[dpdk-dev] [PATCH 1/7] net/mlx5: remove Tx datapath implementation

Viacheslav Ovsiienko viacheslavo at mellanox.com
Thu Jul 4 18:29:21 CEST 2019


This patch removes the existing Tx datapath code
as preparation step before introducing the new
implementation. The following entities are being
removed:

- obsolete devargs
- tx_burst() routines
- related PRM definitions
- SQ configuration code
- Tx routine selection code
- incompatible Tx completion code

Signed-off-by: Viacheslav Ovsiienko <viacheslavo at mellanox.com>
---
 drivers/net/mlx5/mlx5.c               |   43 -
 drivers/net/mlx5/mlx5.h               |    5 -
 drivers/net/mlx5/mlx5_defs.h          |   16 -
 drivers/net/mlx5/mlx5_ethdev.c        |   58 --
 drivers/net/mlx5/mlx5_prm.h           |   77 --
 drivers/net/mlx5/mlx5_rxtx.c          | 1434 +--------------------------------
 drivers/net/mlx5/mlx5_rxtx.h          |  273 -------
 drivers/net/mlx5/mlx5_rxtx_vec.c      |  175 ----
 drivers/net/mlx5/mlx5_rxtx_vec_neon.h |  289 -------
 drivers/net/mlx5/mlx5_rxtx_vec_sse.h  |  284 -------
 drivers/net/mlx5/mlx5_txq.c           |  110 +--
 11 files changed, 35 insertions(+), 2729 deletions(-)

diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index d93f92d..42b36a7 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -68,33 +68,15 @@
 /* Device parameter to set the minimum number of Rx queues to enable MPRQ. */
 #define MLX5_RXQS_MIN_MPRQ "rxqs_min_mprq"
 
-/* Device parameter to configure inline send. */
-#define MLX5_TXQ_INLINE "txq_inline"
-
 /*
  * Device parameter to configure the number of TX queues threshold for
  * enabling inline send.
  */
 #define MLX5_TXQS_MIN_INLINE "txqs_min_inline"
 
-/*
- * Device parameter to configure the number of TX queues threshold for
- * enabling vectorized Tx.
- */
-#define MLX5_TXQS_MAX_VEC "txqs_max_vec"
-
 /* Device parameter to enable multi-packet send WQEs. */
 #define MLX5_TXQ_MPW_EN "txq_mpw_en"
 
-/* Device parameter to include 2 dsegs in the title WQEBB. */
-#define MLX5_TXQ_MPW_HDR_DSEG_EN "txq_mpw_hdr_dseg_en"
-
-/* Device parameter to limit the size of inlining packet. */
-#define MLX5_TXQ_MAX_INLINE_LEN "txq_max_inline_len"
-
-/* Device parameter to enable hardware Tx vector. */
-#define MLX5_TX_VEC_EN "tx_vec_en"
-
 /* Device parameter to enable hardware Rx vector. */
 #define MLX5_RX_VEC_EN "rx_vec_en"
 
@@ -902,20 +884,10 @@ struct mlx5_dev_spawn_data {
 		config->mprq.max_memcpy_len = tmp;
 	} else if (strcmp(MLX5_RXQS_MIN_MPRQ, key) == 0) {
 		config->mprq.min_rxqs_num = tmp;
-	} else if (strcmp(MLX5_TXQ_INLINE, key) == 0) {
-		config->txq_inline = tmp;
 	} else if (strcmp(MLX5_TXQS_MIN_INLINE, key) == 0) {
 		config->txqs_inline = tmp;
-	} else if (strcmp(MLX5_TXQS_MAX_VEC, key) == 0) {
-		config->txqs_vec = tmp;
 	} else if (strcmp(MLX5_TXQ_MPW_EN, key) == 0) {
 		config->mps = !!tmp;
-	} else if (strcmp(MLX5_TXQ_MPW_HDR_DSEG_EN, key) == 0) {
-		config->mpw_hdr_dseg = !!tmp;
-	} else if (strcmp(MLX5_TXQ_MAX_INLINE_LEN, key) == 0) {
-		config->inline_max_packet_sz = tmp;
-	} else if (strcmp(MLX5_TX_VEC_EN, key) == 0) {
-		config->tx_vec_en = !!tmp;
 	} else if (strcmp(MLX5_RX_VEC_EN, key) == 0) {
 		config->rx_vec_en = !!tmp;
 	} else if (strcmp(MLX5_L3_VXLAN_EN, key) == 0) {
@@ -960,13 +932,8 @@ struct mlx5_dev_spawn_data {
 		MLX5_RX_MPRQ_LOG_STRIDE_NUM,
 		MLX5_RX_MPRQ_MAX_MEMCPY_LEN,
 		MLX5_RXQS_MIN_MPRQ,
-		MLX5_TXQ_INLINE,
 		MLX5_TXQS_MIN_INLINE,
-		MLX5_TXQS_MAX_VEC,
 		MLX5_TXQ_MPW_EN,
-		MLX5_TXQ_MPW_HDR_DSEG_EN,
-		MLX5_TXQ_MAX_INLINE_LEN,
-		MLX5_TX_VEC_EN,
 		MLX5_RX_VEC_EN,
 		MLX5_L3_VXLAN_EN,
 		MLX5_VF_NL_EN,
@@ -1914,12 +1881,8 @@ struct mlx5_dev_spawn_data {
 	dev_config = (struct mlx5_dev_config){
 		.hw_padding = 0,
 		.mps = MLX5_ARG_UNSET,
-		.tx_vec_en = 1,
 		.rx_vec_en = 1,
-		.txq_inline = MLX5_ARG_UNSET,
 		.txqs_inline = MLX5_ARG_UNSET,
-		.txqs_vec = MLX5_ARG_UNSET,
-		.inline_max_packet_sz = MLX5_ARG_UNSET,
 		.vf_nl_en = 1,
 		.mr_ext_memseg_en = 1,
 		.mprq = {
@@ -1932,9 +1895,6 @@ struct mlx5_dev_spawn_data {
 	};
 	/* Device specific configuration. */
 	switch (pci_dev->id.device_id) {
-	case PCI_DEVICE_ID_MELLANOX_CONNECTX5BF:
-		dev_config.txqs_vec = MLX5_VPMD_MAX_TXQS_BLUEFIELD;
-		break;
 	case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
 	case PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF:
 	case PCI_DEVICE_ID_MELLANOX_CONNECTX5VF:
@@ -1944,9 +1904,6 @@ struct mlx5_dev_spawn_data {
 	default:
 		break;
 	}
-	/* Set architecture-dependent default value if unset. */
-	if (dev_config.txqs_vec == MLX5_ARG_UNSET)
-		dev_config.txqs_vec = MLX5_VPMD_MAX_TXQS;
 	for (i = 0; i != ns; ++i) {
 		uint32_t restore;
 
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index e6d24d7..47c9e47 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -188,9 +188,7 @@ struct mlx5_dev_config {
 	unsigned int cqe_comp:1; /* CQE compression is enabled. */
 	unsigned int cqe_pad:1; /* CQE padding is enabled. */
 	unsigned int tso:1; /* Whether TSO is supported. */
-	unsigned int tx_vec_en:1; /* Tx vector is enabled. */
 	unsigned int rx_vec_en:1; /* Rx vector is enabled. */
-	unsigned int mpw_hdr_dseg:1; /* Enable DSEGs in the title WQEBB. */
 	unsigned int mr_ext_memseg_en:1;
 	/* Whether memseg should be extended for MR creation. */
 	unsigned int l3_vxlan_en:1; /* Enable L3 VXLAN flow creation. */
@@ -214,10 +212,7 @@ struct mlx5_dev_config {
 	unsigned int tso_max_payload_sz; /* Maximum TCP payload for TSO. */
 	unsigned int ind_table_max_size; /* Maximum indirection table size. */
 	unsigned int max_dump_files_num; /* Maximum dump files per queue. */
-	int txq_inline; /* Maximum packet size for inlining. */
 	int txqs_inline; /* Queue number threshold for inlining. */
-	int txqs_vec; /* Queue number threshold for vectorized Tx. */
-	int inline_max_packet_sz; /* Max packet size for inlining. */
 	struct mlx5_hca_attr hca_attr; /* HCA attributes. */
 };
 
diff --git a/drivers/net/mlx5/mlx5_defs.h b/drivers/net/mlx5/mlx5_defs.h
index 13801a5..6861304 100644
--- a/drivers/net/mlx5/mlx5_defs.h
+++ b/drivers/net/mlx5/mlx5_defs.h
@@ -60,15 +60,6 @@
 /* Maximum Packet headers size (L2+L3+L4) for TSO. */
 #define MLX5_MAX_TSO_HEADER 192
 
-/* Default maximum number of Tx queues for vectorized Tx. */
-#if defined(RTE_ARCH_ARM64)
-#define MLX5_VPMD_MAX_TXQS 8
-#define MLX5_VPMD_MAX_TXQS_BLUEFIELD 16
-#else
-#define MLX5_VPMD_MAX_TXQS 4
-#define MLX5_VPMD_MAX_TXQS_BLUEFIELD MLX5_VPMD_MAX_TXQS
-#endif
-
 /* Threshold of buffer replenishment for vectorized Rx. */
 #define MLX5_VPMD_RXQ_RPLNSH_THRESH(n) \
 	(RTE_MIN(MLX5_VPMD_RX_MAX_BURST, (unsigned int)(n) >> 2))
@@ -76,13 +67,6 @@
 /* Maximum size of burst for vectorized Rx. */
 #define MLX5_VPMD_RX_MAX_BURST 64U
 
-/*
- * Maximum size of burst for vectorized Tx. This is related to the maximum size
- * of Enhanced MPW (eMPW) WQE as vectorized Tx is supported with eMPW.
- * Careful when changing, large value can cause WQE DS to overlap.
- */
-#define MLX5_VPMD_TX_MAX_BURST        32U
-
 /* Number of packets vectorized Rx can simultaneously process in a loop. */
 #define MLX5_VPMD_DESCS_PER_LOOP      4
 
diff --git a/drivers/net/mlx5/mlx5_ethdev.c b/drivers/net/mlx5/mlx5_ethdev.c
index 9377f96..e98f1c1 100644
--- a/drivers/net/mlx5/mlx5_ethdev.c
+++ b/drivers/net/mlx5/mlx5_ethdev.c
@@ -1576,64 +1576,6 @@ int mlx5_fw_version_get(struct rte_eth_dev *dev, char *fw_ver, size_t fw_size)
 }
 
 /**
- * Configure the TX function to use.
- *
- * @param dev
- *   Pointer to private data structure.
- *
- * @return
- *   Pointer to selected Tx burst function.
- */
-eth_tx_burst_t
-mlx5_select_tx_function(struct rte_eth_dev *dev)
-{
-	struct mlx5_priv *priv = dev->data->dev_private;
-	eth_tx_burst_t tx_pkt_burst = mlx5_tx_burst;
-	struct mlx5_dev_config *config = &priv->config;
-	uint64_t tx_offloads = dev->data->dev_conf.txmode.offloads;
-	int tso = !!(tx_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));
-	int swp = !!(tx_offloads & (DEV_TX_OFFLOAD_IP_TNL_TSO |
-				    DEV_TX_OFFLOAD_UDP_TNL_TSO |
-				    DEV_TX_OFFLOAD_OUTER_IPV4_CKSUM));
-	int vlan_insert = !!(tx_offloads & DEV_TX_OFFLOAD_VLAN_INSERT);
-
-	assert(priv != NULL);
-	/* Select appropriate TX function. */
-	if (vlan_insert || tso || swp)
-		return tx_pkt_burst;
-	if (config->mps == MLX5_MPW_ENHANCED) {
-		if (mlx5_check_vec_tx_support(dev) > 0) {
-			if (mlx5_check_raw_vec_tx_support(dev) > 0)
-				tx_pkt_burst = mlx5_tx_burst_raw_vec;
-			else
-				tx_pkt_burst = mlx5_tx_burst_vec;
-			DRV_LOG(DEBUG,
-				"port %u selected enhanced MPW Tx vectorized"
-				" function",
-				dev->data->port_id);
-		} else {
-			tx_pkt_burst = mlx5_tx_burst_empw;
-			DRV_LOG(DEBUG,
-				"port %u selected enhanced MPW Tx function",
-				dev->data->port_id);
-		}
-	} else if (config->mps && (config->txq_inline > 0)) {
-		tx_pkt_burst = mlx5_tx_burst_mpw_inline;
-		DRV_LOG(DEBUG, "port %u selected MPW inline Tx function",
-			dev->data->port_id);
-	} else if (config->mps) {
-		tx_pkt_burst = mlx5_tx_burst_mpw;
-		DRV_LOG(DEBUG, "port %u selected MPW Tx function",
-			dev->data->port_id);
-	}
-	return tx_pkt_burst;
-}
-
-/**
  * Configure the RX function to use.
  *
  * @param dev
diff --git a/drivers/net/mlx5/mlx5_prm.h b/drivers/net/mlx5/mlx5_prm.h
index 1a19958..3589f51 100644
--- a/drivers/net/mlx5/mlx5_prm.h
+++ b/drivers/net/mlx5/mlx5_prm.h
@@ -39,32 +39,12 @@
 /* Invalidate a CQE. */
 #define MLX5_CQE_INVALIDATE (MLX5_CQE_INVALID << 4)
 
-/* Maximum number of packets a multi-packet WQE can handle. */
-#define MLX5_MPW_DSEG_MAX 5
-
 /* WQE DWORD size */
 #define MLX5_WQE_DWORD_SIZE 16
 
 /* WQE size */
 #define MLX5_WQE_SIZE (4 * MLX5_WQE_DWORD_SIZE)
 
-/* Max size of a WQE session. */
-#define MLX5_WQE_SIZE_MAX 960U
-
-/* Compute the number of DS. */
-#define MLX5_WQE_DS(n) \
-	(((n) + MLX5_WQE_DWORD_SIZE - 1) / MLX5_WQE_DWORD_SIZE)
-
-/* Room for inline data in multi-packet WQE. */
-#define MLX5_MWQE64_INL_DATA 28
-
-/* Default minimum number of Tx queues for inlining packets. */
-#define MLX5_EMPW_MIN_TXQS 8
-
-/* Default max packet length to be inlined. */
-#define MLX5_EMPW_MAX_INLINE_LEN (4U * MLX5_WQE_SIZE)
-
-
 #define MLX5_OPC_MOD_ENHANCED_MPSW 0
 #define MLX5_OPCODE_ENHANCED_MPSW 0x29
 
@@ -164,47 +144,11 @@ enum mlx5_completion_mode {
 	MLX5_COMP_CQE_AND_EQE = 0x3,
 };
 
-/* Subset of struct mlx5_wqe_eth_seg. */
-struct mlx5_wqe_eth_seg_small {
-	uint32_t rsvd0;
-	uint8_t	cs_flags;
-	uint8_t	rsvd1;
-	uint16_t mss;
-	uint32_t flow_table_metadata;
-	uint16_t inline_hdr_sz;
-	uint8_t inline_hdr[2];
-} __rte_aligned(MLX5_WQE_DWORD_SIZE);
-
-struct mlx5_wqe_inl_small {
-	uint32_t byte_cnt;
-	uint8_t raw;
-} __rte_aligned(MLX5_WQE_DWORD_SIZE);
-
-struct mlx5_wqe_ctrl {
-	uint32_t ctrl0;
-	uint32_t ctrl1;
-	uint32_t ctrl2;
-	uint32_t ctrl3;
-} __rte_aligned(MLX5_WQE_DWORD_SIZE);
-
 /* Small common part of the WQE. */
 struct mlx5_wqe {
 	uint32_t ctrl[4];
-	struct mlx5_wqe_eth_seg_small eseg;
-};
-
-/* Vectorize WQE header. */
-struct mlx5_wqe_v {
-	rte_v128u32_t ctrl;
-	rte_v128u32_t eseg;
 };
 
