> -----Original Message-----
> From: Michael Baum <michae...@nvidia.com>
> Sent: Monday, April 5, 2021 17:01
> To: dev@dpdk.org
> Cc: Matan Azrad <ma...@nvidia.com>; Raslan Darawsheh
> <rasl...@nvidia.com>; Slava Ovsiienko <viachesl...@nvidia.com>
> Subject: [PATCH 1/6] net/mlx5: separate Rx function declarations to another
> file
>
> The mlx5_rxtx.c file contains a lot of Tx burst functions, each of those
> is performance-optimized for the specific set of requested offloads.
> These ones are generated on the basis of the template function and it
> takes significant time to compile, just due to a large number of giant
> functions generated in the same file and this compilation is not being
> done in parallel with using multithreading.
>
> Therefore we can split the mlx5_rxtx.c file into several separate files
> to allow different functions to be compiled simultaneously.
> In this patch, we separate Rx function declarations to different header
> file in preparation for removing them from the source file and as an
> optional preparation step for further consolidation of Rx burst
> functions.
>
> Signed-off-by: Michael Baum <michae...@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viachesl...@nvidia.com>
> ---
> drivers/net/mlx5/linux/mlx5_mp_os.c | 1 +
> drivers/net/mlx5/linux/mlx5_os.c | 1 +
> drivers/net/mlx5/linux/mlx5_verbs.c | 1 +
> drivers/net/mlx5/mlx5.c | 1 +
> drivers/net/mlx5/mlx5_devx.c | 1 +
> drivers/net/mlx5/mlx5_ethdev.c | 1 +
> drivers/net/mlx5/mlx5_flow.c | 1 +
> drivers/net/mlx5/mlx5_flow_dv.c | 1 +
> drivers/net/mlx5/mlx5_flow_verbs.c | 1 +
> drivers/net/mlx5/mlx5_mr.c | 1 +
> drivers/net/mlx5/mlx5_rss.c | 1 +
> drivers/net/mlx5/mlx5_rx.h | 598
> ++++++++++++++++++++++++++++++++++++
> drivers/net/mlx5/mlx5_rxq.c | 1 +
> drivers/net/mlx5/mlx5_rxtx.c | 1 +
> drivers/net/mlx5/mlx5_rxtx.h | 569 ----------------------------------
> drivers/net/mlx5/mlx5_rxtx_vec.c | 1 +
> drivers/net/mlx5/mlx5_stats.c | 1 +
> drivers/net/mlx5/mlx5_trigger.c | 1 +
> drivers/net/mlx5/mlx5_txpp.c | 1 +
> drivers/net/mlx5/mlx5_vlan.c | 1 +
> drivers/net/mlx5/windows/mlx5_os.c | 1 +
> 21 files changed, 617 insertions(+), 569 deletions(-)
> create mode 100644 drivers/net/mlx5/mlx5_rx.h
>
> diff --git a/drivers/net/mlx5/linux/mlx5_mp_os.c
> b/drivers/net/mlx5/linux/mlx5_mp_os.c
> index 8011ca8..63fa278 100644
> --- a/drivers/net/mlx5/linux/mlx5_mp_os.c
> +++ b/drivers/net/mlx5/linux/mlx5_mp_os.c
> @@ -16,6 +16,7 @@
>
> #include "mlx5.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_utils.h"
>
> int
> diff --git a/drivers/net/mlx5/linux/mlx5_os.c
> b/drivers/net/mlx5/linux/mlx5_os.c
> index 2d5bcab..97a28ec 100644
> --- a/drivers/net/mlx5/linux/mlx5_os.c
> +++ b/drivers/net/mlx5/linux/mlx5_os.c
> @@ -40,6 +40,7 @@
> #include "mlx5_common_os.h"
> #include "mlx5_utils.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_autoconf.h"
> #include "mlx5_mr.h"
> #include "mlx5_flow.h"
> diff --git a/drivers/net/mlx5/linux/mlx5_verbs.c
> b/drivers/net/mlx5/linux/mlx5_verbs.c
> index c7d4b17..73096af 100644
> --- a/drivers/net/mlx5/linux/mlx5_verbs.c
