X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Flinux%2Fmlx5_os.c;h=d1bf89922ed480c17d43b034f14b407bbc28ad18;hb=c4c3e8afefa8b7e7bc19073f9a159d50c75c8770;hp=eeeca27ac2a049efeff235b35fdc5a1172d27669;hpb=45633c460c223a67dd1a7cc084c3eceb5e17687c;p=dpdk.git diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c index eeeca27ac2..d1bf89922e 100644 --- a/drivers/net/mlx5/linux/mlx5_os.c +++ b/drivers/net/mlx5/linux/mlx5_os.c @@ -44,7 +44,6 @@ #include "mlx5_rx.h" #include "mlx5_tx.h" #include "mlx5_autoconf.h" -#include "mlx5_mr.h" #include "mlx5_flow.h" #include "rte_pmd_mlx5.h" #include "mlx5_verbs.h" @@ -113,7 +112,7 @@ static struct mlx5_indexed_pool_config icfg[] = { * Pointer to RQ channel object, which includes the channel fd * * @param[out] fd - * The file descriptor (representing the intetrrupt) used in this channel. + * The file descriptor (representing the interrupt) used in this channel. * * @return * 0 on successfully setting the fd to non-blocking, non-zero otherwise. @@ -132,25 +131,29 @@ mlx5_os_set_nonblock_channel_fd(int fd) * with out parameter of type 'struct ibv_device_attr_ex *'. Then fill in mlx5 * device attributes from the glue out parameter. * - * @param dev - * Pointer to ibv context. + * @param cdev + * Pointer to mlx5 device. * * @param device_attr * Pointer to mlx5 device attributes. * * @return - * 0 on success, non zero error number otherwise + * 0 on success, a negative errno value otherwise and rte_errno is set. */ int -mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) +mlx5_os_get_dev_attr(struct mlx5_common_device *cdev, + struct mlx5_dev_attr *device_attr) { int err; + struct ibv_context *ctx = cdev->ctx; struct ibv_device_attr_ex attr_ex; + memset(device_attr, 0, sizeof(*device_attr)); err = mlx5_glue->query_device_ex(ctx, NULL, &attr_ex); - if (err) - return err; - + if (err) { + rte_errno = errno; + return -rte_errno; + } device_attr->device_cap_flags_ex = attr_ex.device_cap_flags_ex; device_attr->max_qp_wr = attr_ex.orig_attr.max_qp_wr; device_attr->max_sge = attr_ex.orig_attr.max_sge; @@ -168,9 +171,20 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) device_attr->tso_supported_qpts = attr_ex.tso_caps.supported_qpts; struct mlx5dv_context dv_attr = { .comp_mask = 0 }; +#ifdef HAVE_IBV_MLX5_MOD_SWP + dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP; +#endif +#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT + dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS; +#endif +#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT + dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_STRIDING_RQ; +#endif err = mlx5_glue->dv_query_device(ctx, &dv_attr); - if (err) - return err; + if (err) { + rte_errno = errno; + return -rte_errno; + } device_attr->flags = dv_attr.flags; device_attr->comp_mask = dv_attr.comp_mask; @@ -178,6 +192,7 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) device_attr->sw_parsing_offloads = dv_attr.sw_parsing_caps.sw_parsing_offloads; #endif +#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT device_attr->min_single_stride_log_num_of_bytes = dv_attr.striding_rq_caps.min_single_stride_log_num_of_bytes; device_attr->max_single_stride_log_num_of_bytes = @@ -188,46 +203,14 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) dv_attr.striding_rq_caps.max_single_wqe_log_num_of_strides; device_attr->stride_supported_qpts = dv_attr.striding_rq_caps.supported_qpts; +#endif #ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT device_attr->tunnel_offloads_caps = dv_attr.tunnel_offloads_caps; #endif strlcpy(device_attr->fw_ver, attr_ex.orig_attr.fw_ver, sizeof(device_attr->fw_ver)); - return err; -} - -/** - * 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 rte_mem_page_size()). - * - * @param[in] size - * The size in bytes of the memory to allocate. - * @param[in] data - * A pointer to the callback data. - * - * @return - * Allocated buffer, NULL otherwise and rte_errno is set. - */ -static void * -mlx5_alloc_verbs_buf(size_t size, void *data) -{ - struct mlx5_dev_ctx_shared *sh = data; - void *ret; - 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, sh->numa_node); - if (!ret && size) - rte_errno = ENOMEM; - return ret; + return 0; } /** @@ -290,7 +273,7 @@ __mlx5_discovery_misc5_cap(struct mlx5_priv *priv) metadata_reg_c_0, 0xffff); } #endif - matcher = mlx5_glue->dv_create_flow_matcher(priv->sh->ctx, + matcher = mlx5_glue->dv_create_flow_matcher(priv->sh->cdev->ctx, &dv_attr, tbl); if (matcher) { priv->sh->misc5_cap = 1; @@ -303,21 +286,6 @@ __mlx5_discovery_misc5_cap(struct mlx5_priv *priv) } #endif -/** - * Verbs callback to free a memory. - * - * @param[in] ptr - * A pointer to the memory to free. - * @param[in] data - * A pointer to the callback data. - */ -static void -mlx5_free_verbs_buf(void *ptr, void *data __rte_unused) -{ - MLX5_ASSERT(data != NULL); - mlx5_free(ptr); -} - /** * Initialize DR related data within private structure. * Routine checks the reference counter and does actual @@ -384,12 +352,22 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) flow_dv_dest_array_clone_free_cb); if (!sh->dest_array_list) goto error; + /* Init shared flex parsers list, no need lcore_share */ + snprintf(s, sizeof(s), "%s_flex_parsers_list", sh->ibdev_name); + sh->flex_parsers_dv = mlx5_list_create(s, sh, false, + mlx5_flex_parser_create_cb, + mlx5_flex_parser_match_cb, + mlx5_flex_parser_remove_cb, + mlx5_flex_parser_clone_cb, + mlx5_flex_parser_clone_free_cb); + if (!sh->flex_parsers_dv) + goto error; #endif #ifdef HAVE_MLX5DV_DR void *domain; /* Reference counter is zero, we should initialize structures. */ - domain = mlx5_glue->dr_create_domain(sh->ctx, + domain = mlx5_glue->dr_create_domain(sh->cdev->ctx, MLX5DV_DR_DOMAIN_TYPE_NIC_RX); if (!domain) { DRV_LOG(ERR, "ingress mlx5dv_dr_create_domain failed"); @@ -397,7 +375,7 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) goto error; } sh->rx_domain = domain; - domain = mlx5_glue->dr_create_domain(sh->ctx, + domain = mlx5_glue->dr_create_domain(sh->cdev->ctx, MLX5DV_DR_DOMAIN_TYPE_NIC_TX); if (!domain) { DRV_LOG(ERR, "egress mlx5dv_dr_create_domain failed"); @@ -407,8 +385,8 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) sh->tx_domain = domain; #ifdef HAVE_MLX5DV_DR_ESWITCH if (priv->config.dv_esw_en) { - domain = mlx5_glue->dr_create_domain - (sh->ctx, MLX5DV_DR_DOMAIN_TYPE_FDB); + domain = mlx5_glue->dr_create_domain(sh->cdev->ctx, + MLX5DV_DR_DOMAIN_TYPE_FDB); if (!domain) { DRV_LOG(ERR, "FDB mlx5dv_dr_create_domain failed"); err = errno; @@ -457,6 +435,7 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) mlx5_glue->dr_create_flow_action_default_miss(); if (!sh->default_miss_action) DRV_LOG(WARNING, "Default miss action is not supported."); + LIST_INIT(&sh->shared_rxqs); return 0; error: /* Rollback the created objects. */ @@ -531,6 +510,7 @@ mlx5_os_free_shared_dr(struct mlx5_priv *priv) MLX5_ASSERT(sh && sh->refcnt); if (sh->refcnt > 1) return; + MLX5_ASSERT(LIST_EMPTY(&sh->shared_rxqs)); #ifdef HAVE_MLX5DV_DR if (sh->rx_domain) { mlx5_glue->dr_destroy_domain(sh->rx_domain); @@ -669,10 +649,6 @@ mlx5_init_once(void) 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) @@ -697,56 +673,6 @@ out: 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. * @@ -760,23 +686,24 @@ 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; + struct mlx5_hca_attr *hca_attr = &sh->cdev->config.hca_attr; 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) || + if (!sh->cdev->config.devx || !priv->config.dv_flow_en || + !hca_attr->flow_counters_dump || + !(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); + hca_attr->flow_counters_dump, + 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; @@ -805,10 +732,15 @@ mlx5_flow_drop_action_config(struct rte_eth_dev *dev __rte_unused) * DR supports drop action placeholder when it is supported; * otherwise, use the queue drop action. */ - if (mlx5_flow_discover_dr_action_support(dev)) - priv->root_drop_action = priv->drop_queue.hrxq->action; - else + if (!priv->sh->drop_action_check_flag) { + if (!mlx5_flow_discover_dr_action_support(dev)) + priv->sh->dr_drop_action_en = 1; + priv->sh->drop_action_check_flag = 1; + } + if (priv->sh->dr_drop_action_en) priv->root_drop_action = priv->sh->dr_drop_action; + else + priv->root_drop_action = priv->drop_queue.hrxq->action; #endif } @@ -816,7 +748,7 @@ 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; + void *ctx = priv->sh->cdev->ctx; priv->q_counters = mlx5_devx_cmd_queue_counter_alloc(ctx); if (!priv->q_counters) { @@ -833,7 +765,7 @@ mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev) .wq_type = IBV_WQT_RQ, .max_wr = 1, .max_sge = 1, - .pd = priv->sh->pd, + .pd = priv->sh->cdev->pd, .cq = cq, }); if (wq) { @@ -928,7 +860,6 @@ mlx5_representor_match(struct mlx5_dev_spawn_data *spawn, return false; } - /** * Spawn an Ethernet device from Verbs information. * @@ -938,7 +869,7 @@ mlx5_representor_match(struct mlx5_dev_spawn_data *spawn, * Verbs device parameters (name, port, switch_info) to spawn. * @param config * Device configuration parameters. - * @param config + * @param eth_da * Device arguments. * * @return @@ -956,26 +887,22 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, { const struct mlx5_switch_info *switch_info = &spawn->info; struct mlx5_dev_ctx_shared *sh = NULL; - struct ibv_port_attr port_attr; - struct mlx5dv_context dv_attr = { .comp_mask = 0 }; + struct mlx5_hca_attr *hca_attr = &spawn->cdev->config.hca_attr; + struct ibv_port_attr port_attr = { .state = IBV_PORT_NOP }; struct rte_eth_dev *eth_dev = NULL; struct mlx5_priv *priv = NULL; int err = 0; unsigned int hw_padding = 0; unsigned int mps; - unsigned int tunnel_en = 0; unsigned int mpls_en = 0; unsigned int swp = 0; unsigned int mprq = 0; - unsigned int mprq_min_stride_size_n = 0; - unsigned int mprq_max_stride_size_n = 0; - unsigned int mprq_min_stride_num_n = 0; - unsigned int mprq_max_stride_num_n = 0; struct rte_ether_addr mac; char name[RTE_ETH_NAME_MAX_LEN]; int own_domain_id = 0; uint16_t port_id; struct mlx5_port_info vport_info = { .query_flags = 0 }; + int nl_rdma = -1; int i; /* Determine if this port representor is supposed to be spawned. */ @@ -997,12 +924,10 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, /* Bonding device. */ if (!switch_info->representor) { err = snprintf(name, sizeof(name), "%s_%s", - dpdk_dev->name, - mlx5_os_get_dev_device_name(spawn->phys_dev)); + dpdk_dev->name, spawn->phys_dev_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), + dpdk_dev->name, spawn->phys_dev_name, switch_info->ctrl_num, switch_info->pf_num, switch_info->name_type == @@ -1034,8 +959,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, err = mlx5_proc_priv_init(eth_dev); if (err) return NULL; - mp_id.port_id = eth_dev->data->port_id; - strlcpy(mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN); + mlx5_mp_id_init(&mp_id, eth_dev->data->port_id); /* Receive command fd from primary process */ err = mlx5_mp_req_verbs_cmd_fd(&mp_id); if (err < 0) @@ -1056,47 +980,54 @@ err_secondary: mlx5_dev_close(eth_dev); return NULL; } - /* - * Some parameters ("tx_db_nc" in particularly) are needed in - * advance to create dv/verbs device context. We proceed the - * devargs here to get ones, and later proceed devargs again - * to override some hardware settings. - */ + /* Process parameters. */ 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; + return NULL; } + sh = mlx5_alloc_shared_dev_ctx(spawn, config); + if (!sh) + return NULL; + /* Update final values for devargs before check sibling 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; +#if !defined(HAVE_IBV_FLOW_DV_SUPPORT) || !defined(HAVE_MLX5DV_DR) + if (config->dv_flow_en) { + DRV_LOG(WARNING, "DV flow is not supported."); + config->dv_flow_en = 0; + } +#endif +#ifdef HAVE_MLX5DV_DR_ESWITCH + if (!(hca_attr->eswitch_manager && config->dv_flow_en && + (switch_info->representor || switch_info->master))) + config->dv_esw_en = 0; +#else + config->dv_esw_en = 0; +#endif + if (!config->dv_esw_en && + config->dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) { + DRV_LOG(WARNING, + "Metadata mode %u is not supported (no E-Switch).", + config->dv_xmeta_en); + config->dv_xmeta_en = MLX5_XMETA_MODE_LEGACY; + } + /* Check sibling device configurations. */ + err = mlx5_dev_check_sibling_config(sh, config, dpdk_dev); + if (err) + goto error; #ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR config->dest_tir = 1; -#endif -#ifdef HAVE_IBV_MLX5_MOD_SWP - dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP; #endif /* * Multi-packet send is supported by ConnectX-4 Lx PF as well * as all ConnectX-5 devices. */ -#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT - dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS; -#endif -#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT - dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_STRIDING_RQ; -#endif - mlx5_glue->dv_query_device(sh->ctx, &dv_attr); - if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) { - if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) { + if (sh->device_attr.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) { + if (sh->device_attr.