X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Fmlx5_rxtx.h;h=acde09d4d0c2caf41df71a6bb6a794a677c4f436;hb=a6bd4911ad93f8ab8a378591b3a86f82223695eb;hp=b7c75bf0aaf30e31fe81dd680a47fbbbefc0f2f2;hpb=4c7a0f5ff876422f81b9e1a9c6b171323dff323f;p=dpdk.git diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h index b7c75bf0aa..acde09d4d0 100644 --- a/drivers/net/mlx5/mlx5_rxtx.h +++ b/drivers/net/mlx5/mlx5_rxtx.h @@ -1,34 +1,6 @@ -/*- - * BSD LICENSE - * - * Copyright 2015 6WIND S.A. - * Copyright 2015 Mellanox. - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * * Neither the name of 6WIND S.A. nor the names of its - * contributors may be used to endorse or promote products derived - * from this software without specific prior written permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright 2015 6WIND S.A. + * Copyright 2015 Mellanox Technologies, Ltd */ #ifndef RTE_PMD_MLX5_RXTX_H_ @@ -54,15 +26,22 @@ #include #include #include +#include +#include +#include #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_glue.h" + +/* Support tunnel matching. */ +#define MLX5_FLOW_TUNNEL 5 struct mlx5_rxq_stats { - unsigned int idx; /**< Mapping index. */ #ifdef MLX5_PMD_SOFT_COUNTERS uint64_t ipackets; /**< Total of successfully received packets. */ uint64_t ibytes; /**< Total of successfully received bytes. */ @@ -72,7 +51,6 @@ struct mlx5_rxq_stats { }; struct mlx5_txq_stats { - unsigned int idx; /**< Mapping index. */ #ifdef MLX5_PMD_SOFT_COUNTERS uint64_t opackets; /**< Total of successfully sent packets. */ uint64_t obytes; /**< Total of successfully sent bytes. */ @@ -80,18 +58,7 @@ struct mlx5_txq_stats { uint64_t oerrors; /**< Total number of failed transmitted packets. */ }; -struct priv; - -/* Memory region queue object. */ -struct mlx5_mr { - LIST_ENTRY(mlx5_mr) next; /**< Pointer to the next element. */ - rte_atomic32_t refcnt; /*<< Reference counter. */ - uint32_t lkey; /*<< rte_cpu_to_be_32(mr->lkey) */ - uintptr_t start; /* Start address of MR */ - uintptr_t end; /* End address of MR */ - struct ibv_mr *mr; /*<< Memory Region. */ - struct rte_mempool *mp; /*<< Memory Pool. */ -}; +struct mlx5_priv; /* Compressed CQE context. */ struct rxq_zip { @@ -102,10 +69,26 @@ struct rxq_zip { uint32_t cqe_cnt; /* Number of CQEs. */ }; +/* Multi-Packet RQ buffer header. */ +struct mlx5_mprq_buf { + struct rte_mempool *mp; + rte_atomic16_t refcnt; /* Atomically accessed refcnt. */ + uint8_t pad[RTE_PKTMBUF_HEADROOM]; /* Headroom for the first packet. */ +} __rte_cache_aligned; + +/* Get pointer to the first stride. */ +#define mlx5_mprq_buf_addr(ptr) ((ptr) + 1) + +enum mlx5_rxq_err_state { + MLX5_RXQ_ERR_STATE_NO_ERROR = 0, + MLX5_RXQ_ERR_STATE_NEED_RESET, + MLX5_RXQ_ERR_STATE_NEED_READY, +}; + /* RX queue descriptor. */ struct mlx5_rxq_data { unsigned int csum:1; /* Enable checksum offloading. */ - unsigned int csum_l2tun:1; /* Same for L2 tunnels. */ + unsigned int hw_timestamp:1; /* Enable HW timestamp. */ 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). */ @@ -113,25 +96,48 @@ struct mlx5_rxq_data { 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 pending_err:1; /* CQE error needs to be handled. */ - unsigned int :15; /* Remaining bits. */ + 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 :4; /* Remaining bits. */ volatile