-/* WQE. */
-struct mlx5_wqe64 {
-	struct mlx5_wqe hdr;
-	uint8_t raw[32];
-} __rte_aligned(MLX5_WQE_SIZE);
-
 /* MPW mode. */
 enum mlx5_mpw_mode {
 	MLX5_MPW_DISABLED,
@@ -212,27 +156,6 @@ enum mlx5_mpw_mode {
 	MLX5_MPW_ENHANCED, /* Enhanced Multi-Packet Send WQE, a.k.a MPWv2. */
 };
 
-/* MPW session status. */
-enum mlx5_mpw_state {
-	MLX5_MPW_STATE_OPENED,
-	MLX5_MPW_INL_STATE_OPENED,
-	MLX5_MPW_ENHANCED_STATE_OPENED,
-	MLX5_MPW_STATE_CLOSED,
-};
-
-/* MPW session descriptor. */
-struct mlx5_mpw {
-	enum mlx5_mpw_state state;
-	unsigned int pkts_n;
-	unsigned int len;
-	unsigned int total_len;
-	volatile struct mlx5_wqe *wqe;
-	union {
-		volatile struct mlx5_wqe_data_seg *dseg[MLX5_MPW_DSEG_MAX];
-		volatile uint8_t *raw;
-	} data;
-};
-
 /* WQE for Multi-Packet RQ. */
 struct mlx5_wqe_mprq {
 	struct mlx5_wqe_srq_next_seg next_seg;
diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
index c1dc8c4..f2d6918 100644
--- a/drivers/net/mlx5/mlx5_rxtx.c
+++ b/drivers/net/mlx5/mlx5_rxtx.c
@@ -288,140 +288,6 @@
 }
 
 /**
- * Return the size of tailroom of WQ.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param addr
- *   Pointer to tail of WQ.
- *
- * @return
- *   Size of tailroom.
- */
-static inline size_t
-tx_mlx5_wq_tailroom(struct mlx5_txq_data *txq, void *addr)
-{
-	size_t tailroom;
-	tailroom = (uintptr_t)(txq->wqes) +
-		   (1 << txq->wqe_n) * MLX5_WQE_SIZE -
-		   (uintptr_t)addr;
-	return tailroom;
-}
-
-/**
- * Copy data to tailroom of circular queue.
- *
- * @param dst
- *   Pointer to destination.
- * @param src
- *   Pointer to source.
- * @param n
- *   Number of bytes to copy.
- * @param base
- *   Pointer to head of queue.
- * @param tailroom
- *   Size of tailroom from dst.
- *
- * @return
- *   Pointer after copied data.
- */
-static inline void *
-mlx5_copy_to_wq(void *dst, const void *src, size_t n,
-		void *base, size_t tailroom)
-{
-	void *ret;
-
-	if (n > tailroom) {
-		rte_memcpy(dst, src, tailroom);
-		rte_memcpy(base, (void *)((uintptr_t)src + tailroom),
-			   n - tailroom);
-		ret = (uint8_t *)base + n - tailroom;
-	} else {
-		rte_memcpy(dst, src, n);
-		ret = (n == tailroom) ? base : (uint8_t *)dst + n;
-	}
-	return ret;
-}
-
-/**
- * Inline TSO headers into WQE.
- *
- * @return
- *   0 on success, negative errno value on failure.
- */
-static int
-inline_tso(struct mlx5_txq_data *txq, struct rte_mbuf *buf,
-	   uint32_t *length,
-	   uintptr_t *addr,
-	   uint16_t *pkt_inline_sz,
-	   uint8_t **raw,
-	   uint16_t *max_wqe,
-	   uint16_t *tso_segsz,
-	   uint16_t *tso_header_sz)
-{
-	uintptr_t end = (uintptr_t)(((uintptr_t)txq->wqes) +
-				    (1 << txq->wqe_n) * MLX5_WQE_SIZE);
-	unsigned int copy_b;
-	uint8_t vlan_sz = (buf->ol_flags & PKT_TX_VLAN_PKT) ? 4 : 0;
-	const uint8_t tunneled = txq->tunnel_en && (buf->ol_flags &
-				 PKT_TX_TUNNEL_MASK);
-	uint16_t n_wqe;
-
-	*tso_segsz = buf->tso_segsz;
-	*tso_header_sz = buf->l2_len + vlan_sz + buf->l3_len + buf->l4_len;
-	if (unlikely(*tso_segsz == 0 || *tso_header_sz == 0)) {
-		txq->stats.oerrors++;
-		return -EINVAL;
-	}
-	if (tunneled)
-		*tso_header_sz += buf->outer_l2_len + buf->outer_l3_len;
-	/* First seg must contain all TSO headers. */
-	if (unlikely(*tso_header_sz > MLX5_MAX_TSO_HEADER) ||
-		     *tso_header_sz > DATA_LEN(buf)) {
-		txq->stats.oerrors++;
-		return -EINVAL;
-	}
-	copy_b = *tso_header_sz - *pkt_inline_sz;
-	if (!copy_b || ((end - (uintptr_t)*raw) < copy_b))
-		return -EAGAIN;
-	n_wqe = (MLX5_WQE_DS(copy_b) - 1 + 3) / 4;
-	if (unlikely(*max_wqe < n_wqe))
-		return -EINVAL;
-	*max_wqe -= n_wqe;
-	rte_memcpy((void *)*raw, (void *)*addr, copy_b);
-	*length -= copy_b;
-	*addr += copy_b;
-	copy_b = MLX5_WQE_DS(copy_b) * MLX5_WQE_DWORD_SIZE;
-	*pkt_inline_sz += copy_b;
-	*raw += copy_b;
-	return 0;
-}
-
-/**
- * DPDK callback to check the status of a tx descriptor.
- *
- * @param tx_queue
- *   The tx queue.
- * @param[in] offset
- *   The index of the descriptor in the ring.
- *
- * @return
- *   The status of the tx descriptor.
- */
-int
-mlx5_tx_descriptor_status(void *tx_queue, uint16_t offset)
-{
-	struct mlx5_txq_data *txq = tx_queue;
-	uint16_t used;
-
-	mlx5_tx_complete(txq);
-	used = txq->elts_head - txq->elts_tail;
-	if (offset < used)
-		return RTE_ETH_TX_DESC_FULL;
-	return RTE_ETH_TX_DESC_DONE;
-}
-
-/**
  * Internal function to compute the number of used descriptors in an RX queue
  *
  * @param rxq
@@ -655,7 +521,7 @@
 						    (1 << txq->cqe_n));
 			mlx5_dump_debug_information(name, "MLX5 Error SQ:",
 						    (const void *)((uintptr_t)
-						    tx_mlx5_wqe(txq, 0)),
+						    txq->wqes),
 						    MLX5_WQE_SIZE *
 						    (1 << txq->wqe_n));
 			txq_ctrl->dump_file_n++;
@@ -683,1247 +549,6 @@
 }
 