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) { DRV_LOG(DEBUG, "enhanced MPW is supported"); mps = MLX5_MPW_ENHANCED; } else { @@ -1108,60 +1039,65 @@ err_secondary: mps = MLX5_MPW_DISABLED; } #ifdef HAVE_IBV_MLX5_MOD_SWP - if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_SWP) - swp = dv_attr.sw_parsing_caps.sw_parsing_offloads; + if (sh->device_attr.comp_mask & MLX5DV_CONTEXT_MASK_SWP) + swp = sh->device_attr.sw_parsing_offloads; DRV_LOG(DEBUG, "SWP support: %u", swp); #endif - config->swp = !!swp; + config->swp = swp & (MLX5_SW_PARSING_CAP | MLX5_SW_PARSING_CSUM_CAP | + MLX5_SW_PARSING_TSO_CAP); #ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT - if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) { - struct mlx5dv_striding_rq_caps mprq_caps = - dv_attr.striding_rq_caps; - + if (sh->device_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) { DRV_LOG(DEBUG, "\tmin_single_stride_log_num_of_bytes: %d", - mprq_caps.min_single_stride_log_num_of_bytes); + sh->device_attr.min_single_stride_log_num_of_bytes); DRV_LOG(DEBUG, "\tmax_single_stride_log_num_of_bytes: %d", - mprq_caps.max_single_stride_log_num_of_bytes); + sh->device_attr.max_single_stride_log_num_of_bytes); DRV_LOG(DEBUG, "\tmin_single_wqe_log_num_of_strides: %d", - mprq_caps.min_single_wqe_log_num_of_strides); + sh->device_attr.min_single_wqe_log_num_of_strides); DRV_LOG(DEBUG, "\tmax_single_wqe_log_num_of_strides: %d", - mprq_caps.max_single_wqe_log_num_of_strides); + sh->device_attr.max_single_wqe_log_num_of_strides); DRV_LOG(DEBUG, "\tsupported_qpts: %d", - mprq_caps.supported_qpts); + sh->device_attr.stride_supported_qpts); + DRV_LOG(DEBUG, "\tmin_stride_wqe_log_size: %d", + config->mprq.log_min_stride_wqe_size); DRV_LOG(DEBUG, "device supports Multi-Packet RQ"); mprq = 1; - mprq_min_stride_size_n = - mprq_caps.min_single_stride_log_num_of_bytes; - mprq_max_stride_size_n = - mprq_caps.max_single_stride_log_num_of_bytes; - mprq_min_stride_num_n = - mprq_caps.min_single_wqe_log_num_of_strides; - mprq_max_stride_num_n = - mprq_caps.max_single_wqe_log_num_of_strides; + config->mprq.log_min_stride_size = + sh->device_attr.min_single_stride_log_num_of_bytes; + config->mprq.log_max_stride_size = + sh->device_attr.max_single_stride_log_num_of_bytes; + config->mprq.log_min_stride_num = + sh->device_attr.min_single_wqe_log_num_of_strides; + config->mprq.log_max_stride_num = + sh->device_attr.max_single_wqe_log_num_of_strides; } #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 & - MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN) && - (dv_attr.tunnel_offloads_caps & - MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE) && - (dv_attr.tunnel_offloads_caps & - MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GENEVE)); - } - DRV_LOG(DEBUG, "tunnel offloading is %ssupported", - tunnel_en ? "" : "not "); + if (sh->device_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) { + config->tunnel_en = sh->device_attr.tunnel_offloads_caps & + (MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN | + MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE | + MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GENEVE); + } + if (config->tunnel_en) { + DRV_LOG(DEBUG, "tunnel offloading is supported for %s%s%s", + config->tunnel_en & + MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN ? "[VXLAN]" : "", + config->tunnel_en & + MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE ? "[GRE]" : "", + config->tunnel_en & + MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GENEVE ? "[GENEVE]" : "" + ); + } else { + DRV_LOG(DEBUG, "tunnel offloading is not supported"); + } #else DRV_LOG(WARNING, "tunnel offloading disabled due to old OFED/rdma-core version"); #endif - config->tunnel_en = tunnel_en; #ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT - mpls_en = ((dv_attr.tunnel_offloads_caps & + mpls_en = ((sh->device_attr.tunnel_offloads_caps & MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_GRE) && - (dv_attr.tunnel_offloads_caps & + (sh->device_attr.tunnel_offloads_caps & MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_UDP)); DRV_LOG(DEBUG, "MPLS over GRE/UDP tunnel offloading is %ssupported", mpls_en ? "" : "not "); @@ -1170,19 +1106,36 @@ err_secondary: " old OFED/rdma-core version or firmware configuration"); #endif config->mpls_en = mpls_en; + nl_rdma = mlx5_nl_init(NETLINK_RDMA); /* Check port status. */ - err = mlx5_glue->query_port(sh->ctx, spawn->phys_port, &port_attr); - if (err) { - DRV_LOG(ERR, "port query failed: %s", strerror(err)); - goto error; - } - if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) { - DRV_LOG(ERR, "port is not configured in Ethernet mode"); - err = EINVAL; - goto error; + if (spawn->phys_port <= UINT8_MAX) { + /* Legacy Verbs api only support u8 port number. */ + err = mlx5_glue->query_port(sh->cdev->ctx, spawn->phys_port, + &port_attr); + if (err) { + DRV_LOG(ERR, "port query failed: %s", strerror(err)); + goto error; + } + if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) { + DRV_LOG(ERR, "port is not configured in Ethernet mode"); + err = EINVAL; + goto error; + } + } else if (nl_rdma >= 0) { + /* IB doesn't allow more than 255 ports, must be Ethernet. */ + err = mlx5_nl_port_state(nl_rdma, + spawn->phys_dev_name, + spawn->phys_port); + if (err < 0) { + DRV_LOG(INFO, "Failed to get netlink port state: %s", + strerror(rte_errno)); + err = -rte_errno; + goto error; + } + port_attr.state = (enum ibv_port_state)err; } if (port_attr.state != IBV_PORT_ACTIVE) - DRV_LOG(DEBUG, "port is not active: \"%s\" (%d)", + DRV_LOG(INFO, "port is not active: \"%s\" (%d)", mlx5_glue->port_state_str(port_attr.state), port_attr.state); /* Allocate private eth device data. */ @@ -1199,7 +1152,7 @@ err_secondary: priv->pci_dev = spawn->pci_dev; priv->mtu = RTE_ETHER_MTU; /* Some internal functions rely on Netlink sockets, open them now. */ - priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA); + priv->nl_socket_rdma = nl_rdma; priv->nl_socket_route = mlx5_nl_init(NETLINK_ROUTE); priv->representor = !!switch_info->representor; priv->master = !!switch_info->master; @@ -1221,14 +1174,13 @@ err_secondary: * register is defined by mask. */ if (switch_info->representor || switch_info->master) { - err = mlx5_glue->devx_port_query(sh->ctx, + err = mlx5_glue->devx_port_query(sh->cdev->ctx, spawn->phys_port, &vport_info); if (err) { DRV_LOG(WARNING, - "can't query devx port %d on device %s", - spawn->phys_port, - mlx5_os_get_dev_device_name(spawn->phys_dev)); + "Cannot query devx port %d on device %s", + spawn->phys_port, spawn->phys_dev_name); vport_info.query_flags = 0; } } @@ -1236,20 +1188,16 @@ err_secondary: priv->vport_meta_tag = vport_info.vport_meta_tag; priv->vport_meta_mask = vport_info.vport_meta_mask; if (!priv->vport_meta_mask) { - DRV_LOG(ERR, "vport zero mask for port %d" - " on bonding device %s", - spawn->phys_port, - mlx5_os_get_dev_device_name - (spawn->phys_dev)); + DRV_LOG(ERR, + "vport zero mask for port %d on bonding device %s", + spawn->phys_port, spawn->phys_dev_name); err = ENOTSUP; goto error; } if (priv->vport_meta_tag & ~priv->vport_meta_mask) { - DRV_LOG(ERR, "invalid vport tag for port %d" - " on bonding device %s", - spawn->phys_port, - mlx5_os_get_dev_device_name - (spawn->phys_dev)); + DRV_LOG(ERR, + "Invalid vport tag for port %d on bonding device %s", + spawn->phys_port, spawn->phys_dev_name); err = ENOTSUP; goto error; } @@ -1258,10 +1206,9 @@ err_secondary: priv->vport_id = vport_info.vport_id; } else if (spawn->pf_bond >= 0 && (switch_info->representor || switch_info->master)) { - DRV_LOG(ERR, "can't deduce vport index for port %d" - " on bonding device %s", - spawn->phys_port, - mlx5_os_get_dev_device_name(spawn->phys_dev)); + DRV_LOG(ERR, + "Cannot deduce vport index for port %d on bonding device %s", + spawn->phys_port, spawn->phys_dev_name); err = ENOTSUP; goto error; } else { @@ -1312,11 +1259,6 @@ err_secondary: DRV_LOG(DEBUG, "dev_port-%u new domain_id=%u\n", priv->dev_port, priv->domain_id); } - /* Override some values set by hardware configuration. */ - 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 & IBV_DEVICE_RAW_IP_CSUM); DRV_LOG(DEBUG, "checksum offloading is %ssupported", @@ -1325,26 +1267,14 @@ err_secondary: !