_esw_for_all_vports(esw, i, vport)
 		esw_disable_vport(esw, vport);
@@ -1814,17 +1850,17 @@ void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw)
 
 	esw_destroy_tsar(esw);
 
-	if (esw->mode == SRIOV_LEGACY)
+	if (esw->mode == MLX5_ESWITCH_LEGACY)
 		esw_destroy_legacy_table(esw);
-	else if (esw->mode == SRIOV_OFFLOADS)
+	else if (esw->mode == MLX5_ESWITCH_OFFLOADS)
 		esw_offloads_cleanup(esw);
 
 	old_mode = esw->mode;
-	esw->mode = SRIOV_NONE;
+	esw->mode = MLX5_ESWITCH_NONE;
 
 	mlx5_lag_update(esw->dev);
 
-	if (old_mode == SRIOV_OFFLOADS) {
+	if (old_mode == MLX5_ESWITCH_OFFLOADS) {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH);
 	}
@@ -1852,6 +1888,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 
 	esw->dev = dev;
 	esw->manager_vport = mlx5_eswitch_manager_vport(dev);
+	esw->first_host_vport = mlx5_eswitch_first_host_vport_num(dev);
 
 	esw->work_queue = create_singlethread_workqueue("mlx5_esw_wq");
 	if (!esw->work_queue) {
@@ -1885,7 +1922,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 	}
 
 	esw->enabled_vports = 0;
-	esw->mode = SRIOV_NONE;
+	esw->mode = MLX5_ESWITCH_NONE;
 	esw->offloads.inline_mode = MLX5_INLINE_MODE_NONE;
 	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, reformat) &&
 	    MLX5_CAP_ESW_FLOWTABLE_FDB(dev, decap))
@@ -1955,7 +1992,7 @@ int mlx5_eswitch_set_vport_mac(struct mlx5_eswitch *esw,
 
 	ether_addr_copy(evport->info.mac, mac);
 	evport->info.node_guid = node_guid;
-	if (evport->enabled && esw->mode == SRIOV_LEGACY)
+	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 
 unlock:
@@ -2039,7 +2076,7 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 
 	evport->info.vlan = vlan;
 	evport->info.qos = qos;
-	if (evport->enabled && esw->mode == SRIOV_LEGACY) {
+	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) {
 		err = esw_vport_ingress_config(esw, evport);
 		if (err)
 			goto unlock;
@@ -2081,7 +2118,7 @@ int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw,
 		mlx5_core_warn(esw->dev,
 			       "Spoofchk in set while MAC is invalid, vport(%d)\n",
 			       evport->vport);
-	if (evport->enabled && esw->mode == SRIOV_LEGACY)
+	if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY)
 		err = esw_vport_ingress_config(esw, evport);
 	if (err)
 		evport->info.spoofchk = pschk;
@@ -2177,7 +2214,7 @@ int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting)
 		return -EPERM;
 
 	mutex_lock(&esw->state_lock);
-	if (esw->mode != SRIOV_LEGACY) {
+	if (esw->mode != MLX5_ESWITCH_LEGACY) {
 		err = -EOPNOTSUPP;
 		goto out;
 	}
@@ -2200,7 +2237,7 @@ int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
 		return -EPERM;
 
 	mutex_lock(&esw->state_lock);
-	if (esw->mode != SRIOV_LEGACY) {
+	if (esw->mode != MLX5_ESWITCH_LEGACY) {
 		err = -EOPNOTSUPP;
 		goto out;
 	}
@@ -2343,7 +2380,7 @@ static int mlx5_eswitch_query_vport_drop_stats(struct mlx5_core_dev *dev,
 	u64 bytes = 0;
 	int err = 0;
 
-	if (!vport->enabled || esw->mode != SRIOV_LEGACY)
+	if (!vport->enabled || esw->mode != MLX5_ESWITCH_LEGACY)
 		return 0;
 
 	if (vport->egress.drop_counter)
@@ -2453,7 +2490,7 @@ free_out:
 
 u8 mlx5_eswitch_mode(struct mlx5_eswitch *esw)
 {
-	return ESW_ALLOWED(esw) ? esw->mode : SRIOV_NONE;
+	return ESW_ALLOWED(esw) ? esw->mode : MLX5_ESWITCH_NONE;
 }
 EXPORT_SYMBOL_GPL(mlx5_eswitch_mode);
 
@@ -2470,10 +2507,10 @@ EXPORT_SYMBOL(mlx5_eswitch_get_encap_mode);
 
 bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
 {
-	if ((dev0->priv.eswitch->mode == SRIOV_NONE &&
-	     dev1->priv.eswitch->mode == SRIOV_NONE) ||
-	    (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
-	     dev1->priv.eswitch->mode == SRIOV_OFFLOADS))
+	if ((dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+	     dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE) ||
+	    (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+	     dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS))
 		return true;
 
 	return false;
@@ -2482,6 +2519,24 @@ bool mlx5_esw_lag_prereq(struct mlx5_core_dev *dev0, struct mlx5_core_dev *dev1)
 bool mlx5_esw_multipath_prereq(struct mlx5_core_dev *dev0,
 			       struct mlx5_core_dev *dev1)
 {
-	return (dev0->priv.eswitch->mode == SRIOV_OFFLOADS &&
-		dev1->priv.eswitch->mode == SRIOV_OFFLOADS);
+	return (dev0->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS &&
+		dev1->priv.eswitch->mode == MLX5_ESWITCH_OFFLOADS);
+}
+
+void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs)
+{
+	u32 out[MLX5_ST_SZ_DW(query_esw_functions_out)] = {};
+	int err;
+
+	WARN_ON_ONCE(esw->mode != MLX5_ESWITCH_NONE);
+
+	if (!mlx5_core_is_ecpf_esw_manager(esw->dev)) {
+		esw->esw_funcs.num_vfs = num_vfs;
+		return;
+	}
+
+	err = mlx5_esw_query_functions(esw->dev, out, sizeof(out));
+	if (!err)
+		esw->esw_funcs.num_vfs = MLX5_GET(query_esw_functions_out, out,
+						  host_params_context.host_num_of_vfs);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index c9589f12c839..3fe57d0ca216 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -68,6 +68,8 @@ struct vport_ingress {
 	struct mlx5_flow_group *allow_spoofchk_only_grp;
 	struct mlx5_flow_group *allow_untagged_only_grp;
 	struct mlx5_flow_group *drop_grp;
+	int modify_metadata_id;
+	struct mlx5_flow_handle  *modify_metadata_rule;
 	struct mlx5_flow_handle  *allow_rule;
 	struct mlx5_flow_handle  *drop_rule;
 	struct mlx5_fc           *drop_counter;
@@ -196,6 +198,10 @@ struct mlx5_esw_functions {
 	u16			num_vfs;
 };
 
+enum {
+	MLX5_ESWITCH_VPORT_MATCH_METADATA = BIT(0),
+};
+
 struct mlx5_eswitch {
 	struct mlx5_core_dev    *dev;
 	struct mlx5_nb          nb;
@@ -203,6 +209,7 @@ struct mlx5_eswitch {
 	struct hlist_head       mc_table[MLX5_L2_ADDR_HASH_SIZE];
 	struct workqueue_struct *work_queue;
 	struct mlx5_vport       *vports;
+	u32 flags;
 	int                     total_vports;
 	int                     enabled_vports;
 	/* Synchronize between vport change events
@@ -220,12 +227,12 @@ struct mlx5_eswitch {
 	int                     mode;
 	int                     nvports;
 	u16                     manager_vport;
+	u16                     first_host_vport;
 	struct mlx5_esw_functions esw_funcs;
 };
 
 void esw_offloads_cleanup(struct mlx5_eswitch *esw);
-int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
-		      int total_nvports);
+int esw_offloads_init(struct mlx5_eswitch *esw);
 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,
@@ -240,12 +247,14 @@ 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);
 
 /* E-Switch API */
 int mlx5_eswitch_init(struct mlx5_core_dev *dev);
 void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw);
-int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode);
-void mlx5_eswitch_disable_sriov(struct mlx5_eswitch *esw);
+int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode);
+void mlx5_eswitch_disable(struct mlx5_eswitch *esw);
 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,
@@ -267,6 +276,11 @@ 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,
+					  void *in, int inlen);
+int mlx5_eswitch_query_esw_vport_context(struct mlx5_eswitch *esw, u16 vport,
+					 void *out, int outlen);
+
 struct mlx5_flow_spec;
 struct mlx5_esw_flow_attr;
 
@@ -356,7 +370,7 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode);
 int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 					 struct netlink_ext_ack *extack);
 int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode);
-int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode);
+int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, u8 *mode);
 int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 					enum devlink_eswitch_encap_mode encap,
 					struct netlink_ext_ack *extack);
@@ -409,6 +423,12 @@ static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
 		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
 }
 
+static inline u16 mlx5_eswitch_first_host_vport_num(struct mlx5_core_dev *dev)
+{
+	return mlx5_core_is_ecpf_esw_manager(dev) ?
+		MLX5_VPORT_PF : MLX5_VPORT_FIRST_VF;
+}
+
 static inline bool mlx5_eswitch_is_funcs_handler(struct mlx5_core_dev *dev)
 {
 	/* Ideally device should have the functions changed supported
@@ -505,15 +525,39 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw);
 #define mlx5_esw_for_each_vf_vport_num_reverse(esw, vport, nvfs)	\
 	for ((vport) = (nvfs); (vport) >= MLX5_VPORT_FIRST_VF; (vport)--)
 
+/* Includes host PF (vport 0) if it's not esw manager. */
+#define mlx5_esw_for_each_host_func_rep(esw, i, rep, nvfs)	\
+	for ((i) = (esw)->first_host_vport;			\
+	     (rep) = &(esw)->offloads.vport_reps[i],		\
+	     (i) <= (nvfs); (i)++)
+
+#define mlx5_esw_for_each_host_func_rep_reverse(esw, i, rep, nvfs)	\
+	for ((i) = (nvfs);						\
+	     (rep) = &(esw)->offloads.vport_reps[i],			\
+	     (i) >= (esw)->first_host_vport; (i)--)
+
+#define mlx5_esw_for_each_host_func_vport(esw, vport, nvfs)	\
+	for ((vport) = (esw)->first_host_vport;			\
+	     (vport) <= (nvfs); (vport)++)
+
+#define mlx5_esw_for_each_host_func_vport_reverse(esw, vport, nvfs)	\
+	for ((vport) = (nvfs);						\
+	     (vport) >= (esw)->first_host_vport; (vport)--)
+
 struct mlx5_vport *__must_check
 mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num);
 
+bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num);
+
+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);
+
 #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_sriov(struct mlx5_eswitch *esw, int nvfs, int mode) { return 0; }
-static inline void mlx5_eswitch_disable_sriov(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 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 int
@@ -522,6 +566,8 @@ mlx5_esw_query_functions(struct mlx5_core_dev *dev, u32 *out, int outlen)
 	return -EOPNOTSUPP;
 }
 
+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
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 6f5bd602a47e..7801e8c5f905 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -88,6 +88,53 @@ u16 mlx5_eswitch_get_prio_range(struct mlx5_eswitch *esw)
 	return 1;
 }
 
+static void
+mlx5_eswitch_set_rule_source_port(struct mlx5_eswitch *esw,
+				  struct mlx5_flow_spec *spec,
+				  struct mlx5_esw_flow_attr *attr)
+{
+	void *misc2;
+	void *misc;
+
+	/* Use metadata matching because vport is not represented by single
+	 * VHCA in dual-port RoCE mode, and matching on source vport may fail.
+	 */
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+		MLX5_SET(fte_match_set_misc2, misc2, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(attr->in_mdev->priv.eswitch,
+								   attr->in_rep->vport));
+
+		misc2 = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc2, metadata_reg_c_0);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+		if (memchr_inv(misc, 0, MLX5_ST_SZ_BYTES(fte_match_set_misc)))
+			spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+		MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
+
+		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+			MLX5_SET(fte_match_set_misc, misc,
+				 source_eswitch_owner_vhca_id,
+				 MLX5_CAP_GEN(attr->in_mdev, vhca_id));
+
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+		if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
+			MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+					 source_eswitch_owner_vhca_id);
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS;
+	}
+
+	if (MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source) &&
+	    attr->in_rep->vport == MLX5_VPORT_UPLINK)
+		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
+}
+
 struct mlx5_flow_handle *
 mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 				struct mlx5_flow_spec *spec,
@@ -99,9 +146,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_table *fdb;
 	int j, i = 0;
-	void *misc;
 
