#include <stdint.h>
#include <sys/queue.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/mlx5dv.h>
-#ifdef PEDANTIC
-#pragma GCC diagnostic error "-Wpedantic"
-#endif
-
#include <rte_mbuf.h>
#include <rte_mempool.h>
#include <rte_common.h>
#include <rte_spinlock.h>
#include <rte_io.h>
#include <rte_bus_pci.h>
+#include <rte_malloc.h>
+#include <rte_cycles.h>
+
+#include <mlx5_glue.h>
+#include <mlx5_prm.h>
+#include <mlx5_common.h>
+#include <mlx5_common_mr.h>
+#include "mlx5_defs.h"
#include "mlx5_utils.h"
#include "mlx5.h"
-#include "mlx5_mr.h"
#include "mlx5_autoconf.h"
-#include "mlx5_defs.h"
-#include "mlx5_prm.h"
+#include "mlx5_mr.h"
/* Support tunnel matching. */
-#define MLX5_FLOW_TUNNEL 5
+#define MLX5_FLOW_TUNNEL 10
+
+/* Mbuf dynamic flag offset for inline. */
+extern uint64_t rte_net_mlx5_dynf_inline_mask;
struct mlx5_rxq_stats {
#ifdef MLX5_PMD_SOFT_COUNTERS
/* Multi-Packet RQ buffer header. */
struct mlx5_mprq_buf {
struct rte_mempool *mp;
- rte_atomic16_t refcnt; /* Atomically accessed refcnt. */
+ uint16_t refcnt; /* Atomically accessed refcnt. */
uint8_t pad[RTE_PKTMBUF_HEADROOM]; /* Headroom for the first packet. */
+ struct rte_mbuf_ext_shared_info shinfos[];
+ /*
+ * Shared information per stride.
+ * More memory will be allocated for the first stride head-room and for
+ * the strides data.
+ */
} __rte_cache_aligned;
/* Get pointer to the first stride. */
-#define mlx5_mprq_buf_addr(ptr) ((ptr) + 1)
+#define mlx5_mprq_buf_addr(ptr, strd_n) (RTE_PTR_ADD((ptr), \
+ sizeof(struct mlx5_mprq_buf) + \
+ (strd_n) * \
+ sizeof(struct rte_mbuf_ext_shared_info) + \
+ RTE_PKTMBUF_HEADROOM))
+
+#define MLX5_MIN_SINGLE_STRIDE_LOG_NUM_BYTES 6
+#define MLX5_MIN_SINGLE_WQE_LOG_NUM_STRIDES 9
+
+enum mlx5_rxq_err_state {
+ MLX5_RXQ_ERR_STATE_NO_ERROR = 0,
+ MLX5_RXQ_ERR_STATE_NEED_RESET,
+ MLX5_RXQ_ERR_STATE_NEED_READY,
+};
+
+enum mlx5_rqx_code {
+ MLX5_RXQ_CODE_EXIT = 0,
+ MLX5_RXQ_CODE_NOMBUF,
+ MLX5_RXQ_CODE_DROPPED,
+};
+
+struct mlx5_eth_rxseg {
+ struct rte_mempool *mp; /**< Memory pool to allocate segment from. */
+ uint16_t length; /**< Segment data length, configures split point. */
+ uint16_t offset; /**< Data offset from beginning of mbuf data buffer. */
+ uint32_t reserved; /**< Reserved field. */
+};
/* RX queue descriptor. */
struct mlx5_rxq_data {
unsigned int csum:1; /* Enable checksum offloading. */
unsigned int hw_timestamp:1; /* Enable HW timestamp. */
+ unsigned int rt_timestamp:1; /* Realtime timestamp format. */
unsigned int vlan_strip:1; /* Enable VLAN stripping. */
unsigned int crc_present:1; /* CRC must be subtracted. */
- unsigned int sges_n:2; /* Log 2 of SGEs (max buffers per packet). */
+ unsigned int sges_n:3; /* Log 2 of SGEs (max buffers per packet). */
unsigned int cqe_n:4; /* Log 2 of CQ elements. */
unsigned int elts_n:4; /* Log 2 of Mbufs. */
unsigned int rss_hash:1; /* RSS hash result is enabled. */
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 strd_scatter_en:1; /* Scattered packets from a stride. */
+ unsigned int lro:1; /* Enable LRO. */
+ unsigned int dynf_meta:1; /* Dynamic metadata is configured. */
volatile uint32_t *rq_db;
volatile uint32_t *cq_db;
uint16_t port_id;
+ uint32_t elts_ci;
uint32_t rq_ci;
uint16_t consumed_strd; /* Number of consumed strides in WQE. */
uint32_t rq_pi;
uint16_t mprq_max_memcpy_len; /* Maximum size of packet to memcpy. */
volatile void *wqes;
volatile struct mlx5_cqe(*cqes)[];
- RTE_STD_C11
- union {
- struct rte_mbuf *(*elts)[];
- struct mlx5_mprq_buf *(*mprq_bufs)[];
- };
+ struct rte_mbuf *(*elts)[];
+ struct mlx5_mprq_buf *(*mprq_bufs)[];
struct rte_mempool *mp;
struct rte_mempool *mprq_mp; /* Mempool for Multi-Packet RQ. */
struct mlx5_mprq_buf *mprq_repl; /* Stashed mbuf for replenish. */
+ struct mlx5_dev_ctx_shared *sh; /* Shared context. */
uint16_t idx; /* Queue index. */
struct mlx5_rxq_stats stats;
- uint64_t mbuf_initializer; /* Default rearm_data for vectorized Rx. */
