* Copyright 2015-2019 Mellanox Technologies, Ltd
*/
-#include <assert.h>
#include <stdint.h>
#include <string.h>
#include <stdlib.h>
#include <rte_branch_prediction.h>
#include <rte_ether.h>
#include <rte_cycles.h>
+#include <rte_flow.h>
+#include <mlx5_devx_cmds.h>
+#include <mlx5_prm.h>
+#include <mlx5_common.h>
+
+#include "mlx5_defs.h"
#include "mlx5.h"
#include "mlx5_utils.h"
#include "mlx5_rxtx.h"
#include "mlx5_autoconf.h"
-#include "mlx5_defs.h"
-#include "mlx5_prm.h"
/* TX burst subroutines return codes. */
enum mlx5_txcmp_code {
#define MLX5_TXOFF_CONFIG_VLAN (1u << 5) /* VLAN insertion supported.*/
#define MLX5_TXOFF_CONFIG_METADATA (1u << 6) /* Flow metadata. */
#define MLX5_TXOFF_CONFIG_EMPW (1u << 8) /* Enhanced MPW supported.*/
+#define MLX5_TXOFF_CONFIG_MPW (1u << 9) /* Legacy MPW supported.*/
/* The most common offloads groups. */
#define MLX5_TXOFF_CONFIG_NONE 0
uint8_t mlx5_cksum_table[1 << 10] __rte_cache_aligned;
uint8_t mlx5_swp_types_table[1 << 10] __rte_cache_aligned;
+uint64_t rte_net_mlx5_dynf_inline_mask;
+#define PKT_TX_DYNF_NOINLINE rte_net_mlx5_dynf_inline_mask
+
/**
* Build a table to translate Rx completion flags to packet type.
*
return RTE_ETH_RX_DESC_AVAIL;
}
+/**
+ * DPDK callback to get the RX queue information
+ *
+ * @param dev
+ * Pointer to the device structure.
+ *
+ * @param rx_queue_id
+ * Rx queue identificator.
+ *
+ * @param qinfo
+ * Pointer to the RX queue information structure.
+ *
+ * @return
+ * None.
+ */
+
+void
+mlx5_rxq_info_get(struct rte_eth_dev *dev, uint16_t rx_queue_id,
+ struct rte_eth_rxq_info *qinfo)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_rxq_data *rxq = (*priv->rxqs)[rx_queue_id];
+ struct mlx5_rxq_ctrl *rxq_ctrl =
+ container_of(rxq, struct mlx5_rxq_ctrl, rxq);
+
+ if (!rxq)
+ return;
+ qinfo->mp = mlx5_rxq_mprq_enabled(&rxq_ctrl->rxq) ?
+ rxq->mprq_mp : rxq->mp;
+ qinfo->conf.rx_thresh.pthresh = 0;
+ qinfo->conf.rx_thresh.hthresh = 0;
+ qinfo->conf.rx_thresh.wthresh = 0;
+ qinfo->conf.rx_free_thresh = rxq->rq_repl_thresh;
+ qinfo->conf.rx_drop_en = 1;
+ qinfo->conf.rx_deferred_start = rxq_ctrl ? 0 : 1;
+ qinfo->conf.offloads = dev->data->dev_conf.rxmode.offloads;
+ qinfo->scattered_rx = dev->data->scattered_rx;
+ qinfo->nb_desc = 1 << rxq->elts_n;
+}
+
+/**
+ * DPDK callback to get the RX packet burst mode information
+ *
+ * @param dev
+ * Pointer to the device structure.
+ *
+ * @param rx_queue_id
+ * Rx queue identificatior.
+ *
+ * @param mode
+ * Pointer to the burts mode information.
+ *
+ * @return
+ * 0 as success, -EINVAL as failure.
+ */
+
+int
+mlx5_rx_burst_mode_get(struct rte_eth_dev *dev,
+ uint16_t rx_queue_id __rte_unused,
+ struct rte_eth_burst_mode *mode)
+{
+ eth_rx_burst_t pkt_burst = dev->rx_pkt_burst;
+
+ if (pkt_burst == mlx5_rx_burst) {
+ snprintf(mode->info, sizeof(mode->info), "%s", "Scalar");
+ } else if (pkt_burst == mlx5_rx_burst_mprq) {
+ snprintf(mode->info, sizeof(mode->info), "%s", "Multi-Packet RQ");
+ } else if (pkt_burst == mlx5_rx_burst_vec) {
+#if defined RTE_ARCH_X86_64
+ snprintf(mode->info, sizeof(mode->info), "%s", "Vector SSE");
+#elif defined RTE_ARCH_ARM64
+ snprintf(mode->info, sizeof(mode->info), "%s", "Vector Neon");
+#elif defined RTE_ARCH_PPC_64
+ snprintf(mode->info, sizeof(mode->info), "%s", "Vector AltiVec");
+#else
+ return -EINVAL;
+#endif
+ } else {
+ return -EINVAL;
+ }
+ return 0;
+}
+
/**
* DPDK callback to get the number of used descriptors in a RX queue
*
* Pointer to the error CQE.
*
* @return
- * Negative value if queue recovery failed,
- * the last Tx buffer element to free otherwise.
+ * Negative value if queue recovery failed, otherwise
+ * the error completion entry is handled successfully.
*/
-int
+static int
mlx5_tx_error_cqe_handle(struct mlx5_txq_data *restrict txq,
volatile struct mlx5_err_cqe *err_cqe)
{
*/
txq->stats.oerrors += ((txq->wqe_ci & wqe_m) -
new_wqe_pi) & wqe_m;
- if (tx_recover_qp(txq_ctrl) == 0) {
- txq->cq_ci++;
- /* Release all the remaining buffers. */
- return txq->elts_head;
+ if (tx_recover_qp(txq_ctrl)) {
+ /* Recovering failed - retry later on the same WQE. */
+ return -1;
}
- /* Recovering failed - try again later on the same WQE. */
- return -1;
- } else {
- txq->cq_ci++;
+ /* Release all the remaining buffers. */
+ txq_free_elts(txq_ctrl);
}
- /* Do not release buffers. */
- return txq->elts_tail;
+ return 0;
}
/**
byte_count = DATA_LEN(buf);
}
/* scat->addr must be able to store a pointer. */
- assert(sizeof(scat->addr) >= sizeof(uintptr_t));
+ MLX5_ASSERT(sizeof(scat->addr) >= sizeof(uintptr_t));
*scat = (struct mlx5_wqe_data_seg){
.addr = rte_cpu_to_be_64(addr),
.byte_count = rte_cpu_to_be_32(byte_count),
pkt->hash.fdir.hi = mlx5_flow_mark_get(mark);
}
}
+ if (rte_flow_dynf_metadata_avail() && cqe->flow_table_metadata) {
+ pkt->ol_flags |= PKT_RX_DYNF_METADATA;
+ *RTE_FLOW_DYNF_METADATA(pkt) = cqe->flow_table_metadata;
+ }
if (rxq->csum)
pkt->ol_flags |= rxq_cq_to_ol_flags(cqe);
if (rxq->vlan_strip &&
break;
}
while (pkt != seg) {
- assert(pkt != (*rxq->elts)[idx]);
+ MLX5_ASSERT(pkt != (*rxq->elts)[idx]);
rep = NEXT(pkt);
NEXT(pkt) = NULL;
NB_SEGS(pkt) = 1;
break;
}
pkt = seg;
- assert(len >= (rxq->crc_present << 2));
- pkt->ol_flags = 0;
+ MLX5_ASSERT(len >= (rxq->crc_present << 2));
+ pkt->ol_flags &= EXT_ATTACHED_MBUF;
/* If compressed, take hash result from mini-CQE. */
rss_hash_res = rte_be_to_cpu_32(mcqe == NULL ?
cqe->rx_hash_res :
&((volatile struct mlx5_wqe_mprq *)rxq->wqes)[rq_idx].dseg;
void *addr;
- assert(rep != NULL);
+ MLX5_ASSERT(rep != NULL);
/* Replace MPRQ buf. */
(*rxq->mprq_bufs)[rq_idx] = rep;
/* Replace WQE. */
byte_cnt = ret;
strd_cnt = (byte_cnt & MLX5_MPRQ_STRIDE_NUM_MASK) >>
MLX5_MPRQ_STRIDE_NUM_SHIFT;
- assert(strd_cnt);
+ MLX5_ASSERT(strd_cnt);
consumed_strd += strd_cnt;
if (byte_cnt & MLX5_MPRQ_FILLER_MASK)
continue;
/* mini-CQE for MPRQ doesn't have hash result. */
strd_idx = rte_be_to_cpu_16(mcqe->stride_idx);
}
- assert(strd_idx < strd_n);
- assert(!((rte_be_to_cpu_16(cqe->wqe_id) ^ rq_ci) & wq_mask));
+ MLX5_ASSERT(strd_idx < strd_n);
+ MLX5_ASSERT(!((rte_be_to_cpu_16(cqe->wqe_id) ^ rq_ci) &
+ wq_mask));
lro_num_seg = cqe->lro_num_seg;
/*
* Currently configured to receive a packet per a stride. But if
break;
}
len = (byte_cnt & MLX5_MPRQ_LEN_MASK) >> MLX5_MPRQ_LEN_SHIFT;
- assert((int)len >= (rxq->crc_present << 2));
+ MLX5_ASSERT((int)len >= (rxq->crc_present << 2));
if (rxq->crc_present)
len -= RTE_ETHER_CRC_LEN;
offset = strd_idx * strd_sz + strd_shift;
/* Increment the refcnt of the whole chunk. */
rte_atomic16_add_return(&buf->refcnt, 1);
- assert((uint16_t)rte_atomic16_read(&buf->refcnt) <=
- strd_n + 1);
+ MLX5_ASSERT((uint16_t)rte_atomic16_read(&buf->refcnt) <=
+ strd_n + 1);
buf_addr = RTE_PTR_SUB(addr, headroom_sz);
/*
* MLX5 device doesn't use iova but it is necessary in a
buf_len, shinfo);
/* Set mbuf head-room. */
pkt->data_off = headroom_sz;
- assert(pkt->ol_flags == EXT_ATTACHED_MBUF);
+ MLX5_ASSERT(pkt->ol_flags == EXT_ATTACHED_MBUF);
/*
* Prevent potential overflow due to MTU change through
* kernel interface.
