#include <rte_atomic.h>
#include <rte_spinlock.h>
#include <rte_io.h>
+#include <rte_bus_pci.h>
#include "mlx5_utils.h"
#include "mlx5.h"
#include "mlx5_autoconf.h"
#include "mlx5_defs.h"
#include "mlx5_prm.h"
+#include "mlx5_glue.h"
/* Support tunnel matching. */
#define MLX5_FLOW_TUNNEL 5
struct mlx5_rxq_stats {
- unsigned int idx; /**< Mapping index. */
#ifdef MLX5_PMD_SOFT_COUNTERS
uint64_t ipackets; /**< Total of successfully received packets. */
uint64_t ibytes; /**< Total of successfully received bytes. */
};
struct mlx5_txq_stats {
- unsigned int idx; /**< Mapping index. */
#ifdef MLX5_PMD_SOFT_COUNTERS
uint64_t opackets; /**< Total of successfully sent packets. */
uint64_t obytes; /**< Total of successfully sent bytes. */
uint64_t oerrors; /**< Total number of failed transmitted packets. */
};
-struct priv;
+struct mlx5_priv;
/* Compressed CQE context. */
struct rxq_zip {
/* Get pointer to the first stride. */
#define mlx5_mprq_buf_addr(ptr) ((ptr) + 1)
+enum mlx5_rxq_err_state {
+ MLX5_RXQ_ERR_STATE_NO_ERROR = 0,
+ MLX5_RXQ_ERR_STATE_NEED_RESET,
+ MLX5_RXQ_ERR_STATE_NEED_READY,
+};
+
/* RX queue descriptor. */
struct mlx5_rxq_data {
unsigned int csum:1; /* Enable checksum offloading. */
unsigned int strd_num_n:5; /* Log 2 of the number of stride. */
unsigned int strd_sz_n:4; /* Log 2 of stride size. */
unsigned int strd_shift_en:1; /* Enable 2bytes shift on a stride. */
- unsigned int :6; /* Remaining bits. */
+ unsigned int err_state:2; /* enum mlx5_rxq_err_state. */
+ unsigned int :4; /* Remaining bits. */
volatile uint32_t *rq_db;
volatile uint32_t *cq_db;
uint16_t port_id;
uint16_t consumed_strd; /* Number of consumed strides in WQE. */
uint32_t rq_pi;
uint32_t cq_ci;
+ uint16_t rq_repl_thresh; /* Threshold for buffer replenishment. */
+ union {
+ struct rxq_zip zip; /* Compressed context. */
+ uint16_t decompressed;
+ /* Number of ready mbufs decompressed from the CQ. */
+ };
struct mlx5_mr_ctrl mr_ctrl; /* MR control descriptor. */
uint16_t mprq_max_memcpy_len; /* Maximum size of packet to memcpy. */
volatile void *wqes;
volatile struct mlx5_cqe(*cqes)[];
- struct rxq_zip zip; /* Compressed context. */
RTE_STD_C11
union {
struct rte_mbuf *(*elts)[];
struct rte_mempool *mp;
struct rte_mempool *mprq_mp; /* Mempool for Multi-Packet RQ. */
struct mlx5_mprq_buf *mprq_repl; /* Stashed mbuf for replenish. */
+ uint16_t idx; /* Queue index. */
struct mlx5_rxq_stats stats;
uint64_t mbuf_initializer; /* Default rearm_data for vectorized Rx. */
struct rte_mbuf fake_mbuf; /* elts padding for vectorized Rx. */
/* RX queue control descriptor. */
struct mlx5_rxq_ctrl {
+ struct mlx5_rxq_data rxq; /* Data path structure. */
LIST_ENTRY(mlx5_rxq_ctrl) next; /* Pointer to the next element. */
rte_atomic32_t refcnt; /* Reference counter. */
struct mlx5_rxq_ibv *ibv; /* Verbs elements. */
- struct priv *priv; /* Back pointer to private data. */
- struct mlx5_rxq_data rxq; /* Data path structure. */
+ struct mlx5_priv *priv; /* Back pointer to private data. */
unsigned int socket; /* CPU socket ID for allocations. */