+ rte_xmm_t mbuf_initializer; /* Default rearm/flags for vectorized Rx. */
struct rte_mbuf fake_mbuf; /* elts padding for vectorized Rx. */
- void *cq_uar; /* CQ user access region. */
+ void *cq_uar; /* Verbs CQ user access region. */
uint32_t cqn; /* CQ number. */
uint8_t cq_arm_sn; /* CQ arm seq number. */
#ifndef RTE_ARCH_64
/* CQ (UAR) access lock required for 32bit implementations */
#endif
uint32_t tunnel; /* Tunnel information. */
+ int timestamp_offset; /* Dynamic mbuf field for timestamp. */
+ uint64_t timestamp_rx_flag; /* Dynamic mbuf flag for timestamp. */
+ uint64_t flow_meta_mask;
+ int32_t flow_meta_offset;
+ uint32_t rxseg_n; /* Number of split segment descriptions. */
+ struct mlx5_eth_rxseg rxseg[MLX5_MAX_RXQ_NSEG];
+ /* Buffer split segment descriptions - sizes, offsets, pools. */
} __rte_cache_aligned;
-/* Verbs Rx queue elements. */
-struct mlx5_rxq_ibv {
- LIST_ENTRY(mlx5_rxq_ibv) next; /* Pointer to the next element. */
- rte_atomic32_t refcnt; /* Reference counter. */
- struct mlx5_rxq_ctrl *rxq_ctrl; /* Back pointer to parent. */
- struct ibv_cq *cq; /* Completion Queue. */
- struct ibv_wq *wq; /* Work Queue. */
- struct ibv_comp_channel *channel;
+enum mlx5_rxq_type {
+ MLX5_RXQ_TYPE_STANDARD, /* Standard Rx queue. */
+ MLX5_RXQ_TYPE_HAIRPIN, /* Hairpin Rx queue. */
+ MLX5_RXQ_TYPE_UNDEFINED,
};
/* 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. */
+ uint32_t refcnt; /* Reference counter. */
+ struct mlx5_rxq_obj *obj; /* Verbs/DevX elements. */
struct mlx5_priv *priv; /* Back pointer to private data. */
+ enum mlx5_rxq_type type; /* Rxq type. */
unsigned int socket; /* CPU socket ID for allocations. */
unsigned int irq:1; /* Whether IRQ is enabled. */
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. */
+ struct mlx5_devx_dbr_page *rq_dbrec_page;
+ uint64_t rq_dbr_offset;
+ /* Storing RQ door-bell information, needed when freeing door-bell. */
+ struct mlx5_devx_dbr_page *cq_dbrec_page;
+ uint64_t cq_dbr_offset;
+ /* Storing CQ door-bell information, needed when freeing door-bell. */
+ void *wq_umem; /* WQ buffer registration info. */
+ void *cq_umem; /* CQ buffer registration info. */
+ struct rte_eth_hairpin_conf hairpin_conf; /* Hairpin configuration. */
};
-/* Indirection table. */
-struct mlx5_ind_table_ibv {
- LIST_ENTRY(mlx5_ind_table_ibv) next; /* Pointer to the next element. */
- rte_atomic32_t refcnt; /* Reference counter. */
- struct ibv_rwq_ind_table *ind_table; /**< Indirection table. */
- uint32_t queues_n; /**< Number of queues in the list. */
- uint16_t queues[]; /**< Queue list. */
-};
-
-/* Hash Rx queue. */
-struct mlx5_hrxq {
- LIST_ENTRY(mlx5_hrxq) next; /* Pointer to the next element. */
- 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. */
+/* TX queue send local data. */
+__extension__
+struct mlx5_txq_local {
+ struct mlx5_wqe *wqe_last; /* last sent WQE pointer. */
+ struct rte_mbuf *mbuf; /* first mbuf to process. */
+ uint16_t pkts_copy; /* packets copied to elts. */
+ uint16_t pkts_sent; /* packets sent. */
+ uint16_t pkts_loop; /* packets sent on loop entry. */
+ uint16_t elts_free; /* available elts remain. */
+ uint16_t wqe_free; /* available wqe remain. */
+ uint16_t mbuf_off; /* data offset in current mbuf. */
+ uint16_t mbuf_nseg; /* number of remaining mbuf. */
};
/* TX queue descriptor. */
struct mlx5_txq_data {
uint16_t elts_head; /* Current counter in (*elts)[]. */
uint16_t elts_tail; /* Counter of first element awaiting completion. */
- uint16_t elts_comp; /* Counter since last completion request. */
- uint16_t mpw_comp; /* WQ index since last completion request. */
- uint16_t cq_ci; /* Consumer index for completion queue. */
-#ifndef NDEBUG
- uint16_t cq_pi; /* Producer index for completion queue. */
-#endif
+ uint16_t elts_comp; /* elts index since last completion request. */
+ uint16_t elts_s; /* Number of mbuf elements. */
+ uint16_t elts_m; /* Mask for mbuf elements indices. */
+ /* Fields related to elts mbuf storage. */
