Merge branch 'mlx5-hardware-steering-part-2'

Tariq Toukan says:

====================
mlx5 Hardware Steering part 2

This series contain HWS code cleanups, enhancements, bug fixes, and
additions. Note that some of these patches are fixing bugs in existing
code, but we submit them without 'Fixes' tag to avoid the unnecessary
burden for stable releases, as HWS still couldn't be enabled.

Patches 1-5:
HWS, various code cleanups and enhancements

Patches 6-14:
HWS, various bug fixes and additions

Patch 15:
HWS, setting timeout on polling
====================

Link: https://patch.msgid.link/20250102181415.1477316-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

19 files changed, 227 insertions, 299 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
index a897cdc60fdb..b5332c54d4fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.c
@@ -11,31 +11,29 @@
 /* This is the longest supported action sequence for FDB table:
  * DECAP, POP_VLAN, MODIFY, CTR, ASO, PUSH_VLAN, MODIFY, ENCAP, Term.
  */
-static const u32 action_order_arr[MLX5HWS_TABLE_TYPE_MAX][MLX5HWS_ACTION_TYP_MAX] = {
-	[MLX5HWS_TABLE_TYPE_FDB] = {
-		BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2),
-		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
-		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
-		BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) |
-		BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3),
-		BIT(MLX5HWS_ACTION_TYP_CTR),
-		BIT(MLX5HWS_ACTION_TYP_TAG),
-		BIT(MLX5HWS_ACTION_TYP_ASO_METER),
-		BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
-		BIT(MLX5HWS_ACTION_TYP_TBL) |
-		BIT(MLX5HWS_ACTION_TYP_VPORT) |
-		BIT(MLX5HWS_ACTION_TYP_DROP) |
-		BIT(MLX5HWS_ACTION_TYP_SAMPLER) |
-		BIT(MLX5HWS_ACTION_TYP_RANGE) |
-		BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY),
-		BIT(MLX5HWS_ACTION_TYP_LAST),
-	},
+static const u32 action_order_arr[MLX5HWS_ACTION_TYP_MAX] = {
+	BIT(MLX5HWS_ACTION_TYP_REMOVE_HEADER) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L2_TO_L2) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2),
+	BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_POP_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+	BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_PUSH_VLAN),
+	BIT(MLX5HWS_ACTION_TYP_INSERT_HEADER) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L2) |
+	BIT(MLX5HWS_ACTION_TYP_REFORMAT_L2_TO_TNL_L3),
+	BIT(MLX5HWS_ACTION_TYP_CTR),
+	BIT(MLX5HWS_ACTION_TYP_TAG),
+	BIT(MLX5HWS_ACTION_TYP_ASO_METER),
+	BIT(MLX5HWS_ACTION_TYP_MODIFY_HDR),
+	BIT(MLX5HWS_ACTION_TYP_TBL) |
+	BIT(MLX5HWS_ACTION_TYP_VPORT) |
+	BIT(MLX5HWS_ACTION_TYP_DROP) |
+	BIT(MLX5HWS_ACTION_TYP_SAMPLER) |
+	BIT(MLX5HWS_ACTION_TYP_RANGE) |
+	BIT(MLX5HWS_ACTION_TYP_DEST_ARRAY),
+	BIT(MLX5HWS_ACTION_TYP_LAST),
 };
 
 static const char * const mlx5hws_action_type_str[] = {
@@ -83,8 +81,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 	int ret;
 
 	mutex_lock(&ctx->ctrl_lock);
-	if (ctx->common_res[tbl_type].shared_stc[stc_type]) {
-		ctx->common_res[tbl_type].shared_stc[stc_type]->refcount++;
+	if (ctx->common_res.shared_stc[stc_type]) {
+		ctx->common_res.shared_stc[stc_type]->refcount++;
 		mutex_unlock(&ctx->ctrl_lock);
 		return 0;
 	}
@@ -124,8 +122,8 @@ static int hws_action_get_shared_stc_nic(struct mlx5hws_context *ctx,
 		goto free_shared_stc;
 	}
 
-	ctx->common_res[tbl_type].shared_stc[stc_type] = shared_stc;
-	ctx->common_res[tbl_type].shared_stc[stc_type]->refcount = 1;
+	ctx->common_res.shared_stc[stc_type] = shared_stc;
+	ctx->common_res.shared_stc[stc_type]->refcount = 1;
 
 	mutex_unlock(&ctx->ctrl_lock);
 
@@ -178,16 +176,16 @@ static void hws_action_put_shared_stc(struct mlx5hws_action *action,
 	}
 
 	mutex_lock(&ctx->ctrl_lock);
-	if (--ctx->common_res[tbl_type].shared_stc[stc_type]->refcount) {
+	if (--ctx->common_res.shared_stc[stc_type]->refcount) {
 		mutex_unlock(&ctx->ctrl_lock);
 		return;
 	}
 
-	shared_stc = ctx->common_res[tbl_type].shared_stc[stc_type];
+	shared_stc = ctx->common_res.shared_stc[stc_type];
 
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &shared_stc->stc_chunk);
 	kfree(shared_stc);
-	ctx->common_res[tbl_type].shared_stc[stc_type] = NULL;
+	ctx->common_res.shared_stc[stc_type] = NULL;
 	mutex_unlock(&ctx->ctrl_lock);
 }
 
@@ -206,10 +204,10 @@ bool mlx5hws_action_check_combo(struct mlx5hws_context *ctx,
 				enum mlx5hws_action_type *user_actions,
 				enum mlx5hws_table_type table_type)
 {
-	const u32 *order_arr = action_order_arr[table_type];
+	const u32 *order_arr = action_order_arr;
+	bool valid_combo;
 	u8 order_idx = 0;
 	u8 user_idx = 0;
-	bool valid_combo;
 
 	if (table_type >= MLX5HWS_TABLE_TYPE_MAX) {
 		mlx5hws_err(ctx, "Invalid table_type %d", table_type);
@@ -321,8 +319,8 @@ int mlx5hws_action_alloc_single_stc(struct mlx5hws_context *ctx,
 __must_hold(&ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_stc_modify_attr cleanup_stc_attr = {0};
-	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
 	struct mlx5hws_cmd_stc_modify_attr fixup_stc_attr = {0};
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	bool use_fixup;
 	u32 obj_0_id;
 	int ret;
@@ -387,8 +385,8 @@ void mlx5hws_action_free_single_stc(struct mlx5hws_context *ctx,
 				    struct mlx5hws_pool_chunk *stc)
 __must_hold(&ctx->ctrl_lock)
 {
-	struct mlx5hws_pool *stc_pool = ctx->stc_pool[table_type];
 	struct mlx5hws_cmd_stc_modify_attr stc_attr = {0};
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	u32 obj_id;
 
