return 0;
}
+static inline void
+txq_complete(struct txq *txq) __attribute__((always_inline));
+
/**
* Manage TX completions.
*
* @param txq
* Pointer to TX queue structure.
*/
-static void
+static inline void
txq_complete(struct txq *txq)
{
const unsigned int elts_n = txq->elts_n;
* Pointer to TX queue structure.
* @param wqe
* Pointer to the WQE to fill.
- * @param addr
- * Buffer data address.
+ * @param buf
+ * Buffer.
* @param length
* Packet length.
- * @param lkey
- * Memory region lkey.
- */
-static inline void
-mlx5_wqe_write(struct txq *txq, volatile union mlx5_wqe *wqe,
- uintptr_t addr, uint32_t length, uint32_t lkey)
-{
- wqe->wqe.ctrl.data[0] = htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND);
- wqe->wqe.ctrl.data[1] = htonl((txq->qp_num_8s) | 4);
- wqe->wqe.ctrl.data[3] = 0;
- wqe->inl.eseg.rsvd0 = 0;
- wqe->inl.eseg.rsvd1 = 0;
- wqe->inl.eseg.mss = 0;
- wqe->inl.eseg.rsvd2 = 0;
- wqe->wqe.eseg.inline_hdr_sz = htons(MLX5_ETH_INLINE_HEADER_SIZE);
- /* Copy the first 16 bytes into inline header. */
- rte_memcpy((uint8_t *)(uintptr_t)wqe->wqe.eseg.inline_hdr_start,
- (uint8_t *)(uintptr_t)addr,
- MLX5_ETH_INLINE_HEADER_SIZE);
- addr += MLX5_ETH_INLINE_HEADER_SIZE;
- length -= MLX5_ETH_INLINE_HEADER_SIZE;
- /* Store remaining data in data segment. */
- wqe->wqe.dseg.byte_count = htonl(length);
- wqe->wqe.dseg.lkey = lkey;
- wqe->wqe.dseg.addr = htonll(addr);
- /* Increment consumer index. */
- ++txq->wqe_ci;
-}
-
-/**
- * Write a regular WQE with VLAN.
*
- * @param txq
- * Pointer to TX queue structure.
- * @param wqe
- * Pointer to the WQE to fill.
- * @param addr
- * Buffer data address.
- * @param length
- * Packet length.
- * @param lkey
- * Memory region lkey.
- * @param vlan_tci
- * VLAN field to insert in packet.
+ * @return ds
+ * Number of DS elements consumed.
*/
-static inline void
-mlx5_wqe_write_vlan(struct txq *txq, volatile union mlx5_wqe *wqe,
- uintptr_t addr, uint32_t length, uint32_t lkey,
- uint16_t vlan_tci)
+static inline unsigned int
+mlx5_wqe_write(struct txq *txq, volatile union mlx5_wqe *wqe,
+ struct rte_mbuf *buf, uint32_t length)
{
- uint32_t vlan = htonl(0x81000000 | vlan_tci);
-
+ uintptr_t raw = (uintptr_t)&wqe->wqe.eseg.inline_hdr_start;
+ uint16_t ds;
+ uint16_t pkt_inline_sz = 16;
+ uintptr_t addr = rte_pktmbuf_mtod(buf, uintptr_t);
+ struct mlx5_wqe_data_seg *dseg = NULL;
+
+ assert(length >= 16);
+ /* Start the know and common part of the WQE structure. */
wqe->wqe.ctrl.data[0] = htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND);
- wqe->wqe.ctrl.data[1] = htonl((txq->qp_num_8s) | 4);
+ wqe->wqe.ctrl.data[2] = 0;
wqe->wqe.ctrl.data[3] = 0;
- wqe->inl.eseg.rsvd0 = 0;
- wqe->inl.eseg.rsvd1 = 0;
- wqe->inl.eseg.mss = 0;
- wqe->inl.eseg.rsvd2 = 0;
- wqe->wqe.eseg.inline_hdr_sz = htons(MLX5_ETH_VLAN_INLINE_HEADER_SIZE);
- /*
- * Copy 12 bytes of source & destination MAC address.
- * Copy 4 bytes of VLAN.
- * Copy 2 bytes of Ether type.
- */
- rte_memcpy((uint8_t *)(uintptr_t)wqe->wqe.eseg.inline_hdr_start,
- (uint8_t *)(uintptr_t)addr, 12);
- rte_memcpy((uint8_t *)((uintptr_t)wqe->wqe.eseg.inline_hdr_start + 12),
- &vlan, sizeof(vlan));
- rte_memcpy((uint8_t *)((uintptr_t)wqe->wqe.eseg.inline_hdr_start + 16),
- (uint8_t *)((uintptr_t)addr + 12), 2);
- addr += MLX5_ETH_VLAN_INLINE_HEADER_SIZE - sizeof(vlan);
- length -= MLX5_ETH_VLAN_INLINE_HEADER_SIZE - sizeof(vlan);
- /* Store remaining data in data segment. */
- wqe->wqe.dseg.byte_count = htonl(length);
- wqe->wqe.dseg.lkey = lkey;
- wqe->wqe.dseg.addr = htonll(addr);
- /* Increment consumer index. */
- ++txq->wqe_ci;
-}
-
-/**
- * Write a inline WQE.