> +++ b/drivers/net/mlx5/linux/mlx5_verbs.c
> @@ -22,6 +22,7 @@
> #include <mlx5_common_mr.h>
> #include <mlx5_rxtx.h>
> #include <mlx5_verbs.h>
> +#include <mlx5_rx.h>
> #include <mlx5_utils.h>
> #include <mlx5_malloc.h>
>
> diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
> index 9557d06..6f77bc2 100644
> --- a/drivers/net/mlx5/mlx5.c
> +++ b/drivers/net/mlx5/mlx5.c
> @@ -35,6 +35,7 @@
> #include "mlx5.h"
> #include "mlx5_utils.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_autoconf.h"
> #include "mlx5_mr.h"
> #include "mlx5_flow.h"
> diff --git a/drivers/net/mlx5/mlx5_devx.c b/drivers/net/mlx5/mlx5_devx.c
> index 5c940ed..76935f6 100644
> --- a/drivers/net/mlx5/mlx5_devx.c
> +++ b/drivers/net/mlx5/mlx5_devx.c
> @@ -21,6 +21,7 @@
> #include "mlx5.h"
> #include "mlx5_common_os.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_utils.h"
> #include "mlx5_devx.h"
> #include "mlx5_flow.h"
> diff --git a/drivers/net/mlx5/mlx5_ethdev.c
> b/drivers/net/mlx5/mlx5_ethdev.c
> index 564d713..708e3a3 100644
> --- a/drivers/net/mlx5/mlx5_ethdev.c
> +++ b/drivers/net/mlx5/mlx5_ethdev.c
> @@ -23,6 +23,7 @@
> #include <mlx5_malloc.h>
>
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_autoconf.h"
>
> /**
> diff --git a/drivers/net/mlx5/mlx5_flow.c b/drivers/net/mlx5/mlx5_flow.c
> index c347f81..b3877a1 100644
> --- a/drivers/net/mlx5/mlx5_flow.c
> +++ b/drivers/net/mlx5/mlx5_flow.c
> @@ -30,6 +30,7 @@
> #include "mlx5_flow.h"
> #include "mlx5_flow_os.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_common_os.h"
> #include "rte_pmd_mlx5.h"
>
> diff --git a/drivers/net/mlx5/mlx5_flow_dv.c
> b/drivers/net/mlx5/mlx5_flow_dv.c
> index 533dadf..cac05fb 100644
> --- a/drivers/net/mlx5/mlx5_flow_dv.c
> +++ b/drivers/net/mlx5/mlx5_flow_dv.c
> @@ -33,6 +33,7 @@
> #include "mlx5_flow.h"
> #include "mlx5_flow_os.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "rte_pmd_mlx5.h"
>
> #if defined(HAVE_IBV_FLOW_DV_SUPPORT) ||
> !defined(HAVE_INFINIBAND_VERBS_H)
> diff --git a/drivers/net/mlx5/mlx5_flow_verbs.c
> b/drivers/net/mlx5/mlx5_flow_verbs.c
> index b442b9b..c331350 100644
> --- a/drivers/net/mlx5/mlx5_flow_verbs.c
> +++ b/drivers/net/mlx5/mlx5_flow_verbs.c
> @@ -24,6 +24,7 @@
> #include "mlx5.h"
> #include "mlx5_flow.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
>
> #define VERBS_SPEC_INNER(item_flags) \
> (!!((item_flags) & MLX5_FLOW_LAYER_TUNNEL) ?
> IBV_FLOW_SPEC_INNER : 0)
> diff --git a/drivers/net/mlx5/mlx5_mr.c b/drivers/net/mlx5/mlx5_mr.c
> index 3255393..2014936 100644
> --- a/drivers/net/mlx5/mlx5_mr.c
> +++ b/drivers/net/mlx5/mlx5_mr.c
> @@ -15,6 +15,7 @@
> #include "mlx5.h"
> #include "mlx5_mr.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
>
> struct mr_find_contig_memsegs_data {
> uintptr_t addr;
> diff --git a/drivers/net/mlx5/mlx5_rss.c b/drivers/net/mlx5/mlx5_rss.c
> index dc0131a..c32129c 100644
> --- a/drivers/net/mlx5/mlx5_rss.c
> +++ b/drivers/net/mlx5/mlx5_rss.c
> @@ -16,6 +16,7 @@
> #include "mlx5_defs.h"
> #include "mlx5.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
>
> /**
> * DPDK callback to update the RSS hash configuration.