 /**
- * DPDK callback for TX.
- *
- * @param dpdk_txq
- *   Generic pointer to TX queue structure.
- * @param[in] pkts
- *   Packets to transmit.
- * @param pkts_n
- *   Number of packets in array.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-uint16_t
-mlx5_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
-	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	unsigned int i = 0;
-	unsigned int j = 0;
-	unsigned int k = 0;
-	uint16_t max_elts;
-	uint16_t max_wqe;
-	unsigned int comp;
-	volatile struct mlx5_wqe_ctrl *last_wqe = NULL;
-	unsigned int segs_n = 0;
-	const unsigned int max_inline = txq->max_inline;
-	uint64_t addr_64;
-
-	if (unlikely(!pkts_n))
-		return 0;
-	/* Prefetch first packet cacheline. */
-	rte_prefetch0(*pkts);
-	/* Start processing. */
-	mlx5_tx_complete(txq);
-	max_elts = (elts_n - (elts_head - txq->elts_tail));
-	max_wqe = (1u << txq->wqe_n) - (txq->wqe_ci - txq->wqe_pi);
-	if (unlikely(!max_wqe))
-		return 0;
-	do {
-		struct rte_mbuf *buf = *pkts; /* First_seg. */
-		uint8_t *raw;
-		volatile struct mlx5_wqe_v *wqe = NULL;
-		volatile rte_v128u32_t *dseg = NULL;
-		uint32_t length;
-		unsigned int ds = 0;
-		unsigned int sg = 0; /* counter of additional segs attached. */
-		uintptr_t addr;
-		uint16_t pkt_inline_sz = MLX5_WQE_DWORD_SIZE + 2;
-		uint16_t tso_header_sz = 0;
-		uint16_t ehdr;
-		uint8_t cs_flags;
-		uint8_t tso = txq->tso_en && (buf->ol_flags & PKT_TX_TCP_SEG);
-		uint32_t swp_offsets = 0;
-		uint8_t swp_types = 0;
-		rte_be32_t metadata;
-		uint16_t tso_segsz = 0;
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		uint32_t total_length = 0;
-#endif
-		int ret;
-
-		segs_n = buf->nb_segs;
-		/*
-		 * Make sure there is enough room to store this packet and
-		 * that one ring entry remains unused.
-		 */
-		assert(segs_n);
-		if (max_elts < segs_n)
-			break;
-		max_elts -= segs_n;
-		sg = --segs_n;
-		if (unlikely(--max_wqe == 0))
-			break;
-		wqe = (volatile struct mlx5_wqe_v *)
-			tx_mlx5_wqe(txq, txq->wqe_ci);
-		rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci + 1));
-		if (pkts_n - i > 1)
-			rte_prefetch0(*(pkts + 1));
-		addr = rte_pktmbuf_mtod(buf, uintptr_t);
-		length = DATA_LEN(buf);
-		ehdr = (((uint8_t *)addr)[1] << 8) |
-		       ((uint8_t *)addr)[0];
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		total_length = length;
-#endif
-		if (length < (MLX5_WQE_DWORD_SIZE + 2)) {
-			txq->stats.oerrors++;
-			break;
-		}
-		/* Update element. */
-		(*txq->elts)[elts_head & elts_m] = buf;
-		/* Prefetch next buffer data. */
-		if (pkts_n - i > 1)
-			rte_prefetch0(
-			    rte_pktmbuf_mtod(*(pkts + 1), volatile void *));
-		cs_flags = txq_ol_cksum_to_cs(buf);
-		txq_mbuf_to_swp(txq, buf, (uint8_t *)&swp_offsets, &swp_types);
-		raw = ((uint8_t *)(uintptr_t)wqe) + 2 * MLX5_WQE_DWORD_SIZE;
-		/* Copy metadata from mbuf if valid */
-		metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
-							     0;
-		/* Replace the Ethernet type by the VLAN if necessary. */
-		if (buf->ol_flags & PKT_TX_VLAN_PKT) {
-			uint32_t vlan = rte_cpu_to_be_32(0x81000000 |
-							 buf->vlan_tci);
-			unsigned int len = 2 * RTE_ETHER_ADDR_LEN - 2;
-
-			addr += 2;
-			length -= 2;
-			/* Copy Destination and source mac address. */
-			memcpy((uint8_t *)raw, ((uint8_t *)addr), len);
-			/* Copy VLAN. */
-			memcpy((uint8_t *)raw + len, &vlan, sizeof(vlan));
-			/* Copy missing two bytes to end the DSeg. */
-			memcpy((uint8_t *)raw + len + sizeof(vlan),
-			       ((uint8_t *)addr) + len, 2);
-			addr += len + 2;
-			length -= (len + 2);
-		} else {
-			memcpy((uint8_t *)raw, ((uint8_t *)addr) + 2,
-			       MLX5_WQE_DWORD_SIZE);
-			length -= pkt_inline_sz;
-			addr += pkt_inline_sz;
-		}
-		raw += MLX5_WQE_DWORD_SIZE;
-		if (tso) {
-			ret = inline_tso(txq, buf, &length,
-					 &addr, &pkt_inline_sz,
-					 &raw, &max_wqe,
-					 &tso_segsz, &tso_header_sz);
-			if (ret == -EINVAL) {
-				break;
-			} else if (ret == -EAGAIN) {
-				/* NOP WQE. */
-				wqe->ctrl = (rte_v128u32_t){
-					rte_cpu_to_be_32(txq->wqe_ci << 8),
-					rte_cpu_to_be_32(txq->qp_num_8s | 1),
-					rte_cpu_to_be_32
-						(MLX5_COMP_ONLY_FIRST_ERR <<
-						 MLX5_COMP_MODE_OFFSET),
-					0,
-				};
-				ds = 1;
-#ifdef MLX5_PMD_SOFT_COUNTERS
-				total_length = 0;
-#endif
-				k++;
-				goto next_wqe;
-			}
-		}
-		/* Inline if enough room. */
-		if (max_inline || tso) {
-			uint32_t inl = 0;
-			uintptr_t end = (uintptr_t)
-				(((uintptr_t)txq->wqes) +
-				 (1 << txq->wqe_n) * MLX5_WQE_SIZE);
-			unsigned int inline_room = max_inline *
-						   RTE_CACHE_LINE_SIZE -
-						   (pkt_inline_sz - 2) -
-						   !!tso * sizeof(inl);
-			uintptr_t addr_end;
-			unsigned int copy_b;
-
-pkt_inline:
-			addr_end = RTE_ALIGN_FLOOR(addr + inline_room,
-						   RTE_CACHE_LINE_SIZE);
-			copy_b = (addr_end > addr) ?
-				 RTE_MIN((addr_end - addr), length) : 0;
-			if (copy_b && ((end - (uintptr_t)raw) >
-				       (copy_b + sizeof(inl)))) {
-				/*
-				 * One Dseg remains in the current WQE.  To
-				 * keep the computation positive, it is
-				 * removed after the bytes to Dseg conversion.
-				 */
-				uint16_t n = (MLX5_WQE_DS(copy_b) - 1 + 3) / 4;
-
-				if (unlikely(max_wqe < n))
-					break;
-				max_wqe -= n;
-				if (tso) {
-					assert(inl == 0);
-					inl = rte_cpu_to_be_32(copy_b |
-							       MLX5_INLINE_SEG);
-					rte_memcpy((void *)raw,
-						   (void *)&inl, sizeof(inl));
-					raw += sizeof(inl);
-					pkt_inline_sz += sizeof(inl);
-				}
-				rte_memcpy((void *)raw, (void *)addr, copy_b);
-				addr += copy_b;
-				length -= copy_b;
-				pkt_inline_sz += copy_b;
-			}
-			/*
-			 * 2 DWORDs consumed by the WQE header + ETH segment +
-			 * the size of the inline part of the packet.
-			 */
-			ds = 2 + MLX5_WQE_DS(pkt_inline_sz - 2);
-			if (length > 0) {
-				if (ds % (MLX5_WQE_SIZE /
-					  MLX5_WQE_DWORD_SIZE) == 0) {
-					if (unlikely(--max_wqe == 0))
-						break;
-					dseg = (volatile rte_v128u32_t *)
-					       tx_mlx5_wqe(txq, txq->wqe_ci +
-							   ds / 4);
-				} else {
-					dseg = (volatile rte_v128u32_t *)
-						((uintptr_t)wqe +
-						 (ds * MLX5_WQE_DWORD_SIZE));
-				}
-				goto use_dseg;
-			} else if (!segs_n) {
-				goto next_pkt;
-			} else {
-				/*
-				 * Further inline the next segment only for
-				 * non-TSO packets.
-				 */
-				if (!tso) {
-					raw += copy_b;
-					inline_room -= copy_b;
-				} else {
-					inline_room = 0;
-				}
-				/* Move to the next segment. */
-				--segs_n;
-				buf = buf->next;
-				assert(buf);
-				addr = rte_pktmbuf_mtod(buf, uintptr_t);
-				length = DATA_LEN(buf);
-#ifdef MLX5_PMD_SOFT_COUNTERS
-				total_length += length;
-#endif
-				(*txq->elts)[++elts_head & elts_m] = buf;
-				goto pkt_inline;
-			}
-		} else {
-			/*
-			 * No inline has been done in the packet, only the
-			 * Ethernet Header as been stored.
-			 */
-			dseg = (volatile rte_v128u32_t *)
-				((uintptr_t)wqe + (3 * MLX5_WQE_DWORD_SIZE));
-			ds = 3;
-use_dseg:
-			/* Add the remaining packet as a simple ds. */
-			addr_64 = rte_cpu_to_be_64(addr);
-			*dseg = (rte_v128u32_t){
-				rte_cpu_to_be_32(length),
-				mlx5_tx_mb2mr(txq, buf),
-				addr_64,
-				addr_64 >> 32,
-			};
-			++ds;
-			if (!segs_n)
-				goto next_pkt;
-		}
-next_seg:
-		assert(buf);
-		assert(ds);
-		assert(wqe);
-		/*
-		 * Spill on next WQE when the current one does not have
-		 * enough room left. Size of WQE must a be a multiple
-		 * of data segment size.
-		 */
-		assert(!(MLX5_WQE_SIZE % MLX5_WQE_DWORD_SIZE));
-		if (!(ds % (MLX5_WQE_SIZE / MLX5_WQE_DWORD_SIZE))) {
-			if (unlikely(--max_wqe == 0))
-				break;
-			dseg = (volatile rte_v128u32_t *)
-			       tx_mlx5_wqe(txq, txq->wqe_ci + ds / 4);
-			rte_prefetch0(tx_mlx5_wqe(txq,
-						  txq->wqe_ci + ds / 4 + 1));
-		} else {
-			++dseg;
-		}
-		++ds;
-		buf = buf->next;
-		assert(buf);
-		length = DATA_LEN(buf);
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		total_length += length;
-#endif
-		/* Store segment information. */
-		addr_64 = rte_cpu_to_be_64(rte_pktmbuf_mtod(buf, uintptr_t));
-		*dseg = (rte_v128u32_t){
-			rte_cpu_to_be_32(length),
-			mlx5_tx_mb2mr(txq, buf),
-			addr_64,
-			addr_64 >> 32,
-		};
-		(*txq->elts)[++elts_head & elts_m] = buf;
-		if (--segs_n)
-			goto next_seg;
-next_pkt:
-		if (ds > MLX5_DSEG_MAX) {
-			txq->stats.oerrors++;
-			break;
-		}
-		++elts_head;
-		++pkts;
-		++i;
-		j += sg;
-		/* Initialize known and common part of the WQE structure. */
-		if (tso) {
-			wqe->ctrl = (rte_v128u32_t){
-				rte_cpu_to_be_32((txq->wqe_ci << 8) |
-						 MLX5_OPCODE_TSO),
-				rte_cpu_to_be_32(txq->qp_num_8s | ds),
-				rte_cpu_to_be_32(MLX5_COMP_ONLY_FIRST_ERR <<
-						 MLX5_COMP_MODE_OFFSET),
-				0,
-			};
-			wqe->eseg = (rte_v128u32_t){
-				swp_offsets,
-				cs_flags | (swp_types << 8) |
-				(rte_cpu_to_be_16(tso_segsz) << 16),
-				metadata,
-				(ehdr << 16) | rte_cpu_to_be_16(tso_header_sz),
-			};
-		} else {
-			wqe->ctrl = (rte_v128u32_t){
-				rte_cpu_to_be_32((txq->wqe_ci << 8) |
-						 MLX5_OPCODE_SEND),
-				rte_cpu_to_be_32(txq->qp_num_8s | ds),
-				rte_cpu_to_be_32(MLX5_COMP_ONLY_FIRST_ERR <<
-						 MLX5_COMP_MODE_OFFSET),
-				0,
-			};
-			wqe->eseg = (rte_v128u32_t){
-				swp_offsets,
-				cs_flags | (swp_types << 8),
-				metadata,
-				(ehdr << 16) | rte_cpu_to_be_16(pkt_inline_sz),
-			};
-		}
-next_wqe:
-		txq->wqe_ci += (ds + 3) / 4;
-		/* Save the last successful WQE for completion request */
-		last_wqe = (volatile struct mlx5_wqe_ctrl *)wqe;
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		/* Increment sent bytes counter. */
-		txq->stats.obytes += total_length;
-#endif
-	} while (i < pkts_n);
-	/* Take a shortcut if nothing must be sent. */
-	if (unlikely((i + k) == 0))
-		return 0;
-	txq->elts_head += (i + j);
-	/* Check whether completion threshold has been reached. */
-	comp = txq->elts_comp + i + j + k;
-	if (comp >= MLX5_TX_COMP_THRESH) {
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		/* Request completion on last WQE. */
-		last_wqe->ctrl2 = rte_cpu_to_be_32(MLX5_COMP_ALWAYS <<
-						   MLX5_COMP_MODE_OFFSET);
-		/* Save elts_head in unused "immediate" field of WQE. */
-		last_wqe->ctrl3 = txq->elts_head;
-		txq->elts_comp = 0;
-	} else {
-		txq->elts_comp = comp;
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	/* Increment sent packets counter. */
-	txq->stats.opackets += i;
-#endif
-	/* Ring QP doorbell. */
-	mlx5_tx_dbrec(txq, (volatile struct mlx5_wqe *)last_wqe);
-	return i;
-}
-
-/**
- * Open a MPW session.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param mpw
- *   Pointer to MPW session structure.
- * @param length
- *   Packet length.
- */
-static inline void
-mlx5_mpw_new(struct mlx5_txq_data *txq, struct mlx5_mpw *mpw, uint32_t length)
-{
-	uint16_t idx = txq->wqe_ci & ((1 << txq->wqe_n) - 1);
-	volatile struct mlx5_wqe_data_seg (*dseg)[MLX5_MPW_DSEG_MAX] =
-		(volatile struct mlx5_wqe_data_seg (*)[])
-		tx_mlx5_wqe(txq, idx + 1);
-
-	mpw->state = MLX5_MPW_STATE_OPENED;
-	mpw->pkts_n = 0;
-	mpw->len = length;
-	mpw->total_len = 0;
-	mpw->wqe = (volatile struct mlx5_wqe *)tx_mlx5_wqe(txq, idx);
-	mpw->wqe->eseg.mss = rte_cpu_to_be_16(length);
-	mpw->wqe->eseg.inline_hdr_sz = 0;
-	mpw->wqe->eseg.rsvd0 = 0;
-	mpw->wqe->eseg.rsvd1 = 0;
-	mpw->wqe->eseg.flow_table_metadata = 0;
-	mpw->wqe->ctrl[0] = rte_cpu_to_be_32((MLX5_OPC_MOD_MPW << 24) |
-					     (txq->wqe_ci << 8) |
-					     MLX5_OPCODE_TSO);
-	mpw->wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ONLY_FIRST_ERR <<
-					     MLX5_COMP_MODE_OFFSET);
-	mpw->wqe->ctrl[3] = 0;
-	mpw->data.dseg[0] = (volatile struct mlx5_wqe_data_seg *)
-		(((uintptr_t)mpw->wqe) + (2 * MLX5_WQE_DWORD_SIZE));
-	mpw->data.dseg[1] = (volatile struct mlx5_wqe_data_seg *)
-		(((uintptr_t)mpw->wqe) + (3 * MLX5_WQE_DWORD_SIZE));
-	mpw->data.dseg[2] = &(*dseg)[0];
-	mpw->data.dseg[3] = &(*dseg)[1];
-	mpw->data.dseg[4] = &(*dseg)[2];
-}
-
-/**
- * Close a MPW session.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param mpw
- *   Pointer to MPW session structure.
- */
-static inline void
-mlx5_mpw_close(struct mlx5_txq_data *txq, struct mlx5_mpw *mpw)
-{
-	unsigned int num = mpw->pkts_n;
-
-	/*
-	 * Store size in multiple of 16 bytes. Control and Ethernet segments
-	 * count as 2.
-	 */
-	mpw->wqe->ctrl[1] = rte_cpu_to_be_32(txq->qp_num_8s | (2 + num));
-	mpw->state = MLX5_MPW_STATE_CLOSED;
-	if (num < 3)
-		++txq->wqe_ci;
-	else
-		txq->wqe_ci += 2;
-	rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci));
-	rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci + 1));
-}
-
-/**
- * DPDK callback for TX with MPW support.
- *
- * @param dpdk_txq
- *   Generic pointer to TX queue structure.
- * @param[in] pkts
- *   Packets to transmit.
- * @param pkts_n
- *   Number of packets in array.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-uint16_t
-mlx5_tx_burst_mpw(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
-	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	unsigned int i = 0;
-	unsigned int j = 0;
-	uint16_t max_elts;
-	uint16_t max_wqe;
-	unsigned int comp;
-	struct mlx5_mpw mpw = {
-		.state = MLX5_MPW_STATE_CLOSED,
-	};
-
-	if (unlikely(!pkts_n))
-		return 0;
-	/* Prefetch first packet cacheline. */
-	rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci));
-	rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci + 1));
-	/* Start processing. */
-	mlx5_tx_complete(txq);
-	max_elts = (elts_n - (elts_head - txq->elts_tail));
-	max_wqe = (1u << txq->wqe_n) - (txq->wqe_ci - txq->wqe_pi);
-	if (unlikely(!max_wqe))
-		return 0;
-	do {
-		struct rte_mbuf *buf = *(pkts++);
-		uint32_t length;
-		unsigned int segs_n = buf->nb_segs;
-		uint32_t cs_flags;
-		rte_be32_t metadata;
-
-		/*
-		 * Make sure there is enough room to store this packet and
-		 * that one ring entry remains unused.
-		 */
-		assert(segs_n);
-		if (max_elts < segs_n)
-			break;
-		/* Do not bother with large packets MPW cannot handle. */
-		if (segs_n > MLX5_MPW_DSEG_MAX) {
-			txq->stats.oerrors++;
-			break;
-		}
-		max_elts -= segs_n;
-		--pkts_n;
-		cs_flags = txq_ol_cksum_to_cs(buf);
-		/* Copy metadata from mbuf if valid */
-		metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
-							     0;
-		/* Retrieve packet information. */
-		length = PKT_LEN(buf);
-		assert(length);
-		/* Start new session if packet differs. */
-		if ((mpw.state == MLX5_MPW_STATE_OPENED) &&
-		    ((mpw.len != length) ||
-		     (segs_n != 1) ||
-		     (mpw.wqe->eseg.flow_table_metadata != metadata) ||
-		     (mpw.wqe->eseg.cs_flags != cs_flags)))
-			mlx5_mpw_close(txq, &mpw);
-		if (mpw.state == MLX5_MPW_STATE_CLOSED) {
-			/*
-			 * Multi-Packet WQE consumes at most two WQE.
-			 * mlx5_mpw_new() expects to be able to use such
-			 * resources.
-			 */
-			if (unlikely(max_wqe < 2))
-				break;
-			max_wqe -= 2;
-			mlx5_mpw_new(txq, &mpw, length);
-			mpw.wqe->eseg.cs_flags = cs_flags;
-			mpw.wqe->eseg.flow_table_metadata = metadata;
-		}
-		/* Multi-segment packets must be alone in their MPW. */
-		assert((segs_n == 1) || (mpw.pkts_n == 0));
-#if defined(MLX5_PMD_SOFT_COUNTERS) || !defined(NDEBUG)
-		length = 0;
-#endif
-		do {
-			volatile struct mlx5_wqe_data_seg *dseg;
-			uintptr_t addr;
-
-			assert(buf);
-			(*txq->elts)[elts_head++ & elts_m] = buf;
-			dseg = mpw.data.dseg[mpw.pkts_n];
-			addr = rte_pktmbuf_mtod(buf, uintptr_t);
-			*dseg = (struct mlx5_wqe_data_seg){
-				.byte_count = rte_cpu_to_be_32(DATA_LEN(buf)),
-				.lkey = mlx5_tx_mb2mr(txq, buf),
-				.addr = rte_cpu_to_be_64(addr),
-			};
-#if defined(MLX5_PMD_SOFT_COUNTERS) || !defined(NDEBUG)
-			length += DATA_LEN(buf);
-#endif
-			buf = buf->next;
-			++mpw.pkts_n;
-			++j;
-		} while (--segs_n);
-		assert(length == mpw.len);
-		if (mpw.pkts_n == MLX5_MPW_DSEG_MAX)
-			mlx5_mpw_close(txq, &mpw);
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		/* Increment sent bytes counter. */
-		txq->stats.obytes += length;
-#endif
-		++i;
-	} while (pkts_n);
-	/* Take a shortcut if nothing must be sent. */
-	if (unlikely(i == 0))
-		return 0;
-	/* Check whether completion threshold has been reached. */
-	/* "j" includes both packets and segments. */
-	comp = txq->elts_comp + j;
-	if (comp >= MLX5_TX_COMP_THRESH) {
-		volatile struct mlx5_wqe *wqe = mpw.wqe;
-
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		/* Request completion on last WQE. */
-		wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ALWAYS <<
-						MLX5_COMP_MODE_OFFSET);
-		/* Save elts_head in unused "immediate" field of WQE. */
-		wqe->ctrl[3] = elts_head;
-		txq->elts_comp = 0;
-	} else {
-		txq->elts_comp = comp;
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	/* Increment sent packets counter. */
-	txq->stats.opackets += i;
-#endif
-	/* Ring QP doorbell. */
-	if (mpw.state == MLX5_MPW_STATE_OPENED)
-		mlx5_mpw_close(txq, &mpw);
-	mlx5_tx_dbrec(txq, mpw.wqe);
-	txq->elts_head = elts_head;
-	return i;
-}
-
-/**
- * Open a MPW inline session.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param mpw
- *   Pointer to MPW session structure.
- * @param length
- *   Packet length.
- */
-static inline void
-mlx5_mpw_inline_new(struct mlx5_txq_data *txq, struct mlx5_mpw *mpw,
-		    uint32_t length)
-{
-	uint16_t idx = txq->wqe_ci & ((1 << txq->wqe_n) - 1);
-	struct mlx5_wqe_inl_small *inl;
-
-	mpw->state = MLX5_MPW_INL_STATE_OPENED;
-	mpw->pkts_n = 0;
-	mpw->len = length;
-	mpw->total_len = 0;
-	mpw->wqe = (volatile struct mlx5_wqe *)tx_mlx5_wqe(txq, idx);
-	mpw->wqe->ctrl[0] = rte_cpu_to_be_32((MLX5_OPC_MOD_MPW << 24) |
-					     (txq->wqe_ci << 8) |
-					     MLX5_OPCODE_TSO);
-	mpw->wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ONLY_FIRST_ERR <<
-					     MLX5_COMP_MODE_OFFSET);
-	mpw->wqe->ctrl[3] = 0;
-	mpw->wqe->eseg.mss = rte_cpu_to_be_16(length);
-	mpw->wqe->eseg.inline_hdr_sz = 0;
-	mpw->wqe->eseg.cs_flags = 0;
-	mpw->wqe->eseg.rsvd0 = 0;
-	mpw->wqe->eseg.rsvd1 = 0;