- *
- * @param txq
- * Pointer to TX queue structure.
- * @param wqe
- * Pointer to the WQE to fill.
- * @param addr
- * Buffer data address.
- * @param length
- * Packet length.
- * @param lkey
- * Memory region lkey.
- */
-static inline void
-mlx5_wqe_write_inline(struct txq *txq, volatile union mlx5_wqe *wqe,
- uintptr_t addr, uint32_t length)
-{
- uint32_t size;
- uint16_t wqe_cnt = txq->wqe_n - 1;
- uint16_t wqe_ci = txq->wqe_ci + 1;
-
- /* Copy the first 16 bytes into inline header. */
- rte_memcpy((void *)(uintptr_t)wqe->inl.eseg.inline_hdr_start,
- (void *)(uintptr_t)addr,
- MLX5_ETH_INLINE_HEADER_SIZE);
- addr += MLX5_ETH_INLINE_HEADER_SIZE;
- length -= MLX5_ETH_INLINE_HEADER_SIZE;
- size = 3 + ((4 + length + 15) / 16);
- wqe->inl.byte_cnt = htonl(length | MLX5_INLINE_SEG);
- rte_memcpy((void *)(uintptr_t)&wqe->inl.data[0],
- (void *)addr, MLX5_WQE64_INL_DATA);
- addr += MLX5_WQE64_INL_DATA;
- length -= MLX5_WQE64_INL_DATA;
- while (length) {
- volatile union mlx5_wqe *wqe_next =
- &(*txq->wqes)[wqe_ci & wqe_cnt];
- uint32_t copy_bytes = (length > sizeof(*wqe)) ?
- sizeof(*wqe) :
- length;
-
- rte_mov64((uint8_t *)(uintptr_t)&wqe_next->data[0],
- (uint8_t *)addr);
- addr += copy_bytes;
- length -= copy_bytes;
- ++wqe_ci;
+ wqe->wqe.eseg.rsvd0 = 0;
+ wqe->wqe.eseg.rsvd1 = 0;
+ wqe->wqe.eseg.mss = 0;
+ wqe->wqe.eseg.rsvd2 = 0;
+ /* Start by copying the Ethernet Header. */
+ rte_mov16((uint8_t *)raw, (uint8_t *)addr);
+ length -= 16;
+ addr += 16;
+ /* Replace the Ethernet type by the VLAN if necessary. */
+ if (buf->ol_flags & PKT_TX_VLAN_PKT) {
+ uint32_t vlan = htonl(0x81000000 | buf->vlan_tci);
+
+ memcpy((uint8_t *)(raw + 16 - sizeof(vlan)),
+ &vlan, sizeof(vlan));
+ addr -= sizeof(vlan);
+ length += sizeof(vlan);
}
- assert(size < 64);
- wqe->inl.ctrl.data[0] = htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND);
- wqe->inl.ctrl.data[1] = htonl(txq->qp_num_8s | size);
- wqe->inl.ctrl.data[3] = 0;
- wqe->inl.eseg.rsvd0 = 0;
- wqe->inl.eseg.rsvd1 = 0;
- wqe->inl.eseg.mss = 0;
- wqe->inl.eseg.rsvd2 = 0;
- wqe->inl.eseg.inline_hdr_sz = htons(MLX5_ETH_INLINE_HEADER_SIZE);
- /* Increment consumer index. */
- txq->wqe_ci = wqe_ci;
-}
-
-/**
- * Write a inline WQE with VLAN.
- *
- * @param txq
- * Pointer to TX queue structure.
- * @param wqe
- * Pointer to the WQE to fill.
- * @param addr
- * Buffer data address.
- * @param length
- * Packet length.
- * @param lkey
- * Memory region lkey.
- * @param vlan_tci
- * VLAN field to insert in packet.
- */
-static inline void
-mlx5_wqe_write_inline_vlan(struct txq *txq, volatile union mlx5_wqe *wqe,
- uintptr_t addr, uint32_t length, uint16_t vlan_tci)
-{
- uint32_t size;
- uint32_t wqe_cnt = txq->wqe_n - 1;
- uint16_t wqe_ci = txq->wqe_ci + 1;
- uint32_t vlan = htonl(0x81000000 | vlan_tci);
-
- /*
- * Copy 12 bytes of source & destination MAC address.
- * Copy 4 bytes of VLAN.
- * Copy 2 bytes of Ether type.