-	if (esw->mode != SRIOV_OFFLOADS)
+	if (esw->mode != MLX5_ESWITCH_OFFLOADS)
 		return ERR_PTR(-EOPNOTSUPP);
 
 	flow_act.action = attr->action;
@@ -159,21 +205,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		i++;
 	}
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-	MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET(fte_match_set_misc, misc,
-			 source_eswitch_owner_vhca_id,
-			 MLX5_CAP_GEN(attr->in_mdev, vhca_id));
-
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
-				 source_eswitch_owner_vhca_id);
+	mlx5_eswitch_set_rule_source_port(esw, spec, attr);
 
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) {
 		if (attr->tunnel_match_level != MLX5_MATCH_NONE)
 			spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
@@ -219,7 +252,6 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	struct mlx5_flow_table *fast_fdb;
 	struct mlx5_flow_table *fwd_fdb;
 	struct mlx5_flow_handle *rule;
-	void *misc;
 	int i;
 
 	fast_fdb = esw_get_prio_table(esw, attr->chain, attr->prio, 0);
@@ -251,25 +283,10 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 	dest[i].ft = fwd_fdb,
 	i++;
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-	MLX5_SET(fte_match_set_misc, misc, source_port, attr->in_rep->vport);
-
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET(fte_match_set_misc, misc,
-			 source_eswitch_owner_vhca_id,
-			 MLX5_CAP_GEN(attr->in_mdev, vhca_id));
-
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
-	if (MLX5_CAP_ESW(esw->dev, merged_eswitch))
-		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
-				 source_eswitch_owner_vhca_id);
+	mlx5_eswitch_set_rule_source_port(esw, spec, attr);
 
-	if (attr->match_level == MLX5_MATCH_NONE)
-		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
-	else
-		spec->match_criteria_enable = MLX5_MATCH_OUTER_HEADERS |
-					      MLX5_MATCH_MISC_PARAMETERS;
+	if (attr->match_level != MLX5_MATCH_NONE)
+		spec->match_criteria_enable |= MLX5_MATCH_OUTER_HEADERS;
 
 	rule = mlx5_add_flow_rules(fast_fdb, spec, &flow_act, dest, i);
 
@@ -327,11 +344,10 @@ mlx5_eswitch_del_fwd_rule(struct mlx5_eswitch *esw,
 static int esw_set_global_vlan_pop(struct mlx5_eswitch *esw, u8 val)
 {
 	struct mlx5_eswitch_rep *rep;
-	int vf_vport, err = 0;
+	int i, err = 0;
 
 	esw_debug(esw->dev, "%s applying global %s policy\n", __func__, val ? "pop" : "none");
-	for (vf_vport = 1; vf_vport < esw->enabled_vports; vf_vport++) {
-		rep = &esw->offloads.vport_reps[vf_vport];
+	mlx5_esw_for_each_host_func_rep(esw, i, rep, esw->esw_funcs.num_vfs) {
 		if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
 			continue;
 
@@ -558,23 +574,87 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule)
 	mlx5_del_flow_rules(rule);
 }
 
-static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
+static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+	u8 fdb_to_vport_reg_c_id;
+	int err;
+
+	err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+						   out, sizeof(out));
+	if (err)
+		return err;
+
+	fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+					 esw_vport_context.fdb_to_vport_reg_c_id);
+
+	fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0;
+	MLX5_SET(modify_esw_vport_context_in, in,
+		 esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+	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,
+						     in, sizeof(in));
+}
+
+static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw)
+{
+	u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {};
+	u8 fdb_to_vport_reg_c_id;
+	int err;
+
+	err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport,
+						   out, sizeof(out));
+	if (err)
+		return err;
+
+	fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out,
+					 esw_vport_context.fdb_to_vport_reg_c_id);
+
+	fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0;
+
+	MLX5_SET(modify_esw_vport_context_in, in,
+		 esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id);
+
+	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,
+						     in, sizeof(in));
+}
+
+static void peer_miss_rules_setup(struct mlx5_eswitch *esw,
+				  struct mlx5_core_dev *peer_dev,
 				  struct mlx5_flow_spec *spec,
 				  struct mlx5_flow_destination *dest)
 {
-	void *misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
-				  misc_parameters);
+	void *misc;
 
-	MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
-		 MLX5_CAP_GEN(peer_dev, vhca_id));
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters_2);
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
 
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-			    misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc,
-			 source_eswitch_owner_vhca_id);
+		MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(peer_dev, vhca_id));
+
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+				 source_eswitch_owner_vhca_id);
+	}
 
 	dest->type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
 	dest->vport.num = peer_dev->priv.eswitch->manager_vport;
@@ -582,6 +662,26 @@ static void peer_miss_rules_setup(struct mlx5_core_dev *peer_dev,
 	dest->vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
 }
 
+static void esw_set_peer_miss_rule_source_port(struct mlx5_eswitch *esw,
+					       struct mlx5_eswitch *peer_esw,
+					       struct mlx5_flow_spec *spec,
+					       u16 vport)
+{
+	void *misc;
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters_2);
+		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(peer_esw,
+								   vport));
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
+		MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+	}
+}
+
 static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 				       struct mlx5_core_dev *peer_dev)
 {
@@ -599,7 +699,7 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	if (!spec)
 		return -ENOMEM;
 
-	peer_miss_rules_setup(peer_dev, spec, &dest);
+	peer_miss_rules_setup(esw, peer_dev, spec, &dest);
 
 	flows = kvzalloc(nvports * sizeof(*flows), GFP_KERNEL);
 	if (!flows) {
@@ -612,7 +712,9 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 			    misc_parameters);
 
 	if (mlx5_core_is_ecpf_esw_manager(esw->dev)) {
-		MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_PF);
+		esw_set_peer_miss_rule_source_port(esw, peer_dev->priv.eswitch,
+						   spec, MLX5_VPORT_PF);
+
 		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
@@ -634,7 +736,10 @@ static int esw_add_fdb_peer_miss_rules(struct mlx5_eswitch *esw,
 	}
 
 	mlx5_esw_for_each_vf_vport_num(esw, i, mlx5_core_max_vfs(esw->dev)) {
-		MLX5_SET(fte_match_set_misc, misc, source_port, i);
+		esw_set_peer_miss_rule_source_port(esw,
+						   peer_dev->priv.eswitch,
+						   spec, i);
+
 		flow = mlx5_add_flow_rules(esw->fdb_table.offloads.slow_fdb,
 					   spec, &flow_act, &dest, 1);
 		if (IS_ERR(flow)) {
@@ -918,6 +1023,30 @@ static void esw_destroy_offloads_fast_fdb_tables(struct mlx5_eswitch *esw)
 #define MAX_PF_SQ 256
 #define MAX_SQ_NVPORTS 32
 
+static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
+					   u32 *flow_group_in)
+{
+	void *match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+					    flow_group_in,
+					    match_criteria);
+
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		MLX5_SET(create_flow_group_in, flow_group_in,
+			 match_criteria_enable,
+			 MLX5_MATCH_MISC_PARAMETERS_2);
+
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+				 misc_parameters_2.metadata_reg_c_0);
+	} else {
+		MLX5_SET(create_flow_group_in, flow_group_in,
+			 match_criteria_enable,
+			 MLX5_MATCH_MISC_PARAMETERS);
+
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+				 misc_parameters.source_port);
+	}
+}
+
 static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -1015,19 +1144,21 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 
 	/* create peer esw miss group */
 	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
-		 MLX5_MATCH_MISC_PARAMETERS);
 
-	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
-				      match_criteria);
+	esw_set_flow_group_source_port(esw, flow_group_in);
+
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		match_criteria = MLX5_ADDR_OF(create_flow_group_in,
+					      flow_group_in,
+					      match_criteria);
 
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-			 misc_parameters.source_port);
-	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
-			 misc_parameters.source_eswitch_owner_vhca_id);
+		MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+				 misc_parameters.source_eswitch_owner_vhca_id);
+
+		MLX5_SET(create_flow_group_in, flow_group_in,
+			 source_eswitch_owner_vhca_id_valid, 1);
+	}
 
-	MLX5_SET(create_flow_group_in, flow_group_in,
-		 source_eswitch_owner_vhca_id_valid, 1);
 	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, ix);
 	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
 		 ix + esw->total_vports - 1);
@@ -1141,7 +1272,6 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_group *g;
 	u32 *flow_group_in;
-	void *match_criteria, *misc;
 	int err = 0;
 
 	nvports = nvports + MLX5_ESW_MISS_FLOWS;
@@ -1151,12 +1281,8 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw, int nvports)
 
 	/* create vport rx group */
 	memset(flow_group_in, 0, inlen);
-	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
-		 MLX5_MATCH_MISC_PARAMETERS);
 
-	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in, match_criteria);
-	misc = MLX5_ADDR_OF(fte_match_param, match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+	esw_set_flow_group_source_port(esw, flow_group_in);
 
 	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, nvports - 1);
@@ -1195,13 +1321,24 @@ mlx5_eswitch_create_vport_rx_rule(struct mlx5_eswitch *esw, u16 vport,
 		goto out;
 	}
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-	MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters_2);
+		MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0,
+			 mlx5_eswitch_get_vport_metadata_for_match(esw, vport));
 
-	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
-	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters_2);
+		MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0);
 
-	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	} else {
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
+		MLX5_SET(fte_match_set_misc, misc, source_port, vport);
+
+		misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+		MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+
+		spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	}
 
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 	flow_rule = mlx5_add_flow_rules(esw->offloads.ft_offloads, spec,
@@ -1219,21 +1356,22 @@ out:
 static int esw_offloads_start(struct mlx5_eswitch *esw,
 			      struct netlink_ext_ack *extack)
 {
-	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
+	int err, err1;
 
-	if (esw->mode != SRIOV_LEGACY &&
+	if (esw->mode != MLX5_ESWITCH_LEGACY &&
 	    !mlx5_core_is_ecpf_esw_manager(esw->dev)) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Can't set offloads mode, SRIOV legacy not enabled");
 		return -EINVAL;
 	}
 
-	mlx5_eswitch_disable_sriov(esw);
-	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+	mlx5_eswitch_disable(esw);
+	mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs);
+	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Failed setting eswitch to offloads");
-		err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+		err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 		if (err1) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Failed setting eswitch back to legacy");
@@ -1241,7 +1379,6 @@ static int esw_offloads_start(struct mlx5_eswitch *esw,
 	}
 	if (esw->offloads.inline_mode == MLX5_INLINE_MODE_NONE) {
 		if (mlx5_eswitch_inline_mode_get(esw,
-						 num_vfs,
 						 &esw->offloads.inline_mode)) {
 			esw->offloads.inline_mode = MLX5_INLINE_MODE_L2;
 			NL_SET_ERR_MSG_MOD(extack,
@@ -1262,7 +1399,7 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_eswitch_rep *rep;
 	u8 hw_id[ETH_ALEN], rep_type;
-	int vport;
+	int vport_index;
 
 	esw->offloads.vport_reps = kcalloc(total_vports,
 					   sizeof(struct mlx5_eswitch_rep),
@@ -1270,10 +1407,11 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw)
 	if (!esw->offloads.vport_reps)
 		return -ENOMEM;
 
-	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
+	mlx5_query_mac_address(dev, hw_id);
 