unsigned int irq:1; /* Whether IRQ is enabled. */
- uint16_t idx; /* Queue index. */
uint32_t flow_mark_n; /* Number of Mark/Flag flows using this Queue. */
uint32_t flow_tunnels_n[MLX5_FLOW_TUNNEL]; /* Tunnels counters. */
+ uint32_t wqn; /* WQ number. */
+ uint16_t dump_file_n; /* Number of dump files. */
};
/* Indirection table. */
rte_atomic32_t refcnt; /* Reference counter. */
struct mlx5_ind_table_ibv *ind_table; /* Indirection table. */
struct ibv_qp *qp; /* Verbs queue pair. */
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ void *action; /* DV QP action pointer. */
+#endif
uint64_t hash_fields; /* Verbs Hash fields. */
uint32_t rss_key_len; /* Hash key length in bytes. */
uint8_t rss_key[]; /* Hash key. */
volatile void *wqes; /* Work queue (use volatile to write into). */
volatile uint32_t *qp_db; /* Work queue doorbell. */
volatile uint32_t *cq_db; /* Completion queue doorbell. */
- volatile void *bf_reg; /* Blueflame register remapped. */
struct rte_mbuf *(*elts)[]; /* TX elements. */
+ uint16_t port_id; /* Port ID of device. */
+ uint16_t idx; /* Queue index. */
struct mlx5_txq_stats stats; /* TX queue counters. */
#ifndef RTE_ARCH_64
rte_spinlock_t *uar_lock;
/* TX queue control descriptor. */
struct mlx5_txq_ctrl {
+ struct mlx5_txq_data txq; /* Data path structure. */
LIST_ENTRY(mlx5_txq_ctrl) next; /* Pointer to the next element. */
rte_atomic32_t refcnt; /* Reference counter. */
unsigned int socket; /* CPU socket ID for allocations. */
unsigned int max_inline_data; /* Max inline data. */
unsigned int max_tso_header; /* Max TSO header size. */
struct mlx5_txq_ibv *ibv; /* Verbs queue object. */
- struct priv *priv; /* Back pointer to private data. */
- struct mlx5_txq_data txq; /* Data path structure. */
+ struct mlx5_priv *priv; /* Back pointer to private data. */
off_t uar_mmap_offset; /* UAR mmap offset for non-primary process. */
- volatile void *bf_reg_orig; /* Blueflame register from verbs. */
- uint16_t idx; /* Queue index. */
+ void *bf_reg; /* BlueFlame register from Verbs. */
+ uint32_t cqn; /* CQ number. */
+ uint16_t dump_file_n; /* Number of dump files. */
};
+#define MLX5_TX_BFREG(txq) \
+ (MLX5_PROC_PRIV((txq)->port_id)->uar_table[(txq)->idx])
+
/* mlx5_rxq.c */
extern uint8_t rss_hash_default_key[];
int mlx5_mprq_enabled(struct rte_eth_dev *dev);
int mlx5_mprq_free_mp(struct rte_eth_dev *dev);
int mlx5_mprq_alloc_mp(struct rte_eth_dev *dev);
-void mlx5_rxq_cleanup(struct mlx5_rxq_ctrl *rxq_ctrl);
int mlx5_rx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
unsigned int socket, const struct rte_eth_rxconf *conf,
struct rte_mempool *mp);
int mlx5_rx_intr_enable(struct rte_eth_dev *dev, uint16_t rx_queue_id);
int mlx5_rx_intr_disable(struct rte_eth_dev *dev, uint16_t rx_queue_id);
struct mlx5_rxq_ibv *mlx5_rxq_ibv_new(struct rte_eth_dev *dev, uint16_t idx);
-struct mlx5_rxq_ibv *mlx5_rxq_ibv_get(struct rte_eth_dev *dev, uint16_t idx);
-int mlx5_rxq_ibv_release(struct mlx5_rxq_ibv *rxq_ibv);
-int mlx5_rxq_ibv_releasable(struct mlx5_rxq_ibv *rxq_ibv);
-struct mlx5_rxq_ibv *mlx5_rxq_ibv_drop_new(struct rte_eth_dev *dev);