 	/* Modify the STC not to point to an object */
@@ -473,6 +471,7 @@ static void hws_action_fill_stc_attr(struct mlx5hws_action *action,
 		break;
 	case MLX5HWS_ACTION_TYP_TBL:
 	case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+	case MLX5HWS_ACTION_TYP_SAMPLER:
 		attr->action_type = MLX5_IFC_STC_ACTION_TYPE_JUMP_TO_FT;
 		attr->action_offset = MLX5HWS_ACTION_OFFSET_HIT;
 		attr->dest_table_id = obj_id;
@@ -561,7 +560,7 @@ hws_action_create_stcs(struct mlx5hws_action *action, u32 obj_id)
 	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB) {
 		ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr,
 						      MLX5HWS_TABLE_TYPE_FDB,
-						      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+						      &action->stc);
 		if (ret)
 			goto out_err;
 	}
@@ -585,7 +584,7 @@ hws_action_destroy_stcs(struct mlx5hws_action *action)
 
 	if (action->flags & MLX5HWS_ACTION_FLAG_HWS_FDB)
 		mlx5hws_action_free_single_stc(ctx, MLX5HWS_TABLE_TYPE_FDB,
-					       &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+					       &action->stc);
 
 	mutex_unlock(&ctx->ctrl_lock);
 }
@@ -1639,8 +1638,8 @@ hws_action_create_dest_match_range_table(struct mlx5hws_context *ctx,
 	rtc_attr.table_type = mlx5hws_table_get_res_fw_ft_type(MLX5HWS_TABLE_TYPE_FDB, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
-	stc_pool = ctx->stc_pool[MLX5HWS_TABLE_TYPE_FDB];
-	default_stc = ctx->common_res[MLX5HWS_TABLE_TYPE_FDB].default_stc;
+	stc_pool = ctx->stc_pool;
+	default_stc = ctx->common_res.default_stc;
 	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
 	rtc_attr.stc_base = obj_id;
 
@@ -1731,7 +1730,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
 	ste_attr.used_id_rtc_0 = &used_rtc_0_id;
 	ste_attr.used_id_rtc_1 = &used_rtc_1_id;
 
-	common_res = &ctx->common_res[MLX5HWS_TABLE_TYPE_FDB];
+	common_res = &ctx->common_res;
 
 	/* init an empty match STE which will always hit */
 	ste_attr.wqe_ctrl = &wqe_ctrl;
@@ -1750,7 +1749,7 @@ hws_action_create_dest_match_range_fill_table(struct mlx5hws_context *ctx,
 	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_CTRL] |=
 		htonl(MLX5HWS_ACTION_STC_IDX_LAST_COMBO2 << 29);
 	wqe_ctrl.stc_ix[MLX5HWS_ACTION_STC_IDX_HIT] =
-		htonl(hit_ft_action->stc[MLX5HWS_TABLE_TYPE_FDB].offset);
+		htonl(hit_ft_action->stc.offset);
 
 	wqe_data_arr = (__force __be32 *)&range_wqe_data;
 
@@ -1843,7 +1842,7 @@ mlx5hws_action_create_dest_match_range(struct mlx5hws_context *ctx,
 	stc_attr.ste_table.match_definer_id = ctx->caps->trivial_match_definer;
 
 	ret = mlx5hws_action_alloc_single_stc(ctx, &stc_attr, MLX5HWS_TABLE_TYPE_FDB,
-					      &action->stc[MLX5HWS_TABLE_TYPE_FDB]);
+					      &action->stc);
 	if (ret)
 		goto error_unlock;
 
@@ -1875,7 +1874,50 @@ struct mlx5hws_action *
 mlx5hws_action_create_flow_sampler(struct mlx5hws_context *ctx,
 				   u32 sampler_id, u32 flags)
 {
-	mlx5hws_err(ctx, "Flow sampler action - unsupported\n");
+	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
+	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
+	struct mlx5hws_cmd_forward_tbl *fw_island;
+	struct mlx5hws_cmd_set_fte_dest dest;
+	struct mlx5hws_action *action;
+	int ret;
+
+	if (flags != (MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED)) {
+		mlx5hws_err(ctx, "Unsupported flags for flow sampler\n");
+		return NULL;
+	}
+
+	ft_attr.type = FS_FT_FDB;
+	ft_attr.level = ctx->caps->fdb_ft.max_level - 1;
+
+	dest.destination_type = MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER;
+	dest.destination_id = sampler_id;
+
+	fte_attr.dests_num = 1;
+	fte_attr.dests = &dest;
+	fte_attr.action_flags = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	fte_attr.ignore_flow_level = 1;
+
+	fw_island = mlx5hws_cmd_forward_tbl_create(ctx->mdev, &ft_attr, &fte_attr);
+	if (!fw_island)
+		return NULL;
+
+	action = hws_action_create_generic(ctx, flags,
+					   MLX5HWS_ACTION_TYP_SAMPLER);
+	if (!action)
+		goto destroy_fw_island;
+
+	ret = hws_action_create_stcs(action, fw_island->ft_id);
+	if (ret)
+		goto free_action;
+
+	action->flow_sampler.fw_island = fw_island;
+
+	return action;
+
+free_action:
+	kfree(action);
+destroy_fw_island:
+	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, fw_island);
 	return NULL;
 }
 
@@ -1914,6 +1956,11 @@ static void hws_action_destroy_hws(struct mlx5hws_action *action)
 		}
 		kfree(action->dest_array.dest_list);
 		break;
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		hws_action_destroy_stcs(action);
+		mlx5hws_cmd_forward_tbl_destroy(action->ctx->mdev,
+						action->flow_sampler.fw_island);
+		break;
 	case MLX5HWS_ACTION_TYP_REFORMAT_TNL_L3_TO_L2:
 	case MLX5HWS_ACTION_TYP_MODIFY_HDR:
 		shared_arg = false;
@@ -1970,8 +2017,8 @@ __must_hold(&ctx->ctrl_lock)
 	struct mlx5hws_action_default_stc *default_stc;
 	int ret;
 