uint32_t *rq_db; volatile uint32_t *cq_db; uint16_t port_id; - uint16_t rq_ci; - uint16_t rq_pi; - uint16_t cq_ci; - volatile struct mlx5_wqe_data_seg(*wqes)[]; + 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. */ + union { + struct rxq_zip zip; /* Compressed context. */ + uint16_t decompressed; + /* Number of ready mbufs decompressed from the CQ. */ + }; + struct mlx5_mr_ctrl mr_ctrl; /* MR control descriptor. */ + uint16_t mprq_max_memcpy_len; /* Maximum size of packet to memcpy. */ + volatile void *wqes; volatile struct mlx5_cqe(*cqes)[]; - struct rxq_zip zip; /* Compressed context. */ - struct rte_mbuf *(*elts)[]; + RTE_STD_C11 + union { + 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. */ + uint16_t idx; /* Queue index. */ struct mlx5_rxq_stats stats; uint64_t mbuf_initializer; /* Default rearm_data for vectorized Rx. */ struct rte_mbuf fake_mbuf; /* elts padding for vectorized Rx. */ void *cq_uar; /* 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. */ } __rte_cache_aligned; /* Verbs Rx queue elements. */ @@ -142,18 +148,21 @@ struct mlx5_rxq_ibv { struct ibv_cq *cq; /* Completion Queue. */ struct ibv_wq *wq; /* Work Queue. */ struct ibv_comp_channel *channel; - struct mlx5_mr *mr; /* Memory Region (for mp). */ }; /* 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 priv *priv; /* Back pointer to private data. */ struct mlx5_rxq_ibv *ibv; /* Verbs elements. */ - struct mlx5_rxq_data rxq; /* Data path structure. */ + struct mlx5_priv *priv; /* Back pointer to private data. */ unsigned int socket; /* CPU socket ID for allocations. */ unsigned int irq:1; /* Whether IRQ is enabled. */ + uint32_t flow_mark_n; /* Number of Mark/Flag flows using this Queue. */ + uint32_t flow_tunnels_n[MLX5_FLOW_TUNNEL]; /* Tunnels counters. */ + uint32_t wqn; /* WQ number. */ + uint16_t dump_file_n; /* Number of dump files. */ }; /* Indirection table. */ @@ -161,107 +170,22 @@ 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. */ - uint16_t queues_n; /**< Number of queues in the list. */ + uint32_t queues_n; /**< Number of queues in the list. */ uint16_t queues[]; /**< Queue list. */ }; -/* Hash RX queue types. */ -enum hash_rxq_type { - HASH_RXQ_TCPV4, - HASH_RXQ_UDPV4, - HASH_RXQ_IPV4, - HASH_RXQ_TCPV6, - HASH_RXQ_UDPV6, - HASH_RXQ_IPV6, - HASH_RXQ_ETH, -}; - -/* Flow structure with Ethernet specification. It is packed to prevent padding - * between attr and spec as this layout is expected by libibverbs. */ -struct flow_attr_spec_eth { - struct ibv_flow_attr attr; - struct ibv_flow_spec_eth spec; -} __attribute__((packed)); - -/* Define a struct flow_attr_spec_eth object as an array of at least - * "size" bytes. Room after the first index is normally used to store - * extra flow specifications. */ -#define FLOW_ATTR_SPEC_ETH(name, size) \ - struct flow_attr_spec_eth name \ - [((size) / sizeof(struct flow_attr_spec_eth)) + \ - !!