-void mlx5_rxq_ibv_drop_release(struct rte_eth_dev *dev);
int mlx5_rxq_ibv_verify(struct rte_eth_dev *dev);
struct mlx5_rxq_ctrl *mlx5_rxq_new(struct rte_eth_dev *dev, uint16_t idx,
uint16_t desc, unsigned int socket,
struct rte_mempool *mp);
struct mlx5_rxq_ctrl *mlx5_rxq_get(struct rte_eth_dev *dev, uint16_t idx);
int mlx5_rxq_release(struct rte_eth_dev *dev, uint16_t idx);
-int mlx5_rxq_releasable(struct rte_eth_dev *dev, uint16_t idx);
int mlx5_rxq_verify(struct rte_eth_dev *dev);
int rxq_alloc_elts(struct mlx5_rxq_ctrl *rxq_ctrl);
-int rxq_alloc_mprq_buf(struct mlx5_rxq_ctrl *rxq_ctrl);
-struct mlx5_ind_table_ibv *mlx5_ind_table_ibv_new(struct rte_eth_dev *dev,
- const uint16_t *queues,
- uint32_t queues_n);
-struct mlx5_ind_table_ibv *mlx5_ind_table_ibv_get(struct rte_eth_dev *dev,
- const uint16_t *queues,
- uint32_t queues_n);
-int mlx5_ind_table_ibv_release(struct rte_eth_dev *dev,
- struct mlx5_ind_table_ibv *ind_tbl);
int mlx5_ind_table_ibv_verify(struct rte_eth_dev *dev);
-struct mlx5_ind_table_ibv *mlx5_ind_table_ibv_drop_new(struct rte_eth_dev *dev);
-void mlx5_ind_table_ibv_drop_release(struct rte_eth_dev *dev);
struct mlx5_hrxq *mlx5_hrxq_new(struct rte_eth_dev *dev,
const uint8_t *rss_key, uint32_t rss_key_len,
uint64_t hash_fields,
int mlx5_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
unsigned int socket, const struct rte_eth_txconf *conf);
void mlx5_tx_queue_release(void *dpdk_txq);
-int mlx5_tx_uar_remap(struct rte_eth_dev *dev, int fd);
+int mlx5_tx_uar_init_secondary(struct rte_eth_dev *dev, int fd);
struct mlx5_txq_ibv *mlx5_txq_ibv_new(struct rte_eth_dev *dev, uint16_t idx);
struct mlx5_txq_ibv *mlx5_txq_ibv_get(struct rte_eth_dev *dev, uint16_t idx);
int mlx5_txq_ibv_release(struct mlx5_txq_ibv *txq_ibv);
-int mlx5_txq_ibv_releasable(struct mlx5_txq_ibv *txq_ibv);
int mlx5_txq_ibv_verify(struct rte_eth_dev *dev);
struct mlx5_txq_ctrl *mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx,
uint16_t desc, unsigned int socket,
void mlx5_set_ptype_table(void);
void mlx5_set_cksum_table(void);
void mlx5_set_swp_types_table(void);
-uint16_t mlx5_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts,
- uint16_t pkts_n);
-uint16_t mlx5_tx_burst_mpw(void *dpdk_txq, struct rte_mbuf **pkts,
- uint16_t pkts_n);
-uint16_t mlx5_tx_burst_mpw_inline(void *dpdk_txq, struct rte_mbuf **pkts,
- uint16_t pkts_n);
-uint16_t mlx5_tx_burst_empw(void *dpdk_txq, struct rte_mbuf **pkts,
- uint16_t pkts_n);
+__rte_noinline uint16_t mlx5_tx_error_cqe_handle(struct mlx5_txq_data *txq,
+ volatile struct mlx5_err_cqe *err_cqe);
uint16_t mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n);
+void mlx5_rxq_initialize(struct mlx5_rxq_data *rxq);
+__rte_noinline int mlx5_rx_err_handle(struct mlx5_rxq_data *rxq,
+ uint8_t mbuf_prepare);
void mlx5_mprq_buf_free_cb(void *addr, void *opaque);
void mlx5_mprq_buf_free(struct mlx5_mprq_buf *buf);
uint16_t mlx5_rx_burst_mprq(void *dpdk_rxq, struct rte_mbuf **pkts,
int mlx5_rx_descriptor_status(void *rx_queue, uint16_t offset);