* copying pointers to temporary array
* for rte_mempool_put_bulk() calls.
*/
- assert(pkts);
- assert(pkts_n);
+ MLX5_ASSERT(pkts);
+ MLX5_ASSERT(pkts_n);
for (;;) {
for (;;) {
/*
*/
mbuf = rte_pktmbuf_prefree_seg(*pkts);
if (likely(mbuf != NULL)) {
- assert(mbuf == *pkts);
+ MLX5_ASSERT(mbuf == *pkts);
if (likely(n_free != 0)) {
if (unlikely(pool != mbuf->pool))
/* From different pool. */
* This loop is implemented to avoid multiple
* inlining of rte_mempool_put_bulk().
*/
- assert(pool);
- assert(p_free);
- assert(n_free);
+ MLX5_ASSERT(pool);
+ MLX5_ASSERT(p_free);
+ MLX5_ASSERT(n_free);
/*
* Free the array of pre-freed mbufs
* belonging to the same memory pool.
{
uint16_t n_elts = tail - txq->elts_tail;
- assert(n_elts);
- assert(n_elts <= txq->elts_s);
+ MLX5_ASSERT(n_elts);
+ MLX5_ASSERT(n_elts <= txq->elts_s);
/*
* Implement a loop to support ring buffer wraparound
* with single inlining of mlx5_tx_free_mbuf().
part = txq->elts_s - (txq->elts_tail & txq->elts_m);
part = RTE_MIN(part, n_elts);
- assert(part);
- assert(part <= txq->elts_s);
+ MLX5_ASSERT(part);
+ MLX5_ASSERT(part <= txq->elts_s);
mlx5_tx_free_mbuf(&txq->elts[txq->elts_tail & txq->elts_m],
part, olx);
txq->elts_tail += part;
unsigned int part;
struct rte_mbuf **elts = (struct rte_mbuf **)txq->elts;
- assert(pkts);
- assert(pkts_n);
+ MLX5_ASSERT(pkts);
+ MLX5_ASSERT(pkts_n);
part = txq->elts_s - (txq->elts_head & txq->elts_m);
- assert(part);
- assert(part <= txq->elts_s);
+ MLX5_ASSERT(part);
+ MLX5_ASSERT(part <= txq->elts_s);
/* This code is a good candidate for vectorizing with SIMD. */
rte_memcpy((void *)(elts + (txq->elts_head & txq->elts_m)),
(void *)pkts,
* Pointer to TX queue structure.
* @param valid CQE pointer
* if not NULL update txq->wqe_pi and flush the buffers
- * @param itail
- * if not negative - flush the buffers till this index.
* @param olx
* Configured Tx offloads mask. It is fully defined at
* compile time and may be used for optimization.
static __rte_always_inline void
mlx5_tx_comp_flush(struct mlx5_txq_data *restrict txq,
volatile struct mlx5_cqe *last_cqe,
- int itail,
unsigned int olx __rte_unused)
{
- uint16_t tail;
-
if (likely(last_cqe != NULL)) {
+ uint16_t tail;
+
txq->wqe_pi = rte_be_to_cpu_16(last_cqe->wqe_counter);
- tail = ((volatile struct mlx5_wqe_cseg *)
- (txq->wqes + (txq->wqe_pi & txq->wqe_m)))->misc;
- } else if (itail >= 0) {
- tail = (uint16_t)itail;
- } else {
- return;
- }
- rte_compiler_barrier();
- *txq->cq_db = rte_cpu_to_be_32(txq->cq_ci);
- if (likely(tail != txq->elts_tail)) {
- mlx5_tx_free_elts(txq, tail, olx);
- assert(tail == txq->elts_tail);
+ tail = txq->fcqs[(txq->cq_ci - 1) & txq->cqe_m];
+ if (likely(tail != txq->elts_tail)) {
+ mlx5_tx_free_elts(txq, tail, olx);
+ MLX5_ASSERT(tail == txq->elts_tail);
+ }
}
}
{
unsigned int count = MLX5_TX_COMP_MAX_CQE;
volatile struct mlx5_cqe *last_cqe = NULL;
+ uint16_t ci = txq->cq_ci;
int ret;
static_assert(MLX5_CQE_STATUS_HW_OWN < 0, "Must be negative value");
do {
volatile struct mlx5_cqe *cqe;
- cqe = &txq->cqes[txq->cq_ci & txq->cqe_m];
- ret = check_cqe(cqe, txq->cqe_s, txq->cq_ci);
+ cqe = &txq->cqes[ci & txq->cqe_m];
+ ret = check_cqe(cqe, txq->cqe_s, ci);
if (unlikely(ret != MLX5_CQE_STATUS_SW_OWN)) {
if (likely(ret != MLX5_CQE_STATUS_ERR)) {
/* No new CQEs in completion queue. */
- assert(ret == MLX5_CQE_STATUS_HW_OWN);
+ MLX5_ASSERT(ret == MLX5_CQE_STATUS_HW_OWN);
break;
}
/*
* here, before we might perform SQ reset.
*/
rte_wmb();
+ txq->cq_ci = ci;
ret = mlx5_tx_error_cqe_handle
(txq, (volatile struct mlx5_err_cqe *)cqe);
+ if (unlikely(ret < 0)) {
+ /*
+ * Some error occurred on queue error
+ * handling, we do not advance the index
+ * here, allowing to retry on next call.
+ */
+ return;
+ }
/*
- * Flush buffers, update consuming index
- * if recovery succeeded. Otherwise
- * just try to recover later.
+ * We are going to fetch all entries with
+ * MLX5_CQE_SYNDROME_WR_FLUSH_ERR status.
+ * The send queue is supposed to be empty.
*/
+ ++ci;
+ txq->cq_pi = ci;
last_cqe = NULL;
- break;
+ continue;
}
/* Normal transmit completion. */
- ++txq->cq_ci;
+ MLX5_ASSERT(ci != txq->cq_pi);
+ MLX5_ASSERT((txq->fcqs[ci & txq->cqe_m] >> 16) ==
+ cqe->wqe_counter);
+ ++ci;
last_cqe = cqe;
-#ifndef NDEBUG
- if (txq->cq_pi)
- --txq->cq_pi;
-#endif
- /*
- * We have to restrict the amount of processed CQEs
- * in one tx_burst routine call. The CQ may be large
- * and many CQEs may be updated by the NIC in one
- * transaction. Buffers freeing is time consuming,
- * multiple iterations may introduce significant
- * latency.
- */
- } while (--count);
- mlx5_tx_comp_flush(txq, last_cqe, ret, olx);
+ /*
+ * We have to restrict the amount of processed CQEs
+ * in one tx_burst routine call. The CQ may be large
+ * and many CQEs may be updated by the NIC in one
+ * transaction. Buffers freeing is time consuming,
+ * multiple iterations may introduce significant
+ * latency.
+ */
+ if (likely(--count == 0))
+ break;
+ } while (true);
+ if (likely(ci != txq->cq_ci)) {
+ /*
+ * Update completion queue consuming index
+ * and ring doorbell to notify hardware.
+ */
+ rte_compiler_barrier();
+ txq->cq_ci = ci;
+ *txq->cq_db = rte_cpu_to_be_32(ci);
+ mlx5_tx_comp_flush(txq, last_cqe, olx);
+ }
}
/**
* Pointer to TX queue structure.
* @param loc
* Pointer to burst routine local context.
- * @param multi,
- * Routine is called from multi-segment sending loop,
- * do not correct the elts_head according to the pkts_copy.
* @param olx
* Configured Tx offloads mask. It is fully defined at
* compile time and may be used for optimization.
static __rte_always_inline void
mlx5_tx_request_completion(struct mlx5_txq_data *restrict txq,
struct mlx5_txq_local *restrict loc,
- bool multi,
unsigned int olx)
{
uint16_t head = txq->elts_head;
unsigned int part;
- part = (MLX5_TXOFF_CONFIG(INLINE) || multi) ?
+ part = MLX5_TXOFF_CONFIG(INLINE) ?
0 : loc->pkts_sent - loc->pkts_copy;
head += part;
if ((uint16_t)(head - txq->elts_comp) >= MLX5_TX_COMP_THRESH ||
/* Request unconditional completion on last WQE. */
last->cseg.flags = RTE_BE32(MLX5_COMP_ALWAYS <<
MLX5_COMP_MODE_OFFSET);
- /* Save elts_head in unused "immediate" field of WQE. */
- last->cseg.misc = head;
- /*
- * A CQE slot must always be available. Count the
- * issued CEQ "always" request instead of production
- * index due to here can be CQE with errors and
- * difference with ci may become inconsistent.