((size) % sizeof(struct flow_attr_spec_eth))] - -/* Initialization data for hash RX queue. */ -struct hash_rxq_init { - uint64_t hash_fields; /* Fields that participate in the hash. */ - uint64_t dpdk_rss_hf; /* Matching DPDK RSS hash fields. */ - unsigned int flow_priority; /* Flow priority to use. */ - union { - struct { - enum ibv_flow_spec_type type; - uint16_t size; - } hdr; - struct ibv_flow_spec_tcp_udp tcp_udp; - struct ibv_flow_spec_ipv4 ipv4; - struct ibv_flow_spec_ipv6 ipv6; - struct ibv_flow_spec_eth eth; - } flow_spec; /* Flow specification template. */ - const struct hash_rxq_init *underlayer; /* Pointer to underlayer. */ -}; - -/* Initialization data for indirection table. */ -struct ind_table_init { - unsigned int max_size; /* Maximum number of WQs. */ - /* Hash RX queues using this table. */ - unsigned int hash_types; - unsigned int hash_types_n; -}; - -/* Initialization data for special flows. */ -struct special_flow_init { - uint8_t dst_mac_val[6]; - uint8_t dst_mac_mask[6]; - unsigned int hash_types; - unsigned int per_vlan:1; -}; - -enum hash_rxq_flow_type { - HASH_RXQ_FLOW_TYPE_PROMISC, - HASH_RXQ_FLOW_TYPE_ALLMULTI, - HASH_RXQ_FLOW_TYPE_BROADCAST, - HASH_RXQ_FLOW_TYPE_IPV6MULTI, - HASH_RXQ_FLOW_TYPE_MAC, -}; - -#ifndef NDEBUG -static inline const char * -hash_rxq_flow_type_str(enum hash_rxq_flow_type flow_type) -{ - switch (flow_type) { - case HASH_RXQ_FLOW_TYPE_PROMISC: - return "promiscuous"; - case HASH_RXQ_FLOW_TYPE_ALLMULTI: - return "allmulticast"; - case HASH_RXQ_FLOW_TYPE_BROADCAST: - return "broadcast"; - case HASH_RXQ_FLOW_TYPE_IPV6MULTI: - return "IPv6 multicast"; - case HASH_RXQ_FLOW_TYPE_MAC: - return "MAC"; - } - return NULL; -} -#endif /* NDEBUG */ - -struct hash_rxq { - struct priv *priv; /* Back pointer to private data. */ - struct ibv_qp *qp; /* Hash RX QP. */ - enum hash_rxq_type type; /* Hash RX queue type. */ - /* MAC flow steering rules, one per VLAN ID. */ - struct ibv_flow *mac_flow - [MLX5_MAX_MAC_ADDRESSES][MLX5_MAX_VLAN_IDS]; - struct ibv_flow *special_flow - [MLX5_MAX_SPECIAL_FLOWS][MLX5_MAX_VLAN_IDS]; +/* 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 descriptor. */ @@ -272,175 +196,241 @@ struct mlx5_txq_data { 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 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 cqe_n:4; /* Number of CQ elements (in log2). */ uint16_t wqe_n:4; /* Number of of WQ elements (in log2). */ - uint16_t inline_en:1; /* When set inline is enabled. */ 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 mr_cache_idx; /* Index of last hit entry. */ uint32_t qp_num_8s; /* QP number shifted by 8. */ - uint32_t flags; /* Flags for Tx Queue. */ + 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). */ volatile uint32_t *qp_db; /* Work queue doorbell. */ volatile uint32_t *cq_db; /* Completion queue doorbell. */ - volatile void *bf_reg; /* Blueflame register. */ - struct mlx5_mr *mp2mr[MLX5_PMD_TX_MP_CACHE]; /* MR translation table. */ struct rte_mbuf *(*elts)[]; /* TX elements. */ + uint16_t port_id; /* Port ID of device. */ + uint16_t idx; /* Queue index. */ struct mlx5_txq_stats stats; /* TX queue counters. */ +#ifndef RTE_ARCH_64 + rte_spinlock_t *uar_lock; + /* UAR access lock required for 32bit implementations */ +#endif } __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. */ }; /* 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. */ - struct priv *priv; /* Back pointer to private data. */ unsigned int socket; /* CPU socket ID for allocations. */ unsigned int max_inline_data; /* Max inline data. */ unsigned int max_tso_header; /* Max TSO header size. */ struct mlx5_txq_ibv *ibv; /* Verbs queue object. */ - struct mlx5_txq_data txq; /* Data path