int mlx5_tx_descriptor_status(void *tx_queue, uint16_t offset);
uint32_t mlx5_rx_queue_count(struct rte_eth_dev *dev, uint16_t rx_queue_id);
+void mlx5_dump_debug_information(const char *path, const char *title,
+ const void *buf, unsigned int len);
+int mlx5_queue_state_modify_primary(struct rte_eth_dev *dev,
+ const struct mlx5_mp_arg_queue_state_modify *sm);
/* Vectorized version of mlx5_rxtx.c */
-int mlx5_check_raw_vec_tx_support(struct rte_eth_dev *dev);
-int mlx5_check_vec_tx_support(struct rte_eth_dev *dev);
int mlx5_rxq_check_vec_support(struct mlx5_rxq_data *rxq_data);
int mlx5_check_vec_rx_support(struct rte_eth_dev *dev);
-uint16_t mlx5_tx_burst_raw_vec(void *dpdk_txq, struct rte_mbuf **pkts,
- uint16_t pkts_n);
-uint16_t mlx5_tx_burst_vec(void *dpdk_txq, struct rte_mbuf **pkts,
- uint16_t pkts_n);
uint16_t mlx5_rx_burst_vec(void *dpdk_txq, struct rte_mbuf **pkts,
uint16_t pkts_n);
void mlx5_mr_flush_local_cache(struct mlx5_mr_ctrl *mr_ctrl);
uint32_t mlx5_rx_addr2mr_bh(struct mlx5_rxq_data *rxq, uintptr_t addr);
-uint32_t mlx5_tx_addr2mr_bh(struct mlx5_txq_data *txq, uintptr_t addr);
+uint32_t mlx5_tx_mb2mr_bh(struct mlx5_txq_data *txq, struct rte_mbuf *mb);
uint32_t mlx5_tx_update_ext_mp(struct mlx5_txq_data *txq, uintptr_t addr,
struct rte_mempool *mp);
+int mlx5_dma_map(struct rte_pci_device *pdev, void *addr, uint64_t iova,
+ size_t len);
+int mlx5_dma_unmap(struct rte_pci_device *pdev, void *addr, uint64_t iova,
+ size_t len);
/**
* Provide safe 64bit store operation to mlx5 UAR region for both 32bit and
* Address of the lock to use for that UAR access.
*/
static __rte_always_inline void
-__mlx5_uar_write64_relaxed(uint64_t val, volatile void *addr,
+__mlx5_uar_write64_relaxed(uint64_t val, void *addr,
rte_spinlock_t *lock __rte_unused)
{
#ifdef RTE_ARCH_64
- rte_write64_relaxed(val, addr);
+ *(uint64_t *)addr = val;
#else /* !RTE_ARCH_64 */
rte_spinlock_lock(lock);
- rte_write32_relaxed(val, addr);
+ *(uint32_t *)addr = val;
rte_io_wmb();
- rte_write32_relaxed(val >> 32,
- (volatile void *)((volatile char *)addr + 4));
+ *((uint32_t *)addr + 1) = val >> 32;
rte_spinlock_unlock(lock);
#endif
}
* Address of the lock to use for that UAR access.
*/
static __rte_always_inline void
-__mlx5_uar_write64(uint64_t val, volatile void *addr, rte_spinlock_t *lock)
+__mlx5_uar_write64(uint64_t val, void *addr, rte_spinlock_t *lock)
{
rte_io_wmb();
__mlx5_uar_write64_relaxed(val, addr, lock);
#define mlx5_uar_write64(val, dst, lock) __mlx5_uar_write64(val, dst, lock)
#endif
-#ifndef NDEBUG
-/**
- * Verify or set magic value in CQE.
- *
- * @param cqe
- * Pointer to CQE.
- *
- * @return
- * 0 the first time.
- */
-static inline int
-check_cqe_seen(volatile struct mlx5_cqe *cqe)
-{
- static const uint8_t magic[] = "seen";
- volatile uint8_t (*buf)[sizeof(cqe->rsvd1)] = &cqe->rsvd1;
- int ret = 1;
- unsigned int i;
-
- 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 */
+/* CQE status. */
+enum mlx5_cqe_status {
+ MLX5_CQE_STATUS_SW_OWN,
+ MLX5_CQE_STATUS_HW_OWN,
+ MLX5_CQE_STATUS_ERR,
+};
/**
* Check whether CQE is valid.
