X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Flinux%2Fmlx5_os.c;h=6ac334263ed03ca516305d4e7b3bd9c3576c6c02;hb=ca5eb60ecd5bcd9d4dfed6972ea991d7ead0e9a3;hp=42f45ec40317f43da9e37f9557e24222c7c87805;hpb=50f95b23c9ba8237a7f376e2e90d4bfa04a3bab6;p=dpdk.git diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c index 42f45ec403..6ac334263e 100644 --- a/drivers/net/mlx5/linux/mlx5_os.c +++ b/drivers/net/mlx5/linux/mlx5_os.c @@ -10,25 +10,14 @@ #include #include #include -#include #include #include #include #include -/* Verbs header. */ -/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */ -#ifdef PEDANTIC -#pragma GCC diagnostic ignored "-Wpedantic" -#endif -#include -#ifdef PEDANTIC -#pragma GCC diagnostic error "-Wpedantic" -#endif - #include -#include -#include +#include +#include #include #include #include @@ -37,6 +26,7 @@ #include #include #include +#include #include #include @@ -55,6 +45,8 @@ #include "mlx5_flow.h" #include "rte_pmd_mlx5.h" #include "mlx5_verbs.h" +#include "mlx5_nl.h" +#include "mlx5_devx.h" #define MLX5_TAGS_HLIST_ARRAY_SIZE 8192 @@ -67,6 +59,35 @@ #define MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP (1 << 4) #endif +static const char *MZ_MLX5_PMD_SHARED_DATA = "mlx5_pmd_shared_data"; + +/* Spinlock for mlx5_shared_data allocation. */ +static rte_spinlock_t mlx5_shared_data_lock = RTE_SPINLOCK_INITIALIZER; + +/* Process local data for secondary processes. */ +static struct mlx5_local_data mlx5_local_data; + +/** + * Set the completion channel file descriptor interrupt as non-blocking. + * + * @param[in] rxq_obj + * Pointer to RQ channel object, which includes the channel fd + * + * @param[out] fd + * The file descriptor (representing the intetrrupt) used in this channel. + * + * @return + * 0 on successfully setting the fd to non-blocking, non-zero otherwise. + */ +int +mlx5_os_set_nonblock_channel_fd(int fd) +{ + int flags; + + flags = fcntl(fd, F_GETFL); + return fcntl(fd, F_SETFL, flags | O_NONBLOCK); +} + /** * Get mlx5 device attributes. The glue function query_device_ex() is called * with out parameter of type 'struct ibv_device_attr_ex *'. Then fill in mlx5 @@ -95,7 +116,12 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) device_attr->max_qp_wr = attr_ex.orig_attr.max_qp_wr; device_attr->max_sge = attr_ex.orig_attr.max_sge; device_attr->max_cq = attr_ex.orig_attr.max_cq; + device_attr->max_cqe = attr_ex.orig_attr.max_cqe; + device_attr->max_mr = attr_ex.orig_attr.max_mr; + device_attr->max_pd = attr_ex.orig_attr.max_pd; device_attr->max_qp = attr_ex.orig_attr.max_qp; + device_attr->max_srq = attr_ex.orig_attr.max_srq; + device_attr->max_srq_wr = attr_ex.orig_attr.max_srq_wr; device_attr->raw_packet_caps = attr_ex.raw_packet_caps; device_attr->max_rwq_indirection_table_size = attr_ex.rss_caps.max_rwq_indirection_table_size; @@ -134,7 +160,7 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) * Verbs callback to allocate a memory. This function should allocate the space * according to the size provided residing inside a huge page. * Please note that all allocation must respect the alignment from libmlx5 - * (i.e. currently sysconf(_SC_PAGESIZE)). + * (i.e. currently rte_mem_page_size()). * * @param[in] size * The size in bytes of the memory to allocate. @@ -147,23 +173,17 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) static void * mlx5_alloc_verbs_buf(size_t size, void *data) { - struct mlx5_priv *priv = data; + struct mlx5_dev_ctx_shared *sh = data; void *ret; - size_t alignment = sysconf(_SC_PAGESIZE); - unsigned int socket = SOCKET_ID_ANY; - - if (priv->verbs_alloc_ctx.type == MLX5_VERBS_ALLOC_TYPE_TX_QUEUE) { - const struct mlx5_txq_ctrl *ctrl = priv->verbs_alloc_ctx.obj; - - socket = ctrl->socket; - } else if (priv->verbs_alloc_ctx.type == - MLX5_VERBS_ALLOC_TYPE_RX_QUEUE) { - const struct mlx5_rxq_ctrl *ctrl = priv->verbs_alloc_ctx.obj; - - socket = ctrl->socket; + size_t alignment = rte_mem_page_size(); + if (alignment == (size_t)-1) { + DRV_LOG(ERR, "Failed to get mem page size"); + rte_errno = ENOMEM; + return NULL; } + MLX5_ASSERT(data != NULL); - ret = mlx5_malloc(0, size, alignment, socket); + ret = mlx5_malloc(0, size, alignment, sh->numa_node); if (!ret && size) rte_errno = ENOMEM; return ret; @@ -199,33 +219,85 @@ static int mlx5_alloc_shared_dr(struct mlx5_priv *priv) { struct mlx5_dev_ctx_shared *sh = priv->sh; - char s[MLX5_HLIST_NAMESIZE]; - int err = 0; + char s[MLX5_HLIST_NAMESIZE] __rte_unused; + int err; - if (!sh->flow_tbls) - err = mlx5_alloc_table_hash_list(priv); - else - DRV_LOG(DEBUG, "sh->flow_tbls[%p] already created, reuse\n", - (void *)sh->flow_tbls); + MLX5_ASSERT(sh && sh->refcnt); + if (sh->refcnt > 1) + return 0; + err = mlx5_alloc_table_hash_list(priv); if (err) - return err; + goto error; + /* The resources below are only valid with DV support. */ +#ifdef HAVE_IBV_FLOW_DV_SUPPORT + /* Init port id action cache list. */ + snprintf(s, sizeof(s), "%s_port_id_action_cache", sh->ibdev_name); + mlx5_cache_list_init(&sh->port_id_action_list, s, 0, sh, + flow_dv_port_id_create_cb, + flow_dv_port_id_match_cb, + flow_dv_port_id_remove_cb); + /* Init push vlan action cache list. */ + snprintf(s, sizeof(s), "%s_push_vlan_action_cache", sh->ibdev_name); + mlx5_cache_list_init(&sh->push_vlan_action_list, s, 0, sh, + flow_dv_push_vlan_create_cb, + flow_dv_push_vlan_match_cb, + flow_dv_push_vlan_remove_cb); + /* Init sample action cache list. */ + snprintf(s, sizeof(s), "%s_sample_action_cache", sh->ibdev_name); + mlx5_cache_list_init(&sh->sample_action_list, s, 0, sh, + flow_dv_sample_create_cb, + flow_dv_sample_match_cb, + flow_dv_sample_remove_cb); + /* Init dest array action cache list. */ + snprintf(s, sizeof(s), "%s_dest_array_cache", sh->ibdev_name); + mlx5_cache_list_init(&sh->dest_array_list, s, 0, sh, + flow_dv_dest_array_create_cb, + flow_dv_dest_array_match_cb, + flow_dv_dest_array_remove_cb); /* Create tags hash list table. */ snprintf(s, sizeof(s), "%s_tags", sh->ibdev_name); - sh->tag_table = mlx5_hlist_create(s, MLX5_TAGS_HLIST_ARRAY_SIZE); + sh->tag_table = mlx5_hlist_create(s, MLX5_TAGS_HLIST_ARRAY_SIZE, 0, + MLX5_HLIST_WRITE_MOST, + flow_dv_tag_create_cb, + flow_dv_tag_match_cb, + flow_dv_tag_remove_cb); if (!sh->tag_table) { DRV_LOG(ERR, "tags with hash creation failed."); err = ENOMEM; goto error; } + sh->tag_table->ctx = sh; + snprintf(s, sizeof(s), "%s_hdr_modify", sh->ibdev_name); + sh->modify_cmds = mlx5_hlist_create(s, MLX5_FLOW_HDR_MODIFY_HTABLE_SZ, + 0, MLX5_HLIST_WRITE_MOST | + MLX5_HLIST_DIRECT_KEY, + flow_dv_modify_create_cb, + flow_dv_modify_match_cb, + flow_dv_modify_remove_cb); + if (!sh->modify_cmds) { + DRV_LOG(ERR, "hdr modify hash creation failed"); + err = ENOMEM; + goto error; + } + sh->modify_cmds->ctx = sh; + snprintf(s, sizeof(s), "%s_encaps_decaps", sh->ibdev_name); + sh->encaps_decaps = mlx5_hlist_create(s, + MLX5_FLOW_ENCAP_DECAP_HTABLE_SZ, + 0, MLX5_HLIST_DIRECT_KEY | + MLX5_HLIST_WRITE_MOST, + flow_dv_encap_decap_create_cb, + flow_dv_encap_decap_match_cb, + flow_dv_encap_decap_remove_cb); + if (!sh->encaps_decaps) { + DRV_LOG(ERR, "encap decap hash creation failed"); + err = ENOMEM; + goto error; + } + sh->encaps_decaps->ctx = sh; +#endif #ifdef HAVE_MLX5DV_DR void *domain; - if (sh->dv_refcnt) { - /* Shared DV/DR structures is already initialized. */ - sh->dv_refcnt++; - priv->dr_shared = 1; - return 0; - } /* Reference counter is zero, we should initialize structures. */ domain = mlx5_glue->dr_create_domain(sh->ctx, MLX5DV_DR_DOMAIN_TYPE_NIC_RX); @@ -242,7 +314,6 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) err = errno; goto error; } - pthread_mutex_init(&sh->dv_mutex, NULL); sh->tx_domain = domain; #ifdef HAVE_MLX5DV_DR_ESWITCH if (priv->config.dv_esw_en) { @@ -254,9 +325,25 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) goto error; } sh->fdb_domain = domain; - sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop(); + } + /* + * The drop action is just some dummy placeholder in rdma-core. It + * does not belong to domains and has no any attributes, and, can be + * shared by the entire device. + */ + sh->dr_drop_action = mlx5_glue->dr_create_flow_action_drop(); + if (!sh->dr_drop_action) { + DRV_LOG(ERR, "FDB mlx5dv_dr_create_flow_action_drop"); + err = errno; + goto error; } #endif + if (!sh->tunnel_hub) + err = mlx5_alloc_tunnel_hub(sh); + if (err) { + DRV_LOG(ERR, "mlx5_alloc_tunnel_hub failed err=%d", err); + goto error; + } if (priv->config.reclaim_mode == MLX5_RCM_AGGR) { mlx5_glue->dr_reclaim_domain_memory(sh->rx_domain, 1); mlx5_glue->dr_reclaim_domain_memory(sh->tx_domain, 1); @@ -265,8 +352,10 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) } sh->pop_vlan_action = mlx5_glue->dr_create_flow_action_pop_vlan(); #endif /* HAVE_MLX5DV_DR */ - sh->dv_refcnt++; - priv->dr_shared = 1; + sh->default_miss_action = + mlx5_glue->dr_create_flow_action_default_miss(); + if (!sh->default_miss_action) + DRV_LOG(WARNING, "Default miss action is not supported."); return 0; error: /* Rollback the created objects. */ @@ -282,19 +371,31 @@ error: mlx5_glue->dr_destroy_domain(sh->fdb_domain); sh->fdb_domain = NULL; } - if (sh->esw_drop_action) { - mlx5_glue->destroy_flow_action(sh->esw_drop_action); - sh->esw_drop_action = NULL; + if (sh->dr_drop_action) { + mlx5_glue->destroy_flow_action(sh->dr_drop_action); + sh->dr_drop_action = NULL; } if (sh->pop_vlan_action) { mlx5_glue->destroy_flow_action(sh->pop_vlan_action); sh->pop_vlan_action = NULL; } + if (sh->encaps_decaps) { + mlx5_hlist_destroy(sh->encaps_decaps); + sh->encaps_decaps = NULL; + } + if (sh->modify_cmds) { + mlx5_hlist_destroy(sh->modify_cmds); + sh->modify_cmds = NULL; + } if (sh->tag_table) { /* tags should be destroyed with flow