-	if (ctx->common_res[tbl_type].default_stc) {
-		ctx->common_res[tbl_type].default_stc->refcount++;
+	if (ctx->common_res.default_stc) {
+		ctx->common_res.default_stc->refcount++;
 		return 0;
 	}
 
@@ -2023,8 +2070,8 @@ __must_hold(&ctx->ctrl_lock)
 		goto free_nop_dw7;
 	}
 
-	ctx->common_res[tbl_type].default_stc = default_stc;
-	ctx->common_res[tbl_type].default_stc->refcount++;
+	ctx->common_res.default_stc = default_stc;
+	ctx->common_res.default_stc->refcount++;
 
 	return 0;
 
@@ -2046,9 +2093,7 @@ __must_hold(&ctx->ctrl_lock)
 {
 	struct mlx5hws_action_default_stc *default_stc;
 
-	default_stc = ctx->common_res[tbl_type].default_stc;
-
-	default_stc = ctx->common_res[tbl_type].default_stc;
+	default_stc = ctx->common_res.default_stc;
 	if (--default_stc->refcount)
 		return;
 
@@ -2058,7 +2103,7 @@ __must_hold(&ctx->ctrl_lock)
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_dw5);
 	mlx5hws_action_free_single_stc(ctx, tbl_type, &default_stc->nop_ctr);
 	kfree(default_stc);
-	ctx->common_res[tbl_type].default_stc = NULL;
+	ctx->common_res.default_stc = NULL;
 }
 
 static void hws_action_modify_write(struct mlx5hws_send_engine *queue,
@@ -2150,8 +2195,7 @@ hws_action_apply_stc(struct mlx5hws_actions_apply_data *apply,
 {
 	struct mlx5hws_action *action = apply->rule_action[action_idx].action;
 
-	apply->wqe_ctrl->stc_ix[stc_idx] =
-		htonl(action->stc[apply->tbl_type].offset);
+	apply->wqe_ctrl->stc_ix[stc_idx] = htonl(action->stc.offset);
 }
 
 static void
@@ -2181,7 +2225,7 @@ hws_action_setter_modify_header(struct mlx5hws_actions_apply_data *apply,
 	rule_action = &apply->rule_action[setter->idx_double];
 	action = rule_action->action;
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2240,7 +2284,7 @@ hws_action_setter_insert_ptr(struct mlx5hws_actions_apply_data *apply,
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2272,7 +2316,7 @@ hws_action_setter_tnl_l3_to_l2(struct mlx5hws_actions_apply_data *apply,
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW6] = 0;
 	apply->wqe_data[MLX5HWS_ACTION_OFFSET_DW7] = htonl(arg_idx);
 
-	stc_idx = htonl(action->stc[apply->tbl_type].offset);
+	stc_idx = htonl(action->stc.offset);
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW6] = stc_idx;
 	apply->wqe_ctrl->stc_ix[MLX5HWS_ACTION_STC_IDX_DW7] = 0;
 
@@ -2434,6 +2478,7 @@ int mlx5hws_action_template_process(struct mlx5hws_action_template *at)
 		case MLX5HWS_ACTION_TYP_DROP:
 		case MLX5HWS_ACTION_TYP_TBL:
 		case MLX5HWS_ACTION_TYP_DEST_ARRAY:
+		case MLX5HWS_ACTION_TYP_SAMPLER:
 		case MLX5HWS_ACTION_TYP_VPORT:
 		case MLX5HWS_ACTION_TYP_MISS:
 			/* Hit action */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
index e8f562c31826..64b76075f7f8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/action.h
@@ -70,12 +70,12 @@ struct mlx5hws_action_default_stc {
 	struct mlx5hws_pool_chunk nop_dw6;
 	struct mlx5hws_pool_chunk nop_dw7;
 	struct mlx5hws_pool_chunk default_hit;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_action_shared_stc {
 	struct mlx5hws_pool_chunk stc_chunk;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_actions_apply_data {
@@ -124,7 +124,7 @@ struct mlx5hws_action {
 	struct mlx5hws_context *ctx;
 	union {
 		struct {
-			struct mlx5hws_pool_chunk stc[MLX5HWS_TABLE_TYPE_MAX];
+			struct mlx5hws_pool_chunk stc;
 			union {
 				struct {
 					u32 pat_id;
@@ -166,6 +166,9 @@ struct mlx5hws_action {
 					struct mlx5hws_cmd_set_fte_dest *dest_list;
 				} dest_array;
 				struct {
+					struct mlx5hws_cmd_forward_tbl *fw_island;
+				} flow_sampler;
+				struct {
 					u8 type;
 					u8 start_anchor;
 					u8 end_anchor;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index baacf662c0ab..a8d886e92144 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -152,6 +152,8 @@ mlx5hws_bwc_matcher_create(struct mlx5hws_table *table,
 	if (!bwc_matcher)
 		return NULL;
 
+	atomic_set(&bwc_matcher->num_of_rules, 0);
+
 	/* Check if the required match params can be all matched
 	 * in single STE, otherwise complex matcher is needed.
 	 */
@@ -199,10 +201,12 @@ int mlx5hws_bwc_matcher_destroy_simple(struct mlx5hws_bwc_matcher *bwc_matcher)
 
 int mlx5hws_bwc_matcher_destroy(struct mlx5hws_bwc_matcher *bwc_matcher)
 {
-	if (bwc_matcher->num_of_rules)
+	u32 num_of_rules = atomic_read(&bwc_matcher->num_of_rules);
+
+	if (num_of_rules)
 		mlx5hws_err(bwc_matcher->matcher->tbl->ctx,
 			    "BWC matcher destroy: matcher still has %d rules\n",
-			    bwc_matcher->num_of_rules);
+			    num_of_rules);
 
 	mlx5hws_bwc_matcher_destroy_simple(bwc_matcher);
 