uint16_t wqe_ci; /* Consumer index for work queue. */
uint16_t wqe_pi; /* Producer index for work queue. */
- uint16_t elts_n:4; /* (*elts)[] length (in log2). */
+ uint16_t wqe_s; /* Number of WQ elements. */
+ uint16_t wqe_m; /* Mask Number for WQ elements. */
+ uint16_t wqe_comp; /* WQE index since last completion request. */
+ uint16_t wqe_thres; /* WQE threshold to request completion in CQ. */
+ /* WQ related fields. */
+ uint16_t cq_ci; /* Consumer index for completion queue. */
+ uint16_t cq_pi; /* Production index for completion queue. */
+ uint16_t cqe_s; /* Number of CQ elements. */
+ uint16_t cqe_m; /* Mask for CQ indices. */
+ /* CQ related fields. */
+ uint16_t elts_n:4; /* elts[] length (in log2). */
uint16_t cqe_n:4; /* Number of CQ elements (in log2). */
- uint16_t wqe_n:4; /* Number of of WQ elements (in log2). */
+ uint16_t wqe_n:4; /* Number of WQ elements (in log2). */
uint16_t tso_en:1; /* When set hardware TSO is enabled. */
uint16_t tunnel_en:1;
/* When set TX offload for tunneled packets are supported. */
uint16_t swp_en:1; /* Whether SW parser is enabled. */
- uint16_t mpw_hdr_dseg:1; /* Enable DSEGs in the title WQEBB. */
- uint16_t max_inline; /* Multiple of RTE_CACHE_LINE_SIZE to inline. */
- uint16_t inline_max_packet_sz; /* Max packet size for inlining. */
+ uint16_t vlan_en:1; /* VLAN insertion in WQE is supported. */
+ uint16_t db_nc:1; /* Doorbell mapped to non-cached region. */
+ uint16_t db_heu:1; /* Doorbell heuristic write barrier. */
+ uint16_t inlen_send; /* Ordinary send data inline size. */
+ uint16_t inlen_empw; /* eMPW max packet size to inline. */
+ uint16_t inlen_mode; /* Minimal data length to inline. */
uint32_t qp_num_8s; /* QP number shifted by 8. */
uint64_t offloads; /* Offloads for Tx Queue. */
struct mlx5_mr_ctrl mr_ctrl; /* MR control descriptor. */
- volatile struct mlx5_cqe (*cqes)[]; /* Completion queue. */
- volatile void *wqes; /* Work queue (use volatile to write into). */
+ struct mlx5_wqe *wqes; /* Work queue. */
+ struct mlx5_wqe *wqes_end; /* Work queue array limit. */
+#ifdef RTE_LIBRTE_MLX5_DEBUG
+ uint32_t *fcqs; /* Free completion queue (debug extended). */
+#else
+ uint16_t *fcqs; /* Free completion queue. */
+#endif
+ volatile struct mlx5_cqe *cqes; /* Completion queue. */
volatile uint32_t *qp_db; /* Work queue doorbell. */
volatile uint32_t *cq_db; /* Completion queue doorbell. */
- struct rte_mbuf *(*elts)[]; /* TX elements. */
uint16_t port_id; /* Port ID of device. */
uint16_t idx; /* Queue index. */
+ uint64_t ts_mask; /* Timestamp flag dynamic mask. */
+ int32_t ts_offset; /* Timestamp field dynamic offset. */
+ struct mlx5_dev_ctx_shared *sh; /* Shared context. */
struct mlx5_txq_stats stats; /* TX queue counters. */
#ifndef RTE_ARCH_64
rte_spinlock_t *uar_lock;
/* UAR access lock required for 32bit implementations */
#endif
+ struct rte_mbuf *elts[0];
+ /* Storage for queued packets, must be the last field. */
} __rte_cache_aligned;
-/* Verbs Rx queue elements. */
-struct mlx5_txq_ibv {
- LIST_ENTRY(mlx5_txq_ibv) next; /* Pointer to the next element. */
- rte_atomic32_t refcnt; /* Reference counter. */
- struct mlx5_txq_ctrl *txq_ctrl; /* Pointer to the control queue. */
- struct ibv_cq *cq; /* Completion Queue. */
- struct ibv_qp *qp; /* Queue Pair. */
+enum mlx5_txq_type {
+ MLX5_TXQ_TYPE_STANDARD, /* Standard Tx queue. */
+ MLX5_TXQ_TYPE_HAIRPIN, /* Hairpin Rx queue. */
};
/* 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. */
+ uint32_t refcnt; /* Reference counter. */
unsigned int socket; /* CPU socket ID for allocations. */
+ enum mlx5_txq_type type; /* The txq ctrl type. */
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 mlx5_txq_obj *obj; /* Verbs/DevX queue object. */
struct mlx5_priv *priv; /* Back pointer to private data. */
off_t uar_mmap_offset; /* UAR mmap offset for non-primary process. */
void *bf_reg; /* BlueFlame register from Verbs. */
+ uint16_t dump_file_n; /* Number of dump files. */