> diff --git a/drivers/net/mlx5/mlx5_rx.h b/drivers/net/mlx5/mlx5_rx.h
> new file mode 100644
> index 0000000..83b1f38
> --- /dev/null
> +++ b/drivers/net/mlx5/mlx5_rx.h
> @@ -0,0 +1,598 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright 2021 6WIND S.A.
> + * Copyright 2021 Mellanox Technologies, Ltd
> + */
> +
> +#ifndef RTE_PMD_MLX5_RX_H_
> +#define RTE_PMD_MLX5_RX_H_
> +
> +#include <stdint.h>
> +#include <sys/queue.h>
> +
> +#include <rte_mbuf.h>
> +#include <rte_mempool.h>
> +#include <rte_common.h>
> +#include <rte_spinlock.h>
> +
> +#include <mlx5_common_mr.h>
> +
> +#include "mlx5.h"
> +#include "mlx5_autoconf.h"
> +#include "mlx5_mr.h"
> +
> +/* Support tunnel matching. */
> +#define MLX5_FLOW_TUNNEL 10
> +
> +struct mlx5_rxq_stats {
> +#ifdef MLX5_PMD_SOFT_COUNTERS
> + uint64_t ipackets; /**< Total of successfully received packets. */
> + uint64_t ibytes; /**< Total of successfully received bytes. */
> +#endif
> + uint64_t idropped; /**< Total of packets dropped when RX ring full.
> */
> + uint64_t rx_nombuf; /**< Total of RX mbuf allocation failures. */
> +};
> +
> +/* Compressed CQE context. */
> +struct rxq_zip {
> + uint16_t ai; /* Array index. */
> + uint16_t ca; /* Current array index. */
> + uint16_t na; /* Next array index. */
> + uint16_t cq_ci; /* The next CQE. */
> + uint32_t cqe_cnt; /* Number of CQEs. */
> +};
> +
> +/* Multi-Packet RQ buffer header. */
> +struct mlx5_mprq_buf {
> + struct rte_mempool *mp;
> + 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, 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: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 mark:1; /* Marked flow available on the queue. */
> + 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 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. */
> + unsigned int mcqe_format:3; /* CQE compression format. */
> + 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;
> + uint32_t cq_ci;
> + uint16_t rq_repl_thresh; /* Threshold for buffer replenishment. */
> + uint32_t byte_mask;
> + 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 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;
> + rte_xmm_t mbuf_initializer; /* Default rearm/flags for vectorized Rx.
> */
> + struct rte_mbuf fake_mbuf; /* elts padding for vectorized Rx. */
> + 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
> + rte_spinlock_t *uar_lock_cq;
> + /* 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 flow_meta_port_mask;
> + 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;
> +
> +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. */
> + 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 rte_eth_hairpin_conf hairpin_conf; /* Hairpin configuration. */
> + uint32_t hairpin_status; /* Hairpin binding status. */
> +};
> +
> +/* mlx5_rxq.c */
> +
> +extern uint8_t rss_hash_default_key[];
> +
> +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);
> +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,
> + 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_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,
> + bool standalone);
> +int mlx5_ind_table_obj_setup(struct rte_eth_dev *dev,
> + struct mlx5_ind_table_obj *ind_tbl);
> +int mlx5_ind_table_obj_modify(struct rte_eth_dev *dev,
> + struct mlx5_ind_table_obj *ind_tbl,
> + uint16_t *queues, const uint32_t queues_n,
> + bool standalone);
> +struct mlx5_cache_entry *mlx5_hrxq_create_cb(struct mlx5_cache_list
> *list,
> + struct mlx5_cache_entry *entry __rte_unused, void
> *cb_ctx);
> +int mlx5_hrxq_match_cb(struct mlx5_cache_list *list,