@@ -215,6 +219,8 @@ static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
 			      u32 *pending_rules,
 			      bool drain)
 {
+	unsigned long timeout = jiffies +
+				msecs_to_jiffies(MLX5HWS_BWC_POLLING_TIMEOUT * MSEC_PER_SEC);
 	struct mlx5hws_flow_op_result comp[MLX5HWS_BWC_MATCHER_REHASH_BURST_TH];
 	u16 burst_th = hws_bwc_get_burst_th(ctx, queue_id);
 	bool got_comp = *pending_rules >= burst_th;
@@ -250,6 +256,11 @@ static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
 		}
 
 		got_comp = !!ret;
+
+		if (unlikely(!got_comp && time_after(jiffies, timeout))) {
+			mlx5hws_err(ctx, "BWC poll error: polling queue %d - TIMEOUT\n", queue_id);
+			return -ETIMEDOUT;
+		}
 	}
 
 	return err;
@@ -309,7 +320,7 @@ static void hws_bwc_rule_list_add(struct mlx5hws_bwc_rule *bwc_rule, u16 idx)
 {
 	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
 
-	bwc_matcher->num_of_rules++;
+	atomic_inc(&bwc_matcher->num_of_rules);
 	bwc_rule->bwc_queue_idx = idx;
 	list_add(&bwc_rule->list_node, &bwc_matcher->rules[idx]);
 }
@@ -318,7 +329,7 @@ static void hws_bwc_rule_list_remove(struct mlx5hws_bwc_rule *bwc_rule)
 {
 	struct mlx5hws_bwc_matcher *bwc_matcher = bwc_rule->bwc_matcher;
 
-	bwc_matcher->num_of_rules--;
+	atomic_dec(&bwc_matcher->num_of_rules);
 	list_del_init(&bwc_rule->list_node);
 }
 
@@ -334,22 +345,21 @@ hws_bwc_rule_destroy_hws_sync(struct mlx5hws_bwc_rule *bwc_rule,
 			      struct mlx5hws_rule_attr *rule_attr)
 {
 	struct mlx5hws_context *ctx = bwc_rule->bwc_matcher->matcher->tbl->ctx;
-	struct mlx5hws_flow_op_result completion;
+	u32 expected_completions = 1;
 	int ret;
 
 	ret = hws_bwc_rule_destroy_hws_async(bwc_rule, rule_attr);
 	if (unlikely(ret))
 		return ret;
 
-	do {
-		ret = mlx5hws_send_queue_poll(ctx, rule_attr->queue_id, &completion, 1);
-	} while (ret != 1);
-
-	if (unlikely(completion.status != MLX5HWS_FLOW_OP_SUCCESS ||
-		     (bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED &&
-		      bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING))) {
-		mlx5hws_err(ctx, "Failed destroying BWC rule: completion %d, rule status %d\n",
-			    completion.status, bwc_rule->rule->status);
+	ret = hws_bwc_queue_poll(ctx, rule_attr->queue_id, &expected_completions, true);
+	if (unlikely(ret))
+		return ret;
+
+	if (unlikely(bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETED &&
+		     bwc_rule->rule->status != MLX5HWS_RULE_STATUS_DELETING)) {
+		mlx5hws_err(ctx, "Failed destroying BWC rule: rule status %d\n",
+			    bwc_rule->rule->status);
 		return -EINVAL;
 	}
 
@@ -615,8 +625,12 @@ static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_match
 
 				ret = hws_bwc_queue_poll(ctx, rule_attr.queue_id,
 							 &pending_rules[i], false);
-				if (unlikely(ret))
+				if (unlikely(ret)) {
+					mlx5hws_err(ctx,
+						    "Moving BWC rule failed during rehash (%d)\n",
+						    ret);
 					goto free_bwc_rules;
+				}
 			}
 		}
 	} while (!all_done);
@@ -629,8 +643,11 @@ static int hws_bwc_matcher_move_all_simple(struct mlx5hws_bwc_matcher *bwc_match
 			mlx5hws_send_engine_flush_queue(&ctx->send_queue[queue_id]);
 			ret = hws_bwc_queue_poll(ctx, queue_id,
 						 &pending_rules[i], true);
-			if (unlikely(ret))
+			if (unlikely(ret)) {
+				mlx5hws_err(ctx,
+					    "Moving BWC rule failed during rehash (%d)\n", ret);
 				goto free_bwc_rules;
+			}
 		}
 	}
 
@@ -704,7 +721,8 @@ hws_bwc_matcher_rehash_size(struct mlx5hws_bwc_matcher *bwc_matcher)
 	 * Need to check again if we really need rehash.
 	 * If the reason for rehash was size, but not any more - skip rehash.
 	 */
-	if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher, bwc_matcher->num_of_rules))
+	if (!hws_bwc_matcher_rehash_size_needed(bwc_matcher,
+						atomic_read(&bwc_matcher->num_of_rules)))
 		return 0;
 
 	/* Now we're done all the checking - do the rehash:
@@ -797,7 +815,7 @@ int mlx5hws_bwc_rule_create_simple(struct mlx5hws_bwc_rule *bwc_rule,
 	}
 
 	/* check if number of rules require rehash */
-	num_of_rules = bwc_matcher->num_of_rules;
+	num_of_rules = atomic_read(&bwc_matcher->num_of_rules);
 
 	if (unlikely(hws_bwc_matcher_rehash_size_needed(bwc_matcher, num_of_rules))) {
 		mutex_unlock(queue_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
index 3d4965213b01..f9f569131dde 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
@@ -8,10 +8,18 @@
 #define MLX5HWS_BWC_MATCHER_SIZE_LOG_STEP 1
 #define MLX5HWS_BWC_MATCHER_REHASH_PERCENT_TH 70
 #define MLX5HWS_BWC_MATCHER_REHASH_BURST_TH 32
-#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 255
+
+/* Max number of AT attach operations for the same matcher.
+ * When the limit is reached, next attempt to attach new AT
+ * will result in creation of a new matcher and moving all
+ * the rules to this matcher.
+ */
+#define MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM 8
 
 #define MLX5HWS_BWC_MAX_ACTS 16
 
+#define MLX5HWS_BWC_POLLING_TIMEOUT 60
+
 struct mlx5hws_bwc_matcher {
 	struct mlx5hws_matcher *matcher;
 	struct mlx5hws_match_template *mt;
@@ -19,7 +27,7 @@ struct mlx5hws_bwc_matcher {
 	u8 num_of_at;
 	u16 priority;
 	u8 size_log;
-	u32 num_of_rules; /* atomically accessed */
+	atomic_t num_of_rules;
 	struct list_head *rules;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
index c00c138c3366..487e75476b0a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
@@ -257,6 +257,12 @@ int mlx5hws_cmd_set_fte(struct mlx5_core_dev *mdev,
 						 dest->ext_reformat_id);
 				}
 				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+				MLX5_SET(dest_format, in_dests,
+					 destination_type, ifc_dest_type);
+				MLX5_SET(dest_format, in_dests, destination_id,
+					 dest->destination_id);
+				break;
 			default:
 				ret = -EOPNOTSUPP;
 				goto out;
@@ -359,7 +365,7 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
 	ft_attr->type = fw_ft_type;
 	ft_attr->table_miss_action = MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL;
 