-	mpw->wqe->eseg.flow_table_metadata = 0;
-	inl = (struct mlx5_wqe_inl_small *)
-		(((uintptr_t)mpw->wqe) + 2 * MLX5_WQE_DWORD_SIZE);
-	mpw->data.raw = (uint8_t *)&inl->raw;
-}
-
-/**
- * Close a MPW inline session.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param mpw
- *   Pointer to MPW session structure.
- */
-static inline void
-mlx5_mpw_inline_close(struct mlx5_txq_data *txq, struct mlx5_mpw *mpw)
-{
-	unsigned int size;
-	struct mlx5_wqe_inl_small *inl = (struct mlx5_wqe_inl_small *)
-		(((uintptr_t)mpw->wqe) + (2 * MLX5_WQE_DWORD_SIZE));
-
-	size = MLX5_WQE_SIZE - MLX5_MWQE64_INL_DATA + mpw->total_len;
-	/*
-	 * Store size in multiple of 16 bytes. Control and Ethernet segments
-	 * count as 2.
-	 */
-	mpw->wqe->ctrl[1] = rte_cpu_to_be_32(txq->qp_num_8s |
-					     MLX5_WQE_DS(size));
-	mpw->state = MLX5_MPW_STATE_CLOSED;
-	inl->byte_cnt = rte_cpu_to_be_32(mpw->total_len | MLX5_INLINE_SEG);
-	txq->wqe_ci += (size + (MLX5_WQE_SIZE - 1)) / MLX5_WQE_SIZE;
-}
-
-/**
- * DPDK callback for TX with MPW inline support.
- *
- * @param dpdk_txq
- *   Generic pointer to TX queue structure.
- * @param[in] pkts
- *   Packets to transmit.
- * @param pkts_n
- *   Number of packets in array.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-uint16_t
-mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf **pkts,
-			 uint16_t pkts_n)
-{
-	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	unsigned int i = 0;
-	unsigned int j = 0;
-	uint16_t max_elts;
-	uint16_t max_wqe;
-	unsigned int comp;
-	unsigned int inline_room = txq->max_inline * RTE_CACHE_LINE_SIZE;
-	struct mlx5_mpw mpw = {
-		.state = MLX5_MPW_STATE_CLOSED,
-	};
-	/*
-	 * Compute the maximum number of WQE which can be consumed by inline
-	 * code.
-	 * - 2 DSEG for:
-	 *   - 1 control segment,
-	 *   - 1 Ethernet segment,
-	 * - N Dseg from the inline request.
-	 */
-	const unsigned int wqe_inl_n =
-		((2 * MLX5_WQE_DWORD_SIZE +
-		  txq->max_inline * RTE_CACHE_LINE_SIZE) +
-		 RTE_CACHE_LINE_SIZE - 1) / RTE_CACHE_LINE_SIZE;
-
-	if (unlikely(!pkts_n))
-		return 0;
-	/* Prefetch first packet cacheline. */
-	rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci));
-	rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci + 1));
-	/* Start processing. */
-	mlx5_tx_complete(txq);
-	max_elts = (elts_n - (elts_head - txq->elts_tail));
-	do {
-		struct rte_mbuf *buf = *(pkts++);
-		uintptr_t addr;
-		uint32_t length;
-		unsigned int segs_n = buf->nb_segs;
-		uint8_t cs_flags;
-		rte_be32_t metadata;
-
-		/*
-		 * Make sure there is enough room to store this packet and
-		 * that one ring entry remains unused.
-		 */
-		assert(segs_n);
-		if (max_elts < segs_n)
-			break;
-		/* Do not bother with large packets MPW cannot handle. */
-		if (segs_n > MLX5_MPW_DSEG_MAX) {
-			txq->stats.oerrors++;
-			break;
-		}
-		max_elts -= segs_n;
-		--pkts_n;
-		/*
-		 * Compute max_wqe in case less WQE were consumed in previous
-		 * iteration.
-		 */
-		max_wqe = (1u << txq->wqe_n) - (txq->wqe_ci - txq->wqe_pi);
-		cs_flags = txq_ol_cksum_to_cs(buf);
-		/* Copy metadata from mbuf if valid */
-		metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
-							     0;
-		/* Retrieve packet information. */
-		length = PKT_LEN(buf);
-		/* Start new session if packet differs. */
-		if (mpw.state == MLX5_MPW_STATE_OPENED) {
-			if ((mpw.len != length) ||
-			    (segs_n != 1) ||
-			    (mpw.wqe->eseg.flow_table_metadata != metadata) ||
-			    (mpw.wqe->eseg.cs_flags != cs_flags))
-				mlx5_mpw_close(txq, &mpw);
-		} else if (mpw.state == MLX5_MPW_INL_STATE_OPENED) {
-			if ((mpw.len != length) ||
-			    (segs_n != 1) ||
-			    (length > inline_room) ||
-			    (mpw.wqe->eseg.flow_table_metadata != metadata) ||
-			    (mpw.wqe->eseg.cs_flags != cs_flags)) {
-				mlx5_mpw_inline_close(txq, &mpw);
-				inline_room =
-					txq->max_inline * RTE_CACHE_LINE_SIZE;
-			}
-		}
-		if (mpw.state == MLX5_MPW_STATE_CLOSED) {
-			if ((segs_n != 1) ||
-			    (length > inline_room)) {
-				/*
-				 * Multi-Packet WQE consumes at most two WQE.
-				 * mlx5_mpw_new() expects to be able to use
-				 * such resources.
-				 */
-				if (unlikely(max_wqe < 2))
-					break;
-				max_wqe -= 2;
-				mlx5_mpw_new(txq, &mpw, length);
-				mpw.wqe->eseg.cs_flags = cs_flags;
-				mpw.wqe->eseg.flow_table_metadata = metadata;
-			} else {
-				if (unlikely(max_wqe < wqe_inl_n))
-					break;
-				max_wqe -= wqe_inl_n;
-				mlx5_mpw_inline_new(txq, &mpw, length);
-				mpw.wqe->eseg.cs_flags = cs_flags;
-				mpw.wqe->eseg.flow_table_metadata = metadata;
-			}
-		}
-		/* Multi-segment packets must be alone in their MPW. */
-		assert((segs_n == 1) || (mpw.pkts_n == 0));
-		if (mpw.state == MLX5_MPW_STATE_OPENED) {
-			assert(inline_room ==
-			       txq->max_inline * RTE_CACHE_LINE_SIZE);
-#if defined(MLX5_PMD_SOFT_COUNTERS) || !defined(NDEBUG)
-			length = 0;
-#endif
-			do {
-				volatile struct mlx5_wqe_data_seg *dseg;
-
-				assert(buf);
-				(*txq->elts)[elts_head++ & elts_m] = buf;
-				dseg = mpw.data.dseg[mpw.pkts_n];
-				addr = rte_pktmbuf_mtod(buf, uintptr_t);
-				*dseg = (struct mlx5_wqe_data_seg){
-					.byte_count =
-					       rte_cpu_to_be_32(DATA_LEN(buf)),
-					.lkey = mlx5_tx_mb2mr(txq, buf),
-					.addr = rte_cpu_to_be_64(addr),
-				};
-#if defined(MLX5_PMD_SOFT_COUNTERS) || !defined(NDEBUG)
-				length += DATA_LEN(buf);
-#endif
-				buf = buf->next;
-				++mpw.pkts_n;
-				++j;
-			} while (--segs_n);
-			assert(length == mpw.len);
-			if (mpw.pkts_n == MLX5_MPW_DSEG_MAX)
-				mlx5_mpw_close(txq, &mpw);
-		} else {
-			unsigned int max;
-
-			assert(mpw.state == MLX5_MPW_INL_STATE_OPENED);
-			assert(length <= inline_room);
-			assert(length == DATA_LEN(buf));
-			addr = rte_pktmbuf_mtod(buf, uintptr_t);
-			(*txq->elts)[elts_head++ & elts_m] = buf;
-			/* Maximum number of bytes before wrapping. */
-			max = ((((uintptr_t)(txq->wqes)) +
-				(1 << txq->wqe_n) *
-				MLX5_WQE_SIZE) -
-			       (uintptr_t)mpw.data.raw);
-			if (length > max) {
-				rte_memcpy((void *)(uintptr_t)mpw.data.raw,
-					   (void *)addr,
-					   max);
-				mpw.data.raw = (volatile void *)txq->wqes;
-				rte_memcpy((void *)(uintptr_t)mpw.data.raw,
-					   (void *)(addr + max),
-					   length - max);
-				mpw.data.raw += length - max;
-			} else {
-				rte_memcpy((void *)(uintptr_t)mpw.data.raw,
-					   (void *)addr,
-					   length);
-
-				if (length == max)
-					mpw.data.raw =
-						(volatile void *)txq->wqes;
-				else
-					mpw.data.raw += length;
-			}
-			++mpw.pkts_n;
-			mpw.total_len += length;
-			++j;
-			if (mpw.pkts_n == MLX5_MPW_DSEG_MAX) {
-				mlx5_mpw_inline_close(txq, &mpw);
-				inline_room =
-					txq->max_inline * RTE_CACHE_LINE_SIZE;
-			} else {
-				inline_room -= length;
-			}
-		}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		/* Increment sent bytes counter. */
-		txq->stats.obytes += length;
-#endif
-		++i;
-	} while (pkts_n);
-	/* Take a shortcut if nothing must be sent. */
-	if (unlikely(i == 0))
-		return 0;
-	/* Check whether completion threshold has been reached. */
-	/* "j" includes both packets and segments. */
-	comp = txq->elts_comp + j;
-	if (comp >= MLX5_TX_COMP_THRESH) {
-		volatile struct mlx5_wqe *wqe = mpw.wqe;
-
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		/* Request completion on last WQE. */
-		wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ALWAYS <<
-						MLX5_COMP_MODE_OFFSET);
-		/* Save elts_head in unused "immediate" field of WQE. */
-		wqe->ctrl[3] = elts_head;
-		txq->elts_comp = 0;
-	} else {
-		txq->elts_comp = comp;
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	/* Increment sent packets counter. */
-	txq->stats.opackets += i;
-#endif
-	/* Ring QP doorbell. */
-	if (mpw.state == MLX5_MPW_INL_STATE_OPENED)
-		mlx5_mpw_inline_close(txq, &mpw);
-	else if (mpw.state == MLX5_MPW_STATE_OPENED)
-		mlx5_mpw_close(txq, &mpw);
-	mlx5_tx_dbrec(txq, mpw.wqe);
-	txq->elts_head = elts_head;
-	return i;
-}
-
-/**
- * Open an Enhanced MPW session.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param mpw
- *   Pointer to MPW session structure.
- * @param length
- *   Packet length.
- */
-static inline void
-mlx5_empw_new(struct mlx5_txq_data *txq, struct mlx5_mpw *mpw, int padding)
-{
-	uint16_t idx = txq->wqe_ci & ((1 << txq->wqe_n) - 1);
-
-	mpw->state = MLX5_MPW_ENHANCED_STATE_OPENED;
-	mpw->pkts_n = 0;
-	mpw->total_len = sizeof(struct mlx5_wqe);
-	mpw->wqe = (volatile struct mlx5_wqe *)tx_mlx5_wqe(txq, idx);
-	mpw->wqe->ctrl[0] =
-		rte_cpu_to_be_32((MLX5_OPC_MOD_ENHANCED_MPSW << 24) |
-				 (txq->wqe_ci << 8) |
-				 MLX5_OPCODE_ENHANCED_MPSW);
-	mpw->wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ONLY_FIRST_ERR <<
-					     MLX5_COMP_MODE_OFFSET);
-	mpw->wqe->ctrl[3] = 0;
-	memset((void *)(uintptr_t)&mpw->wqe->eseg, 0, MLX5_WQE_DWORD_SIZE);
-	if (unlikely(padding)) {
-		uintptr_t addr = (uintptr_t)(mpw->wqe + 1);
-
-		/* Pad the first 2 DWORDs with zero-length inline header. */
-		*(volatile uint32_t *)addr = rte_cpu_to_be_32(MLX5_INLINE_SEG);
-		*(volatile uint32_t *)(addr + MLX5_WQE_DWORD_SIZE) =
-			rte_cpu_to_be_32(MLX5_INLINE_SEG);
-		mpw->total_len += 2 * MLX5_WQE_DWORD_SIZE;
-		/* Start from the next WQEBB. */
-		mpw->data.raw = (volatile void *)(tx_mlx5_wqe(txq, idx + 1));
-	} else {
-		mpw->data.raw = (volatile void *)(mpw->wqe + 1);
-	}
-}
-
-/**
- * Close an Enhanced MPW session.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param mpw
- *   Pointer to MPW session structure.
- *
- * @return
- *   Number of consumed WQEs.
- */
-static inline uint16_t
-mlx5_empw_close(struct mlx5_txq_data *txq, struct mlx5_mpw *mpw)
-{
-	uint16_t ret;
-
-	/* Store size in multiple of 16 bytes. Control and Ethernet segments
-	 * count as 2.
-	 */
-	mpw->wqe->ctrl[1] = rte_cpu_to_be_32(txq->qp_num_8s |
-					     MLX5_WQE_DS(mpw->total_len));
-	mpw->state = MLX5_MPW_STATE_CLOSED;
-	ret = (mpw->total_len + (MLX5_WQE_SIZE - 1)) / MLX5_WQE_SIZE;
-	txq->wqe_ci += ret;
-	return ret;
-}
-
-/**
- * TX with Enhanced MPW support.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param[in] pkts
- *   Packets to transmit.
- * @param pkts_n
- *   Number of packets in array.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-static inline uint16_t
-txq_burst_empw(struct mlx5_txq_data *txq, struct rte_mbuf **pkts,
-	       uint16_t pkts_n)
-{
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	unsigned int i = 0;
-	unsigned int j = 0;
-	uint16_t max_elts;
-	uint16_t max_wqe;
-	unsigned int max_inline = txq->max_inline * RTE_CACHE_LINE_SIZE;
-	unsigned int mpw_room = 0;
-	unsigned int inl_pad = 0;
-	uint32_t inl_hdr;
-	uint64_t addr_64;
-	struct mlx5_mpw mpw = {
-		.state = MLX5_MPW_STATE_CLOSED,
-	};
-
-	if (unlikely(!pkts_n))
-		return 0;
-	/* Start processing. */
-	mlx5_tx_complete(txq);
-	max_elts = (elts_n - (elts_head - txq->elts_tail));
-	max_wqe = (1u << txq->wqe_n) - (txq->wqe_ci - txq->wqe_pi);
-	if (unlikely(!max_wqe))
-		return 0;
-	do {
-		struct rte_mbuf *buf = *(pkts++);
-		uintptr_t addr;
-		unsigned int do_inline = 0; /* Whether inline is possible. */
-		uint32_t length;
-		uint8_t cs_flags;
-		rte_be32_t metadata;
-
-		/* Multi-segmented packet is handled in slow-path outside. */
-		assert(NB_SEGS(buf) == 1);
-		/* Make sure there is enough room to store this packet. */
-		if (max_elts - j == 0)
-			break;
-		cs_flags = txq_ol_cksum_to_cs(buf);
-		/* Copy metadata from mbuf if valid */
-		metadata = buf->ol_flags & PKT_TX_METADATA ? buf->tx_metadata :
-							     0;
-		/* Retrieve packet information. */
-		length = PKT_LEN(buf);
-		/* Start new session if:
-		 * - multi-segment packet
-		 * - no space left even for a dseg
-		 * - next packet can be inlined with a new WQE
-		 * - cs_flag differs
-		 */
-		if (mpw.state == MLX5_MPW_ENHANCED_STATE_OPENED) {
-			if ((inl_pad + sizeof(struct mlx5_wqe_data_seg) >
-			     mpw_room) ||
-			    (length <= txq->inline_max_packet_sz &&
-			     inl_pad + sizeof(inl_hdr) + length >
-			     mpw_room) ||
-			     (mpw.wqe->eseg.flow_table_metadata != metadata) ||
-			    (mpw.wqe->eseg.cs_flags != cs_flags))
-				max_wqe -= mlx5_empw_close(txq, &mpw);
-		}
-		if (unlikely(mpw.state == MLX5_MPW_STATE_CLOSED)) {
-			/* In Enhanced MPW, inline as much as the budget is
-			 * allowed. The remaining space is to be filled with
-			 * dsegs. If the title WQEBB isn't padded, it will have
-			 * 2 dsegs there.
-			 */
-			mpw_room = RTE_MIN(MLX5_WQE_SIZE_MAX,
-					   (max_inline ? max_inline :
-					    pkts_n * MLX5_WQE_DWORD_SIZE) +
-					   MLX5_WQE_SIZE);
-			if (unlikely(max_wqe * MLX5_WQE_SIZE < mpw_room))
-				break;
-			/* Don't pad the title WQEBB to not waste WQ. */
-			mlx5_empw_new(txq, &mpw, 0);
-			mpw_room -= mpw.total_len;
-			inl_pad = 0;
-			do_inline = length <= txq->inline_max_packet_sz &&
-				    sizeof(inl_hdr) + length <= mpw_room &&
-				    !txq->mpw_hdr_dseg;
-			mpw.wqe->eseg.cs_flags = cs_flags;
-			mpw.wqe->eseg.flow_table_metadata = metadata;
-		} else {
-			/* Evaluate whether the next packet can be inlined.
-			 * Inlininig is possible when:
-			 * - length is less than configured value
-			 * - length fits for remaining space
-			 * - not required to fill the title WQEBB with dsegs
-			 */
-			do_inline =
-				length <= txq->inline_max_packet_sz &&
-				inl_pad + sizeof(inl_hdr) + length <=
-				 mpw_room &&
-				(!txq->mpw_hdr_dseg ||
-				 mpw.total_len >= MLX5_WQE_SIZE);
-		}
-		if (max_inline && do_inline) {
-			/* Inline packet into WQE. */
-			unsigned int max;
-
-			assert(mpw.state == MLX5_MPW_ENHANCED_STATE_OPENED);
-			assert(length == DATA_LEN(buf));
-			inl_hdr = rte_cpu_to_be_32(length | MLX5_INLINE_SEG);
-			addr = rte_pktmbuf_mtod(buf, uintptr_t);
-			mpw.data.raw = (volatile void *)
-				((uintptr_t)mpw.data.raw + inl_pad);
-			max = tx_mlx5_wq_tailroom(txq,
-					(void *)(uintptr_t)mpw.data.raw);
-			/* Copy inline header. */
-			mpw.data.raw = (volatile void *)
-				mlx5_copy_to_wq(
-					  (void *)(uintptr_t)mpw.data.raw,
-					  &inl_hdr,
-					  sizeof(inl_hdr),
-					  (void *)(uintptr_t)txq->wqes,
-					  max);
-			max = tx_mlx5_wq_tailroom(txq,
-					(void *)(uintptr_t)mpw.data.raw);
-			/* Copy packet data. */
-			mpw.data.raw = (volatile void *)
-				mlx5_copy_to_wq(
-					  (void *)(uintptr_t)mpw.data.raw,
-					  (void *)addr,
-					  length,
-					  (void *)(uintptr_t)txq->wqes,
-					  max);
-			++mpw.pkts_n;
-			mpw.total_len += (inl_pad + sizeof(inl_hdr) + length);
-			/* No need to get completion as the entire packet is
-			 * copied to WQ. Free the buf right away.
-			 */
-			rte_pktmbuf_free_seg(buf);
-			mpw_room -= (inl_pad + sizeof(inl_hdr) + length);
-			/* Add pad in the next packet if any. */
-			inl_pad = (((uintptr_t)mpw.data.raw +
-					(MLX5_WQE_DWORD_SIZE - 1)) &
-					~(MLX5_WQE_DWORD_SIZE - 1)) -
-				  (uintptr_t)mpw.data.raw;
-		} else {
-			/* No inline. Load a dseg of packet pointer. */
-			volatile rte_v128u32_t *dseg;
-
-			assert(mpw.state == MLX5_MPW_ENHANCED_STATE_OPENED);
-			assert((inl_pad + sizeof(*dseg)) <= mpw_room);
-			assert(length == DATA_LEN(buf));
-			if (!tx_mlx5_wq_tailroom(txq,
-					(void *)((uintptr_t)mpw.data.raw
-						+ inl_pad)))
-				dseg = (volatile void *)txq->wqes;
-			else
-				dseg = (volatile void *)
-					((uintptr_t)mpw.data.raw +
-					 inl_pad);
-			(*txq->elts)[elts_head++ & elts_m] = buf;
-			addr_64 = rte_cpu_to_be_64(rte_pktmbuf_mtod(buf,
-								    uintptr_t));
-			*dseg = (rte_v128u32_t) {
-				rte_cpu_to_be_32(length),
-				mlx5_tx_mb2mr(txq, buf),
-				addr_64,
-				addr_64 >> 32,
-			};
-			mpw.data.raw = (volatile void *)(dseg + 1);
-			mpw.total_len += (inl_pad + sizeof(*dseg));
-			++j;
-			++mpw.pkts_n;
-			mpw_room -= (inl_pad + sizeof(*dseg));
-			inl_pad = 0;
-		}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		/* Increment sent bytes counter. */
-		txq->stats.obytes += length;
-#endif
-		++i;
-	} while (i < pkts_n);
-	/* Take a shortcut if nothing must be sent. */
-	if (unlikely(i == 0))
-		return 0;
-	/* Check whether completion threshold has been reached. */
-	if (txq->elts_comp + j >= MLX5_TX_COMP_THRESH ||
-			(uint16_t)(txq->wqe_ci - txq->mpw_comp) >=
-			 (1 << txq->wqe_n) / MLX5_TX_COMP_THRESH_INLINE_DIV) {
-		volatile struct mlx5_wqe *wqe = mpw.wqe;
-
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		/* Request completion on last WQE. */
-		wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ALWAYS <<
-						MLX5_COMP_MODE_OFFSET);
-		/* Save elts_head in unused "immediate" field of WQE. */
-		wqe->ctrl[3] = elts_head;
-		txq->elts_comp = 0;
-		txq->mpw_comp = txq->wqe_ci;
-	} else {
-		txq->elts_comp += j;
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	/* Increment sent packets counter. */
-	txq->stats.opackets += i;
-#endif
-	if (mpw.state == MLX5_MPW_ENHANCED_STATE_OPENED)
-		mlx5_empw_close(txq, &mpw);
-	/* Ring QP doorbell. */
-	mlx5_tx_dbrec(txq, mpw.wqe);
-	txq->elts_head = elts_head;
-	return i;
-}
-
-/**
- * DPDK callback for TX with Enhanced MPW support.
- *
- * @param dpdk_txq
- *   Generic pointer to TX queue structure.
- * @param[in] pkts
- *   Packets to transmit.
- * @param pkts_n
- *   Number of packets in array.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-uint16_t
-mlx5_tx_burst_empw(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
-	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
-	uint16_t nb_tx = 0;
-
-	while (pkts_n > nb_tx) {
-		uint16_t n;
-		uint16_t ret;
-
-		n = txq_count_contig_multi_seg(&pkts[nb_tx], pkts_n - nb_tx);
-		if (n) {
-			ret = mlx5_tx_burst(dpdk_txq, &pkts[nb_tx], n);
-			if (!ret)
-				break;
-			nb_tx += ret;
-		}
-		n = txq_count_contig_single_seg(&pkts[nb_tx], pkts_n - nb_tx);
-		if (n) {
-			ret = txq_burst_empw(txq, &pkts[nb_tx], n);
-			if (!ret)
-				break;
-			nb_tx += ret;
-		}
-	}
-	return nb_tx;
-}
-
-/**
  * Translate RX completion flags to packet type.
  *
  * @param[in] rxq
@@ -2867,22 +1492,6 @@
  */
 
