X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Fmlx5_txq.c;h=0140f8b3b2c64b47ae82edae0cf7e6949648ca61;hb=7158e46cb94be6f6071ccdabfc1fa48256955906;hp=e8bf7d7b4026015d4737ca9b69774ee58fc9405b;hpb=17a57183c0eb207d8ca9c0b1f624f27aa1a4d09b;p=dpdk.git

diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index e8bf7d7b40..0140f8b3b2 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -12,20 +12,19 @@
 
 #include <rte_mbuf.h>
 #include <rte_malloc.h>
-#include <rte_ethdev_driver.h>
+#include <ethdev_driver.h>
+#include <rte_bus_pci.h>
 #include <rte_common.h>
 #include <rte_eal_paging.h>
 
-#include <mlx5_glue.h>
-#include <mlx5_devx_cmds.h>
 #include <mlx5_common.h>
 #include <mlx5_common_mr.h>
-#include <mlx5_common_os.h>
 #include <mlx5_malloc.h>
 
 #include "mlx5_defs.h"
 #include "mlx5_utils.h"
 #include "mlx5.h"
+#include "mlx5_tx.h"
 #include "mlx5_rxtx.h"
 #include "mlx5_autoconf.h"
 
@@ -99,33 +98,44 @@ uint64_t
 mlx5_get_tx_port_offloads(struct rte_eth_dev *dev)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
-	uint64_t offloads = (DEV_TX_OFFLOAD_MULTI_SEGS |
-			     DEV_TX_OFFLOAD_VLAN_INSERT);
-	struct mlx5_dev_config *config = &priv->config;
-
-	if (config->hw_csum)
-		offloads |= (DEV_TX_OFFLOAD_IPV4_CKSUM |
-			     DEV_TX_OFFLOAD_UDP_CKSUM |
-			     DEV_TX_OFFLOAD_TCP_CKSUM);
-	if (config->tso)
-		offloads |= DEV_TX_OFFLOAD_TCP_TSO;
-	if (config->tx_pp)
-		offloads |= DEV_TX_OFFLOAD_SEND_ON_TIMESTAMP;
-	if (config->swp) {
-		if (config->hw_csum)
-			offloads |= DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM;
-		if (config->tso)
-			offloads |= (DEV_TX_OFFLOAD_IP_TNL_TSO |
-				     DEV_TX_OFFLOAD_UDP_TNL_TSO);
-	}
-	if (config->tunnel_en) {
-		if (config->hw_csum)
-			offloads |= DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM;
-		if (config->tso)
-			offloads |= (DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
-				     DEV_TX_OFFLOAD_GRE_TNL_TSO |
-				     DEV_TX_OFFLOAD_GENEVE_TNL_TSO);
+	uint64_t offloads = (RTE_ETH_TX_OFFLOAD_MULTI_SEGS |
+			     RTE_ETH_TX_OFFLOAD_VLAN_INSERT);
+	struct mlx5_port_config *config = &priv->config;
+	struct mlx5_dev_cap *dev_cap = &priv->sh->dev_cap;
+
+	if (dev_cap->hw_csum)
+		offloads |= (RTE_ETH_TX_OFFLOAD_IPV4_CKSUM |
+			     RTE_ETH_TX_OFFLOAD_UDP_CKSUM |
+			     RTE_ETH_TX_OFFLOAD_TCP_CKSUM);
+	if (dev_cap->tso)
+		offloads |= RTE_ETH_TX_OFFLOAD_TCP_TSO;
+	if (priv->sh->config.tx_pp ||
+	    priv->sh->cdev->config.hca_attr.wait_on_time)
+		offloads |= RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP;
+	if (dev_cap->swp) {
+		if (dev_cap->swp & MLX5_SW_PARSING_CSUM_CAP)
+			offloads |= RTE_ETH_TX_OFFLOAD_OUTER_IPV4_CKSUM;
+		if (dev_cap->swp & MLX5_SW_PARSING_TSO_CAP)
+			offloads |= (RTE_ETH_TX_OFFLOAD_IP_TNL_TSO |
+				     RTE_ETH_TX_OFFLOAD_UDP_TNL_TSO);
+	}
+	if (dev_cap->tunnel_en) {
+		if (dev_cap->hw_csum)
+			offloads |= RTE_ETH_TX_OFFLOAD_OUTER_IPV4_CKSUM;
+		if (dev_cap->tso) {
+			if (dev_cap->tunnel_en &
+				MLX5_TUNNELED_OFFLOADS_VXLAN_CAP)
+				offloads |= RTE_ETH_TX_OFFLOAD_VXLAN_TNL_TSO;
+			if (dev_cap->tunnel_en &
+				MLX5_TUNNELED_OFFLOADS_GRE_CAP)
+				offloads |= RTE_ETH_TX_OFFLOAD_GRE_TNL_TSO;
+			if (dev_cap->tunnel_en &
+				MLX5_TUNNELED_OFFLOADS_GENEVE_CAP)
+				offloads |= RTE_ETH_TX_OFFLOAD_GENEVE_TNL_TSO;
+		}
 	}
+	if (!config->mprq.enabled)
+		offloads |= RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE;
 	return offloads;
 }
 
@@ -157,6 +167,7 @@ txq_sync_cq(struct mlx5_txq_data *txq)
 	/* Resync CQE and WQE (WQ in reset state). */
 	rte_io_wmb();
 	*txq->cq_db = rte_cpu_to_be_32(txq->cq_ci);
+	txq->cq_pi = txq->cq_ci;
 	rte_io_wmb();
 }
 
@@ -183,37 +194,10 @@ mlx5_tx_queue_stop_primary(struct rte_eth_dev *dev, uint16_t idx)
 
 	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
 	/* Move QP to RESET state. */
-	if (txq_ctrl->obj->type == MLX5_TXQ_OBJ_TYPE_DEVX_SQ) {
-		struct mlx5_devx_modify_sq_attr msq_attr = { 0 };
-
-		/* Change queue state to reset with DevX. */
-		msq_attr.sq_state = MLX5_SQC_STATE_RDY;
-		msq_attr.state = MLX5_SQC_STATE_RST;
-		ret = mlx5_devx_cmd_modify_sq(txq_ctrl->obj->sq_devx,
-					      &msq_attr);
-		if (ret) {
-			DRV_LOG(ERR, "Cannot change the "
-				"Tx QP state to RESET %s",
-				strerror(errno));
-			rte_errno = errno;
-			return ret;
-		}
-	} else {
-		struct ibv_qp_attr mod = {
-			.qp_state = IBV_QPS_RESET,
-			.port_num = (uint8_t)priv->dev_port,
-		};
-		struct ibv_qp *qp = txq_ctrl->obj->qp;
-
-		/* Change queue state to reset with Verbs. */
-		ret = mlx5_glue->modify_qp(qp, &mod, IBV_QP_STATE);
-		if (ret) {
-			DRV_LOG(ERR, "Cannot change the Tx QP state to RESET "
-				"%s", strerror(errno));
-			rte_errno = errno;
-			return ret;
-		}
-	}
+	ret = priv->obj_ops.txq_obj_modify(txq_ctrl->obj, MLX5_TXQ_MOD_RDY2RST,
+					   (uint8_t)priv->dev_port);
+	if (ret)
+		return ret;
 	/* Handle all send completions. */
 	txq_sync_cq(txq);
 	/* Free elts stored in the SQ. */
@@ -282,70 +266,11 @@ mlx5_tx_queue_start_primary(struct rte_eth_dev *dev, uint16_t idx)
 	int ret;
 