-	mlx5_esw_for_all_reps(esw, vport, rep) {
-		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport);
+	mlx5_esw_for_all_reps(esw, vport_index, rep) {
+		rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index);
+		rep->vport_index = vport_index;
 		ether_addr_copy(rep->hw_id, hw_id);
 
 		for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++)
@@ -1328,21 +1466,20 @@ static void esw_offloads_unload_vf_reps(struct mlx5_eswitch *esw, int nvports)
 		__unload_reps_vf_vport(esw, nvports, rep_type);
 }
 
-static void __unload_reps_all_vport(struct mlx5_eswitch *esw, int nvports,
-				    u8 rep_type)
+static void __unload_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	__unload_reps_vf_vport(esw, nvports, rep_type);
+	__unload_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);
 
 	/* Special vports must be the last to unload. */
 	__unload_reps_special_vport(esw, rep_type);
 }
 
-static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw, int nvports)
+static void esw_offloads_unload_all_reps(struct mlx5_eswitch *esw)
 {
 	u8 rep_type = NUM_REP_TYPES;
 
 	while (rep_type-- > 0)
-		__unload_reps_all_vport(esw, nvports, rep_type);
+		__unload_reps_all_vport(esw, rep_type);
 }
 
 static int __esw_offloads_load_rep(struct mlx5_eswitch *esw,
@@ -1418,6 +1555,26 @@ err_vf:
 	return err;
 }
 
+static int __load_reps_all_vport(struct mlx5_eswitch *esw, u8 rep_type)
+{
+	int err;
+
+	/* Special vports must be loaded first, uplink rep creates mdev resource. */
+	err = __load_reps_special_vport(esw, rep_type);
+	if (err)
+		return err;
+
+	err = __load_reps_vf_vport(esw, esw->esw_funcs.num_vfs, rep_type);
+	if (err)
+		goto err_vfs;
+
+	return 0;
+
+err_vfs:
+	__unload_reps_special_vport(esw, rep_type);
+	return err;
+}
+
 static int esw_offloads_load_vf_reps(struct mlx5_eswitch *esw, int nvports)
 {
 	u8 rep_type = 0;
@@ -1437,13 +1594,13 @@ err_reps:
 	return err;
 }
 
-static int esw_offloads_load_special_vport(struct mlx5_eswitch *esw)
+static int esw_offloads_load_all_reps(struct mlx5_eswitch *esw)
 {
 	u8 rep_type = 0;
 	int err;
 
 	for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) {
-		err = __load_reps_special_vport(esw, rep_type);
+		err = __load_reps_all_vport(esw, rep_type);
 		if (err)
 			goto err_reps;
 	}
@@ -1452,7 +1609,7 @@ static int esw_offloads_load_special_vport(struct mlx5_eswitch *esw)
 
 err_reps:
 	while (rep_type-- > 0)
-		__unload_reps_special_vport(esw, rep_type);
+		__unload_reps_all_vport(esw, rep_type);
 	return err;
 }
 
@@ -1488,6 +1645,10 @@ static int mlx5_esw_offloads_devcom_event(int event,
 
 	switch (event) {
 	case ESW_OFFLOADS_DEVCOM_PAIR:
+		if (mlx5_eswitch_vport_match_metadata_enabled(esw) !=
+		    mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
+			break;
+
 		err = mlx5_esw_offloads_pair(esw, peer_esw);
 		if (err)
 			goto err_out;
@@ -1556,32 +1717,16 @@ static void esw_offloads_devcom_cleanup(struct mlx5_eswitch *esw)
 static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
 					     struct mlx5_vport *vport)
 {
-	struct mlx5_core_dev *dev = esw->dev;
 	struct mlx5_flow_act flow_act = {0};
 	struct mlx5_flow_spec *spec;
 	int err = 0;
 
 	/* For prio tag mode, there is only 1 FTEs:
-	 * 1) Untagged packets - push prio tag VLAN, allow
+	 * 1) Untagged packets - push prio tag VLAN and modify metadata if
+	 * required, allow
 	 * Unmatched traffic is allowed by default
 	 */
 
-	if (!MLX5_CAP_ESW_INGRESS_ACL(dev, ft_support))
-		return -EOPNOTSUPP;
-
-	esw_vport_cleanup_ingress_rules(esw, vport);
-
-	err = esw_vport_enable_ingress_acl(esw, vport);
-	if (err) {
-		mlx5_core_warn(esw->dev,
-			       "failed to enable prio tag ingress acl (%d) on vport[%d]\n",
-			       err, vport->vport);
-		return err;
-	}
-
-	esw_debug(esw->dev,
-		  "vport[%d] configure ingress rules\n", vport->vport);
-
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec) {
 		err = -ENOMEM;
@@ -1597,6 +1742,12 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw,
 	flow_act.vlan[0].ethtype = ETH_P_8021Q;
 	flow_act.vlan[0].vid = 0;
 	flow_act.vlan[0].prio = 0;
+
+	if (vport->ingress.modify_metadata_rule) {
+		flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
+		flow_act.modify_id = vport->ingress.modify_metadata_id;
+	}
+
 	vport->ingress.allow_rule =
 		mlx5_add_flow_rules(vport->ingress.acl, spec,
 				    &flow_act, NULL, 0);
@@ -1617,6 +1768,58 @@ out_no_mem:
 	return err;
 }
 
+static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw,
+						     struct mlx5_vport *vport)
+{
+	u8 action[MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto)] = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec spec = {};
+	int err = 0;
+
+	MLX5_SET(set_action_in, action, action_type, MLX5_ACTION_TYPE_SET);
+	MLX5_SET(set_action_in, action, field, MLX5_ACTION_IN_FIELD_METADATA_REG_C_0);
+	MLX5_SET(set_action_in, action, data,
+		 mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport));
+
+	err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+				       1, action, &vport->ingress.modify_metadata_id);
+	if (err) {
+		esw_warn(esw->dev,
+			 "failed to alloc modify header for vport %d ingress acl (%d)\n",
+			 vport->vport, err);
+		return err;
+	}
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW;
+	flow_act.modify_id = vport->ingress.modify_metadata_id;
+	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);
+		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;
+		goto out;
+	}
+
+out:
+	if (err)
+		mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id);
+	return err;
+}
+
+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_id);
+
+		vport->ingress.modify_metadata_rule = NULL;
+	}
+}
+
 static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
 					    struct mlx5_vport *vport)
 {
@@ -1624,6 +1827,9 @@ static int esw_vport_egress_prio_tag_config(struct mlx5_eswitch *esw,
 	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
@@ -1677,27 +1883,98 @@ out_no_mem:
 	return err;
 }
 
-static int esw_prio_tag_acls_config(struct mlx5_eswitch *esw, int nvports)
+static int esw_vport_ingress_common_config(struct mlx5_eswitch *esw,
+					   struct mlx5_vport *vport)
 {
-	struct mlx5_vport *vport = NULL;
-	int i, j;
 	int err;
 
-	mlx5_esw_for_each_vf_vport(esw, i, vport, nvports) {
+	if (!mlx5_eswitch_vport_match_metadata_enabled(esw) &&
+	    !MLX5_CAP_GEN(esw->dev, prio_tag_required))
+		return 0;
+
+	esw_vport_cleanup_ingress_rules(esw, vport);
+
+	err = esw_vport_enable_ingress_acl(esw, vport);
+	if (err) {
+		esw_warn(esw->dev,
+			 "failed to enable ingress acl (%d) on vport[%d]\n",
+			 err, vport->vport);
+		return 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;
+	}
+
+	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 err_ingress;
-		err = esw_vport_egress_prio_tag_config(esw, vport);
+			goto out;
+	}
+
+out:
+	if (err)
+		esw_vport_disable_ingress_acl(esw, vport);
+	return err;
+}
+
+static bool
+esw_check_vport_match_metadata_supported(const struct mlx5_eswitch *esw)
+{
+	if (!MLX5_CAP_ESW(esw->dev, esw_uplink_ingress_acl))
+		return false;
+
+	if (!(MLX5_CAP_ESW_FLOWTABLE(esw->dev, fdb_to_vport_reg_c_id) &
+	      MLX5_FDB_TO_VPORT_REG_C_0))
+		return false;
+
+	if (!MLX5_CAP_ESW_FLOWTABLE(esw->dev, flow_source))
+		return false;
+
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev) ||
+	    mlx5_ecpf_vport_exists(esw->dev))
+		return false;
+
+	return true;
+}
+
+static int esw_create_offloads_acl_tables(struct mlx5_eswitch *esw)
+{
+	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_egress;
+			goto err_ingress;
+
+		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_vport_match_metadata_enabled(esw))
+		esw_info(esw->dev, "Use metadata reg_c as source vport to match\n");
+
 	return 0;
 
 err_egress:
 	esw_vport_disable_ingress_acl(esw, vport);
 err_ingress:
-	mlx5_esw_for_each_vf_vport_reverse(esw, j, vport, i - 1) {
+	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);
 	}
@@ -1705,40 +1982,46 @@ err_ingress:
 	return err;
 }
 
-static void esw_prio_tag_acls_cleanup(struct mlx5_eswitch *esw)
+static void esw_destroy_offloads_acl_tables(struct mlx5_eswitch *esw)
 {
 	struct mlx5_vport *vport;
 	int i;
 
-	mlx5_esw_for_each_vf_vport(esw, i, vport, esw->dev->priv.sriov.num_vfs) {
+	mlx5_esw_for_all_vports(esw, i, vport) {
 		esw_vport_disable_egress_acl(esw, vport);
 		esw_vport_disable_ingress_acl(esw, vport);
 	}
+
+	esw->flags &= ~MLX5_ESWITCH_VPORT_MATCH_METADATA;
 }
 
-static int esw_offloads_steering_init(struct mlx5_eswitch *esw, int vf_nvports,
-				      int nvports)
+static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 {
+	int num_vfs = esw->esw_funcs.num_vfs;
+	int total_vports;
 	int err;
 
+	if (mlx5_core_is_ecpf_esw_manager(esw->dev))
+		total_vports = esw->total_vports;
+	else
+		total_vports = num_vfs + MLX5_SPECIAL_VPORTS(esw->dev);
+
 	memset(&esw->fdb_table.offloads, 0, sizeof(struct offloads_fdb));
 	mutex_init(&esw->fdb_table.offloads.fdb_prio_lock);
 
-	if (MLX5_CAP_GEN(esw->dev, prio_tag_required)) {
-		err = esw_prio_tag_acls_config(esw, vf_nvports);
-		if (err)
-			return err;
-	}
-
-	err = esw_create_offloads_fdb_tables(esw, nvports);
+	err = esw_create_offloads_acl_tables(esw);
 	if (err)
 		return err;
 
-	err = esw_create_offloads_table(esw, nvports);
+	err = esw_create_offloads_fdb_tables(esw, total_vports);
+	if (err)
+		goto create_fdb_err;
+
+	err = esw_create_offloads_table(esw, total_vports);
 	if (err)
 		goto create_ft_err;
 
-	err = esw_create_vport_rx_group(esw, nvports);
+	err = esw_create_vport_rx_group(esw, total_vports);
 	if (err)
 		goto create_fg_err;
 
@@ -1750,6 +2033,9 @@ create_fg_err:
 create_ft_err:
 	esw_destroy_offloads_fdb_tables(esw);
 
+create_fdb_err:
+	esw_destroy_offloads_acl_tables(esw);
+
 	return err;
 }
 
@@ -1758,8 +2044,7 @@ 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);
-	if (MLX5_CAP_GEN(esw->dev, prio_tag_required))
-		esw_prio_tag_acls_cleanup(esw);
+	esw_destroy_offloads_acl_tables(esw);
 }
 
 static void esw_functions_changed_event_handler(struct work_struct *work)
@@ -1767,6 +2052,7 @@ static void esw_functions_changed_event_handler(struct work_struct *work)
 	u32 out[MLX5_ST_SZ_DW(query_esw_functions_out)] = {};
 	struct mlx5_host_work *host_work;
 	struct mlx5_eswitch *esw;
+	bool host_pf_disabled;
 	u16 num_vfs = 0;
 	int err;
 