structure. */ + struct mlx5_priv *priv; /* Back pointer to private data. */ off_t uar_mmap_offset; /* UAR mmap offset for non-primary process. */ + void *bf_reg; /* BlueFlame register from Verbs. */ + uint32_t cqn; /* CQ number. */ + uint16_t dump_file_n; /* Number of dump files. */ }; -/* mlx5_rxq.c */ +#define MLX5_TX_BFREG(txq) \ + (MLX5_PROC_PRIV((txq)->port_id)->uar_table[(txq)->idx]) -extern const struct hash_rxq_init hash_rxq_init[]; -extern const unsigned int hash_rxq_init_n; +/* mlx5_rxq.c */ extern uint8_t rss_hash_default_key[]; -extern const size_t rss_hash_default_key_len; - -size_t priv_flow_attr(struct priv *, struct ibv_flow_attr *, - size_t, enum hash_rxq_type); -int priv_create_hash_rxqs(struct priv *); -void priv_destroy_hash_rxqs(struct priv *); -int priv_allow_flow_type(struct priv *, enum hash_rxq_flow_type); -int priv_rehash_flows(struct priv *); -void mlx5_rxq_cleanup(struct mlx5_rxq_ctrl *); -int mlx5_rx_queue_setup(struct rte_eth_dev *, uint16_t, uint16_t, unsigned int, - const struct rte_eth_rxconf *, struct rte_mempool *); -void mlx5_rx_queue_release(void *); -int priv_rx_intr_vec_enable(struct priv *priv); -void priv_rx_intr_vec_disable(struct priv *priv); + +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); +int mlx5_mprq_free_mp(struct rte_eth_dev *dev); +int mlx5_mprq_alloc_mp(struct rte_eth_dev *dev); +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); +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_priv_rxq_ibv_new(struct priv *, uint16_t); -struct mlx5_rxq_ibv *mlx5_priv_rxq_ibv_get(struct priv *, uint16_t); -int mlx5_priv_rxq_ibv_release(struct priv *, struct mlx5_rxq_ibv *); -int mlx5_priv_rxq_ibv_releasable(struct priv *, struct mlx5_rxq_ibv *); -int mlx5_priv_rxq_ibv_verify(struct priv *); -struct mlx5_rxq_ctrl *mlx5_priv_rxq_new(struct priv *, uint16_t, - uint16_t, unsigned int, - struct rte_mempool *); -struct mlx5_rxq_ctrl *mlx5_priv_rxq_get(struct priv *, uint16_t); -int mlx5_priv_rxq_release(struct priv *, uint16_t); -int mlx5_priv_rxq_releasable(struct priv *, uint16_t); -int mlx5_priv_rxq_verify(struct priv *); -int rxq_alloc_elts(struct mlx5_rxq_ctrl *); -struct mlx5_ind_table_ibv *mlx5_priv_ind_table_ibv_new(struct priv *, - uint16_t [], - uint16_t); -struct mlx5_ind_table_ibv *mlx5_priv_ind_table_ibv_get(struct priv *, - uint16_t [], - uint16_t); -int mlx5_priv_ind_table_ibv_release(struct priv *, struct mlx5_ind_table_ibv *); -int mlx5_priv_ind_table_ibv_verify(struct priv *); +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); +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); +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); +uint64_t mlx5_get_rx_port_offloads(void); +uint64_t mlx5_get_rx_queue_offloads(struct rte_eth_dev *dev); /* mlx5_txq.c */ -int mlx5_tx_queue_setup(struct rte_eth_dev *, uint16_t, uint16_t, unsigned int, - const struct rte_eth_txconf *); -void mlx5_tx_queue_release(void *); -int priv_tx_uar_remap(struct priv *priv, int fd); -struct mlx5_txq_ibv *mlx5_priv_txq_ibv_new(struct priv *, uint16_t); -struct mlx5_txq_ibv *mlx5_priv_txq_ibv_get(struct priv *, uint16_t); -int mlx5_priv_txq_ibv_release(struct priv *, struct mlx5_txq_ibv *); -int mlx5_priv_txq_ibv_releasable(struct priv *, struct mlx5_txq_ibv *); -int mlx5_priv_txq_ibv_verify(struct priv *); -struct mlx5_txq_ctrl *mlx5_priv_txq_new(struct priv *, uint16_t, - uint16_t, unsigned int, - const struct rte_eth_txconf *); -struct mlx5_txq_ctrl *mlx5_priv_txq_get(struct priv *, uint16_t); -int mlx5_priv_txq_release(struct priv *, uint16_t); -int mlx5_priv_txq_releasable(struct priv *, uint16_t); -int mlx5_priv_txq_verify(struct priv *); -void txq_alloc_elts(struct mlx5_txq_ctrl *); +int mlx5_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc, + unsigned int socket, const struct rte_eth_txconf *conf); +void mlx5_tx_queue_release(void *dpdk_txq); +int mlx5_tx_uar_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); +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_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); +uint64_t mlx5_get_tx_port_offloads(struct rte_eth_dev *dev); /* mlx5_rxtx.c */ extern uint32_t mlx5_ptype_table[]; +extern uint8_t mlx5_cksum_table[]; +extern uint8_t mlx5_swp_types_table[]; void mlx5_set_ptype_table(void); -uint16_t mlx5_tx_burst(void *, struct rte_mbuf **, uint16_t); -uint16_t mlx5_tx_burst_mpw(void *, struct rte_mbuf **, uint16_t); -uint16_t mlx5_tx_burst_mpw_inline(void *, struct rte_mbuf **, uint16_t); -uint16_t mlx5_tx_burst_empw(void *, struct rte_mbuf **, uint16_t); -uint16_t mlx5_rx_burst(void *, struct rte_mbuf **, uint16_t); -uint16_t removed_tx_burst(void *, struct rte_mbuf **, uint16_t); -uint16_t removed_rx_burst(void *, struct rte_mbuf **, uint16_t); -int mlx5_rx_descriptor_status(void *, uint16_t); -int mlx5_tx_descriptor_status(void *, uint16_t); +void mlx5_set_cksum_table(void); +void mlx5_set_swp_types_table(void); +__rte_noinline uint16_t mlx5_tx_error_cqe_handle(struct mlx5_txq_data *txq, + volatile struct mlx5_err_cqe *err_cqe); +uint16_t mlx5_rx_burst(void *dpdk_rxq, struct rte_mbuf **pkts, uint16_t pkts_n); +void mlx5_rxq_initialize(struct mlx5_rxq_data *rxq); +__rte_noinline int mlx5_rx_err_handle(struct mlx5_rxq_data *rxq, + uint8_t mbuf_prepare); +void mlx5_mprq_buf_free_cb(void *addr, void *opaque); +void mlx5_mprq_buf_free(struct mlx5_mprq_buf *buf); +uint16_t mlx5_rx_burst_mprq(void *dpdk_rxq, struct rte_mbuf **pkts, + 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); /* Vectorized version of mlx5_rxtx.c */ -int priv_check_raw_vec_tx_support(struct priv *); -int priv_check_vec_tx_support(struct priv *); -int rxq_check_vec_support(struct mlx5_rxq_data *); -int priv_check_vec_rx_support(struct priv *); -uint16_t mlx5_tx_burst_raw_vec(void *, struct rte_mbuf **, uint16_t); -uint16_t mlx5_tx_burst_vec(void *, struct rte_mbuf **, uint16_t); -uint16_t mlx5_rx_burst_vec(void *, struct rte_mbuf **, uint16_t); +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); /* mlx5_mr.c */ -void mlx5_mp2mr_iter(struct rte_mempool *, void *); -struct mlx5_mr *priv_txq_mp2mr_reg(struct priv *priv, struct mlx5_txq_data *, - struct rte_mempool *, unsigned int); -struct mlx5_mr *mlx5_txq_mp2mr_reg(struct mlx5_txq_data *, struct rte_mempool *, - unsigned int); +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); +int mlx5_dma_map(struct rte_pci_device *pdev, void *addr, uint64_t iova, + size_t len); +int mlx5_dma_unmap(struct rte_pci_device *pdev, void *addr, uint64_t iova, + size_t len); -#ifndef NDEBUG /** - * Verify or set magic value in CQE. + * Provide safe 64bit store operation