diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 1348a08261a949806ddb9399675bfaf326bb1b97..853574345d91eb40b654ebd5eb592aa3c9525b11 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1571,6 +1571,48 @@ static void deallocate_uars(struct mlx5_ib_dev *dev,
 			mlx5_cmd_free_uar(dev->mdev, bfregi->sys_pages[i]);
 }
 
+int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
+{
+	int err = 0;
+
+	mutex_lock(&dev->lb.mutex);
+	if (td)
+		dev->lb.user_td++;
+	if (qp)
+		dev->lb.qps++;
+
+	if (dev->lb.user_td == 2 ||
+	    dev->lb.qps == 1) {
+		if (!dev->lb.enabled) {
+			err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
+			dev->lb.enabled = true;
+		}
+	}
+
+	mutex_unlock(&dev->lb.mutex);
+
+	return err;
+}
+
+void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp)
+{
+	mutex_lock(&dev->lb.mutex);
+	if (td)
+		dev->lb.user_td--;
+	if (qp)
+		dev->lb.qps--;
+
+	if (dev->lb.user_td == 1 &&
+	    dev->lb.qps == 0) {
+		if (dev->lb.enabled) {
+			mlx5_nic_vport_update_local_lb(dev->mdev, false);
+			dev->lb.enabled = false;
+		}
+	}
+
+	mutex_unlock(&dev->lb.mutex);
+}
+
 static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn)
 {
 	int err;
@@ -1587,14 +1629,7 @@ static int mlx5_ib_alloc_transport_domain(struct mlx5_ib_dev *dev, u32 *tdn)
 	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		return err;
 
-	mutex_lock(&dev->lb_mutex);
-	dev->user_td++;
-
-	if (dev->user_td == 2)
-		err = mlx5_nic_vport_update_local_lb(dev->mdev, true);
-
-	mutex_unlock(&dev->lb_mutex);
-	return err;
+	return mlx5_ib_enable_lb(dev, true, false);
 }
 
 static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn)
@@ -1609,13 +1644,7 @@ static void mlx5_ib_dealloc_transport_domain(struct mlx5_ib_dev *dev, u32 tdn)
 	     !MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
 		return;
 
-	mutex_lock(&dev->lb_mutex);
-	dev->user_td--;
-
-	if (dev->user_td < 2)
-		mlx5_nic_vport_update_local_lb(dev->mdev, false);
-
-	mutex_unlock(&dev->lb_mutex);
+	mlx5_ib_disable_lb(dev, true, false);
 }
 
 static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
@@ -5867,7 +5896,7 @@ int mlx5_ib_stage_caps_init(struct mlx5_ib_dev *dev)
 	if ((MLX5_CAP_GEN(dev->mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&
 	    (MLX5_CAP_GEN(dev->mdev, disable_local_lb_uc) ||
 	     MLX5_CAP_GEN(dev->mdev, disable_local_lb_mc)))
-		mutex_init(&dev->lb_mutex);
+		mutex_init(&dev->lb.mutex);
 
 	return 0;
 }
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index dc34ffa4c8b331de1ac3a062db51d8c38bd3f3a1..a28d04d4c9df8a4d36151ffda594f4ddf4cbb786 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -430,7 +430,7 @@ struct mlx5_ib_qp {
 	struct list_head	cq_send_list;
 	struct mlx5_rate_limit	rl;
 	u32                     underlay_qpn;
-	bool			tunnel_offload_en;
+	u32			flags_en;
 	/* storage for qp sub type when core qp type is IB_QPT_DRIVER */
 	enum ib_qp_type		qp_sub_type;
 };
@@ -868,6 +868,14 @@ to_mcounters(struct ib_counters *ibcntrs)
 int parse_flow_flow_action(struct mlx5_ib_flow_action *maction,
 			   bool is_egress,
 			   struct mlx5_flow_act *action);
+struct mlx5_ib_lb_state {
+	/* protect the user_td */
+	struct mutex		mutex;
+	u32			user_td;
+	int			qps;
+	bool			enabled;
+};
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	const struct uverbs_object_tree_def *driver_trees[7];
@@ -909,9 +917,7 @@ struct mlx5_ib_dev {
 	const struct mlx5_ib_profile	*profile;
 	struct mlx5_eswitch_rep		*rep;
 