- */
- assert(txq->cqe_s > ++txq->cq_pi);
+ /* Save elts_head in dedicated free on completion queue. */
+#ifdef RTE_LIBRTE_MLX5_DEBUG
+ txq->fcqs[txq->cq_pi++ & txq->cqe_m] = head |
+ (last->cseg.opcode >> 8) << 16;
+#else
+ txq->fcqs[txq->cq_pi++ & txq->cqe_m] = head;
+#endif
+ /* A CQE slot must always be available. */
+ MLX5_ASSERT((txq->cq_pi - txq->cq_ci) <= txq->cqe_s);
}
}
{
struct mlx5_wqe_cseg *restrict cs = &wqe->cseg;
+ /* For legacy MPW replace the EMPW by TSO with modifier. */
+ if (MLX5_TXOFF_CONFIG(MPW) && opcode == MLX5_OPCODE_ENHANCED_MPSW)
+ opcode = MLX5_OPCODE_TSO | MLX5_OPC_MOD_MPW << 24;
cs->opcode = rte_cpu_to_be_32((txq->wqe_ci << 8) | opcode);
cs->sq_ds = rte_cpu_to_be_32(txq->qp_num_8s | ds);
cs->flags = RTE_BE32(MLX5_COMP_ONLY_FIRST_ERR <<
es->swp_offs = txq_mbuf_to_swp(loc, &es->swp_flags, olx);
/* Fill metadata field if needed. */
es->metadata = MLX5_TXOFF_CONFIG(METADATA) ?
- loc->mbuf->ol_flags & PKT_TX_METADATA ?
- loc->mbuf->tx_metadata : 0 : 0;
+ loc->mbuf->ol_flags & PKT_TX_DYNF_METADATA ?
+ *RTE_FLOW_DYNF_METADATA(loc->mbuf) : 0 : 0;
/* Engage VLAN tag insertion feature if requested. */
if (MLX5_TXOFF_CONFIG(VLAN) &&
loc->mbuf->ol_flags & PKT_TX_VLAN_PKT) {
* We should get here only if device support
* this feature correctly.
*/
- assert(txq->vlan_en);
+ MLX5_ASSERT(txq->vlan_en);
es->inline_hdr = rte_cpu_to_be_32(MLX5_ETH_WQE_VLAN_INSERT |
loc->mbuf->vlan_tci);
} else {
es->swp_offs = txq_mbuf_to_swp(loc, &es->swp_flags, olx);
/* Fill metadata field if needed. */
es->metadata = MLX5_TXOFF_CONFIG(METADATA) ?
- loc->mbuf->ol_flags & PKT_TX_METADATA ?
- loc->mbuf->tx_metadata : 0 : 0;
+ loc->mbuf->ol_flags & PKT_TX_DYNF_METADATA ?
+ *RTE_FLOW_DYNF_METADATA(loc->mbuf) : 0 : 0;
static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
(sizeof(uint16_t) +
sizeof(rte_v128u32_t)),
loc->mbuf->vlan_tci);
pdst += sizeof(struct rte_vlan_hdr);
/* Copy the rest two bytes from packet data. */
- assert(pdst == RTE_PTR_ALIGN(pdst, sizeof(uint16_t)));
+ MLX5_ASSERT(pdst == RTE_PTR_ALIGN(pdst, sizeof(uint16_t)));
*(uint16_t *)pdst = *(unaligned_uint16_t *)psrc;
} else {
/* Fill the gap in the title WQEBB with inline data. */
es->swp_offs = txq_mbuf_to_swp(loc, &es->swp_flags, olx);
/* Fill metadata field if needed. */
es->metadata = MLX5_TXOFF_CONFIG(METADATA) ?
- loc->mbuf->ol_flags & PKT_TX_METADATA ?
- loc->mbuf->tx_metadata : 0 : 0;
+ loc->mbuf->ol_flags & PKT_TX_DYNF_METADATA ?
+ *RTE_FLOW_DYNF_METADATA(loc->mbuf) : 0 : 0;
static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
(sizeof(uint16_t) +
sizeof(rte_v128u32_t)),
loc->mbuf->vlan_tci);
pdst += sizeof(struct rte_vlan_hdr);
/* Copy the rest two bytes from packet data. */
- assert(pdst == RTE_PTR_ALIGN(pdst, sizeof(uint16_t)));
+ MLX5_ASSERT(pdst == RTE_PTR_ALIGN(pdst, sizeof(uint16_t)));
*(uint16_t *)pdst = *(unaligned_uint16_t *)psrc;
psrc += sizeof(uint16_t);
} else {
psrc += sizeof(rte_v128u32_t);
}
pdst = (uint8_t *)(es + 2);
- assert(inlen >= MLX5_ESEG_MIN_INLINE_SIZE);
- assert(pdst < (uint8_t *)txq->wqes_end);
+ MLX5_ASSERT(inlen >= MLX5_ESEG_MIN_INLINE_SIZE);
+ MLX5_ASSERT(pdst < (uint8_t *)txq->wqes_end);
inlen -= MLX5_ESEG_MIN_INLINE_SIZE;
if (!inlen) {
- assert(pdst == RTE_PTR_ALIGN(pdst, MLX5_WSEG_SIZE));
+ MLX5_ASSERT(pdst == RTE_PTR_ALIGN(pdst, MLX5_WSEG_SIZE));
return (struct mlx5_wqe_dseg *)pdst;
}
/*
* Pointer to burst routine local context.
* @param len
* Length of data to be copied.
+ * @param must
+ * Length of data to be copied ignoring no inline hint.
* @param olx
* Configured Tx offloads mask. It is fully defined at
* compile time and may be used for optimization.
+ *
+ * @return
+ * Number of actual copied data bytes. This is always greater than or
+ * equal to must parameter and might be lesser than len in no inline
+ * hint flag is encountered.
*/
-static __rte_always_inline void
+static __rte_always_inline unsigned int
mlx5_tx_mseg_memcpy(uint8_t *pdst,
struct mlx5_txq_local *restrict loc,
unsigned int len,
+ unsigned int must,
unsigned int olx __rte_unused)
{
struct rte_mbuf *mbuf;
- unsigned int part, dlen;
+ unsigned int part, dlen, copy = 0;
uint8_t *psrc;
- assert(len);
+ MLX5_ASSERT(len);
+ MLX5_ASSERT(must <= len);
do {
/* Allow zero length packets, must check first. */
dlen = rte_pktmbuf_data_len(loc->mbuf);
loc->mbuf = mbuf->next;
rte_pktmbuf_free_seg(mbuf);
loc->mbuf_off = 0;
- assert(loc->mbuf_nseg > 1);
- assert(loc->mbuf);
+ MLX5_ASSERT(loc->mbuf_nseg > 1);
+ MLX5_ASSERT(loc->mbuf);
--loc->mbuf_nseg;
+ if (loc->mbuf->ol_flags & PKT_TX_DYNF_NOINLINE) {
+ unsigned int diff;
+
+ if (copy >= must) {
+ /*
+ * We already copied the minimal
+ * requested amount of data.
+ */
+ return copy;
+ }
+ diff = must - copy;
+ if (diff <= rte_pktmbuf_data_len(loc->mbuf)) {
+ /*
+ * Copy only the minimal required
+ * part of the data buffer.
+ */
+ len = diff;
+ }
+ }
continue;
}
dlen -= loc->mbuf_off;
loc->mbuf_off);
part = RTE_MIN(len, dlen);
rte_memcpy(pdst, psrc, part);
+ copy += part;
loc->mbuf_off += part;
len -= part;
if (!len) {
loc->mbuf = mbuf->next;
rte_pktmbuf_free_seg(mbuf);
loc->mbuf_off = 0;
- assert(loc->mbuf_nseg >= 1);
+ MLX5_ASSERT(loc->mbuf_nseg >= 1);
--loc->mbuf_nseg;
}
- return;
+ return copy;
}
pdst += part;
} while (true);
struct mlx5_wqe_eseg *restrict es = &wqe->eseg;
uint32_t csum;
uint8_t *pdst;
- unsigned int part;
+ unsigned int part, tlen = 0;
/*
* Calculate and set check sum flags first, uint32_t field
es->swp_offs = txq_mbuf_to_swp(loc, &es->swp_flags, olx);
/* Fill metadata field if needed. */
es->metadata = MLX5_TXOFF_CONFIG(METADATA) ?
- loc->mbuf->ol_flags & PKT_TX_METADATA ?
- loc->mbuf->tx_metadata : 0 : 0;
+ loc->mbuf->ol_flags & PKT_TX_DYNF_METADATA ?
+ *RTE_FLOW_DYNF_METADATA(loc->mbuf) : 0 : 0;
static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
(sizeof(uint16_t) +
sizeof(rte_v128u32_t)),
sizeof(struct rte_vlan_hdr) +
2 * RTE_ETHER_ADDR_LEN),
"invalid Ethernet Segment data size");
- assert(inlen >= MLX5_ESEG_MIN_INLINE_SIZE);
- es->inline_hdr_sz = rte_cpu_to_be_16(inlen);
+ MLX5_ASSERT(inlen >= MLX5_ESEG_MIN_INLINE_SIZE);
pdst = (uint8_t *)&es->inline_data;
if (MLX5_TXOFF_CONFIG(VLAN) && vlan) {
/* Implement VLAN tag insertion as part inline data. */
- mlx5_tx_mseg_memcpy(pdst, loc, 2 * RTE_ETHER_ADDR_LEN, olx);
+ mlx5_tx_mseg_memcpy(pdst, loc,
+ 2 * RTE_ETHER_ADDR_LEN,
+ 2 * RTE_ETHER_ADDR_LEN, olx);
pdst += 2 * RTE_ETHER_ADDR_LEN;
*(unaligned_uint32_t *)pdst = rte_cpu_to_be_32
((RTE_ETHER_TYPE_VLAN << 16) |
loc->mbuf->vlan_tci);
pdst += sizeof(struct rte_vlan_hdr);
- inlen -= 2 * RTE_ETHER_ADDR_LEN + sizeof(struct rte_vlan_hdr);
+ tlen += 2 * RTE_ETHER_ADDR_LEN + sizeof(struct rte_vlan_hdr);
}
- assert(pdst < (uint8_t *)txq->wqes_end);
+ MLX5_ASSERT(pdst < (uint8_t *)txq->wqes_end);
/*
* The WQEBB space availability is checked by caller.