 	MLX5_ASSERT(rte_eal_process_type() ==  RTE_PROC_PRIMARY);
-	if (txq_ctrl->obj->type == MLX5_TXQ_OBJ_TYPE_DEVX_SQ) {
-		struct mlx5_devx_modify_sq_attr msq_attr = { 0 };
-		struct mlx5_txq_obj *obj = txq_ctrl->obj;
-
-		msq_attr.sq_state = MLX5_SQC_STATE_RDY;
-		msq_attr.state = MLX5_SQC_STATE_RST;
-		ret = mlx5_devx_cmd_modify_sq(obj->sq_devx, &msq_attr);
-		if (ret) {
-			rte_errno = errno;
-			DRV_LOG(ERR,
-				"Cannot change the Tx QP state to RESET "
-				"%s", strerror(errno));
-			return ret;
-		}
-		msq_attr.sq_state = MLX5_SQC_STATE_RST;
-		msq_attr.state = MLX5_SQC_STATE_RDY;
-		ret = mlx5_devx_cmd_modify_sq(obj->sq_devx, &msq_attr);
-		if (ret) {
-			rte_errno = errno;
-			DRV_LOG(ERR,
-				"Cannot change the Tx QP state to READY "
-				"%s", strerror(errno));
-			return ret;
-		}
-	} else {
-		struct ibv_qp_attr mod = {
-			.qp_state = IBV_QPS_RESET,
-			.port_num = (uint8_t)priv->dev_port,
-		};
-		struct ibv_qp *qp = txq_ctrl->obj->qp;
-
-		ret = mlx5_glue->modify_qp(qp, &mod, IBV_QP_STATE);
-		if (ret) {
-			DRV_LOG(ERR, "Cannot change the Tx QP state to RESET "
-				"%s", strerror(errno));
-			rte_errno = errno;
-			return ret;
-		}
-		mod.qp_state = IBV_QPS_INIT;
-		ret = mlx5_glue->modify_qp(qp, &mod,
-					   (IBV_QP_STATE | IBV_QP_PORT));
-		if (ret) {
-			DRV_LOG(ERR, "Cannot change Tx QP state to INIT %s",
-				strerror(errno));
-			rte_errno = errno;
-			return ret;
-		}
-		mod.qp_state = IBV_QPS_RTR;
-		ret = mlx5_glue->modify_qp(qp, &mod, IBV_QP_STATE);
-		if (ret) {
-			DRV_LOG(ERR, "Cannot change Tx QP state to RTR %s",
-				strerror(errno));
-			rte_errno = errno;
-			return ret;
-		}
-		mod.qp_state = IBV_QPS_RTS;
-		ret = mlx5_glue->modify_qp(qp, &mod, IBV_QP_STATE);
-		if (ret) {
-			DRV_LOG(ERR, "Cannot change Tx QP state to RTS %s",
-				strerror(errno));
-			rte_errno = errno;
-			return ret;
-		}
-	}
+	ret = priv->obj_ops.txq_obj_modify(txq_ctrl->obj,
+					   MLX5_TXQ_MOD_RST2RDY,
+					   (uint8_t)priv->dev_port);
+	if (ret)
+		return ret;
 	txq_ctrl->txq.wqe_ci = 0;
 	txq_ctrl->txq.wqe_pi = 0;
 	txq_ctrl->txq.elts_comp = 0;
@@ -477,7 +402,6 @@ mlx5_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 	DRV_LOG(DEBUG, "port %u adding Tx queue %u to list",
 		dev->data->port_id, idx);
 	(*priv->txqs)[idx] = &txq_ctrl->txq;
-	dev->data->tx_queue_state[idx] = RTE_ETH_QUEUE_STATE_STARTED;
 	return 0;
 }
 
@@ -510,15 +434,35 @@ mlx5_tx_hairpin_queue_setup(struct rte_eth_dev *dev, uint16_t idx,
 	res = mlx5_tx_queue_pre_setup(dev, idx, &desc);
 	if (res)
 		return res;
-	if (hairpin_conf->peer_count != 1 ||
-	    hairpin_conf->peers[0].port != dev->data->port_id ||
-	    hairpin_conf->peers[0].queue >= priv->rxqs_n) {
-		DRV_LOG(ERR, "port %u unable to setup hairpin queue index %u "
-			" invalid hairpind configuration", dev->data->port_id,
-			idx);
+	if (hairpin_conf->peer_count != 1) {
 		rte_errno = EINVAL;
+		DRV_LOG(ERR, "port %u unable to setup Tx hairpin queue index %u"
+			" peer count is %u", dev->data->port_id,
+			idx, hairpin_conf->peer_count);
 		return -rte_errno;
 	}
+	if (hairpin_conf->peers[0].port == dev->data->port_id) {
+		if (hairpin_conf->peers[0].queue >= priv->rxqs_n) {
+			rte_errno = EINVAL;
+			DRV_LOG(ERR, "port %u unable to setup Tx hairpin queue"
+				" index %u, Rx %u is larger than %u",
+				dev->data->port_id, idx,
+				hairpin_conf->peers[0].queue, priv->txqs_n);
+			return -rte_errno;
+		}
+	} else {
+		if (hairpin_conf->manual_bind == 0 ||
+		    hairpin_conf->tx_explicit == 0) {
+			rte_errno = EINVAL;
+			DRV_LOG(ERR, "port %u unable to setup Tx hairpin queue"
+				" index %u peer port %u with attributes %u %u",
+				dev->data->port_id, idx,
+				hairpin_conf->peers[0].port,
+				hairpin_conf->manual_bind,
+				hairpin_conf->tx_explicit);
+			return -rte_errno;
+		}
+	}
 	txq_ctrl = mlx5_txq_hairpin_new(dev, idx, desc,	hairpin_conf);
 	if (!txq_ctrl) {
 		DRV_LOG(ERR, "port %u unable to allocate queue index %u",
@@ -535,86 +479,21 @@ mlx5_tx_hairpin_queue_setup(struct rte_eth_dev *dev, uint16_t idx,
 /**
  * DPDK callback to release a TX queue.
  *
- * @param dpdk_txq
- *   Generic TX queue pointer.
+ * @param dev
+ *   Pointer to Ethernet device structure.
+ * @param qid
+ *   Transmit queue index.
  */
 void
-mlx5_tx_queue_release(void *dpdk_txq)
+mlx5_tx_queue_release(struct rte_eth_dev *dev, uint16_t qid)
 {
-	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
-	struct mlx5_txq_ctrl *txq_ctrl;
-	struct mlx5_priv *priv;
-	unsigned int i;
+	struct mlx5_txq_data *txq = dev->data->tx_queues[qid];
 
 	if (txq == NULL)
 		return;
-	txq_ctrl = container_of(txq, struct mlx5_txq_ctrl, txq);
-	priv = txq_ctrl->priv;
-	for (i = 0; (i != priv->txqs_n); ++i)
-		if ((*priv->txqs)[i] == txq) {
-			DRV_LOG(DEBUG, "port %u removing Tx queue %u from list",
-				PORT_ID(priv), txq->idx);
-			mlx5_txq_release(ETH_DEV(priv), i);
-			break;
-		}
-}
-
-/**
- * Configure the doorbell register non-cached attribute.
- *
- * @param txq_ctrl
- *   Pointer to Tx queue control structure.
- * @param page_size
- *   Systme page size
- */
-static void
-txq_uar_ncattr_init(struct mlx5_txq_ctrl *txq_ctrl, size_t page_size)
-{
-	struct mlx5_priv *priv = txq_ctrl->priv;
-	off_t cmd;
-
-	txq_ctrl->txq.db_heu = priv->config.dbnc == MLX5_TXDB_HEURISTIC;
-	txq_ctrl->txq.db_nc = 0;
-	/* Check the doorbell register mapping type. */
-	cmd = txq_ctrl->uar_mmap_offset / page_size;
-	cmd >>= MLX5_UAR_MMAP_CMD_SHIFT;
-	cmd &= MLX5_UAR_MMAP_CMD_MASK;
-	if (cmd == MLX5_MMAP_GET_NC_PAGES_CMD)
-		txq_ctrl->txq.db_nc = 1;
-}
-
-/**
- * Initialize Tx UAR registers for primary process.
- *
- * @param txq_ctrl
- *   Pointer to Tx queue control structure.
- */
-static void
-txq_uar_init(struct mlx5_txq_ctrl *txq_ctrl)
-{
-	struct mlx5_priv *priv = txq_ctrl->priv;
-	struct mlx5_proc_priv *ppriv = MLX5_PROC_PRIV(PORT_ID(priv));
-#ifndef RTE_ARCH_64
-	unsigned int lock_idx;
-#endif
-	const size_t page_size = rte_mem_page_size();
-	if (page_size == (size_t)-1) {
-		DRV_LOG(ERR, "Failed to get mem page size");
-		rte_errno = ENOMEM;
-	}
-
-	if (txq_ctrl->type != MLX5_TXQ_TYPE_STANDARD)
-		return;
-	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY);
-	MLX5_ASSERT(ppriv);
-	ppriv->uar_table[txq_ctrl->txq.idx] = txq_ctrl->bf_reg;
-	txq_uar_ncattr_init(txq_ctrl, page_size);
-#ifndef RTE_ARCH_64
-	/* Assign an UAR lock according to UAR page number */
-	lock_idx = (txq_ctrl->uar_mmap_offset / page_size) &
-		   MLX5_UAR_PAGE_NUM_MASK;
-	txq_ctrl->txq.uar_lock = &priv->sh->uar_lock[lock_idx];
-#endif
+	DRV_LOG(DEBUG, "port %u removing Tx queue %u from list",
+		dev->data->port_id, qid);
+	mlx5_txq_release(dev, qid);
 }
 