-	default_miss_tbl = ctx->common_res[type].default_miss->ft_id;
+	default_miss_tbl = ctx->common_res.default_miss->ft_id;
 	if (!default_miss_tbl) {
 		pr_warn("HWS: no flow table ID for default miss\n");
 		return;
@@ -622,12 +628,12 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
 			   u32 pd,
 			   u32 *arg_id)
 {
+	u32 in[MLX5_ST_SZ_DW(create_modify_header_arg_in)] = {0};
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_arg_in)] = {0};
 	void *attr;
 	int ret;
 
-	attr = MLX5_ADDR_OF(create_arg_in, in, hdr);
+	attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, hdr);
 	MLX5_SET(general_obj_in_cmd_hdr,
 		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
 	MLX5_SET(general_obj_in_cmd_hdr,
@@ -635,8 +641,8 @@ int mlx5hws_cmd_arg_create(struct mlx5_core_dev *mdev,
 	MLX5_SET(general_obj_in_cmd_hdr,
 		 attr, op_param.create.log_obj_range, log_obj_range);
 
-	attr = MLX5_ADDR_OF(create_arg_in, in, arg);
-	MLX5_SET(arg, attr, access_pd, pd);
+	attr = MLX5_ADDR_OF(create_modify_header_arg_in, in, arg);
+	MLX5_SET(modify_header_arg, attr, access_pd, pd);
 
 	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 	if (ret) {
@@ -812,7 +818,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
 				       struct mlx5hws_cmd_packet_reformat_create_attr *attr,
 				       u32 *reformat_id)
 {
-	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_out)] = {0};
+	u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {0};
 	size_t insz, cmd_data_sz, cmd_total_sz;
 	void *prctx;
 	void *pdata;
@@ -845,7 +851,7 @@ int mlx5hws_cmd_packet_reformat_create(struct mlx5_core_dev *mdev,
 		goto out;
 	}
 
-	*reformat_id = MLX5_GET(alloc_packet_reformat_out, out, packet_reformat_id);
+	*reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id);
 out:
 	kfree(in);
 	return ret;
@@ -854,13 +860,13 @@ out:
 int mlx5hws_cmd_packet_reformat_destroy(struct mlx5_core_dev *mdev,
 					u32 reformat_id)
 {
-	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_in)] = {0};
+	u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {0};
+	u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {0};
 	int ret;
 
-	MLX5_SET(dealloc_packet_reformat_in, in, opcode,
+	MLX5_SET(dealloc_packet_reformat_context_in, in, opcode,
 		 MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT);
-	MLX5_SET(dealloc_packet_reformat_in, in,
+	MLX5_SET(dealloc_packet_reformat_context_in, in,
 		 packet_reformat_id, reformat_id);
 
 	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
@@ -889,73 +895,6 @@ int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn)
 	return ret;
 }
 
-int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
-					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr)
-{
-	u32 out[MLX5_ST_SZ_DW(allow_other_vhca_access_out)] = {0};
-	u32 in[MLX5_ST_SZ_DW(allow_other_vhca_access_in)] = {0};
-	void *key;
-	int ret;
-
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, opcode, MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS);
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, object_type_to_be_accessed, attr->obj_type);
-	MLX5_SET(allow_other_vhca_access_in,
-		 in, object_id_to_be_accessed, attr->obj_id);
-
-	key = MLX5_ADDR_OF(allow_other_vhca_access_in, in, access_key);
-	memcpy(key, attr->access_key, sizeof(attr->access_key));
-
-	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-	if (ret)
-		mlx5_core_err(mdev, "Failed to execute ALLOW_OTHER_VHCA_ACCESS command\n");
-
-	return ret;
-}
-
-int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
-				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
-				 u32 *obj_id)
-{
-	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {0};
-	u32 in[MLX5_ST_SZ_DW(create_alias_obj_in)] = {0};
-	void *attr;
-	void *key;
-	int ret;
-
-	attr = MLX5_ADDR_OF(create_alias_obj_in, in, hdr);
-	MLX5_SET(general_obj_in_cmd_hdr,
-		 attr, opcode, MLX5_CMD_OP_CREATE_GENERAL_OBJECT);
-	MLX5_SET(general_obj_in_cmd_hdr,
-		 attr, obj_type, alias_attr->obj_type);
-	MLX5_SET(general_obj_in_cmd_hdr, attr, op_param.create.alias_object, 1);
-
-	attr = MLX5_ADDR_OF(create_alias_obj_in, in, alias_ctx);
-	MLX5_SET(alias_context, attr, vhca_id_to_be_accessed, alias_attr->vhca_id);
-	MLX5_SET(alias_context, attr, object_id_to_be_accessed, alias_attr->obj_id);
-
-	key = MLX5_ADDR_OF(alias_context, attr, access_key);
-	memcpy(key, alias_attr->access_key, sizeof(alias_attr->access_key));
-
-	ret = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-	if (ret) {
-		mlx5_core_err(mdev, "Failed to create ALIAS OBJ\n");
-		goto out;
-	}
-
-	*obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id);
-out:
-	return ret;
-}
-
-int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
-				  u16 obj_type,
-				  u32 obj_id)
-{
-	return hws_cmd_general_obj_destroy(mdev, obj_type, obj_id);
-}
-
 int mlx5hws_cmd_generate_wqe(struct mlx5_core_dev *mdev,
 			     struct mlx5hws_cmd_generate_wqe_attr *attr,
 			     struct mlx5_cqe64 *ret_cqe)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
index 434f62b0904e..610c63d81ad9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
@@ -63,7 +63,7 @@ struct mlx5hws_cmd_forward_tbl {
 	u8 type;
 	u32 ft_id;
 	u32 fg_id;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 };
 
 struct mlx5hws_cmd_rtc_create_attr {
@@ -334,14 +334,6 @@ mlx5hws_cmd_forward_tbl_create(struct mlx5_core_dev *mdev,
 void mlx5hws_cmd_forward_tbl_destroy(struct mlx5_core_dev *mdev,
 				     struct mlx5hws_cmd_forward_tbl *tbl);
 