* Here we should be aware of WQE ring buffer wraparound only.
*/
part = (uint8_t *)txq->wqes_end - pdst;
- part = RTE_MIN(part, inlen);
- assert(part);
+ part = RTE_MIN(part, inlen - tlen);
+ MLX5_ASSERT(part);
do {
- mlx5_tx_mseg_memcpy(pdst, loc, part, olx);
- inlen -= part;
- if (likely(!inlen)) {
- pdst += part;
+ unsigned int copy;
+
+ /*
+ * Copying may be interrupted inside the routine
+ * if run into no inline hint flag.
+ */
+ copy = tlen >= txq->inlen_mode ? 0 : (txq->inlen_mode - tlen);
+ copy = mlx5_tx_mseg_memcpy(pdst, loc, part, copy, olx);
+ tlen += copy;
+ if (likely(inlen <= tlen) || copy < part) {
+ es->inline_hdr_sz = rte_cpu_to_be_16(tlen);
+ pdst += copy;
pdst = RTE_PTR_ALIGN(pdst, MLX5_WSEG_SIZE);
return (struct mlx5_wqe_dseg *)pdst;
}
pdst = (uint8_t *)txq->wqes;
- part = inlen;
+ part = inlen - tlen;
} while (true);
}
unsigned int olx __rte_unused)
{
- assert(len);
+ MLX5_ASSERT(len);
dseg->bcount = rte_cpu_to_be_32(len);
dseg->lkey = mlx5_tx_mb2mr(txq, loc->mbuf);
dseg->pbuf = rte_cpu_to_be_64((uintptr_t)buf);
{
uintptr_t dst, src;
- assert(len);
+ MLX5_ASSERT(len);
if (len > MLX5_DSEG_MIN_INLINE_SIZE) {
dseg->bcount = rte_cpu_to_be_32(len);
dseg->lkey = mlx5_tx_mb2mr(txq, loc->mbuf);
src = (uintptr_t)buf;
if (len & 0x08) {
#ifdef RTE_ARCH_STRICT_ALIGN
- assert(dst == RTE_PTR_ALIGN(dst, sizeof(uint32_t)));
+ MLX5_ASSERT(dst == RTE_PTR_ALIGN(dst, sizeof(uint32_t)));
*(uint32_t *)dst = *(unaligned_uint32_t *)src;
dst += sizeof(uint32_t);
src += sizeof(uint32_t);
unsigned int part;
uint8_t *pdst;
- assert(len > MLX5_ESEG_MIN_INLINE_SIZE);
+ MLX5_ASSERT(len > MLX5_ESEG_MIN_INLINE_SIZE);
static_assert(MLX5_DSEG_MIN_INLINE_SIZE ==
(2 * RTE_ETHER_ADDR_LEN),
"invalid Data Segment data size");
pdst += MLX5_DSEG_MIN_INLINE_SIZE;
len -= MLX5_DSEG_MIN_INLINE_SIZE;
/* Insert VLAN ethertype + VLAN tag. Pointer is aligned. */
- assert(pdst == RTE_PTR_ALIGN(pdst, MLX5_WSEG_SIZE));
+ MLX5_ASSERT(pdst == RTE_PTR_ALIGN(pdst, MLX5_WSEG_SIZE));
if (unlikely(pdst >= (uint8_t *)txq->wqes_end))
pdst = (uint8_t *)txq->wqes;
*(uint32_t *)pdst = rte_cpu_to_be_32((RTE_ETHER_TYPE_VLAN << 16) |
struct mlx5_wqe_dseg *restrict dseg;
unsigned int ds;
- assert((rte_pktmbuf_pkt_len(loc->mbuf) + vlan) >= inlen);
+ MLX5_ASSERT((rte_pktmbuf_pkt_len(loc->mbuf) + vlan) >= inlen);
loc->mbuf_nseg = NB_SEGS(loc->mbuf);
loc->mbuf_off = 0;
* Non-zero offset means there are some data
* remained in the packet.
*/
- assert(loc->mbuf_off < rte_pktmbuf_data_len(loc->mbuf));
- assert(rte_pktmbuf_data_len(loc->mbuf));
+ MLX5_ASSERT(loc->mbuf_off < rte_pktmbuf_data_len(loc->mbuf));
+ MLX5_ASSERT(rte_pktmbuf_data_len(loc->mbuf));
dptr = rte_pktmbuf_mtod_offset(loc->mbuf, uint8_t *,
loc->mbuf_off);
dlen = rte_pktmbuf_data_len(loc->mbuf) - loc->mbuf_off;
dseg = (struct mlx5_wqe_dseg *)txq->wqes;
mlx5_tx_dseg_iptr(txq, loc, dseg, dptr, dlen, olx);
/* Store the mbuf to be freed on completion. */
- assert(loc->elts_free);
+ MLX5_ASSERT(loc->elts_free);
txq->elts[txq->elts_head++ & txq->elts_m] = loc->mbuf;
--loc->elts_free;
++dseg;
(txq, loc, dseg,
rte_pktmbuf_mtod(loc->mbuf, uint8_t *),
rte_pktmbuf_data_len(loc->mbuf), olx);
- assert(loc->elts_free);
+ MLX5_ASSERT(loc->elts_free);
txq->elts[txq->elts_head++ & txq->elts_m] = loc->mbuf;
--loc->elts_free;
++dseg;
inlen <= MLX5_ESEG_MIN_INLINE_SIZE ||
inlen > (dlen + vlan)))
return MLX5_TXCMP_CODE_ERROR;
- assert(inlen >= txq->inlen_mode);
+ MLX5_ASSERT(inlen >= txq->inlen_mode);
/*
* Check whether there are enough free WQEBBs:
* - Control Segment
wqe->cseg.sq_ds = rte_cpu_to_be_32(txq->qp_num_8s | ds);
txq->wqe_ci += (ds + 3) / 4;
loc->wqe_free -= (ds + 3) / 4;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, true, olx);
return MLX5_TXCMP_CODE_MULTI;
}
struct mlx5_wqe *restrict wqe;
unsigned int ds, nseg;
- assert(NB_SEGS(loc->mbuf) > 1);
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) > 1);
/*
* No inline at all, it means the CPU cycles saving
* is prioritized at configuration, we should not
} while (true);
txq->wqe_ci += (ds + 3) / 4;
loc->wqe_free -= (ds + 3) / 4;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, true, olx);
return MLX5_TXCMP_CODE_MULTI;
}
struct mlx5_wqe *restrict wqe;
unsigned int ds, inlen, dlen, vlan = 0;
- assert(MLX5_TXOFF_CONFIG(INLINE));
- assert(NB_SEGS(loc->mbuf) > 1);
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) > 1);
/*
* First calculate data length to be inlined
* to estimate the required space for WQE.
/* Check against minimal length. */
if (inlen <= MLX5_ESEG_MIN_INLINE_SIZE)
return MLX5_TXCMP_CODE_ERROR;
- assert(txq->inlen_send >= MLX5_ESEG_MIN_INLINE_SIZE);
- if (inlen > txq->inlen_send) {
+ MLX5_ASSERT(txq->inlen_send >= MLX5_ESEG_MIN_INLINE_SIZE);
+ if (inlen > txq->inlen_send ||
+ loc->mbuf->ol_flags & PKT_TX_DYNF_NOINLINE) {
struct rte_mbuf *mbuf;
unsigned int nxlen;
uintptr_t start;
* inlining is required.
*/
if (txq->inlen_mode) {
- assert(txq->inlen_mode >= MLX5_ESEG_MIN_INLINE_SIZE);
- assert(txq->inlen_mode <= txq->inlen_send);
+ MLX5_ASSERT(txq->inlen_mode >=
+ MLX5_ESEG_MIN_INLINE_SIZE);
+ MLX5_ASSERT(txq->inlen_mode <= txq->inlen_send);
inlen = txq->inlen_mode;
} else {
- if (!vlan || txq->vlan_en) {
+ if (loc->mbuf->ol_flags & PKT_TX_DYNF_NOINLINE ||
+ !vlan || txq->vlan_en) {
/*
* VLAN insertion will be done inside by HW.
* It is not utmost effective - VLAN flag is
do {
smlen = nxlen;
mbuf = NEXT(mbuf);
- assert(mbuf);
+ MLX5_ASSERT(mbuf);
nxlen = rte_pktmbuf_data_len(mbuf);
nxlen += smlen;
} while (unlikely(nxlen < inlen));
inlen = nxlen;
mbuf = NEXT(mbuf);
/* There should be not end of packet. */
- assert(mbuf);
+ MLX5_ASSERT(mbuf);
nxlen = inlen + rte_pktmbuf_data_len(mbuf);
} while (unlikely(nxlen < txq->inlen_send));
}
* Estimate the number of Data Segments conservatively,
* supposing no any mbufs is being freed during inlining.