 __rte_weak uint16_t
-mlx5_tx_burst_raw_vec(void *dpdk_txq __rte_unused,
-		      struct rte_mbuf **pkts __rte_unused,
-		      uint16_t pkts_n __rte_unused)
-{
-	return 0;
-}
-
-__rte_weak uint16_t
-mlx5_tx_burst_vec(void *dpdk_txq __rte_unused,
-		  struct rte_mbuf **pkts __rte_unused,
-		  uint16_t pkts_n __rte_unused)
-{
-	return 0;
-}
-
-__rte_weak uint16_t
 mlx5_rx_burst_vec(void *dpdk_txq __rte_unused,
 		  struct rte_mbuf **pkts __rte_unused,
 		  uint16_t pkts_n __rte_unused)
@@ -2891,25 +1500,50 @@
 }
 
 __rte_weak int
-mlx5_check_raw_vec_tx_support(struct rte_eth_dev *dev __rte_unused)
+mlx5_rxq_check_vec_support(struct mlx5_rxq_data *rxq __rte_unused)
 {
 	return -ENOTSUP;
 }
 
 __rte_weak int
-mlx5_check_vec_tx_support(struct rte_eth_dev *dev __rte_unused)
+mlx5_check_vec_rx_support(struct rte_eth_dev *dev __rte_unused)
 {
 	return -ENOTSUP;
 }
 
-__rte_weak int
-mlx5_rxq_check_vec_support(struct mlx5_rxq_data *rxq __rte_unused)
+/**
+ * DPDK callback to check the status of a tx descriptor.
+ *
+ * @param tx_queue
+ *   The tx queue.
+ * @param[in] offset
+ *   The index of the descriptor in the ring.
+ *
+ * @return
+ *   The status of the tx descriptor.
+ */
+int
+mlx5_tx_descriptor_status(void *tx_queue, uint16_t offset)
 {
-	return -ENOTSUP;
+	(void)tx_queue;
+	(void)offset;
+	return RTE_ETH_TX_DESC_FULL;
 }
 
-__rte_weak int
-mlx5_check_vec_rx_support(struct rte_eth_dev *dev __rte_unused)
+/**
+ * Configure the TX function to use.
+ *
+ * @param dev
+ *   Pointer to private data structure.
+ *
+ * @return
+ *   Pointer to selected Tx burst function.
+ */
+eth_tx_burst_t
+mlx5_select_tx_function(struct rte_eth_dev *dev)
 {
-	return -ENOTSUP;
+	(void)dev;
+	return removed_tx_burst;
 }
+
+
diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
index 3d79c18..acde09d 100644
--- a/drivers/net/mlx5/mlx5_rxtx.h
+++ b/drivers/net/mlx5/mlx5_rxtx.h
@@ -329,14 +329,6 @@ struct mlx5_txq_ctrl *mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx,
 void mlx5_set_ptype_table(void);
 void mlx5_set_cksum_table(void);
 void mlx5_set_swp_types_table(void);
-uint16_t mlx5_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts,
-		       uint16_t pkts_n);
-uint16_t mlx5_tx_burst_mpw(void *dpdk_txq, struct rte_mbuf **pkts,
-			   uint16_t pkts_n);
-uint16_t mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf **pkts,
-				  uint16_t pkts_n);
-uint16_t mlx5_tx_burst_empw(void *dpdk_txq, struct rte_mbuf **pkts,
-			    uint16_t pkts_n);
 __rte_noinline uint16_t mlx5_tx_error_cqe_handle(struct mlx5_txq_data *txq,
 					volatile struct mlx5_err_cqe *err_cqe);
 uint16_t mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n);
@@ -360,14 +352,8 @@ int mlx5_queue_state_modify_primary(struct rte_eth_dev *dev,
 			const struct mlx5_mp_arg_queue_state_modify *sm);
 
 /* Vectorized version of mlx5_rxtx.c */
-int mlx5_check_raw_vec_tx_support(struct rte_eth_dev *dev);
-int mlx5_check_vec_tx_support(struct rte_eth_dev *dev);
 int mlx5_rxq_check_vec_support(struct mlx5_rxq_data *rxq_data);
 int mlx5_check_vec_rx_support(struct rte_eth_dev *dev);
-uint16_t mlx5_tx_burst_raw_vec(void *dpdk_txq, struct rte_mbuf **pkts,
-			       uint16_t pkts_n);
-uint16_t mlx5_tx_burst_vec(void *dpdk_txq, struct rte_mbuf **pkts,
-			   uint16_t pkts_n);
 uint16_t mlx5_rx_burst_vec(void *dpdk_txq, struct rte_mbuf **pkts,
 			   uint16_t pkts_n);
 