+ struct rte_eth_hairpin_conf hairpin_conf; /* Hairpin configuration. */
+ struct mlx5_txq_data txq; /* Data path structure. */
+ /* Must be the last field in the structure, contains elts[]. */
};
#define MLX5_TX_BFREG(txq) \
int mlx5_check_mprq_support(struct rte_eth_dev *dev);
int mlx5_rxq_mprq_enabled(struct mlx5_rxq_data *rxq);
int mlx5_mprq_enabled(struct rte_eth_dev *dev);
+unsigned int mlx5_rxq_cqe_num(struct mlx5_rxq_data *rxq_data);
int mlx5_mprq_free_mp(struct rte_eth_dev *dev);
int mlx5_mprq_alloc_mp(struct rte_eth_dev *dev);
+int mlx5_rx_queue_start(struct rte_eth_dev *dev, uint16_t queue_id);
+int mlx5_rx_queue_stop(struct rte_eth_dev *dev, uint16_t queue_id);
+int mlx5_rx_queue_start_primary(struct rte_eth_dev *dev, uint16_t queue_id);
+int mlx5_rx_queue_stop_primary(struct rte_eth_dev *dev, uint16_t queue_id);
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_hairpin_queue_setup
+ (struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+ const struct rte_eth_hairpin_conf *hairpin_conf);
void mlx5_rx_queue_release(void *dpdk_rxq);
int mlx5_rx_intr_vec_enable(struct rte_eth_dev *dev);
void mlx5_rx_intr_vec_disable(struct rte_eth_dev *dev);
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);
-int mlx5_rxq_ibv_verify(struct rte_eth_dev *dev);
+int mlx5_rxq_obj_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,
const struct rte_eth_rxconf *conf,
- struct rte_mempool *mp);
+ const struct rte_eth_rxseg_split *rx_seg,
+ uint16_t n_seg);
+struct mlx5_rxq_ctrl *mlx5_rxq_hairpin_new
+ (struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+ const struct rte_eth_hairpin_conf *hairpin_conf);
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_verify(struct rte_eth_dev *dev);
int rxq_alloc_elts(struct mlx5_rxq_ctrl *rxq_ctrl);
-int mlx5_ind_table_ibv_verify(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,
- const uint16_t *queues, uint32_t queues_n,
- int tunnel __rte_unused);
-struct mlx5_hrxq *mlx5_hrxq_get(struct rte_eth_dev *dev,
- const uint8_t *rss_key, uint32_t rss_key_len,
- uint64_t hash_fields,
- const uint16_t *queues, uint32_t queues_n);
-int mlx5_hrxq_release(struct rte_eth_dev *dev, struct mlx5_hrxq *hxrq);
-int mlx5_hrxq_ibv_verify(struct rte_eth_dev *dev);
-struct mlx5_hrxq *mlx5_hrxq_drop_new(struct rte_eth_dev *dev);
-void mlx5_hrxq_drop_release(struct rte_eth_dev *dev);
+int mlx5_ind_table_obj_verify(struct rte_eth_dev *dev);
+struct mlx5_ind_table_obj *mlx5_ind_table_obj_get(struct rte_eth_dev *dev,
+ const uint16_t *queues,
+ uint32_t queues_n);
+int mlx5_ind_table_obj_release(struct rte_eth_dev *dev,
+ struct mlx5_ind_table_obj *ind_tbl);
+uint32_t mlx5_hrxq_new(struct rte_eth_dev *dev,
+ const uint8_t *rss_key, uint32_t rss_key_len,
+ uint64_t hash_fields,
+ const uint16_t *queues, uint32_t queues_n,
+ int tunnel, bool shared);
+uint32_t mlx5_hrxq_get(struct rte_eth_dev *dev,
+ const uint8_t *rss_key, uint32_t rss_key_len,
+ uint64_t hash_fields,
+ const uint16_t *queues, uint32_t queues_n);
+int mlx5_hrxq_release(struct rte_eth_dev *dev, uint32_t hxrq_idx);
+int mlx5_hrxq_verify(struct rte_eth_dev *dev);
+enum mlx5_rxq_type mlx5_rxq_get_type(struct rte_eth_dev *dev, uint16_t idx);
+struct mlx5_hrxq *mlx5_drop_action_create(struct rte_eth_dev *dev);
+void mlx5_drop_action_destroy(struct rte_eth_dev *dev);
uint64_t mlx5_get_rx_port_offloads(void);
uint64_t mlx5_get_rx_queue_offloads(struct rte_eth_dev *dev);
+void mlx5_rxq_timestamp_set(struct rte_eth_dev *dev);
+int mlx5_hrxq_modify(struct rte_eth_dev *dev, uint32_t hxrq_idx,
+ const uint8_t *rss_key, uint32_t rss_key_len,
+ uint64_t hash_fields,
+ const uint16_t *queues, uint32_t queues_n);
/* mlx5_txq.c */
+int mlx5_tx_queue_start(struct rte_eth_dev *dev, uint16_t queue_id);
+int mlx5_tx_queue_stop(struct rte_eth_dev *dev, uint16_t queue_id);
+int mlx5_tx_queue_start_primary(struct rte_eth_dev *dev, uint16_t queue_id);
+int mlx5_tx_queue_stop_primary(struct rte_eth_dev *dev, uint16_t queue_id);
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);