to mlx5 UAR region for both 32bit and + * 64bit architectures. * - * @param cqe - * Pointer to CQE. + * @param val + * value to write in CPU endian format. + * @param addr + * Address to write to. + * @param lock + * Address of the lock to use for that UAR access. + */ +static __rte_always_inline void +__mlx5_uar_write64_relaxed(uint64_t val, void *addr, + rte_spinlock_t *lock __rte_unused) +{ +#ifdef RTE_ARCH_64 + *(uint64_t *)addr = val; +#else /* !RTE_ARCH_64 */ + rte_spinlock_lock(lock); + *(uint32_t *)addr = val; + rte_io_wmb(); + *((uint32_t *)addr + 1) = val >> 32; + rte_spinlock_unlock(lock); +#endif +} + +/** + * Provide safe 64bit store operation to mlx5 UAR region for both 32bit and + * 64bit architectures while guaranteeing the order of execution with the + * code being executed. * - * @return - * 0 the first time. + * @param val + * value to write in CPU endian format. + * @param addr + * Address to write to. + * @param lock + * Address of the lock to use for that UAR access. */ -static inline int -check_cqe_seen(volatile struct mlx5_cqe *cqe) +static __rte_always_inline void +__mlx5_uar_write64(uint64_t val, void *addr, rte_spinlock_t *lock) { - static const uint8_t magic[] = "seen"; - volatile uint8_t (*buf)[sizeof(cqe->rsvd0)] = &cqe->rsvd0; - 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; + rte_io_wmb(); + __mlx5_uar_write64_relaxed(val, addr, lock); } -#endif /* NDEBUG */ + +/* Assist macros, used instead of directly calling the functions they wrap. */ +#ifdef RTE_ARCH_64 +#define mlx5_uar_write64_relaxed(val, dst, lock) \ + __mlx5_uar_write64_relaxed(val, dst, NULL) +#define mlx5_uar_write64(val, dst, lock) __mlx5_uar_write64(val, dst, NULL) +#else +#define mlx5_uar_write64_relaxed(val, dst, lock) \ + __mlx5_uar_write64_relaxed(val, dst, lock) +#define mlx5_uar_write64(val, dst, lock) __mlx5_uar_write64(val, dst, lock) +#endif + +/* CQE status. */ +enum mlx5_cqe_status { + MLX5_CQE_STATUS_SW_OWN, + MLX5_CQE_STATUS_HW_OWN, + MLX5_CQE_STATUS_ERR, +}; /** * Check whether CQE is valid. @@ -453,239 +443,141 @@ check_cqe_seen(volatile struct mlx5_cqe *cqe) * Consumer index. * * @return - * 0 on success, 1 on failure. + * The CQE status. */ -static __rte_always_inline int -check_cqe(volatile struct mlx5_cqe *cqe, - unsigned int cqes_n, const uint16_t ci) +static __rte_always_inline enum mlx5_cqe_status +check_cqe(volatile struct mlx5_cqe *cqe, const uint16_t cqes_n, + const uint16_t ci) { - uint16_t idx = ci & cqes_n; - uint8_t op_own = cqe->op_own; - uint8_t op_owner = MLX5_CQE_OWNER(op_own); - uint8_t op_code = MLX5_CQE_OPCODE(op_own); + const uint16_t idx = ci & cqes_n; + const uint8_t op_own = cqe->op_own; + const uint8_t op_owner = MLX5_CQE_OWNER(op_own); + const uint8_t op_code = MLX5_CQE_OPCODE(op_own); if (unlikely((op_owner != (!!(idx))) || (op_code == MLX5_CQE_INVALID))) - return 1; /* No CQE. */ -#ifndef NDEBUG - if ((op_code == MLX5_CQE_RESP_ERR) || - (op_code == MLX5_CQE_REQ_ERR)) { - volatile struct mlx5_err_cqe *err_cqe = (volatile void *)cqe; - uint8_t syndrome = err_cqe->syndrome; - - if ((syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR) || - (syndrome == MLX5_CQE_SYNDROME_REMOTE_ABORTED_ERR)) - return 0; - if (!check_cqe_seen(cqe)) { - ERROR("unexpected CQE error %u (0x%02x)" - " syndrome 