@@ -478,122 +464,6 @@ enum mlx5_cqe_status {
 }
 
 /**
- * Return the address of the WQE.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param  wqe_ci
- *   WQE consumer index.
- *
- * @return
- *   WQE address.
- */
-static inline uintptr_t *
-tx_mlx5_wqe(struct mlx5_txq_data *txq, uint16_t ci)
-{
-	ci &= ((1 << txq->wqe_n) - 1);
-	return (uintptr_t *)((uintptr_t)txq->wqes + ci * MLX5_WQE_SIZE);
-}
-
-/**
- * Handle the next CQE.
- *
- * @param txq
- *   Pointer to TX queue structure.
- *
- * @return
- *   The last Tx buffer element to free.
- */
-static __rte_always_inline uint16_t
-mlx5_tx_cqe_handle(struct mlx5_txq_data *txq)
-{
-	const unsigned int cqe_n = 1 << txq->cqe_n;
-	const unsigned int cqe_cnt = cqe_n - 1;
-	uint16_t last_elts;
-	union {
-		volatile struct mlx5_cqe *cqe;
-		volatile struct mlx5_err_cqe *err_cqe;
-	} u = {
-		.cqe =  &(*txq->cqes)[txq->cq_ci & cqe_cnt],
-	};
-	int ret = check_cqe(u.cqe, cqe_n, txq->cq_ci);
-
-	if (unlikely(ret != MLX5_CQE_STATUS_SW_OWN)) {
-		if (unlikely(ret == MLX5_CQE_STATUS_ERR))
-			last_elts = mlx5_tx_error_cqe_handle(txq, u.err_cqe);
-		else
-			/* Do not release buffers. */
-			return txq->elts_tail;
-	} else {
-		uint16_t new_wqe_pi = rte_be_to_cpu_16(u.cqe->wqe_counter);
-		volatile struct mlx5_wqe_ctrl *ctrl =
-				(volatile struct mlx5_wqe_ctrl *)
-					tx_mlx5_wqe(txq, new_wqe_pi);
-
-		/* Release completion burst buffers. */
-		last_elts = ctrl->ctrl3;
-		txq->wqe_pi = new_wqe_pi;
-		txq->cq_ci++;
-	}
-	rte_compiler_barrier();
-	*txq->cq_db = rte_cpu_to_be_32(txq->cq_ci);
-	return last_elts;
-}
-
-/**
- * Manage TX completions.
- *
- * When sending a burst, mlx5_tx_burst() posts several WRs.
- *
- * @param txq
- *   Pointer to TX queue structure.
- */
-static __rte_always_inline void
-mlx5_tx_complete(struct mlx5_txq_data *txq)
-{
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	uint16_t elts_free = txq->elts_tail;
-	uint16_t elts_tail;
-	struct rte_mbuf *m, *free[elts_n];
-	struct rte_mempool *pool = NULL;
-	unsigned int blk_n = 0;
-
-	elts_tail = mlx5_tx_cqe_handle(txq);
-	assert((elts_tail & elts_m) < (1 << txq->wqe_n));
-	/* Free buffers. */
-	while (elts_free != elts_tail) {
-		m = rte_pktmbuf_prefree_seg((*txq->elts)[elts_free++ & elts_m]);
-		if (likely(m != NULL)) {
-			if (likely(m->pool == pool)) {
-				free[blk_n++] = m;
-			} else {
-				if (likely(pool != NULL))
-					rte_mempool_put_bulk(pool,
-							     (void *)free,
-							     blk_n);
-				free[0] = m;
-				pool = m->pool;
-				blk_n = 1;
-			}
-		}
-	}
-	if (blk_n)
-		rte_mempool_put_bulk(pool, (void *)free, blk_n);
-#ifndef NDEBUG
-	elts_free = txq->elts_tail;
-	/* Poisoning. */
-	while (elts_free != elts_tail) {
-		memset(&(*txq->elts)[elts_free & elts_m],
-		       0x66,
-		       sizeof((*txq->elts)[elts_free & elts_m]));
-		++elts_free;
-	}
-#endif
-	txq->elts_tail = elts_tail;
-}
-
-/**
  * Get Memory Pool (MP) from mbuf. If mbuf is indirect, the pool from which the
  * cloned mbuf is allocated is returned instead.
  *
@@ -710,147 +580,4 @@ enum mlx5_cqe_status {
 	mlx5_tx_dbrec_cond_wmb(txq, wqe, 1);
 }
 
-/**
- * Convert mbuf to Verb SWP.
- *
- * @param txq_data
- *   Pointer to the Tx queue.
- * @param buf
- *   Pointer to the mbuf.
- * @param offsets
- *   Pointer to the SWP header offsets.
- * @param swp_types
- *   Pointer to the SWP header types.
- */
-static __rte_always_inline void
-txq_mbuf_to_swp(struct mlx5_txq_data *txq, struct rte_mbuf *buf,
-		uint8_t *offsets, uint8_t *swp_types)
-{
-	const uint64_t vlan = buf->ol_flags & PKT_TX_VLAN_PKT;
-	const uint64_t tunnel = buf->ol_flags & PKT_TX_TUNNEL_MASK;
-	const uint64_t tso = buf->ol_flags & PKT_TX_TCP_SEG;
-	const uint64_t csum_flags = buf->ol_flags & PKT_TX_L4_MASK;
-	const uint64_t inner_ip =
-		buf->ol_flags & (PKT_TX_IPV4 | PKT_TX_IPV6);
-	const uint64_t ol_flags_mask = PKT_TX_L4_MASK | PKT_TX_IPV6 |
-				       PKT_TX_OUTER_IPV6;
-	uint16_t idx;
-	uint16_t off;
-
-	if (likely(!txq->swp_en || (tunnel != PKT_TX_TUNNEL_UDP &&
-				    tunnel != PKT_TX_TUNNEL_IP)))
-		return;
-	/*
-	 * The index should have:
-	 * bit[0:1] = PKT_TX_L4_MASK
-	 * bit[4] = PKT_TX_IPV6
-	 * bit[8] = PKT_TX_OUTER_IPV6
-	 * bit[9] = PKT_TX_OUTER_UDP
-	 */
-	idx = (buf->ol_flags & ol_flags_mask) >> 52;
-	if (tunnel == PKT_TX_TUNNEL_UDP)
-		idx |= 1 << 9;
-	*swp_types = mlx5_swp_types_table[idx];
-	/*
-	 * Set offsets for SW parser. Since ConnectX-5, SW parser just
-	 * complements HW parser. SW parser starts to engage only if HW parser
-	 * can't reach a header. For the older devices, HW parser will not kick
-	 * in if any of SWP offsets is set. Therefore, all of the L3 offsets
-	 * should be set regardless of HW offload.
-	 */
-	off = buf->outer_l2_len + (vlan ? sizeof(struct rte_vlan_hdr) : 0);
-	offsets[1] = off >> 1; /* Outer L3 offset. */
-	off += buf->outer_l3_len;
-	if (tunnel == PKT_TX_TUNNEL_UDP)
-		offsets[0] = off >> 1; /* Outer L4 offset. */
-	if (inner_ip) {
-		off += buf->l2_len;
-		offsets[3] = off >> 1; /* Inner L3 offset. */
-		if (csum_flags == PKT_TX_TCP_CKSUM || tso ||
-		    csum_flags == PKT_TX_UDP_CKSUM) {
-			off += buf->l3_len;
-			offsets[2] = off >> 1; /* Inner L4 offset. */
-		}
-	}
-}
-
-/**
- * Convert the Checksum offloads to Verbs.
- *
- * @param buf
- *   Pointer to the mbuf.
- *
- * @return
- *   Converted checksum flags.
- */
-static __rte_always_inline uint8_t
-txq_ol_cksum_to_cs(struct rte_mbuf *buf)
-{
-	uint32_t idx;
-	uint8_t is_tunnel = !!(buf->ol_flags & PKT_TX_TUNNEL_MASK);
-	const uint64_t ol_flags_mask = PKT_TX_TCP_SEG | PKT_TX_L4_MASK |
-				       PKT_TX_IP_CKSUM | PKT_TX_OUTER_IP_CKSUM;
-
-	/*
-	 * The index should have:
-	 * bit[0] = PKT_TX_TCP_SEG
-	 * bit[2:3] = PKT_TX_UDP_CKSUM, PKT_TX_TCP_CKSUM
-	 * bit[4] = PKT_TX_IP_CKSUM
-	 * bit[8] = PKT_TX_OUTER_IP_CKSUM
-	 * bit[9] = tunnel
-	 */
-	idx = ((buf->ol_flags & ol_flags_mask) >> 50) | (!!is_tunnel << 9);
-	return mlx5_cksum_table[idx];
-}
-
-/**
- * Count the number of contiguous single segment packets.
- *
- * @param pkts
- *   Pointer to array of packets.
- * @param pkts_n
- *   Number of packets.
- *
- * @return
- *   Number of contiguous single segment packets.
- */
-static __rte_always_inline unsigned int
-txq_count_contig_single_seg(struct rte_mbuf **pkts, uint16_t pkts_n)
-{
-	unsigned int pos;
-
-	if (!pkts_n)
-		return 0;
-	/* Count the number of contiguous single segment packets. */
-	for (pos = 0; pos < pkts_n; ++pos)
-		if (NB_SEGS(pkts[pos]) > 1)
-			break;
-	return pos;
-}
-
-/**
- * Count the number of contiguous multi-segment packets.
- *
- * @param pkts
- *   Pointer to array of packets.
- * @param pkts_n
- *   Number of packets.
- *
- * @return
- *   Number of contiguous multi-segment packets.
- */
-static __rte_always_inline unsigned int
-txq_count_contig_multi_seg(struct rte_mbuf **pkts, uint16_t pkts_n)
-{
-	unsigned int pos;
-
-	if (!pkts_n)
-		return 0;
-	/* Count the number of contiguous multi-segment packets. */
-	for (pos = 0; pos < pkts_n; ++pos)
-		if (NB_SEGS(pkts[pos]) == 1)
-			break;
-	return pos;
-}
-
 #endif /* RTE_PMD_MLX5_RXTX_H_ */
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.c b/drivers/net/mlx5/mlx5_rxtx_vec.c
index 073044f..f6ec828 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec.c
+++ b/drivers/net/mlx5/mlx5_rxtx_vec.c
@@ -40,138 +40,6 @@
 #endif
 
 /**
- * Count the number of packets having same ol_flags and same metadata (if
- * PKT_TX_METADATA is set in ol_flags), and calculate cs_flags.
- *
- * @param pkts
- *   Pointer to array of packets.
- * @param pkts_n
- *   Number of packets.
- * @param cs_flags
- *   Pointer of flags to be returned.
- * @param metadata
- *   Pointer of metadata to be returned.
- * @param txq_offloads
- *   Offloads enabled on Tx queue
- *
- * @return
- *   Number of packets having same ol_flags and metadata, if relevant.
- */
-static inline unsigned int
-txq_calc_offload(struct rte_mbuf **pkts, uint16_t pkts_n, uint8_t *cs_flags,
-		 rte_be32_t *metadata, const uint64_t txq_offloads)
-{
-	unsigned int pos;
-	const uint64_t cksum_ol_mask =
-		PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM |
-		PKT_TX_UDP_CKSUM | PKT_TX_TUNNEL_GRE |
-		PKT_TX_TUNNEL_VXLAN | PKT_TX_OUTER_IP_CKSUM;
-	rte_be32_t p0_metadata, pn_metadata;
-
-	if (!pkts_n)
-		return 0;
-	p0_metadata = pkts[0]->ol_flags & PKT_TX_METADATA ?
-			pkts[0]->tx_metadata : 0;
-	/* Count the number of packets having same offload parameters. */
-	for (pos = 1; pos < pkts_n; ++pos) {
-		/* Check if packet has same checksum flags. */
-		if ((txq_offloads & MLX5_VEC_TX_CKSUM_OFFLOAD_CAP) &&
-		    ((pkts[pos]->ol_flags ^ pkts[0]->ol_flags) & cksum_ol_mask))
-			break;
-		/* Check if packet has same metadata. */
-		if (txq_offloads & DEV_TX_OFFLOAD_MATCH_METADATA) {
-			pn_metadata = pkts[pos]->ol_flags & PKT_TX_METADATA ?
-					pkts[pos]->tx_metadata : 0;
-			if (pn_metadata != p0_metadata)
-				break;
-		}
-	}
-	*cs_flags = txq_ol_cksum_to_cs(pkts[0]);
-	*metadata = p0_metadata;
-	return pos;
-}
-
-/**
- * DPDK callback for vectorized TX.
- *
- * @param dpdk_txq
- *   Generic pointer to TX queue structure.
- * @param[in] pkts
- *   Packets to transmit.
- * @param pkts_n
- *   Number of packets in array.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-uint16_t
-mlx5_tx_burst_raw_vec(void *dpdk_txq, struct rte_mbuf **pkts,
-		      uint16_t pkts_n)
-{
-	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
-	uint16_t nb_tx = 0;
-
-	while (pkts_n > nb_tx) {
-		uint16_t n;
-		uint16_t ret;
-
-		n = RTE_MIN((uint16_t)(pkts_n - nb_tx), MLX5_VPMD_TX_MAX_BURST);
-		ret = txq_burst_v(txq, &pkts[nb_tx], n, 0, 0);
-		nb_tx += ret;
-		if (!ret)
-			break;
-	}
-	return nb_tx;
-}
-
-/**
- * DPDK callback for vectorized TX with multi-seg packets and offload.
- *
- * @param dpdk_txq
- *   Generic pointer to TX queue structure.
- * @param[in] pkts
- *   Packets to transmit.
- * @param pkts_n
- *   Number of packets in array.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-uint16_t
-mlx5_tx_burst_vec(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
-	struct mlx5_txq_data *txq = (struct mlx5_txq_data *)dpdk_txq;
-	uint16_t nb_tx = 0;
-
-	while (pkts_n > nb_tx) {
-		uint8_t cs_flags = 0;
-		uint16_t n;
-		uint16_t ret;
-		rte_be32_t metadata = 0;
-
-		/* Transmit multi-seg packets in the head of pkts list. */
-		if ((txq->offloads & DEV_TX_OFFLOAD_MULTI_SEGS) &&
-		    NB_SEGS(pkts[nb_tx]) > 1)
-			nb_tx += txq_scatter_v(txq,
-					       &pkts[nb_tx],
-					       pkts_n - nb_tx);
-		n = RTE_MIN((uint16_t)(pkts_n - nb_tx), MLX5_VPMD_TX_MAX_BURST);
-		if (txq->offloads & DEV_TX_OFFLOAD_MULTI_SEGS)
-			n = txq_count_contig_single_seg(&pkts[nb_tx], n);
-		if (txq->offloads & (MLX5_VEC_TX_CKSUM_OFFLOAD_CAP |
-				     DEV_TX_OFFLOAD_MATCH_METADATA))
-			n = txq_calc_offload(&pkts[nb_tx], n,
-					     &cs_flags, &metadata,
-					     txq->offloads);
-		ret = txq_burst_v(txq, &pkts[nb_tx], n, cs_flags, metadata);
-		nb_tx += ret;
-		if (!ret)
-			break;
-	}
-	return nb_tx;
-}
-
-/**
  * Skip error packets.
  *
  * @param rxq
@@ -243,49 +111,6 @@
 }
 
 /**
- * Check Tx queue flags are set for raw vectorized Tx.
- *
- * @param dev
- *   Pointer to Ethernet device.
- *
- * @return
- *   1 if supported, negative errno value if not.
- */
-int __attribute__((cold))
-mlx5_check_raw_vec_tx_support(struct rte_eth_dev *dev)
-{
-	uint64_t offloads = dev->data->dev_conf.txmode.offloads;
-
-	/* Doesn't support any offload. */
-	if (offloads)
-		return -ENOTSUP;
-	return 1;
-}
-
-/**
- * Check a device can support vectorized TX.
- *
- * @param dev
- *   Pointer to Ethernet device.
- *
- * @return
- *   1 if supported, negative errno value if not.
- */
-int __attribute__((cold))
-mlx5_check_vec_tx_support(struct rte_eth_dev *dev)
-{
-	struct mlx5_priv *priv = dev->data->dev_private;
-	uint64_t offloads = dev->data->dev_conf.txmode.offloads;
-
-	if (!priv->config.tx_vec_en ||
-	    priv->txqs_n > (unsigned int)priv->config.txqs_vec ||
-	    priv->config.mps != MLX5_MPW_ENHANCED ||
-	    offloads & ~MLX5_VEC_TX_OFFLOAD_CAP)
-		return -ENOTSUP;
-	return 1;
-}
-
-/**
  * Check a RX queue can support vectorized RX.
  *
  * @param rxq
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
index 1c7e3b4..9930286 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
@@ -27,295 +27,6 @@
 #pragma GCC diagnostic ignored "-Wcast-qual"
 