- */
- rte_memcpy((uint8_t *)(uintptr_t)wqe->inl.eseg.inline_hdr_start,
- (uint8_t *)addr, 12);
- rte_memcpy((uint8_t *)(uintptr_t)wqe->inl.eseg.inline_hdr_start + 12,
- &vlan, sizeof(vlan));
- rte_memcpy((uint8_t *)(uintptr_t)wqe->inl.eseg.inline_hdr_start + 16,
- ((uint8_t *)addr + 12), 2);
- addr += MLX5_ETH_VLAN_INLINE_HEADER_SIZE - sizeof(vlan);
- length -= MLX5_ETH_VLAN_INLINE_HEADER_SIZE - sizeof(vlan);
- size = (sizeof(wqe->inl.ctrl.ctrl) +
- sizeof(wqe->inl.eseg) +
- sizeof(wqe->inl.byte_cnt) +
- length + 15) / 16;
- wqe->inl.byte_cnt = htonl(length | MLX5_INLINE_SEG);
- rte_memcpy((void *)(uintptr_t)&wqe->inl.data[0],
- (void *)addr, MLX5_WQE64_INL_DATA);
- addr += MLX5_WQE64_INL_DATA;
- length -= MLX5_WQE64_INL_DATA;
- while (length) {
- volatile union mlx5_wqe *wqe_next =
- &(*txq->wqes)[wqe_ci & wqe_cnt];
- uint32_t copy_bytes = (length > sizeof(*wqe)) ?
- sizeof(*wqe) :
- length;
-
- rte_mov64((uint8_t *)(uintptr_t)&wqe_next->data[0],
- (uint8_t *)addr);
- addr += copy_bytes;
- length -= copy_bytes;
- ++wqe_ci;
+ /* Inline if enough room. */
+ if (txq->max_inline != 0) {
+ uintptr_t end = (uintptr_t)&(*txq->wqes)[txq->wqe_n];
+ uint16_t max_inline = txq->max_inline * RTE_CACHE_LINE_SIZE;
+ uint16_t room;
+
+ raw += 16;
+ room = end - (uintptr_t)raw;
+ if (room > max_inline) {
+ uintptr_t addr_end = (addr + max_inline) &
+ ~(RTE_CACHE_LINE_SIZE - 1);
+ uint16_t copy_b = ((addr_end - addr) > length) ?
+ length :
+ (addr_end - addr);
+
+ rte_memcpy((void *)raw, (void *)addr, copy_b);
+ addr += copy_b;
+ length -= copy_b;
+ pkt_inline_sz += copy_b;
+ /* Sanity check. */
+ assert(addr <= addr_end);
+ }
+ /* Store the inlined packet size in the WQE. */
+ wqe->wqe.eseg.inline_hdr_sz = htons(pkt_inline_sz);
+ /*
+ * 2 DWORDs consumed by the WQE header + 1 DSEG +
+ * the size of the inline part of the packet.
+ */
+ ds = 2 + ((pkt_inline_sz - 2 + 15) / 16);
+ if (length > 0) {
+ dseg = (struct mlx5_wqe_data_seg *)
+ ((uintptr_t)wqe + (ds * 16));
+ if ((uintptr_t)dseg >= end)
+ dseg = (struct mlx5_wqe_data_seg *)
+ ((uintptr_t)&(*txq->wqes)[0]);
+ goto use_dseg;
+ }
+ } else {
+ /* Add the remaining packet as a simple ds. */
+ ds = 3;
+ /*
+ * No inline has been done in the packet, only the Ethernet
+ * Header as been stored.
+ */
+ wqe->wqe.eseg.inline_hdr_sz = htons(16);
+ dseg = (struct mlx5_wqe_data_seg *)
+ ((uintptr_t)wqe + (ds * 16));
+use_dseg:
+ *dseg = (struct mlx5_wqe_data_seg) {
+ .addr = htonll(addr),
+ .byte_count = htonl(length),
+ .lkey = txq_mp2mr(txq, txq_mb2mp(buf)),
+ };
+ ++ds;
}
- assert(size < 64);
- wqe->inl.ctrl.data[0] = htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND);
- wqe->inl.ctrl.data[1] = htonl(txq->qp_num_8s | size);
- wqe->inl.ctrl.data[3] = 0;
- wqe->inl.eseg.rsvd0 = 0;
- wqe->inl.eseg.rsvd1 = 0;
- wqe->inl.eseg.mss = 0;
- wqe->inl.eseg.rsvd2 = 0;
- wqe->inl.eseg.inline_hdr_sz = htons(MLX5_ETH_VLAN_INLINE_HEADER_SIZE);
- /* Increment consumer index. */
- txq->wqe_ci = wqe_ci;
+ wqe->wqe.ctrl.data[1] = htonl(txq->qp_num_8s | ds);
+ return ds;
}
/**
struct txq *txq = (struct txq *)dpdk_txq;
uint16_t elts_head = txq->elts_head;
const unsigned int elts_n = txq->elts_n;
- unsigned int i;
+ unsigned int i = 0;
+ unsigned int j = 0;
unsigned int max;
unsigned int comp;
- volatile union mlx5_wqe *wqe;
- struct rte_mbuf *buf;
+ volatile union mlx5_wqe *wqe = NULL;
if (unlikely(!pkts_n))
return 0;
- buf = pkts[0];
/* Prefetch first packet cacheline. */
tx_prefetch_cqe(txq, txq->cq_ci);
tx_prefetch_cqe(txq, txq->cq_ci + 1);
- rte_prefetch0(buf);
+ rte_prefetch0(*pkts);
/* Start processing. */
txq_complete(txq);
max = (elts_n - (elts_head - txq->elts_tail));
if (max > elts_n)
max -= elts_n;
- assert(max >= 1);
- assert(max <= elts_n);
- /* Always leave one free entry in the ring. */
- --max;
- if (max == 0)
- return 0;
- if (max > pkts_n)
- max = pkts_n;
- for (i = 0; (i != max); ++i) {
- unsigned int elts_head_next = (elts_head + 1) & (elts_n - 1);
- uintptr_t addr;
+ do {
+ struct rte_mbuf *buf = *(pkts++);
+ unsigned int elts_head_next;
uint32_t length;
- uint32_t lkey;
+ unsigned int segs_n = buf->nb_segs;
+ volatile struct mlx5_wqe_data_seg *dseg;
+ unsigned int ds = sizeof(*wqe) / 16;
+ /*
+ * Make sure there is enough room to store this packet and
+ * that one ring entry remains unused.
+ */
+ assert(segs_n);
+ if (max < segs_n + 1)
+ break;
+ max -= segs_n;
+ --pkts_n;
+ elts_head_next = (elts_head + 1) & (elts_n - 1);
wqe = &(*txq->wqes)[txq->wqe_ci & (txq->wqe_n - 1)];
- rte_prefetch0(wqe);
- if (i + 1 < max)
- rte_prefetch0(pkts[i + 1]);
- /* Retrieve buffer information. */
- addr = rte_pktmbuf_mtod(buf, uintptr_t);
+ tx_prefetch_wqe(txq, txq->wqe_ci);
+ tx_prefetch_wqe(txq, txq->wqe_ci + 1);
+ if (pkts_n)
+ rte_prefetch0(*pkts);
length = DATA_LEN(buf);
/* Update element. */
(*txq->elts)[elts_head] = buf;
/* Prefetch next buffer data. */
- if (i + 1 < max)
- rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 1],
+ if (pkts_n)
+ rte_prefetch0(rte_pktmbuf_mtod(*pkts,
volatile void *));
- /* Retrieve Memory Region key for this memory pool. */
- lkey = txq_mp2mr(txq, txq_mb2mp(buf));
- if (buf->ol_flags & PKT_TX_VLAN_PKT)
- mlx5_wqe_write_vlan(txq, wqe, addr, length, lkey,
- buf->vlan_tci);
- else
- mlx5_wqe_write(txq, wqe, addr, length, lkey);
- wqe->wqe.ctrl.data[2] = 0;
/* Should we enable HW CKSUM offload */
if (buf->ol_flags &
(PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM | PKT_TX_UDP_CKSUM)) {
} else {
wqe->wqe.eseg.cs_flags = 0;
}
+ ds = mlx5_wqe_write(txq, wqe, buf, length);
+ if (segs_n == 1)
+ goto skip_segs;
+ dseg = (volatile struct mlx5_wqe_data_seg *)
+ (((uintptr_t)wqe) + ds * 16);
+ while (--segs_n) {
+ /*
+ * 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(!(sizeof(*wqe) % sizeof(*dseg)));
+ if (!(ds % (sizeof(*wqe) / 16)))
+ dseg = (volatile void *)
+ &(*txq->wqes)[txq->wqe_ci++ &
+ (txq->wqe_n - 1)];
+ else
+ ++dseg;
+ ++ds;
+ buf = buf->next;
+ assert(buf);
+ /* Store segment information. */
+ dseg->byte_count = htonl(DATA_LEN(buf));
+ dseg->lkey = txq_mp2mr(txq, txq_mb2mp(buf));
+ dseg->addr = htonll(rte_pktmbuf_mtod(buf, uintptr_t));
+ (*txq->elts)[elts_head_next] = buf;
+ elts_head_next = (elts_head_next + 1) & (elts_n - 1);
#ifdef MLX5_PMD_SOFT_COUNTERS
- /* Increment sent bytes counter. */
- txq->stats.obytes += length;
-#endif
- elts_head = elts_head_next;
- buf = pkts[i + 1];
- }
- /* Take a shortcut if nothing must be sent. */
- if (unlikely(i == 0))
- return 0;
- /* Check whether completion threshold has been reached. */
- comp = txq->elts_comp + i;
- if (comp >= MLX5_TX_COMP_THRESH) {
- /* Request completion on last WQE. */
- wqe->wqe.ctrl.data[2] = htonl(8);
- /* Save elts_head in unused "immediate" field of WQE. */
- wqe->wqe.ctrl.data[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;
+ length += DATA_LEN(buf);
#endif
- /* Ring QP doorbell. */
- mlx5_tx_dbrec(txq);
- txq->elts_head = elts_head;
- return i;
-}
-
-/**
- * DPDK callback for TX with 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_inline(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
- struct txq *txq = (struct txq *)dpdk_txq;
- uint16_t elts_head = txq->elts_head;
- const unsigned int elts_n = txq->elts_n;
- unsigned int i;
- unsigned int max;
- unsigned int comp;
- volatile union mlx5_wqe *wqe;
- struct rte_mbuf *buf;
- unsigned int max_inline = txq->max_inline;
-
- if (unlikely(!pkts_n))
- return 0;
- buf = pkts[0];
- /* Prefetch first packet cacheline. */
- tx_prefetch_cqe(txq, txq->cq_ci);
- tx_prefetch_cqe(txq, txq->cq_ci + 1);
- rte_prefetch0(buf);
- /* Start processing. */
- txq_complete(txq);
- max = (elts_n - (elts_head - txq->elts_tail));
- if (max > elts_n)
- max -= elts_n;
- assert(max >= 1);
- assert(max <= elts_n);
- /* Always leave one free entry in the ring. */
- --max;
- if (max == 0)
- return 0;
- if (max > pkts_n)
- max = pkts_n;
- for (i = 0; (i != max); ++i) {
- unsigned int elts_head_next = (elts_head + 1) & (elts_n - 1);
- uintptr_t addr;
- uint32_t length;
- uint32_t lkey;
-
- wqe = &(*txq->wqes)[txq->wqe_ci & (txq->wqe_n - 1)];
- tx_prefetch_wqe(txq, txq->wqe_ci);
- tx_prefetch_wqe(txq, txq->wqe_ci + 1);
- if (i + 1 < max)
- rte_prefetch0(pkts[i + 1]);
- /* Should we enable HW CKSUM offload */
- if (buf->ol_flags &
- (PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM | PKT_TX_UDP_CKSUM)) {
- wqe->inl.eseg.cs_flags =
- MLX5_ETH_WQE_L3_CSUM |
- MLX5_ETH_WQE_L4_CSUM;
- } else {
- wqe->inl.eseg.cs_flags = 0;
+ ++j;
}
- /* Retrieve buffer information. */
- addr = rte_pktmbuf_mtod(buf, uintptr_t);
- length = DATA_LEN(buf);
- /* Update element. */
- (*txq->elts)[elts_head] = buf;
- /* Prefetch next buffer data. */
- if (i + 1 < max)
- rte_prefetch0(rte_pktmbuf_mtod(pkts[i + 1],
- volatile void *));
- if (length <= max_inline) {
- if (buf->ol_flags & PKT_TX_VLAN_PKT)
- mlx5_wqe_write_inline_vlan(txq, wqe,
- addr, length,
- buf->vlan_tci);
- else
- mlx5_wqe_write_inline(txq, wqe, addr, length);
- } else {
- /* Retrieve Memory Region key for this memory pool. */
- lkey = txq_mp2mr(txq, txq_mb2mp(buf));
- if (buf->ol_flags & PKT_TX_VLAN_PKT)
- mlx5_wqe_write_vlan(txq, wqe, addr, length,
- lkey, buf->vlan_tci);
- else
- mlx5_wqe_write(txq, wqe, addr, length, lkey);
- }
- wqe->inl.ctrl.data[2] = 0;
- elts_head = elts_head_next;
- buf = pkts[i + 1];
+ /* Update DS field in WQE. */
+ wqe->wqe.ctrl.data[1] &= htonl(0xffffffc0);
+ wqe->wqe.ctrl.data[1] |= htonl(ds & 0x3f);
+skip_segs:
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Increment sent bytes counter. */
txq->stats.obytes += length;
#endif
- }
+ /* Increment consumer index. */
+ txq->wqe_ci += (ds + 3) / 4;
+ elts_head = elts_head_next;
+ ++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. */
- comp = txq->elts_comp + i;
+ comp = txq->elts_comp + i + j;
if (comp >= MLX5_TX_COMP_THRESH) {
/* Request completion on last WQE. */
- wqe->inl.ctrl.data[2] = htonl(8);
+ wqe->wqe.ctrl.data[2] = htonl(8);
/* Save elts_head in unused "immediate" field of WQE. */
- wqe->inl.ctrl.data[3] = elts_head;
+ wqe->wqe.ctrl.data[3] = elts_head;
txq->elts_comp = 0;
} else {
txq->elts_comp = comp;
struct txq *txq = (struct txq *)dpdk_txq;
uint16_t elts_head = txq->elts_head;
const unsigned int elts_n = txq->elts_n;
- unsigned int i;
+ unsigned int i = 0;
+ unsigned int j = 0;
unsigned int max;
unsigned int comp;
struct mlx5_mpw mpw = {
.state = MLX5_MPW_STATE_CLOSED,
};
+ if (unlikely(!pkts_n))
+ return 0;
/* Prefetch first packet cacheline. */
tx_prefetch_cqe(txq, txq->cq_ci);
tx_prefetch_wqe(txq, txq->wqe_ci);
max = (elts_n - (elts_head - txq->elts_tail));
if (max > elts_n)
max -= elts_n;
- assert(max >= 1);
- assert(max <= elts_n);
- /* Always leave one free entry in the ring. */
- --max;
- if (max == 0)
- return 0;
- if (max > pkts_n)
- max = pkts_n;
- for (i = 0; (i != max); ++i) {
- struct rte_mbuf *buf = pkts[i];
- volatile struct mlx5_wqe_data_seg *dseg;
- unsigned int elts_head_next = (elts_head + 1) & (elts_n - 1);
- uintptr_t addr;
+ do {
+ struct rte_mbuf *buf = *(pkts++);
+ unsigned int elts_head_next;
uint32_t length;
+ unsigned int segs_n = buf->nb_segs;
uint32_t cs_flags = 0;
+ /*
+ * Make sure there is enough room to store this packet and
+ * that one ring entry remains unused.
+ */
+ assert(segs_n);
+ if (max < segs_n + 1)
+ break;
+ /* Do not bother with large packets MPW cannot handle. */
+ if (segs_n > MLX5_MPW_DSEG_MAX)
+ break;
+ max -= segs_n;
+ --pkts_n;
/* Should we enable HW CKSUM offload */
if (buf->ol_flags &
(PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM | PKT_TX_UDP_CKSUM))
cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
- /* Retrieve buffer information. */
- addr = rte_pktmbuf_mtod(buf, uintptr_t);
- length = DATA_LEN(buf);
- /* Update element. */
- (*txq->elts)[elts_head] = buf;
+ /* 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->mpw.eseg.cs_flags != cs_flags)))
mlx5_mpw_close(txq, &mpw);
if (mpw.state == MLX5_MPW_STATE_CLOSED) {
mlx5_mpw_new(txq, &mpw, length);
mpw.wqe->mpw.eseg.cs_flags = cs_flags;
}
- dseg = mpw.data.dseg[mpw.pkts_n];
- *dseg = (struct mlx5_wqe_data_seg){
- .byte_count = htonl(length),
- .lkey = txq_mp2mr(txq, txq_mb2mp(buf)),
- .addr = htonll(addr),
- };
- ++mpw.pkts_n;
+ /* 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;
+
+ elts_head_next = (elts_head + 1) & (elts_n - 1);
+ assert(buf);
+ (*txq->elts)[elts_head] = buf;
+ dseg = mpw.data.dseg[mpw.pkts_n];
+ addr = rte_pktmbuf_mtod(buf, uintptr_t);
+ *dseg = (struct mlx5_wqe_data_seg){
+ .byte_count = htonl(DATA_LEN(buf)),
+ .lkey = txq_mp2mr(txq, txq_mb2mp(buf)),
+ .addr = htonll(addr),
+ };
+ elts_head = elts_head_next;
+#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);
elts_head = elts_head_next;
/* 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. */
- comp = txq->elts_comp + i;
+ /* "j" includes both packets and segments. */
+ comp = txq->elts_comp + j;
if (comp >= MLX5_TX_COMP_THRESH) {
volatile union mlx5_wqe *wqe = mpw.wqe;
struct txq *txq = (struct txq *)dpdk_txq;
uint16_t elts_head = txq->elts_head;
const unsigned int elts_n = txq->elts_n;
- unsigned int i;
+ unsigned int i = 0;
+ unsigned int j = 0;
unsigned int max;
unsigned int comp;
- unsigned int inline_room = txq->max_inline;
+ unsigned int inline_room = txq->max_inline * RTE_CACHE_LINE_SIZE;
struct mlx5_mpw mpw = {
.state = MLX5_MPW_STATE_CLOSED,
};
+ if (unlikely(!pkts_n))
+ return 0;
/* Prefetch first packet cacheline. */
tx_prefetch_cqe(txq, txq->cq_ci);
tx_prefetch_wqe(txq, txq->wqe_ci);
max = (elts_n - (elts_head - txq->elts_tail));
if (max > elts_n)
max -= elts_n;
- assert(max >= 1);
- assert(max <= elts_n);
- /* Always leave one free entry in the ring. */
- --max;
- if (max == 0)
- return 0;
- if (max > pkts_n)
- max = pkts_n;
- for (i = 0; (i != max); ++i) {
- struct rte_mbuf *buf = pkts[i];
- unsigned int elts_head_next = (elts_head + 1) & (elts_n - 1);
+ do {
+ struct rte_mbuf *buf = *(pkts++);
+ unsigned int elts_head_next;
uintptr_t addr;
uint32_t length;
+ unsigned int segs_n = buf->nb_segs;
uint32_t cs_flags = 0;
+ /*
+ * Make sure there is enough room to store this packet and
+ * that one ring entry remains unused.
+ */
+ assert(segs_n);
+ if (max < segs_n + 1)
+ break;
+ /* Do not bother with large packets MPW cannot handle. */
+ if (segs_n > MLX5_MPW_DSEG_MAX)
+ break;
+ max -= segs_n;
+ --pkts_n;
/* Should we enable HW CKSUM offload */
if (buf->ol_flags &
(PKT_TX_IP_CKSUM | PKT_TX_TCP_CKSUM | PKT_TX_UDP_CKSUM))
cs_flags = MLX5_ETH_WQE_L3_CSUM | MLX5_ETH_WQE_L4_CSUM;
- /* Retrieve buffer information. */
- addr = rte_pktmbuf_mtod(buf, uintptr_t);
- length = DATA_LEN(buf);
- /* Update element. */
- (*txq->elts)[elts_head] = buf;
+ /* 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->mpw.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->mpw_inl.eseg.cs_flags != cs_flags)) {
mlx5_mpw_inline_close(txq, &mpw);
- inline_room = txq->max_inline;
+ inline_room =
+ txq->max_inline * RTE_CACHE_LINE_SIZE;
}
}
if (mpw.state == MLX5_MPW_STATE_CLOSED) {
- if (length > inline_room) {
+ if ((segs_n != 1) ||
+ (length > inline_room)) {
mlx5_mpw_new(txq, &mpw, length);
mpw.wqe->mpw.eseg.cs_flags = cs_flags;
} else {
mpw.wqe->mpw_inl.eseg.cs_flags = cs_flags;
}
}
+ /* Multi-segment packets must be alone in their MPW. */
+ assert((segs_n == 1) || (mpw.pkts_n == 0));
if (mpw.state == MLX5_MPW_STATE_OPENED) {
- volatile struct mlx5_wqe_data_seg *dseg;
-
- assert(inline_room == txq->max_inline);
- dseg = mpw.data.dseg[mpw.pkts_n];
- *dseg = (struct mlx5_wqe_data_seg){
- .byte_count = htonl(length),
- .lkey = txq_mp2mr(txq, txq_mb2mp(buf)),
- .addr = htonll(addr),
- };
- ++mpw.pkts_n;
+ 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;
+
+ elts_head_next =
+ (elts_head + 1) & (elts_n - 1);
+ assert(buf);
+ (*txq->elts)[elts_head] = buf;
+ dseg = mpw.data.dseg[mpw.pkts_n];
+ addr = rte_pktmbuf_mtod(buf, uintptr_t);
+ *dseg = (struct mlx5_wqe_data_seg){
+ .byte_count = htonl(DATA_LEN(buf)),
+ .lkey = txq_mp2mr(txq, txq_mb2mp(buf)),
+ .addr = htonll(addr),
+ };
+ elts_head = elts_head_next;
+#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 {
assert(mpw.state == MLX5_MPW_INL_STATE_OPENED);
assert(length <= inline_room);
+ assert(length == DATA_LEN(buf));
+ elts_head_next = (elts_head + 1) & (elts_n - 1);
+ addr = rte_pktmbuf_mtod(buf, uintptr_t);
+ (*txq->elts)[elts_head] = buf;
/* Maximum number of bytes before wrapping. */
max = ((uintptr_t)&(*txq->wqes)[txq->wqe_n] -
(uintptr_t)mpw.data.raw);
mpw.data.raw =
(volatile void *)&(*txq->wqes)[0];
++mpw.pkts_n;
+ ++j;
if (mpw.pkts_n == MLX5_MPW_DSEG_MAX) {
mlx5_mpw_inline_close(txq, &mpw);
- inline_room = txq->max_inline;
+ inline_room =
+ txq->max_inline * RTE_CACHE_LINE_SIZE;
} else {
inline_room -= length;
}
/* 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. */
- comp = txq->elts_comp + i;
+ /* "j" includes both packets and segments. */
+ comp = txq->elts_comp + j;
if (comp >= MLX5_TX_COMP_THRESH) {
volatile union mlx5_wqe *wqe = mpw.wqe;
mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
{
struct rxq *rxq = dpdk_rxq;
- unsigned int pkts_ret = 0;
- unsigned int i;
- unsigned int rq_ci = rxq->rq_ci;
- const unsigned int elts_n = rxq->elts_n;
- const unsigned int wqe_cnt = elts_n - 1;
+ const unsigned int wqe_cnt = rxq->elts_n - 1;
const unsigned int cqe_cnt = rxq->cqe_n - 1;
-
- for (i = 0; (i != pkts_n); ++i) {
+ const unsigned int sges_n = rxq->sges_n;
+ struct rte_mbuf *pkt = NULL;
+ struct rte_mbuf *seg = NULL;
+ volatile struct mlx5_cqe64 *cqe =
+ &(*rxq->cqes)[rxq->cq_ci & cqe_cnt].cqe64;
+ unsigned int i = 0;
+ unsigned int rq_ci = rxq->rq_ci << sges_n;
+ int len;
+
+ while (pkts_n) {
unsigned int idx = rq_ci & wqe_cnt;
- int len;
- struct rte_mbuf *rep;
- struct rte_mbuf *pkt;
volatile struct mlx5_wqe_data_seg *wqe = &(*rxq->wqes)[idx];
- volatile struct mlx5_cqe64 *cqe =
- &(*rxq->cqes)[rxq->cq_ci & cqe_cnt].cqe64;
+ struct rte_mbuf *rep = (*rxq->elts)[idx];
- pkt = (*rxq->elts)[idx];
+ if (pkt)
+ NEXT(seg) = rep;
+ seg = rep;
+ rte_prefetch0(seg);
rte_prefetch0(cqe);
+ rte_prefetch0(wqe);
rep = rte_mbuf_raw_alloc(rxq->mp);
if (unlikely(rep == NULL)) {
++rxq->stats.rx_nombuf;
+ if (!pkt) {
+ /*
+ * no buffers before we even started,
+ * bail out silently.
+ */
+ break;
+ }
+ while (pkt != seg) {
+ assert(pkt != (*rxq->elts)[idx]);
+ seg = NEXT(pkt);
+ rte_mbuf_refcnt_set(pkt, 0);
+ __rte_mbuf_raw_free(pkt);
+ pkt = seg;
+ }
break;
}
- SET_DATA_OFF(rep, RTE_PKTMBUF_HEADROOM);
- NB_SEGS(rep) = 1;
- PORT(rep) = rxq->port_id;
- NEXT(rep) = NULL;
- len = mlx5_rx_poll_len(rxq, cqe, cqe_cnt);
- if (unlikely(len == 0)) {
- rte_mbuf_refcnt_set(rep, 0);
- __rte_mbuf_raw_free(rep);
- break;
- }
- if (unlikely(len == -1)) {
- /* RX error, packet is likely too large. */
- rte_mbuf_refcnt_set(rep, 0);
- __rte_mbuf_raw_free(rep);
- ++rxq->stats.idropped;
- --i;
- goto skip;
+ if (!pkt) {
+ cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt].cqe64;
+ len = mlx5_rx_poll_len(rxq, cqe, cqe_cnt);
+ if (len == 0) {
+ rte_mbuf_refcnt_set(rep, 0);
+ __rte_mbuf_raw_free(rep);
+ break;
+ }
+ if (unlikely(len == -1)) {
+ /* RX error, packet is likely too large. */
+ rte_mbuf_refcnt_set(rep, 0);
+ __rte_mbuf_raw_free(rep);
+ ++rxq->stats.idropped;
+ goto skip;
+ }
+ pkt = seg;
+ assert(len >= (rxq->crc_present << 2));
+ /* Update packet information. */
+ pkt->packet_type = 0;
+ pkt->ol_flags = 0;
+ if (rxq->csum | rxq->csum_l2tun | rxq->vlan_strip |
+ rxq->crc_present) {
+ if (rxq->csum) {
+ pkt->packet_type =
+ rxq_cq_to_pkt_type(cqe);
+ pkt->ol_flags =
+ rxq_cq_to_ol_flags(rxq, cqe);
+ }
+ if (cqe->l4_hdr_type_etc &
+ MLX5_CQE_VLAN_STRIPPED) {
+ pkt->ol_flags |= PKT_RX_VLAN_PKT |
+ PKT_RX_VLAN_STRIPPED;
+ pkt->vlan_tci = ntohs(cqe->vlan_info);
+ }
+ if (rxq->crc_present)
+ len -= ETHER_CRC_LEN;
+ }
+ PKT_LEN(pkt) = len;
}
+ DATA_LEN(rep) = DATA_LEN(seg);
+ PKT_LEN(rep) = PKT_LEN(seg);
+ SET_DATA_OFF(rep, DATA_OFF(seg));
+ NB_SEGS(rep) = NB_SEGS(seg);
+ PORT(rep) = PORT(seg);
+ NEXT(rep) = NULL;
+ (*rxq->elts)[idx] = rep;
/*
* Fill NIC descriptor with the new buffer. The lkey and size
* of the buffers are already known, only the buffer address
* changes.
*/
- wqe->addr = htonll((uintptr_t)rep->buf_addr +
- RTE_PKTMBUF_HEADROOM);
- (*rxq->elts)[idx] = rep;
- /* Update pkt information. */
- if (rxq->csum | rxq->csum_l2tun | rxq->vlan_strip |
- rxq->crc_present) {
- if (rxq->csum) {
- pkt->packet_type = rxq_cq_to_pkt_type(cqe);
- pkt->ol_flags = rxq_cq_to_ol_flags(rxq, cqe);
- }
- if (cqe->l4_hdr_type_etc & MLX5_CQE_VLAN_STRIPPED) {
- pkt->ol_flags |= PKT_RX_VLAN_PKT |
- PKT_RX_VLAN_STRIPPED;
- pkt->vlan_tci = ntohs(cqe->vlan_info);
- }
- if (rxq->crc_present)
- len -= ETHER_CRC_LEN;
+ wqe->addr = htonll(rte_pktmbuf_mtod(rep, uintptr_t));
+ if (len > DATA_LEN(seg)) {
+ len -= DATA_LEN(seg);
+ ++NB_SEGS(pkt);
+ ++rq_ci;
+ continue;
}
- PKT_LEN(pkt) = len;
- DATA_LEN(pkt) = len;
+ DATA_LEN(seg) = len;
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Increment bytes counter. */
- rxq->stats.ibytes += len;
+ rxq->stats.ibytes += PKT_LEN(pkt);
#endif
/* Return packet. */
*(pkts++) = pkt;
- ++pkts_ret;
+ pkt = NULL;
+ --pkts_n;
+ ++i;
skip:
+ /* Align consumer index to the next stride. */
+ rq_ci >>= sges_n;
++rq_ci;
+ rq_ci <<= sges_n;
}
- if (unlikely((i == 0) && (rq_ci == rxq->rq_ci)))
+ if (unlikely((i == 0) && ((rq_ci >> sges_n) == rxq->rq_ci)))
return 0;
- /* Repost WRs. */
-#ifdef DEBUG_RECV
- DEBUG("%p: reposting %u WRs", (void *)rxq, i);
-#endif
/* Update the consumer index. */
- rxq->rq_ci = rq_ci;
+ rxq->rq_ci = rq_ci >> sges_n;
rte_wmb();
*rxq->cq_db = htonl(rxq->cq_ci);
rte_wmb();
*rxq->rq_db = htonl(rxq->rq_ci);
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Increment packets counter. */
- rxq->stats.ipackets += pkts_ret;
+ rxq->stats.ipackets += i;
#endif
- return pkts_ret;
+ return i;
}
/**
git.droids-corp.org / dpdk.git / blobdiff