before. */ - mlx5_hlist_destroy(sh->tag_table, NULL, NULL); + mlx5_hlist_destroy(sh->tag_table); sh->tag_table = NULL; } + if (sh->tunnel_hub) { + mlx5_release_tunnel_hub(sh, priv->dev_port); + sh->tunnel_hub = NULL; + } mlx5_free_table_hash_list(priv); return err; } @@ -308,17 +409,12 @@ error: void mlx5_os_free_shared_dr(struct mlx5_priv *priv) { - struct mlx5_dev_ctx_shared *sh; + struct mlx5_dev_ctx_shared *sh = priv->sh; - if (!priv->dr_shared) + MLX5_ASSERT(sh && sh->refcnt); + if (sh->refcnt > 1) return; - priv->dr_shared = 0; - sh = priv->sh; - MLX5_ASSERT(sh); #ifdef HAVE_MLX5DV_DR - MLX5_ASSERT(sh->dv_refcnt); - if (sh->dv_refcnt && --sh->dv_refcnt) - return; if (sh->rx_domain) { mlx5_glue->dr_destroy_domain(sh->rx_domain); sh->rx_domain = NULL; @@ -332,25 +428,350 @@ mlx5_os_free_shared_dr(struct mlx5_priv *priv) mlx5_glue->dr_destroy_domain(sh->fdb_domain); sh->fdb_domain = NULL; } - if (sh->esw_drop_action) { - mlx5_glue->destroy_flow_action(sh->esw_drop_action); - sh->esw_drop_action = NULL; + if (sh->dr_drop_action) { + mlx5_glue->destroy_flow_action(sh->dr_drop_action); + sh->dr_drop_action = NULL; } #endif if (sh->pop_vlan_action) { mlx5_glue->destroy_flow_action(sh->pop_vlan_action); sh->pop_vlan_action = NULL; } - pthread_mutex_destroy(&sh->dv_mutex); #endif /* HAVE_MLX5DV_DR */ + if (sh->default_miss_action) + mlx5_glue->destroy_flow_action + (sh->default_miss_action); + if (sh->encaps_decaps) { + mlx5_hlist_destroy(sh->encaps_decaps); + sh->encaps_decaps = NULL; + } + if (sh->modify_cmds) { + mlx5_hlist_destroy(sh->modify_cmds); + sh->modify_cmds = NULL; + } if (sh->tag_table) { /* tags should be destroyed with flow before. */ - mlx5_hlist_destroy(sh->tag_table, NULL, NULL); + mlx5_hlist_destroy(sh->tag_table); sh->tag_table = NULL; } + if (sh->tunnel_hub) { + mlx5_release_tunnel_hub(sh, priv->dev_port); + sh->tunnel_hub = NULL; + } + mlx5_cache_list_destroy(&sh->port_id_action_list); + mlx5_cache_list_destroy(&sh->push_vlan_action_list); mlx5_free_table_hash_list(priv); } +/** + * Initialize shared data between primary and secondary process. + * + * A memzone is reserved by primary process and secondary processes attach to + * the memzone. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +mlx5_init_shared_data(void) +{ + const struct rte_memzone *mz; + int ret = 0; + + rte_spinlock_lock(&mlx5_shared_data_lock); + if (mlx5_shared_data == NULL) { + if (rte_eal_process_type() == RTE_PROC_PRIMARY) { + /* Allocate shared memory. */ + mz = rte_memzone_reserve(MZ_MLX5_PMD_SHARED_DATA, + sizeof(*mlx5_shared_data), + SOCKET_ID_ANY, 0); + if (mz == NULL) { + DRV_LOG(ERR, + "Cannot allocate mlx5 shared data"); + ret = -rte_errno; + goto error; + } + mlx5_shared_data = mz->addr; + memset(mlx5_shared_data, 0, sizeof(*mlx5_shared_data)); + rte_spinlock_init(&mlx5_shared_data->lock); + } else { + /* Lookup allocated shared memory. */ + mz = rte_memzone_lookup(MZ_MLX5_PMD_SHARED_DATA); + if (mz == NULL) { + DRV_LOG(ERR, + "Cannot attach mlx5 shared data"); + ret = -rte_errno; + goto error; + } + mlx5_shared_data = mz->addr; + memset(&mlx5_local_data, 0, sizeof(mlx5_local_data)); + } + } +error: + rte_spinlock_unlock(&mlx5_shared_data_lock); + return ret; +} + +/** + * PMD global initialization. + * + * Independent from individual device, this function initializes global + * per-PMD data structures distinguishing primary and secondary processes. + * Hence, each initialization is called once per a process. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +mlx5_init_once(void) +{ + struct mlx5_shared_data *sd; + struct mlx5_local_data *ld = &mlx5_local_data; + int ret = 0; + + if (mlx5_init_shared_data()) + return -rte_errno; + sd = mlx5_shared_data; + MLX5_ASSERT(sd); + rte_spinlock_lock(&sd->lock); + switch (rte_eal_process_type()) { + case RTE_PROC_PRIMARY: + if (sd->init_done) + break; + LIST_INIT(&sd->mem_event_cb_list); + rte_rwlock_init(&sd->mem_event_rwlock); + rte_mem_event_callback_register("MLX5_MEM_EVENT_CB", + mlx5_mr_mem_event_cb, NULL); + ret = mlx5_mp_init_primary(MLX5_MP_NAME, + mlx5_mp_os_primary_handle); + if (ret) + goto out; + sd->init_done = true; + break; + case RTE_PROC_SECONDARY: + if (ld->init_done) + break; + ret = mlx5_mp_init_secondary(MLX5_MP_NAME, + mlx5_mp_os_secondary_handle); + if (ret) + goto out; + ++sd->secondary_cnt; + ld->init_done = true; + break; + default: + break; + } +out: + rte_spinlock_unlock(&sd->lock); + return ret; +} + +/** + * Create the Tx queue DevX/Verbs object. + * + * @param dev + * Pointer to Ethernet device. + * @param idx + * Queue index in DPDK Tx queue array. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +mlx5_os_txq_obj_new(struct rte_eth_dev *dev, uint16_t idx) +{ + struct mlx5_priv *priv = dev->data->dev_private; + struct mlx5_txq_data *txq_data = (*priv->txqs)[idx]; + struct mlx5_txq_ctrl *txq_ctrl = + container_of(txq_data, struct mlx5_txq_ctrl, txq); + + if (txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN) + return mlx5_txq_devx_obj_new(dev, idx); +#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET + if (!priv->config.dv_esw_en) + return mlx5_txq_devx_obj_new(dev, idx); +#endif + return mlx5_txq_ibv_obj_new(dev, idx); +} + +/** + * Release an Tx DevX/verbs queue object. + * + * @param txq_obj + * DevX/Verbs Tx queue object. + */ +static void +mlx5_os_txq_obj_release(struct mlx5_txq_obj *txq_obj) +{ + if (txq_obj->txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN) { + mlx5_txq_devx_obj_release(txq_obj); + return; + } +#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET + if (!txq_obj->txq_ctrl->priv->config.dv_esw_en) { + mlx5_txq_devx_obj_release(txq_obj); + return; + } +#endif + mlx5_txq_ibv_obj_release(txq_obj); +} + +/** + * DV flow counter mode detect and config. + * + * @param dev + * Pointer to rte_eth_dev structure. + * + */ +static void +mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused) +{ +#ifdef HAVE_IBV_FLOW_DV_SUPPORT + struct mlx5_priv *priv = dev->data->dev_private; + struct mlx5_dev_ctx_shared *sh = priv->sh; + bool fallback; + +#ifndef HAVE_IBV_DEVX_ASYNC + fallback = true; +#else + fallback = false; + if (!priv->config.devx || !priv->config.dv_flow_en || + !priv->config.hca_attr.flow_counters_dump || + !(priv->config.hca_attr.flow_counter_bulk_alloc_bitmap & 0x4) || + (mlx5_flow_dv_discover_counter_offset_support(dev) == -ENOTSUP)) + fallback = true; +#endif + if (fallback) + DRV_LOG(INFO, "Use fall-back DV counter management. Flow " + "counter dump:%d, bulk_alloc_bitmap:0x%hhx.", + priv->config.hca_attr.flow_counters_dump, + priv->config.hca_attr.flow_counter_bulk_alloc_bitmap); + /* Initialize fallback mode only on the port initializes sh. */ + if (sh->refcnt == 1) + sh->cmng.counter_fallback = fallback; + else if (fallback != sh->cmng.counter_fallback) + DRV_LOG(WARNING, "Port %d in sh has different fallback mode " + "with others:%d.", PORT_ID(priv), fallback); +#endif +} + +static void +mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev) +{ + struct mlx5_priv *priv = dev->data->dev_private; + void *ctx = priv->sh->ctx; + + priv->q_counters = mlx5_devx_cmd_queue_counter_alloc(ctx); + if (!priv->q_counters) { + struct ibv_cq *cq = mlx5_glue->create_cq(ctx, 1, NULL, NULL, 0); + struct ibv_wq *wq; + + DRV_LOG(DEBUG, "Port %d queue counter object cannot be created " + "by DevX - fall-back to use the kernel driver global " + "queue counter.", dev->data->port_id); + /* Create WQ by kernel and query its queue counter ID. */ + if (cq) { + wq = mlx5_glue->create_wq(ctx, + &(struct ibv_wq_init_attr){ + .wq_type = IBV_WQT_RQ, + .max_wr = 1, + .max_sge = 1, + .pd = priv->sh->pd, + .cq = cq, + }); + if (wq) { + /* Counter is assigned only on RDY state. */ + int ret = mlx5_glue->modify_wq(wq, + &(struct ibv_wq_attr){ + .attr_mask = IBV_WQ_ATTR_STATE, + .wq_state = IBV_WQS_RDY, + }); + + if (ret == 0) + mlx5_devx_cmd_wq_query(wq, + &priv->counter_set_id); + claim_zero(mlx5_glue->destroy_wq(wq)); + } + claim_zero(mlx5_glue->destroy_cq(cq)); + } + } else { + priv->counter_set_id = priv->q_counters->id; + } + if (priv->counter_set_id == 0) + DRV_LOG(INFO, "Part of the port %d statistics will not be " + "available.", dev->data->port_id); +} + +/** + * Check if representor spawn info match devargs. + * + * @param spawn + * Verbs device parameters (name, port, switch_info) to spawn. + * @param eth_da + * Device devargs to probe. + * + * @return + * Match result. + */ +static bool +mlx5_representor_match(struct mlx5_dev_spawn_data *spawn, + struct rte_eth_devargs *eth_da) +{ + struct mlx5_switch_info *switch_info = &spawn->info; + unsigned int p, f; + uint16_t id; + uint16_t repr_id = mlx5_representor_id_encode(switch_info, + eth_da->type); + + switch (eth_da->type) { + case RTE_ETH_REPRESENTOR_SF: + if (!(spawn->info.port_name == -1 && + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFHPF) && + switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFSF) { + rte_errno = EBUSY; + return false; + } + break; + case RTE_ETH_REPRESENTOR_VF: + /* Allows HPF representor index -1 as exception. */ + if (!