*/
- assert(inlen <= txq->inlen_send);
+ MLX5_ASSERT(inlen <= txq->inlen_send);
ds = NB_SEGS(loc->mbuf) + 2 + (inlen -
MLX5_ESEG_MIN_INLINE_SIZE +
MLX5_WSEG_SIZE +
wqe->cseg.sq_ds = rte_cpu_to_be_32(txq->qp_num_8s | ds);
txq->wqe_ci += (ds + 3) / 4;
loc->wqe_free -= (ds + 3) / 4;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, true, olx);
return MLX5_TXCMP_CODE_MULTI;
}
struct mlx5_txq_local *restrict loc,
unsigned int olx)
{
- assert(loc->elts_free && loc->wqe_free);
- assert(pkts_n > loc->pkts_sent);
+ MLX5_ASSERT(loc->elts_free && loc->wqe_free);
+ MLX5_ASSERT(pkts_n > loc->pkts_sent);
pkts += loc->pkts_sent + 1;
pkts_n -= loc->pkts_sent;
for (;;) {
enum mlx5_txcmp_code ret;
- assert(NB_SEGS(loc->mbuf) > 1);
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) > 1);
/*
* Estimate the number of free elts quickly but
* conservatively. Some segment may be fully inlined
return MLX5_TXCMP_CODE_TSO;
return MLX5_TXCMP_CODE_SINGLE;
}
- assert(false);
+ MLX5_ASSERT(false);
}
/**
struct mlx5_txq_local *restrict loc,
unsigned int olx)
{
- assert(loc->elts_free && loc->wqe_free);
- assert(pkts_n > loc->pkts_sent);
+ MLX5_ASSERT(loc->elts_free && loc->wqe_free);
+ MLX5_ASSERT(pkts_n > loc->pkts_sent);
pkts += loc->pkts_sent + 1;
pkts_n -= loc->pkts_sent;
for (;;) {
unsigned int ds, dlen, hlen, ntcp, vlan = 0;
uint8_t *dptr;
- assert(NB_SEGS(loc->mbuf) == 1);
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1);
dlen = rte_pktmbuf_data_len(loc->mbuf);
if (MLX5_TXOFF_CONFIG(VLAN) &&
loc->mbuf->ol_flags & PKT_TX_VLAN_PKT) {
--loc->elts_free;
++loc->pkts_sent;
--pkts_n;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, false, olx);
if (unlikely(!pkts_n || !loc->elts_free || !loc->wqe_free))
return MLX5_TXCMP_CODE_EXIT;
loc->mbuf = *pkts++;
return MLX5_TXCMP_CODE_SINGLE;
/* Continue with the next TSO packet. */
}
- assert(false);
+ MLX5_ASSERT(false);
}
/**
/**
* Check the next packet attributes to match with the eMPW batch ones.
+ * In addition, for legacy MPW the packet length is checked either.
*
* @param txq
* Pointer to TX queue structure.
* Pointer to Ethernet Segment of eMPW batch.
* @param loc
* Pointer to burst routine local context.
+ * @param dlen
+ * Length of previous packet in MPW descriptor.
* @param olx
* Configured Tx offloads mask. It is fully defined at
* compile time and may be used for optimization.
mlx5_tx_match_empw(struct mlx5_txq_data *restrict txq __rte_unused,
struct mlx5_wqe_eseg *restrict es,
struct mlx5_txq_local *restrict loc,
+ uint32_t dlen,
unsigned int olx)
{
uint8_t swp_flags = 0;
return false;
/* Fill metadata field if needed. */
if (MLX5_TXOFF_CONFIG(METADATA) &&
- es->metadata != (loc->mbuf->ol_flags & PKT_TX_METADATA ?
- loc->mbuf->tx_metadata : 0))
+ es->metadata != (loc->mbuf->ol_flags & PKT_TX_DYNF_METADATA ?
+ *RTE_FLOW_DYNF_METADATA(loc->mbuf) : 0))
+ return false;
+ /* Legacy MPW can send packets with the same lengt only. */
+ if (MLX5_TXOFF_CONFIG(MPW) &&
+ dlen != rte_pktmbuf_data_len(loc->mbuf))
return false;
/* There must be no VLAN packets in eMPW loop. */
if (MLX5_TXOFF_CONFIG(VLAN))
- assert(!(loc->mbuf->ol_flags & PKT_TX_VLAN_PKT));
+ MLX5_ASSERT(!(loc->mbuf->ol_flags & PKT_TX_VLAN_PKT));
return true;
}
struct mlx5_txq_local *restrict loc,
unsigned int ds,
unsigned int slen,
- unsigned int olx)
+ unsigned int olx __rte_unused)
{
- assert(!MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT(!MLX5_TXOFF_CONFIG(INLINE));
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Update sent data bytes counter. */
txq->stats.obytes += slen;
loc->wqe_last->cseg.sq_ds = rte_cpu_to_be_32(txq->qp_num_8s | ds);
txq->wqe_ci += (ds + 3) / 4;
loc->wqe_free -= (ds + 3) / 4;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, false, olx);
}
/*
unsigned int slen,
unsigned int olx __rte_unused)
{
- assert(MLX5_TXOFF_CONFIG(INLINE));
- assert((len % MLX5_WSEG_SIZE) == 0);
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT((len % MLX5_WSEG_SIZE) == 0);
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Update sent data bytes counter. */
txq->stats.obytes += slen;
loc->wqe_last->cseg.sq_ds = rte_cpu_to_be_32(txq->qp_num_8s | len);
txq->wqe_ci += (len + 3) / 4;
loc->wqe_free -= (len + 3) / 4;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, false, olx);
}
/**
* and sends single-segment packet with eMPW opcode
* without data inlining.
*/
- assert(!MLX5_TXOFF_CONFIG(INLINE));
- assert(MLX5_TXOFF_CONFIG(EMPW));
- assert(loc->elts_free && loc->wqe_free);
- assert(pkts_n > loc->pkts_sent);
+ MLX5_ASSERT(!MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(EMPW));
+ MLX5_ASSERT(loc->elts_free && loc->wqe_free);
+ MLX5_ASSERT(pkts_n > loc->pkts_sent);
static_assert(MLX5_EMPW_MIN_PACKETS >= 2, "invalid min size");
pkts += loc->pkts_sent + 1;
pkts_n -= loc->pkts_sent;
unsigned int slen = 0;
next_empw:
- part = RTE_MIN(pkts_n, MLX5_EMPW_MAX_PACKETS);
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1);
+ part = RTE_MIN(pkts_n, MLX5_TXOFF_CONFIG(MPW) ?
+ MLX5_MPW_MAX_PACKETS :
+ MLX5_EMPW_MAX_PACKETS);
if (unlikely(loc->elts_free < part)) {
/* We have no enough elts to save all mbufs. */
if (unlikely(loc->elts_free < MLX5_EMPW_MIN_PACKETS))
eseg = &loc->wqe_last->eseg;
dseg = &loc->wqe_last->dseg[0];
loop = part;
+ /* Store the packet length for legacy MPW. */
+ if (MLX5_TXOFF_CONFIG(MPW))
+ eseg->mss = rte_cpu_to_be_16
+ (rte_pktmbuf_data_len(loc->mbuf));
for (;;) {
uint32_t dlen = rte_pktmbuf_data_len(loc->mbuf);
#ifdef MLX5_PMD_SOFT_COUNTERS
return MLX5_TXCMP_CODE_EXIT;
return MLX5_TXCMP_CODE_MULTI;
}
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1);
if (ret == MLX5_TXCMP_CODE_TSO) {
part -= loop;
mlx5_tx_sdone_empw(txq, loc, part, slen, olx);
return MLX5_TXCMP_CODE_SINGLE;
}
if (ret != MLX5_TXCMP_CODE_EMPW) {
- assert(false);
+ MLX5_ASSERT(false);
part -= loop;
mlx5_tx_sdone_empw(txq, loc, part, slen, olx);
return MLX5_TXCMP_CODE_ERROR;
* - check sum settings
* - metadata value
* - software parser settings
+ * - packets length (legacy MPW only)
*/
- if (!mlx5_tx_match_empw(txq, eseg, loc, olx)) {
- assert(loop);
+ if (!mlx5_tx_match_empw(txq, eseg, loc, dlen, olx)) {
+ MLX5_ASSERT(loop);
part -= loop;
mlx5_tx_sdone_empw(txq, loc, part, slen, olx);
if (unlikely(!loc->elts_free ||
dseg = (struct mlx5_wqe_dseg *)txq->wqes;
}
/* eMPW is built successfully, update loop parameters. */
- assert(!loop);
- assert(pkts_n >= part);
+ MLX5_ASSERT(!loop);
+ MLX5_ASSERT(pkts_n >= part);
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Update sent data bytes counter. */
txq->stats.obytes += slen;
txq->wqe_ci += (2 + part + 3) / 4;
loc->wqe_free -= (2 + part + 3) / 4;
pkts_n -= part;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, false, olx);
if (unlikely(!pkts_n || !loc->elts_free || !loc->wqe_free))
return MLX5_TXCMP_CODE_EXIT;
loc->mbuf = *pkts++;
return ret;
/* Continue sending eMPW batches. */
}
- assert(false);
+ MLX5_ASSERT(false);
}
/**
* and sends single-segment packet with eMPW opcode
* with data inlining.
*/
- assert(MLX5_TXOFF_CONFIG(INLINE));
- assert(MLX5_TXOFF_CONFIG(EMPW));
- assert(loc->elts_free && loc->wqe_free);
- assert(pkts_n > loc->pkts_sent);
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(EMPW));
+ MLX5_ASSERT(loc->elts_free && loc->wqe_free);
+ MLX5_ASSERT(pkts_n > loc->pkts_sent);
static_assert(MLX5_EMPW_MIN_PACKETS >= 2, "invalid min size");
pkts += loc->pkts_sent + 1;
pkts_n -= loc->pkts_sent;
unsigned int room, part, nlim;
unsigned int slen = 0;
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1);
/*
* Limits the amount of packets in one WQE
* to improve CQE latency generation.