> + struct mlx5_cache_entry *entry,
> + void *cb_ctx);
> +void mlx5_hrxq_remove_cb(struct mlx5_cache_list *list,
> + struct mlx5_cache_entry *entry);
> +uint32_t mlx5_hrxq_get(struct rte_eth_dev *dev,
> + struct mlx5_flow_rss_desc *rss_desc);
> +int mlx5_hrxq_release(struct rte_eth_dev *dev, uint32_t hxrq_idx);
> +uint32_t mlx5_hrxq_verify(struct rte_eth_dev *dev);
> +enum mlx5_rxq_type mlx5_rxq_get_type(struct rte_eth_dev *dev,
> uint16_t idx);
> +const struct rte_eth_hairpin_conf *mlx5_rxq_get_hairpin_conf
> + (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_rxtx.c */
> +
> +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,
> + uint16_t pkts_n);
> +uint16_t removed_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts,
> + uint16_t pkts_n);
> +int mlx5_rx_descriptor_status(void *rx_queue, uint16_t offset);
> +uint32_t mlx5_rx_queue_count(struct rte_eth_dev *dev, uint16_t
> rx_queue_id);
> +void mlx5_rxq_info_get(struct rte_eth_dev *dev, uint16_t queue_id,
> + struct rte_eth_rxq_info *qinfo);
> +int mlx5_rx_burst_mode_get(struct rte_eth_dev *dev, uint16_t
> rx_queue_id,
> + struct rte_eth_burst_mode *mode);
> +
> +/* Vectorized version of mlx5_rxtx.c */
> +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_rx_burst_vec(void *dpdk_rxq, struct rte_mbuf **pkts,
> + uint16_t pkts_n);
> +uint16_t mlx5_rx_burst_mprq_vec(void *dpdk_rxq, struct rte_mbuf
> **pkts,
> + uint16_t pkts_n);
> +
> +/* mlx5_mr.c */
> +
> +uint32_t mlx5_rx_addr2mr_bh(struct mlx5_rxq_data *rxq, uintptr_t addr);
> +
> +/**
> + * Query LKey from a packet buffer for Rx. No need to flush local caches for
> Rx
> + * as mempool is pre-configured and static.
> + *
> + * @param rxq
> + * Pointer to Rx queue structure.
> + * @param addr
> + * Address to search.
> + *
> + * @return
> + * Searched LKey on success, UINT32_MAX on no match.
> + */
> +static __rte_always_inline uint32_t
> +mlx5_rx_addr2mr(struct mlx5_rxq_data *rxq, uintptr_t addr)
> +{
> + struct mlx5_mr_ctrl *mr_ctrl = &rxq->mr_ctrl;
> + uint32_t lkey;
> +
> + /* Linear search on MR cache array. */
> + 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. */
> + return mlx5_rx_addr2mr_bh(rxq, addr);
> +}
> +
> +#define mlx5_rx_mb2mr(rxq, mb) mlx5_rx_addr2mr(rxq, (uintptr_t)((mb)-
> >buf_addr))
> +
> +/**
> + * Convert timestamp from HW format to linear counter
> + * from Packet Pacing Clock Queue CQE timestamp format.
> + *
> + * @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 uint64_t
> +mlx5_txpp_convert_rx_ts(struct mlx5_dev_ctx_shared *sh, uint64_t ts)
> +{
> + RTE_SET_USED(sh);
> + return (ts & UINT32_MAX) + (ts >> 32) * NS_PER_S;
> +}
> +
> +/**
> + * Set timestamp in mbuf dynamic field.
> + *
> + * @param mbuf
> + * Structure to write into.
> + * @param offset
> + * Dynamic field offset in mbuf structure.
> + * @param timestamp
> + * Value to write.
> + */
> +static __rte_always_inline void
> +mlx5_timestamp_set(struct rte_mbuf *mbuf, int offset,
> + rte_mbuf_timestamp_t timestamp)
> +{
> + *RTE_MBUF_DYNFIELD(mbuf, offset, rte_mbuf_timestamp_t *) =
> timestamp;
> +}
> +
> +/**
> + * Replace MPRQ buffer.
> + *
> + * @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.
> + *
> + * @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 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)
> +{
> + 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);
> +
> + /*
> + * 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;
> +}
> +
> +/**
> + * Check whether Multi-Packet RQ can be enabled for the device.