* Consumer index.
*
* @return
- * 0 on success, 1 on failure.
+ * The CQE status.
*/
-static __rte_always_inline int
-check_cqe(volatile struct mlx5_cqe *cqe,
- unsigned int cqes_n, const uint16_t ci)
+static __rte_always_inline enum mlx5_cqe_status
+check_cqe(volatile struct mlx5_cqe *cqe, const uint16_t 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);
+ const uint16_t idx = ci & cqes_n;
+ const uint8_t op_own = cqe->op_own;
+ const uint8_t op_owner = MLX5_CQE_OWNER(op_own);
+ const 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)) {
- DRV_LOG(ERR,
- "unexpected CQE error %u (0x%02x) syndrome"
- " 0x%02x",
- op_code, op_code, syndrome);
- rte_hexdump(stderr, "MLX5 Error CQE:",
- (const void *)((uintptr_t)err_cqe),
- sizeof(*err_cqe));
- }
- return 1;
- } else if ((op_code != MLX5_CQE_RESP_SEND) &&
- (op_code != MLX5_CQE_REQ)) {
- if (!check_cqe_seen(cqe)) {
- DRV_LOG(ERR, "unexpected CQE opcode %u (0x%02x)",
- op_code, op_code);
- rte_hexdump(stderr, "MLX5 CQE:",
- (const void *)((uintptr_t)cqe),
- sizeof(*cqe));
- }
- 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 mlx5_txq_data *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 __rte_always_inline void
-mlx5_tx_complete(struct mlx5_txq_data *txq)
-{
- const uint16_t elts_n = 1 << txq->elts_n;
- const uint16_t elts_m = elts_n - 1;
- 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;
- struct rte_mbuf *m, *free[elts_n];
- struct rte_mempool *pool = NULL;
- unsigned int blk_n = 0;
-
- cqe = &(*txq->cqes)[cq_ci & cqe_cnt];
- if (unlikely(check_cqe(cqe, cqe_n, cq_ci)))
- return;
-#ifndef NDEBUG
- 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)) {
- DRV_LOG(ERR, "unexpected error CQE, Tx stopped");
- rte_hexdump(stderr, "MLX5 TXQ:",
- (const void *)((uintptr_t)txq->wqes),
- ((1 << txq->wqe_n) *
- MLX5_WQE_SIZE));
- }
- return;
- }
-#endif /* NDEBUG */
- ++cq_ci;
- txq->wqe_pi = rte_be_to_cpu_16(cqe->wqe_counter);
- ctrl = (volatile struct mlx5_wqe_ctrl *)
- tx_mlx5_wqe(txq, txq->wqe_pi);
- elts_tail = ctrl->ctrl3;
- assert((elts_tail & elts_m) < (1 << txq->wqe_n));
- /* Free buffers. */
- while (elts_free != elts_tail) {
- m = rte_pktmbuf_prefree_seg((*txq->elts)[elts_free++ & elts_m]);
- if (likely(m != NULL)) {
- if (likely(m->pool == pool)) {
- free[blk_n++] = m;
- } else {
- if (likely(pool != NULL))
- rte_mempool_put_bulk(pool,
- (void *)free,
- blk_n);
- free[0] = m;
- pool = m->pool;
- blk_n = 1;
- }
- }
- }
- if (blk_n)
- rte_mempool_put_bulk(pool, (void *)free, blk_n);
-#ifndef NDEBUG
- elts_free = txq->elts_tail;
- /* Poisoning. */
- while (elts_free != elts_tail) {
- memset(&(*txq->elts)[elts_free & elts_m],
- 0x66,
- sizeof((*txq->elts)[elts_free & elts_m]));
- ++elts_free;
- }
-#endif
- txq->cq_ci = cq_ci;
- txq->elts_tail = elts_tail;
- /* Update the consumer index. */
- rte_compiler_barrier();
- *txq->cq_db = rte_cpu_to_be_32(cq_ci);
+ return MLX5_CQE_STATUS_HW_OWN;
+ rte_cio_rmb();
+ if (unlikely(op_code == MLX5_CQE_RESP_ERR ||
+ op_code == MLX5_CQE_REQ_ERR))
+ return MLX5_CQE_STATUS_ERR;
+ return MLX5_CQE_STATUS_SW_OWN;
}
/**
* @return
* Memory pool where data is located for given mbuf.