*/
- nlim = RTE_MIN(pkts_n, MLX5_EMPW_MAX_PACKETS);
+ nlim = RTE_MIN(pkts_n, MLX5_TXOFF_CONFIG(MPW) ?
+ MLX5_MPW_INLINE_MAX_PACKETS :
+ MLX5_EMPW_MAX_PACKETS);
/* Check whether we have minimal amount WQEs */
if (unlikely(loc->wqe_free <
((2 + MLX5_EMPW_MIN_PACKETS + 3) / 4)))
olx & ~MLX5_TXOFF_CONFIG_VLAN);
eseg = &loc->wqe_last->eseg;
dseg = &loc->wqe_last->dseg[0];
+ /* Store the packet length for legacy MPW. */
+ if (MLX5_TXOFF_CONFIG(MPW))
+ eseg->mss = rte_cpu_to_be_16
+ (rte_pktmbuf_data_len(loc->mbuf));
room = RTE_MIN(MLX5_WQE_SIZE_MAX / MLX5_WQE_SIZE,
loc->wqe_free) * MLX5_WQE_SIZE -
MLX5_WQE_CSEG_SIZE -
uint8_t *dptr = rte_pktmbuf_mtod(loc->mbuf, uint8_t *);
unsigned int tlen;
- assert(room >= MLX5_WQE_DSEG_SIZE);
- assert((room % MLX5_WQE_DSEG_SIZE) == 0);
- assert((uintptr_t)dseg < (uintptr_t)txq->wqes_end);
+ MLX5_ASSERT(room >= MLX5_WQE_DSEG_SIZE);
+ MLX5_ASSERT((room % MLX5_WQE_DSEG_SIZE) == 0);
+ MLX5_ASSERT((uintptr_t)dseg < (uintptr_t)txq->wqes_end);
/*
* Some Tx offloads may cause an error if
* packet is not long enough, check against
return MLX5_TXCMP_CODE_ERROR;
}
/* Inline or not inline - that's the Question. */
- if (dlen > txq->inlen_empw)
+ if (dlen > txq->inlen_empw ||
+ loc->mbuf->ol_flags & PKT_TX_DYNF_NOINLINE)
goto pointer_empw;
/* Inline entire packet, optional VLAN insertion. */
tlen = sizeof(dseg->bcount) + dlen;
* mlx5_tx_able_to_empw() and packet
* fits into inline length guaranteed.
*/
- assert((dlen + sizeof(struct rte_vlan_hdr)) <=
- txq->inlen_empw);
+ MLX5_ASSERT((dlen +
+ sizeof(struct rte_vlan_hdr)) <=
+ txq->inlen_empw);
tlen += sizeof(struct rte_vlan_hdr);
if (room < tlen)
break;
dptr, dlen, olx);
}
tlen = RTE_ALIGN(tlen, MLX5_WSEG_SIZE);
- assert(room >= tlen);
+ MLX5_ASSERT(room >= tlen);
room -= tlen;
/*
* Packet data are completely inlined,
* Not inlinable VLAN packets are
* proceeded outside of this routine.
*/
- assert(room >= MLX5_WQE_DSEG_SIZE);
+ MLX5_ASSERT(room >= MLX5_WQE_DSEG_SIZE);
if (MLX5_TXOFF_CONFIG(VLAN))
- assert(!(loc->mbuf->ol_flags &
- PKT_TX_VLAN_PKT));
+ MLX5_ASSERT(!(loc->mbuf->ol_flags &
+ PKT_TX_VLAN_PKT));
mlx5_tx_dseg_ptr(txq, loc, dseg, dptr, dlen, olx);
/* We have to store mbuf in elts.*/
txq->elts[txq->elts_head++ & txq->elts_m] = loc->mbuf;
return MLX5_TXCMP_CODE_EXIT;
return MLX5_TXCMP_CODE_MULTI;
}
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1);
if (ret == MLX5_TXCMP_CODE_TSO) {
part -= room;
mlx5_tx_idone_empw(txq, loc, part, slen, olx);
return MLX5_TXCMP_CODE_SINGLE;
}
if (ret != MLX5_TXCMP_CODE_EMPW) {
- assert(false);
+ MLX5_ASSERT(false);
part -= room;
mlx5_tx_idone_empw(txq, loc, part, slen, olx);
return MLX5_TXCMP_CODE_ERROR;
* - check sum settings
* - metadata value
* - software parser settings
+ * - packets length (legacy MPW only)
*/
- if (!mlx5_tx_match_empw(txq, eseg, loc, olx))
+ if (!mlx5_tx_match_empw(txq, eseg, loc, dlen, olx))
break;
/* Packet attributes match, continue the same eMPW. */
if ((uintptr_t)dseg >= (uintptr_t)txq->wqes_end)
* We get here to close an existing eMPW
* session and start the new one.
*/
- assert(pkts_n);
+ MLX5_ASSERT(pkts_n);
part -= room;
if (unlikely(!part))
return MLX5_TXCMP_CODE_EXIT;
return MLX5_TXCMP_CODE_EXIT;
/* Continue the loop with new eMPW session. */
}
- assert(false);
+ MLX5_ASSERT(false);
}
/**
* Subroutine is the part of mlx5_tx_burst_single()
* and sends single-segment packet with SEND opcode.
*/
- assert(loc->elts_free && loc->wqe_free);
- assert(pkts_n > loc->pkts_sent);
+ MLX5_ASSERT(loc->elts_free && loc->wqe_free);
+ MLX5_ASSERT(pkts_n > loc->pkts_sent);
pkts += loc->pkts_sent + 1;
pkts_n -= loc->pkts_sent;
for (;;) {
struct mlx5_wqe *restrict wqe;
enum mlx5_txcmp_code ret;
- assert(NB_SEGS(loc->mbuf) == 1);
+ MLX5_ASSERT(NB_SEGS(loc->mbuf) == 1);
if (MLX5_TXOFF_CONFIG(INLINE)) {
unsigned int inlen, vlan = 0;
* Otherwise we would do extra check for data
* size to avoid crashes due to length overflow.
*/
- assert(txq->inlen_send >= MLX5_ESEG_MIN_INLINE_SIZE);
+ MLX5_ASSERT(txq->inlen_send >=
+ MLX5_ESEG_MIN_INLINE_SIZE);
if (inlen <= txq->inlen_send) {
unsigned int seg_n, wqe_n;
/* Check against minimal length. */
if (inlen <= MLX5_ESEG_MIN_INLINE_SIZE)
return MLX5_TXCMP_CODE_ERROR;
+ if (loc->mbuf->ol_flags &
+ PKT_TX_DYNF_NOINLINE) {
+ /*
+ * The hint flag not to inline packet
+ * data is set. Check whether we can
+ * follow the hint.
+ */
+ if ((!MLX5_TXOFF_CONFIG(EMPW) &&
+ txq->inlen_mode) ||
+ (MLX5_TXOFF_CONFIG(MPW) &&
+ txq->inlen_mode)) {
+ /*
+ * The hardware requires the
+ * minimal inline data header.
+ */
+ goto single_min_inline;
+ }
+ if (MLX5_TXOFF_CONFIG(VLAN) &&
+ vlan && !txq->vlan_en) {
+ /*
+ * We must insert VLAN tag
+ * by software means.
+ */
+ goto single_part_inline;
+ }
+ goto single_no_inline;
+ }
/*
* Completely inlined packet data WQE:
* - Control Segment, SEND opcode
* free the packet immediately.
*/
rte_pktmbuf_free_seg(loc->mbuf);
- } else if (!MLX5_TXOFF_CONFIG(EMPW) &&
- txq->inlen_mode) {
+ } else if ((!MLX5_TXOFF_CONFIG(EMPW) ||
+ MLX5_TXOFF_CONFIG(MPW)) &&
+ txq->inlen_mode) {
/*
* If minimal inlining is requested the eMPW
* feature should be disabled due to data is
* We should check the free space in
* WQE ring buffer to inline partially.
*/
- assert(txq->inlen_send >= txq->inlen_mode);
- assert(inlen > txq->inlen_mode);
- assert(txq->inlen_mode >=
- MLX5_ESEG_MIN_INLINE_SIZE);
+single_min_inline:
+ MLX5_ASSERT(txq->inlen_send >= txq->inlen_mode);
+ MLX5_ASSERT(inlen > txq->inlen_mode);
+ MLX5_ASSERT(txq->inlen_mode >=
+ MLX5_ESEG_MIN_INLINE_SIZE);
/*
* Check whether there are enough free WQEBBs:
* - Control Segment
txq->wqe_ci += (ds + 3) / 4;
loc->wqe_free -= (ds + 3) / 4;
/* We have to store mbuf in elts.*/
- assert(MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(INLINE));
txq->elts[txq->elts_head++ & txq->elts_m] =
loc->mbuf;
--loc->elts_free;
* We also get here if VLAN insertion is not
* supported by HW, the inline is enabled.
*/
+single_part_inline:
wqe = txq->wqes + (txq->wqe_ci & txq->wqe_m);
loc->wqe_last = wqe;
mlx5_tx_cseg_init(txq, loc, wqe, 4,
* comparing with txq->inlen_send. We should
* not get overflow here.