0x%02x", - op_code, op_code, syndrome); - rte_hexdump(stderr, "MLX5 Error CQE:", - (const void *)((uintptr_t)err_cqe), - sizeof(*err_cqe)); - } - return 1; - } else if ((op_code != MLX5_CQE_RESP_SEND) && - (op_code != MLX5_CQE_REQ)) { - if (!check_cqe_seen(cqe)) { - ERROR("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 MLX5_CQE_STATUS_HW_OWN; + rte_cio_rmb(); + if (unlikely(op_code == MLX5_CQE_RESP_ERR || + op_code == MLX5_CQE_REQ_ERR)) + return MLX5_CQE_STATUS_ERR; + return MLX5_CQE_STATUS_SW_OWN; } /** - * Return the address of the WQE. + * Get Memory Pool (MP) from mbuf. If mbuf is indirect, the pool from which the + * cloned mbuf is allocated is returned instead. * - * @param txq - * Pointer to TX queue structure. - * @param wqe_ci - * WQE consumer index. + * @param buf + * Pointer to mbuf. * * @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. + * Memory pool where data is located for given mbuf. */ -static __rte_always_inline void -mlx5_tx_complete(struct mlx5_txq_data *txq) +static inline struct rte_mempool * +mlx5_mb2mp(struct rte_mbuf *buf) { - 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)) { - ERROR("unexpected error CQE, TX stopped"); - rte_hexdump(stderr, "MLX5 TXQ:", - (const void *)((uintptr_t)txq->wqes), - ((1 << txq->wqe_n) * - MLX5_WQE_SIZE)); - } - return; - } -#endif /* NDEBUG */ - ++cq_ci; - txq->wqe_pi = rte_be_to_cpu_16(cqe->wqe_counter); - ctrl = (volatile struct mlx5_wqe_ctrl *) - tx_mlx5_wqe(txq, txq->wqe_pi); - elts_tail = ctrl->ctrl3; - assert((elts_tail & elts_m) < (1 << txq->wqe_n)); - /* Free buffers. */ - while (elts_free != elts_tail) { - m = rte_pktmbuf_prefree_seg((*txq->elts)[elts_free++ & elts_m]); - if (likely(m != NULL)) { - if (likely(m->pool == pool)) { - free[blk_n++] = m; - } else { - if (likely(pool != NULL)) - rte_mempool_put_bulk(pool, - (void *)free, - blk_n); - free[0] = m; - pool = m->pool; - blk_n = 1; - } - } - } - if (blk_n) - rte_mempool_put_bulk(pool, (void *)free, blk_n); -#ifndef NDEBUG - elts_free = txq->elts_tail; - /* Poisoning. */ - while (elts_free != elts_tail) { - memset(&(*txq->elts)[elts_free & elts_m], - 0x66, - sizeof((*txq->elts)[elts_free & elts_m])); - ++elts_free; - } -#endif - txq->cq_ci = cq_ci; - txq->elts_tail = elts_tail; - /* Update the consumer index. */ - rte_wmb(); - *txq->cq_db = rte_cpu_to_be_32(cq_ci); + if (unlikely(RTE_MBUF_CLONED(buf))) + return rte_mbuf_from_indirect(buf)->pool; + return buf->pool; } /** - * Get Memory Pool (MP) from mbuf. If mbuf is indirect, the pool from which - * the cloned mbuf is allocated is returned instead. + * Query LKey from a packet buffer for Rx. No need to flush local caches for Rx + * as mempool is pre-configured and static. * - * @param buf - * Pointer to mbuf. + * @param rxq + * Pointer to Rx queue structure. + * @param addr + * Address to search. * * @return - * Memory pool where data is located for given mbuf. + * Searched LKey on success, UINT32_MAX on no match. */ -static struct rte_mempool * -mlx5_tx_mb2mp(struct rte_mbuf *buf) +static __rte_always_inline uint32_t +mlx5_rx_addr2mr(struct mlx5_rxq_data *rxq, uintptr_t addr) { - if (unlikely(RTE_MBUF_INDIRECT(buf))) - return rte_mbuf_from_indirect(buf)->pool; - return buf->pool; + struct mlx5_mr_ctrl *mr_ctrl = &rxq->mr_ctrl; + 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); + 