@@ -1776,7 +2062,9 @@ static void esw_functions_changed_event_handler(struct work_struct *work)
 	err = mlx5_esw_query_functions(esw->dev, out, sizeof(out));
 	num_vfs = MLX5_GET(query_esw_functions_out, out,
 			   host_params_context.host_num_of_vfs);
-	if (err || num_vfs == esw->esw_funcs.num_vfs)
+	host_pf_disabled = MLX5_GET(query_esw_functions_out, out,
+				    host_params_context.host_pf_disabled);
+	if (err || host_pf_disabled || num_vfs == esw->esw_funcs.num_vfs)
 		goto out;
 
 	/* Number of VFs can only change from "0 to x" or "x to 0". */
@@ -1795,23 +2083,7 @@ out:
 	kfree(host_work);
 }
 
-static void esw_emulate_event_handler(struct work_struct *work)
-{
-	struct mlx5_host_work *host_work =
-		container_of(work, struct mlx5_host_work, work);
-	struct mlx5_eswitch *esw = host_work->esw;
-	int err;
-
-	if (esw->esw_funcs.num_vfs) {
-		err = esw_offloads_load_vf_reps(esw, esw->esw_funcs.num_vfs);
-		if (err)
-			esw_warn(esw->dev, "Load vf reps err=%d\n", err);
-	}
-	kfree(host_work);
-}
-
-static int esw_functions_changed_event(struct notifier_block *nb,
-				       unsigned long type, void *data)
+int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data)
 {
 	struct mlx5_esw_functions *esw_funcs;
 	struct mlx5_host_work *host_work;
@@ -1826,74 +2098,40 @@ static int esw_functions_changed_event(struct notifier_block *nb,
 
 	host_work->esw = esw;
 
-	if (mlx5_eswitch_is_funcs_handler(esw->dev))
-		INIT_WORK(&host_work->work,
-			  esw_functions_changed_event_handler);
-	else
-		INIT_WORK(&host_work->work, esw_emulate_event_handler);
+	INIT_WORK(&host_work->work, esw_functions_changed_event_handler);
 	queue_work(esw->work_queue, &host_work->work);
 
 	return NOTIFY_OK;
 }
 
-static void esw_functions_changed_event_init(struct mlx5_eswitch *esw,
-					     u16 vf_nvports)
-{
-	if (mlx5_eswitch_is_funcs_handler(esw->dev)) {
-		esw->esw_funcs.num_vfs = 0;
-		MLX5_NB_INIT(&esw->esw_funcs.nb, esw_functions_changed_event,
-			     ESW_FUNCTIONS_CHANGED);
-		mlx5_eq_notifier_register(esw->dev, &esw->esw_funcs.nb);
-	} else {
-		esw->esw_funcs.num_vfs = vf_nvports;
-	}
-}
-
-static void esw_functions_changed_event_cleanup(struct mlx5_eswitch *esw)
-{
-	if (!mlx5_eswitch_is_funcs_handler(esw->dev))
-		return;
-
-	mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb);
-	flush_workqueue(esw->work_queue);
-}
-
-int esw_offloads_init(struct mlx5_eswitch *esw, int vf_nvports,
-		      int total_nvports)
+int esw_offloads_init(struct mlx5_eswitch *esw)
 {
 	int err;
 
-	err = esw_offloads_steering_init(esw, vf_nvports, total_nvports);
+	err = esw_offloads_steering_init(esw);
 	if (err)
 		return err;
 
-	/* Only load special vports reps. VF reps will be loaded in
-	 * context of functions_changed event handler through real
-	 * or emulated event.
-	 */
-	err = esw_offloads_load_special_vport(esw);
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw)) {
+		err = mlx5_eswitch_enable_passing_vport_metadata(esw);
+		if (err)
+			goto err_vport_metadata;
+	}
+
+	err = esw_offloads_load_all_reps(esw);
 	if (err)
 		goto err_reps;
 
 	esw_offloads_devcom_init(esw);
 
-	esw_functions_changed_event_init(esw, vf_nvports);
-
 	mlx5_rdma_enable_roce(esw->dev);
 
-	/* Call esw_functions_changed event to load VF reps:
-	 * 1. HW does not support the event then emulate it
-	 * Or
-	 * 2. The event was already notified when num_vfs changed
-	 * and eswitch was in legacy mode
-	 */
-	esw_functions_changed_event(&esw->esw_funcs.nb.nb,
-				    MLX5_EVENT_TYPE_ESW_FUNCTIONS_CHANGED,
-				    NULL);
-
 	return 0;
 
 err_reps:
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+		mlx5_eswitch_disable_passing_vport_metadata(esw);
+err_vport_metadata:
 	esw_offloads_steering_cleanup(esw);
 	return err;
 }
@@ -1901,13 +2139,13 @@ err_reps:
 static int esw_offloads_stop(struct mlx5_eswitch *esw,
 			     struct netlink_ext_ack *extack)
 {
-	int err, err1, num_vfs = esw->dev->priv.sriov.num_vfs;
+	int err, err1;
 
-	mlx5_eswitch_disable_sriov(esw);
-	err = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_LEGACY);
+	mlx5_eswitch_disable(esw);
+	err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy");
-		err1 = mlx5_eswitch_enable_sriov(esw, num_vfs, SRIOV_OFFLOADS);
+		err1 = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS);
 		if (err1) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Failed setting eswitch back to offloads");
@@ -1919,10 +2157,11 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 
 void esw_offloads_cleanup(struct mlx5_eswitch *esw)
 {
-	esw_functions_changed_event_cleanup(esw);
 	mlx5_rdma_disable_roce(esw->dev);
 	esw_offloads_devcom_cleanup(esw);
-	esw_offloads_unload_all_reps(esw, esw->esw_funcs.num_vfs);
+	esw_offloads_unload_all_reps(esw);
+	if (mlx5_eswitch_vport_match_metadata_enabled(esw))
+		mlx5_eswitch_disable_passing_vport_metadata(esw);
 	esw_offloads_steering_cleanup(esw);
 }
 
@@ -1930,10 +2169,10 @@ static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
 {
 	switch (mode) {
 	case DEVLINK_ESWITCH_MODE_LEGACY:
-		*mlx5_mode = SRIOV_LEGACY;
+		*mlx5_mode = MLX5_ESWITCH_LEGACY;
 		break;
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
-		*mlx5_mode = SRIOV_OFFLOADS;
+		*mlx5_mode = MLX5_ESWITCH_OFFLOADS;
 		break;
 	default:
 		return -EINVAL;
@@ -1945,10 +2184,10 @@ static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode)
 static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode)
 {
 	switch (mlx5_mode) {
-	case SRIOV_LEGACY:
+	case MLX5_ESWITCH_LEGACY:
 		*mode = DEVLINK_ESWITCH_MODE_LEGACY;
 		break;
-	case SRIOV_OFFLOADS:
+	case MLX5_ESWITCH_OFFLOADS:
 		*mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
 		break;
 	default:
@@ -2012,7 +2251,7 @@ static int mlx5_devlink_eswitch_check(struct devlink *devlink)
 	if(!MLX5_ESWITCH_MANAGER(dev))
 		return -EPERM;
 
-	if (dev->priv.eswitch->mode == SRIOV_NONE &&
+	if (dev->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
 	    !mlx5_core_is_ecpf_esw_manager(dev))
 		return -EOPNOTSUPP;
 
@@ -2063,7 +2302,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 {
 	struct mlx5_core_dev *dev = devlink_priv(devlink);
 	struct mlx5_eswitch *esw = dev->priv.eswitch;
-	int err, vport;
+	int err, vport, num_vport;
 	u8 mlx5_mode;
 
 	err = mlx5_devlink_eswitch_check(devlink);
@@ -2092,7 +2331,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	if (err)
 		goto out;
 
-	for (vport = 1; vport < esw->enabled_vports; vport++) {
+	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
 		err = mlx5_modify_nic_vport_min_inline(dev, vport, mlx5_mode);
 		if (err) {
 			NL_SET_ERR_MSG_MOD(extack,
@@ -2105,7 +2344,8 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode,
 	return 0;
 
 revert_inline_mode:
-	while (--vport > 0)
+	num_vport = --vport;
+	mlx5_esw_for_each_host_func_vport_reverse(esw, vport, num_vport)
 		mlx5_modify_nic_vport_min_inline(dev,
 						 vport,
 						 esw->offloads.inline_mode);
@@ -2126,7 +2366,7 @@ int mlx5_devlink_eswitch_inline_mode_get(struct devlink *devlink, u8 *mode)
 	return esw_inline_mode_to_devlink(esw->offloads.inline_mode, mode);
 }
 
-int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
+int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, u8 *mode)
 {
 	u8 prev_mlx5_mode, mlx5_mode = MLX5_INLINE_MODE_L2;
 	struct mlx5_core_dev *dev = esw->dev;
@@ -2135,7 +2375,7 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 	if (!MLX5_CAP_GEN(dev, vport_group_manager))
 		return -EOPNOTSUPP;
 
-	if (esw->mode == SRIOV_NONE)
+	if (esw->mode == MLX5_ESWITCH_NONE)
 		return -EOPNOTSUPP;
 
 	switch (MLX5_CAP_ETH(dev, wqe_inline_mode)) {
@@ -2150,9 +2390,10 @@ int mlx5_eswitch_inline_mode_get(struct mlx5_eswitch *esw, int nvfs, u8 *mode)
 	}
 
 query_vports:
-	for (vport = 1; vport <= nvfs; vport++) {
+	mlx5_query_nic_vport_min_inline(dev, esw->first_host_vport, &prev_mlx5_mode);
+	mlx5_esw_for_each_host_func_vport(esw, vport, esw->esw_funcs.num_vfs) {
 		mlx5_query_nic_vport_min_inline(dev, vport, &mlx5_mode);
-		if (vport > 1 && prev_mlx5_mode != mlx5_mode)
+		if (prev_mlx5_mode != mlx5_mode)
 			return -EINVAL;
 		prev_mlx5_mode = mlx5_mode;
 	}
@@ -2182,7 +2423,7 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink,
 	if (encap && encap != DEVLINK_ESWITCH_ENCAP_MODE_BASIC)
 		return -EOPNOTSUPP;
 
-	if (esw->mode == SRIOV_LEGACY) {
+	if (esw->mode == MLX5_ESWITCH_LEGACY) {
 		esw->offloads.encap = encap;
 		return 0;
 	}
@@ -2245,12 +2486,11 @@ EXPORT_SYMBOL(mlx5_eswitch_register_vport_reps);
 
 void mlx5_eswitch_unregister_vport_reps(struct mlx5_eswitch *esw, u8 rep_type)
 {
-	u16 max_vf = mlx5_core_max_vfs(esw->dev);
 	struct mlx5_eswitch_rep *rep;
 	int i;
 
-	if (esw->mode == SRIOV_OFFLOADS)
-		__unload_reps_all_vport(esw, max_vf, rep_type);
+	if (esw->mode == MLX5_ESWITCH_OFFLOADS)
+		__unload_reps_all_vport(esw, rep_type);
 
 	mlx5_esw_for_all_reps(esw, i, rep)
 		atomic_set(&rep->rep_data[rep_type].state, REP_UNREGISTERED);
@@ -2292,3 +2532,22 @@ struct mlx5_eswitch_rep *mlx5_eswitch_vport_rep(struct mlx5_eswitch *esw,
 	return mlx5_eswitch_get_rep(esw, vport);
 }
 EXPORT_SYMBOL(mlx5_eswitch_vport_rep);
+
+bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num)
+{
+	return vport_num >= MLX5_VPORT_FIRST_VF &&
+	       vport_num <= esw->dev->priv.sriov.max_vfs;
+}
+
+bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw)
+{
+	return !!(esw->flags & MLX5_ESWITCH_VPORT_MATCH_METADATA);
+}
+EXPORT_SYMBOL(mlx5_eswitch_vport_match_metadata_enabled);
+
+u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+					      u16 vport_num)
+{
+	return ((MLX5_CAP_GEN(esw->dev, vhca_id) & 0xffff) << 16) | vport_num;
+}
+EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
index ca2296a2f9ee..4c50efe4e7f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/conn.c
@@ -414,7 +414,8 @@ static void mlx5_fpga_conn_cq_tasklet(unsigned long data)
 	mlx5_fpga_conn_cqes(conn, MLX5_FPGA_CQ_BUDGET);
 }
 