+int mlx5_tx_hairpin_queue_setup
+ (struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+ const struct rte_eth_hairpin_conf *hairpin_conf);
void mlx5_tx_queue_release(void *dpdk_txq);
+void txq_uar_init(struct mlx5_txq_ctrl *txq_ctrl);
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_verify(struct rte_eth_dev *dev);
+void mlx5_tx_uar_uninit_secondary(struct rte_eth_dev *dev);
+int mlx5_txq_obj_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,
const struct rte_eth_txconf *conf);
+struct mlx5_txq_ctrl *mlx5_txq_hairpin_new
+ (struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
+ const struct rte_eth_hairpin_conf *hairpin_conf);
struct mlx5_txq_ctrl *mlx5_txq_get(struct rte_eth_dev *dev, uint16_t idx);
int mlx5_txq_release(struct rte_eth_dev *dev, uint16_t idx);
int mlx5_txq_releasable(struct rte_eth_dev *dev, uint16_t idx);
int mlx5_txq_verify(struct rte_eth_dev *dev);
void txq_alloc_elts(struct mlx5_txq_ctrl *txq_ctrl);
+void txq_free_elts(struct mlx5_txq_ctrl *txq_ctrl);
uint64_t mlx5_get_tx_port_offloads(struct rte_eth_dev *dev);
+void mlx5_txq_dynf_timestamp_set(struct rte_eth_dev *dev);
/* mlx5_rxtx.c */
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);
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 vec);
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,
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);
+void mlx5_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
+ struct rte_eth_rxq_info *qinfo);
+void mlx5_txq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
+ struct rte_eth_txq_info *qinfo);
+int mlx5_rx_burst_mode_get(struct rte_eth_dev *dev, uint16_t rx_queue_id,
+ struct rte_eth_burst_mode *mode);
+int mlx5_tx_burst_mode_get(struct rte_eth_dev *dev, uint16_t tx_queue_id,
+ struct rte_eth_burst_mode *mode);
/* 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);
+uint16_t mlx5_rx_burst_mprq_vec(void *dpdk_txq, struct rte_mbuf **pkts,
+ uint16_t pkts_n);
/* mlx5_mr.c */
#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 */
-
-/**
- * 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 __rte_always_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)) {
- 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(*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;
- rte_cio_rmb();
- 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);
-}
-
/**
* Get Memory Pool (MP) from mbuf. If mbuf is indirect, the pool from which the
* cloned mbuf is allocated is returned instead.
uint32_t lkey;
/* Linear search on MR cache array. */
- lkey = mlx5_mr_lookup_cache(mr_ctrl->cache, &mr_ctrl->mru,
- MLX5_MR_CACHE_N, addr);
+ lkey = mlx5_mr_lookup_lkey(mr_ctrl->cache, &mr_ctrl->mru,
+ MLX5_MR_CACHE_N, addr);
if (likely(lkey != UINT32_MAX))
return lkey;
/* Take slower bottom-half (Binary Search) on miss. */
if (unlikely(*mr_ctrl->dev_gen_ptr != mr_ctrl->cur_gen))
mlx5_mr_flush_local_cache(mr_ctrl);
/* Linear search on MR cache array. */
- lkey = mlx5_mr_lookup_cache(mr_ctrl->cache, &mr_ctrl->mru,
- MLX5_MR_CACHE_N, addr);
+ lkey = mlx5_mr_lookup_lkey(mr_ctrl->cache, &mr_ctrl->mru,
+ MLX5_MR_CACHE_N, addr);
if (likely(lkey != UINT32_MAX))
return lkey;
/* Take slower bottom-half on miss. */
uint64_t *dst = MLX5_TX_BFREG(txq);
volatile uint64_t *src = ((volatile uint64_t *)wqe);
- rte_cio_wmb();
+ rte_io_wmb();
*txq->qp_db = rte_cpu_to_be_32(txq->wqe_ci);
/* Ensure ordering between DB record and BF copy. */
rte_wmb();
}
/**
- * Convert mbuf to Verb SWP.
+ * Convert timestamp from HW format to linear counter
+ * from Packet Pacing Clock Queue CQE timestamp format.
*
- * @param txq_data
- * Pointer to the Tx queue.
- * @param buf
- * Pointer to the mbuf.
- * @param offsets
- * Pointer to the SWP header offsets.
- * @param swp_types
- * Pointer to the SWP header types.
+ * @param sh
+ * Pointer to the device shared context. Might be needed
+ * to convert according current device configuration.
+ * @param ts
+ * Timestamp from CQE to convert.