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)) + /** - * Get Memory Region (MR) <-> rte_mbuf association from txq->mp2mr[]. - * Add MP to txq->mp2mr[] if it's not registered yet. If mp2mr[] is full, - * remove an entry first. + * Query LKey from a packet buffer for Tx. If not found, add the mempool. * * @param txq - * Pointer to TX queue structure. - * @param[in] mp - * Memory Pool for which a Memory Region lkey must be returned. + * Pointer to Tx queue structure. + * @param addr + * Address to search. * * @return - * mr->lkey on success, (uint32_t)-1 on failure. + * Searched LKey on success, UINT32_MAX on no match. */ static __rte_always_inline uint32_t mlx5_tx_mb2mr(struct mlx5_txq_data *txq, struct rte_mbuf *mb) { - uint16_t i = txq->mr_cache_idx; - uintptr_t addr = rte_pktmbuf_mtod(mb, uintptr_t); - struct mlx5_mr *mr; - - assert(i < RTE_DIM(txq->mp2mr)); - if (likely(txq->mp2mr[i]->start <= addr && txq->mp2mr[i]->end >= addr)) - return txq->mp2mr[i]->lkey; - for (i = 0; (i != RTE_DIM(txq->mp2mr)); ++i) { - if (unlikely(txq->mp2mr[i]->mr == NULL)) { - /* Unknown MP, add a new MR for it. */ - break; - } - if (txq->mp2mr[i]->start <= addr && - txq->mp2mr[i]->end >= addr) { - assert(txq->mp2mr[i]->lkey != (uint32_t)-1); - assert(rte_cpu_to_be_32(txq->mp2mr[i]->mr->lkey) == - txq->mp2mr[i]->lkey); - txq->mr_cache_idx = i; - return txq->mp2mr[i]->lkey; - } - } - txq->mr_cache_idx = 0; - mr = mlx5_txq_mp2mr_reg(txq, mlx5_tx_mb2mp(mb), i); - /* - * Request the reference to use in this queue, the original one is - * kept by the control plane. - */ - if (mr) { - rte_atomic32_inc(&mr->refcnt); - return mr->lkey; - } - return (uint32_t)-1; + struct mlx5_mr_ctrl *mr_ctrl = &txq->mr_ctrl; + uintptr_t addr = (uintptr_t)mb->buf_addr; + uint32_t lkey; + + /* Check generation bit to see if there's any change on existing MRs. */ + 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); + if (likely(lkey != UINT32_MAX)) + return lkey; + /* Take slower bottom-half on miss. */ + return mlx5_tx_mb2mr_bh(txq, mb); } /** - * Ring TX queue doorbell. + * Ring TX queue doorbell and flush the update if requested. * * @param txq * Pointer to TX queue structure. * @param wqe * Pointer to the last WQE posted in the NIC. + * @param cond + * Request for write memory barrier after BlueFlame update. */ static __rte_always_inline void -mlx5_tx_dbrec(struct mlx5_txq_data *txq, volatile struct mlx5_wqe *wqe) +mlx5_tx_dbrec_cond_wmb(struct mlx5_txq_data *txq, volatile struct mlx5_wqe *wqe, + int cond) { - uint64_t *dst = (uint64_t *)((uintptr_t)txq->bf_reg); + uint64_t *dst = MLX5_TX_BFREG(txq); volatile uint64_t *src = ((volatile uint64_t *)wqe); - rte_io_wmb(); + rte_cio_wmb(); *txq->qp_db = rte_cpu_to_be_32(txq->wqe_ci); /* Ensure ordering between DB record and BF copy. */ rte_wmb(); - *dst = *src; + mlx5_uar_write64_relaxed(*src, dst, txq->uar_lock); + if (cond) + rte_wmb(); +} + +/** + * Ring TX queue doorbell and flush the update by write memory barrier. + * + * @param txq + * Pointer to TX queue structure. + * @param wqe + * Pointer to the last WQE posted in the NIC. + */ +static __rte_always_inline void +mlx5_tx_dbrec(struct mlx5_txq_data *txq, volatile struct mlx5_wqe *wqe) +{ + mlx5_tx_dbrec_cond_wmb(txq, wqe, 1); } #endif /* RTE_PMD_MLX5_RXTX_H_ */