 /**
@@ -636,6 +515,7 @@ txq_uar_init_secondary(struct mlx5_txq_ctrl *txq_ctrl, int fd)
 {
 	struct mlx5_priv *priv = txq_ctrl->priv;
 	struct mlx5_proc_priv *ppriv = MLX5_PROC_PRIV(PORT_ID(priv));
+	struct mlx5_proc_priv *primary_ppriv = priv->sh->pppriv;
 	struct mlx5_txq_data *txq = &txq_ctrl->txq;
 	void *addr;
 	uintptr_t uar_va;
@@ -647,27 +527,29 @@ txq_uar_init_secondary(struct mlx5_txq_ctrl *txq_ctrl, int fd)
 		return -rte_errno;
 	}
 
-	if (txq_ctrl->type != MLX5_TXQ_TYPE_STANDARD)
+	if (txq_ctrl->is_hairpin)
 		return 0;
 	MLX5_ASSERT(ppriv);
 	/*
 	 * As rdma-core, UARs are mapped in size of OS page
 	 * size. Ref to libmlx5 function: mlx5_init_context()
 	 */
-	uar_va = (uintptr_t)txq_ctrl->bf_reg;
+	uar_va = (uintptr_t)primary_ppriv->uar_table[txq->idx].db;
 	offset = uar_va & (page_size - 1); /* Offset in page. */
 	addr = rte_mem_map(NULL, page_size, RTE_PROT_WRITE, RTE_MAP_SHARED,
-			    fd, txq_ctrl->uar_mmap_offset);
+			   fd, txq_ctrl->uar_mmap_offset);
 	if (!addr) {
-		DRV_LOG(ERR,
-			"port %u mmap failed for BF reg of txq %u",
+		DRV_LOG(ERR, "Port %u mmap failed for BF reg of txq %u.",
 			txq->port_id, txq->idx);
 		rte_errno = ENXIO;
 		return -rte_errno;
 	}
 	addr = RTE_PTR_ADD(addr, offset);
-	ppriv->uar_table[txq->idx] = addr;
-	txq_uar_ncattr_init(txq_ctrl, page_size);
+	ppriv->uar_table[txq->idx].db = addr;
+#ifndef RTE_ARCH_64
+	ppriv->uar_table[txq->idx].sl_p =
+			primary_ppriv->uar_table[txq->idx].sl_p;
+#endif
 	return 0;
 }
 
@@ -688,9 +570,9 @@ txq_uar_uninit_secondary(struct mlx5_txq_ctrl *txq_ctrl)
 		rte_errno = ENOMEM;
 	}
 
-	if (txq_ctrl->type != MLX5_TXQ_TYPE_STANDARD)
+	if (txq_ctrl->is_hairpin)
 		return;
-	addr = ppriv->uar_table[txq_ctrl->txq.idx];
+	addr = ppriv->uar_table[txq_ctrl->txq.idx].db;
 	rte_mem_unmap(RTE_PTR_ALIGN_FLOOR(addr, page_size), page_size);
 }
 
@@ -703,18 +585,23 @@ txq_uar_uninit_secondary(struct mlx5_txq_ctrl *txq_ctrl)
 void
 mlx5_tx_uar_uninit_secondary(struct rte_eth_dev *dev)
 {
-	struct mlx5_priv *priv = dev->data->dev_private;
-	struct mlx5_txq_data *txq;
-	struct mlx5_txq_ctrl *txq_ctrl;
+	struct mlx5_proc_priv *ppriv = (struct mlx5_proc_priv *)
+					dev->process_private;
+	const size_t page_size = rte_mem_page_size();
+	void *addr;
 	unsigned int i;
 
+	if (page_size == (size_t)-1) {
+		DRV_LOG(ERR, "Failed to get mem page size");
+		return;
+	}
 	MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_SECONDARY);
-	for (i = 0; i != priv->txqs_n; ++i) {
-		if (!(*priv->txqs)[i])
+	for (i = 0; i != ppriv->uar_table_sz; ++i) {
+		if (!ppriv->uar_table[i].db)
 			continue;
-		txq = (*priv->txqs)[i];
-		txq_ctrl = container_of(txq, struct mlx5_txq_ctrl, txq);
-		txq_uar_uninit_secondary(txq_ctrl);
+		addr = ppriv->uar_table[i].db;
+		rte_mem_unmap(RTE_PTR_ALIGN_FLOOR(addr, page_size), page_size);
+
 	}
 }
 
@@ -744,7 +631,7 @@ mlx5_tx_uar_init_secondary(struct rte_eth_dev *dev, int fd)
 			continue;
 		txq = (*priv->txqs)[i];
 		txq_ctrl = container_of(txq, struct mlx5_txq_ctrl, txq);
-		if (txq_ctrl->type != MLX5_TXQ_TYPE_STANDARD)
+		if (txq_ctrl->is_hairpin)
 			continue;
 		MLX5_ASSERT(txq->idx == (uint16_t)i);
 		ret = txq_uar_init_secondary(txq_ctrl, fd);
@@ -764,663 +651,6 @@ error:
 	return -rte_errno;
 }
 