+ * @return
+ * UTC in nanoseconds
*/
-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)
+static __rte_always_inline uint64_t
+mlx5_txpp_convert_rx_ts(struct mlx5_dev_ctx_shared *sh, uint64_t ts)
{
- const uint64_t vlan = buf->ol_flags & PKT_TX_VLAN_PKT;
- const uint64_t tunnel = buf->ol_flags & PKT_TX_TUNNEL_MASK;
- const uint64_t tso = buf->ol_flags & PKT_TX_TCP_SEG;
- const uint64_t csum_flags = buf->ol_flags & PKT_TX_L4_MASK;
- const uint64_t inner_ip =
- buf->ol_flags & (PKT_TX_IPV4 | PKT_TX_IPV6);
- const uint64_t ol_flags_mask = PKT_TX_L4_MASK | PKT_TX_IPV6 |
- PKT_TX_OUTER_IPV6;
- uint16_t idx;
- uint16_t off;
-
- if (likely(!txq->swp_en || (tunnel != PKT_TX_TUNNEL_UDP &&
- tunnel != PKT_TX_TUNNEL_IP)))
- return;
- /*
- * The index should have:
- * bit[0:1] = PKT_TX_L4_MASK
- * bit[4] = PKT_TX_IPV6
- * bit[8] = PKT_TX_OUTER_IPV6
- * bit[9] = PKT_TX_OUTER_UDP
- */
- idx = (buf->ol_flags & ol_flags_mask) >> 52;
- if (tunnel == PKT_TX_TUNNEL_UDP)
- idx |= 1 << 9;
- *swp_types = mlx5_swp_types_table[idx];
- /*
- * Set offsets for SW parser. Since ConnectX-5, SW parser just
- * complements HW parser. SW parser starts to engage only if HW parser
- * can't reach a header. For the older devices, HW parser will not kick
- * in if any of SWP offsets is set. Therefore, all of the L3 offsets
- * should be set regardless of HW offload.
- */
- off = buf->outer_l2_len + (vlan ? sizeof(struct rte_vlan_hdr) : 0);
- offsets[1] = off >> 1; /* Outer L3 offset. */
- off += buf->outer_l3_len;
- if (tunnel == PKT_TX_TUNNEL_UDP)
- offsets[0] = off >> 1; /* Outer L4 offset. */
- if (inner_ip) {
- off += buf->l2_len;
- offsets[3] = off >> 1; /* Inner L3 offset. */
- if (csum_flags == PKT_TX_TCP_CKSUM || tso ||
- csum_flags == PKT_TX_UDP_CKSUM) {
- off += buf->l3_len;
- offsets[2] = off >> 1; /* Inner L4 offset. */
- }
- }
+ RTE_SET_USED(sh);
+ return (ts & UINT32_MAX) + (ts >> 32) * NS_PER_S;
}
/**
- * Convert the Checksum offloads to Verbs.
- *
- * @param buf
- * Pointer to the mbuf.
+ * Convert timestamp from mbuf format to linear counter
+ * of Clock Queue completions (24 bits)
*
+ * @param sh
+ * Pointer to the device shared context to fetch Tx
+ * packet pacing timestamp and parameters.
+ * @param ts
+ * Timestamp from mbuf to convert.
* @return
- * Converted checksum flags.
+ * positive or zero value - completion ID to wait
+ * negative value - conversion error
*/
-static __rte_always_inline uint8_t
-txq_ol_cksum_to_cs(struct rte_mbuf *buf)
+static __rte_always_inline int32_t
+mlx5_txpp_convert_tx_ts(struct mlx5_dev_ctx_shared *sh, uint64_t mts)
{
- 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];
+ uint64_t ts, ci;
+ uint32_t tick;
+
+ do {
+ /*
+ * Read atomically two uint64_t fields and compare lsb bits.
+ * It there is no match - the timestamp was updated in
+ * the service thread, data should be re-read.
+ */
+ rte_compiler_barrier();
+ ci = rte_atomic64_read(&sh->txpp.ts.ci_ts);
+ ts = rte_atomic64_read(&sh->txpp.ts.ts);
+ rte_compiler_barrier();
+ if (!((ts ^ ci) << (64 - MLX5_CQ_INDEX_WIDTH)))
+ break;
+ } while (true);
+ /* Perform the skew correction, positive value to send earlier. */
+ mts -= sh->txpp.skew;
+ mts -= ts;
+ if (unlikely(mts >= UINT64_MAX / 2)) {
+ /* We have negative integer, mts is in the past. */
+ rte_atomic32_inc(&sh->txpp.err_ts_past);
+ return -1;
+ }
+ tick = sh->txpp.tick;
+ MLX5_ASSERT(tick);
+ /* Convert delta to completions, round up. */
+ mts = (mts + tick - 1) / tick;
+ if (unlikely(mts >= (1 << MLX5_CQ_INDEX_WIDTH) / 2 - 1)) {
+ /* We have mts is too distant future. */
+ rte_atomic32_inc(&sh->txpp.err_ts_future);
+ return -1;
+ }
+ mts <<= 64 - MLX5_CQ_INDEX_WIDTH;
+ ci += mts;
+ ci >>= 64 - MLX5_CQ_INDEX_WIDTH;
+ return ci;
}
/**
- * Count the number of contiguous single segment packets.