-static void mlx5_fpga_conn_cq_complete(struct mlx5_core_cq *mcq)
+static void mlx5_fpga_conn_cq_complete(struct mlx5_core_cq *mcq,
+				       struct mlx5_eqe *eqe)
 {
 	struct mlx5_fpga_conn *conn;
 
@@ -429,6 +430,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	struct mlx5_fpga_device *fdev = conn->fdev;
 	struct mlx5_core_dev *mdev = fdev->mdev;
 	u32 temp_cqc[MLX5_ST_SZ_DW(cqc)] = {0};
+	u32 out[MLX5_ST_SZ_DW(create_cq_out)];
 	struct mlx5_wq_param wqp;
 	struct mlx5_cqe64 *cqe;
 	int inlen, err, eqn;
@@ -476,7 +478,7 @@ static int mlx5_fpga_conn_create_cq(struct mlx5_fpga_conn *conn, int cq_size)
 	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas);
 	mlx5_fill_page_frag_array(&conn->cq.wq_ctrl.buf, pas);
 
-	err = mlx5_core_create_cq(mdev, &conn->cq.mcq, in, inlen);
+	err = mlx5_core_create_cq(mdev, &conn->cq.mcq, in, inlen, out, sizeof(out));
 	kvfree(in);
 
 	if (err)
@@ -867,7 +869,7 @@ struct mlx5_fpga_conn *mlx5_fpga_conn_create(struct mlx5_fpga_device *fdev,
 	conn->cb_arg = attr->cb_arg;
 
 	remote_mac = MLX5_ADDR_OF(fpga_qpc, conn->fpga_qpc, remote_mac_47_32);
-	err = mlx5_query_nic_vport_mac_address(fdev->mdev, 0, remote_mac);
+	err = mlx5_query_mac_address(fdev->mdev, remote_mac);
 	if (err) {
 		mlx5_fpga_err(fdev, "Failed to query local MAC: %d\n", err);
 		ret = ERR_PTR(err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
index 52c47d3dd5a5..c76da309506b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c
@@ -636,7 +636,8 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
 					   u8 match_criteria_enable,
 					   const u32 *match_c,
 					   const u32 *match_v,
-					   struct mlx5_flow_act *flow_act)
+					   struct mlx5_flow_act *flow_act,
+					   struct mlx5_flow_context *flow_context)
 {
 	const void *outer_c = MLX5_ADDR_OF(fte_match_param, match_c,
 					   outer_headers);
@@ -655,7 +656,7 @@ static bool mlx5_is_fpga_egress_ipsec_rule(struct mlx5_core_dev *dev,
 	    (match_criteria_enable &
 	     ~(MLX5_MATCH_OUTER_HEADERS | MLX5_MATCH_MISC_PARAMETERS)) ||
 	    (flow_act->action & ~(MLX5_FLOW_CONTEXT_ACTION_ENCRYPT | MLX5_FLOW_CONTEXT_ACTION_ALLOW)) ||
-	     (flow_act->flags & FLOW_ACT_HAS_TAG))
+	     (flow_context->flags & FLOW_CONTEXT_HAS_TAG))
 		return false;
 
 	return true;
@@ -767,7 +768,8 @@ mlx5_fpga_ipsec_fs_create_sa_ctx(struct mlx5_core_dev *mdev,
 					    fg->mask.match_criteria_enable,
 					    fg->mask.match_criteria,
 					    fte->val,
-					    &fte->action))
+					    &fte->action,
+					    &fte->flow_context))
 		return ERR_PTR(-EINVAL);
 	else if (!mlx5_is_fpga_ipsec_rule(mdev,
 					  fg->mask.match_criteria_enable,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index bb24c3797218..7ac1249eadc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -396,7 +396,11 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev,
 	in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context);
 	MLX5_SET(flow_context, in_flow_context, group_id, group_id);
 
-	MLX5_SET(flow_context, in_flow_context, flow_tag, fte->action.flow_tag);
+	MLX5_SET(flow_context, in_flow_context, flow_tag,
+		 fte->flow_context.flow_tag);
+	MLX5_SET(flow_context, in_flow_context, flow_source,
+		 fte->flow_context.flow_source);
+
 	MLX5_SET(flow_context, in_flow_context, extended_destination,
 		 extended_dest);
 	if (extended_dest) {
@@ -771,6 +775,10 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev,
 		max_actions = MLX5_CAP_FLOWTABLE_NIC_TX(dev, max_modify_header_actions);
 		table_type = FS_FT_NIC_TX;
 		break;
+	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:
+		max_actions = MLX5_CAP_ESW_INGRESS_ACL(dev, max_modify_header_actions);
+		table_type = FS_FT_ESW_INGRESS_ACL;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index fe76c6fd6d80..585e7adcbf99 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -584,7 +584,7 @@ err_ida_remove:
 }
 
 static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
-				u32 *match_value,
+				struct mlx5_flow_spec *spec,
 				struct mlx5_flow_act *flow_act)
 {
 	struct mlx5_flow_steering *steering = get_steering(&ft->node);
@@ -594,9 +594,10 @@ static struct fs_fte *alloc_fte(struct mlx5_flow_table *ft,
 	if (!fte)
 		return ERR_PTR(-ENOMEM);
 
-	memcpy(fte->val, match_value, sizeof(fte->val));
+	memcpy(fte->val, &spec->match_value, sizeof(fte->val));
 	fte->node.type =  FS_TYPE_FLOW_ENTRY;
 	fte->action = *flow_act;
+	fte->flow_context = spec->flow_context;
 
 	tree_init_node(&fte->node, NULL, del_sw_fte);
 
@@ -1430,7 +1431,9 @@ static bool check_conflicting_actions(u32 action1, u32 action2)
 	return false;
 }
 
-static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act *flow_act)
+static int check_conflicting_ftes(struct fs_fte *fte,
+				  const struct mlx5_flow_context *flow_context,
+				  const struct mlx5_flow_act *flow_act)
 {
 	if (check_conflicting_actions(flow_act->action, fte->action.action)) {
 		mlx5_core_warn(get_dev(&fte->node),
@@ -1438,12 +1441,12 @@ static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act
 		return -EEXIST;
 	}
 
-	if ((flow_act->flags & FLOW_ACT_HAS_TAG) &&
-	    fte->action.flow_tag != flow_act->flow_tag) {
+	if ((flow_context->flags & FLOW_CONTEXT_HAS_TAG) &&
+	    fte->flow_context.flow_tag != flow_context->flow_tag) {
 		mlx5_core_warn(get_dev(&fte->node),
 			       "FTE flow tag %u already exists with different flow tag %u\n",
-			       fte->action.flow_tag,
-			       flow_act->flow_tag);
+			       fte->flow_context.flow_tag,
+			       flow_context->flow_tag);
 		return -EEXIST;
 	}
 
@@ -1451,7 +1454,7 @@ static int check_conflicting_ftes(struct fs_fte *fte, const struct mlx5_flow_act
 }
 
 static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
-					    u32 *match_value,
+					    struct mlx5_flow_spec *spec,
 					    struct mlx5_flow_act *flow_act,
 					    struct mlx5_flow_destination *dest,
 					    int dest_num,
@@ -1462,7 +1465,7 @@ static struct mlx5_flow_handle *add_rule_fg(struct mlx5_flow_group *fg,
 	int i;
 	int ret;
 
-	ret = check_conflicting_ftes(fte, flow_act);
+	ret = check_conflicting_ftes(fte, &spec->flow_context, flow_act);
 	if (ret)
 		return ERR_PTR(ret);
 
@@ -1637,7 +1640,7 @@ try_add_to_existing_fg(struct mlx5_flow_table *ft,
 	u64  version;
 	int err;
 
-	fte = alloc_fte(ft, spec->match_value, flow_act);
+	fte = alloc_fte(ft, spec, flow_act);
 	if (IS_ERR(fte))
 		return  ERR_PTR(-ENOMEM);
 
@@ -1653,8 +1656,7 @@ search_again_locked:
 		fte_tmp = lookup_fte_locked(g, spec->match_value, take_write);
 		if (!fte_tmp)
 			continue;
-		rule = add_rule_fg(g, spec->match_value,
-				   flow_act, dest, dest_num, fte_tmp);
+		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte_tmp);
 		up_write_ref_node(&fte_tmp->node, false);
 		tree_put_node(&fte_tmp->node, false);
 		kmem_cache_free(steering->ftes_cache, fte);
@@ -1701,8 +1703,7 @@ skip_search:
 
 		nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
 		up_write_ref_node(&g->node, false);
-		rule = add_rule_fg(g, spec->match_value,
-				   flow_act, dest, dest_num, fte);
+		rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 		up_write_ref_node(&fte->node, false);
 		tree_put_node(&fte->node, false);
 		return rule;
@@ -1788,7 +1789,7 @@ search_again_locked:
 	if (err)
 		goto err_release_fg;
 
-	fte = alloc_fte(ft, spec->match_value, flow_act);
+	fte = alloc_fte(ft, spec, flow_act);
 	if (IS_ERR(fte)) {
 		err = PTR_ERR(fte);
 		goto err_release_fg;
@@ -1802,8 +1803,7 @@ search_again_locked:
 
 	nested_down_write_ref_node(&fte->node, FS_LOCK_CHILD);
 	up_write_ref_node(&g->node, false);
-	rule = add_rule_fg(g, spec->match_value, flow_act, dest,
-			   dest_num, fte);
+	rule = add_rule_fg(g, spec, flow_act, dest, dest_num, fte);
 	up_write_ref_node(&fte->node, false);
 	tree_put_node(&fte->node, false);
 	tree_put_node(&g->node, false);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index a08c3d09a50f..c48c382f926f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -170,6 +170,7 @@ struct fs_fte {
 	u32				val[MLX5_ST_SZ_DW_MATCH_PARAM];
 	u32				dests_size;
 	u32				index;
+	struct mlx5_flow_context	flow_context;
 	struct mlx5_flow_act		action;
 	enum fs_fte_status		status;
 	struct mlx5_fc			*counter;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index 1ab6f7e3bec6..05367f15c3a7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -202,6 +202,12 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, event_cap)) {
+		err = mlx5_core_get_caps(dev, MLX5_CAP_DEV_EVENT);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
index 959605559858..c5ef2ff26465 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag.c
@@ -305,8 +305,8 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 			   !mlx5_sriov_is_enabled(dev1);
 
 #ifdef CONFIG_MLX5_ESWITCH
-		roce_lag &= dev0->priv.eswitch->mode == SRIOV_NONE &&
-			    dev1->priv.eswitch->mode == SRIOV_NONE;
+		roce_lag &= dev0->priv.eswitch->mode == MLX5_ESWITCH_NONE &&
+			    dev1->priv.eswitch->mode == MLX5_ESWITCH_NONE;
 #endif
 
 		if (roce_lag)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
index 24bd991a727e..3dfab91ae5f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h
@@ -75,7 +75,7 @@ int mlx5_eq_table_create(struct mlx5_core_dev *dev);
 void mlx5_eq_table_destroy(struct mlx5_core_dev *dev);
 
 int mlx5_eq_add_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
-int mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
+void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq);
 struct mlx5_eq_comp *mlx5_eqn2comp_eq(struct mlx5_core_dev *dev, int eqn);
 struct mlx5_eq *mlx5_get_async_eq(struct mlx5_core_dev *dev);
 void mlx5_cq_tasklet_cb(unsigned long data);
@@ -97,7 +97,4 @@ void mlx5_core_eq_free_irqs(struct mlx5_core_dev *dev);
 struct cpu_rmap *mlx5_eq_table_get_rmap(struct mlx5_core_dev *dev);
 #endif
 