-/**
- * Create the Tx hairpin queue object.
- *
- * @param dev
- *   Pointer to Ethernet device.
- * @param idx
- *   Queue index in DPDK Tx queue array
- *
- * @return
- *   The hairpin DevX object initialised, NULL otherwise and rte_errno is set.
- */
-static struct mlx5_txq_obj *
-mlx5_txq_obj_hairpin_new(struct rte_eth_dev *dev, uint16_t idx)
-{
-	struct mlx5_priv *priv = dev->data->dev_private;
-	struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
-	struct mlx5_txq_ctrl *txq_ctrl =
-		container_of(txq_data, struct mlx5_txq_ctrl, txq);
-	struct mlx5_devx_create_sq_attr attr = { 0 };
-	struct mlx5_txq_obj *tmpl = NULL;
-	uint32_t max_wq_data;
-
-	MLX5_ASSERT(txq_data);
-	MLX5_ASSERT(!txq_ctrl->obj);
-	tmpl = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO, sizeof(*tmpl), 0,
-			   txq_ctrl->socket);
-	if (!tmpl) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u cannot allocate memory resources",
-			dev->data->port_id, txq_data->idx);
-		rte_errno = ENOMEM;
-		return NULL;
-	}
-	tmpl->type = MLX5_TXQ_OBJ_TYPE_DEVX_HAIRPIN;
-	tmpl->txq_ctrl = txq_ctrl;
-	attr.hairpin = 1;
-	attr.tis_lst_sz = 1;
-	max_wq_data = priv->config.hca_attr.log_max_hairpin_wq_data_sz;
-	/* Jumbo frames > 9KB should be supported, and more packets. */
-	if (priv->config.log_hp_size != (uint32_t)MLX5_ARG_UNSET) {
-		if (priv->config.log_hp_size > max_wq_data) {
-			DRV_LOG(ERR, "total data size %u power of 2 is "
-				"too large for hairpin",
-				priv->config.log_hp_size);
-			mlx5_free(tmpl);
-			rte_errno = ERANGE;
-			return NULL;
-		}
-		attr.wq_attr.log_hairpin_data_sz = priv->config.log_hp_size;
-	} else {
-		attr.wq_attr.log_hairpin_data_sz =
-				(max_wq_data < MLX5_HAIRPIN_JUMBO_LOG_SIZE) ?
-				 max_wq_data : MLX5_HAIRPIN_JUMBO_LOG_SIZE;
-	}
-	/* Set the packets number to the maximum value for performance. */
-	attr.wq_attr.log_hairpin_num_packets =
-			attr.wq_attr.log_hairpin_data_sz -
-			MLX5_HAIRPIN_QUEUE_STRIDE;
-	attr.tis_num = priv->sh->tis->id;
-	tmpl->sq = mlx5_devx_cmd_create_sq(priv->sh->ctx, &attr);
-	if (!tmpl->sq) {
-		DRV_LOG(ERR,
-			"port %u tx hairpin queue %u can't create sq object",
-			dev->data->port_id, idx);
-		mlx5_free(tmpl);
-		rte_errno = errno;
-		return NULL;
-	}
-	DRV_LOG(DEBUG, "port %u sxq %u updated with %p", dev->data->port_id,
-		idx, (void *)&tmpl);
-	LIST_INSERT_HEAD(&priv->txqsobj, tmpl, next);
-	return tmpl;
-}
-
-/**
- * Destroy the Tx queue DevX object.
- *
- * @param txq_obj
- *   Txq object to destroy
- */
-static void
-txq_release_sq_resources(struct mlx5_txq_obj *txq_obj)
-{
-	MLX5_ASSERT(txq_obj->type == MLX5_TXQ_OBJ_TYPE_DEVX_SQ);
-
-	if (txq_obj->sq_devx)
-		claim_zero(mlx5_devx_cmd_destroy(txq_obj->sq_devx));
-	if (txq_obj->sq_dbrec_page)
-		claim_zero(mlx5_release_dbr
-				(&txq_obj->txq_ctrl->priv->dbrpgs,
-				mlx5_os_get_umem_id
-					(txq_obj->sq_dbrec_page->umem),
-				txq_obj->sq_dbrec_offset));
-	if (txq_obj->sq_umem)
-		claim_zero(mlx5_glue->devx_umem_dereg(txq_obj->sq_umem));
-	if (txq_obj->sq_buf)
-		mlx5_free(txq_obj->sq_buf);
-	if (txq_obj->cq_devx)
-		claim_zero(mlx5_devx_cmd_destroy(txq_obj->cq_devx));
-	if (txq_obj->cq_dbrec_page)
-		claim_zero(mlx5_release_dbr
-				(&txq_obj->txq_ctrl->priv->dbrpgs,
-				mlx5_os_get_umem_id
-					(txq_obj->cq_dbrec_page->umem),
-				txq_obj->cq_dbrec_offset));
-	if (txq_obj->cq_umem)
-		claim_zero(mlx5_glue->devx_umem_dereg(txq_obj->cq_umem));
-	if (txq_obj->cq_buf)
-		mlx5_free(txq_obj->cq_buf);
-}
-
-/**
- * Create the Tx queue DevX object.
- *
- * @param dev
- *   Pointer to Ethernet device.
- * @param idx
- *   Queue index in DPDK Tx queue array
- *
- * @return
- *   The DevX object initialised, NULL otherwise and rte_errno is set.
- */
-static struct mlx5_txq_obj *
-mlx5_txq_obj_devx_new(struct rte_eth_dev *dev, uint16_t idx)
-{
-#ifndef HAVE_MLX5DV_DEVX_UAR_OFFSET
-	DRV_LOG(ERR, "port %u Tx queue %u cannot create with DevX, no UAR",
-		     dev->data->port_id, idx);
-	rte_errno = ENOMEM;
-	return NULL;
-#else
-	struct mlx5_priv *priv = dev->data->dev_private;
-	struct mlx5_dev_ctx_shared *sh = priv->sh;
-	struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
-	struct mlx5_txq_ctrl *txq_ctrl =
-		container_of(txq_data, struct mlx5_txq_ctrl, txq);
-	struct mlx5_devx_create_sq_attr sq_attr = { 0 };
-	struct mlx5_devx_modify_sq_attr msq_attr = { 0 };
-	struct mlx5_devx_cq_attr cq_attr = { 0 };
-	struct mlx5_txq_obj *txq_obj = NULL;
-	size_t page_size;
-	struct mlx5_cqe *cqe;
-	uint32_t i, nqe;
-	void *reg_addr;
-	size_t alignment = (size_t)-1;
-	int ret = 0;
-
-	MLX5_ASSERT(txq_data);
-	MLX5_ASSERT(!txq_ctrl->obj);
-	page_size = rte_mem_page_size();
-	if (page_size == (size_t)-1) {
-		DRV_LOG(ERR, "Failed to get mem page size");
-		rte_errno = ENOMEM;
-		return NULL;
-	}
-	txq_obj = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO,
-			      sizeof(struct mlx5_txq_obj), 0,
-			      txq_ctrl->socket);
-	if (!txq_obj) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u cannot allocate memory resources",
-			dev->data->port_id, txq_data->idx);
-		rte_errno = ENOMEM;
-		return NULL;
-	}
-	txq_obj->type = MLX5_TXQ_OBJ_TYPE_DEVX_SQ;
-	txq_obj->txq_ctrl = txq_ctrl;
-	txq_obj->dev = dev;
-	/* Create the Completion Queue. */
-	nqe = (1UL << txq_data->elts_n) / MLX5_TX_COMP_THRESH +
-	       1 + MLX5_TX_COMP_THRESH_INLINE_DIV;
-	nqe = 1UL << log2above(nqe);
-	if (nqe > UINT16_MAX) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u requests to many CQEs %u",
-			dev->data->port_id, txq_data->idx, nqe);
-		rte_errno = EINVAL;
-		goto error;
-	}
-	/* Allocate memory buffer for CQEs. */
-	alignment = MLX5_CQE_BUF_ALIGNMENT;
-	if (alignment == (size_t)-1) {
-		DRV_LOG(ERR, "Failed to get mem page size");
-		rte_errno = ENOMEM;
-		goto error;
-	}
-	txq_obj->cq_buf = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO,
-				      nqe * sizeof(struct mlx5_cqe),
-				      alignment,
-				      sh->numa_node);
-	if (!txq_obj->cq_buf) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u cannot allocate memory (CQ)",
-			dev->data->port_id, txq_data->idx);
-		rte_errno = ENOMEM;
-		goto error;
-	}
-	txq_data->cqe_n = log2above(nqe);
-	txq_data->cqe_s = 1 << txq_data->cqe_n;
-	txq_data->cqe_m = txq_data->cqe_s - 1;
-	txq_data->cqes = (volatile struct mlx5_cqe *)txq_obj->cq_buf;
-	txq_data->cq_ci = 0;
-	txq_data->cq_pi = 0;
-	/* Register allocated buffer in user space with DevX. */
-	txq_obj->cq_umem = mlx5_glue->devx_umem_reg
-					(sh->ctx,
-					 (void *)txq_obj->cq_buf,
-					 nqe * sizeof(struct mlx5_cqe),
-					 IBV_ACCESS_LOCAL_WRITE);
-	if (!txq_obj->cq_umem) {
-		rte_errno = errno;
-		DRV_LOG(ERR,
-			"port %u Tx queue %u cannot register memory (CQ)",
-			dev->data->port_id, txq_data->idx);
-		goto error;
-	}
-	/* Allocate doorbell record for completion queue. */
-	txq_obj->cq_dbrec_offset = mlx5_get_dbr(sh->ctx,
-						&priv->dbrpgs,
-						&txq_obj->cq_dbrec_page);
-	if (txq_obj->cq_dbrec_offset < 0)
-		goto error;
-	txq_data->cq_db = (volatile uint32_t *)(txq_obj->cq_dbrec_page->dbrs +
-						txq_obj->cq_dbrec_offset);
-	*txq_data->cq_db = 0;
-	/* Create completion queue object with DevX. */
-	cq_attr.cqe_size = (sizeof(struct mlx5_cqe) == 128) ?
-			    MLX5_CQE_SIZE_128B : MLX5_CQE_SIZE_64B;
-	cq_attr.uar_page_id = mlx5_os_get_devx_uar_page_id(sh->tx_uar);
-	cq_attr.eqn = sh->txpp.eqn;
-	cq_attr.q_umem_valid = 1;
-	cq_attr.q_umem_offset = (uintptr_t)txq_obj->cq_buf % page_size;
-	cq_attr.q_umem_id = mlx5_os_get_umem_id(txq_obj->cq_umem);
-	cq_attr.db_umem_valid = 1;
-	cq_attr.db_umem_offset = txq_obj->cq_dbrec_offset;
-	cq_attr.db_umem_id = mlx5_os_get_umem_id(txq_obj->cq_dbrec_page->umem);
-	cq_attr.log_cq_size = rte_log2_u32(nqe);
-	cq_attr.log_page_size = rte_log2_u32(page_size);
-	txq_obj->cq_devx = mlx5_devx_cmd_create_cq(sh->ctx, &cq_attr);
-	if (!txq_obj->cq_devx) {
-		rte_errno = errno;
-		DRV_LOG(ERR, "port %u Tx queue %u CQ creation failure",
-			dev->data->port_id, idx);
-		goto error;
-	}
-	/* Initial fill CQ buffer with invalid CQE opcode. */
-	cqe = (struct mlx5_cqe *)txq_obj->cq_buf;
-	for (i = 0; i < txq_data->cqe_s; i++) {
-		cqe->op_own = (MLX5_CQE_INVALID << 4) | MLX5_CQE_OWNER_MASK;
-		++cqe;
-	}
-	/* Create the Work Queue. */
-	nqe = RTE_MIN(1UL << txq_data->elts_n,
-		      (uint32_t)sh->device_attr.max_qp_wr);
-	txq_obj->sq_buf = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO,
-				      nqe * sizeof(struct mlx5_wqe),
-				      page_size, sh->numa_node);
-	if (!txq_obj->sq_buf) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u cannot allocate memory (SQ)",
-			dev->data->port_id, txq_data->idx);
-		rte_errno = ENOMEM;
-		goto error;
-	}
-	txq_data->wqe_n = log2above(nqe);
-	txq_data->wqe_s = 1 << txq_data->wqe_n;
-	txq_data->wqe_m = txq_data->wqe_s - 1;
-	txq_data->wqes = (struct mlx5_wqe *)txq_obj->sq_buf;
-	txq_data->wqes_end = txq_data->wqes + txq_data->wqe_s;
-	txq_data->wqe_ci = 0;
-	txq_data->wqe_pi = 0;
-	txq_data->wqe_comp = 0;
-	txq_data->wqe_thres = txq_data->wqe_s / MLX5_TX_COMP_THRESH_INLINE_DIV;
-	/* Register allocated buffer in user space with DevX. */
-	txq_obj->sq_umem = mlx5_glue->devx_umem_reg
-					(sh->ctx,
-					 (void *)txq_obj->sq_buf,
-					 nqe * sizeof(struct mlx5_wqe),
-					 IBV_ACCESS_LOCAL_WRITE);
-	if (!txq_obj->sq_umem) {
-		rte_errno = errno;
-		DRV_LOG(ERR,
-			"port %u Tx queue %u cannot register memory (SQ)",
-			dev->data->port_id, txq_data->idx);
-		goto error;
-	}
-	/* Allocate doorbell record for send queue. */
-	txq_obj->sq_dbrec_offset = mlx5_get_dbr(sh->ctx,
-						&priv->dbrpgs,
-						&txq_obj->sq_dbrec_page);
-	if (txq_obj->sq_dbrec_offset < 0)
-		goto error;
-	txq_data->qp_db = (volatile uint32_t *)
-					(txq_obj->sq_dbrec_page->dbrs +
-					 txq_obj->sq_dbrec_offset +
-					 MLX5_SND_DBR * sizeof(uint32_t));
-	*txq_data->qp_db = 0;
-	/* Create Send Queue object with DevX. */
-	sq_attr.tis_lst_sz = 1;
-	sq_attr.tis_num = sh->tis->id;
-	sq_attr.state = MLX5_SQC_STATE_RST;
-	sq_attr.cqn = txq_obj->cq_devx->id;
-	sq_attr.flush_in_error_en = 1;
-	sq_attr.allow_multi_pkt_send_wqe = !!priv->config.mps;
-	sq_attr.allow_swp = !!priv->config.swp;
-	sq_attr.min_wqe_inline_mode = priv->config.hca_attr.vport_inline_mode;
-	sq_attr.wq_attr.uar_page = mlx5_os_get_devx_uar_page_id(sh->tx_uar);
-	sq_attr.wq_attr.wq_type = MLX5_WQ_TYPE_CYCLIC;
-	sq_attr.wq_attr.pd = sh->pdn;
-	sq_attr.wq_attr.log_wq_stride = rte_log2_u32(MLX5_WQE_SIZE);
-	sq_attr.wq_attr.log_wq_sz = txq_data->wqe_n;
-	sq_attr.wq_attr.dbr_umem_valid = 1;
-	sq_attr.wq_attr.dbr_addr = txq_obj->sq_dbrec_offset;
-	sq_attr.wq_attr.dbr_umem_id =
-			mlx5_os_get_umem_id(txq_obj->sq_dbrec_page->umem);
-	sq_attr.wq_attr.wq_umem_valid = 1;
-	sq_attr.wq_attr.wq_umem_id = mlx5_os_get_umem_id(txq_obj->sq_umem);