*/
- assert(inlen > MLX5_ESEG_MIN_INLINE_SIZE);
+ MLX5_ASSERT(inlen > MLX5_ESEG_MIN_INLINE_SIZE);
dlen = inlen - MLX5_ESEG_MIN_INLINE_SIZE;
mlx5_tx_dseg_ptr(txq, loc, &wqe->dseg[1],
dptr, dlen, olx);
++txq->wqe_ci;
--loc->wqe_free;
/* We have to store mbuf in elts.*/
- assert(MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(INLINE));
txq->elts[txq->elts_head++ & txq->elts_m] =
loc->mbuf;
--loc->elts_free;
* - Ethernet Segment, optional VLAN, no inline
* - Data Segment, pointer type
*/
+single_no_inline:
wqe = txq->wqes + (txq->wqe_ci & txq->wqe_m);
loc->wqe_last = wqe;
mlx5_tx_cseg_init(txq, loc, wqe, 3,
* if no inlining is configured, this is done
* by calling routine in a batch copy.
*/
- assert(!MLX5_TXOFF_CONFIG(INLINE));
+ MLX5_ASSERT(!MLX5_TXOFF_CONFIG(INLINE));
--loc->elts_free;
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Update sent data bytes counter. */
}
++loc->pkts_sent;
--pkts_n;
- /* Request CQE generation if limits are reached. */
- mlx5_tx_request_completion(txq, loc, false, olx);
if (unlikely(!pkts_n || !loc->elts_free || !loc->wqe_free))
return MLX5_TXCMP_CODE_EXIT;
loc->mbuf = *pkts++;
if (unlikely(ret != MLX5_TXCMP_CODE_SINGLE))
return ret;
}
- assert(false);
+ MLX5_ASSERT(false);
}
static __rte_always_inline enum mlx5_txcmp_code
ret = mlx5_tx_able_to_empw(txq, loc, olx, false);
if (ret == MLX5_TXCMP_CODE_SINGLE)
goto ordinary_send;
- assert(ret == MLX5_TXCMP_CODE_EMPW);
+ MLX5_ASSERT(ret == MLX5_TXCMP_CODE_EMPW);
for (;;) {
/* Optimize for inline/no inline eMPW send. */
ret = (MLX5_TXOFF_CONFIG(INLINE)) ?
if (ret != MLX5_TXCMP_CODE_SINGLE)
return ret;
/* The resources to send one packet should remain. */
- assert(loc->elts_free && loc->wqe_free);
+ MLX5_ASSERT(loc->elts_free && loc->wqe_free);
ordinary_send:
ret = mlx5_tx_burst_single_send(txq, pkts, pkts_n, loc, olx);
- assert(ret != MLX5_TXCMP_CODE_SINGLE);
+ MLX5_ASSERT(ret != MLX5_TXCMP_CODE_SINGLE);
if (ret != MLX5_TXCMP_CODE_EMPW)
return ret;
/* The resources to send one packet should remain. */
- assert(loc->elts_free && loc->wqe_free);
+ MLX5_ASSERT(loc->elts_free && loc->wqe_free);
}
}
enum mlx5_txcmp_code ret;
unsigned int part;
- assert(txq->elts_s >= (uint16_t)(txq->elts_head - txq->elts_tail));
- assert(txq->wqe_s >= (uint16_t)(txq->wqe_ci - txq->wqe_pi));
+ MLX5_ASSERT(txq->elts_s >= (uint16_t)(txq->elts_head - txq->elts_tail));
+ MLX5_ASSERT(txq->wqe_s >= (uint16_t)(txq->wqe_ci - txq->wqe_pi));
if (unlikely(!pkts_n))
return 0;
loc.pkts_sent = 0;
* - data inlining into WQEs, one packet may require multiple
* WQEBBs, the WQEs become the limiting factor.
*/
- assert(txq->elts_s >= (uint16_t)(txq->elts_head - txq->elts_tail));
+ MLX5_ASSERT(txq->elts_s >= (uint16_t)(txq->elts_head - txq->elts_tail));
loc.elts_free = txq->elts_s -
(uint16_t)(txq->elts_head - txq->elts_tail);
- assert(txq->wqe_s >= (uint16_t)(txq->wqe_ci - txq->wqe_pi));
+ MLX5_ASSERT(txq->wqe_s >= (uint16_t)(txq->wqe_ci - txq->wqe_pi));
loc.wqe_free = txq->wqe_s -
(uint16_t)(txq->wqe_ci - txq->wqe_pi);
if (unlikely(!loc.elts_free || !loc.wqe_free))
* per WQE, do it in dedicated routine.
*/
enter_send_multi:
- assert(loc.pkts_sent >= loc.pkts_copy);
+ MLX5_ASSERT(loc.pkts_sent >= loc.pkts_copy);
part = loc.pkts_sent - loc.pkts_copy;
if (!MLX5_TXOFF_CONFIG(INLINE) && part) {
/*
part, olx);
loc.pkts_copy = loc.pkts_sent;
}
- assert(pkts_n > loc.pkts_sent);
+ MLX5_ASSERT(pkts_n > loc.pkts_sent);
ret = mlx5_tx_burst_mseg(txq, pkts, pkts_n, &loc, olx);
if (!MLX5_TXOFF_CONFIG(INLINE))
loc.pkts_copy = loc.pkts_sent;
goto enter_send_tso;
}
/* We must not get here. Something is going wrong. */
- assert(false);
+ MLX5_ASSERT(false);
txq->stats.oerrors++;
break;
}
* in dedicated branch.
*/
enter_send_tso:
- assert(NB_SEGS(loc.mbuf) == 1);
- assert(pkts_n > loc.pkts_sent);
+ MLX5_ASSERT(NB_SEGS(loc.mbuf) == 1);
+ MLX5_ASSERT(pkts_n > loc.pkts_sent);
ret = mlx5_tx_burst_tso(txq, pkts, pkts_n, &loc, olx);
/*
* These returned code checks are supposed
goto enter_send_multi;
}
/* We must not get here. Something is going wrong. */
- assert(false);
+ MLX5_ASSERT(false);
txq->stats.oerrors++;
break;
}
* offloads are requested at SQ configuration time).
*/
enter_send_single:
- assert(pkts_n > loc.pkts_sent);
+ MLX5_ASSERT(pkts_n > loc.pkts_sent);
ret = mlx5_tx_burst_single(txq, pkts, pkts_n, &loc, olx);
/*
* These returned code checks are supposed
goto enter_send_tso;
}
/* We must not get here. Something is going wrong. */
- assert(false);
+ MLX5_ASSERT(false);
txq->stats.oerrors++;
break;
}
* - doorbell the hardware
* - copy the rest of mbufs to elts (if any)
*/
- assert(MLX5_TXOFF_CONFIG(INLINE) || loc.pkts_sent >= loc.pkts_copy);
+ MLX5_ASSERT(MLX5_TXOFF_CONFIG(INLINE) ||
+ loc.pkts_sent >= loc.pkts_copy);
/* Take a shortcut if nothing is sent. */
if (unlikely(loc.pkts_sent == loc.pkts_loop))
goto burst_exit;
+ /* Request CQE generation if limits are reached. */
+ mlx5_tx_request_completion(txq, &loc, olx);
/*
* Ring QP doorbell immediately after WQE building completion
* to improve latencies. The pure software related data treatment
* can be completed after doorbell. Tx CQEs for this SQ are
* processed in this thread only by the polling.
+ *
+ * The rdma core library can map doorbell register in two ways,
+ * depending on the environment variable "MLX5_SHUT_UP_BF":
+ *
+ * - as regular cached memory, the variable is either missing or
+ * set to zero. This type of mapping may cause the significant
+ * doorbell register writing latency and requires explicit
+ * memory write barrier to mitigate this issue and prevent
+ * write combining.
+ *
+ * - as non-cached memory, the variable is present and set to
+ * not "0" value. This type of mapping may cause performance
+ * impact under heavy loading conditions but the explicit write
+ * memory barrier is not required and it may improve core
+ * performance.
+ *
+ * - the legacy behaviour (prior 19.08 release) was to use some
+ * heuristics to decide whether write memory barrier should
+ * be performed. This behavior is supported with specifying
+ * tx_db_nc=2, write barrier is skipped if application
+ * provides the full recommended burst of packets, it
+ * supposes the next packets are coming and the write barrier
+ * will be issued on the next burst (after descriptor writing,
+ * at least).
*/
- mlx5_tx_dbrec_cond_wmb(txq, loc.wqe_last, 0);
+ mlx5_tx_dbrec_cond_wmb(txq, loc.wqe_last, !txq->db_nc &&
+ (!txq->db_heu || pkts_n % MLX5_TX_DEFAULT_BURST));
/* Not all of the mbufs may be stored into elts yet. */
part = MLX5_TXOFF_CONFIG(INLINE) ? 0 : loc.pkts_sent - loc.pkts_copy;
if (!MLX5_TXOFF_CONFIG(INLINE) && part) {
mlx5_tx_copy_elts(txq, pkts + loc.pkts_copy, part, olx);
loc.pkts_copy = loc.pkts_sent;
}
- assert(txq->elts_s >= (uint16_t)(txq->elts_head - txq->elts_tail));
- assert(txq->wqe_s >= (uint16_t)(txq->wqe_ci - txq->wqe_pi));
+ MLX5_ASSERT(txq->elts_s >= (uint16_t)(txq->elts_head - txq->elts_tail));
+ MLX5_ASSERT(txq->wqe_s >= (uint16_t)(txq->wqe_ci - txq->wqe_pi));
if (pkts_n > loc.pkts_sent) {
/*
* If burst size is large there might be no enough CQE
MLX5_TXOFF_CONFIG_INLINE | MLX5_TXOFF_CONFIG_VLAN |
MLX5_TXOFF_CONFIG_METADATA)
+/*
+ * Generate routines with Legacy Multi-Packet Write support.