-int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
-int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
-
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 2a766defb74e..051ade00f59c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -731,8 +731,7 @@ static int mlx5_pci_init(struct mlx5_core_dev *dev, struct pci_dev *pdev,
 	struct mlx5_priv *priv = &dev->priv;
 	int err = 0;
 
-	priv->pci_dev_data = id->driver_data;
-
+	mutex_init(&dev->pci_status_mutex);
 	pci_set_drvdata(dev->pdev, dev);
 
 	dev->bar_addr = pci_resource_start(pdev, 0);
@@ -1258,7 +1257,6 @@ static int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx)
 
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
-	mutex_init(&dev->pci_status_mutex);
 	mutex_init(&dev->intf_state_mutex);
 
 	mutex_init(&priv->bfregs.reg_head.lock);
@@ -1320,6 +1318,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	dev->device = &pdev->dev;
 	dev->pdev = pdev;
 
+	dev->coredev_type = id->driver_data & MLX5_PCI_DEV_IS_VF ?
+			 MLX5_COREDEV_VF : MLX5_COREDEV_PF;
+
 	err = mlx5_mdev_init(dev, prof_sel);
 	if (err)
 		goto mdev_init_err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
index ea744d8466ea..9231b39d18b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c
@@ -38,15 +38,12 @@
 
 void mlx5_init_mkey_table(struct mlx5_core_dev *dev)
 {
-	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
-
-	memset(table, 0, sizeof(*table));
-	rwlock_init(&table->lock);
-	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+	xa_init_flags(&dev->priv.mkey_table, XA_FLAGS_LOCK_IRQ);
 }
 
 void mlx5_cleanup_mkey_table(struct mlx5_core_dev *dev)
 {
+	WARN_ON(!xa_empty(&dev->priv.mkey_table));
 }
 
 int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
@@ -56,8 +53,8 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 			     mlx5_async_cbk_t callback,
 			     struct mlx5_async_work *context)
 {
-	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	u32 lout[MLX5_ST_SZ_DW(create_mkey_out)] = {0};
+	struct xarray *mkeys = &dev->priv.mkey_table;
 	u32 mkey_index;
 	void *mkc;
 	int err;
@@ -88,12 +85,10 @@ int mlx5_core_create_mkey_cb(struct mlx5_core_dev *dev,
 	mlx5_core_dbg(dev, "out 0x%x, key 0x%x, mkey 0x%x\n",
 		      mkey_index, key, mkey->key);
 
-	/* connect to mkey tree */
-	write_lock_irq(&table->lock);
-	err = radix_tree_insert(&table->tree, mlx5_base_mkey(mkey->key), mkey);
-	write_unlock_irq(&table->lock);
+	err = xa_err(xa_store_irq(mkeys, mlx5_base_mkey(mkey->key), mkey,
+				  GFP_KERNEL));
 	if (err) {
-		mlx5_core_warn(dev, "failed radix tree insert of mkey 0x%x, %d\n",
+		mlx5_core_warn(dev, "failed xarray insert of mkey 0x%x, %d\n",
 			       mlx5_base_mkey(mkey->key), err);
 		mlx5_core_destroy_mkey(dev, mkey);
 	}
@@ -114,17 +109,17 @@ EXPORT_SYMBOL(mlx5_core_create_mkey);
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev,
 			   struct mlx5_core_mkey *mkey)
 {
-	struct mlx5_mkey_table *table = &dev->priv.mkey_table;
 	u32 out[MLX5_ST_SZ_DW(destroy_mkey_out)] = {0};
 	u32 in[MLX5_ST_SZ_DW(destroy_mkey_in)]   = {0};
+	struct xarray *mkeys = &dev->priv.mkey_table;
 	struct mlx5_core_mkey *deleted_mkey;
 	unsigned long flags;
 
-	write_lock_irqsave(&table->lock, flags);
-	deleted_mkey = radix_tree_delete(&table->tree, mlx5_base_mkey(mkey->key));
-	write_unlock_irqrestore(&table->lock, flags);
+	xa_lock_irqsave(mkeys, flags);
+	deleted_mkey = __xa_erase(mkeys, mlx5_base_mkey(mkey->key));
+	xa_unlock_irqrestore(mkeys, flags);
 	if (!deleted_mkey) {
-		mlx5_core_dbg(dev, "failed radix tree delete of mkey 0x%x\n",
+		mlx5_core_dbg(dev, "failed xarray delete of mkey 0x%x\n",
 			      mlx5_base_mkey(mkey->key));
 		return -ENOENT;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
index 401441aefbcb..17ce9dd56b13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c
@@ -126,7 +126,7 @@ static void mlx5_rdma_make_default_gid(struct mlx5_core_dev *dev, union ib_gid *
 {
 	u8 hw_id[ETH_ALEN];
 
-	mlx5_query_nic_vport_mac_address(dev, 0, hw_id);
+	mlx5_query_mac_address(dev, hw_id);
 	gid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
 	addrconf_addr_eui48(&gid->raw[8], hw_id);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
index 2eecb831c499..547d0be9025e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c
@@ -74,17 +74,11 @@ static int mlx5_device_enable_sriov(struct mlx5_core_dev *dev, int num_vfs)
 	int err;
 	int vf;
 
-	if (sriov->enabled_vfs) {
-		mlx5_core_warn(dev,
-			       "failed to enable SRIOV on device, already enabled with %d vfs\n",
-			       sriov->enabled_vfs);
-		return -EBUSY;
-	}
-
 	if (!MLX5_ESWITCH_MANAGER(dev))
 		goto enable_vfs_hca;
 
-	err = mlx5_eswitch_enable_sriov(dev->priv.eswitch, num_vfs, SRIOV_LEGACY);
+	mlx5_eswitch_update_num_of_vfs(dev->priv.eswitch, num_vfs);
+	err = mlx5_eswitch_enable(dev->priv.eswitch, MLX5_ESWITCH_LEGACY);
 	if (err) {
 		mlx5_core_warn(dev,
 			       "failed to enable eswitch SRIOV (%d)\n", err);
@@ -99,7 +93,6 @@ enable_vfs_hca:
 			continue;
 		}
 		sriov->vfs_ctx[vf].enabled = 1;
-		sriov->enabled_vfs++;
 		if (MLX5_CAP_GEN(dev, port_type) == MLX5_CAP_PORT_TYPE_IB) {
 			err = sriov_restore_guids(dev, vf);
 			if (err) {
@@ -118,13 +111,11 @@ enable_vfs_hca:
 static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
+	int num_vfs = pci_num_vf(dev->pdev);
 	int err;
 	int vf;
 
-	if (!sriov->enabled_vfs)
-		goto out;
-
-	for (vf = 0; vf < sriov->num_vfs; vf++) {
+	for (vf = num_vfs - 1; vf >= 0; vf--) {
 		if (!sriov->vfs_ctx[vf].enabled)
 			continue;
 		err = mlx5_core_disable_hca(dev, vf + 1);
@@ -133,12 +124,10 @@ static void mlx5_device_disable_sriov(struct mlx5_core_dev *dev)
 			continue;
 		}
 		sriov->vfs_ctx[vf].enabled = 0;
-		sriov->enabled_vfs--;
 	}
 
-out:
 	if (MLX5_ESWITCH_MANAGER(dev))
-		mlx5_eswitch_disable_sriov(dev->priv.eswitch);
+		mlx5_eswitch_disable(dev->priv.eswitch);
 
 	if (mlx5_wait_for_pages(dev, &dev->priv.vfs_pages))
 		mlx5_core_warn(dev, "timeout reclaiming VFs pages\n");
@@ -191,13 +180,11 @@ int mlx5_core_sriov_configure(struct pci_dev *pdev, int num_vfs)
 
 int mlx5_sriov_attach(struct mlx5_core_dev *dev)
 {
-	struct mlx5_core_sriov *sriov = &dev->priv.sriov;
-
-	if (!mlx5_core_is_pf(dev) || !sriov->num_vfs)
+	if (!mlx5_core_is_pf(dev) || !pci_num_vf(dev->pdev))
 		return 0;
 
 	/* If sriov VFs exist in PCI level, enable them in device level */
-	return mlx5_device_enable_sriov(dev, sriov->num_vfs);
+	return mlx5_device_enable_sriov(dev, pci_num_vf(dev->pdev));
 }
 
 void mlx5_sriov_detach(struct mlx5_core_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 95cdc8cbcba4..670fa493c5f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -155,11 +155,12 @@ int mlx5_modify_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 }
 
 int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
-				     u16 vport, u8 *addr)
+				     u16 vport, bool other, u8 *addr)
 {
-	u32 *out;
 	int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out);
+	u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {};
 	u8 *out_addr;
+	u32 *out;
 	int err;
 
 	out = kvzalloc(outlen, GFP_KERNEL);
@@ -169,7 +170,12 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 	out_addr = MLX5_ADDR_OF(query_nic_vport_context_out, out,
 				nic_vport_context.permanent_address);
 
-	err = mlx5_query_nic_vport_context(mdev, vport, out, outlen);
+	MLX5_SET(query_nic_vport_context_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
+	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
+	MLX5_SET(query_nic_vport_context_in, in, other_vport, other);
+
+	err = mlx5_cmd_exec(mdev, in, sizeof(in), out, outlen);
 	if (!err)
 		ether_addr_copy(addr, &out_addr[2]);
 
@@ -178,6 +184,12 @@ int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 }
 EXPORT_SYMBOL_GPL(mlx5_query_nic_vport_mac_address);
 
+int mlx5_query_mac_address(struct mlx5_core_dev *mdev, u8 *addr)
+{
+	return mlx5_query_nic_vport_mac_address(mdev, 0, false, addr);
+}
+EXPORT_SYMBOL_GPL(mlx5_query_mac_address);
+
 int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				      u16 vport, u8 *addr)
 {
@@ -194,9 +206,7 @@ int mlx5_modify_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 field_select.permanent_address, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
-
-	if (vport)
-		MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
 
 	nic_vport_ctx = MLX5_ADDR_OF(modify_nic_vport_context_in,
 				     in, nic_vport_context);
@@ -291,9 +301,7 @@ int mlx5_query_nic_vport_mac_list(struct mlx5_core_dev *dev,
 		 MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT);
 	MLX5_SET(query_nic_vport_context_in, in, allowed_list_type, list_type);
 	MLX5_SET(query_nic_vport_context_in, in, vport_number, vport);
-
-	if (vport)
-		MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
+	MLX5_SET(query_nic_vport_context_in, in, other_vport, 1);
 
 	err = mlx5_cmd_exec(dev, in, sizeof(in), out, out_sz);
 	if (err)
@@ -483,7 +491,7 @@ int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 	MLX5_SET(modify_nic_vport_context_in, in,
 		 field_select.node_guid, 1);
 	MLX5_SET(modify_nic_vport_context_in, in, vport_number, vport);
-	MLX5_SET(modify_nic_vport_context_in, in, other_vport, !!vport);
+	MLX5_SET(modify_nic_vport_context_in, in, other_vport, 1);
 
 	nic_vport_context = MLX5_ADDR_OF(modify_nic_vport_context_in,
 					 in, nic_vport_context);
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 769326ea1d9b..40748fc1b11b 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -47,7 +47,7 @@ struct mlx5_core_cq {
 	struct completion	free;
 	unsigned		vector;
 	unsigned int		irqn;
-	void (*comp)		(struct mlx5_core_cq *);
+	void (*comp)(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe);
 	void (*event)		(struct mlx5_core_cq *, enum mlx5_event);
 	u32			cons_index;
 	unsigned		arm_sn;
@@ -55,7 +55,7 @@ struct mlx5_core_cq {
 	int			pid;
 	struct {
 		struct list_head list;
-		void (*comp)(struct mlx5_core_cq *);
+		void (*comp)(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe);
 		void		*priv;
 	} tasklet_ctx;
 	int			reset_notify_added;
@@ -185,7 +185,7 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq)
 }
 
 int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
-			u32 *in, int inlen);
+			u32 *in, int inlen, u32 *out, int outlen);
 int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq);
 int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 		       u32 *out, int outlen);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 5e760067ac41..0d1abe097627 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -351,7 +351,7 @@ enum mlx5_event {
 