-int mlx5hws_cmd_alias_obj_create(struct mlx5_core_dev *mdev,
-				 struct mlx5hws_cmd_alias_obj_create_attr *alias_attr,
-				 u32 *obj_id);
-
-int mlx5hws_cmd_alias_obj_destroy(struct mlx5_core_dev *mdev,
-				  u16 obj_type,
-				  u32 obj_id);
-
 int mlx5hws_cmd_sq_modify_rdy(struct mlx5_core_dev *mdev, u32 sqn);
 
 int mlx5hws_cmd_query_caps(struct mlx5_core_dev *mdev,
@@ -352,9 +344,6 @@ void mlx5hws_cmd_set_attr_connect_miss_tbl(struct mlx5hws_context *ctx,
 					   enum mlx5hws_table_type type,
 					   struct mlx5hws_cmd_ft_modify_attr *ft_attr);
 
-int mlx5hws_cmd_allow_other_vhca_access(struct mlx5_core_dev *mdev,
-					struct mlx5hws_cmd_allow_other_vhca_access_attr *attr);
-
 int mlx5hws_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_function,
 			   u16 vport_number, u16 *gvmi);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
index 4a8928f33bb9..9cda2774fd64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.c
@@ -23,7 +23,6 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx)
 	struct mlx5hws_pool_attr pool_attr = {0};
 	u8 max_log_sz;
 	int ret;
-	int i;
 
 	ret = mlx5hws_pat_init_pattern_cache(&ctx->pattern_cache);
 	if (ret)
@@ -39,23 +38,17 @@ static int hws_context_pools_init(struct mlx5hws_context *ctx)
 	max_log_sz = min(MLX5HWS_POOL_STC_LOG_SZ, ctx->caps->stc_alloc_log_max);
 	pool_attr.alloc_log_sz = max(max_log_sz, ctx->caps->stc_alloc_log_gran);
 
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		pool_attr.table_type = i;
-		ctx->stc_pool[i] = mlx5hws_pool_create(ctx, &pool_attr);
-		if (!ctx->stc_pool[i]) {
-			mlx5hws_err(ctx, "Failed to allocate STC pool [%d]", i);
-			ret = -ENOMEM;
-			goto free_stc_pools;
-		}
+	pool_attr.table_type = MLX5HWS_TABLE_TYPE_FDB;
+	ctx->stc_pool = mlx5hws_pool_create(ctx, &pool_attr);
+	if (!ctx->stc_pool) {
+		mlx5hws_err(ctx, "Failed to allocate STC pool\n");
+		ret = -ENOMEM;
+		goto uninit_cache;
 	}
 
 	return 0;
 
-free_stc_pools:
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++)
-		if (ctx->stc_pool[i])
-			mlx5hws_pool_destroy(ctx->stc_pool[i]);
-
+uninit_cache:
 	mlx5hws_definer_uninit_cache(ctx->definer_cache);
 uninit_pat_cache:
 	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
@@ -64,12 +57,8 @@ uninit_pat_cache:
 
 static void hws_context_pools_uninit(struct mlx5hws_context *ctx)
 {
-	int i;
-
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		if (ctx->stc_pool[i])
-			mlx5hws_pool_destroy(ctx->stc_pool[i]);
-	}
+	if (ctx->stc_pool)
+		mlx5hws_pool_destroy(ctx->stc_pool);
 
 	mlx5hws_definer_uninit_cache(ctx->definer_cache);
 	mlx5hws_pat_uninit_pattern_cache(ctx->pattern_cache);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
index 1c9cc4fba083..38c3647444ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/context.h
@@ -38,8 +38,8 @@ struct mlx5hws_context {
 	struct mlx5_core_dev *mdev;
 	struct mlx5hws_cmd_query_caps *caps;
 	u32 pd_num;
-	struct mlx5hws_pool *stc_pool[MLX5HWS_TABLE_TYPE_MAX];
-	struct mlx5hws_context_common_res common_res[MLX5HWS_TABLE_TYPE_MAX];
+	struct mlx5hws_pool *stc_pool;
+	struct mlx5hws_context_common_res common_res;
 	struct mlx5hws_pattern_cache *pattern_cache;
 	struct mlx5hws_definer_cache *definer_cache;
 	struct mutex ctrl_lock; /* control lock to protect the whole context */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
index 5b200b4bc1a8..60ada3143d60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/debug.c
@@ -368,9 +368,10 @@ static int hws_debug_dump_context_info(struct seq_file *f, struct mlx5hws_contex
 
 static int hws_debug_dump_context_stc_resource(struct seq_file *f,
 					       struct mlx5hws_context *ctx,
-					       u32 tbl_type,
 					       struct mlx5hws_pool_resource *resource)
 {
+	u32 tbl_type = MLX5HWS_TABLE_TYPE_BASE + MLX5HWS_TABLE_TYPE_FDB;
+
 	seq_printf(f, "%d,0x%llx,%u,%u\n",
 		   MLX5HWS_DEBUG_RES_TYPE_CONTEXT_STC,
 		   HWS_PTR_TO_ID(ctx),
@@ -382,31 +383,22 @@ static int hws_debug_dump_context_stc_resource(struct seq_file *f,
 
 static int hws_debug_dump_context_stc(struct seq_file *f, struct mlx5hws_context *ctx)
 {
-	struct mlx5hws_pool *stc_pool;
-	u32 table_type;
+	struct mlx5hws_pool *stc_pool = ctx->stc_pool;
 	int ret;
-	int i;
-
-	for (i = 0; i < MLX5HWS_TABLE_TYPE_MAX; i++) {
-		stc_pool = ctx->stc_pool[i];
-		table_type = MLX5HWS_TABLE_TYPE_BASE + i;
 
-		if (!stc_pool)
-			continue;
+	if (!stc_pool)
+		return 0;
 
-		if (stc_pool->resource[0]) {
-			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
-								  stc_pool->resource[0]);
-			if (ret)
-				return ret;
-		}
+	if (stc_pool->resource[0]) {
+		ret = hws_debug_dump_context_stc_resource(f, ctx, stc_pool->resource[0]);
+		if (ret)
+			return ret;
+	}
 