 /**
- * Fill in buffer descriptors in a multi-packet send descriptor.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param dseg
- *   Pointer to buffer descriptor to be written.
- * @param pkts
- *   Pointer to array of packets to be sent.
- * @param n
- *   Number of packets to be filled.
- */
-static inline void
-txq_wr_dseg_v(struct mlx5_txq_data *txq, uint8_t *dseg,
-	      struct rte_mbuf **pkts, unsigned int n)
-{
-	unsigned int pos;
-	uintptr_t addr;
-	const uint8x16_t dseg_shuf_m = {
-		 3,  2,  1,  0, /* length, bswap32 */
-		 4,  5,  6,  7, /* lkey */
-		15, 14, 13, 12, /* addr, bswap64 */
-		11, 10,  9,  8
-	};
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	uint32_t tx_byte = 0;
-#endif
-
-	for (pos = 0; pos < n; ++pos, dseg += MLX5_WQE_DWORD_SIZE) {
-		uint8x16_t desc;
-		struct rte_mbuf *pkt = pkts[pos];
-
-		addr = rte_pktmbuf_mtod(pkt, uintptr_t);
-		desc = vreinterpretq_u8_u32((uint32x4_t) {
-				DATA_LEN(pkt),
-				mlx5_tx_mb2mr(txq, pkt),
-				addr,
-				addr >> 32 });
-		desc = vqtbl1q_u8(desc, dseg_shuf_m);
-		vst1q_u8(dseg, desc);
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		tx_byte += DATA_LEN(pkt);
-#endif
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	txq->stats.obytes += tx_byte;
-#endif
-}
-
-/**
- * Send multi-segmented packets until it encounters a single segment packet in
- * the pkts list.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param pkts
- *   Pointer to array of packets to be sent.
- * @param pkts_n
- *   Number of packets to be sent.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-static uint16_t
-txq_scatter_v(struct mlx5_txq_data *txq, struct rte_mbuf **pkts,
-	      uint16_t pkts_n)
-{
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	const uint16_t wq_n = 1 << txq->wqe_n;
-	const uint16_t wq_mask = wq_n - 1;
-	const unsigned int nb_dword_per_wqebb =
-		MLX5_WQE_SIZE / MLX5_WQE_DWORD_SIZE;
-	const unsigned int nb_dword_in_hdr =
-		sizeof(struct mlx5_wqe) / MLX5_WQE_DWORD_SIZE;
-	unsigned int n;
-	volatile struct mlx5_wqe *wqe = NULL;
-	bool metadata_ol =
-		txq->offloads & DEV_TX_OFFLOAD_MATCH_METADATA ? true : false;
-
-	assert(elts_n > pkts_n);
-	mlx5_tx_complete(txq);
-	if (unlikely(!pkts_n))
-		return 0;
-	for (n = 0; n < pkts_n; ++n) {
-		struct rte_mbuf *buf = pkts[n];
-		unsigned int segs_n = buf->nb_segs;
-		unsigned int ds = nb_dword_in_hdr;
-		unsigned int len = PKT_LEN(buf);
-		uint16_t wqe_ci = txq->wqe_ci;
-		const uint8x16_t ctrl_shuf_m = {
-			3,  2,  1,  0, /* bswap32 */
-			7,  6,  5,  4, /* bswap32 */
-			11, 10,  9,  8, /* bswap32 */
-			12, 13, 14, 15
-		};
-		uint8_t cs_flags;
-		uint16_t max_elts;
-		uint16_t max_wqe;
-		uint8x16_t *t_wqe;
-		uint8_t *dseg;
-		uint8x16_t ctrl;
-		rte_be32_t metadata =
-			metadata_ol && (buf->ol_flags & PKT_TX_METADATA) ?
-			buf->tx_metadata : 0;
-
-		assert(segs_n);
-		max_elts = elts_n - (elts_head - txq->elts_tail);
-		max_wqe = wq_n - (txq->wqe_ci - txq->wqe_pi);
-		/*
-		 * A MPW session consumes 2 WQEs at most to
-		 * include MLX5_MPW_DSEG_MAX pointers.
-		 */
-		if (segs_n == 1 ||
-		    max_elts < segs_n || max_wqe < 2)
-			break;
-		wqe = &((volatile struct mlx5_wqe64 *)
-			 txq->wqes)[wqe_ci & wq_mask].hdr;
-		cs_flags = txq_ol_cksum_to_cs(buf);
-		/* Title WQEBB pointer. */
-		t_wqe = (uint8x16_t *)wqe;
-		dseg = (uint8_t *)(wqe + 1);
-		do {
-			if (!(ds++ % nb_dword_per_wqebb)) {
-				dseg = (uint8_t *)
-					&((volatile struct mlx5_wqe64 *)
-					   txq->wqes)[++wqe_ci & wq_mask];
-			}
-			txq_wr_dseg_v(txq, dseg, &buf, 1);
-			dseg += MLX5_WQE_DWORD_SIZE;
-			(*txq->elts)[elts_head++ & elts_m] = buf;
-			buf = buf->next;
-		} while (--segs_n);
-		++wqe_ci;
-		/* Fill CTRL in the header. */
-		ctrl = vreinterpretq_u8_u32((uint32x4_t) {
-				MLX5_OPC_MOD_MPW << 24 |
-				txq->wqe_ci << 8 | MLX5_OPCODE_TSO,
-				txq->qp_num_8s | ds, 4, 0});
-		ctrl = vqtbl1q_u8(ctrl, ctrl_shuf_m);
-		vst1q_u8((void *)t_wqe, ctrl);
-		/* Fill ESEG in the header. */
-		vst1q_u32((void *)(t_wqe + 1),
-			  ((uint32x4_t){ 0,
-					 rte_cpu_to_be_16(len) << 16 | cs_flags,
-					 metadata, 0 }));
-		txq->wqe_ci = wqe_ci;
-	}
-	if (!n)
-		return 0;
-	txq->elts_comp += (uint16_t)(elts_head - txq->elts_head);
-	txq->elts_head = elts_head;
-	if (txq->elts_comp >= MLX5_TX_COMP_THRESH) {
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ALWAYS <<
-						MLX5_COMP_MODE_OFFSET);
-		wqe->ctrl[3] = txq->elts_head;
-		txq->elts_comp = 0;
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	txq->stats.opackets += n;
-#endif
-	mlx5_tx_dbrec(txq, wqe);
-	return n;
-}
-
-/**
- * Send burst of packets with Enhanced MPW. If it encounters a multi-seg packet,
- * it returns to make it processed by txq_scatter_v(). All the packets in
- * the pkts list should be single segment packets having same offload flags.
- * This must be checked by txq_count_contig_single_seg() and txq_calc_offload().
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param pkts
- *   Pointer to array of packets to be sent.
- * @param pkts_n
- *   Number of packets to be sent (<= MLX5_VPMD_TX_MAX_BURST).
- * @param cs_flags
- *   Checksum offload flags to be written in the descriptor.
- * @param metadata
- *   Metadata value to be written in the descriptor.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-static inline uint16_t
-txq_burst_v(struct mlx5_txq_data *txq, struct rte_mbuf **pkts, uint16_t pkts_n,
-	    uint8_t cs_flags, rte_be32_t metadata)
-{
-	struct rte_mbuf **elts;
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	const unsigned int nb_dword_per_wqebb =
-		MLX5_WQE_SIZE / MLX5_WQE_DWORD_SIZE;
-	const unsigned int nb_dword_in_hdr =
-		sizeof(struct mlx5_wqe) / MLX5_WQE_DWORD_SIZE;
-	unsigned int n = 0;
-	unsigned int pos;
-	uint16_t max_elts;
-	uint16_t max_wqe;
-	uint32_t comp_req;
-	const uint16_t wq_n = 1 << txq->wqe_n;
-	const uint16_t wq_mask = wq_n - 1;
-	uint16_t wq_idx = txq->wqe_ci & wq_mask;
-	volatile struct mlx5_wqe64 *wq =
-		&((volatile struct mlx5_wqe64 *)txq->wqes)[wq_idx];
-	volatile struct mlx5_wqe *wqe = (volatile struct mlx5_wqe *)wq;
-	const uint8x16_t ctrl_shuf_m = {
-		 3,  2,  1,  0, /* bswap32 */
-		 7,  6,  5,  4, /* bswap32 */
-		11, 10,  9,  8, /* bswap32 */
-		12, 13, 14, 15
-	};
-	uint8x16_t *t_wqe;
-	uint8_t *dseg;
-	uint8x16_t ctrl;
-
-	/* Make sure all packets can fit into a single WQE. */
-	assert(elts_n > pkts_n);
-	mlx5_tx_complete(txq);
-	max_elts = (elts_n - (elts_head - txq->elts_tail));
-	max_wqe = (1u << txq->wqe_n) - (txq->wqe_ci - txq->wqe_pi);
-	pkts_n = RTE_MIN((unsigned int)RTE_MIN(pkts_n, max_wqe), max_elts);
-	if (unlikely(!pkts_n))
-		return 0;
-	elts = &(*txq->elts)[elts_head & elts_m];
-	/* Loop for available tailroom first. */
-	n = RTE_MIN(elts_n - (elts_head & elts_m), pkts_n);
-	for (pos = 0; pos < (n & -2); pos += 2)
-		vst1q_u64((void *)&elts[pos], vld1q_u64((void *)&pkts[pos]));
-	if (n & 1)
-		elts[pos] = pkts[pos];
-	/* Check if it crosses the end of the queue. */
-	if (unlikely(n < pkts_n)) {
-		elts = &(*txq->elts)[0];
-		for (pos = 0; pos < pkts_n - n; ++pos)
-			elts[pos] = pkts[n + pos];
-	}
-	txq->elts_head += pkts_n;
-	/* Save title WQEBB pointer. */
-	t_wqe = (uint8x16_t *)wqe;
-	dseg = (uint8_t *)(wqe + 1);
-	/* Calculate the number of entries to the end. */
-	n = RTE_MIN(
-		(wq_n - wq_idx) * nb_dword_per_wqebb - nb_dword_in_hdr,
-		pkts_n);
-	/* Fill DSEGs. */
-	txq_wr_dseg_v(txq, dseg, pkts, n);
-	/* Check if it crosses the end of the queue. */
-	if (n < pkts_n) {
-		dseg = (uint8_t *)txq->wqes;
-		txq_wr_dseg_v(txq, dseg, &pkts[n], pkts_n - n);
-	}
-	if (txq->elts_comp + pkts_n < MLX5_TX_COMP_THRESH) {
-		txq->elts_comp += pkts_n;
-		comp_req = MLX5_COMP_ONLY_FIRST_ERR << MLX5_COMP_MODE_OFFSET;
-	} else {
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		/* Request a completion. */
-		txq->elts_comp = 0;
-		comp_req = MLX5_COMP_ALWAYS << MLX5_COMP_MODE_OFFSET;
-	}
-	/* Fill CTRL in the header. */
-	ctrl = vreinterpretq_u8_u32((uint32x4_t) {
-			MLX5_OPC_MOD_ENHANCED_MPSW << 24 |
-			txq->wqe_ci << 8 | MLX5_OPCODE_ENHANCED_MPSW,
-			txq->qp_num_8s | (pkts_n + 2),
-			comp_req,
-			txq->elts_head });
-	ctrl = vqtbl1q_u8(ctrl, ctrl_shuf_m);
-	vst1q_u8((void *)t_wqe, ctrl);
-	/* Fill ESEG in the header. */
-	vst1q_u32((void *)(t_wqe + 1),
-		 ((uint32x4_t) { 0, cs_flags, metadata, 0 }));
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	txq->stats.opackets += pkts_n;
-#endif
-	txq->wqe_ci += (nb_dword_in_hdr + pkts_n + (nb_dword_per_wqebb - 1)) /
-		       nb_dword_per_wqebb;
-	/* Ring QP doorbell. */
-	mlx5_tx_dbrec_cond_wmb(txq, wqe, pkts_n < MLX5_VPMD_TX_MAX_BURST);
-	return pkts_n;
-}
-
-/**
  * Store free buffers to RX SW ring.
  *
  * @param rxq
diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
index 503ca0f..7bd254f 100644
--- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
+++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
@@ -29,290 +29,6 @@
 #endif
 