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) { - DRV_LOG(WARNING, "DV flow is not supported"); - config->dv_flow_en = 0; - } -#endif - if (spawn->max_port > UINT8_MAX) { - /* Verbs can't support ports larger than 255 by design. */ - DRV_LOG(ERR, "can't support IB ports > UINT8_MAX"); - err = EINVAL; - goto error; - } 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)RTE_ETH_RSS_RETA_SIZE_512) + config->ind_table_max_size = RTE_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 & @@ -1383,32 +1313,13 @@ err_secondary: 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; - } - /* 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->steering_format_version = - config->hca_attr.steering_format_version; - sh->qp_ts_format = config->hca_attr.qp_ts_format; + if (sh->cdev->config.devx) { + sh->steering_format_version = hca_attr->steering_format_version; /* Check for LRO support. */ - if (config->dest_tir && config->hca_attr.lro_cap && + if (config->dest_tir && hca_attr->lro_cap && config->dv_flow_en) { /* TBD check tunnel lro caps. */ - config->lro.supported = config->hca_attr.lro_cap; + config->lro.supported = hca_attr->lro_cap; DRV_LOG(DEBUG, "Device supports LRO"); /* * If LRO timeout is not configured by application, @@ -1416,21 +1327,19 @@ err_secondary: */ if (!config->lro.timeout) config->lro.timeout = - config->hca_attr.lro_timer_supported_periods[0]; + hca_attr->lro_timer_supported_periods[0]; DRV_LOG(DEBUG, "LRO session timeout set to %d usec", 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); + hca_attr->lro_min_mss_size); } #if defined(HAVE_MLX5DV_DR) && \ (defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_METER) || \ defined(HAVE_MLX5_DR_CREATE_ACTION_ASO)) - if (config->hca_attr.qos.sup && - config->hca_attr.qos.flow_meter_old && + if (hca_attr->qos.sup && hca_attr->qos.flow_meter_old && config->dv_flow_en) { - uint8_t reg_c_mask = - config->hca_attr.qos.flow_meter_reg_c_ids; + uint8_t reg_c_mask = 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. @@ -1454,20 +1363,18 @@ err_secondary: 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; + priv->mtr_reg_share = hca_attr->qos.flow_meter; DRV_LOG(DEBUG, "The REG_C meter uses is %d", priv->mtr_color_reg); } } - if (config->hca_attr.qos.sup && - config->hca_attr.qos.flow_meter_aso_sup) { + if (hca_attr->qos.sup && hca_attr->qos.flow_meter_aso_sup) { uint32_t log_obj_size = rte_log2_u32(MLX5_ASO_MTRS_PER_POOL >> 1); if (log_obj_size >= - config->hca_attr.qos.log_meter_aso_granularity && - log_obj_size <= - config->hca_attr.qos.log_meter_aso_max_alloc) + hca_attr->qos.log_meter_aso_granularity && + log_obj_size <= + hca_attr->qos.log_meter_aso_max_alloc) sh->meter_aso_en = 1; } if (priv->mtr_en) { @@ -1477,12 +1384,11 @@ err_secondary: goto error; } } - if (config->hca_attr.flow.tunnel_header_0_1) + if (hca_attr->flow.tunnel_header_0_1) sh->tunnel_header_0_1 = 1; #endif #ifdef HAVE_MLX5_DR_CREATE_ACTION_ASO - if (config->hca_attr.flow_hit_aso && - priv->mtr_color_reg == REG_C_3) { + if (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) { @@ -1494,8 +1400,7 @@ err_secondary: #endif /* HAVE_MLX5_DR_CREATE_ACTION_ASO */ #if defined(HAVE_MLX5_DR_CREATE_ACTION_ASO) && \ defined(HAVE_MLX5_DR_ACTION_ASO_CT) - if (config->hca_attr.ct_offload && - priv->mtr_color_reg == REG_C_3) { + if (hca_attr->ct_offload && priv->mtr_color_reg == REG_C_3) { err = mlx5_flow_aso_ct_mng_init(sh); if (err) { err = -err; @@ -1506,13 +1411,13 @@ err_secondary: } #endif /* HAVE_MLX5_DR_CREATE_ACTION_ASO && HAVE_MLX5_DR_ACTION_ASO_CT */ #if defined(HAVE_MLX5DV_DR) && defined(HAVE_MLX5_DR_CREATE_ACTION_FLOW_SAMPLE) - if (config->hca_attr.log_max_ft_sampler_num > 0 && + if (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) + if (!hca_attr->log_max_ft_sampler_num) DRV_LOG(WARNING, "No available register for sampler."); else @@ -1521,18 +1426,18 @@ err_secondary: #endif } if (config->cqe_comp && RTE_CACHE_LINE_SIZE == 128 && - !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP)) { + !(sh->device_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)) { + (!sh->cdev->config.devx || !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)) { + (!sh->cdev->config.devx || !hca_attr->mini_cqe_resp_l3_l4_tag)) { DRV_LOG(WARNING, "L3/L4 Header CQE compression" " format isn't supported."); config->cqe_comp = 0; @@ -1541,55 +1446,55 @@ err_secondary: config->cqe_comp ? "" : "not "); if (config->tx_pp) { DRV_LOG(DEBUG, "Timestamp counter frequency %u kHz", - config->hca_attr.dev_freq_khz); + hca_attr->dev_freq_khz); DRV_LOG(DEBUG, "Packet pacing is %ssupported", - config->hca_attr.qos.packet_pacing ? "" : "not "); + hca_attr->qos.packet_pacing ? "" : "not "); DRV_LOG(DEBUG, "Cross channel ops are %ssupported", - config->hca_attr.cross_channel ? "" : "not "); + hca_attr->cross_channel ? "" : "not "); DRV_LOG(DEBUG, "WQE index ignore is %ssupported", - config->hca_attr.wqe_index_ignore ? "" : "not "); + hca_attr->wqe_index_ignore ? "" : "not "); DRV_LOG(DEBUG, "Non-wire SQ feature is %ssupported", - config->hca_attr.non_wire_sq ? "" : "not "); + 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); + hca_attr->log_max_static_sq_wq ? "" : "not ", + 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) { + hca_attr->qos.wqe_rate_pp ? "" : "not "); + if (!sh->cdev->config.devx) { DRV_LOG(ERR, "DevX is required for packet pacing"); err = ENODEV; goto error; } - if (!config->hca_attr.qos.packet_pacing) { + if (!hca_attr->qos.packet_pacing) { DRV_LOG(ERR, "Packet pacing is not supported"); err = ENODEV; goto error; } - if (!config->hca_attr.cross_channel) { + if (!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 (!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 (!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 (!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 (!hca_attr->qos.wqe_rate_pp) { DRV_LOG(ERR, "WQE rate mode is required" " for packet pacing"); err = ENODEV; @@ -1602,12 +1507,21 @@ err_secondary: goto error; #endif } - if (config->devx) { + if (config->std_delay_drop || config->hp_delay_drop) { + if (!hca_attr->rq_delay_drop) { + config->std_delay_drop = 0; + config->hp_delay_drop = 0; + DRV_LOG(WARNING, + "dev_port-%u: Rxq delay drop is not supported", + priv->dev_port); + } + } + if (sh->cdev->config.devx) { uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)]; - err = config->hca_attr.access_register_user ? + err = hca_attr->access_register_user ? mlx5_devx_cmd_register_read - (sh->ctx, MLX5_REGISTER_ID_MTUTC, 0, + (sh->cdev->ctx, MLX5_REGISTER_ID_MTUTC, 0, reg, MLX5_ST_SZ_DW(register_mtutc)) : ENOTSUP; if (!err) { uint32_t ts_mode; @@ -1619,50 +1533,20 @@ err_secondary: config->rt_timestamp = 1; } else { /* Kernel does not support register reading. */ - if (config->hca_attr.dev_freq_khz == - (NS_PER_S / MS_PER_S)) + if (hca_attr->dev_freq_khz == (NS_PER_S / MS_PER_S)) config->rt_timestamp = 1; } } /* * If HW has bug working with tunnel packet decapsulation and * scatter FCS, and decapsulation is needed, clear the hw_fcs_strip - * bit. Then DEV_RX_OFFLOAD_KEEP_CRC bit will not be set anymore. + * bit. Then RTE_ETH_RX_OFFLOAD_KEEP_CRC bit will not be set anymore. */ - if (config->hca_attr.scatter_fcs_w_decap_disable && config->decap_en) + if (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 = - RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N, - mprq_min_stride_num_n), - mprq_max_stride_num_n); - DRV_LOG(WARNING, - "the number of strides" - " for Multi-Packet RQ is out of range," - " setting default value (%u)", - 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 = - RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_SIZE_N, - mprq_min_stride_size_n), - mprq_max_stride_size_n); - DRV_LOG(WARNING, - "the size of a stride" - " for Multi-Packet RQ is out of range," - " setting default value (%u)", - 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) { + if (config->mprq.enabled && !mprq) { DRV_LOG(WARNING, "Multi-Packet RQ isn't supported"); config->mprq.enabled = 0; } @@ -1677,6 +1561,19 @@ err_secondary: if (priv->representor) { eth_dev->data->dev_flags |= RTE_ETH_DEV_REPRESENTOR; eth_dev->data->representor_id = priv->representor_id; + MLX5_ETH_FOREACH_DEV(port_id, dpdk_dev) { + struct mlx5_priv *opriv = + rte_eth_devices[port_id].data->dev_private; + if (opriv && + opriv->master && + opriv->domain_id == priv->domain_id && + opriv->sh == priv->sh) { + eth_dev->data->backer_port_id = port_id; + break; + } + } + if (port_id >= RTE_MAX_ETHPORTS) + eth_dev->data->backer_port_id = eth_dev->data->port_id; } priv->mp_id.port_id = eth_dev->data->port_id; strlcpy(priv->mp_id.name, MLX5_MP_NAME, RTE_MP_MAX_NAME_LEN); @@ -1687,6 +1584,7 @@ err_secondary: */ MLX5_ASSERT(spawn->ifindex); priv->if_index = spawn->ifindex; + priv->lag_affinity_idx = sh->refcnt - 1; eth_dev->data->dev_private = priv; priv->dev_data = eth_dev->data; eth_dev->data->mac_addrs = priv->mac; @@ -1702,11 +1600,8 @@ err_secondary: goto error; } DRV_LOG(INFO, - "port %u MAC address is %02x:%02x:%02x:%02x:%02x:%02x", - eth_dev->data->port_id, - mac.addr_bytes[0], mac.addr_bytes[1], - mac.addr_bytes[2], mac.addr_bytes[3], - mac.addr_bytes[4], mac.addr_bytes[5]); + "port %u MAC address is " RTE_ETHER_ADDR_PRT_FMT, + eth_dev->data->port_id, RTE_ETHER_ADDR_BYTES(&mac)); #ifdef RTE_LIBRTE_MLX5_DEBUG { char