 	MLX5_EVENT_TYPE_DEVICE_TRACER      = 0x26,
 
-	MLX5_EVENT_TYPE_MAX                = MLX5_EVENT_TYPE_DEVICE_TRACER + 1,
+	MLX5_EVENT_TYPE_MAX                = 0x100,
 };
 
 enum {
@@ -1077,6 +1077,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_DEBUG,
 	MLX5_CAP_RESERVED_14,
 	MLX5_CAP_DEV_MEM,
+	MLX5_CAP_DEV_EVENT = 0x14,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1255,6 +1256,9 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP64_DEV_MEM(mdev, cap)\
 	MLX5_GET64(device_mem_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_MEM], cap)
 
+#define MLX5_CAP_DEV_EVENT(mdev, cap)\
+	MLX5_ADDR_OF(device_event_cap, (mdev)->caps.hca_cur[MLX5_CAP_DEV_EVENT], cap)
+
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
 	MLX5_CMD_STAT_INT_ERR			= 0x1,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index d8ab633406c2..24b02ab206c3 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -41,7 +41,7 @@
 #include <linux/semaphore.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <linux/radix-tree.h>
+#include <linux/xarray.h>
 #include <linux/workqueue.h>
 #include <linux/mempool.h>
 #include <linux/interrupt.h>
@@ -138,6 +138,7 @@ enum {
 	MLX5_REG_MTPPS		 = 0x9053,
 	MLX5_REG_MTPPSE		 = 0x9054,
 	MLX5_REG_MPEGC		 = 0x9056,
+	MLX5_REG_MCQS		 = 0x9060,
 	MLX5_REG_MCQI		 = 0x9061,
 	MLX5_REG_MCC		 = 0x9062,
 	MLX5_REG_MCDA		 = 0x9063,
@@ -181,6 +182,11 @@ enum port_state_policy {
 	MLX5_POLICY_INVALID	= 0xffffffff
 };
 
+enum mlx5_coredev_type {
+	MLX5_COREDEV_PF,
+	MLX5_COREDEV_VF
+};
+
 struct mlx5_field_desc {
 	struct dentry	       *dent;
 	int			i;
@@ -452,13 +458,6 @@ struct mlx5_qp_table {
 	struct radix_tree_root	tree;
 };
 
-struct mlx5_mkey_table {
-	/* protect radix tree
-	 */
-	rwlock_t		lock;
-	struct radix_tree_root	tree;
-};
-
 struct mlx5_vf_context {
 	int	enabled;
 	u64	port_guid;
@@ -469,7 +468,6 @@ struct mlx5_vf_context {
 struct mlx5_core_sriov {
 	struct mlx5_vf_context	*vfs_ctx;
 	int			num_vfs;
-	int			enabled_vfs;
 	u16			max_vfs;
 };
 
@@ -546,9 +544,7 @@ struct mlx5_priv {
 	struct dentry	       *cmdif_debugfs;
 	/* end: qp staff */
 
-	/* start: mkey staff */
-	struct mlx5_mkey_table	mkey_table;
-	/* end: mkey staff */
+	struct xarray           mkey_table;
 
 	/* start: alloc staff */
 	/* protect buffer alocation according to numa node */
@@ -575,7 +571,6 @@ struct mlx5_priv {
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
 	struct mlx5_devcom	*devcom;
-	unsigned long		pci_dev_data;
 	struct mlx5_core_roce	roce;
 	struct mlx5_fc_stats		fc_stats;
 	struct mlx5_rl_table            rl_table;
@@ -654,6 +649,7 @@ struct mlx5_vxlan;
 
 struct mlx5_core_dev {
 	struct device *device;
+	enum mlx5_coredev_type coredev_type;
 	struct pci_dev	       *pdev;
 	/* sync pci state */
 	struct mutex		pci_status_mutex;
@@ -1047,6 +1043,8 @@ int mlx5_register_interface(struct mlx5_interface *intf);
 void mlx5_unregister_interface(struct mlx5_interface *intf);
 int mlx5_notifier_register(struct mlx5_core_dev *dev, struct notifier_block *nb);
 int mlx5_notifier_unregister(struct mlx5_core_dev *dev, struct notifier_block *nb);
+int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
+int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb);
 
 int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
 
@@ -1087,9 +1085,9 @@ enum {
 	MLX5_PCI_DEV_IS_VF		= 1 << 0,
 };
 
-static inline int mlx5_core_is_pf(struct mlx5_core_dev *dev)
+static inline bool mlx5_core_is_pf(struct mlx5_core_dev *dev)
 {
-	return !(dev->priv.pci_dev_data & MLX5_PCI_DEV_IS_VF);
+	return dev->coredev_type == MLX5_COREDEV_PF;
 }
 
 static inline bool mlx5_core_is_ecpf(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h
index 70e16dcfb4c4..e49d8c0d4f26 100644
--- a/include/linux/mlx5/eq.h
+++ b/include/linux/mlx5/eq.h
@@ -15,7 +15,7 @@ struct mlx5_core_dev;
 struct mlx5_eq_param {
 	u8             irq_index;
 	int            nent;
-	u64            mask;
+	u64            mask[4];
 };
 
 struct mlx5_eq *
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index ee1335ab1df0..43fa5594ba61 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -12,9 +12,9 @@
 #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
 
 enum {
-	SRIOV_NONE,
-	SRIOV_LEGACY,
-	SRIOV_OFFLOADS
+	MLX5_ESWITCH_NONE,
+	MLX5_ESWITCH_LEGACY,
+	MLX5_ESWITCH_OFFLOADS
 };
 
 enum {
@@ -46,6 +46,8 @@ struct mlx5_eswitch_rep {
 	u16		       vport;
 	u8		       hw_id[ETH_ALEN];
 	u16		       vlan;
+	/* Only IB rep is using vport_index */
+	u16		       vport_index;
 	u32		       vlan_refcount;
 };
 
@@ -67,11 +69,28 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *esw,
 #ifdef CONFIG_MLX5_ESWITCH
 enum devlink_eswitch_encap_mode
 mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev);
+
+bool mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw);
+u32 mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+					      u16 vport_num);
 #else  /* CONFIG_MLX5_ESWITCH */
 static inline enum devlink_eswitch_encap_mode
 mlx5_eswitch_get_encap_mode(const struct mlx5_core_dev *dev)
 {
 	return DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }
+
+static inline bool
+mlx5_eswitch_vport_match_metadata_enabled(const struct mlx5_eswitch *esw)
+{
+	return false;
+};
+
+static inline u32
+mlx5_eswitch_get_vport_metadata_for_match(const struct mlx5_eswitch *esw,
+					  int vport_num)
+{
+	return 0;
+};
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2ddaa97f2179..dc7e7aa53a13 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -88,10 +88,21 @@ struct mlx5_flow_group;
 struct mlx5_flow_namespace;
 struct mlx5_flow_handle;
 
+enum {
+	FLOW_CONTEXT_HAS_TAG = BIT(0),
+};
+
+struct mlx5_flow_context {
+	u32 flags;
+	u32 flow_tag;
+	u32 flow_source;
+};
+
 struct mlx5_flow_spec {
 	u8   match_criteria_enable;
 	u32  match_criteria[MLX5_ST_SZ_DW(fte_match_param)];
 	u32  match_value[MLX5_ST_SZ_DW(fte_match_param)];
+	struct mlx5_flow_context flow_context;
 };
 
 enum {
@@ -173,13 +184,11 @@ struct mlx5_fs_vlan {
 #define MLX5_FS_VLAN_DEPTH	2
 
 enum {
-	FLOW_ACT_HAS_TAG   = BIT(0),
-	FLOW_ACT_NO_APPEND = BIT(1),
+	FLOW_ACT_NO_APPEND = BIT(0),
 };
 
 struct mlx5_flow_act {
 	u32 action;
-	u32 flow_tag;
 	u32 reformat_id;
 	u32 modify_id;
 	uintptr_t esp_id;
@@ -190,7 +199,6 @@ struct mlx5_flow_act {
 
 #define MLX5_DECLARE_FLOW_ACT(name) \
 	struct mlx5_flow_act name = { .action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST,\
-				      .flow_tag = MLX5_FS_DEFAULT_FLOW_TAG, \
 				      .reformat_id = 0, \
 				      .modify_id = 0, \
 				      .flags =  0, }
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index e3c154b573a2..be92401a25a0 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -91,6 +91,20 @@ enum {
 
 enum {
 	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
+	MLX5_OBJ_TYPE_MKEY = 0xff01,
+	MLX5_OBJ_TYPE_QP = 0xff02,
+	MLX5_OBJ_TYPE_PSV = 0xff03,
+	MLX5_OBJ_TYPE_RMP = 0xff04,
+	MLX5_OBJ_TYPE_XRC_SRQ = 0xff05,
+	MLX5_OBJ_TYPE_RQ = 0xff06,
+	MLX5_OBJ_TYPE_SQ = 0xff07,
+	MLX5_OBJ_TYPE_TIR = 0xff08,
+	MLX5_OBJ_TYPE_TIS = 0xff09,
+	MLX5_OBJ_TYPE_DCT = 0xff0a,
+	MLX5_OBJ_TYPE_XRQ = 0xff0b,
+	MLX5_OBJ_TYPE_RQT = 0xff0e,
+	MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f,
+	MLX5_OBJ_TYPE_CQ = 0xff10,
 };
 
 enum {
@@ -106,6 +120,9 @@ enum {
 	MLX5_CMD_OP_QUERY_ISSI                    = 0x10a,
 	MLX5_CMD_OP_SET_ISSI                      = 0x10b,
 	MLX5_CMD_OP_SET_DRIVER_VERSION            = 0x10d,
+	MLX5_CMD_OP_QUERY_SF_PARTITION            = 0x111,
+	MLX5_CMD_OP_ALLOC_SF                      = 0x113,
+	MLX5_CMD_OP_DEALLOC_SF                    = 0x114,
 	MLX5_CMD_OP_CREATE_MKEY                   = 0x200,
 	MLX5_CMD_OP_QUERY_MKEY                    = 0x201,
 	MLX5_CMD_OP_DESTROY_MKEY                  = 0x202,
@@ -528,7 +545,21 @@ struct mlx5_ifc_fte_match_set_misc2_bits {
 
 	struct mlx5_ifc_fte_match_mpls_bits outer_first_mpls_over_udp;
 
-	u8         reserved_at_80[0x100];
+	u8         metadata_reg_c_7[0x20];
+
+	u8         metadata_reg_c_6[0x20];
+
+	u8         metadata_reg_c_5[0x20];
+
+	u8         metadata_reg_c_4[0x20];
+
+	u8         metadata_reg_c_3[0x20];
+
+	u8         metadata_reg_c_2[0x20];
+
+	u8         metadata_reg_c_1[0x20];
+
+	u8         metadata_reg_c_0[0x20];
 
 	u8         metadata_reg_a[0x20];
 
@@ -636,8 +667,22 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 	u8         reserved_at_e00[0x7200];
 };
 