> + *
> + * @param dev
> + * Pointer to Ethernet device.
> + *
> + * @return
> + * 1 if supported, negative errno value if not.
> + */
> +static __rte_always_inline int
> +mlx5_check_mprq_support(struct rte_eth_dev *dev)
> +{
> + struct mlx5_priv *priv = dev->data->dev_private;
> +
> + if (priv->config.mprq.enabled &&
> + priv->rxqs_n >= priv->config.mprq.min_rxqs_num)
> + return 1;
> + return -ENOTSUP;
> +}
> +
> +/**
> + * Check whether Multi-Packet RQ is enabled for the Rx queue.
> + *
> + * @param rxq
> + * Pointer to receive queue structure.
> + *
> + * @return
> + * 0 if disabled, otherwise enabled.
> + */
> +static __rte_always_inline int
> +mlx5_rxq_mprq_enabled(struct mlx5_rxq_data *rxq)
> +{
> + return rxq->strd_num_n > 0;
> +}
> +
> +/**
> + * Check whether Multi-Packet RQ is enabled for the device.
> + *
> + * @param dev
> + * Pointer to Ethernet device.
> + *
> + * @return
> + * 0 if disabled, otherwise enabled.
> + */
> +static __rte_always_inline int
> +mlx5_mprq_enabled(struct rte_eth_dev *dev)
> +{
> + struct mlx5_priv *priv = dev->data->dev_private;
> + uint32_t i;
> + uint16_t n = 0;
> + uint16_t n_ibv = 0;
> +
> + if (mlx5_check_mprq_support(dev) < 0)
> + return 0;
> + /* All the configured queues should be enabled. */
> + for (i = 0; i < priv->rxqs_n; ++i) {
> + struct mlx5_rxq_data *rxq = (*priv->rxqs)[i];
> + struct mlx5_rxq_ctrl *rxq_ctrl = container_of
> + (rxq, struct mlx5_rxq_ctrl, rxq);
> +
> + if (rxq == NULL || rxq_ctrl->type !=
> MLX5_RXQ_TYPE_STANDARD)
> + continue;
> + n_ibv++;
> + if (mlx5_rxq_mprq_enabled(rxq))
> + ++n;
> + }
> + /* Multi-Packet RQ can't be partially configured. */
> + MLX5_ASSERT(n == 0 || n == n_ibv);
> + return n == n_ibv;
> +}
> +
> +#endif /* RTE_PMD_MLX5_RX_H_ */
> diff --git a/drivers/net/mlx5/mlx5_rxq.c b/drivers/net/mlx5/mlx5_rxq.c
> index 9009eb8..19df0fa 100644
> --- a/drivers/net/mlx5/mlx5_rxq.c
> +++ b/drivers/net/mlx5/mlx5_rxq.c
> @@ -25,6 +25,7 @@
> #include "mlx5_defs.h"
> #include "mlx5.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_utils.h"
> #include "mlx5_autoconf.h"
>
> diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c
> index c76b995..d004e1e 100644
> --- a/drivers/net/mlx5/mlx5_rxtx.c
> +++ b/drivers/net/mlx5/mlx5_rxtx.c
> @@ -25,6 +25,7 @@
> #include "mlx5_mr.h"
> #include "mlx5_utils.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
>
> /* TX burst subroutines return codes. */
> enum mlx5_txcmp_code {
> diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h
> index 4f0fda0..d443db4 100644
> --- a/drivers/net/mlx5/mlx5_rxtx.h
> +++ b/drivers/net/mlx5/mlx5_rxtx.h
> @@ -31,21 +31,10 @@
> #include "mlx5_autoconf.h"
> #include "mlx5_mr.h"
>
> -/* Support tunnel matching. */
> -#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
> - uint64_t ipackets; /**< Total of successfully received packets. */
> - uint64_t ibytes; /**< Total of successfully received bytes. */
> -#endif
> - uint64_t idropped; /**< Total of packets dropped when RX ring full.