-	sq_attr.wq_attr.wq_umem_offset = (uintptr_t)txq_obj->sq_buf % page_size;
-	txq_obj->sq_devx = mlx5_devx_cmd_create_sq(sh->ctx, &sq_attr);
-	if (!txq_obj->sq_devx) {
-		rte_errno = errno;
-		DRV_LOG(ERR, "port %u Tx queue %u SQ creation failure",
-			dev->data->port_id, idx);
-		goto error;
-	}
-	txq_data->qp_num_8s = txq_obj->sq_devx->id << 8;
-	/* Change Send Queue state to Ready-to-Send. */
-	msq_attr.sq_state = MLX5_SQC_STATE_RST;
-	msq_attr.state = MLX5_SQC_STATE_RDY;
-	ret = mlx5_devx_cmd_modify_sq(txq_obj->sq_devx, &msq_attr);
-	if (ret) {
-		rte_errno = errno;
-		DRV_LOG(ERR,
-			"port %u Tx queue %u SP state to SQC_STATE_RDY failed",
-			dev->data->port_id, idx);
-		goto error;
-	}
-	txq_data->fcqs = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO,
-				     txq_data->cqe_s * sizeof(*txq_data->fcqs),
-				     RTE_CACHE_LINE_SIZE,
-				     txq_ctrl->socket);
-	if (!txq_data->fcqs) {
-		DRV_LOG(ERR, "port %u Tx queue %u cannot allocate memory (FCQ)",
-			dev->data->port_id, idx);
-		rte_errno = ENOMEM;
-		goto error;
-	}
-#ifdef HAVE_IBV_FLOW_DV_SUPPORT
-	/*
-	 * If using DevX need to query and store TIS transport domain value.
-	 * This is done once per port.
-	 * Will use this value on Rx, when creating matching TIR.
-	 */
-	if (priv->config.devx && !priv->sh->tdn)
-		priv->sh->tdn = priv->sh->td->id;
-#endif
-	MLX5_ASSERT(sh->tx_uar);
-	reg_addr = mlx5_os_get_devx_uar_reg_addr(sh->tx_uar);
-	MLX5_ASSERT(reg_addr);
-	txq_ctrl->bf_reg = reg_addr;
-	txq_ctrl->uar_mmap_offset =
-		mlx5_os_get_devx_uar_mmap_offset(sh->tx_uar);
-	txq_uar_init(txq_ctrl);
-	LIST_INSERT_HEAD(&priv->txqsobj, txq_obj, next);
-	return txq_obj;
-error:
-	ret = rte_errno; /* Save rte_errno before cleanup. */
-	txq_release_sq_resources(txq_obj);
-	if (txq_data->fcqs) {
-		mlx5_free(txq_data->fcqs);
-		txq_data->fcqs = NULL;
-	}
-	mlx5_free(txq_obj);
-	rte_errno = ret; /* Restore rte_errno. */
-	return NULL;
-#endif
-}
-
-/**
- * Create the Tx queue Verbs object.
- *
- * @param dev
- *   Pointer to Ethernet device.
- * @param idx
- *   Queue index in DPDK Tx queue array.
- * @param type
- *   Type of the Tx queue object to create.
- *
- * @return
- *   The Verbs object initialised, NULL otherwise and rte_errno is set.
- */
-struct mlx5_txq_obj *
-mlx5_txq_obj_new(struct rte_eth_dev *dev, uint16_t idx,
-		 enum mlx5_txq_obj_type type)
-{
-	struct mlx5_priv *priv = dev->data->dev_private;
-	struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
-	struct mlx5_txq_ctrl *txq_ctrl =
-		container_of(txq_data, struct mlx5_txq_ctrl, txq);
-	struct mlx5_txq_obj tmpl;
-	struct mlx5_txq_obj *txq_obj = NULL;
-	union {
-		struct ibv_qp_init_attr_ex init;
-		struct ibv_qp_attr mod;
-	} attr;
-	unsigned int cqe_n;
-	struct mlx5dv_qp qp = { .comp_mask = MLX5DV_QP_MASK_UAR_MMAP_OFFSET };
-	struct mlx5dv_cq cq_info;
-	struct mlx5dv_obj obj;
-	const int desc = 1 << txq_data->elts_n;
-	int ret = 0;
-
-	if (type == MLX5_TXQ_OBJ_TYPE_DEVX_HAIRPIN)
-		return mlx5_txq_obj_hairpin_new(dev, idx);
-	if (type == MLX5_TXQ_OBJ_TYPE_DEVX_SQ)
-		return mlx5_txq_obj_devx_new(dev, idx);
-#ifdef HAVE_IBV_FLOW_DV_SUPPORT
-	/* If using DevX, need additional mask to read tisn value. */
-	if (priv->config.devx && !priv->sh->tdn)
-		qp.comp_mask |= MLX5DV_QP_MASK_RAW_QP_HANDLES;
-#endif
-	MLX5_ASSERT(txq_data);
-	priv->verbs_alloc_ctx.type = MLX5_VERBS_ALLOC_TYPE_TX_QUEUE;
-	priv->verbs_alloc_ctx.obj = txq_ctrl;
-	if (mlx5_getenv_int("MLX5_ENABLE_CQE_COMPRESSION")) {
-		DRV_LOG(ERR,
-			"port %u MLX5_ENABLE_CQE_COMPRESSION must never be set",
-			dev->data->port_id);
-		rte_errno = EINVAL;
-		return NULL;
-	}
-	memset(&tmpl, 0, sizeof(struct mlx5_txq_obj));
-	cqe_n = desc / MLX5_TX_COMP_THRESH +
-		1 + MLX5_TX_COMP_THRESH_INLINE_DIV;
-	tmpl.cq = mlx5_glue->create_cq(priv->sh->ctx, cqe_n, NULL, NULL, 0);
-	if (tmpl.cq == NULL) {
-		DRV_LOG(ERR, "port %u Tx queue %u CQ creation failure",
-			dev->data->port_id, idx);
-		rte_errno = errno;
-		goto error;
-	}
-	attr.init = (struct ibv_qp_init_attr_ex){
-		/* CQ to be associated with the send queue. */
-		.send_cq = tmpl.cq,
-		/* CQ to be associated with the receive queue. */
-		.recv_cq = tmpl.cq,
-		.cap = {
-			/* Max number of outstanding WRs. */
-			.max_send_wr =
-				((priv->sh->device_attr.max_qp_wr <
-				  desc) ?
-				 priv->sh->device_attr.max_qp_wr :
-				 desc),
-			/*
-			 * Max number of scatter/gather elements in a WR,
-			 * must be 1 to prevent libmlx5 from trying to affect
-			 * too much memory. TX gather is not impacted by the
-			 * device_attr.max_sge limit and will still work
-			 * properly.
-			 */
-			.max_send_sge = 1,
-		},
-		.qp_type = IBV_QPT_RAW_PACKET,
-		/*
-		 * Do *NOT* enable this, completions events are managed per
-		 * Tx burst.
-		 */
-		.sq_sig_all = 0,
-		.pd = priv->sh->pd,
-		.comp_mask = IBV_QP_INIT_ATTR_PD,
-	};
-	if (txq_data->inlen_send)
-		attr.init.cap.max_inline_data = txq_ctrl->max_inline_data;
-	if (txq_data->tso_en) {
-		attr.init.max_tso_header = txq_ctrl->max_tso_header;
-		attr.init.comp_mask |= IBV_QP_INIT_ATTR_MAX_TSO_HEADER;
-	}
-	tmpl.qp = mlx5_glue->create_qp_ex(priv->sh->ctx, &attr.init);
-	if (tmpl.qp == NULL) {
-		DRV_LOG(ERR, "port %u Tx queue %u QP creation failure",
-			dev->data->port_id, idx);
-		rte_errno = errno;
-		goto error;
-	}
-	attr.mod = (struct ibv_qp_attr){
-		/* Move the QP to this state. */
-		.qp_state = IBV_QPS_INIT,
-		/* IB device port number. */
-		.port_num = (uint8_t)priv->dev_port,
-	};
-	ret = mlx5_glue->modify_qp(tmpl.qp, &attr.mod,
-				   (IBV_QP_STATE | IBV_QP_PORT));
-	if (ret) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u QP state to IBV_QPS_INIT failed",
-			dev->data->port_id, idx);
-		rte_errno = errno;
-		goto error;
-	}
-	attr.mod = (struct ibv_qp_attr){
-		.qp_state = IBV_QPS_RTR
-	};
-	ret = mlx5_glue->modify_qp(tmpl.qp, &attr.mod, IBV_QP_STATE);
-	if (ret) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u QP state to IBV_QPS_RTR failed",
-			dev->data->port_id, idx);
-		rte_errno = errno;
-		goto error;
-	}
-	attr.mod.qp_state = IBV_QPS_RTS;
-	ret = mlx5_glue->modify_qp(tmpl.qp, &attr.mod, IBV_QP_STATE);
-	if (ret) {
-		DRV_LOG(ERR,
-			"port %u Tx queue %u QP state to IBV_QPS_RTS failed",
-			dev->data->port_id, idx);
-		rte_errno = errno;
-		goto error;
-	}
-	txq_obj = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO,
-			      sizeof(struct mlx5_txq_obj), 0,
-			      txq_ctrl->socket);
-	if (!txq_obj) {
-		DRV_LOG(ERR, "port %u Tx queue %u cannot allocate memory",
-			dev->data->port_id, idx);
-		rte_errno = ENOMEM;
-		goto error;
-	}
-	obj.cq.in = tmpl.cq;
-	obj.cq.out = &cq_info;
-	obj.qp.in = tmpl.qp;
-	obj.qp.out = &qp;
-	ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_CQ | MLX5DV_OBJ_QP);
-	if (ret != 0) {
-		rte_errno = errno;
-		goto error;
-	}
-	if (cq_info.cqe_size != RTE_CACHE_LINE_SIZE) {
-		DRV_LOG(ERR,
-			"port %u wrong MLX5_CQE_SIZE environment variable"
-			" value: it should be set to %u",
-			dev->data->port_id, RTE_CACHE_LINE_SIZE);
-		rte_errno = EINVAL;
-		goto error;
-	}
-	txq_data->cqe_n = log2above(cq_info.cqe_cnt);
-	txq_data->cqe_s = 1 << txq_data->cqe_n;
-	txq_data->cqe_m = txq_data->cqe_s - 1;
-	txq_data->qp_num_8s = ((struct ibv_qp *)tmpl.qp)->qp_num << 8;
-	txq_data->wqes = qp.sq.buf;
-	txq_data->wqe_n = log2above(qp.sq.wqe_cnt);
-	txq_data->wqe_s = 1 << txq_data->wqe_n;
-	txq_data->wqe_m = txq_data->wqe_s - 1;
-	txq_data->wqes_end = txq_data->wqes + txq_data->wqe_s;
-	txq_data->qp_db = &qp.dbrec[MLX5_SND_DBR];
-	txq_data->cq_db = cq_info.dbrec;
-	txq_data->cqes = (volatile struct mlx5_cqe *)cq_info.buf;
-	txq_data->cq_ci = 0;
-	txq_data->cq_pi = 0;
-	txq_data->wqe_ci = 0;
-	txq_data->wqe_pi = 0;
-	txq_data->wqe_comp = 0;
-	txq_data->wqe_thres = txq_data->wqe_s / MLX5_TX_COMP_THRESH_INLINE_DIV;
-	txq_data->fcqs = mlx5_malloc(MLX5_MEM_RTE | MLX5_MEM_ZERO,
-				     txq_data->cqe_s * sizeof(*txq_data->fcqs),
-				     RTE_CACHE_LINE_SIZE, txq_ctrl->socket);
-	if (!txq_data->fcqs) {
-		DRV_LOG(ERR, "port %u Tx queue %u cannot allocate memory (FCQ)",
-			dev->data->port_id, idx);
-		rte_errno = ENOMEM;
-		goto error;
-	}
-#ifdef HAVE_IBV_FLOW_DV_SUPPORT
-	/*
-	 * If using DevX need to query and store TIS transport domain value.
-	 * This is done once per port.
-	 * Will use this value on Rx, when creating matching TIR.
-	 */
-	if (priv->config.devx && !priv->sh->tdn) {
-		ret = mlx5_devx_cmd_qp_query_tis_td(tmpl.qp, qp.tisn,
-						    &priv->sh->tdn);
-		if (ret) {
-			DRV_LOG(ERR, "Fail to query port %u Tx queue %u QP TIS "
-				"transport domain", dev->data->port_id, idx);
-			rte_errno = EINVAL;
-			goto error;
-		} else {
-			DRV_LOG(DEBUG, "port %u Tx queue %u TIS number %d "
-				"transport domain %d", dev->data->port_id,
-				idx, qp.tisn, priv->sh->tdn);
-		}
-	}
-#endif
-	txq_obj->qp = tmpl.qp;
-	txq_obj->cq = tmpl.cq;
-	txq_ctrl->bf_reg = qp.bf.reg;
-	if (qp.comp_mask & MLX5DV_QP_MASK_UAR_MMAP_OFFSET) {
-		txq_ctrl->uar_mmap_offset = qp.uar_mmap_offset;
-		DRV_LOG(DEBUG, "port %u: uar_mmap_offset 0x%"PRIx64,
-			dev->data->port_id, txq_ctrl->uar_mmap_offset);
-	} else {
-		DRV_LOG(ERR,
-			"port %u failed to retrieve UAR info, invalid"
-			" libmlx5.so",
-			dev->data->port_id);
-		rte_errno = EINVAL;
-		goto error;
-	}
-	txq_uar_init(txq_ctrl);
-	LIST_INSERT_HEAD(&priv->txqsobj, txq_obj, next);
-	txq_obj->txq_ctrl = txq_ctrl;
-	priv->verbs_alloc_ctx.type = MLX5_VERBS_ALLOC_TYPE_NONE;
-	return txq_obj;
-error:
-	ret = rte_errno; /* Save rte_errno before cleanup. */
-	if (tmpl.cq)
-		claim_zero(mlx5_glue->destroy_cq(tmpl.cq));
-	if (tmpl.qp)
-		claim_zero(mlx5_glue->destroy_qp(tmpl.qp));
-	if (txq_data && txq_data->fcqs) {
-		mlx5_free(txq_data->fcqs);
-		txq_data->fcqs = NULL;
-	}
-	if (txq_obj)
-		mlx5_free(txq_obj);
-	priv->verbs_alloc_ctx.type = MLX5_VERBS_ALLOC_TYPE_NONE;
-	rte_errno = ret; /* Restore rte_errno. */
-	return NULL;
-}
-
-/**
- * Release an Tx verbs queue object.
- *
- * @param txq_obj
- *   Verbs Tx queue object..
- */
-void
-mlx5_txq_obj_release(struct mlx5_txq_obj *txq_obj)
-{
-	MLX5_ASSERT(txq_obj);
-	if (txq_obj->type == MLX5_TXQ_OBJ_TYPE_DEVX_HAIRPIN) {
-		if (txq_obj->tis)
-			claim_zero(mlx5_devx_cmd_destroy(txq_obj->tis));
-	} else if (txq_obj->type == MLX5_TXQ_OBJ_TYPE_DEVX_SQ) {
-		txq_release_sq_resources(txq_obj);
-	} else {
-		claim_zero(mlx5_glue->destroy_qp(txq_obj->qp));
-		claim_zero(mlx5_glue->destroy_cq(txq_obj->cq));
-	}
-	if (txq_obj->txq_ctrl->txq.fcqs) {
-		mlx5_free(txq_obj->txq_ctrl->txq.fcqs);
-		txq_obj->txq_ctrl->txq.fcqs = NULL;
-	}
-	LIST_REMOVE(txq_obj, next);
-	mlx5_free(txq_obj);
-}
-
 /**
  * Verify the Verbs Tx queue list is empty
  *
@@ -1486,7 +716,7 @@ txq_calc_inline_max(struct mlx5_txq_ctrl *txq_ctrl)
 	struct mlx5_priv *priv = txq_ctrl->priv;
 	unsigned int wqe_size;
 