+ * This mode is supported by ConnectX-4LX only and imposes
+ * offload limitations, not supported:
+ * - ACL/Flows (metadata are becoming meaningless)
+ * - WQE Inline headers
+ * - SRIOV (E-Switch offloads)
+ * - VLAN insertion
+ * - tunnel encapsulation/decapsulation
+ * - TSO
+ */
+MLX5_TXOFF_DECL(none_mpw,
+ MLX5_TXOFF_CONFIG_NONE | MLX5_TXOFF_CONFIG_EMPW |
+ MLX5_TXOFF_CONFIG_MPW)
+
+MLX5_TXOFF_DECL(mci_mpw,
+ MLX5_TXOFF_CONFIG_MULTI | MLX5_TXOFF_CONFIG_CSUM |
+ MLX5_TXOFF_CONFIG_INLINE | MLX5_TXOFF_CONFIG_EMPW |
+ MLX5_TXOFF_CONFIG_MPW)
+
+MLX5_TXOFF_DECL(mc_mpw,
+ MLX5_TXOFF_CONFIG_MULTI | MLX5_TXOFF_CONFIG_CSUM |
+ MLX5_TXOFF_CONFIG_EMPW | MLX5_TXOFF_CONFIG_MPW)
+
+MLX5_TXOFF_DECL(i_mpw,
+ MLX5_TXOFF_CONFIG_INLINE | MLX5_TXOFF_CONFIG_EMPW |
+ MLX5_TXOFF_CONFIG_MPW)
+
/*
* Array of declared and compiled Tx burst function and corresponding
* supported offloads set. The array is used to select the Tx burst
MLX5_TXOFF_CONFIG_INLINE |
MLX5_TXOFF_CONFIG_METADATA)
-
MLX5_TXOFF_INFO(mtv,
MLX5_TXOFF_CONFIG_MULTI | MLX5_TXOFF_CONFIG_TSO |
MLX5_TXOFF_CONFIG_VLAN |
MLX5_TXOFF_INFO(iv,
MLX5_TXOFF_CONFIG_INLINE | MLX5_TXOFF_CONFIG_VLAN |
MLX5_TXOFF_CONFIG_METADATA)
+
+MLX5_TXOFF_INFO(none_mpw,
+ MLX5_TXOFF_CONFIG_NONE | MLX5_TXOFF_CONFIG_EMPW |
+ MLX5_TXOFF_CONFIG_MPW)
+
+MLX5_TXOFF_INFO(mci_mpw,
+ MLX5_TXOFF_CONFIG_MULTI | MLX5_TXOFF_CONFIG_CSUM |
+ MLX5_TXOFF_CONFIG_INLINE | MLX5_TXOFF_CONFIG_EMPW |
+ MLX5_TXOFF_CONFIG_MPW)
+
+MLX5_TXOFF_INFO(mc_mpw,
+ MLX5_TXOFF_CONFIG_MULTI | MLX5_TXOFF_CONFIG_CSUM |
+ MLX5_TXOFF_CONFIG_EMPW | MLX5_TXOFF_CONFIG_MPW)
+
+MLX5_TXOFF_INFO(i_mpw,
+ MLX5_TXOFF_CONFIG_INLINE | MLX5_TXOFF_CONFIG_EMPW |
+ MLX5_TXOFF_CONFIG_MPW)
};
/**
"invalid WQE Data Segment size");
static_assert(MLX5_WQE_SIZE == 4 * MLX5_WSEG_SIZE,
"invalid WQE size");
- assert(priv);
+ MLX5_ASSERT(priv);
if (tx_offloads & DEV_TX_OFFLOAD_MULTI_SEGS) {
/* We should support Multi-Segment Packets. */
olx |= MLX5_TXOFF_CONFIG_MULTI;
if (config->mps == MLX5_MPW_ENHANCED &&
config->txq_inline_min <= 0) {
/*
- * The NIC supports Enhanced Multi-Packet Write.
- * We do not support legacy MPW due to its
- * hardware related problems, so we just ignore
- * legacy MLX5_MPW settings. There should be no
- * minimal required inline data.
+ * The NIC supports Enhanced Multi-Packet Write
+ * and does not require minimal inline data.
*/
olx |= MLX5_TXOFF_CONFIG_EMPW;
}
- if (tx_offloads & DEV_TX_OFFLOAD_MATCH_METADATA) {
+ if (rte_flow_dynf_metadata_avail()) {
/* We should support Flow metadata. */
olx |= MLX5_TXOFF_CONFIG_METADATA;
}
+ if (config->mps == MLX5_MPW) {
+ /*
+ * The NIC supports Legacy Multi-Packet Write.
+ * The MLX5_TXOFF_CONFIG_MPW controls the
+ * descriptor building method in combination
+ * with MLX5_TXOFF_CONFIG_EMPW.
+ */
+ if (!(olx & (MLX5_TXOFF_CONFIG_TSO |
+ MLX5_TXOFF_CONFIG_SWP |
+ MLX5_TXOFF_CONFIG_VLAN |
+ MLX5_TXOFF_CONFIG_METADATA)))
+ olx |= MLX5_TXOFF_CONFIG_EMPW |
+ MLX5_TXOFF_CONFIG_MPW;
+ }
/*
* Scan the routines table to find the minimal
* satisfying routine with requested offloads.
DRV_LOG(DEBUG, "\tVLANI (VLAN insertion)");
if (txoff_func[m].olx & MLX5_TXOFF_CONFIG_METADATA)
DRV_LOG(DEBUG, "\tMETAD (tx Flow metadata)");
- if (txoff_func[m].olx & MLX5_TXOFF_CONFIG_EMPW)
- DRV_LOG(DEBUG, "\tEMPW (Enhanced MPW)");
+ if (txoff_func[m].olx & MLX5_TXOFF_CONFIG_EMPW) {
+ if (txoff_func[m].olx & MLX5_TXOFF_CONFIG_MPW)
+ DRV_LOG(DEBUG, "\tMPW (Legacy MPW)");
+ else
+ DRV_LOG(DEBUG, "\tEMPW (Enhanced MPW)");
+ }
return txoff_func[m].func;
}
+
+/**
+ * DPDK callback to get the TX queue information
+ *
+ * @param dev
+ * Pointer to the device structure.
+ *
+ * @param tx_queue_id
+ * Tx queue identificator.
+ *
+ * @param qinfo
+ * Pointer to the TX queue information structure.
+ *
+ * @return
+ * None.
+ */
+
+void
+mlx5_txq_info_get(struct rte_eth_dev *dev, uint16_t tx_queue_id,
+ struct rte_eth_txq_info *qinfo)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_txq_data *txq = (*priv->txqs)[tx_queue_id];
+ struct mlx5_txq_ctrl *txq_ctrl =
+ container_of(txq, struct mlx5_txq_ctrl, txq);
+
+ if (!txq)
+ return;
+ qinfo->nb_desc = txq->elts_s;
+ qinfo->conf.tx_thresh.pthresh = 0;
+ qinfo->conf.tx_thresh.hthresh = 0;
+ qinfo->conf.tx_thresh.wthresh = 0;
+ qinfo->conf.tx_rs_thresh = 0;
+ qinfo->conf.tx_free_thresh = 0;
+ qinfo->conf.tx_deferred_start = txq_ctrl ? 0 : 1;
+ qinfo->conf.offloads = dev->data->dev_conf.txmode.offloads;
+}
+
+/**
+ * DPDK callback to get the TX packet burst mode information
+ *
+ * @param dev
+ * Pointer to the device structure.
+ *
+ * @param tx_queue_id
+ * Tx queue identificatior.
+ *
+ * @param mode
+ * Pointer to the burts mode information.
+ *
+ * @return
+ * 0 as success, -EINVAL as failure.
+ */
+
+int
+mlx5_tx_burst_mode_get(struct rte_eth_dev *dev,
+ uint16_t tx_queue_id __rte_unused,
+ struct rte_eth_burst_mode *mode)
+{
+ eth_tx_burst_t pkt_burst = dev->tx_pkt_burst;
+ unsigned int i, olx;
+
+ for (i = 0; i < RTE_DIM(txoff_func); i++) {
+ if (pkt_burst == txoff_func[i].func) {
+ olx = txoff_func[i].olx;
+ snprintf(mode->info, sizeof(mode->info),
+ "%s%s%s%s%s%s%s%s",
+ (olx & MLX5_TXOFF_CONFIG_EMPW) ?
+ ((olx & MLX5_TXOFF_CONFIG_MPW) ?
+ "Legacy MPW" : "Enhanced MPW") : "No MPW",
+ (olx & MLX5_TXOFF_CONFIG_MULTI) ?
+ " + MULTI" : "",
+ (olx & MLX5_TXOFF_CONFIG_TSO) ?
+ " + TSO" : "",
+ (olx & MLX5_TXOFF_CONFIG_SWP) ?
+ " + SWP" : "",
+ (olx & MLX5_TXOFF_CONFIG_CSUM) ?
+ " + CSUM" : "",
+ (olx & MLX5_TXOFF_CONFIG_INLINE) ?
+ " + INLINE" : "",
+ (olx & MLX5_TXOFF_CONFIG_VLAN) ?
+ " + VLAN" : "",
+ (olx & MLX5_TXOFF_CONFIG_METADATA) ?
+ " + METADATA" : "");
+ return 0;
+ }
+ }
+ return -EINVAL;
+}