 /**
- * Fill in buffer descriptors in a multi-packet send descriptor.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param dseg
- *   Pointer to buffer descriptor to be written.
- * @param pkts
- *   Pointer to array of packets to be sent.
- * @param n
- *   Number of packets to be filled.
- */
-static inline void
-txq_wr_dseg_v(struct mlx5_txq_data *txq, __m128i *dseg,
-	      struct rte_mbuf **pkts, unsigned int n)
-{
-	unsigned int pos;
-	uintptr_t addr;
-	const __m128i shuf_mask_dseg =
-		_mm_set_epi8(8,  9, 10, 11, /* addr, bswap64 */
-			    12, 13, 14, 15,
-			     7,  6,  5,  4, /* lkey */
-			     0,  1,  2,  3  /* length, bswap32 */);
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	uint32_t tx_byte = 0;
-#endif
-
-	for (pos = 0; pos < n; ++pos, ++dseg) {
-		__m128i desc;
-		struct rte_mbuf *pkt = pkts[pos];
-
-		addr = rte_pktmbuf_mtod(pkt, uintptr_t);
-		desc = _mm_set_epi32(addr >> 32,
-				     addr,
-				     mlx5_tx_mb2mr(txq, pkt),
-				     DATA_LEN(pkt));
-		desc = _mm_shuffle_epi8(desc, shuf_mask_dseg);
-		_mm_store_si128(dseg, desc);
-#ifdef MLX5_PMD_SOFT_COUNTERS
-		tx_byte += DATA_LEN(pkt);
-#endif
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	txq->stats.obytes += tx_byte;
-#endif
-}
-
-/**
- * Send multi-segmented packets until it encounters a single segment packet in
- * the pkts list.
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param pkts
- *   Pointer to array of packets to be sent.
- * @param pkts_n
- *   Number of packets to be sent.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-static uint16_t
-txq_scatter_v(struct mlx5_txq_data *txq, struct rte_mbuf **pkts,
-	      uint16_t pkts_n)
-{
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	const uint16_t wq_n = 1 << txq->wqe_n;
-	const uint16_t wq_mask = wq_n - 1;
-	const unsigned int nb_dword_per_wqebb =
-		MLX5_WQE_SIZE / MLX5_WQE_DWORD_SIZE;
-	const unsigned int nb_dword_in_hdr =
-		sizeof(struct mlx5_wqe) / MLX5_WQE_DWORD_SIZE;
-	unsigned int n;
-	volatile struct mlx5_wqe *wqe = NULL;
-	bool metadata_ol =
-		txq->offloads & DEV_TX_OFFLOAD_MATCH_METADATA ? true : false;
-
-	assert(elts_n > pkts_n);
-	mlx5_tx_complete(txq);
-	if (unlikely(!pkts_n))
-		return 0;
-	for (n = 0; n < pkts_n; ++n) {
-		struct rte_mbuf *buf = pkts[n];
-		unsigned int segs_n = buf->nb_segs;
-		unsigned int ds = nb_dword_in_hdr;
-		unsigned int len = PKT_LEN(buf);
-		uint16_t wqe_ci = txq->wqe_ci;
-		const __m128i shuf_mask_ctrl =
-			_mm_set_epi8(15, 14, 13, 12,
-				      8,  9, 10, 11, /* bswap32 */
-				      4,  5,  6,  7, /* bswap32 */
-				      0,  1,  2,  3  /* bswap32 */);
-		uint8_t cs_flags;
-		uint16_t max_elts;
-		uint16_t max_wqe;
-		__m128i *t_wqe, *dseg;
-		__m128i ctrl;
-		rte_be32_t metadata =
-			metadata_ol && (buf->ol_flags & PKT_TX_METADATA) ?
-			buf->tx_metadata : 0;
-
-		assert(segs_n);
-		max_elts = elts_n - (elts_head - txq->elts_tail);
-		max_wqe = wq_n - (txq->wqe_ci - txq->wqe_pi);
-		/*
-		 * A MPW session consumes 2 WQEs at most to
-		 * include MLX5_MPW_DSEG_MAX pointers.
-		 */
-		if (segs_n == 1 ||
-		    max_elts < segs_n || max_wqe < 2)
-			break;
-		if (segs_n > MLX5_MPW_DSEG_MAX) {
-			txq->stats.oerrors++;
-			break;
-		}
-		wqe = &((volatile struct mlx5_wqe64 *)
-			 txq->wqes)[wqe_ci & wq_mask].hdr;
-		cs_flags = txq_ol_cksum_to_cs(buf);
-		/* Title WQEBB pointer. */
-		t_wqe = (__m128i *)wqe;
-		dseg = (__m128i *)(wqe + 1);
-		do {
-			if (!(ds++ % nb_dword_per_wqebb)) {
-				dseg = (__m128i *)
-					&((volatile struct mlx5_wqe64 *)
-					   txq->wqes)[++wqe_ci & wq_mask];
-			}
-			txq_wr_dseg_v(txq, dseg++, &buf, 1);
-			(*txq->elts)[elts_head++ & elts_m] = buf;
-			buf = buf->next;
-		} while (--segs_n);
-		++wqe_ci;
-		/* Fill CTRL in the header. */
-		ctrl = _mm_set_epi32(0, 4, txq->qp_num_8s | ds,
-				     MLX5_OPC_MOD_MPW << 24 |
-				     txq->wqe_ci << 8 | MLX5_OPCODE_TSO);
-		ctrl = _mm_shuffle_epi8(ctrl, shuf_mask_ctrl);
-		_mm_store_si128(t_wqe, ctrl);
-		/* Fill ESEG in the header. */
-		_mm_store_si128(t_wqe + 1,
-				_mm_set_epi32(0, metadata,
-					      (rte_cpu_to_be_16(len) << 16) |
-					      cs_flags, 0));
-		txq->wqe_ci = wqe_ci;
-	}
-	if (!n)
-		return 0;
-	txq->elts_comp += (uint16_t)(elts_head - txq->elts_head);
-	txq->elts_head = elts_head;
-	if (txq->elts_comp >= MLX5_TX_COMP_THRESH) {
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		wqe->ctrl[2] = rte_cpu_to_be_32(MLX5_COMP_ALWAYS <<
-						MLX5_COMP_MODE_OFFSET);
-		wqe->ctrl[3] = txq->elts_head;
-		txq->elts_comp = 0;
-	}
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	txq->stats.opackets += n;
-#endif
-	mlx5_tx_dbrec(txq, wqe);
-	return n;
-}
-
-/**
- * Send burst of packets with Enhanced MPW. If it encounters a multi-seg packet,
- * it returns to make it processed by txq_scatter_v(). All the packets in
- * the pkts list should be single segment packets having same offload flags.
- * This must be checked by txq_count_contig_single_seg() and txq_calc_offload().
- *
- * @param txq
- *   Pointer to TX queue structure.
- * @param pkts
- *   Pointer to array of packets to be sent.
- * @param pkts_n
- *   Number of packets to be sent (<= MLX5_VPMD_TX_MAX_BURST).
- * @param cs_flags
- *   Checksum offload flags to be written in the descriptor.
- * @param metadata
- *   Metadata value to be written in the descriptor.
- *
- * @return
- *   Number of packets successfully transmitted (<= pkts_n).
- */
-static inline uint16_t
-txq_burst_v(struct mlx5_txq_data *txq, struct rte_mbuf **pkts, uint16_t pkts_n,
-	    uint8_t cs_flags, rte_be32_t metadata)
-{
-	struct rte_mbuf **elts;
-	uint16_t elts_head = txq->elts_head;
-	const uint16_t elts_n = 1 << txq->elts_n;
-	const uint16_t elts_m = elts_n - 1;
-	const unsigned int nb_dword_per_wqebb =
-		MLX5_WQE_SIZE / MLX5_WQE_DWORD_SIZE;
-	const unsigned int nb_dword_in_hdr =
-		sizeof(struct mlx5_wqe) / MLX5_WQE_DWORD_SIZE;
-	unsigned int n = 0;
-	unsigned int pos;
-	uint16_t max_elts;
-	uint16_t max_wqe;
-	uint32_t comp_req;
-	const uint16_t wq_n = 1 << txq->wqe_n;
-	const uint16_t wq_mask = wq_n - 1;
-	uint16_t wq_idx = txq->wqe_ci & wq_mask;
-	volatile struct mlx5_wqe64 *wq =
-		&((volatile struct mlx5_wqe64 *)txq->wqes)[wq_idx];
-	volatile struct mlx5_wqe *wqe = (volatile struct mlx5_wqe *)wq;
-	const __m128i shuf_mask_ctrl =
-		_mm_set_epi8(15, 14, 13, 12,
-			      8,  9, 10, 11, /* bswap32 */
-			      4,  5,  6,  7, /* bswap32 */
-			      0,  1,  2,  3  /* bswap32 */);
-	__m128i *t_wqe, *dseg;
-	__m128i ctrl;
-
-	/* Make sure all packets can fit into a single WQE. */
-	assert(elts_n > pkts_n);
-	mlx5_tx_complete(txq);
-	max_elts = (elts_n - (elts_head - txq->elts_tail));
-	max_wqe = (1u << txq->wqe_n) - (txq->wqe_ci - txq->wqe_pi);
-	pkts_n = RTE_MIN((unsigned int)RTE_MIN(pkts_n, max_wqe), max_elts);
-	assert(pkts_n <= MLX5_DSEG_MAX - nb_dword_in_hdr);
-	if (unlikely(!pkts_n))
-		return 0;
-	elts = &(*txq->elts)[elts_head & elts_m];
-	/* Loop for available tailroom first. */
-	n = RTE_MIN(elts_n - (elts_head & elts_m), pkts_n);
-	for (pos = 0; pos < (n & -2); pos += 2)
-		_mm_storeu_si128((__m128i *)&elts[pos],
-				 _mm_loadu_si128((__m128i *)&pkts[pos]));
-	if (n & 1)
-		elts[pos] = pkts[pos];
-	/* Check if it crosses the end of the queue. */
-	if (unlikely(n < pkts_n)) {
-		elts = &(*txq->elts)[0];
-		for (pos = 0; pos < pkts_n - n; ++pos)
-			elts[pos] = pkts[n + pos];
-	}
-	txq->elts_head += pkts_n;
-	/* Save title WQEBB pointer. */
-	t_wqe = (__m128i *)wqe;
-	dseg = (__m128i *)(wqe + 1);
-	/* Calculate the number of entries to the end. */
-	n = RTE_MIN(
-		(wq_n - wq_idx) * nb_dword_per_wqebb - nb_dword_in_hdr,
-		pkts_n);
-	/* Fill DSEGs. */
-	txq_wr_dseg_v(txq, dseg, pkts, n);
-	/* Check if it crosses the end of the queue. */
-	if (n < pkts_n) {
-		dseg = (__m128i *)txq->wqes;
-		txq_wr_dseg_v(txq, dseg, &pkts[n], pkts_n - n);
-	}
-	if (txq->elts_comp + pkts_n < MLX5_TX_COMP_THRESH) {
-		txq->elts_comp += pkts_n;
-		comp_req = MLX5_COMP_ONLY_FIRST_ERR << MLX5_COMP_MODE_OFFSET;
-	} else {
-		/* A CQE slot must always be available. */
-		assert((1u << txq->cqe_n) - (txq->cq_pi++ - txq->cq_ci));
-		/* Request a completion. */
-		txq->elts_comp = 0;
-		comp_req = MLX5_COMP_ALWAYS << MLX5_COMP_MODE_OFFSET;
-	}
-	/* Fill CTRL in the header. */
-	ctrl = _mm_set_epi32(txq->elts_head, comp_req,
-			     txq->qp_num_8s | (pkts_n + 2),
-			     MLX5_OPC_MOD_ENHANCED_MPSW << 24 |
-				txq->wqe_ci << 8 | MLX5_OPCODE_ENHANCED_MPSW);
-	ctrl = _mm_shuffle_epi8(ctrl, shuf_mask_ctrl);
-	_mm_store_si128(t_wqe, ctrl);
-	/* Fill ESEG in the header. */
-	_mm_store_si128(t_wqe + 1, _mm_set_epi32(0, metadata, cs_flags, 0));
-#ifdef MLX5_PMD_SOFT_COUNTERS
-	txq->stats.opackets += pkts_n;
-#endif
-	txq->wqe_ci += (nb_dword_in_hdr + pkts_n + (nb_dword_per_wqebb - 1)) /
-		       nb_dword_per_wqebb;
-	/* Ring QP doorbell. */
-	mlx5_tx_dbrec_cond_wmb(txq, wqe, pkts_n < MLX5_VPMD_TX_MAX_BURST);
-	return pkts_n;
-}
-
-/**
  * Store free buffers to RX SW ring.
  *
  * @param rxq
diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index 7741095..0d2dbfa 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -365,25 +365,6 @@
 }
 
 /**
- * Check if the burst function is using eMPW.
- *
- * @param tx_pkt_burst
- *   Tx burst function pointer.
- *
- * @return
- *   1 if the burst function is using eMPW, 0 otherwise.
- */
-static int
-is_empw_burst_func(eth_tx_burst_t tx_pkt_burst)
-{
-	if (tx_pkt_burst == mlx5_tx_burst_raw_vec ||
-	    tx_pkt_burst == mlx5_tx_burst_vec ||
-	    tx_pkt_burst == mlx5_tx_burst_empw)
-		return 1;
-	return 0;
-}
-
-/**
  * Create the Tx queue Verbs object.
  *
  * @param dev
@@ -414,7 +395,6 @@ struct mlx5_txq_ibv *
 	struct mlx5dv_cq cq_info;
 	struct mlx5dv_obj obj;
 	const int desc = 1 << txq_data->elts_n;
-	eth_tx_burst_t tx_pkt_burst = mlx5_select_tx_function(dev);
 	int ret = 0;
 
 	assert(txq_data);
@@ -432,8 +412,6 @@ struct mlx5_txq_ibv *
 		.comp_mask = 0,
 	};
 	cqe_n = desc / MLX5_TX_COMP_THRESH + 1;
-	if (is_empw_burst_func(tx_pkt_burst))
-		cqe_n += 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",
@@ -698,93 +676,7 @@ struct mlx5_txq_ibv *
 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;
-	const unsigned int max_tso_inline =
-		((MLX5_MAX_TSO_HEADER + (RTE_CACHE_LINE_SIZE - 1)) /
-		 RTE_CACHE_LINE_SIZE);
-	unsigned int txq_inline;
-	unsigned int txqs_inline;
-	unsigned int inline_max_packet_sz;
-	eth_tx_burst_t tx_pkt_burst =
-		mlx5_select_tx_function(ETH_DEV(priv));
-	int is_empw_func = is_empw_burst_func(tx_pkt_burst);
-	int 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));
-
-	txq_inline = (config->txq_inline == MLX5_ARG_UNSET) ?
-		0 : config->txq_inline;
-	txqs_inline = (config->txqs_inline == MLX5_ARG_UNSET) ?
-		0 : config->txqs_inline;
-	inline_max_packet_sz =
-		(config->inline_max_packet_sz == MLX5_ARG_UNSET) ?
-		0 : config->inline_max_packet_sz;
-	if (is_empw_func) {
-		if (config->txq_inline == MLX5_ARG_UNSET)
-			txq_inline = MLX5_WQE_SIZE_MAX - MLX5_WQE_SIZE;
-		if (config->txqs_inline == MLX5_ARG_UNSET)
-			txqs_inline = MLX5_EMPW_MIN_TXQS;
-		if (config->inline_max_packet_sz == MLX5_ARG_UNSET)
-			inline_max_packet_sz = MLX5_EMPW_MAX_INLINE_LEN;
-		txq_ctrl->txq.mpw_hdr_dseg = config->mpw_hdr_dseg;
-		txq_ctrl->txq.inline_max_packet_sz = inline_max_packet_sz;
-	}
-	if (txq_inline && priv->txqs_n >= txqs_inline) {
-		unsigned int ds_cnt;
-
-		txq_ctrl->txq.max_inline =
-			((txq_inline + (RTE_CACHE_LINE_SIZE - 1)) /
-			 RTE_CACHE_LINE_SIZE);
-		if (is_empw_func) {
-			/* To minimize the size of data set, avoid requesting
-			 * too large WQ.
-			 */
-			txq_ctrl->max_inline_data =
-				((RTE_MIN(txq_inline,
-					  inline_max_packet_sz) +
-				  (RTE_CACHE_LINE_SIZE - 1)) /
-				 RTE_CACHE_LINE_SIZE) * RTE_CACHE_LINE_SIZE;
-		} else {
-			txq_ctrl->max_inline_data =
-				txq_ctrl->txq.max_inline * RTE_CACHE_LINE_SIZE;
-		}
-		/*
-		 * Check if the inline size is too large in a way which
-		 * can make the WQE DS to overflow.
-		 * Considering in calculation:
-		 *      WQE CTRL (1 DS)
-		 *      WQE ETH  (1 DS)
-		 *      Inline part (N DS)
-		 */
-		ds_cnt = 2 + (txq_ctrl->txq.max_inline / MLX5_WQE_DWORD_SIZE);
-		if (ds_cnt > MLX5_DSEG_MAX) {
-			unsigned int max_inline = (MLX5_DSEG_MAX - 2) *
-						  MLX5_WQE_DWORD_SIZE;
-
-			max_inline = max_inline - (max_inline %
-						   RTE_CACHE_LINE_SIZE);
-			DRV_LOG(WARNING,
-				"port %u txq inline is too large (%d) setting"
-				" it to the maximum possible: %d\n",
-				PORT_ID(priv), txq_inline, max_inline);
-			txq_ctrl->txq.max_inline = max_inline /
-						   RTE_CACHE_LINE_SIZE;
-		}
-	}
-	if (tso) {
-		txq_ctrl->max_tso_header = max_tso_inline * RTE_CACHE_LINE_SIZE;
-		txq_ctrl->txq.max_inline = RTE_MAX(txq_ctrl->txq.max_inline,
-						   max_tso_inline);
-		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;
+	(void)txq_ctrl;
 }
 
 /**
-- 
1.8.3.1



More information about the dev mailing list