> */
> - uint64_t rx_nombuf; /**< Total of RX mbuf allocation failures. */
> -};
> -
> struct mlx5_txq_stats {
> #ifdef MLX5_PMD_SOFT_COUNTERS
> uint64_t opackets; /**< Total of successfully sent packets. */
> @@ -56,148 +45,6 @@ struct mlx5_txq_stats {
>
> struct mlx5_priv;
>
> -/* Compressed CQE context. */
> -struct rxq_zip {
> - uint16_t ai; /* Array index. */
> - uint16_t ca; /* Current array index. */
> - uint16_t na; /* Next array index. */
> - uint16_t cq_ci; /* The next CQE. */
> - uint32_t cqe_cnt; /* Number of CQEs. */
> -};
> -
> -/* Multi-Packet RQ buffer header. */
> -struct mlx5_mprq_buf {
> - struct rte_mempool *mp;
> - 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, 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: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 mark:1; /* Marked flow available on the queue. */
> - 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 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. */
> - unsigned int mcqe_format:3; /* CQE compression format. */
> - 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;
> - uint32_t cq_ci;
> - uint16_t rq_repl_thresh; /* Threshold for buffer replenishment. */
> - uint32_t byte_mask;
> - 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 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;
> - rte_xmm_t mbuf_initializer; /* Default rearm/flags for vectorized Rx.
> */
> - struct rte_mbuf fake_mbuf; /* elts padding for vectorized Rx. */
> - 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
> - rte_spinlock_t *uar_lock_cq;
> - /* 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 flow_meta_port_mask;
> - 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;
> -
> -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. */
> - 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 rte_eth_hairpin_conf hairpin_conf; /* Hairpin configuration. */
> - uint32_t hairpin_status; /* Hairpin binding status. */
> -};
> -
> /* TX queue send local data. */
> __extension__
> struct mlx5_txq_local {
> @@ -302,80 +149,6 @@ struct mlx5_txq_ctrl {
> #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[];
> -
> -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);
> -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,
> - 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_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,
> - bool standalone);
> -int mlx5_ind_table_obj_setup(struct rte_eth_dev *dev,
> - struct mlx5_ind_table_obj *ind_tbl);
> -int mlx5_ind_table_obj_modify(struct rte_eth_dev *dev,
> - struct mlx5_ind_table_obj *ind_tbl,
> - uint16_t *queues, const uint32_t queues_n,
> - bool standalone);
> -struct mlx5_cache_entry *mlx5_hrxq_create_cb(struct mlx5_cache_list
> *list,
> - struct mlx5_cache_entry *entry __rte_unused, void
> *cb_ctx);
> -int mlx5_hrxq_match_cb(struct mlx5_cache_list *list,
> - struct mlx5_cache_entry *entry,
> - void *cb_ctx);
> -void mlx5_hrxq_remove_cb(struct mlx5_cache_list *list,
> - struct mlx5_cache_entry *entry);
> -uint32_t mlx5_hrxq_get(struct rte_eth_dev *dev,
> - struct mlx5_flow_rss_desc *rss_desc);
> -int mlx5_hrxq_release(struct rte_eth_dev *dev, uint32_t hxrq_idx);
> -uint32_t mlx5_hrxq_verify(struct rte_eth_dev *dev);
> -
> -
> -enum mlx5_rxq_type mlx5_rxq_get_type(struct rte_eth_dev *dev,
> uint16_t idx);
> -const struct rte_eth_hairpin_conf *mlx5_rxq_get_hairpin_conf
> - (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);
> @@ -416,45 +189,21 @@ struct mlx5_txq_ctrl *mlx5_txq_hairpin_new
> void mlx5_set_ptype_table(void);
> void mlx5_set_cksum_table(void);
> void mlx5_set_swp_types_table(void);
> -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,
> - uint16_t pkts_n);
> uint16_t removed_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts,
> uint16_t pkts_n);
> -uint16_t removed_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts,
> - uint16_t pkts_n);
> -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);
> -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_rxq_check_vec_support(struct mlx5_rxq_data *rxq_data);
> -int mlx5_check_vec_rx_support(struct rte_eth_dev *dev);
> -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 */
>
> 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_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);
> @@ -538,35 +287,6 @@ int mlx5_dma_unmap(struct rte_pci_device *pdev,
> void *addr, uint64_t iova,
> }
>
> /**
> - * Query LKey from a packet buffer for Rx. No need to flush local caches for
> Rx
> - * as mempool is pre-configured and static.