-	wqe_size = priv->sh->device_attr.max_qp_wr / desc;
+	wqe_size = priv->sh->dev_cap.max_qp_wr / desc;
 	if (!wqe_size)
 		return 0;
 	/*
@@ -1512,24 +742,29 @@ static void
 txq_set_params(struct mlx5_txq_ctrl *txq_ctrl)
 {
 	struct mlx5_priv *priv = txq_ctrl->priv;
-	struct mlx5_dev_config *config = &priv->config;
+	struct mlx5_port_config *config = &priv->config;
+	struct mlx5_dev_cap *dev_cap = &priv->sh->dev_cap;
 	unsigned int inlen_send; /* Inline data for ordinary SEND.*/
 	unsigned int inlen_empw; /* Inline data for enhanced MPW. */
 	unsigned int inlen_mode; /* Minimal required Inline data. */
 	unsigned int txqs_inline; /* Min Tx queues to enable inline. */
 	uint64_t dev_txoff = priv->dev_data->dev_conf.txmode.offloads;
-	bool tso = txq_ctrl->txq.offloads & (DEV_TX_OFFLOAD_TCP_TSO |
-					    DEV_TX_OFFLOAD_VXLAN_TNL_TSO |
-					    DEV_TX_OFFLOAD_GRE_TNL_TSO |
-					    DEV_TX_OFFLOAD_IP_TNL_TSO |
-					    DEV_TX_OFFLOAD_UDP_TNL_TSO);
+	bool tso = txq_ctrl->txq.offloads & (RTE_ETH_TX_OFFLOAD_TCP_TSO |
+					    RTE_ETH_TX_OFFLOAD_VXLAN_TNL_TSO |
+					    RTE_ETH_TX_OFFLOAD_GRE_TNL_TSO |
+					    RTE_ETH_TX_OFFLOAD_IP_TNL_TSO |
+					    RTE_ETH_TX_OFFLOAD_UDP_TNL_TSO);
 	bool vlan_inline;
 	unsigned int temp;
 