(spawn->info.port_name == -1 && + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFHPF) && + switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFVF) { + rte_errno = EBUSY; + return false; + } + break; + case RTE_ETH_REPRESENTOR_NONE: + rte_errno = EBUSY; + return false; + default: + rte_errno = ENOTSUP; + DRV_LOG(ERR, "unsupported representor type"); + return false; + } + /* Check representor ID: */ + for (p = 0; p < eth_da->nb_ports; ++p) { + if (spawn->pf_bond < 0) { + /* For non-LAG mode, allow and ignore pf. */ + switch_info->pf_num = eth_da->ports[p]; + repr_id = mlx5_representor_id_encode(switch_info, + eth_da->type); + } + for (f = 0; f < eth_da->nb_representor_ports; ++f) { + id = MLX5_REPRESENTOR_ID + (eth_da->ports[p], eth_da->type, + eth_da->representor_ports[f]); + if (repr_id == id) + return true; + } + } + rte_errno = EBUSY; + return false; +} + + /** * Spawn an Ethernet device from Verbs information. * @@ -360,6 +781,8 @@ mlx5_os_free_shared_dr(struct mlx5_priv *priv) * Verbs device parameters (name, port, switch_info) to spawn. * @param config * Device configuration parameters. + * @param config + * Device arguments. * * @return * A valid Ethernet device object on success, NULL otherwise and rte_errno @@ -371,7 +794,8 @@ mlx5_os_free_shared_dr(struct mlx5_priv *priv) static struct rte_eth_dev * mlx5_dev_spawn(struct rte_device *dpdk_dev, struct mlx5_dev_spawn_data *spawn, - struct mlx5_dev_config config) + struct mlx5_dev_config *config, + struct rte_eth_devargs *eth_da) { const struct mlx5_switch_info *switch_info = &spawn->info; struct mlx5_dev_ctx_shared *sh = NULL; @@ -382,8 +806,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, int err = 0; unsigned int hw_padding = 0; unsigned int mps; - unsigned int cqe_comp; - unsigned int cqe_pad = 0; unsigned int tunnel_en = 0; unsigned int mpls_en = 0; unsigned int swp = 0; @@ -396,51 +818,44 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, char name[RTE_ETH_NAME_MAX_LEN]; int own_domain_id = 0; uint16_t port_id; - unsigned int i; #ifdef HAVE_MLX5DV_DR_DEVX_PORT struct mlx5dv_devx_port devx_port = { .comp_mask = 0 }; #endif /* Determine if this port representor is supposed to be spawned. */ - if (switch_info->representor && dpdk_dev->devargs) { - struct rte_eth_devargs eth_da; - - err = rte_eth_devargs_parse(dpdk_dev->devargs->args, ð_da); - if (err) { - rte_errno = -err; - DRV_LOG(ERR, "failed to process device arguments: %s", - strerror(rte_errno)); - return NULL; - } - for (i = 0; i < eth_da.nb_representor_ports; ++i) - if (eth_da.representor_ports[i] == - (uint16_t)switch_info->port_name) - break; - if (i == eth_da.nb_representor_ports) { - rte_errno = EBUSY; - return NULL; - } - } + if (switch_info->representor && dpdk_dev->devargs && + !mlx5_representor_match(spawn, eth_da)) + return NULL; /* Build device name. */ - if (spawn->pf_bond < 0) { + if (spawn->pf_bond < 0) { /* Single device. */ if (!switch_info->representor) strlcpy(name, dpdk_dev->name, sizeof(name)); else - snprintf(name, sizeof(name), "%s_representor_%u", - dpdk_dev->name, switch_info->port_name); + err = snprintf(name, sizeof(name), "%s_representor_%s%u", + dpdk_dev->name, + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf", + switch_info->port_name); } else { /* Bonding device. */ - if (!switch_info->representor) - snprintf(name, sizeof(name), "%s_%s", + if (!switch_info->representor) { + err = snprintf(name, sizeof(name), "%s_%s", dpdk_dev->name, mlx5_os_get_dev_device_name(spawn->phys_dev)); - else - snprintf(name, sizeof(name), "%s_%s_representor_%u", - dpdk_dev->name, - mlx5_os_get_dev_device_name(spawn->phys_dev), - switch_info->port_name); + } else { + err = snprintf(name, sizeof(name), "%s_%s_representor_c%dpf%d%s%u", + dpdk_dev->name, + mlx5_os_get_dev_device_name(spawn->phys_dev), + switch_info->ctrl_num, + switch_info->pf_num, + switch_info->name_type == + MLX5_PHYS_PORT_NAME_TYPE_PFSF ? "sf" : "vf", + switch_info->port_name); + } } + if (err >= (int)sizeof(name)) + DRV_LOG(WARNING, "device name overflow %s", name); /* check if the device is already spawned */ if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) { rte_errno = EEXIST; @@ -457,7 +872,9 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, return NULL; } eth_dev->device = dpdk_dev; - eth_dev->dev_ops = &mlx5_os_dev_sec_ops; + eth_dev->dev_ops = &mlx5_dev_sec_ops; + eth_dev->rx_descriptor_status = mlx5_rx_descriptor_status; + eth_dev->tx_descriptor_status = mlx5_tx_descriptor_status; err = mlx5_proc_priv_init(eth_dev); if (err) return NULL; @@ -489,20 +906,24 @@ err_secondary: * devargs here to get ones, and later proceed devargs again * to override some hardware settings. */ - err = mlx5_args(&config, dpdk_dev->devargs); + err = mlx5_args(config, dpdk_dev->devargs); if (err) { err = rte_errno; DRV_LOG(ERR, "failed to process device arguments: %s", strerror(rte_errno)); goto error; } - mlx5_malloc_mem_select(config.sys_mem_en); - sh = mlx5_alloc_shared_dev_ctx(spawn, &config); + if (config->dv_miss_info) { + if (switch_info->master || switch_info->representor) + config->dv_xmeta_en = MLX5_XMETA_MODE_META16; + } + mlx5_malloc_mem_select(config->sys_mem_en); + sh = mlx5_alloc_shared_dev_ctx(spawn, config); if (!sh) return NULL; - config.devx = sh->devx; + config->devx = sh->devx; #ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR - config.dest_tir = 1; + config->dest_tir = 1; #endif #ifdef HAVE_IBV_MLX5_MOD_SWP dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP; @@ -535,7 +956,7 @@ err_secondary: swp = dv_attr.sw_parsing_caps.sw_parsing_offloads; DRV_LOG(DEBUG, "SWP support: %u", swp); #endif - config.swp = !!swp; + config->swp = !!swp; #ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) { struct mlx5dv_striding_rq_caps mprq_caps = @@ -563,17 +984,8 @@ err_secondary: mprq_caps.max_single_wqe_log_num_of_strides; } #endif - if (RTE_CACHE_LINE_SIZE == 128 && - !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP)) - cqe_comp = 0; - else - cqe_comp = 1; - config.cqe_comp = cqe_comp; -#ifdef HAVE_IBV_MLX5_MOD_CQE_128B_PAD - /* Whether device supports 128B Rx CQE padding. */ - cqe_pad = RTE_CACHE_LINE_SIZE == 128 && - (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_PAD); -#endif + /* Rx CQE compression is enabled by default. */ + config->cqe_comp = 1; #ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) { tunnel_en = ((dv_attr.tunnel_offloads_caps & @@ -589,7 +1001,7 @@ err_secondary: DRV_LOG(WARNING, "tunnel offloading disabled due to old OFED/rdma-core version"); #endif - config.tunnel_en = tunnel_en; + config->tunnel_en = tunnel_en; #ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT mpls_en = ((dv_attr.tunnel_offloads_caps & MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_GRE) && @@ -601,7 +1013,7 @@ err_secondary: DRV_LOG(WARNING, "MPLS over GRE/UDP tunnel offloading disabled due to" " old OFED/rdma-core version or firmware configuration"); #endif - config.mpls_en = mpls_en; + config->mpls_en = mpls_en; /* Check port status. */ err = mlx5_glue->query_port(sh->ctx, spawn->phys_port, &port_attr); if (err) { @@ -630,8 +1042,6 @@ err_secondary: priv->dev_port = spawn->phys_port; priv->pci_dev = spawn->pci_dev; priv->mtu = RTE_ETHER_MTU; - priv->mp_id.port_id = port_id; - strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN); /* Some internal functions rely on Netlink sockets, open them now. */ priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA); priv->nl_socket_route = mlx5_nl_init(NETLINK_ROUTE); @@ -712,9 +1122,8 @@ err_secondary: priv->vport_id = switch_info->representor ? switch_info->port_name + 1 : -1; #endif - /* representor_id field keeps the unmodified VF index. */ - priv->representor_id = switch_info->representor ? - switch_info->port_name : -1; + priv->representor_id = mlx5_representor_id_encode(switch_info, + eth_da->type); /* * Look for sibling devices in order to reuse their switch domain * if any, otherwise allocate one. @@ -742,39 +1151,39 @@ err_secondary: own_domain_id = 1; } /* Override some values set by hardware configuration. */ - mlx5_args(&config, dpdk_dev->devargs); - err = mlx5_dev_check_sibling_config(priv, &config); + mlx5_args(config, dpdk_dev->devargs); + err = mlx5_dev_check_sibling_config(priv, config); if (err) goto error; - config.hw_csum = !!(sh->device_attr.device_cap_flags_ex & + config->hw_csum = !!(sh->device_attr.device_cap_flags_ex & IBV_DEVICE_RAW_IP_CSUM); DRV_LOG(DEBUG, "checksum offloading is %ssupported", - (config.hw_csum ? "" : "not ")); + (config->hw_csum ? "" : "not ")); #if !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V42) && \ !defined(HAVE_IBV_DEVICE_COUNTERS_SET_V45) DRV_LOG(DEBUG, "counters are not supported"); #endif #if !defined(HAVE_IBV_FLOW_DV_SUPPORT) || !defined(HAVE_MLX5DV_DR) - if (config.dv_flow_en) { + if (config->dv_flow_en) { DRV_LOG(WARNING, "DV flow is not supported"); - config.dv_flow_en = 0; + config->dv_flow_en = 0; } #endif - config.ind_table_max_size = + config->ind_table_max_size = sh->device_attr.max_rwq_indirection_table_size; /* * Remove this check once DPDK supports larger/variable * indirection tables. */ - if (config.ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512) - config.ind_table_max_size = ETH_RSS_RETA_SIZE_512; + if (config->ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512) + config->ind_table_max_size = ETH_RSS_RETA_SIZE_512; DRV_LOG(DEBUG, "maximum Rx indirection table size is %u", - config.ind_table_max_size); - config.hw_vlan_strip = !!(sh->device_attr.raw_packet_caps & + config->ind_table_max_size); + config->hw_vlan_strip = !!(sh->device_attr.raw_packet_caps & IBV_RAW_PACKET_CAP_CVLAN_STRIPPING); DRV_LOG(DEBUG, "VLAN stripping is %ssupported", - (config.hw_vlan_strip ? "" : "not ")); - config.hw_fcs_strip = !!(sh->device_attr.raw_packet_caps & + (config->hw_vlan_strip ? "" : "not ")); + config->hw_fcs_strip = !!(sh->device_attr.raw_packet_caps & IBV_RAW_PACKET_CAP_SCATTER_FCS); #if defined(HAVE_IBV_WQ_FLAG_RX_END_PADDING) hw_padding = !!sh->device_attr.rx_pad_end_addr_align; @@ -782,75 +1191,74 @@ err_secondary: hw_padding = !!