-	/* protect the user_td */
-	struct mutex		lb_mutex;
-	u32			user_td;
+	struct mlx5_ib_lb_state		lb;
 	u8			umr_fence;
 	struct list_head	ib_dev_list;
 	u64			sys_image_guid;
@@ -1026,6 +1032,8 @@ int mlx5_ib_query_srq(struct ib_srq *ibsrq, struct ib_srq_attr *srq_attr);
 int mlx5_ib_destroy_srq(struct ib_srq *srq);
 int mlx5_ib_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			  const struct ib_recv_wr **bad_wr);
+int mlx5_ib_enable_lb(struct mlx5_ib_dev *dev, bool td, bool qp);
+void mlx5_ib_disable_lb(struct mlx5_ib_dev *dev, bool td, bool qp);
 struct ib_qp *mlx5_ib_create_qp(struct ib_pd *pd,
 				struct ib_qp_init_attr *init_attr,
 				struct ib_udata *udata);
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 1f35ecbefffe3e59bfe46f1b61bcc7e995439296..1f318a47040cf1d754e007ecac62c4340eab40a0 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1256,10 +1256,21 @@ static bool tunnel_offload_supported(struct mlx5_core_dev *dev)
 		 MLX5_CAP_ETH(dev, tunnel_stateless_geneve_rx));
 }
 
+static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
+				      struct mlx5_ib_rq *rq,
+				      u32 qp_flags_en)
+{
+	if (qp_flags_en & (MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+			   MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC))
+		mlx5_ib_disable_lb(dev, false, true);
+	mlx5_core_destroy_tir(dev->mdev, rq->tirn);
+}
+
 static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 				    struct mlx5_ib_rq *rq, u32 tdn,
-				    bool tunnel_offload_en)
+				    u32 *qp_flags_en)
 {
+	u8 lb_flag = 0;
 	u32 *in;
 	void *tirc;
 	int inlen;
@@ -1274,26 +1285,35 @@ static int create_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 	MLX5_SET(tirc, tirc, disp_type, MLX5_TIRC_DISP_TYPE_DIRECT);
 	MLX5_SET(tirc, tirc, inline_rqn, rq->base.mqp.qpn);
 	MLX5_SET(tirc, tirc, transport_domain, tdn);
-	if (tunnel_offload_en)
+	if (*qp_flags_en & MLX5_QP_FLAG_TUNNEL_OFFLOADS)
 		MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
 
-	if (dev->rep)
-		MLX5_SET(tirc, tirc, self_lb_block,
-			 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_);
+	if (*qp_flags_en & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC)
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+
+	if (*qp_flags_en & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC)
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+
+	if (dev->rep) {
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+		*qp_flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+	}
+
+	MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
 
 	err = mlx5_core_create_tir(dev->mdev, in, inlen, &rq->tirn);
 
+	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
+		err = mlx5_ib_enable_lb(dev, false, true);
+
+		if (err)
+			destroy_raw_packet_qp_tir(dev, rq, 0);
+	}
 	kvfree(in);
 
 	return err;
 }
 
-static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
-				      struct mlx5_ib_rq *rq)
-{
-	mlx5_core_destroy_tir(dev->mdev, rq->tirn);
-}
-
 static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 				u32 *in, size_t inlen,
 				struct ib_pd *pd)
@@ -1332,8 +1352,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 			goto err_destroy_sq;
 
 
-		err = create_raw_packet_qp_tir(dev, rq, tdn,
-					       qp->tunnel_offload_en);
+		err = create_raw_packet_qp_tir(dev, rq, tdn, &qp->flags_en);
 		if (err)
 			goto err_destroy_rq;
 	}
@@ -1363,7 +1382,7 @@ static void destroy_raw_packet_qp(struct mlx5_ib_dev *dev,
 	struct mlx5_ib_rq *rq = &raw_packet_qp->rq;
 
 	if (qp->rq.wqe_cnt) {
-		destroy_raw_packet_qp_tir(dev, rq);
+		destroy_raw_packet_qp_tir(dev, rq, qp->flags_en);
 		destroy_raw_packet_qp_rq(dev, rq);
 	}
 
@@ -1387,6 +1406,9 @@ static void raw_packet_qp_copy_info(struct mlx5_ib_qp *qp,
 
 static void destroy_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp)
 {
+	if (qp->flags_en & (MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+			    MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC))
+		mlx5_ib_disable_lb(dev, false, true);
 	mlx5_core_destroy_tir(dev->mdev, qp->rss_qp.tirn);
 }
 
@@ -1410,6 +1432,7 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	u32 tdn = mucontext->tdn;
 	struct mlx5_ib_create_qp_rss ucmd = {};
 	size_t required_cmd_sz;
+	u8 lb_flag = 0;
 
 	if (init_attr->qp_type != IB_QPT_RAW_PACKET)
 		return -EOPNOTSUPP;
@@ -1444,7 +1467,9 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		return -EOPNOTSUPP;
 	}
 