+	txq_ctrl->txq.fast_free =
+		!!((txq_ctrl->txq.offloads & RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE) &&
+		   !(txq_ctrl->txq.offloads & RTE_ETH_TX_OFFLOAD_MULTI_SEGS) &&
+		   !config->mprq.enabled);
 	if (config->txqs_inline == MLX5_ARG_UNSET)
 		txqs_inline =
 #if defined(RTE_ARCH_ARM64)
-		(priv->pci_dev->id.device_id ==
+		(priv->pci_dev && priv->pci_dev->id.device_id ==
 			PCI_DEVICE_ID_MELLANOX_CONNECTX5BF) ?
 			MLX5_INLINE_MAX_TXQS_BLUEFIELD :
 #endif
@@ -1583,7 +818,7 @@ txq_set_params(struct mlx5_txq_ctrl *txq_ctrl)
 	 * tx_burst routine.
 	 */
 	txq_ctrl->txq.vlan_en = config->hw_vlan_insert;
-	vlan_inline = (dev_txoff & DEV_TX_OFFLOAD_VLAN_INSERT) &&
+	vlan_inline = (dev_txoff & RTE_ETH_TX_OFFLOAD_VLAN_INSERT) &&
 		      !config->hw_vlan_insert;
 	/*
 	 * If there are few Tx queues it is prioritized
@@ -1691,11 +926,21 @@ txq_set_params(struct mlx5_txq_ctrl *txq_ctrl)
 						    MLX5_MAX_TSO_HEADER);
 		txq_ctrl->txq.tso_en = 1;
 	}
-	txq_ctrl->txq.tunnel_en = config->tunnel_en | config->swp;
-	txq_ctrl->txq.swp_en = ((DEV_TX_OFFLOAD_IP_TNL_TSO |
-				 DEV_TX_OFFLOAD_UDP_TNL_TSO |
-				 DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM) &
-				txq_ctrl->txq.offloads) && config->swp;
+	if (((RTE_ETH_TX_OFFLOAD_VXLAN_TNL_TSO & txq_ctrl->txq.offloads) &&
+	    (dev_cap->tunnel_en & MLX5_TUNNELED_OFFLOADS_VXLAN_CAP)) |
+	   ((RTE_ETH_TX_OFFLOAD_GRE_TNL_TSO & txq_ctrl->txq.offloads) &&
+	    (dev_cap->tunnel_en & MLX5_TUNNELED_OFFLOADS_GRE_CAP)) |
+	   ((RTE_ETH_TX_OFFLOAD_GENEVE_TNL_TSO & txq_ctrl->txq.offloads) &&
+	    (dev_cap->tunnel_en & MLX5_TUNNELED_OFFLOADS_GENEVE_CAP)) |
+	   (dev_cap->swp  & MLX5_SW_PARSING_TSO_CAP))
+		txq_ctrl->txq.tunnel_en = 1;
+	txq_ctrl->txq.swp_en = (((RTE_ETH_TX_OFFLOAD_IP_TNL_TSO |
+				  RTE_ETH_TX_OFFLOAD_UDP_TNL_TSO) &
+				  txq_ctrl->txq.offloads) && (dev_cap->swp &
+				  MLX5_SW_PARSING_TSO_CAP)) |
+				((RTE_ETH_TX_OFFLOAD_OUTER_IPV4_CKSUM &
+				 txq_ctrl->txq.offloads) && (dev_cap->swp &
+				 MLX5_SW_PARSING_CSUM_CAP));
 }
 