> - *
> - * @param rxq
> - * Pointer to Rx queue structure.
> - * @param addr
> - * Address to search.
> - *
> - * @return
> - * Searched LKey on success, UINT32_MAX on no match.
> - */
> -static __rte_always_inline uint32_t
> -mlx5_rx_addr2mr(struct mlx5_rxq_data *rxq, uintptr_t addr)
> -{
> - struct mlx5_mr_ctrl *mr_ctrl = &rxq->mr_ctrl;
> - uint32_t lkey;
> -
> - /* Linear search on MR cache array. */
> - 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. */
> - return mlx5_rx_addr2mr_bh(rxq, addr);
> -}
> -
> -#define mlx5_rx_mb2mr(rxq, mb) mlx5_rx_addr2mr(rxq, (uintptr_t)((mb)-
> >buf_addr))
> -
> -/**
> * Query LKey from a packet buffer for Tx. If not found, add the mempool.
> *
> * @param txq
> @@ -637,25 +357,6 @@ int mlx5_dma_unmap(struct rte_pci_device *pdev,
> void *addr, uint64_t iova,
> }
>
> /**
> - * Convert timestamp from HW format to linear counter
> - * from Packet Pacing Clock Queue CQE timestamp format.
> - *
> - * @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 uint64_t
> -mlx5_txpp_convert_rx_ts(struct mlx5_dev_ctx_shared *sh, uint64_t ts)
> -{
> - RTE_SET_USED(sh);
> - return (ts & UINT32_MAX) + (ts >> 32) * NS_PER_S;
> -}
> -
> -/**
> * Convert timestamp from mbuf format to linear counter
> * of Clock Queue completions (24 bits)
> *
> @@ -712,274 +413,4 @@ int mlx5_dma_unmap(struct rte_pci_device *pdev,
> void *addr, uint64_t iova,
> return ci;
> }
>
> -/**
> - * Set timestamp in mbuf dynamic field.
> - *
> - * @param mbuf
> - * Structure to write into.
> - * @param offset
> - * Dynamic field offset in mbuf structure.
> - * @param timestamp
> - * Value to write.
> - */
> -static __rte_always_inline void
> -mlx5_timestamp_set(struct rte_mbuf *mbuf, int offset,
> - rte_mbuf_timestamp_t timestamp)
> -{
> - *RTE_MBUF_DYNFIELD(mbuf, offset, rte_mbuf_timestamp_t *) =
> timestamp;
> -}
> -
> -/**
> - * Replace MPRQ buffer.
> - *
> - * @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.
> - *
> - * @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 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)
> -{
> - 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);
> -
> - /*
> - * 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;
> -}
> -
> -/**
> - * Check whether Multi-Packet RQ can be enabled for the device.
> - *
> - * @param dev
> - * Pointer to Ethernet device.
> - *
> - * @return
> - * 1 if supported, negative errno value if not.
> - */
> -static __rte_always_inline int
> -mlx5_check_mprq_support(struct rte_eth_dev *dev)
> -{
> - struct mlx5_priv *priv = dev->data->dev_private;
> -
> - if (priv->config.mprq.enabled &&
> - priv->rxqs_n >= priv->config.mprq.min_rxqs_num)
> - return 1;
> - return -ENOTSUP;
> -}
> -
> -/**
> - * Check whether Multi-Packet RQ is enabled for the Rx queue.
> - *
> - * @param rxq
> - * Pointer to receive queue structure.
> - *
> - * @return
> - * 0 if disabled, otherwise enabled.
> - */
> -static __rte_always_inline int
> -mlx5_rxq_mprq_enabled(struct mlx5_rxq_data *rxq)
> -{
> - return rxq->strd_num_n > 0;
> -}
> -
> -/**
> - * Check whether Multi-Packet RQ is enabled for the device.
> - *
> - * @param dev
> - * Pointer to Ethernet device.
> - *
> - * @return
> - * 0 if disabled, otherwise enabled.