-		if (i == MLX5HWS_TABLE_TYPE_FDB && stc_pool->mirror_resource[0]) {
-			ret = hws_debug_dump_context_stc_resource(f, ctx, table_type,
-								  stc_pool->mirror_resource[0]);
-			if (ret)
-				return ret;
-		}
+	if (stc_pool->mirror_resource[0]) {
+		ret = hws_debug_dump_context_stc_resource(f, ctx, stc_pool->mirror_resource[0]);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index 8fe96eb76baf..10ece7df1cfa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -70,7 +70,7 @@
 			u32 second_dw_mask = (mask) & ((1 << _bit_off) - 1); \
 			_HWS_SET32(p, (v) >> _bit_off, byte_off, 0, (mask) >> _bit_off); \
 			_HWS_SET32(p, (v) & second_dw_mask, (byte_off) + DW_SIZE, \
-				    (bit_off) % BITS_IN_DW, second_dw_mask); \
+				    (bit_off + BITS_IN_DW) % BITS_IN_DW, second_dw_mask); \
 		} else { \
 			_HWS_SET32(p, v, byte_off, (bit_off), (mask)); \
 		} \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
index 9432d5084def..5c1a2086efba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.h
@@ -785,7 +785,7 @@ struct mlx5hws_definer_cache {
 
 struct mlx5hws_definer_cache_item {
 	struct mlx5hws_definer definer;
-	u32 refcount;
+	u32 refcount; /* protected by context ctrl lock */
 	struct list_head list_node;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
index 1bb3a6f8c3cd..4419c72ad314 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/matcher.c
@@ -165,14 +165,14 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 						    next->match_ste.rtc_0_id,
 						    next->match_ste.rtc_1_id);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect matcher\n");
+			return ret;
 		}
 	} else {
 		ret = mlx5hws_table_connect_to_miss_table(tbl, tbl->default_miss.miss_tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Failed to disconnect last matcher\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx, "Fatal error, failed to disconnect last matcher\n");
+			return ret;
 		}
 	}
 
@@ -180,27 +180,19 @@ static int hws_matcher_disconnect(struct mlx5hws_matcher *matcher)
 	if (prev_ft_id == tbl->ft_id) {
 		ret = mlx5hws_table_update_connected_miss_tables(tbl);
 		if (ret) {
-			mlx5hws_err(tbl->ctx, "Fatal error, failed to update connected miss table\n");
-			goto matcher_reconnect;
+			mlx5hws_err(tbl->ctx,
+				    "Fatal error, failed to update connected miss table\n");
+			return ret;
 		}
 	}
 
 	ret = mlx5hws_table_ft_set_default_next_ft(tbl, prev_ft_id);
 	if (ret) {
 		mlx5hws_err(tbl->ctx, "Fatal error, failed to restore matcher ft default miss\n");
-		goto matcher_reconnect;
+		return ret;
 	}
 
 	return 0;
-
-matcher_reconnect:
-	if (list_empty(&tbl->matchers_list) || !prev)
-		list_add(&matcher->list_node, &tbl->matchers_list);
-	else
-		/* insert after prev matcher */
-		list_add(&matcher->list_node, &prev->list_node);
-
-	return ret;
 }
 
 static void hws_matcher_set_rtc_attr_sz(struct mlx5hws_matcher *matcher,
@@ -318,8 +310,8 @@ static int hws_matcher_create_rtc(struct mlx5hws_matcher *matcher,
 	hws_matcher_set_rtc_attr_sz(matcher, &rtc_attr, rtc_type, false);
 
 	/* STC is a single resource (obj_id), use any STC for the ID */
-	stc_pool = ctx->stc_pool[tbl->type];
-	default_stc = ctx->common_res[tbl->type].default_stc;
+	stc_pool = ctx->stc_pool;
+	default_stc = ctx->common_res.default_stc;
 	obj_id = mlx5hws_pool_chunk_get_base_id(stc_pool, &default_stc->default_hit);
 	rtc_attr.stc_base = obj_id;
 
@@ -1007,9 +999,9 @@ hws_matcher_set_templates(struct mlx5hws_matcher *matcher,
 	if (!matcher->mt)
 		return -ENOMEM;
 
-	matcher->at = kcalloc(num_of_at + matcher->attr.max_num_of_at_attach,
-			      sizeof(*matcher->at),
-			      GFP_KERNEL);
+	matcher->at = kvcalloc(num_of_at + matcher->attr.max_num_of_at_attach,
+			       sizeof(*matcher->at),
+			       GFP_KERNEL);
 	if (!matcher->at) {
 		mlx5hws_err(ctx, "Failed to allocate action template array\n");
 		ret = -ENOMEM;
@@ -1035,7 +1027,7 @@ free_mt:
 static void
 hws_matcher_unset_templates(struct mlx5hws_matcher *matcher)
 {
-	kfree(matcher->at);
+	kvfree(matcher->at);
 	kfree(matcher->mt);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index 06db5e4726ae..d9dc4f2d0dc6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -344,7 +344,7 @@ void mlx5hws_arg_write(struct mlx5hws_send_engine *queue,
 		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_ctrl, &wqe_len);
 		memset(wqe_ctrl, 0, wqe_len);
 		mlx5hws_send_engine_post_req_wqe(&ctrl, (void *)&wqe_arg, &wqe_len);
-		memcpy(wqe_arg, arg_data, wqe_len);
+		memcpy(wqe_arg, arg_data, MLX5HWS_ARG_DATA_SIZE);
 		send_attr.id = arg_idx++;
 		mlx5hws_send_engine_post_end(&ctrl, &send_attr);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
index 27ca93385b08..8ddb51980044 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.h
@@ -31,7 +31,7 @@ struct mlx5hws_pattern_cache_item {
 		u8 *data;
 		u16 num_of_actions;
 	} mh_data;
-	u32 refcount;
+	u32 refcount; /* protected by pattern_cache lock */
 	struct list_head ptrn_list_node;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
index fed2d913f3b8..50a81d360bb2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pool.c
@@ -183,7 +183,7 @@ static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool,
 	*seg = -1;
 
 	/* Find the next free place from the buddy array */
-	while (*seg == -1) {
+	while (*seg < 0) {
 		for (i = 0; i < MLX5HWS_POOL_RESOURCE_ARR_SZ; i++) {
 			buddy = hws_pool_buddy_get_next_buddy(pool, i,
 							      order,
@@ -194,7 +194,7 @@ static int hws_pool_buddy_get_mem_chunk(struct mlx5hws_pool *pool,
 			}
 