 /**
@@ -1716,7 +961,7 @@ static int
 txq_adjust_params(struct mlx5_txq_ctrl *txq_ctrl)
 {
 	struct mlx5_priv *priv = txq_ctrl->priv;
-	struct mlx5_dev_config *config = &priv->config;
+	struct mlx5_port_config *config = &priv->config;
 	unsigned int max_inline;
 
 	max_inline = txq_calc_inline_max(txq_ctrl);
@@ -1740,8 +985,7 @@ txq_adjust_params(struct mlx5_txq_ctrl *txq_ctrl)
 			" satisfied (%u) on port %u, try the smaller"
 			" Tx queue size (%d)",
 			txq_ctrl->txq.inlen_mode, max_inline,
-			priv->dev_data->port_id,
-			priv->sh->device_attr.max_qp_wr);
+			priv->dev_data->port_id, priv->sh->dev_cap.max_qp_wr);
 		goto error;
 	}
 	if (txq_ctrl->txq.inlen_send > max_inline &&
@@ -1752,8 +996,7 @@ txq_adjust_params(struct mlx5_txq_ctrl *txq_ctrl)
 			" satisfied (%u) on port %u, try the smaller"
 			" Tx queue size (%d)",
 			txq_ctrl->txq.inlen_send, max_inline,
-			priv->dev_data->port_id,
-			priv->sh->device_attr.max_qp_wr);
+			priv->dev_data->port_id, priv->sh->dev_cap.max_qp_wr);
 		goto error;
 	}
 	if (txq_ctrl->txq.inlen_empw > max_inline &&
@@ -1764,8 +1007,7 @@ txq_adjust_params(struct mlx5_txq_ctrl *txq_ctrl)
 			" satisfied (%u) on port %u, try the smaller"
 			" Tx queue size (%d)",
 			txq_ctrl->txq.inlen_empw, max_inline,
-			priv->dev_data->port_id,
-			priv->sh->device_attr.max_qp_wr);
+			priv->dev_data->port_id, priv->sh->dev_cap.max_qp_wr);
 		goto error;
 	}
 	if (txq_ctrl->txq.tso_en && max_inline < MLX5_MAX_TSO_HEADER) {
@@ -1774,8 +1016,7 @@ txq_adjust_params(struct mlx5_txq_ctrl *txq_ctrl)
 			" satisfied (%u) on port %u, try the smaller"
 			" Tx queue size (%d)",
 			MLX5_MAX_TSO_HEADER, max_inline,
-			priv->dev_data->port_id,
-			priv->sh->device_attr.max_qp_wr);
+			priv->dev_data->port_id, priv->sh->dev_cap.max_qp_wr);
 		goto error;
 	}
 	if (txq_ctrl->txq.inlen_send > max_inline) {
@@ -1837,13 +1078,11 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 		rte_errno = ENOMEM;
 		return NULL;
 	}
-	if (mlx5_mr_btree_init(&tmpl->txq.mr_ctrl.cache_bh,
-			       MLX5_MR_BTREE_CACHE_N, socket)) {
+	if (mlx5_mr_ctrl_init(&tmpl->txq.mr_ctrl,
+			      &priv->sh->cdev->mr_scache.dev_gen, socket)) {
 		/* rte_errno is already set. */
 		goto error;
 	}
-	/* Save pointer of global generation number to check memory event. */
-	tmpl->txq.mr_ctrl.dev_gen_ptr = &priv->sh->share_cache.dev_gen;
 	MLX5_ASSERT(desc > MLX5_TX_COMP_THRESH);
 	tmpl->txq.offloads = conf->offloads |
 			     dev->data->dev_conf.txmode.offloads;
@@ -1858,20 +1097,21 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 	if (txq_adjust_params(tmpl))
 		goto error;
 	if (txq_calc_wqebb_cnt(tmpl) >
-	    priv->sh->device_attr.max_qp_wr) {
+	    priv->sh->dev_cap.max_qp_wr) {
 		DRV_LOG(ERR,
 			"port %u Tx WQEBB count (%d) exceeds the limit (%d),"
 			" try smaller queue size",
 			dev->data->port_id, txq_calc_wqebb_cnt(tmpl),
-			priv->sh->device_attr.max_qp_wr);
+			priv->sh->dev_cap.max_qp_wr);
 		rte_errno = ENOMEM;
 		goto error;
 	}
-	rte_atomic32_inc(&tmpl->refcnt);
-	tmpl->type = MLX5_TXQ_TYPE_STANDARD;
+	__atomic_fetch_add(&tmpl->refcnt, 1, __ATOMIC_RELAXED);
+	tmpl->is_hairpin = false;
 	LIST_INSERT_HEAD(&priv->txqsctrl, tmpl, next);
 	return tmpl;
 error:
+	mlx5_mr_btree_free(&tmpl->txq.mr_ctrl.cache_bh);
 	mlx5_free(tmpl);
 	return NULL;
 }
@@ -1910,8 +1150,8 @@ mlx5_txq_hairpin_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
 	tmpl->txq.port_id = dev->data->port_id;
 	tmpl->txq.idx = idx;
 	tmpl->hairpin_conf = *hairpin_conf;
-	tmpl->type = MLX5_TXQ_TYPE_HAIRPIN;
-	rte_atomic32_inc(&tmpl->refcnt);
+	tmpl->is_hairpin = true;
+	__atomic_fetch_add(&tmpl->refcnt, 1, __ATOMIC_RELAXED);
 	LIST_INSERT_HEAD(&priv->txqsctrl, tmpl, next);
 	return tmpl;
 }
@@ -1936,7 +1176,7 @@ mlx5_txq_get(struct rte_eth_dev *dev, uint16_t idx)
 
 	if (txq_data) {
 		ctrl = container_of(txq_data, struct mlx5_txq_ctrl, txq);
-		rte_atomic32_inc(&ctrl->refcnt);
+		__atomic_fetch_add(&ctrl->refcnt, 1, __ATOMIC_RELAXED);
 	}
 	return ctrl;
 }
@@ -1956,23 +1196,34 @@ int
 mlx5_txq_release(struct rte_eth_dev *dev, uint16_t idx)
 {
 	struct mlx5_priv *priv = dev->data->dev_private;
-	struct mlx5_txq_ctrl *txq;
+	struct mlx5_txq_ctrl *txq_ctrl;
 
-	if (!(*priv->txqs)[idx])
+	if (priv->txqs == NULL || (*priv->txqs)[idx] == NULL)
 		return 0;
-	txq = container_of((*priv->txqs)[idx], struct mlx5_txq_ctrl, txq);
-	if (!rte_atomic32_dec_and_test(&txq->refcnt))
+	txq_ctrl = container_of((*priv->txqs)[idx], struct mlx5_txq_ctrl, txq);
+	if (__atomic_sub_fetch(&txq_ctrl->refcnt, 1, __ATOMIC_RELAXED) > 1)
 		return 1;
-	if (txq->obj) {
-		mlx5_txq_obj_release(txq->obj);
-		txq->obj = NULL;
+	if (txq_ctrl->obj) {
+		priv->obj_ops.txq_obj_release(txq_ctrl->obj);
+		LIST_REMOVE(txq_ctrl->obj, next);
+		mlx5_free(txq_ctrl->obj);
+		txq_ctrl->obj = NULL;
+	}
+	if (!txq_ctrl->is_hairpin) {
+		if (txq_ctrl->txq.fcqs) {
+			mlx5_free(txq_ctrl->txq.fcqs);
+			txq_ctrl->txq.fcqs = NULL;
+		}
+		txq_free_elts(txq_ctrl);
+		dev->data->tx_queue_state[idx] = RTE_ETH_QUEUE_STATE_STOPPED;
+	}
+	if (!__atomic_load_n(&txq_ctrl->refcnt, __ATOMIC_RELAXED)) {
+		if (!txq_ctrl->is_hairpin)
+			mlx5_mr_btree_free(&txq_ctrl->txq.mr_ctrl.cache_bh);
+		LIST_REMOVE(txq_ctrl, next);
+		mlx5_free(txq_ctrl);
+		(*priv->txqs)[idx] = NULL;
 	}
-	txq_free_elts(txq);
-	mlx5_mr_btree_free(&txq->txq.mr_ctrl.cache_bh);
-	LIST_REMOVE(txq, next);
-	mlx5_free(txq);
-	(*priv->txqs)[idx] = NULL;
-	dev->data->tx_queue_state[idx] = RTE_ETH_QUEUE_STATE_STOPPED;
 	return 0;
 }
 
@@ -1996,7 +1247,7 @@ mlx5_txq_releasable(struct rte_eth_dev *dev, uint16_t idx)
 	if (!(*priv->txqs)[idx])
 		return -1;
 	txq = container_of((*priv->txqs)[idx], struct mlx5_txq_ctrl, txq);
-	return (rte_atomic32_read(&txq->refcnt) == 1);
+	return (__atomic_load_n(&txq->refcnt, __ATOMIC_RELAXED) == 1);
 }
 
 /**
@@ -2038,12 +1289,21 @@ mlx5_txq_dynf_timestamp_set(struct rte_eth_dev *dev)
 	int off, nbit;
 	unsigned int i;
 	uint64_t mask = 0;
+	uint64_t ts_mask;
 
+	if (sh->dev_cap.rt_timestamp ||
+	    !sh->cdev->config.hca_attr.dev_freq_khz)
+		ts_mask = MLX5_TS_MASK_SECS << 32;
+	else
+		ts_mask = rte_align64pow2(MLX5_TS_MASK_SECS * 1000ull *
+				sh->cdev->config.hca_attr.dev_freq_khz);
+	ts_mask = rte_cpu_to_be_64(ts_mask - 1ull);
 	nbit = rte_mbuf_dynflag_lookup
 				(RTE_MBUF_DYNFLAG_TX_TIMESTAMP_NAME, NULL);
 	off = rte_mbuf_dynfield_lookup
 				(RTE_MBUF_DYNFIELD_TIMESTAMP_NAME, NULL);
-	if (nbit > 0 && off >= 0 && sh->txpp.refcnt)
+	if (nbit >= 0 && off >= 0 &&
+	    (sh->txpp.refcnt || priv->sh->cdev->config.hca_attr.wait_on_time))
 		mask = 1ULL << nbit;
 	for (i = 0; i != priv->txqs_n; ++i) {
 		data = (*priv->txqs)[i];
@@ -2052,5 +1312,9 @@ mlx5_txq_dynf_timestamp_set(struct rte_eth_dev *dev)
 		data->sh = sh;
 		data->ts_mask = mask;
 		data->ts_offset = off;
+		data->rt_timestamp = sh->dev_cap.rt_timestamp;
+		data->rt_timemask = (data->offloads &
+				     RTE_ETH_TX_OFFLOAD_SEND_ON_TIMESTAMP) ?
+				     ts_mask : 0;
 	}
 }