> - */
> -static __rte_always_inline int
> -mlx5_mprq_enabled(struct rte_eth_dev *dev)
> -{
> - struct mlx5_priv *priv = dev->data->dev_private;
> - uint32_t i;
> - uint16_t n = 0;
> - uint16_t n_ibv = 0;
> -
> - if (mlx5_check_mprq_support(dev) < 0)
> - return 0;
> - /* All the configured queues should be enabled. */
> - for (i = 0; i < priv->rxqs_n; ++i) {
> - struct mlx5_rxq_data *rxq = (*priv->rxqs)[i];
> - struct mlx5_rxq_ctrl *rxq_ctrl = container_of
> - (rxq, struct mlx5_rxq_ctrl, rxq);
> -
> - if (rxq == NULL || rxq_ctrl->type !=
> MLX5_RXQ_TYPE_STANDARD)
> - continue;
> - n_ibv++;
> - if (mlx5_rxq_mprq_enabled(rxq))
> - ++n;
> - }
> - /* Multi-Packet RQ can't be partially configured. */
> - MLX5_ASSERT(n == 0 || n == n_ibv);
> - return n == n_ibv;
> -}
> #endif /* RTE_PMD_MLX5_RXTX_H_ */
> diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.c
> b/drivers/net/mlx5/mlx5_rxtx_vec.c
> index 028e0f6..d5af2d9 100644
> --- a/drivers/net/mlx5/mlx5_rxtx_vec.c
> +++ b/drivers/net/mlx5/mlx5_rxtx_vec.c
> @@ -19,6 +19,7 @@
> #include "mlx5.h"
> #include "mlx5_utils.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_rxtx_vec.h"
> #include "mlx5_autoconf.h"
>
> diff --git a/drivers/net/mlx5/mlx5_stats.c b/drivers/net/mlx5/mlx5_stats.c
> index a6569b2..4dbd831 100644
> --- a/drivers/net/mlx5/mlx5_stats.c
> +++ b/drivers/net/mlx5/mlx5_stats.c
> @@ -17,6 +17,7 @@
> #include "mlx5_defs.h"
> #include "mlx5.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_malloc.h"
>
> /**
> diff --git a/drivers/net/mlx5/mlx5_trigger.c
> b/drivers/net/mlx5/mlx5_trigger.c
> index 94dd567..c88cb22 100644
> --- a/drivers/net/mlx5/mlx5_trigger.c
> +++ b/drivers/net/mlx5/mlx5_trigger.c
> @@ -16,6 +16,7 @@
> #include "mlx5.h"
> #include "mlx5_mr.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_utils.h"
> #include "rte_pmd_mlx5.h"
>
> diff --git a/drivers/net/mlx5/mlx5_txpp.c b/drivers/net/mlx5/mlx5_txpp.c
> index e8d632a..89e1c5d 100644
> --- a/drivers/net/mlx5/mlx5_txpp.c
> +++ b/drivers/net/mlx5/mlx5_txpp.c
> @@ -17,6 +17,7 @@
>
> #include "mlx5.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_common_os.h"
>
> static_assert(sizeof(struct mlx5_cqe_ts) == sizeof(rte_int128_t),
> diff --git a/drivers/net/mlx5/mlx5_vlan.c b/drivers/net/mlx5/mlx5_vlan.c
> index 64678d3..60f97f2 100644
> --- a/drivers/net/mlx5/mlx5_vlan.c
> +++ b/drivers/net/mlx5/mlx5_vlan.c
> @@ -16,6 +16,7 @@
> #include "mlx5.h"
> #include "mlx5_autoconf.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_utils.h"
> #include "mlx5_devx.h"
>
> diff --git a/drivers/net/mlx5/windows/mlx5_os.c
> b/drivers/net/mlx5/windows/mlx5_os.c
> index 6f39276..79eac80 100644
> --- a/drivers/net/mlx5/windows/mlx5_os.c
> +++ b/drivers/net/mlx5/windows/mlx5_os.c
> @@ -23,6 +23,7 @@
> #include "mlx5_common_os.h"
> #include "mlx5_utils.h"
> #include "mlx5_rxtx.h"
> +#include "mlx5_rx.h"
> #include "mlx5_autoconf.h"
> #include "mlx5_mr.h"
> #include "mlx5_flow.h"
> --
> 1.8.3.1