+enum {
+	MLX5_FDB_TO_VPORT_REG_C_0 = 0x01,
+	MLX5_FDB_TO_VPORT_REG_C_1 = 0x02,
+	MLX5_FDB_TO_VPORT_REG_C_2 = 0x04,
+	MLX5_FDB_TO_VPORT_REG_C_3 = 0x08,
+	MLX5_FDB_TO_VPORT_REG_C_4 = 0x10,
+	MLX5_FDB_TO_VPORT_REG_C_5 = 0x20,
+	MLX5_FDB_TO_VPORT_REG_C_6 = 0x40,
+	MLX5_FDB_TO_VPORT_REG_C_7 = 0x80,
+};
+
 struct mlx5_ifc_flow_table_eswitch_cap_bits {
-	u8      reserved_at_0[0x1a];
+	u8      fdb_to_vport_reg_c_id[0x8];
+	u8      reserved_at_8[0xf];
+	u8      flow_source[0x1];
+	u8      reserved_at_18[0x2];
 	u8      multi_fdb_encap[0x1];
 	u8      reserved_at_1b[0x1];
 	u8      fdb_multi_path_to_table[0x1];
@@ -665,7 +710,9 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert_if_not_exist[0x1];
 	u8         vport_cvlan_insert_overwrite[0x1];
-	u8         reserved_at_5[0x14];
+	u8         reserved_at_5[0x3];
+	u8         esw_uplink_ingress_acl[0x1];
+	u8         reserved_at_9[0x10];
 	u8         esw_functions_changed[0x1];
 	u8         reserved_at_1a[0x1];
 	u8         ecpf_vport_exists[0x1];
@@ -683,7 +730,11 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         reserved_2b[0x6];
 	u8         max_encap_header_size[0xa];
 
-	u8         reserved_40[0x7c0];
+	u8         reserved_at_40[0xb];
+	u8         log_max_esw_sf[0x5];
+	u8         esw_sf_base_id[0x10];
+
+	u8         reserved_at_60[0x7a0];
 
 };
 
@@ -823,6 +874,12 @@ struct mlx5_ifc_device_mem_cap_bits {
 	u8         reserved_at_180[0x680];
 };
 
+struct mlx5_ifc_device_event_cap_bits {
+	u8         user_affiliated_events[4][0x40];
+
+	u8         user_unaffiliated_events[4][0x40];
+};
+
 enum {
 	MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_1_BYTE     = 0x0,
 	MLX5_ATOMIC_CAPS_ATOMIC_SIZE_QP_2_BYTES    = 0x2,
@@ -980,7 +1037,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_max_srq_sz[0x8];
 	u8         log_max_qp_sz[0x8];
-	u8         reserved_at_90[0x8];
+	u8         event_cap[0x1];
+	u8         reserved_at_91[0x7];
 	u8         prio_tag_required[0x1];
 	u8         reserved_at_99[0x2];
 	u8         log_max_qp[0x5];
@@ -1300,13 +1358,24 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_640[0x10];
 	u8         num_q_monitor_counters[0x10];
 
-	u8         reserved_at_660[0x40];
+	u8         reserved_at_660[0x20];
+
+	u8         sf[0x1];
+	u8         sf_set_partition[0x1];
+	u8         reserved_at_682[0x1];
+	u8         log_max_sf[0x5];
+	u8         reserved_at_688[0x8];
+	u8         log_min_sf_size[0x8];
+	u8         max_num_sf_partitions[0x8];
 
 	u8         uctx_cap[0x20];
 
 	u8         reserved_at_6c0[0x4];
 	u8         flex_parser_id_geneve_tlv_option_0[0x4];
-	u8         reserved_at_6c8[0x138];
+	u8	   reserved_at_6c8[0x28];
+	u8	   sf_base_id[0x10];
+
+	u8	   reserved_at_700[0x100];
 };
 
 enum mlx5_flow_destination_type {
@@ -2555,6 +2624,12 @@ enum {
 	MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2 = 0x800,
 };
 
+enum {
+	MLX5_FLOW_CONTEXT_FLOW_SOURCE_ANY_VPORT         = 0x0,
+	MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK            = 0x1,
+	MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT       = 0x2,
+};
+
 struct mlx5_ifc_vlan_bits {
 	u8         ethtype[0x10];
 	u8         prio[0x3];
@@ -2574,7 +2649,9 @@ struct mlx5_ifc_flow_context_bits {
 	u8         action[0x10];
 
 	u8         extended_destination[0x1];
-	u8         reserved_at_80[0x7];
+	u8         reserved_at_81[0x1];
+	u8         flow_source[0x2];
+	u8         reserved_at_84[0x4];
 	u8         destination_list_size[0x18];
 
 	u8         reserved_at_a0[0x8];
@@ -3099,12 +3176,14 @@ struct mlx5_ifc_hca_vport_context_bits {
 };
 
 struct mlx5_ifc_esw_vport_context_bits {
-	u8         reserved_at_0[0x3];
+	u8         fdb_to_vport_reg_c[0x1];
+	u8         reserved_at_1[0x2];
 	u8         vport_svlan_strip[0x1];
 	u8         vport_cvlan_strip[0x1];
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_insert[0x2];
-	u8         reserved_at_8[0x18];
+	u8         fdb_to_vport_reg_c_id[0x8];
+	u8         reserved_at_10[0x10];
 
 	u8         reserved_at_20[0x20];
 
@@ -4985,7 +5064,8 @@ struct mlx5_ifc_modify_esw_vport_context_out_bits {
 };
 
 struct mlx5_ifc_esw_vport_context_fields_select_bits {
-	u8         reserved_at_0[0x1c];
+	u8         reserved_at_0[0x1b];
+	u8         fdb_to_vport_reg_c_id[0x1];
 	u8         vport_cvlan_insert[0x1];
 	u8         vport_svlan_insert[0x1];
 	u8         vport_cvlan_strip[0x1];
@@ -5182,6 +5262,7 @@ enum {
 	MLX5_ACTION_IN_FIELD_OUT_DIPV4         = 0x16,
 	MLX5_ACTION_IN_FIELD_OUT_FIRST_VID     = 0x17,
 	MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT = 0x47,
+	MLX5_ACTION_IN_FIELD_METADATA_REG_C_0  = 0x51,
 };
 
 struct mlx5_ifc_alloc_modify_header_context_out_bits {
@@ -7362,9 +7443,9 @@ struct mlx5_ifc_create_eq_in_bits {
 
 	u8         reserved_at_280[0x40];
 
-	u8         event_bitmask[0x40];
+	u8         event_bitmask[4][0x40];
 
-	u8         reserved_at_300[0x580];
+	u8         reserved_at_3c0[0x4c0];
 
 	u8         pas[0][0x40];
 };
@@ -8482,7 +8563,7 @@ struct mlx5_ifc_mcam_access_reg_bits {
 	u8         mcda[0x1];
 	u8         mcc[0x1];
 	u8         mcqi[0x1];
-	u8         reserved_at_1f[0x1];
+	u8         mcqs[0x1];
 
 	u8         regs_95_to_87[0x9];
 	u8         mpegc[0x1];
@@ -8974,6 +9055,24 @@ struct mlx5_ifc_mtppse_reg_bits {
 	u8         reserved_at_40[0x40];
 };
 
+struct mlx5_ifc_mcqs_reg_bits {
+	u8         last_index_flag[0x1];
+	u8         reserved_at_1[0x7];
+	u8         fw_device[0x8];
+	u8         component_index[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         identifier[0x10];
+
+	u8         reserved_at_40[0x17];
+	u8         component_status[0x5];
+	u8         component_update_state[0x4];
+
+	u8         last_update_state_changer_type[0x4];
+	u8         last_update_state_changer_host_id[0x4];
+	u8         reserved_at_68[0x18];
+};
+
 struct mlx5_ifc_mcqi_cap_bits {
 	u8         supported_info_bitmask[0x20];
 
@@ -8994,6 +9093,43 @@ struct mlx5_ifc_mcqi_cap_bits {
 	u8         reserved_at_86[0x1a];
 };
 
+struct mlx5_ifc_mcqi_version_bits {
+	u8         reserved_at_0[0x2];
+	u8         build_time_valid[0x1];
+	u8         user_defined_time_valid[0x1];
+	u8         reserved_at_4[0x14];
+	u8         version_string_length[0x8];
+
+	u8         version[0x20];
+
+	u8         build_time[0x40];
+
+	u8         user_defined_time[0x40];
+
+	u8         build_tool_version[0x20];
+
+	u8         reserved_at_e0[0x20];
+
+	u8         version_string[92][0x8];
+};
+
+struct mlx5_ifc_mcqi_activation_method_bits {
+	u8         pending_server_ac_power_cycle[0x1];
+	u8         pending_server_dc_power_cycle[0x1];
+	u8         pending_server_reboot[0x1];
+	u8         pending_fw_reset[0x1];
+	u8         auto_activate[0x1];
+	u8         all_hosts_sync[0x1];
+	u8         device_hw_reset[0x1];
+	u8         reserved_at_7[0x19];
+};
+
+union mlx5_ifc_mcqi_reg_data_bits {
+	struct mlx5_ifc_mcqi_cap_bits               mcqi_caps;
+	struct mlx5_ifc_mcqi_version_bits           mcqi_version;
+	struct mlx5_ifc_mcqi_activation_method_bits mcqi_activation_mathod;
+};
+
 struct mlx5_ifc_mcqi_reg_bits {
 	u8         read_pending_component[0x1];
 	u8         reserved_at_1[0xf];
@@ -9011,7 +9147,7 @@ struct mlx5_ifc_mcqi_reg_bits {
 	u8         reserved_at_a0[0x10];
 	u8         data_size[0x10];
 
-	u8         data[0][0x20];
+	union mlx5_ifc_mcqi_reg_data_bits data[0];
 };
 
 struct mlx5_ifc_mcc_reg_bits {
@@ -9708,7 +9844,8 @@ struct mlx5_ifc_mtrc_ctrl_bits {
 
 struct mlx5_ifc_host_params_context_bits {
 	u8         host_number[0x8];
-	u8         reserved_at_8[0x8];
+	u8         reserved_at_8[0x7];
+	u8         host_pf_disabled[0x1];
 	u8         host_num_of_vfs[0x10];
 
 	u8         host_total_vfs[0x10];
@@ -9744,6 +9881,88 @@ struct mlx5_ifc_query_esw_functions_out_bits {
 	struct mlx5_ifc_host_params_context_bits host_params_context;
 
 	u8         reserved_at_280[0x180];
+	u8         host_sf_enable[0][0x40];
+};
+
+struct mlx5_ifc_sf_partition_bits {
+	u8         reserved_at_0[0x10];
+	u8         log_num_sf[0x8];
+	u8         log_sf_bar_size[0x8];
+};
+
+struct mlx5_ifc_query_sf_partitions_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x18];
+	u8         num_sf_partitions[0x8];
+
+	u8         reserved_at_60[0x20];
+
+	struct mlx5_ifc_sf_partition_bits sf_partition[0];
+};
+
+struct mlx5_ifc_query_sf_partitions_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_dealloc_sf_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_dealloc_sf_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         function_id[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_alloc_sf_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_alloc_sf_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         function_id[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_affiliated_event_header_bits {
+	u8         reserved_at_0[0x10];
+	u8         obj_type[0x10];
+
+	u8         obj_id[0x20];
 };
 
 #endif /* MLX5_IFC_H */
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index 08e43cd9e742..90f5f889742d 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -552,11 +552,6 @@ static inline struct mlx5_core_qp *__mlx5_qp_lookup(struct mlx5_core_dev *dev, u
 	return radix_tree_lookup(&dev->priv.qp_table.tree, qpn);
 }
 
-static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key)
-{
-	return radix_tree_lookup(&dev->priv.mkey_table.tree, key);
-}
-
 int mlx5_core_create_dct(struct mlx5_core_dev *dev,
 			 struct mlx5_core_dct *qp,
 			 u32 *in, int inlen,
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 3d1c6cdbbba7..6cbf29229749 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -58,6 +58,7 @@ enum {
 	MLX5_CAP_INLINE_MODE_NOT_REQUIRED,
 };
 
+/* Vport number for each function must keep unchanged */
 enum {
 	MLX5_VPORT_PF			= 0x0,
 	MLX5_VPORT_FIRST_VF		= 0x1,
@@ -69,7 +70,8 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport);
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 other_vport, u8 state);
 int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
-				     u16 vport, u8 *addr);
+				     u16 vport, bool other, u8 *addr);
+int mlx5_query_mac_address(struct mlx5_core_dev *mdev, u8 *addr);
 int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev,
 				    u16 vport, u8 *min_inline);
 void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline);