-/*-
- * BSD LICENSE
- *
- * Copyright 2015 6WIND S.A.
- * Copyright 2015 Mellanox.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of 6WIND S.A. nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright 2015 6WIND S.A.
+ * Copyright 2015-2019 Mellanox Technologies, Ltd
*/
-#include <assert.h>
#include <stdint.h>
#include <string.h>
#include <stdlib.h>
-/* Verbs header. */
-/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */
-#ifdef PEDANTIC
-#pragma GCC diagnostic ignored "-Wpedantic"
-#endif
-#include <infiniband/verbs.h>
-#include <infiniband/mlx5_hw.h>
-#include <infiniband/arch.h>
-#ifdef PEDANTIC
-#pragma GCC diagnostic error "-Wpedantic"
-#endif
-
-/* DPDK headers don't like -pedantic. */
-#ifdef PEDANTIC
-#pragma GCC diagnostic ignored "-Wpedantic"
-#endif
#include <rte_mbuf.h>
#include <rte_mempool.h>
#include <rte_prefetch.h>
#include <rte_common.h>
#include <rte_branch_prediction.h>
#include <rte_ether.h>
-#ifdef PEDANTIC
-#pragma GCC diagnostic error "-Wpedantic"
-#endif
+#include <rte_cycles.h>
+#include <rte_flow.h>
+
+#include <mlx5_prm.h>
+#include <mlx5_common.h>
+#include "mlx5_autoconf.h"
+#include "mlx5_defs.h"
#include "mlx5.h"
+#include "mlx5_mr.h"
#include "mlx5_utils.h"
#include "mlx5_rxtx.h"
-#include "mlx5_autoconf.h"
-#include "mlx5_defs.h"
-#include "mlx5_prm.h"
-
-static inline int
-check_cqe(volatile struct mlx5_cqe *cqe,
- unsigned int cqes_n, const uint16_t ci)
- __attribute__((always_inline));
-
-static inline void
-txq_complete(struct txq *txq) __attribute__((always_inline));
-
-static inline uint32_t
-txq_mp2mr(struct txq *txq, struct rte_mempool *mp)
- __attribute__((always_inline));
-
-static inline void
-mlx5_tx_dbrec(struct txq *txq, volatile struct mlx5_wqe *wqe)
- __attribute__((always_inline));
-
-static inline uint32_t
-rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe)
- __attribute__((always_inline));
-
-static inline int
-mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe *cqe,
- uint16_t cqe_cnt, uint32_t *rss_hash)
- __attribute__((always_inline));
-
-static inline uint32_t
-rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe *cqe)
- __attribute__((always_inline));
-
-#ifndef NDEBUG
+#include "mlx5_rx.h"
+#include "mlx5_tx.h"
+
+/* static asserts */
+static_assert(MLX5_CQE_STATUS_HW_OWN < 0, "Must be negative value");
+static_assert(MLX5_CQE_STATUS_SW_OWN < 0, "Must be negative value");
+static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
+ (sizeof(uint16_t) +
+ sizeof(rte_v128u32_t)),
+ "invalid Ethernet Segment data size");
+static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
+ (sizeof(uint16_t) +
+ sizeof(struct rte_vlan_hdr) +
+ 2 * RTE_ETHER_ADDR_LEN),
+ "invalid Ethernet Segment data size");
+static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
+ (sizeof(uint16_t) +
+ sizeof(rte_v128u32_t)),
+ "invalid Ethernet Segment data size");
+static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
+ (sizeof(uint16_t) +
+ sizeof(struct rte_vlan_hdr) +
+ 2 * RTE_ETHER_ADDR_LEN),
+ "invalid Ethernet Segment data size");
+static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
+ (sizeof(uint16_t) +
+ sizeof(rte_v128u32_t)),
+ "invalid Ethernet Segment data size");
+static_assert(MLX5_ESEG_MIN_INLINE_SIZE ==
+ (sizeof(uint16_t) +
+ sizeof(struct rte_vlan_hdr) +
+ 2 * RTE_ETHER_ADDR_LEN),
+ "invalid Ethernet Segment data size");
+static_assert(MLX5_DSEG_MIN_INLINE_SIZE ==
+ (2 * RTE_ETHER_ADDR_LEN),
+ "invalid Data Segment data size");
+static_assert(MLX5_EMPW_MIN_PACKETS >= 2, "invalid min size");
+static_assert(MLX5_EMPW_MIN_PACKETS >= 2, "invalid min size");
+static_assert((sizeof(struct rte_vlan_hdr) +
+ sizeof(struct rte_ether_hdr)) ==
+ MLX5_ESEG_MIN_INLINE_SIZE,
+ "invalid min inline data size");
+static_assert(MLX5_WQE_SIZE_MAX / MLX5_WSEG_SIZE <=
+ MLX5_DSEG_MAX, "invalid WQE max size");
+static_assert(MLX5_WQE_CSEG_SIZE == MLX5_WSEG_SIZE,
+ "invalid WQE Control Segment size");
+static_assert(MLX5_WQE_ESEG_SIZE == MLX5_WSEG_SIZE,
+ "invalid WQE Ethernet Segment size");
+static_assert(MLX5_WQE_DSEG_SIZE == MLX5_WSEG_SIZE,
+ "invalid WQE Data Segment size");
+static_assert(MLX5_WQE_SIZE == 4 * MLX5_WSEG_SIZE,
+ "invalid WQE size");
+
+uint32_t mlx5_ptype_table[] __rte_cache_aligned = {
+ [0xff] = RTE_PTYPE_ALL_MASK, /* Last entry for errored packet. */
+};
+
+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;
/**
- * Verify or set magic value in CQE.
+ * Build a table to translate Rx completion flags to packet type.
*
- * @param cqe
- * Pointer to CQE.
- *
- * @return
- * 0 the first time.
+ * @note: fix mlx5_dev_supported_ptypes_get() if any change here.
*/
-static inline int
-check_cqe_seen(volatile struct mlx5_cqe *cqe)
+void
+mlx5_set_ptype_table(void)
{
- static const uint8_t magic[] = "seen";
- volatile uint8_t (*buf)[sizeof(cqe->rsvd0)] = &cqe->rsvd0;
- int ret = 1;
unsigned int i;
+ uint32_t (*p)[RTE_DIM(mlx5_ptype_table)] = &mlx5_ptype_table;
- for (i = 0; i < sizeof(magic) && i < sizeof(*buf); ++i)
- if (!ret || (*buf)[i] != magic[i]) {
- ret = 0;
- (*buf)[i] = magic[i];
- }
- return ret;
-}
-
-#endif /* NDEBUG */
-
-/**
- * Check whether CQE is valid.
- *
- * @param cqe
- * Pointer to CQE.
- * @param cqes_n
- * Size of completion queue.
- * @param ci
- * Consumer index.
- *
- * @return
- * 0 on success, 1 on failure.
- */
-static inline int
-check_cqe(volatile struct mlx5_cqe *cqe,
- unsigned int cqes_n, const uint16_t ci)
-{
- uint16_t idx = ci & cqes_n;
- uint8_t op_own = cqe->op_own;
- uint8_t op_owner = MLX5_CQE_OWNER(op_own);
- uint8_t op_code = MLX5_CQE_OPCODE(op_own);
-
- if (unlikely((op_owner != (!!(idx))) || (op_code == MLX5_CQE_INVALID)))
- return 1; /* No CQE. */
-#ifndef NDEBUG
- if ((op_code == MLX5_CQE_RESP_ERR) ||
- (op_code == MLX5_CQE_REQ_ERR)) {
- volatile struct mlx5_err_cqe *err_cqe = (volatile void *)cqe;
- uint8_t syndrome = err_cqe->syndrome;
-
- if ((syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR) ||
- (syndrome == MLX5_CQE_SYNDROME_REMOTE_ABORTED_ERR))
- return 0;
- if (!check_cqe_seen(cqe))
- ERROR("unexpected CQE error %u (0x%02x)"
- " syndrome 0x%02x",
- op_code, op_code, syndrome);
- return 1;
- } else if ((op_code != MLX5_CQE_RESP_SEND) &&
- (op_code != MLX5_CQE_REQ)) {
- if (!check_cqe_seen(cqe))
- ERROR("unexpected CQE opcode %u (0x%02x)",
- op_code, op_code);
- return 1;
- }
-#endif /* NDEBUG */
- return 0;
-}
-
-/**
- * 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 txq *txq, uint16_t ci)
-{
- ci &= ((1 << txq->wqe_n) - 1);
- return (uintptr_t *)((uintptr_t)txq->wqes + ci * MLX5_WQE_SIZE);
-}
-
-/**
- * Manage TX completions.
- *
- * When sending a burst, mlx5_tx_burst() posts several WRs.
- *
- * @param txq
- * Pointer to TX queue structure.
- */
-static inline void
-txq_complete(struct txq *txq)
-{
- const unsigned int elts_n = 1 << txq->elts_n;
- const unsigned int cqe_n = 1 << txq->cqe_n;
- const unsigned int cqe_cnt = cqe_n - 1;
- uint16_t elts_free = txq->elts_tail;
- uint16_t elts_tail;
- uint16_t cq_ci = txq->cq_ci;
- volatile struct mlx5_cqe *cqe = NULL;
- volatile struct mlx5_wqe_ctrl *ctrl;
-
- do {
- volatile struct mlx5_cqe *tmp;
-
- tmp = &(*txq->cqes)[cq_ci & cqe_cnt];
- if (check_cqe(tmp, cqe_n, cq_ci))
- break;
- cqe = tmp;
-#ifndef NDEBUG
- if (MLX5_CQE_FORMAT(cqe->op_own) == MLX5_COMPRESSED) {
- if (!check_cqe_seen(cqe))
- ERROR("unexpected compressed CQE, TX stopped");
- return;
- }
- if ((MLX5_CQE_OPCODE(cqe->op_own) == MLX5_CQE_RESP_ERR) ||
- (MLX5_CQE_OPCODE(cqe->op_own) == MLX5_CQE_REQ_ERR)) {
- if (!check_cqe_seen(cqe))
- ERROR("unexpected error CQE, TX stopped");
- return;
- }
-#endif /* NDEBUG */
- ++cq_ci;
- } while (1);
- if (unlikely(cqe == NULL))
- return;
- ctrl = (volatile struct mlx5_wqe_ctrl *)
- tx_mlx5_wqe(txq, ntohs(cqe->wqe_counter));
- elts_tail = ctrl->ctrl3;
- assert(elts_tail < (1 << txq->wqe_n));
- /* Free buffers. */
- while (elts_free != elts_tail) {
- struct rte_mbuf *elt = (*txq->elts)[elts_free];
- unsigned int elts_free_next =
- (elts_free + 1) & (elts_n - 1);
- struct rte_mbuf *elt_next = (*txq->elts)[elts_free_next];
-
-#ifndef NDEBUG
- /* Poisoning. */
- memset(&(*txq->elts)[elts_free],
- 0x66,
- sizeof((*txq->elts)[elts_free]));
-#endif
- RTE_MBUF_PREFETCH_TO_FREE(elt_next);
- /* Only one segment needs to be freed. */
- rte_pktmbuf_free_seg(elt);
- elts_free = elts_free_next;
- }
- txq->cq_ci = cq_ci;
- txq->elts_tail = elts_tail;
- /* Update the consumer index. */
- rte_wmb();
- *txq->cq_db = htonl(cq_ci);
-}
-
-/**
- * Get Memory Pool (MP) from mbuf. If mbuf is indirect, the pool from which
- * the cloned mbuf is allocated is returned instead.
- *
- * @param buf
- * Pointer to mbuf.
- *
- * @return
- * Memory pool where data is located for given mbuf.
- */
-static struct rte_mempool *
-txq_mb2mp(struct rte_mbuf *buf)
-{
- if (unlikely(RTE_MBUF_INDIRECT(buf)))
- return rte_mbuf_from_indirect(buf)->pool;
- return buf->pool;
+ /* Last entry must not be overwritten, reserved for errored packet. */
+ for (i = 0; i < RTE_DIM(mlx5_ptype_table) - 1; ++i)
+ (*p)[i] = RTE_PTYPE_UNKNOWN;
+ /*
+ * The index to the array should have:
+ * bit[1:0] = l3_hdr_type
+ * bit[4:2] = l4_hdr_type
+ * bit[5] = ip_frag
+ * bit[6] = tunneled
+ * bit[7] = outer_l3_type
+ */
+ /* L2 */
+ (*p)[0x00] = RTE_PTYPE_L2_ETHER;
+ /* L3 */
+ (*p)[0x01] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG;
+ (*p)[0x02] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG;
+ /* Fragmented */
+ (*p)[0x21] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_FRAG;
+ (*p)[0x22] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_FRAG;
+ /* TCP */
+ (*p)[0x05] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x06] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x0d] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x0e] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x11] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x12] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ /* UDP */
+ (*p)[0x09] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP;
+ (*p)[0x0a] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP;
+ /* Repeat with outer_l3_type being set. Just in case. */
+ (*p)[0x81] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG;
+ (*p)[0x82] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_NONFRAG;
+ (*p)[0xa1] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_FRAG;
+ (*p)[0xa2] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_FRAG;
+ (*p)[0x85] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x86] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x8d] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x8e] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x91] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x92] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_TCP;
+ (*p)[0x89] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP;
+ (*p)[0x8a] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_L4_UDP;
+ /* Tunneled - L3 */
+ (*p)[0x40] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN;
+ (*p)[0x41] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG;
+ (*p)[0x42] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG;
+ (*p)[0xc0] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN;
+ (*p)[0xc1] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG;
+ (*p)[0xc2] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_NONFRAG;
+ /* Tunneled - Fragmented */
+ (*p)[0x61] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG;
+ (*p)[0x62] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG;
+ (*p)[0xe1] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG;
+ (*p)[0xe2] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_FRAG;
+ /* Tunneled - TCP */
+ (*p)[0x45] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0x46] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0x4d] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0x4e] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0x51] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0x52] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0xc5] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0xc6] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0xcd] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0xce] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0xd1] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ (*p)[0xd2] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_TCP;
+ /* Tunneled - UDP */
+ (*p)[0x49] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP;
+ (*p)[0x4a] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP;
+ (*p)[0xc9] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP;
+ (*p)[0xca] = RTE_PTYPE_L2_ETHER | RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN |
+ RTE_PTYPE_INNER_L4_UDP;
}
/**
- * Get Memory Region (MR) <-> Memory Pool (MP) association from txq->mp2mr[].
- * Add MP to txq->mp2mr[] if it's not registered yet. If mp2mr[] is full,
- * remove an entry first.
- *
- * @param txq
- * Pointer to TX queue structure.
- * @param[in] mp
- * Memory Pool for which a Memory Region lkey must be returned.
- *
- * @return
- * mr->lkey on success, (uint32_t)-1 on failure.
+ * Build a table to translate packet to checksum type of Verbs.
*/
-static inline uint32_t
-txq_mp2mr(struct txq *txq, struct rte_mempool *mp)
+void
+mlx5_set_cksum_table(void)
{
unsigned int i;
- uint32_t lkey = (uint32_t)-1;
-
- for (i = 0; (i != RTE_DIM(txq->mp2mr)); ++i) {
- if (unlikely(txq->mp2mr[i].mp == NULL)) {
- /* Unknown MP, add a new MR for it. */
- break;
- }
- if (txq->mp2mr[i].mp == mp) {
- assert(txq->mp2mr[i].lkey != (uint32_t)-1);
- assert(htonl(txq->mp2mr[i].mr->lkey) ==
- txq->mp2mr[i].lkey);
- lkey = txq->mp2mr[i].lkey;
- break;
- }
- }
- if (unlikely(lkey == (uint32_t)-1))
- lkey = txq_mp2mr_reg(txq, mp, i);
- return lkey;
-}
-
-/**
- * Ring TX queue doorbell.
- *
- * @param txq
- * Pointer to TX queue structure.
- * @param wqe
- * Pointer to the last WQE posted in the NIC.
- */
-static inline void
-mlx5_tx_dbrec(struct txq *txq, volatile struct mlx5_wqe *wqe)
-{
- uint64_t *dst = (uint64_t *)((uintptr_t)txq->bf_reg);
- volatile uint64_t *src = ((volatile uint64_t *)wqe);
-
- rte_wmb();
- *txq->qp_db = htonl(txq->wqe_ci);
- /* Ensure ordering between DB record and BF copy. */
- rte_wmb();
- *dst = *src;
-}
-
-/**
- * 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 txq *txq = (struct txq *)dpdk_txq;
- uint16_t elts_head = txq->elts_head;
- const unsigned int elts_n = 1 << txq->elts_n;
- unsigned int i = 0;
- unsigned int j = 0;
- unsigned int max;
- unsigned int comp;
- volatile struct mlx5_wqe_v *wqe = NULL;
- unsigned int segs_n = 0;
- struct rte_mbuf *buf = NULL;
- uint8_t *raw;
-
- if (unlikely(!pkts_n))
- return 0;
- /* Prefetch first packet cacheline. */
- rte_prefetch0(*pkts);
- /* Start processing. */
- txq_complete(txq);
- max = (elts_n - (elts_head - txq->elts_tail));
- if (max > elts_n)
- max -= elts_n;
- do {
- volatile rte_v128u32_t *dseg = NULL;
- uint32_t length;
- unsigned int ds = 0;
- uintptr_t addr;
- uint64_t naddr;
- uint16_t pkt_inline_sz = MLX5_WQE_DWORD_SIZE;
- uint16_t ehdr;
- uint8_t cs_flags = 0;
-#ifdef MLX5_PMD_SOFT_COUNTERS
- uint32_t total_length = 0;
-#endif
-
- /* first_seg */
- buf = *(pkts++);
- 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 < segs_n + 1)
- break;
- max -= segs_n;
- --segs_n;
- if (!segs_n)
- --pkts_n;
- 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 > 1)
- rte_prefetch0(*pkts);
- 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
- assert(length >= MLX5_WQE_DWORD_SIZE);
- /* Update element. */
- (*txq->elts)[elts_head] = buf;
- elts_head = (elts_head + 1) & (elts_n - 1);
- /* Prefetch next buffer data. */
- if (pkts_n > 1) {
- volatile void *pkt_addr;
-
- pkt_addr = rte_pktmbuf_mtod(*pkts, volatile void *);
- rte_prefetch0(pkt_addr);
- }
- /* 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;
- }
- raw = ((uint8_t *)(uintptr_t)wqe) + 2 * MLX5_WQE_DWORD_SIZE;
- /*
- * Start by copying the Ethernet header minus the first two
- * bytes which will be appended at the end of the Ethernet
- * segment.
- */
- memcpy((uint8_t *)raw, ((uint8_t *)addr) + 2, 16);
- length -= MLX5_WQE_DWORD_SIZE;
- addr += MLX5_WQE_DWORD_SIZE;
- /* 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 + MLX5_WQE_DWORD_SIZE - 2 -
- sizeof(vlan)),
- &vlan, sizeof(vlan));
- addr -= sizeof(vlan);
- length += sizeof(vlan);
- }
- /* Inline if enough room. */
- if (txq->max_inline != 0) {
- uintptr_t end = (uintptr_t)
- (((uintptr_t)txq->wqes) +
- (1 << txq->wqe_n) * MLX5_WQE_SIZE);
- uint16_t max_inline =
- txq->max_inline * RTE_CACHE_LINE_SIZE;
- uint16_t room;
-
- /*
- * raw starts two bytes before the boundary to
- * continue the above copy of packet data.
- */
- raw += MLX5_WQE_DWORD_SIZE - 2;
- 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);
- }
- /*
- * 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) {
- dseg = (volatile rte_v128u32_t *)
- ((uintptr_t)wqe +
- (ds * MLX5_WQE_DWORD_SIZE));
- if ((uintptr_t)dseg >= end)
- dseg = (volatile rte_v128u32_t *)
- txq->wqes;
- goto use_dseg;
- } else if (!segs_n) {
- goto next_pkt;
- } else {
- /* dseg will be advance as part of next_seg */
- dseg = (volatile rte_v128u32_t *)
- ((uintptr_t)wqe +
- ((ds - 1) * MLX5_WQE_DWORD_SIZE));
- goto next_seg;
- }
- } 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. */
- naddr = htonll(addr);
- *dseg = (rte_v128u32_t){
- htonl(length),
- txq_mp2mr(txq, txq_mb2mp(buf)),
- naddr,
- naddr >> 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))) {
- unsigned int n = (txq->wqe_ci + ((ds + 3) / 4)) &
- ((1 << txq->wqe_n) - 1);
-
- dseg = (volatile rte_v128u32_t *)
- tx_mlx5_wqe(txq, n);
- rte_prefetch0(tx_mlx5_wqe(txq, n + 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. */
- naddr = htonll(rte_pktmbuf_mtod(buf, uintptr_t));
- *dseg = (rte_v128u32_t){
- htonl(length),
- txq_mp2mr(txq, txq_mb2mp(buf)),
- naddr,
- naddr >> 32,
- };
- (*txq->elts)[elts_head] = buf;
- elts_head = (elts_head + 1) & (elts_n - 1);
- ++j;
- --segs_n;
- if (segs_n)
- goto next_seg;
- else
- --pkts_n;
-next_pkt:
- ++i;
- /* Initialize known and common part of the WQE structure. */
- wqe->ctrl = (rte_v128u32_t){
- htonl((txq->wqe_ci << 8) | MLX5_OPCODE_SEND),
- htonl(txq->qp_num_8s | ds),
- 0,
- 0,
- };
- wqe->eseg = (rte_v128u32_t){
- 0,
- cs_flags,
- 0,
- (ehdr << 16) | htons(pkt_inline_sz),
- };
- txq->wqe_ci += (ds + 3) / 4;
-#ifdef MLX5_PMD_SOFT_COUNTERS
- /* Increment sent bytes counter. */
- txq->stats.obytes += total_length;
-#endif
- } 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;
- if (comp >= MLX5_TX_COMP_THRESH) {
- volatile struct mlx5_wqe_ctrl *w =
- (volatile struct mlx5_wqe_ctrl *)wqe;
-
- /* Request completion on last WQE. */
- w->ctrl2 = htonl(8);
- /* Save elts_head in unused "immediate" field of WQE. */
- w->ctrl3 = 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 *)wqe);
- txq->elts_head = elts_head;
- 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 txq *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 = htons(length);
- mpw->wqe->eseg.inline_hdr_sz = 0;
- mpw->wqe->eseg.rsvd0 = 0;
- mpw->wqe->eseg.rsvd1 = 0;
- mpw->wqe->eseg.rsvd2 = 0;
- mpw->wqe->ctrl[0] = htonl((MLX5_OPC_MOD_MPW << 24) |
- (txq->wqe_ci << 8) | MLX5_OPCODE_TSO);
- mpw->wqe->ctrl[2] = 0;
- 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 txq *txq, struct mlx5_mpw *mpw)
-{
- unsigned int num = mpw->pkts_n;
+ uint8_t v;
/*
- * Store size in multiple of 16 bytes. Control and Ethernet segments
- * count as 2.
+ * 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
*/
- mpw->wqe->ctrl[1] = htonl(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 txq *txq = (struct txq *)dpdk_txq;
- uint16_t elts_head = txq->elts_head;
- const unsigned int elts_n = 1 << txq->elts_n;
- 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. */
- rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci));
- rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci + 1));
- /* Start processing. */
- txq_complete(txq);
- max = (elts_n - (elts_head - txq->elts_tail));
- if (max > elts_n)
- max -= elts_n;
- 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 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.cs_flags != cs_flags)))
- mlx5_mpw_close(txq, &mpw);
- if (mpw.state == MLX5_MPW_STATE_CLOSED) {
- mlx5_mpw_new(txq, &mpw, length);
- mpw.wqe->eseg.cs_flags = cs_flags;
+ for (i = 0; i < RTE_DIM(mlx5_cksum_table); ++i) {
+ v = 0;
+ if (i & (1 << 9)) {
+ /* Tunneled packet. */
+ if (i & (1 << 8)) /* Outer IP. */
+ v |= MLX5_ETH_WQE_L3_CSUM;
+ if (i & (1 << 4)) /* Inner IP. */
+ v |= MLX5_ETH_WQE_L3_INNER_CSUM;
+ if (i & (3 << 2 | 1 << 0)) /* L4 or TSO. */
+ v |= MLX5_ETH_WQE_L4_INNER_CSUM;
+ } else {
+ /* No tunnel. */
+ if (i & (1 << 4)) /* IP. */
+ v |= MLX5_ETH_WQE_L3_CSUM;
+ if (i & (3 << 2 | 1 << 0)) /* L4 or TSO. */
+ v |= MLX5_ETH_WQE_L4_CSUM;
}
- /* 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;
-#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;
-
- /* Request completion on last WQE. */
- wqe->ctrl[2] = htonl(8);
- /* Save elts_head in unused "immediate" field of WQE. */
- wqe->ctrl[3] = elts_head;
- txq->elts_comp = 0;
- } else {
- txq->elts_comp = comp;
+ mlx5_cksum_table[i] = v;
}
-#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 txq *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] = htonl((MLX5_OPC_MOD_MPW << 24) |
- (txq->wqe_ci << 8) |
- MLX5_OPCODE_TSO);
- mpw->wqe->ctrl[2] = 0;
- mpw->wqe->ctrl[3] = 0;
- mpw->wqe->eseg.mss = htons(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.rsvd2 = 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.
+ * Build a table to translate packet type of mbuf to SWP type of Verbs.
*/
-static inline void
-mlx5_mpw_inline_close(struct txq *txq, struct mlx5_mpw *mpw)
+void
+mlx5_set_swp_types_table(void)
{
- unsigned int size;
- struct mlx5_wqe_inl_small *inl = (struct mlx5_wqe_inl_small *)
- (((uintptr_t)mpw->wqe) + (2 * MLX5_WQE_DWORD_SIZE));
+ unsigned int i;
+ uint8_t v;
- 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.
+ * 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
*/
- mpw->wqe->ctrl[1] = htonl(txq->qp_num_8s | MLX5_WQE_DS(size));
- mpw->state = MLX5_MPW_STATE_CLOSED;
- inl->byte_cnt = htonl(mpw->total_len | MLX5_INLINE_SEG);
- txq->wqe_ci += (size + (MLX5_WQE_SIZE - 1)) / MLX5_WQE_SIZE;
+ for (i = 0; i < RTE_DIM(mlx5_swp_types_table); ++i) {
+ v = 0;
+ if (i & (1 << 8))
+ v |= MLX5_ETH_WQE_L3_OUTER_IPV6;
+ if (i & (1 << 9))
+ v |= MLX5_ETH_WQE_L4_OUTER_UDP;
+ if (i & (1 << 4))
+ v |= MLX5_ETH_WQE_L3_INNER_IPV6;
+ if ((i & 3) == (PKT_TX_UDP_CKSUM >> 52))
+ v |= MLX5_ETH_WQE_L4_INNER_UDP;
+ mlx5_swp_types_table[i] = v;
+ }
}
+#define MLX5_SYSTEM_LOG_DIR "/var/log"
/**
- * 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.
+ * Dump debug information to log file.
*
- * @return
- * Number of packets successfully transmitted (<= pkts_n).
+ * @param fname
+ * The file name.
+ * @param hex_title
+ * If not NULL this string is printed as a header to the output
+ * and the output will be in hexadecimal view.
+ * @param buf
+ * This is the buffer address to print out.
+ * @param len
+ * The number of bytes to dump out.
*/
-uint16_t
-mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf **pkts,
- uint16_t pkts_n)
+void
+mlx5_dump_debug_information(const char *fname, const char *hex_title,
+ const void *buf, unsigned int hex_len)
{
- struct txq *txq = (struct txq *)dpdk_txq;
- uint16_t elts_head = txq->elts_head;
- const unsigned int elts_n = 1 << txq->elts_n;
- unsigned int i = 0;
- unsigned int j = 0;
- unsigned int max;
- unsigned int comp;
- 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. */
- rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci));
- rte_prefetch0(tx_mlx5_wqe(txq, txq->wqe_ci + 1));
- /* Start processing. */
- txq_complete(txq);
- max = (elts_n - (elts_head - txq->elts_tail));
- if (max > elts_n)
- max -= elts_n;
- 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 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.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.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)) {
- mlx5_mpw_new(txq, &mpw, length);
- mpw.wqe->eseg.cs_flags = cs_flags;
- } else {
- mlx5_mpw_inline_new(txq, &mpw, length);
- mpw.wqe->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) {
- 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 {
- unsigned int max;
-
- 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)) +
- (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);
- mpw.data.raw += length;
- }
- if ((uintptr_t)mpw.data.raw ==
- (uintptr_t)tx_mlx5_wqe(txq, 1 << txq->wqe_n))
- mpw.data.raw = (volatile void *)txq->wqes;
- ++mpw.pkts_n;
- ++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;
- }
+ FILE *fd;
+
+ MKSTR(path, "%s/%s", MLX5_SYSTEM_LOG_DIR, fname);
+ fd = fopen(path, "a+");
+ if (!fd) {
+ DRV_LOG(WARNING, "cannot open %s for debug dump", path);
+ MKSTR(path2, "./%s", fname);
+ fd = fopen(path2, "a+");
+ if (!fd) {
+ DRV_LOG(ERR, "cannot open %s for debug dump", path2);
+ return;
}
- mpw.total_len += length;
- elts_head = elts_head_next;
-#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;
-
- /* Request completion on last WQE. */
- wqe->ctrl[2] = htonl(8);
- /* Save elts_head in unused "immediate" field of WQE. */
- wqe->ctrl[3] = elts_head;
- txq->elts_comp = 0;
+ DRV_LOG(INFO, "New debug dump in file %s", path2);
} else {
- txq->elts_comp = comp;
+ DRV_LOG(INFO, "New debug dump in file %s", path);
}
-#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;
-}
-
-/**
- * Translate RX completion flags to packet type.
- *
- * @param[in] cqe
- * Pointer to CQE.
- *
- * @note: fix mlx5_dev_supported_ptypes_get() if any change here.
- *
- * @return
- * Packet type for struct rte_mbuf.
- */
-static inline uint32_t
-rxq_cq_to_pkt_type(volatile struct mlx5_cqe *cqe)
-{
- uint32_t pkt_type;
- uint8_t flags = cqe->l4_hdr_type_etc;
-
- if (cqe->pkt_info & MLX5_CQE_RX_TUNNEL_PACKET)
- pkt_type =
- TRANSPOSE(flags,
- MLX5_CQE_RX_OUTER_IPV4_PACKET,
- RTE_PTYPE_L3_IPV4_EXT_UNKNOWN) |
- TRANSPOSE(flags,
- MLX5_CQE_RX_OUTER_IPV6_PACKET,
- RTE_PTYPE_L3_IPV6_EXT_UNKNOWN) |
- TRANSPOSE(flags,
- MLX5_CQE_RX_IPV4_PACKET,
- RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN) |
- TRANSPOSE(flags,
- MLX5_CQE_RX_IPV6_PACKET,
- RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN);
+ if (hex_title)
+ rte_hexdump(fd, hex_title, buf, hex_len);
else
- pkt_type =
- TRANSPOSE(flags,
- MLX5_CQE_L3_HDR_TYPE_IPV6,
- RTE_PTYPE_L3_IPV6_EXT_UNKNOWN) |
- TRANSPOSE(flags,
- MLX5_CQE_L3_HDR_TYPE_IPV4,
- RTE_PTYPE_L3_IPV4_EXT_UNKNOWN);
- return pkt_type;
+ fprintf(fd, "%s", (const char *)buf);
+ fprintf(fd, "\n\n\n");
+ fclose(fd);
}
/**
- * Get size of the next packet for a given CQE. For compressed CQEs, the
- * consumer index is updated only once all packets of the current one have
- * been processed.
+ * Modify a Verbs/DevX queue state.
+ * This must be called from the primary process.
*
- * @param rxq
- * Pointer to RX queue.
- * @param cqe
- * CQE to process.
- * @param[out] rss_hash
- * Packet RSS Hash result.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param sm
+ * State modify request parameters.
*
* @return
- * Packet size in bytes (0 if there is none), -1 in case of completion
- * with error.
+ * 0 in case of success else non-zero value and rte_errno is set.
*/
-static inline int
-mlx5_rx_poll_len(struct rxq *rxq, volatile struct mlx5_cqe *cqe,
- uint16_t cqe_cnt, uint32_t *rss_hash)
+int
+mlx5_queue_state_modify_primary(struct rte_eth_dev *dev,
+ const struct mlx5_mp_arg_queue_state_modify *sm)
{
- struct rxq_zip *zip = &rxq->zip;
- uint16_t cqe_n = cqe_cnt + 1;
- int len = 0;
-
- /* Process compressed data in the CQE and mini arrays. */
- if (zip->ai) {
- volatile struct mlx5_mini_cqe8 (*mc)[8] =
- (volatile struct mlx5_mini_cqe8 (*)[8])
- (uintptr_t)(&(*rxq->cqes)[zip->ca & cqe_cnt]);
-
- len = ntohl((*mc)[zip->ai & 7].byte_cnt);
- *rss_hash = ntohl((*mc)[zip->ai & 7].rx_hash_result);
- if ((++zip->ai & 7) == 0) {
- /*
- * Increment consumer index to skip the number of
- * CQEs consumed. Hardware leaves holes in the CQ
- * ring for software use.
- */
- zip->ca = zip->na;
- zip->na += 8;
+ int ret;
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ if (sm->is_wq) {
+ struct mlx5_rxq_data *rxq = (*priv->rxqs)[sm->queue_id];
+ struct mlx5_rxq_ctrl *rxq_ctrl =
+ container_of(rxq, struct mlx5_rxq_ctrl, rxq);
+
+ ret = priv->obj_ops.rxq_obj_modify(rxq_ctrl->obj, sm->state);
+ if (ret) {
+ DRV_LOG(ERR, "Cannot change Rx WQ state to %u - %s",
+ sm->state, strerror(errno));
+ rte_errno = errno;
+ return ret;
}
- if (unlikely(rxq->zip.ai == rxq->zip.cqe_cnt)) {
- uint16_t idx = rxq->cq_ci + 1;
- uint16_t end = zip->cq_ci;
-
- while (idx != end) {
- (*rxq->cqes)[idx & cqe_cnt].op_own =
- MLX5_CQE_INVALIDATE;
- ++idx;
- }
- rxq->cq_ci = zip->cq_ci;
- zip->ai = 0;
- }
- /* No compressed data, get next CQE and verify if it is compressed. */
} else {
- int ret;
- int8_t op_own;
-
- ret = check_cqe(cqe, cqe_n, rxq->cq_ci);
- if (unlikely(ret == 1))
- return 0;
- ++rxq->cq_ci;
- op_own = cqe->op_own;
- if (MLX5_CQE_FORMAT(op_own) == MLX5_COMPRESSED) {
- volatile struct mlx5_mini_cqe8 (*mc)[8] =
- (volatile struct mlx5_mini_cqe8 (*)[8])
- (uintptr_t)(&(*rxq->cqes)[rxq->cq_ci &
- cqe_cnt]);
-
- /* Fix endianness. */
- zip->cqe_cnt = ntohl(cqe->byte_cnt);
- /*
- * Current mini array position is the one returned by
- * check_cqe64().
- *
- * If completion comprises several mini arrays, as a
- * special case the second one is located 7 CQEs after
- * the initial CQE instead of 8 for subsequent ones.
- */
- zip->ca = rxq->cq_ci & cqe_cnt;
- zip->na = zip->ca + 7;
- /* Compute the next non compressed CQE. */
- --rxq->cq_ci;
- zip->cq_ci = rxq->cq_ci + zip->cqe_cnt;
- /* Get packet size to return. */
- len = ntohl((*mc)[0].byte_cnt);
- *rss_hash = ntohl((*mc)[0].rx_hash_result);
- zip->ai = 1;
- } else {
- len = ntohl(cqe->byte_cnt);
- *rss_hash = ntohl(cqe->rx_hash_res);
- }
- /* Error while receiving packet. */
- if (unlikely(MLX5_CQE_OPCODE(op_own) == MLX5_CQE_RESP_ERR))
- return -1;
+ struct mlx5_txq_data *txq = (*priv->txqs)[sm->queue_id];
+ struct mlx5_txq_ctrl *txq_ctrl =
+ container_of(txq, struct mlx5_txq_ctrl, txq);
+
+ ret = priv->obj_ops.txq_obj_modify(txq_ctrl->obj,
+ MLX5_TXQ_MOD_ERR2RDY,
+ (uint8_t)priv->dev_port);
+ if (ret)
+ return ret;
}
- return len;
-}
-
-/**
- * Translate RX completion flags to offload flags.
- *
- * @param[in] rxq
- * Pointer to RX queue structure.
- * @param[in] cqe
- * Pointer to CQE.
- *
- * @return
- * Offload flags (ol_flags) for struct rte_mbuf.
- */
-static inline uint32_t
-rxq_cq_to_ol_flags(struct rxq *rxq, volatile struct mlx5_cqe *cqe)
-{
- uint32_t ol_flags = 0;
- uint8_t l3_hdr = (cqe->l4_hdr_type_etc) & MLX5_CQE_L3_HDR_TYPE_MASK;
- uint8_t l4_hdr = (cqe->l4_hdr_type_etc) & MLX5_CQE_L4_HDR_TYPE_MASK;
-
- if ((l3_hdr == MLX5_CQE_L3_HDR_TYPE_IPV4) ||
- (l3_hdr == MLX5_CQE_L3_HDR_TYPE_IPV6))
- ol_flags |= TRANSPOSE(cqe->hds_ip_ext,
- MLX5_CQE_L3_OK,
- PKT_RX_IP_CKSUM_GOOD);
- if ((l4_hdr == MLX5_CQE_L4_HDR_TYPE_TCP) ||
- (l4_hdr == MLX5_CQE_L4_HDR_TYPE_TCP_EMP_ACK) ||
- (l4_hdr == MLX5_CQE_L4_HDR_TYPE_TCP_ACK) ||
- (l4_hdr == MLX5_CQE_L4_HDR_TYPE_UDP))
- ol_flags |= TRANSPOSE(cqe->hds_ip_ext,
- MLX5_CQE_L4_OK,
- PKT_RX_L4_CKSUM_GOOD);
- if ((cqe->pkt_info & MLX5_CQE_RX_TUNNEL_PACKET) && (rxq->csum_l2tun))
- ol_flags |=
- TRANSPOSE(cqe->l4_hdr_type_etc,
- MLX5_CQE_RX_OUTER_IP_CSUM_OK,
- PKT_RX_IP_CKSUM_GOOD) |
- TRANSPOSE(cqe->l4_hdr_type_etc,
- MLX5_CQE_RX_OUTER_TCP_UDP_CSUM_OK,
- PKT_RX_L4_CKSUM_GOOD);
- return ol_flags;
-}
-
-/**
- * DPDK callback for RX.
- *
- * @param dpdk_rxq
- * Generic pointer to RX queue structure.
- * @param[out] pkts
- * Array to store received packets.
- * @param pkts_n
- * Maximum number of packets in array.
- *
- * @return
- * Number of packets successfully received (<= pkts_n).
- */
-uint16_t
-mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
- struct rxq *rxq = dpdk_rxq;
- const unsigned int wqe_cnt = (1 << rxq->elts_n) - 1;
- const unsigned int cqe_cnt = (1 << rxq->cqe_n) - 1;
- const unsigned int sges_n = rxq->sges_n;
- struct rte_mbuf *pkt = NULL;
- struct rte_mbuf *seg = NULL;
- volatile struct mlx5_cqe *cqe =
- &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
- unsigned int i = 0;
- unsigned int rq_ci = rxq->rq_ci << sges_n;
- int len; /* keep its value across iterations. */
-
- while (pkts_n) {
- unsigned int idx = rq_ci & wqe_cnt;
- volatile struct mlx5_wqe_data_seg *wqe = &(*rxq->wqes)[idx];
- struct rte_mbuf *rep = (*rxq->elts)[idx];
- uint32_t rss_hash_res = 0;
-
- 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]);
- rep = NEXT(pkt);
- rte_mbuf_refcnt_set(pkt, 0);
- __rte_mbuf_raw_free(pkt);
- pkt = rep;
- }
- break;
- }
- if (!pkt) {
- cqe = &(*rxq->cqes)[rxq->cq_ci & cqe_cnt];
- len = mlx5_rx_poll_len(rxq, cqe, cqe_cnt,
- &rss_hash_res);
- if (!len) {
- 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 (rss_hash_res && rxq->rss_hash) {
- pkt->hash.rss = rss_hash_res;
- pkt->ol_flags = PKT_RX_RSS_HASH;
- }
- if (rxq->mark &&
- ((cqe->sop_drop_qpn !=
- htonl(MLX5_FLOW_MARK_INVALID)) ||
- (cqe->sop_drop_qpn !=
- htonl(MLX5_FLOW_MARK_DEFAULT)))) {
- pkt->hash.fdir.hi =
- mlx5_flow_mark_get(cqe->sop_drop_qpn);
- pkt->ol_flags &= ~PKT_RX_RSS_HASH;
- pkt->ol_flags |= PKT_RX_FDIR | PKT_RX_FDIR_ID;
- }
- 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(rte_pktmbuf_mtod(rep, uintptr_t));
- if (len > DATA_LEN(seg)) {
- len -= DATA_LEN(seg);
- ++NB_SEGS(pkt);
- ++rq_ci;
- continue;
- }
- DATA_LEN(seg) = len;
-#ifdef MLX5_PMD_SOFT_COUNTERS
- /* Increment bytes counter. */
- rxq->stats.ibytes += PKT_LEN(pkt);
-#endif
- /* Return packet. */
- *(pkts++) = pkt;
- 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 >> sges_n) == rxq->rq_ci)))
- return 0;
- /* Update the consumer index. */
- 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 += i;
-#endif
- return i;
-}
-
-/**
- * Dummy DPDK callback for TX.
- *
- * This function is used to temporarily replace the real callback during
- * unsafe control operations on the queue, or in case of error.
- *
- * @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
-removed_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
-{
- (void)dpdk_txq;
- (void)pkts;
- (void)pkts_n;
return 0;
}
/**
- * Dummy DPDK callback for RX.
- *
- * This function is used to temporarily replace the real callback during
- * unsafe control operations on the queue, or in case of error.
+ * Modify a Verbs queue state.
*
- * @param dpdk_rxq
- * Generic pointer to RX queue structure.
- * @param[out] pkts
- * Array to store received packets.
- * @param pkts_n
- * Maximum number of packets in array.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param sm
+ * State modify request parameters.
*
* @return
- * Number of packets successfully received (<= pkts_n).
+ * 0 in case of success else non-zero value.
*/
-uint16_t
-removed_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n)
+int
+mlx5_queue_state_modify(struct rte_eth_dev *dev,
+ struct mlx5_mp_arg_queue_state_modify *sm)
{
- (void)dpdk_rxq;
- (void)pkts;
- (void)pkts_n;
- return 0;
+ struct mlx5_priv *priv = dev->data->dev_private;
+ int ret = 0;
+
+ switch (rte_eal_process_type()) {
+ case RTE_PROC_PRIMARY:
+ ret = mlx5_queue_state_modify_primary(dev, sm);
+ break;
+ case RTE_PROC_SECONDARY:
+ ret = mlx5_mp_req_queue_state_modify(&priv->mp_id, sm);
+ break;
+ default:
+ break;
+ }
+ return ret;
}
git.droids-corp.org / dpdk.git / blobdiff