*/
-static struct rte_mempool *
+static inline struct rte_mempool *
mlx5_mb2mp(struct rte_mbuf *buf)
{
- if (unlikely(RTE_MBUF_INDIRECT(buf)))
+ if (unlikely(RTE_MBUF_CLONED(buf)))
return rte_mbuf_from_indirect(buf)->pool;
return buf->pool;
}
* Searched LKey on success, UINT32_MAX on no match.
*/
static __rte_always_inline uint32_t
-mlx5_tx_addr2mr(struct mlx5_txq_data *txq, uintptr_t addr)
+mlx5_tx_mb2mr(struct mlx5_txq_data *txq, struct rte_mbuf *mb)
{
struct mlx5_mr_ctrl *mr_ctrl = &txq->mr_ctrl;
+ uintptr_t addr = (uintptr_t)mb->buf_addr;
uint32_t lkey;
/* Check generation bit to see if there's any change on existing MRs. */
MLX5_MR_CACHE_N, addr);
if (likely(lkey != UINT32_MAX))
return lkey;
- /* Take slower bottom-half (binary search) on miss. */
- return mlx5_tx_addr2mr_bh(txq, addr);
-}
-
-static __rte_always_inline uint32_t
-mlx5_tx_mb2mr(struct mlx5_txq_data *txq, struct rte_mbuf *mb)
-{
- uintptr_t addr = (uintptr_t)mb->buf_addr;
- uint32_t lkey = mlx5_tx_addr2mr(txq, addr);
-
- if (likely(lkey != UINT32_MAX))
- return lkey;
- if (rte_errno == ENXIO) {
- /* Mempool may have externally allocated memory. */
- lkey = mlx5_tx_update_ext_mp(txq, addr, mlx5_mb2mp(mb));
- }
- return lkey;
+ /* Take slower bottom-half on miss. */
+ return mlx5_tx_mb2mr_bh(txq, mb);
}
/**
mlx5_tx_dbrec_cond_wmb(struct mlx5_txq_data *txq, volatile struct mlx5_wqe *wqe,
int cond)
{
- uint64_t *dst = (uint64_t *)((uintptr_t)txq->bf_reg);
+ uint64_t *dst = MLX5_TX_BFREG(txq);
volatile uint64_t *src = ((volatile uint64_t *)wqe);
rte_cio_wmb();
mlx5_tx_dbrec_cond_wmb(txq, wqe, 1);
}
-/**
- * Convert mbuf to Verb SWP.
- *
- * @param txq_data
- * Pointer to the Tx queue.
- * @param buf
- * Pointer to the mbuf.
- * @param tso
- * TSO offloads enabled.
- * @param vlan
- * VLAN offloads enabled
- * @param offsets
- * Pointer to the SWP header offsets.
- * @param swp_types
- * Pointer to the SWP header types.
- */
-static __rte_always_inline void
-txq_mbuf_to_swp(struct mlx5_txq_data *txq, struct rte_mbuf *buf,
- uint8_t *offsets, uint8_t *swp_types)
-{
- const uint64_t vlan = buf->ol_flags & PKT_TX_VLAN_PKT;
- const uint64_t tunnel = buf->ol_flags & PKT_TX_TUNNEL_MASK;
- const uint64_t tso = buf->ol_flags & PKT_TX_TCP_SEG;
- const uint64_t csum_flags = buf->ol_flags & PKT_TX_L4_MASK;
- const uint64_t inner_ip =
- buf->ol_flags & (PKT_TX_IPV4 | PKT_TX_IPV6);
- const uint64_t ol_flags_mask = PKT_TX_L4_MASK | PKT_TX_IPV6 |
- PKT_TX_OUTER_IPV6;
- uint16_t idx;
- uint16_t off;
-
- if (likely(!txq->swp_en || (tunnel != PKT_TX_TUNNEL_UDP &&
- tunnel != PKT_TX_TUNNEL_IP)))
- return;
- /*
- * The index should have:
- * bit[0:1] = PKT_TX_L4_MASK
- * bit[4] = PKT_TX_IPV6
- * bit[8] = PKT_TX_OUTER_IPV6
- * bit[9] = PKT_TX_OUTER_UDP
- */
- idx = (buf->ol_flags & ol_flags_mask) >> 52;
- if (tunnel == PKT_TX_TUNNEL_UDP)
- idx |= 1 << 9;
- *swp_types = mlx5_swp_types_table[idx];
- /*
- * Set offsets for SW parser. Since ConnectX-5, SW parser just
- * complements HW parser. SW parser starts to engage only if HW parser
- * can't reach a header. For the older devices, HW parser will not kick
- * in if any of SWP offsets is set. Therefore, all of the L3 offsets
- * should be set regardless of HW offload.