- *
- * @param pkts
- * Pointer to array of packets.
- * @param pkts_n
- * Number of packets.
+ * Set timestamp in mbuf dynamic field.
*
- * @return
- * Number of contiguous single segment packets.
+ * @param mbuf
+ * Structure to write into.
+ * @param offset
+ * Dynamic field offset in mbuf structure.
+ * @param timestamp
+ * Value to write.
*/
-static __rte_always_inline unsigned int
-txq_count_contig_single_seg(struct rte_mbuf **pkts, uint16_t pkts_n)
+static __rte_always_inline void
+mlx5_timestamp_set(struct rte_mbuf *mbuf, int offset,
+ rte_mbuf_timestamp_t timestamp)
{
- 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;
+ *RTE_MBUF_DYNFIELD(mbuf, offset, rte_mbuf_timestamp_t *) = timestamp;
}
/**
- * Count the number of contiguous multi-segment packets.
+ * Replace MPRQ buffer.
*
- * @param pkts
- * Pointer to array of packets.
- * @param pkts_n
- * Number of packets.
+ * @param rxq
+ * Pointer to Rx queue structure.
+ * @param rq_idx
+ * RQ index to replace.
+ */
+static __rte_always_inline void
+mprq_buf_replace(struct mlx5_rxq_data *rxq, uint16_t rq_idx)
+{
+ const uint32_t strd_n = 1 << rxq->strd_num_n;
+ struct mlx5_mprq_buf *rep = rxq->mprq_repl;
+ volatile struct mlx5_wqe_data_seg *wqe =
+ &((volatile struct mlx5_wqe_mprq *)rxq->wqes)[rq_idx].dseg;
+ struct mlx5_mprq_buf *buf = (*rxq->mprq_bufs)[rq_idx];
+ void *addr;
+
+ if (__atomic_load_n(&buf->refcnt, __ATOMIC_RELAXED) > 1) {
+ MLX5_ASSERT(rep != NULL);
+ /* Replace MPRQ buf. */
+ (*rxq->mprq_bufs)[rq_idx] = rep;
+ /* Replace WQE. */
+ addr = mlx5_mprq_buf_addr(rep, strd_n);
+ wqe->addr = rte_cpu_to_be_64((uintptr_t)addr);
+ /* If there's only one MR, no need to replace LKey in WQE. */
+ if (unlikely(mlx5_mr_btree_len(&rxq->mr_ctrl.cache_bh) > 1))
+ wqe->lkey = mlx5_rx_addr2mr(rxq, (uintptr_t)addr);
+ /* Stash a mbuf for next replacement. */
+ if (likely(!rte_mempool_get(rxq->mprq_mp, (void **)&rep)))
+ rxq->mprq_repl = rep;
+ else
+ rxq->mprq_repl = NULL;
+ /* Release the old buffer. */
+ mlx5_mprq_buf_free(buf);
+ } else if (unlikely(rxq->mprq_repl == NULL)) {
+ struct mlx5_mprq_buf *rep;
+
+ /*
+ * Currently, the MPRQ mempool is out of buffer
+ * and doing memcpy regardless of the size of Rx
+ * packet. Retry allocation to get back to
+ * normal.
+ */
+ if (!rte_mempool_get(rxq->mprq_mp, (void **)&rep))
+ rxq->mprq_repl = rep;
+ }
+}
+
+/**
+ * Attach or copy MPRQ buffer content to a packet.
*
- * @return
- * Number of contiguous multi-segment packets.
+ * @param rxq
+ * Pointer to Rx queue structure.
+ * @param pkt
+ * Pointer to a packet to fill.
+ * @param len
+ * Packet length.
+ * @param buf
+ * Pointer to a MPRQ buffer to take the data from.
+ * @param strd_idx
+ * Stride index to start from.
+ * @param strd_cnt
+ * Number of strides to consume.
*/
-static __rte_always_inline unsigned int
-txq_count_contig_multi_seg(struct rte_mbuf **pkts, uint16_t pkts_n)
+static __rte_always_inline enum mlx5_rqx_code
+mprq_buf_to_pkt(struct mlx5_rxq_data *rxq, struct rte_mbuf *pkt, uint32_t len,
+ struct mlx5_mprq_buf *buf, uint16_t strd_idx, uint16_t strd_cnt)
{
- unsigned int pos;
+ const uint32_t strd_n = 1 << rxq->strd_num_n;
+ const uint16_t strd_sz = 1 << rxq->strd_sz_n;
+ const uint16_t strd_shift =
+ MLX5_MPRQ_STRIDE_SHIFT_BYTE * rxq->strd_shift_en;
+ const int32_t hdrm_overlap =
+ len + RTE_PKTMBUF_HEADROOM - strd_cnt * strd_sz;
+ const uint32_t offset = strd_idx * strd_sz + strd_shift;
+ void *addr = RTE_PTR_ADD(mlx5_mprq_buf_addr(buf, strd_n), offset);
- 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;
+ /*
+ * Memcpy packets to the target mbuf if:
+ * - The size of packet is smaller than mprq_max_memcpy_len.
+ * - Out of buffer in the Mempool for Multi-Packet RQ.
+ * - The packet's stride overlaps a headroom and scatter is off.
+ */
+ if (len <= rxq->mprq_max_memcpy_len ||
+ rxq->mprq_repl == NULL ||
+ (hdrm_overlap > 0 && !rxq->strd_scatter_en)) {
+ if (likely(len <=
+ (uint32_t)(pkt->buf_len - RTE_PKTMBUF_HEADROOM))) {
+ rte_memcpy(rte_pktmbuf_mtod(pkt, void *),
+ addr, len);
+ DATA_LEN(pkt) = len;
+ } else if (rxq->strd_scatter_en) {
+ struct rte_mbuf *prev = pkt;
+ uint32_t seg_len = RTE_MIN(len, (uint32_t)
+ (pkt->buf_len - RTE_PKTMBUF_HEADROOM));
+ uint32_t rem_len = len - seg_len;
+
+ rte_memcpy(rte_pktmbuf_mtod(pkt, void *),
+ addr, seg_len);
+ DATA_LEN(pkt) = seg_len;
+ while (rem_len) {
+ struct rte_mbuf *next =
+ rte_pktmbuf_alloc(rxq->mp);
+
+ if (unlikely(next == NULL))
+ return MLX5_RXQ_CODE_NOMBUF;
+ NEXT(prev) = next;
+ SET_DATA_OFF(next, 0);
+ addr = RTE_PTR_ADD(addr, seg_len);
+ seg_len = RTE_MIN(rem_len, (uint32_t)
+ (next->buf_len - RTE_PKTMBUF_HEADROOM));
+ rte_memcpy
+ (rte_pktmbuf_mtod(next, void *),
+ addr, seg_len);
+ DATA_LEN(next) = seg_len;
+ rem_len -= seg_len;
+ prev = next;
+ ++NB_SEGS(pkt);
+ }
+ } else {
+ return MLX5_RXQ_CODE_DROPPED;
+ }
+ } else {
+ rte_iova_t buf_iova;
+ struct rte_mbuf_ext_shared_info *shinfo;
+ uint16_t buf_len = strd_cnt * strd_sz;
+ void *buf_addr;
+
+ /* Increment the refcnt of the whole chunk. */
+ __atomic_add_fetch(&buf->refcnt, 1, __ATOMIC_RELAXED);
+ MLX5_ASSERT(__atomic_load_n(&buf->refcnt,
+ __ATOMIC_RELAXED) <= strd_n + 1);
+ buf_addr = RTE_PTR_SUB(addr, RTE_PKTMBUF_HEADROOM);
+ /*
+ * MLX5 device doesn't use iova but it is necessary in a
+ * case where the Rx packet is transmitted via a
+ * different PMD.
+ */
+ buf_iova = rte_mempool_virt2iova(buf) +
+ RTE_PTR_DIFF(buf_addr, buf);
+ shinfo = &buf->shinfos[strd_idx];
+ rte_mbuf_ext_refcnt_set(shinfo, 1);
+ /*
+ * EXT_ATTACHED_MBUF will be set to pkt->ol_flags when
+ * attaching the stride to mbuf and more offload flags
+ * will be added below by calling rxq_cq_to_mbuf().
+ * Other fields will be overwritten.
+ */
+ rte_pktmbuf_attach_extbuf(pkt, buf_addr, buf_iova,
+ buf_len, shinfo);
+ /* Set mbuf head-room. */
+ SET_DATA_OFF(pkt, RTE_PKTMBUF_HEADROOM);
+ MLX5_ASSERT(pkt->ol_flags == EXT_ATTACHED_MBUF);
+ MLX5_ASSERT(rte_pktmbuf_tailroom(pkt) >=
+ len - (hdrm_overlap > 0 ? hdrm_overlap : 0));
+ DATA_LEN(pkt) = len;
+ /*
+ * Copy the last fragment of a packet (up to headroom
+ * size bytes) in case there is a stride overlap with
+ * a next packet's headroom. Allocate a separate mbuf
+ * to store this fragment and link it. Scatter is on.
+ */
+ if (hdrm_overlap > 0) {
+ MLX5_ASSERT(rxq->strd_scatter_en);
+ struct rte_mbuf *seg =
+ rte_pktmbuf_alloc(rxq->mp);
+
+ if (unlikely(seg == NULL))
+ return MLX5_RXQ_CODE_NOMBUF;
+ SET_DATA_OFF(seg, 0);
+ rte_memcpy(rte_pktmbuf_mtod(seg, void *),
+ RTE_PTR_ADD(addr, len - hdrm_overlap),
+ hdrm_overlap);
+ DATA_LEN(seg) = hdrm_overlap;
+ DATA_LEN(pkt) = len - hdrm_overlap;
+ NEXT(pkt) = seg;
+ NB_SEGS(pkt) = 2;
+ }
+ }
+ return MLX5_RXQ_CODE_EXIT;
}
#endif /* RTE_PMD_MLX5_RXTX_H_ */