(sh->device_attr.device_cap_flags_ex & IBV_DEVICE_PCI_WRITE_END_PADDING); #endif - if (config.hw_padding && !hw_padding) { + if (config->hw_padding && !hw_padding) { DRV_LOG(DEBUG, "Rx end alignment padding isn't supported"); - config.hw_padding = 0; - } else if (config.hw_padding) { + config->hw_padding = 0; + } else if (config->hw_padding) { DRV_LOG(DEBUG, "Rx end alignment padding is enabled"); } - config.tso = (sh->device_attr.max_tso > 0 && + config->tso = (sh->device_attr.max_tso > 0 && (sh->device_attr.tso_supported_qpts & (1 << IBV_QPT_RAW_PACKET))); - if (config.tso) - config.tso_max_payload_sz = sh->device_attr.max_tso; + if (config->tso) + config->tso_max_payload_sz = sh->device_attr.max_tso; /* * MPW is disabled by default, while the Enhanced MPW is enabled * by default. */ - if (config.mps == MLX5_ARG_UNSET) - config.mps = (mps == MLX5_MPW_ENHANCED) ? MLX5_MPW_ENHANCED : + if (config->mps == MLX5_ARG_UNSET) + config->mps = (mps == MLX5_MPW_ENHANCED) ? MLX5_MPW_ENHANCED : MLX5_MPW_DISABLED; else - config.mps = config.mps ? mps : MLX5_MPW_DISABLED; + config->mps = config->mps ? mps : MLX5_MPW_DISABLED; DRV_LOG(INFO, "%sMPS is %s", - config.mps == MLX5_MPW_ENHANCED ? "enhanced " : - config.mps == MLX5_MPW ? "legacy " : "", - config.mps != MLX5_MPW_DISABLED ? "enabled" : "disabled"); - if (config.cqe_comp && !cqe_comp) { - DRV_LOG(WARNING, "Rx CQE compression isn't supported"); - config.cqe_comp = 0; - } - if (config.cqe_pad && !cqe_pad) { - DRV_LOG(WARNING, "Rx CQE padding isn't supported"); - config.cqe_pad = 0; - } else if (config.cqe_pad) { - DRV_LOG(INFO, "Rx CQE padding is enabled"); - } - if (config.devx) { - priv->counter_fallback = 0; - err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config.hca_attr); + config->mps == MLX5_MPW_ENHANCED ? "enhanced " : + config->mps == MLX5_MPW ? "legacy " : "", + config->mps != MLX5_MPW_DISABLED ? "enabled" : "disabled"); + if (config->devx) { + err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config->hca_attr); if (err) { err = -err; goto error; } - if (!config.hca_attr.flow_counters_dump) - priv->counter_fallback = 1; -#ifndef HAVE_IBV_DEVX_ASYNC - priv->counter_fallback = 1; -#endif - if (priv->counter_fallback) - DRV_LOG(INFO, "Use fall-back DV counter management"); + /* Check relax ordering support. */ + if (!haswell_broadwell_cpu) { + sh->cmng.relaxed_ordering_write = + config->hca_attr.relaxed_ordering_write; + sh->cmng.relaxed_ordering_read = + config->hca_attr.relaxed_ordering_read; + } else { + sh->cmng.relaxed_ordering_read = 0; + sh->cmng.relaxed_ordering_write = 0; + } + sh->rq_ts_format = config->hca_attr.rq_ts_format; + sh->sq_ts_format = config->hca_attr.sq_ts_format; + sh->qp_ts_format = config->hca_attr.qp_ts_format; /* Check for LRO support. */ - if (config.dest_tir && config.hca_attr.lro_cap && - config.dv_flow_en) { + if (config->dest_tir && config->hca_attr.lro_cap && + config->dv_flow_en) { /* TBD check tunnel lro caps. */ - config.lro.supported = config.hca_attr.lro_cap; + config->lro.supported = config->hca_attr.lro_cap; DRV_LOG(DEBUG, "Device supports LRO"); /* * If LRO timeout is not configured by application, * use the minimal supported value. */ - if (!config.lro.timeout) - config.lro.timeout = - config.hca_attr.lro_timer_supported_periods[0]; + if (!config->lro.timeout) + config->lro.timeout = + config->hca_attr.lro_timer_supported_periods[0]; DRV_LOG(DEBUG, "LRO session timeout set to %d usec", - config.lro.timeout); + config->lro.timeout); + DRV_LOG(DEBUG, "LRO minimal size of TCP segment " + "required for coalescing is %d bytes", + config->hca_attr.lro_min_mss_size); } #if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER) - if (config.hca_attr.qos.sup && config.hca_attr.qos.srtcm_sup && - config.dv_flow_en) { + if (config->hca_attr.qos.sup && + config->hca_attr.qos.flow_meter_old && + config->dv_flow_en) { uint8_t reg_c_mask = - config.hca_attr.qos.flow_meter_reg_c_ids; + config->hca_attr.qos.flow_meter_reg_c_ids; /* * Meter needs two REG_C's for color match and pre-sfx * flow match. Here get the REG_C for color match. @@ -862,68 +1270,122 @@ err_secondary: DRV_LOG(WARNING, "No available register for" " meter."); } else { - priv->mtr_color_reg = ffs(reg_c_mask) - 1 + - REG_C_0; + /* + * The meter color register is used by the + * flow-hit feature as well. + * The flow-hit feature must use REG_C_3 + * Prefer REG_C_3 if it is available. + */ + if (reg_c_mask & (1 << (REG_C_3 - REG_C_0))) + priv->mtr_color_reg = REG_C_3; + else + priv->mtr_color_reg = ffs(reg_c_mask) + - 1 + REG_C_0; priv->mtr_en = 1; priv->mtr_reg_share = - config.hca_attr.qos.flow_meter_reg_share; + config->hca_attr.qos.flow_meter; DRV_LOG(DEBUG, "The REG_C meter uses is %d", priv->mtr_color_reg); } } +#endif +#ifdef HAVE_MLX5_DR_CREATE_ACTION_ASO + if (config->hca_attr.flow_hit_aso && + priv->mtr_color_reg == REG_C_3) { + sh->flow_hit_aso_en = 1; + err = mlx5_flow_aso_age_mng_init(sh); + if (err) { + err = -err; + goto error; + } + DRV_LOG(DEBUG, "Flow Hit ASO is supported."); + } +#endif /* HAVE_MLX5_DR_CREATE_ACTION_ASO */ +#if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_SAMPLE) + if (config->hca_attr.log_max_ft_sampler_num > 0 && + config->dv_flow_en) { + priv->sampler_en = 1; + DRV_LOG(DEBUG, "Sampler enabled!"); + } else { + priv->sampler_en = 0; + if (!config->hca_attr.log_max_ft_sampler_num) + DRV_LOG(WARNING, + "No available register for sampler."); + else + DRV_LOG(DEBUG, "DV flow is not supported!"); + } #endif } - if (config.tx_pp) { + if (config->cqe_comp && RTE_CACHE_LINE_SIZE == 128 && + !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP)) { + DRV_LOG(WARNING, "Rx CQE 128B compression is not supported"); + config->cqe_comp = 0; + } + if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_FTAG_STRIDX && + (!config->devx || !config->hca_attr.mini_cqe_resp_flow_tag)) { + DRV_LOG(WARNING, "Flow Tag CQE compression" + " format isn't supported."); + config->cqe_comp = 0; + } + if (config->cqe_comp_fmt == MLX5_CQE_RESP_FORMAT_L34H_STRIDX && + (!config->devx || !config->hca_attr.mini_cqe_resp_l3_l4_tag)) { + DRV_LOG(WARNING, "L3/L4 Header CQE compression" + " format isn't supported."); + config->cqe_comp = 0; + } + DRV_LOG(DEBUG, "Rx CQE compression is %ssupported", + config->cqe_comp ? "" : "not "); + if (config->tx_pp) { DRV_LOG(DEBUG, "Timestamp counter frequency %u kHz", - config.hca_attr.dev_freq_khz); + config->hca_attr.dev_freq_khz); DRV_LOG(DEBUG, "Packet pacing is %ssupported", - config.hca_attr.qos.packet_pacing ? "" : "not "); + config->hca_attr.qos.packet_pacing ? "" : "not "); DRV_LOG(DEBUG, "Cross channel ops are %ssupported", - config.hca_attr.cross_channel ? "" : "not "); + config->hca_attr.cross_channel ? "" : "not "); DRV_LOG(DEBUG, "WQE index ignore is %ssupported", - config.hca_attr.wqe_index_ignore ? "" : "not "); + config->hca_attr.wqe_index_ignore ? "" : "not "); DRV_LOG(DEBUG, "Non-wire SQ feature is %ssupported", - config.hca_attr.non_wire_sq ? "" : "not "); + config->hca_attr.non_wire_sq ? "" : "not "); DRV_LOG(DEBUG, "Static WQE SQ feature is %ssupported (%d)", - config.hca_attr.log_max_static_sq_wq ? "" : "not ", - config.hca_attr.log_max_static_sq_wq); + config->hca_attr.log_max_static_sq_wq ? "" : "not ", + config->hca_attr.log_max_static_sq_wq); DRV_LOG(DEBUG, "WQE rate PP mode is %ssupported", - config.hca_attr.qos.wqe_rate_pp ? "" : "not "); - if (!config.devx) { + config->hca_attr.qos.wqe_rate_pp ? "" : "not "); + if (!config->devx) { DRV_LOG(ERR, "DevX is required for packet pacing"); err = ENODEV; goto error; } - if (!config.hca_attr.qos.packet_pacing) { + if (!config->hca_attr.qos.packet_pacing) { DRV_LOG(ERR, "Packet pacing is not supported"); err = ENODEV; goto error; } - if (!config.hca_attr.cross_channel) { + if (!config->hca_attr.cross_channel) { DRV_LOG(ERR, "Cross channel operations are" " required for packet pacing"); err = ENODEV; goto error; } - if (!config.hca_attr.wqe_index_ignore) { + if (!config->hca_attr.wqe_index_ignore) { DRV_LOG(ERR, "WQE index ignore feature is" " required for packet pacing"); err = ENODEV; goto error; } - if (!config.hca_attr.non_wire_sq) { + if (!config->hca_attr.non_wire_sq) { DRV_LOG(ERR, "Non-wire SQ feature is" " required for packet pacing"); err = ENODEV; goto error; } - if (!config.hca_attr.log_max_static_sq_wq) { + if (!config->hca_attr.log_max_static_sq_wq) { DRV_LOG(ERR, "Static WQE SQ feature is" " required for packet pacing"); err = ENODEV; goto error; } - if (!config.hca_attr.qos.wqe_rate_pp) { + if (!config->hca_attr.qos.wqe_rate_pp) { DRV_LOG(ERR, "WQE rate mode is required" " for packet pacing"); err = ENODEV; @@ -936,12 +1398,13 @@ err_secondary: goto error; #endif } - if (config.devx) { + if (config->devx) { uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)]; - err = mlx5_devx_cmd_register_read - (sh->ctx, MLX5_REGISTER_ID_MTUTC, 0, - reg, MLX5_ST_SZ_DW(register_mtutc)); + err = config->hca_attr.access_register_user ? + mlx5_devx_cmd_register_read + (sh->ctx, MLX5_REGISTER_ID_MTUTC, 0, + reg, MLX5_ST_SZ_DW(register_mtutc)) : ENOTSUP; if (!err) { uint32_t ts_mode; @@ -949,12 +1412,12 @@ err_secondary: ts_mode = MLX5_GET(register_mtutc, reg, time_stamp_mode); if (ts_mode == MLX5_MTUTC_TIMESTAMP_MODE_REAL_TIME) - config.rt_timestamp = 1; + config->rt_timestamp = 1; } else { /* Kernel does not support register reading. */ - if (config.hca_attr.dev_freq_khz == + if (config->hca_attr.dev_freq_khz == (NS_PER_S / MS_PER_S)) - config.rt_timestamp = 1; + config->rt_timestamp = 1; } } /* @@ -962,15 +1425,15 @@ err_secondary: * scatter FCS, and decapsulation is needed, clear the hw_fcs_strip * bit. Then DEV_RX_OFFLOAD_KEEP_CRC bit will not be set anymore. */ - if (config.hca_attr.scatter_fcs_w_decap_disable && config.decap_en) - config.hw_fcs_strip = 0; + if (config->hca_attr.scatter_fcs_w_decap_disable && config->decap_en) + config->hw_fcs_strip = 0; DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported", - (config.hw_fcs_strip ? "" : "not ")); - if (config.mprq.enabled && mprq) { - if (config.mprq.stride_num_n && - (config.mprq.stride_num_n > mprq_max_stride_num_n || - config.mprq.stride_num_n < mprq_min_stride_num_n)) { - config.mprq.stride_num_n = + (config->hw_fcs_strip ? "" : "not ")); + if (config->mprq.enabled && mprq) { + if (config->mprq.stride_num_n && + (config->mprq.stride_num_n > mprq_max_stride_num_n || + config->mprq.stride_num_n < mprq_min_stride_num_n)) { + config->mprq.stride_num_n = RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N, mprq_min_stride_num_n), mprq_max_stride_num_n); @@ -978,12 +1441,12 @@ err_secondary: "the number of strides" " for Multi-Packet RQ is out of range," " setting default value (%u)", - 1 << config.mprq.stride_num_n); + 1 << config->mprq.stride_num_n); } - if (config.mprq.stride_size_n && - (config.mprq.stride_size_n > mprq_max_stride_size_n || - config.mprq.stride_size_n < mprq_min_stride_size_n)) { - config.mprq.stride_size_n = + if (config->mprq.stride_size_n && + (config->mprq.stride_size_n > mprq_max_stride_size_n || + config->mprq.stride_size_n < mprq_min_stride_size_n)) { + config->mprq.stride_size_n = RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_SIZE_N, mprq_min_stride_size_n), mprq_max_stride_size_n); @@ -991,28 +1454,28 @@ err_secondary: "the size of a stride" " for Multi-Packet RQ is out of range," " setting default value (%u)", - 1 << config.mprq.stride_size_n); + 1 << config->mprq.stride_size_n); } - config.mprq.min_stride_size_n = mprq_min_stride_size_n; - config.mprq.max_stride_size_n = mprq_max_stride_size_n; - } else if (config.mprq.enabled && !mprq) { + config->mprq.min_stride_size_n = mprq_min_stride_size_n; + config->mprq.max_stride_size_n = mprq_max_stride_size_n; + } else if (config->mprq.enabled && !mprq) { DRV_LOG(WARNING, "Multi-Packet RQ isn't supported"); - config.mprq.enabled = 0; + config->mprq.enabled = 0; } - if (config.max_dump_files_num == 0) - config.max_dump_files_num = 128; + if (config->max_dump_files_num == 0) + config->max_dump_files_num = 128; eth_dev = rte_eth_dev_allocate(name); if (eth_dev == NULL) { DRV_LOG(ERR, "can not allocate rte ethdev"); err = ENOMEM; goto error; } - /* Flag to call rte_eth_dev_release_port() in rte_eth_dev_close(). */ - eth_dev->data->dev_flags |= RTE_ETH_DEV_CLOSE_REMOVE; if (priv->representor) { eth_dev->data->dev_flags |= RTE_ETH_DEV_REPRESENTOR; eth_dev->data->representor_id = priv->representor_id; } + priv->mp_id.port_id = eth_dev->data->port_id; + strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN); /* * Store associated network device interface index. This index * is permanent throughout the lifetime of device. So, we may store @@ -1024,6 +1487,7 @@ err_secondary: priv->dev_data = eth_dev->data; eth_dev->data->mac_addrs = priv->mac; eth_dev->device = dpdk_dev; + eth_dev->data->dev_flags |= RTE_ETH_DEV_AUTOFILL_QUEUE_XSTATS; /* Configure the first MAC address by default. */ if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) { DRV_LOG(ERR, @@ -1041,7 +1505,7 @@ err_secondary: mac.addr_bytes[4], mac.addr_bytes[5]); #ifdef RTE_LIBRTE_MLX5_DEBUG { - char ifname[IF_NAMESIZE]; + char ifname[MLX5_NAMESIZE]; if (mlx5_get_ifname(eth_dev, &ifname) == 0) DRV_LOG(DEBUG, "port %u ifname is \"%s\"", @@ -1062,16 +1526,20 @@ err_secondary: /* Initialize burst functions to prevent crashes before link-up. */ eth_dev->rx_pkt_burst = removed_rx_burst; eth_dev->tx_pkt_burst = removed_tx_burst; - eth_dev->dev_ops = &mlx5_os_dev_ops; + eth_dev->dev_ops = &mlx5_dev_ops; + eth_dev->rx_descriptor_status = mlx5_rx_descriptor_status; + eth_dev->tx_descriptor_status = mlx5_tx_descriptor_status; + eth_dev->rx_queue_count = mlx5_rx_queue_count; /* Register MAC address. */ claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0)); - if (config.vf && config.vf_nl_en) + if (config->vf && config->vf_nl_en) mlx5_nl_mac_addr_sync(priv->nl_socket_route, mlx5_ifindex(eth_dev), eth_dev->data->mac_addrs, MLX5_MAX_MAC_ADDRESSES); priv->flows = 0; priv->ctrl_flows = 0; + rte_spinlock_init(&priv->flow_list_lock); TAILQ_INIT(&priv->flow_meters); TAILQ_INIT(&priv->flow_meter_profiles); /* Hint libmlx5 to use PMD allocator for data plane resources */ @@ -1080,7 +1548,7 @@ err_secondary: (void *)((uintptr_t)&(struct mlx5dv_ctx_allocators){ .alloc = &mlx5_alloc_verbs_buf, .free = &mlx5_free_verbs_buf, - .data = priv, + .data = sh, })); /* Bring Ethernet device up. */ DRV_LOG(DEBUG, "port %u forcing Ethernet interface up", @@ -1093,34 +1561,47 @@ err_secondary: */ mlx5_link_update(eth_dev, 0); #ifdef HAVE_MLX5DV_DR_ESWITCH - if (!(config.hca_attr.eswitch_manager && config.dv_flow_en && + if (!(config->hca_attr.eswitch_manager && config->dv_flow_en && (switch_info->representor || switch_info->master))) - config.dv_esw_en = 0; + config->dv_esw_en = 0; #else - config.dv_esw_en = 0; + config->dv_esw_en = 0; #endif /* Detect minimal data bytes to inline. */ - mlx5_set_min_inline(spawn, &config); + mlx5_set_min_inline(spawn, config); /* Store device configuration on private structure. */ - priv->config = config; + priv->config = *config; /* Create context for virtual machine VLAN workaround. */ priv->vmwa_context = mlx5_vlan_vmwa_init(eth_dev, spawn->ifindex); - if (config.dv_flow_en) { + if (config->dv_flow_en) { err = mlx5_alloc_shared_dr(priv); if (err) goto error; - /* - * RSS id is shared with meter flow id. Meter flow id can only - * use the 24 MSB of the register. - */ - priv->qrss_id_pool = mlx5_flow_id_pool_alloc(UINT32_MAX >> - MLX5_MTR_COLOR_BITS); - if (!priv->qrss_id_pool) { - DRV_LOG(ERR, "can't create flow id pool"); - err = ENOMEM; - goto error; - } } + if (config->devx && config->dv_flow_en && config->dest_tir) { + priv->obj_ops = devx_obj_ops; + priv->obj_ops.drop_action_create = + ibv_obj_ops.drop_action_create; + priv->obj_ops.drop_action_destroy = + ibv_obj_ops.drop_action_destroy; +#ifndef HAVE_MLX5DV_DEVX_UAR_OFFSET + priv->obj_ops.txq_obj_modify = ibv_obj_ops.txq_obj_modify; +#else + if (config->dv_esw_en) + priv->obj_ops.txq_obj_modify = + ibv_obj_ops.txq_obj_modify; +#endif + /* Use specific wrappers for Tx object. */ + priv->obj_ops.txq_obj_new = mlx5_os_txq_obj_new; + priv->obj_ops.txq_obj_release = mlx5_os_txq_obj_release; + mlx5_queue_counter_id_prepare(eth_dev); + + } else { + priv->obj_ops = ibv_obj_ops; + } + priv->drop_queue.hrxq = mlx5_drop_action_create(eth_dev); + if (!priv->drop_queue.hrxq) + goto error; /* Supported Verbs flow priority number detection. */ err = mlx5_flow_discover_priorities(eth_dev); if (err < 0) { @@ -1143,11 +1624,10 @@ err_secondary: err = ENOTSUP; goto error; } - /* - * Allocate the buffer for flow creating, just once. - * The allocation must be done before any flow creating. - */ - mlx5_flow_alloc_intermediate(eth_dev); + mlx5_cache_list_init(&priv->hrxqs, "hrxq", 0, eth_dev, + mlx5_hrxq_create_cb, + mlx5_hrxq_match_cb, + mlx5_hrxq_remove_cb); /* Query availability of metadata reg_c's. */ err = mlx5_flow_discover_mreg_c(eth_dev); if (err < 0) { @@ -1171,17 +1651,26 @@ err_secondary: mlx5_flow_ext_mreg_supported(eth_dev) && priv->sh->dv_regc0_mask) { priv->mreg_cp_tbl = mlx5_hlist_create(MLX5_FLOW_MREG_HNAME, - MLX5_FLOW_MREG_HTABLE_SZ); + MLX5_FLOW_MREG_HTABLE_SZ, + 0, 0, + flow_dv_mreg_create_cb, + flow_dv_mreg_match_cb, + flow_dv_mreg_remove_cb); if (!priv->mreg_cp_tbl) { err = ENOMEM; goto error; } + priv->mreg_cp_tbl->ctx = eth_dev; } + rte_spinlock_init(&priv->shared_act_sl); + mlx5_flow_counter_mode_config(eth_dev); + if (priv->config.dv_flow_en) + eth_dev->data->dev_flags |= RTE_ETH_DEV_FLOW_OPS_THREAD_SAFE; return eth_dev; error: if (priv) { if (priv->mreg_cp_tbl) - mlx5_hlist_destroy(priv->mreg_cp_tbl, NULL, NULL); + mlx5_hlist_destroy(priv->mreg_cp_tbl); if (priv->sh) mlx5_os_free_shared_dr(priv); if (priv->nl_socket_route >= 0) @@ -1190,10 +1679,11 @@ error: close(priv->nl_socket_rdma); if (priv->vmwa_context) mlx5_vlan_vmwa_exit(priv->vmwa_context); - if (priv->qrss_id_pool) - mlx5_flow_id_pool_release(priv->qrss_id_pool); + if (eth_dev && priv->drop_queue.hrxq) + mlx5_drop_action_destroy(eth_dev); if (own_domain_id) claim_zero(rte_eth_switch_domain_free(priv->domain_id)); + mlx5_cache_list_destroy(&priv->hrxqs); mlx5_free(priv); if (eth_dev != NULL) eth_dev->data->dev_private = NULL; @@ -1256,9 +1746,13 @@ mlx5_dev_spawn_data_cmp(const void *a, const void *b) * @param[in] ibv_dev * Pointer to Infiniband device structure. * @param[in] pci_dev - * Pointer to PCI device structure to match PCI address. + * Pointer to primary PCI address structure to match. * @param[in] nl_rdma * Netlink RDMA group socket handle. + * @param[in] owner + * Rerepsentor owner PF index. + * @param[out] bond_info + * Pointer to bonding information. * * @return * negative value if no bonding device found, otherwise @@ -1266,20 +1760,23 @@ mlx5_dev_spawn_data_cmp(const void *a, const void *b) */ static int mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, - const struct rte_pci_device *pci_dev, - int nl_rdma) + const struct rte_pci_addr *pci_dev, + int nl_rdma, uint16_t owner, + struct mlx5_bond_info *bond_info) { char ifname[IF_NAMESIZE + 1]; unsigned int ifindex; unsigned int np, i; - FILE *file = NULL; + FILE *bond_file = NULL, *file; int pf = -1; + int ret; /* * Try to get master device name. If something goes * wrong suppose the lack of kernel support and no * bonding devices. */ + memset(bond_info, 0, sizeof(*bond_info)); if (nl_rdma < 0) return -1; if (!strstr(ibv_dev->name, "bond")) @@ -1303,15 +1800,15 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, /* Try to read bonding slave names from sysfs. */ MKSTR(slaves, "/sys/class/net/%s/master/bonding/slaves", ifname); - file = fopen(slaves, "r"); - if (file) + bond_file = fopen(slaves, "r"); + if (bond_file) break; } - if (!file) + if (!bond_file) return -1; /* Use safe format to check maximal buffer length. */ MLX5_ASSERT(atol(RTE_STR(IF_NAMESIZE)) == IF_NAMESIZE); - while (fscanf(file, "%" RTE_STR(IF_NAMESIZE) "s", ifname) == 1) { + while (fscanf(bond_file, "%" RTE_STR(IF_NAMESIZE) "s", ifname) == 1) { char tmp_str[IF_NAMESIZE + 32]; struct rte_pci_addr pci_addr; struct mlx5_switch_info info; @@ -1324,13 +1821,7 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, " for netdev \"%s\"", ifname); continue; } - if (pci_dev->addr.domain != pci_addr.domain || - pci_dev->addr.bus != pci_addr.bus || - pci_dev->addr.devid != pci_addr.devid || - pci_dev->addr.function != pci_addr.function) - continue; /* Slave interface PCI address match found. */ - fclose(file); snprintf(tmp_str, sizeof(tmp_str), "/sys/class/net/%s/phys_port_name", ifname); file = fopen(tmp_str, "rb"); @@ -1339,32 +1830,75 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, info.name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET; if (fscanf(file, "%32s", tmp_str) == 1) mlx5_translate_port_name(tmp_str, &info); - if (info.name_type == MLX5_PHYS_PORT_NAME_TYPE_LEGACY || - info.name_type == MLX5_PHYS_PORT_NAME_TYPE_UPLINK) + fclose(file); + /* Only process PF ports. */ + if (info.name_type != MLX5_PHYS_PORT_NAME_TYPE_LEGACY && + info.name_type != MLX5_PHYS_PORT_NAME_TYPE_UPLINK) + continue; + /* Check max bonding member. */ + if (info.port_name >= MLX5_BOND_MAX_PORTS) { + DRV_LOG(WARNING, "bonding index out of range, " + "please increase MLX5_BOND_MAX_PORTS: %s", + tmp_str); + break; + } + /* Match PCI address. */ + if (pci_dev->domain == pci_addr.domain && + pci_dev->bus == pci_addr.bus && + pci_dev->devid == pci_addr.devid && + pci_dev->function + owner == pci_addr.function) pf = info.port_name; - break; - } - if (file) + /* Get ifindex. */ + snprintf(tmp_str, sizeof(tmp_str), + "/sys/class/net/%s/ifindex", ifname); + file = fopen(tmp_str, "rb"); + if (!file) + break; + ret = fscanf(file, "%u", &ifindex); fclose(file); + if (ret != 1) + break; + /* Save bonding info. */ + strncpy(bond_info->ports[info.port_name].ifname, ifname, + sizeof(bond_info->ports[0].ifname)); + bond_info->ports[info.port_name].pci_addr = pci_addr; + bond_info->ports[info.port_name].ifindex = ifindex; + bond_info->n_port++; + } + if (pf >= 0) { + /* Get bond interface info */ + ret = mlx5_sysfs_bond_info(ifindex, &bond_info->ifindex, + bond_info->ifname); + if (ret) + DRV_LOG(ERR, "unable to get bond info: %s", + strerror(rte_errno)); + else + DRV_LOG(INFO, "PF device %u, bond device %u(%s)", + ifindex, bond_info->ifindex, bond_info->ifname); + } return pf; } /** - * DPDK callback to register a PCI device. + * Register a PCI device within bonding. * - * This function spawns Ethernet devices out of a given PCI device. + * This function spawns Ethernet devices out of a given PCI device and + * bonding owner PF index. * - * @param[in] pci_drv - * PCI driver structure (mlx5_driver). * @param[in] pci_dev * PCI device information. + * @param[in] req_eth_da + * Requested ethdev device argument. + * @param[in] owner_id + * Requested owner PF port ID within bonding device, default to 0. * * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ -int -mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, - struct rte_pci_device *pci_dev) +static int +mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, + struct rte_eth_devargs *req_eth_da, + uint16_t owner_id) { struct ibv_device **ibv_list; /* @@ -1393,13 +1927,12 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, int bd = -1; struct mlx5_dev_spawn_data *list = NULL; struct mlx5_dev_config dev_config; - int ret; + unsigned int dev_config_vf; + struct rte_eth_devargs eth_da = *req_eth_da; + struct rte_pci_addr owner_pci = pci_dev->addr; /* Owner PF. */ + struct mlx5_bond_info bond_info; + int ret = -1; - if (mlx5_class_get(pci_dev->device.devargs) != MLX5_CLASS_NET) { - DRV_LOG(DEBUG, "Skip probing - should be probed by other mlx5" - " driver."); - return 1; - } if (rte_eal_process_type() == RTE_PROC_PRIMARY) mlx5_pmd_socket_init(); ret = mlx5_init_once(); @@ -1408,7 +1941,6 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, strerror(rte_errno)); return -rte_errno; } - MLX5_ASSERT(pci_drv == &mlx5_driver); errno = 0; ibv_list = mlx5_glue->get_device_list(&ret); if (!ibv_list) { @@ -1430,7 +1962,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name); bd = mlx5_device_bond_pci_match - (ibv_list[ret], pci_dev, nl_rdma); + (ibv_list[ret], &owner_pci, nl_rdma, owner_id, + &bond_info); if (bd >= 0) { /* * Bonding device detected. Only one match is allowed, @@ -1447,23 +1980,28 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, ret = -rte_errno; goto exit; } + /* Amend owner pci address if owner PF ID specified. */ + if (eth_da.nb_representor_ports) + owner_pci.function += owner_id; DRV_LOG(INFO, "PCI information matches for" " slave %d bonding device \"%s\"", bd, ibv_list[ret]->name); ibv_match[nd++] = ibv_list[ret]; break; + } else { + /* Bonding device not found. */ + if (mlx5_dev_to_pci_addr + (ibv_list[ret]->ibdev_path, &pci_addr)) + continue; + if (owner_pci.domain != pci_addr.domain || + owner_pci.bus != pci_addr.bus || + owner_pci.devid != pci_addr.devid || + owner_pci.function != pci_addr.function) + continue; + DRV_LOG(INFO, "PCI information matches for device \"%s\"", + ibv_list[ret]->name); + ibv_match[nd++] = ibv_list[ret]; } - if (mlx5_dev_to_pci_addr - (ibv_list[ret]->ibdev_path, &pci_addr)) - continue; - if (pci_dev->addr.domain != pci_addr.domain || - pci_dev->addr.bus != pci_addr.bus || - pci_dev->addr.devid != pci_addr.devid || - pci_dev->addr.function != pci_addr.function) - continue; - DRV_LOG(INFO, "PCI information matches for device \"%s\"", - ibv_list[ret]->name); - ibv_match[nd++] = ibv_list[ret]; } ibv_match[nd] = NULL; if (!nd) { @@ -1471,8 +2009,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, DRV_LOG(WARNING, "no Verbs device matches PCI device " PCI_PRI_FMT "," " are kernel drivers loaded?", - pci_dev->addr.domain, pci_dev->addr.bus, - pci_dev->addr.devid, pci_dev->addr.function); + owner_pci.domain, owner_pci.bus, + owner_pci.devid, owner_pci.function); rte_errno = ENOENT; ret = -rte_errno; goto exit; @@ -1534,6 +2072,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, MLX5_ASSERT(nd == 1); MLX5_ASSERT(np); for (i = 1; i <= np; ++i) { + list[ns].bond_info = &bond_info; list[ns].max_port = np; list[ns].phys_port = i; list[ns].phys_dev = ibv_match[0]; @@ -1571,6 +2110,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, (list[ns].ifindex, &list[ns].info); } +#ifdef HAVE_MLX5DV_DR_DEVX_PORT if (!ret && bd >= 0) { switch (list[ns].info.name_type) { case MLX5_PHYS_PORT_NAME_TYPE_UPLINK: @@ -1580,6 +2120,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, case MLX5_PHYS_PORT_NAME_TYPE_PFHPF: /* Fallthrough */ case MLX5_PHYS_PORT_NAME_TYPE_PFVF: + /* Fallthrough */ + case MLX5_PHYS_PORT_NAME_TYPE_PFSF: if (list[ns].info.pf_num == bd) ns++; break; @@ -1588,6 +2130,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, } continue; } +#endif if (!ret && (list[ns].info.representor ^ list[ns].info.master)) ns++; @@ -1620,6 +2163,7 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, */ for (i = 0; i != nd; ++i) { memset(&list[ns].info, 0, sizeof(list[ns].info)); + list[ns].bond_info = NULL; list[ns].max_port = 1; list[ns].phys_port = 1; list[ns].phys_dev = ibv_match[i]; @@ -1718,30 +2262,6 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, * (i.e. master first, then representors from lowest to highest ID). */ qsort(list, ns, sizeof(*list), mlx5_dev_spawn_data_cmp); - /* Default configuration. */ - dev_config = (struct mlx5_dev_config){ - .hw_padding = 0, - .mps = MLX5_ARG_UNSET, - .dbnc = MLX5_ARG_UNSET, - .rx_vec_en = 1, - .txq_inline_max = MLX5_ARG_UNSET, - .txq_inline_min = MLX5_ARG_UNSET, - .txq_inline_mpw = MLX5_ARG_UNSET, - .txqs_inline = MLX5_ARG_UNSET, - .vf_nl_en = 1, - .mr_ext_memseg_en = 1, - .mprq = { - .enabled = 0, /* Disabled by default. */ - .stride_num_n = 0, - .stride_size_n = 0, - .max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN, - .min_rxqs_num = MLX5_MPRQ_MIN_RXQS, - }, - .dv_esw_en = 1, - .dv_flow_en = 1, - .decap_en = 1, - .log_hp_size = MLX5_ARG_UNSET, - }; /* Device specific configuration. */ switch (pci_dev->id.device_id) { case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF: @@ -1750,18 +2270,56 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF: case PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF: case PCI_DEVICE_ID_MELLANOX_CONNECTX6VF: - case PCI_DEVICE_ID_MELLANOX_CONNECTX6DXVF: - dev_config.vf = 1; + case PCI_DEVICE_ID_MELLANOX_CONNECTXVF: + dev_config_vf = 1; break; default: + dev_config_vf = 0; break; } + if (eth_da.type != RTE_ETH_REPRESENTOR_NONE) { + /* Set devargs default values. */ + if (eth_da.nb_mh_controllers == 0) { + eth_da.nb_mh_controllers = 1; + eth_da.mh_controllers[0] = 0; + } + if (eth_da.nb_ports == 0 && ns > 0) { + if (list[0].pf_bond >= 0 && list[0].info.representor) + DRV_LOG(WARNING, "Representor on Bonding device should use pf#vf# syntax: %s", + pci_dev->device.devargs->args); + eth_da.nb_ports = 1; + eth_da.ports[0] = list[0].info.pf_num; + } + if (eth_da.nb_representor_ports == 0) { + eth_da.nb_representor_ports = 1; + eth_da.representor_ports[0] = 0; + } + } for (i = 0; i != ns; ++i) { uint32_t restore; + /* Default configuration. */ + memset(&dev_config, 0, sizeof(struct mlx5_dev_config)); + dev_config.vf = dev_config_vf; + dev_config.mps = MLX5_ARG_UNSET; + dev_config.dbnc = MLX5_ARG_UNSET; + dev_config.rx_vec_en = 1; + dev_config.txq_inline_max = MLX5_ARG_UNSET; + dev_config.txq_inline_min = MLX5_ARG_UNSET; + dev_config.txq_inline_mpw = MLX5_ARG_UNSET; + dev_config.txqs_inline = MLX5_ARG_UNSET; + dev_config.vf_nl_en = 1; + dev_config.mr_ext_memseg_en = 1; + dev_config.mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN; + dev_config.mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS; + dev_config.dv_esw_en = 1; + dev_config.dv_flow_en = 1; + dev_config.decap_en = 1; + dev_config.log_hp_size = MLX5_ARG_UNSET; list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device, &list[i], - dev_config); + &dev_config, + ð_da); if (!list[i].eth_dev) { if (rte_errno != EBUSY && rte_errno != EEXIST) break; @@ -1778,8 +2336,8 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, DRV_LOG(ERR, "probe of PCI device " PCI_PRI_FMT " aborted after" " encountering an error: %s", - pci_dev->addr.domain, pci_dev->addr.bus, - pci_dev->addr.devid, pci_dev->addr.function, + owner_pci.domain, owner_pci.bus, + owner_pci.devid, owner_pci.function, strerror(rte_errno)); ret = -rte_errno; /* Roll back. */ @@ -1814,6 +2372,60 @@ exit: return ret; } +/** + * DPDK callback to register a PCI device. + * + * This function spawns Ethernet devices out of a given PCI device. + * + * @param[in] pci_drv + * PCI driver structure (mlx5_driver). + * @param[in] pci_dev + * PCI device information. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, + struct rte_pci_device *pci_dev) +{ + struct rte_eth_devargs eth_da = { .type = RTE_ETH_REPRESENTOR_NONE }; + int ret = 0; + uint16_t p; + + if (pci_dev->device.devargs) { + /* Parse representor information from device argument. */ + if (pci_dev->device.devargs->cls_str) + ret = rte_eth_devargs_parse + (pci_dev->device.devargs->cls_str, ð_da); + if (ret) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + pci_dev->device.devargs->cls_str); + return -rte_errno; + } + if (eth_da.type == RTE_ETH_REPRESENTOR_NONE) { + /* Support legacy device argument */ + ret = rte_eth_devargs_parse + (pci_dev->device.devargs->args, ð_da); + if (ret) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + pci_dev->device.devargs->args); + return -rte_errno; + } + } + } + + if (eth_da.nb_ports > 0) { + /* Iterate all port if devargs pf is range: "pf[0-1]vf[...]". */ + for (p = 0; p < eth_da.nb_ports; p++) + ret = mlx5_os_pci_probe_pf(pci_dev, ð_da, + eth_da.ports[p]); + } else { + ret = mlx5_os_pci_probe_pf(pci_dev, ð_da, 0); + } + return ret; +} + static int mlx5_config_doorbell_mapping_env(const struct mlx5_dev_config *config) { @@ -1932,6 +2544,16 @@ mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn, DRV_LOG(DEBUG, "DevX is NOT supported"); err = 0; } + if (!err && sh->ctx) { + /* Hint libmlx5 to use PMD allocator for data plane resources */ + mlx5_glue->dv_set_context_attr(sh->ctx, + MLX5DV_CTX_ATTR_BUF_ALLOCATORS, + (void *)((uintptr_t)&(struct mlx5dv_ctx_allocators){ + .alloc = &mlx5_alloc_verbs_buf, + .free = &mlx5_free_verbs_buf, + .data = sh, + })); + } return err; } @@ -2038,11 +2660,25 @@ mlx5_os_read_dev_stat(struct mlx5_priv *priv, const char *ctr_name, int fd; if (priv->sh) { + if (priv->q_counters != NULL && + strcmp(ctr_name, "out_of_buffer") == 0) + return mlx5_devx_cmd_queue_counter_query(priv->sh->ctx, + 0, (uint32_t *)stat); MKSTR(path, "%s/ports/%d/hw_counters/%s", - priv->sh->ibdev_path, - priv->dev_port, - ctr_name); + priv->sh->ibdev_path, + priv->dev_port, + ctr_name); fd = open(path, O_RDONLY); + /* + * in switchdev the file location is not per port + * but rather in /hw_counters/. + */ + if (fd == -1) { + MKSTR(path1, "%s/hw_counters/%s", + priv->sh->ibdev_path, + ctr_name); + fd = open(path1, O_RDONLY); + } if (fd != -1) { char buf[21] = {'\0'}; ssize_t n = read(fd, buf, sizeof(buf)); @@ -2059,436 +2695,148 @@ mlx5_os_read_dev_stat(struct mlx5_priv *priv, const char *ctr_name, } /** - * Read device counters table. + * Set the reg_mr and dereg_mr call backs * - * @param dev - * Pointer to Ethernet device. - * @param[out] stats - * Counters table output buffer. + * @param reg_mr_cb[out] + * Pointer to reg_mr func + * @param dereg_mr_cb[out] + * Pointer to dereg_mr func * - * @return - * 0 on success and stats is filled, negative errno value otherwise and - * rte_errno is set. */ -int -mlx5_os_read_dev_counters(struct rte_eth_dev *dev, uint64_t *stats) +void +mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb, + mlx5_dereg_mr_t *dereg_mr_cb) +{ + *reg_mr_cb = mlx5_mr_verbs_ops.reg_mr; + *dereg_mr_cb = mlx5_mr_verbs_ops.dereg_mr; +} + +/** + * Remove a MAC address from device + * + * @param dev + * Pointer to Ethernet device structure. + * @param index + * MAC address index. + */ +void +mlx5_os_mac_addr_remove(struct rte_eth_dev *dev, uint32_t index) { struct mlx5_priv *priv = dev->data->dev_private; - struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl; - unsigned int i; - struct ifreq ifr; - unsigned int stats_sz = xstats_ctrl->stats_n * sizeof(uint64_t); - unsigned char et_stat_buf[sizeof(struct ethtool_stats) + stats_sz]; - struct ethtool_stats *et_stats = (struct ethtool_stats *)et_stat_buf; - int ret; + const int vf = priv->config.vf; - et_stats->cmd = ETHTOOL_GSTATS; - et_stats->n_stats = xstats_ctrl->stats_n; - ifr.ifr_data = (caddr_t)et_stats; - ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); - if (ret) { - DRV_LOG(WARNING, - "port %u unable to read statistic values from device", - dev->data->port_id); - return ret; - } - for (i = 0; i != xstats_ctrl->mlx5_stats_n; ++i) { - if (xstats_ctrl->info[i].dev) { - ret = mlx5_os_read_dev_stat(priv, - xstats_ctrl->info[i].ctr_name, - &stats[i]); - /* return last xstats counter if fail to read. */ - if (ret == 0) - xstats_ctrl->xstats[i] = stats[i]; - else - stats[i] = xstats_ctrl->xstats[i]; - } else { - stats[i] = (uint64_t) - et_stats->data[xstats_ctrl->dev_table_idx[i]]; - } - } - return 0; + if (vf) + mlx5_nl_mac_addr_remove(priv->nl_socket_route, + mlx5_ifindex(dev), priv->mac_own, + &dev->data->mac_addrs[index], index); } /** - * Query the number of statistics provided by ETHTOOL. + * Adds a MAC address to the device * * @param dev - * Pointer to Ethernet device. + * Pointer to Ethernet device structure. + * @param mac_addr + * MAC address to register. + * @param index + * MAC address index. * * @return - * Number of statistics on success, negative errno value otherwise and - * rte_errno is set. + * 0 on success, a negative errno value otherwise */ int -mlx5_os_get_stats_n(struct rte_eth_dev *dev) +mlx5_os_mac_addr_add(struct rte_eth_dev *dev, struct rte_ether_addr *mac, + uint32_t index) { - struct ethtool_drvinfo drvinfo; - struct ifreq ifr; - int ret; + struct mlx5_priv *priv = dev->data->dev_private; + const int vf = priv->config.vf; + int ret = 0; - drvinfo.cmd = ETHTOOL_GDRVINFO; - ifr.ifr_data = (caddr_t)&drvinfo; - ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); - if (ret) { - DRV_LOG(WARNING, "port %u unable to query number of statistics", - dev->data->port_id); - return ret; - } - return drvinfo.n_stats; + if (vf) + ret = mlx5_nl_mac_addr_add(priv->nl_socket_route, + mlx5_ifindex(dev), priv->mac_own, + mac, index); + return ret; } -static const struct mlx5_counter_ctrl mlx5_counters_init[] = { - { - .dpdk_name = "rx_port_unicast_bytes", - .ctr_name = "rx_vport_unicast_bytes", - }, - { - .dpdk_name = "rx_port_multicast_bytes", - .ctr_name = "rx_vport_multicast_bytes", - }, - { - .dpdk_name = "rx_port_broadcast_bytes", - .ctr_name = "rx_vport_broadcast_bytes", - }, - { - .dpdk_name = "rx_port_unicast_packets", - .ctr_name = "rx_vport_unicast_packets", - }, - { - .dpdk_name = "rx_port_multicast_packets", - .ctr_name = "rx_vport_multicast_packets", - }, - { - .dpdk_name = "rx_port_broadcast_packets", - .ctr_name = "rx_vport_broadcast_packets", - }, - { - .dpdk_name = "tx_port_unicast_bytes", - .ctr_name = "tx_vport_unicast_bytes", - }, - { - .dpdk_name = "tx_port_multicast_bytes", - .ctr_name = "tx_vport_multicast_bytes", - }, - { - .dpdk_name = "tx_port_broadcast_bytes", - .ctr_name = "tx_vport_broadcast_bytes", - }, - { - .dpdk_name = "tx_port_unicast_packets", - .ctr_name = "tx_vport_unicast_packets", - }, - { - .dpdk_name = "tx_port_multicast_packets", - .ctr_name = "tx_vport_multicast_packets", - }, - { - .dpdk_name = "tx_port_broadcast_packets", - .ctr_name = "tx_vport_broadcast_packets", - }, - { - .dpdk_name = "rx_wqe_err", - .ctr_name = "rx_wqe_err", - }, - { - .dpdk_name = "rx_crc_errors_phy", - .ctr_name = "rx_crc_errors_phy", - }, - { - .dpdk_name = "rx_in_range_len_errors_phy", - .ctr_name = "rx_in_range_len_errors_phy", - }, - { - .dpdk_name = "rx_symbol_err_phy", - .ctr_name = "rx_symbol_err_phy", - }, - { - .dpdk_name = "tx_errors_phy", - .ctr_name = "tx_errors_phy", - }, - { - .dpdk_name = "rx_out_of_buffer", - .ctr_name = "out_of_buffer", - .dev = 1, - }, - { - .dpdk_name = "tx_packets_phy", - .ctr_name = "tx_packets_phy", - }, - { - .dpdk_name = "rx_packets_phy", - .ctr_name = "rx_packets_phy", - }, - { - .dpdk_name = "tx_discards_phy", - .ctr_name = "tx_discards_phy", - }, - { - .dpdk_name = "rx_discards_phy", - .ctr_name = "rx_discards_phy", - }, - { - .dpdk_name = "tx_bytes_phy", - .ctr_name = "tx_bytes_phy", - }, - { - .dpdk_name = "rx_bytes_phy", - .ctr_name = "rx_bytes_phy", - }, - /* Representor only */ - { - .dpdk_name = "rx_packets", - .ctr_name = "vport_rx_packets", - }, - { - .dpdk_name = "rx_bytes", - .ctr_name = "vport_rx_bytes", - }, - { - .dpdk_name = "tx_packets", - .ctr_name = "vport_tx_packets", - }, - { - .dpdk_name = "tx_bytes", - .ctr_name = "vport_tx_bytes", - }, -}; - -static const unsigned int xstats_n = RTE_DIM(mlx5_counters_init); +/** + * Modify a VF MAC address + * + * @param priv + * Pointer to device private data. + * @param mac_addr + * MAC address to modify into. + * @param iface_idx + * Net device interface index + * @param vf_index + * VF index + * + * @return + * 0 on success, a negative errno value otherwise + */ +int +mlx5_os_vf_mac_addr_modify(struct mlx5_priv *priv, + unsigned int iface_idx, + struct rte_ether_addr *mac_addr, + int vf_index) +{ + return mlx5_nl_vf_mac_addr_modify + (priv->nl_socket_route, iface_idx, mac_addr, vf_index); +} /** - * Init the structures to read device counters. + * Set device promiscuous mode * * @param dev - * Pointer to Ethernet device. + * Pointer to Ethernet device structure. + * @param enable + * 0 - promiscuous is disabled, otherwise - enabled + * + * @return + * 0 on success, a negative error value otherwise */ -void -mlx5_os_stats_init(struct rte_eth_dev *dev) +int +mlx5_os_set_promisc(struct rte_eth_dev *dev, int enable) { struct mlx5_priv *priv = dev->data->dev_private; - struct mlx5_xstats_ctrl *xstats_ctrl = &priv->xstats_ctrl; - struct mlx5_stats_ctrl *stats_ctrl = &priv->stats_ctrl; - unsigned int i; - unsigned int j; - struct ifreq ifr; - struct ethtool_gstrings *strings = NULL; - unsigned int dev_stats_n; - unsigned int str_sz; - int ret; - /* So that it won't aggregate for each init. */ - xstats_ctrl->mlx5_stats_n = 0; - ret = mlx5_os_get_stats_n(dev); - if (ret < 0) { - DRV_LOG(WARNING, "port %u no extended statistics available", - dev->data->port_id); - return; - } - dev_stats_n = ret; - /* Allocate memory to grab stat names and values. */ - str_sz = dev_stats_n * ETH_GSTRING_LEN; - strings = (struct ethtool_gstrings *) - mlx5_malloc(0, str_sz + sizeof(struct ethtool_gstrings), 0, - SOCKET_ID_ANY); - if (!strings) { - DRV_LOG(WARNING, "port %u unable to allocate memory for xstats", - dev->data->port_id); - return; - } - strings->cmd = ETHTOOL_GSTRINGS; - strings->string_set = ETH_SS_STATS; - strings->len = dev_stats_n; - ifr.ifr_data = (caddr_t)strings; - ret = mlx5_ifreq(dev, SIOCETHTOOL, &ifr); - if (ret) { - DRV_LOG(WARNING, "port %u unable to get statistic names", - dev->data->port_id); - goto free; - } - for (i = 0; i != dev_stats_n; ++i) { - const char *curr_string = (const char *) - &strings->data[i * ETH_GSTRING_LEN]; - - for (j = 0; j != xstats_n; ++j) { - if (!strcmp(mlx5_counters_init[j].ctr_name, - curr_string)) { - unsigned int idx = xstats_ctrl->mlx5_stats_n++; + return mlx5_nl_promisc(priv->nl_socket_route, + mlx5_ifindex(dev), !!enable); +} - xstats_ctrl->dev_table_idx[idx] = i; - xstats_ctrl->info[idx] = mlx5_counters_init[j]; - break; - } - } - } - /* Add dev counters. */ - for (i = 0; i != xstats_n; ++i) { - if (mlx5_counters_init[i].dev) { - unsigned int idx = xstats_ctrl->mlx5_stats_n++; +/** + * Set device promiscuous mode + * + * @param dev + * Pointer to Ethernet device structure. + * @param enable + * 0 - all multicase is disabled, otherwise - enabled + * + * @return + * 0 on success, a negative error value otherwise + */ +int +mlx5_os_set_allmulti(struct rte_eth_dev *dev, int enable) +{ + struct mlx5_priv *priv = dev->data->dev_private; - xstats_ctrl->info[idx] = mlx5_counters_init[i]; - xstats_ctrl->hw_stats[idx] = 0; - } - } - MLX5_ASSERT(xstats_ctrl->mlx5_stats_n <= MLX5_MAX_XSTATS); - xstats_ctrl->stats_n = dev_stats_n; - /* Copy to base at first time. */ - ret = mlx5_os_read_dev_counters(dev, xstats_ctrl->base); - if (ret) - DRV_LOG(ERR, "port %u cannot read device counters: %s", - dev->data->port_id, strerror(rte_errno)); - mlx5_os_read_dev_stat(priv, "out_of_buffer", &stats_ctrl->imissed_base); - stats_ctrl->imissed = 0; -free: - mlx5_free(strings); + return mlx5_nl_allmulti(priv->nl_socket_route, + mlx5_ifindex(dev), !!enable); } /** - * Set the reg_mr and dereg_mr call backs + * Flush device MAC addresses * - * @param reg_mr_cb[out] - * Pointer to reg_mr func - * @param dereg_mr_cb[out] - * Pointer to dereg_mr func + * @param dev + * Pointer to Ethernet device structure. * */ void -mlx5_os_set_reg_mr_cb(mlx5_reg_mr_t *reg_mr_cb, - mlx5_dereg_mr_t *dereg_mr_cb) +mlx5_os_mac_addr_flush(struct rte_eth_dev *dev) { - *reg_mr_cb = mlx5_verbs_ops.reg_mr; - *dereg_mr_cb = mlx5_verbs_ops.dereg_mr; -} + struct mlx5_priv *priv = dev->data->dev_private; -const struct eth_dev_ops mlx5_os_dev_ops = { - .dev_configure = mlx5_dev_configure, - .dev_start = mlx5_dev_start, - .dev_stop = mlx5_dev_stop, - .dev_set_link_down = mlx5_set_link_down, - .dev_set_link_up = mlx5_set_link_up, - .dev_close = mlx5_dev_close, - .promiscuous_enable = mlx5_promiscuous_enable, - .promiscuous_disable = mlx5_promiscuous_disable, - .allmulticast_enable = mlx5_allmulticast_enable, - .allmulticast_disable = mlx5_allmulticast_disable, - .link_update = mlx5_link_update, - .stats_get = mlx5_stats_get, - .stats_reset = mlx5_stats_reset, - .xstats_get = mlx5_xstats_get, - .xstats_reset = mlx5_xstats_reset, - .xstats_get_names = mlx5_xstats_get_names, - .fw_version_get = mlx5_fw_version_get, - .dev_infos_get = mlx5_dev_infos_get, - .read_clock = mlx5_txpp_read_clock, - .dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get, - .vlan_filter_set = mlx5_vlan_filter_set, - .rx_queue_setup = mlx5_rx_queue_setup, - .rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup, - .tx_queue_setup = mlx5_tx_queue_setup, - .tx_hairpin_queue_setup = mlx5_tx_hairpin_queue_setup, - .rx_queue_release = mlx5_rx_queue_release, - .tx_queue_release = mlx5_tx_queue_release, - .flow_ctrl_get = mlx5_dev_get_flow_ctrl, - .flow_ctrl_set = mlx5_dev_set_flow_ctrl, - .mac_addr_remove = mlx5_mac_addr_remove, - .mac_addr_add = mlx5_mac_addr_add, - .mac_addr_set = mlx5_mac_addr_set, - .set_mc_addr_list = mlx5_set_mc_addr_list, - .mtu_set = mlx5_dev_set_mtu, - .vlan_strip_queue_set = mlx5_vlan_strip_queue_set, - .vlan_offload_set = mlx5_vlan_offload_set, - .reta_update = mlx5_dev_rss_reta_update, - .reta_query = mlx5_dev_rss_reta_query, - .rss_hash_update = mlx5_rss_hash_update, - .rss_hash_conf_get = mlx5_rss_hash_conf_get, - .filter_ctrl = mlx5_dev_filter_ctrl, - .rx_descriptor_status = mlx5_rx_descriptor_status, - .tx_descriptor_status = mlx5_tx_descriptor_status, - .rxq_info_get = mlx5_rxq_info_get, - .txq_info_get = mlx5_txq_info_get, - .rx_burst_mode_get = mlx5_rx_burst_mode_get, - .tx_burst_mode_get = mlx5_tx_burst_mode_get, - .rx_queue_count = mlx5_rx_queue_count, - .rx_queue_intr_enable = mlx5_rx_intr_enable, - .rx_queue_intr_disable = mlx5_rx_intr_disable, - .is_removed = mlx5_is_removed, - .udp_tunnel_port_add = mlx5_udp_tunnel_port_add, - .get_module_info = mlx5_get_module_info, - .get_module_eeprom = mlx5_get_module_eeprom, - .hairpin_cap_get = mlx5_hairpin_cap_get, - .mtr_ops_get = mlx5_flow_meter_ops_get, -}; - -/* Available operations from secondary process. */ -const struct eth_dev_ops mlx5_os_dev_sec_ops = { - .stats_get = mlx5_stats_get, - .stats_reset = mlx5_stats_reset, - .xstats_get = mlx5_xstats_get, - .xstats_reset = mlx5_xstats_reset, - .xstats_get_names = mlx5_xstats_get_names, - .fw_version_get = mlx5_fw_version_get, - .dev_infos_get = mlx5_dev_infos_get, - .read_clock = mlx5_txpp_read_clock, - .rx_descriptor_status = mlx5_rx_descriptor_status, - .tx_descriptor_status = mlx5_tx_descriptor_status, - .rxq_info_get = mlx5_rxq_info_get, - .txq_info_get = mlx5_txq_info_get, - .rx_burst_mode_get = mlx5_rx_burst_mode_get, - .tx_burst_mode_get = mlx5_tx_burst_mode_get, - .get_module_info = mlx5_get_module_info, - .get_module_eeprom = mlx5_get_module_eeprom, -}; - -/* Available operations in flow isolated mode. */ -const struct eth_dev_ops mlx5_os_dev_ops_isolate = { - .dev_configure = mlx5_dev_configure, - .dev_start = mlx5_dev_start, - .dev_stop = mlx5_dev_stop, - .dev_set_link_down = mlx5_set_link_down, - .dev_set_link_up = mlx5_set_link_up, - .dev_close = mlx5_dev_close, - .promiscuous_enable = mlx5_promiscuous_enable, - .promiscuous_disable = mlx5_promiscuous_disable, - .allmulticast_enable = mlx5_allmulticast_enable, - .allmulticast_disable = mlx5_allmulticast_disable, - .link_update = mlx5_link_update, - .stats_get = mlx5_stats_get, - .stats_reset = mlx5_stats_reset, - .xstats_get = mlx5_xstats_get, - .xstats_reset = mlx5_xstats_reset, - .xstats_get_names = mlx5_xstats_get_names, - .fw_version_get = mlx5_fw_version_get, - .dev_infos_get = mlx5_dev_infos_get, - .read_clock = mlx5_txpp_read_clock, - .dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get, - .vlan_filter_set = mlx5_vlan_filter_set, - .rx_queue_setup = mlx5_rx_queue_setup, - .rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup, - .tx_queue_setup = mlx5_tx_queue_setup, - .tx_hairpin_queue_setup = mlx5_tx_hairpin_queue_setup, - .rx_queue_release = mlx5_rx_queue_release, - .tx_queue_release = mlx5_tx_queue_release, - .flow_ctrl_get = mlx5_dev_get_flow_ctrl, - .flow_ctrl_set = mlx5_dev_set_flow_ctrl, - .mac_addr_remove = mlx5_mac_addr_remove, - .mac_addr_add = mlx5_mac_addr_add, - .mac_addr_set = mlx5_mac_addr_set, - .set_mc_addr_list = mlx5_set_mc_addr_list, - .mtu_set = mlx5_dev_set_mtu, - .vlan_strip_queue_set = mlx5_vlan_strip_queue_set, - .vlan_offload_set = mlx5_vlan_offload_set, - .filter_ctrl = mlx5_dev_filter_ctrl, - .rx_descriptor_status = mlx5_rx_descriptor_status, - .tx_descriptor_status = mlx5_tx_descriptor_status, - .rxq_info_get = mlx5_rxq_info_get, - .txq_info_get = mlx5_txq_info_get, - .rx_burst_mode_get = mlx5_rx_burst_mode_get, - .tx_burst_mode_get = mlx5_tx_burst_mode_get, - .rx_queue_intr_enable = mlx5_rx_intr_enable, - .rx_queue_intr_disable = mlx5_rx_intr_disable, - .is_removed = mlx5_is_removed, - .get_module_info = mlx5_get_module_info, - .get_module_eeprom = mlx5_get_module_eeprom, - .hairpin_cap_get = mlx5_hairpin_cap_get, - .mtr_ops_get = mlx5_flow_meter_ops_get, -}; + mlx5_nl_mac_addr_flush(priv->nl_socket_route, mlx5_ifindex(dev), + dev->data->mac_addrs, + MLX5_MAX_MAC_ADDRESSES, priv->mac_own); +}