-	if (ucmd.flags & ~MLX5_QP_FLAG_TUNNEL_OFFLOADS) {
+	if (ucmd.flags & ~(MLX5_QP_FLAG_TUNNEL_OFFLOADS |
+			   MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC |
+			   MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC)) {
 		mlx5_ib_dbg(dev, "invalid flags\n");
 		return -EOPNOTSUPP;
 	}
@@ -1461,6 +1486,16 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		return -EOPNOTSUPP;
 	}
 
+	if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC || dev->rep) {
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST;
+		qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+	}
+
+	if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC) {
+		lb_flag |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST;
+		qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC;
+	}
+
 	err = ib_copy_to_udata(udata, &resp, min(udata->outlen, sizeof(resp)));
 	if (err) {
 		mlx5_ib_dbg(dev, "copy failed\n");
@@ -1484,6 +1519,8 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (ucmd.flags & MLX5_QP_FLAG_TUNNEL_OFFLOADS)
 		MLX5_SET(tirc, tirc, tunneled_offload_en, 1);
 
+	MLX5_SET(tirc, tirc, self_lb_block, lb_flag);
+
 	if (ucmd.rx_hash_fields_mask & MLX5_RX_HASH_INNER)
 		hfso = MLX5_ADDR_OF(tirc, tirc, rx_hash_field_selector_inner);
 	else
@@ -1580,12 +1617,15 @@ static int create_rss_raw_qp_tir(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	MLX5_SET(rx_hash_field_select, hfso, selected_fields, selected_fields);
 
 create_tir:
-	if (dev->rep)
-		MLX5_SET(tirc, tirc, self_lb_block,
-			 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_);
-
 	err = mlx5_core_create_tir(dev->mdev, in, inlen, &qp->rss_qp.tirn);
 
+	if (!err && MLX5_GET(tirc, tirc, self_lb_block)) {
+		err = mlx5_ib_enable_lb(dev, false, true);
+
+		if (err)
+			mlx5_core_destroy_tir(dev->mdev, qp->rss_qp.tirn);
+	}
+
 	if (err)
 		goto err;
 
@@ -1710,7 +1750,23 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 				mlx5_ib_dbg(dev, "Tunnel offload isn't supported\n");
 				return -EOPNOTSUPP;
 			}
-			qp->tunnel_offload_en = true;
+			qp->flags_en |= MLX5_QP_FLAG_TUNNEL_OFFLOADS;
+		}
+
+		if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC) {
+			if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+				mlx5_ib_dbg(dev, "Self-LB UC isn't supported\n");
+				return -EOPNOTSUPP;
+			}
+			qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC;
+		}
+
+		if (ucmd.flags & MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC) {
+			if (init_attr->qp_type != IB_QPT_RAW_PACKET) {
+				mlx5_ib_dbg(dev, "Self-LB UM isn't supported\n");
+				return -EOPNOTSUPP;
+			}
+			qp->flags_en |= MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC;
 		}
 
 		if (init_attr->create_flags & IB_QP_CREATE_SOURCE_QPN) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
index db3278cc052ba3639fb8e74cdf4cf610637c8201..3078491cc0d0678a6f1867373c752ed95496a59e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c
@@ -153,7 +153,7 @@ int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb)
 
 	if (enable_uc_lb)
 		MLX5_SET(modify_tir_in, in, ctx.self_lb_block,
-			 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_);
+			 MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST);
 
 	MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1);
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3a4a2e0567e9031206b6fd7bcac571634d82be00..4c7a1d25d73bddb3fa4de52eded76beb8901f789 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2559,8 +2559,8 @@ enum {
 };
 
 enum {
-	MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST_    = 0x1,
-	MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST_  = 0x2,
+	MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST    = 0x1,
+	MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST  = 0x2,
 };
 
 struct mlx5_ifc_tirc_bits {
diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h
index addbb9c4529eaa0aa2ffa3c12da9f72c6615ca6a..e584ba40208e3437f7fc3d817e6951625455648e 100644
--- a/include/uapi/rdma/mlx5-abi.h
+++ b/include/uapi/rdma/mlx5-abi.h
@@ -45,6 +45,8 @@ enum {
 	MLX5_QP_FLAG_BFREG_INDEX	= 1 << 3,
 	MLX5_QP_FLAG_TYPE_DCT		= 1 << 4,
 	MLX5_QP_FLAG_TYPE_DCI		= 1 << 5,
+	MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_UC = 1 << 6,
+	MLX5_QP_FLAG_TIR_ALLOW_SELF_LB_MC = 1 << 7,
 };
 
 enum {