 			*seg = mlx5hws_buddy_alloc_mem(buddy, order);
-			if (*seg != -1)
+			if (*seg >= 0)
 				goto found;
 
 			if (pool->flags & MLX5HWS_POOL_FLAGS_ONE_RESOURCE) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
index de92cecbeb92..271490a51b96 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/prm.h
@@ -390,11 +390,6 @@ struct mlx5_ifc_definer_bits {
 	u8 match_mask[0x160];
 };
 
-struct mlx5_ifc_arg_bits {
-	u8 rsvd0[0x88];
-	u8 access_pd[0x18];
-};
-
 struct mlx5_ifc_header_modify_pattern_in_bits {
 	u8 modify_field_select[0x40];
 
@@ -428,11 +423,6 @@ struct mlx5_ifc_create_definer_in_bits {
 	struct mlx5_ifc_definer_bits definer;
 };
 
-struct mlx5_ifc_create_arg_in_bits {
-	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
-	struct mlx5_ifc_arg_bits arg;
-};
-
 struct mlx5_ifc_create_header_modify_pattern_in_bits {
 	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
 	struct mlx5_ifc_header_modify_pattern_in_bits pattern;
@@ -479,36 +469,4 @@ enum {
 	MLX5_IFC_MODIFY_FLOW_TABLE_MISS_ACTION_GOTO_TBL = 1,
 };
 
-struct mlx5_ifc_alloc_packet_reformat_out_bits {
-	u8 status[0x8];
-	u8 reserved_at_8[0x18];
-
-	u8 syndrome[0x20];
-
-	u8 packet_reformat_id[0x20];
-
-	u8 reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_dealloc_packet_reformat_in_bits {
-	u8 opcode[0x10];
-	u8 reserved_at_10[0x10];
-
-	u8 reserved_at_20[0x10];
-	u8 op_mod[0x10];
-
-	u8 packet_reformat_id[0x20];
-
-	u8 reserved_at_60[0x20];
-};
-
-struct mlx5_ifc_dealloc_packet_reformat_out_bits {
-	u8 status[0x8];
-	u8 reserved_at_8[0x18];
-
-	u8 syndrome[0x20];
-
-	u8 reserved_at_40[0x40];
-};
-
 #endif /* MLX5_PRM_H_ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
index e20c67a04203..14f6307a1772 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/rule.c
@@ -315,7 +315,7 @@ static void hws_rule_create_init(struct mlx5hws_rule *rule,
 
 	/* Init default action apply */
 	apply->tbl_type = tbl->type;
-	apply->common_res = &ctx->common_res[tbl->type];
+	apply->common_res = &ctx->common_res;
 	apply->jump_to_action_stc = matcher->action_ste[0].stc.offset;
 	apply->require_dep = 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
index 20fe126ffd22..c680b7f984e1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/send.c
@@ -633,6 +633,7 @@ static int hws_send_ring_create_sq(struct mlx5_core_dev *mdev, u32 pdn,
 
 	MLX5_SET(sqc, sqc, state, MLX5_SQC_STATE_RST);
 	MLX5_SET(sqc, sqc, flush_in_error_en, 1);
+	MLX5_SET(sqc, sqc, non_wire, 1);
 
 	ts_format = mlx5_is_real_time_sq(mdev) ? MLX5_TIMESTAMP_FORMAT_REAL_TIME :
 						 MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
index 9576e02d00c3..ab1297531232 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/table.c
@@ -37,6 +37,7 @@ static void hws_table_set_cap_attr(struct mlx5hws_table *tbl,
 }
 
 static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+__must_hold(&tbl->ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_ft_create_attr ft_attr = {0};
 	struct mlx5hws_cmd_set_fte_attr fte_attr = {0};
@@ -48,8 +49,8 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
 	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
 		return 0;
 
-	if (ctx->common_res[tbl_type].default_miss) {
-		ctx->common_res[tbl_type].default_miss->refcount++;
+	if (ctx->common_res.default_miss) {
+		ctx->common_res.default_miss->refcount++;
 		return 0;
 	}
 
@@ -70,29 +71,28 @@ static int hws_table_up_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
 		return -EINVAL;
 	}
 
-	/* ctx->ctrl_lock must be held here */
-	ctx->common_res[tbl_type].default_miss = default_miss;
-	ctx->common_res[tbl_type].default_miss->refcount++;
+	ctx->common_res.default_miss = default_miss;
+	ctx->common_res.default_miss->refcount++;
 
 	return 0;
 }
 
 /* Called under ctx->ctrl_lock */
 static void hws_table_down_default_fdb_miss_tbl(struct mlx5hws_table *tbl)
+__must_hold(&tbl->ctx->ctrl_lock)
 {
 	struct mlx5hws_cmd_forward_tbl *default_miss;
 	struct mlx5hws_context *ctx = tbl->ctx;
-	u8 tbl_type = tbl->type;
 
 	if (tbl->type != MLX5HWS_TABLE_TYPE_FDB)
 		return;
 
-	default_miss = ctx->common_res[tbl_type].default_miss;
+	default_miss = ctx->common_res.default_miss;
 	if (--default_miss->refcount)
 		return;
 
 	mlx5hws_cmd_forward_tbl_destroy(ctx->mdev, default_miss);
-	ctx->common_res[tbl_type].default_miss = NULL;
+	ctx->common_res.default_miss = NULL;
 }
 
 static int hws_table_connect_to_default_miss_tbl(struct mlx5hws_table *tbl, u32 ft_id)
@@ -478,15 +478,9 @@ int mlx5hws_table_set_default_miss(struct mlx5hws_table *tbl,
 	if (old_miss_tbl)
 		list_del_init(&tbl->default_miss.next);
 
-	old_miss_tbl = tbl->default_miss.miss_tbl;
-	if (old_miss_tbl)
-		list_del_init(&old_miss_tbl->default_miss.head);
-
 	if (miss_tbl)
 		list_add(&tbl->default_miss.next, &miss_tbl->default_miss.head);
 
-	mutex_unlock(&ctx->ctrl_lock);
-	return 0;
 out:
 	mutex_unlock(&ctx->ctrl_lock);
 	return ret;