- */
- off = buf->outer_l2_len + (vlan ? sizeof(struct vlan_hdr) : 0);
- offsets[1] = off >> 1; /* Outer L3 offset. */
- off += buf->outer_l3_len;
- if (tunnel == PKT_TX_TUNNEL_UDP)
- offsets[0] = off >> 1; /* Outer L4 offset. */
- if (inner_ip) {
- off += buf->l2_len;
- offsets[3] = off >> 1; /* Inner L3 offset. */
- if (csum_flags == PKT_TX_TCP_CKSUM || tso ||
- csum_flags == PKT_TX_UDP_CKSUM) {
- off += buf->l3_len;
- offsets[2] = off >> 1; /* Inner L4 offset. */
- }
- }
-}
-
-/**
- * Convert the Checksum offloads to Verbs.
- *
- * @param buf
- * Pointer to the mbuf.
- *
- * @return
- * Converted checksum flags.
- */
-static __rte_always_inline uint8_t
-txq_ol_cksum_to_cs(struct rte_mbuf *buf)
-{
- uint32_t idx;
- uint8_t is_tunnel = !!(buf->ol_flags & PKT_TX_TUNNEL_MASK);
- const uint64_t ol_flags_mask = PKT_TX_TCP_SEG | PKT_TX_L4_MASK |
- PKT_TX_IP_CKSUM | PKT_TX_OUTER_IP_CKSUM;
-
- /*
- * The index should have:
- * bit[0] = PKT_TX_TCP_SEG
- * bit[2:3] = PKT_TX_UDP_CKSUM, PKT_TX_TCP_CKSUM
- * bit[4] = PKT_TX_IP_CKSUM
- * bit[8] = PKT_TX_OUTER_IP_CKSUM
- * bit[9] = tunnel
- */
- idx = ((buf->ol_flags & ol_flags_mask) >> 50) | (!!is_tunnel << 9);
- return mlx5_cksum_table[idx];
-}
-
-/**
- * Count the number of contiguous single segment packets.
- *
- * @param pkts
- * Pointer to array of packets.
- * @param pkts_n
- * Number of packets.
- *
- * @return
- * Number of contiguous single segment packets.
- */
-static __rte_always_inline unsigned int
-txq_count_contig_single_seg(struct rte_mbuf **pkts, uint16_t pkts_n)
-{
- unsigned int pos;
-
- if (!pkts_n)
- return 0;
- /* Count the number of contiguous single segment packets. */
- for (pos = 0; pos < pkts_n; ++pos)
- if (NB_SEGS(pkts[pos]) > 1)
- break;
- return pos;
-}
-
-/**
- * Count the number of contiguous multi-segment packets.
- *
- * @param pkts
- * Pointer to array of packets.
- * @param pkts_n
- * Number of packets.
- *
- * @return
- * Number of contiguous multi-segment packets.
- */
-static __rte_always_inline unsigned int
-txq_count_contig_multi_seg(struct rte_mbuf **pkts, uint16_t pkts_n)
-{
- unsigned int pos;
-
- if (!pkts_n)
- return 0;
- /* Count the number of contiguous multi-segment packets. */
- for (pos = 0; pos < pkts_n; ++pos)
- if (NB_SEGS(pkts[pos]) == 1)
- break;
- return pos;
-}
-
#endif /* RTE_PMD_MLX5_RXTX_H_ */