ifname[MLX5_NAMESIZE]; @@ -1728,8 +1623,8 @@ err_secondary: DRV_LOG(DEBUG, "port %u MTU is %u", eth_dev->data->port_id, priv->mtu); /* 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->rx_pkt_burst = rte_eth_pkt_burst_dummy; + eth_dev->tx_pkt_burst = rte_eth_pkt_burst_dummy; 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; @@ -1747,14 +1642,6 @@ err_secondary: priv->mtr_profile_tbl = mlx5_l3t_create(MLX5_L3T_TYPE_PTR); if (!priv->mtr_profile_tbl) goto error; - /* 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, - })); /* Bring Ethernet device up. */ DRV_LOG(DEBUG, "port %u forcing Ethernet interface up", eth_dev->data->port_id); @@ -1765,13 +1652,6 @@ err_secondary: * Verbs context returned by ibv_open_device(). */ mlx5_link_update(eth_dev, 0); -#ifdef HAVE_MLX5DV_DR_ESWITCH - if (!(config->hca_attr.eswitch_manager && config->dv_flow_en && - (switch_info->representor || switch_info->master))) - config->dv_esw_en = 0; -#else - config->dv_esw_en = 0; -#endif /* Detect minimal data bytes to inline. */ mlx5_set_min_inline(spawn, config); /* Store device configuration on private structure. */ @@ -1790,34 +1670,26 @@ err_secondary: err = mlx5_alloc_shared_dr(priv); if (err) goto error; + if (mlx5_flex_item_port_init(eth_dev) < 0) + goto error; } - if (config->devx && config->dv_flow_en && config->dest_tir) { + if (sh->cdev->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); priv->obj_ops.lb_dummy_queue_create = mlx5_rxq_ibv_obj_dummy_lb_create; priv->obj_ops.lb_dummy_queue_release = mlx5_rxq_ibv_obj_dummy_lb_release; + } else if (spawn->max_port > UINT8_MAX) { + /* Verbs can't support ports larger than 255 by design. */ + DRV_LOG(ERR, "must enable DV and ESW when RDMA link ports > 255"); + err = ENOTSUP; + goto error; } else { priv->obj_ops = ibv_obj_ops; } if (config->tx_pp && - (priv->config.dv_esw_en || - priv->obj_ops.txq_obj_new != mlx5_os_txq_obj_new)) { + priv->obj_ops.txq_obj_new != mlx5_txq_devx_obj_new) { /* * HAVE_MLX5DV_DEVX_UAR_OFFSET is required to support * packet pacing and already checked above. @@ -1833,19 +1705,19 @@ err_secondary: 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); + /* Port representor shares the same max priority with pf port. */ + if (!priv->sh->flow_priority_check_flag) { + /* Supported Verbs flow priority number detection. */ + err = mlx5_flow_discover_priorities(eth_dev); + priv->sh->flow_max_priority = err; + priv->sh->flow_priority_check_flag = 1; + } else { + err = priv->sh->flow_max_priority; + } if (err < 0) { err = -err; goto error; } - priv->config.flow_prio = err; - if (!priv->config.dv_esw_en && - priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) { - DRV_LOG(WARNING, "metadata mode %u is not supported " - "(no E-Switch)", priv->config.dv_xmeta_en); - priv->config.dv_xmeta_en = MLX5_XMETA_MODE_LEGACY; - } mlx5_set_metadata_mask(eth_dev); if (priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY && !priv->sh->dv_regc0_mask) { @@ -1865,10 +1737,12 @@ err_secondary: goto error; rte_rwlock_init(&priv->ind_tbls_lock); /* Query availability of metadata reg_c's. */ - err = mlx5_flow_discover_mreg_c(eth_dev); - if (err < 0) { - err = -err; - goto error; + if (!priv->sh->metadata_regc_check_flag) { + err = mlx5_flow_discover_mreg_c(eth_dev); + if (err < 0) { + err = -err; + goto error; + } } if (!mlx5_flow_ext_mreg_supported(eth_dev)) { DRV_LOG(DEBUG, @@ -1913,8 +1787,6 @@ error: mlx5_os_free_shared_dr(priv); if (priv->nl_socket_route >= 0) close(priv->nl_socket_route); - if (priv->nl_socket_rdma >= 0) - close(priv->nl_socket_rdma); if (priv->vmwa_context) mlx5_vlan_vmwa_exit(priv->vmwa_context); if (eth_dev && priv->drop_queue.hrxq) @@ -1925,6 +1797,8 @@ error: claim_zero(rte_eth_switch_domain_free(priv->domain_id)); if (priv->hrxqs) mlx5_list_destroy(priv->hrxqs); + if (eth_dev && priv->flex_item_map) + mlx5_flex_item_port_cleanup(eth_dev); mlx5_free(priv); if (eth_dev != NULL) eth_dev->data->dev_private = NULL; @@ -1938,6 +1812,8 @@ error: } if (sh) mlx5_free_shared_dev_ctx(sh); + if (nl_rdma >= 0) + close(nl_rdma); MLX5_ASSERT(err > 0); rte_errno = err; return NULL; @@ -1984,14 +1860,14 @@ mlx5_dev_spawn_data_cmp(const void *a, const void *b) /** * Match PCI information for possible slaves of bonding device. * - * @param[in] ibv_dev - * Pointer to Infiniband device structure. + * @param[in] ibdev_name + * Name of Infiniband device. * @param[in] pci_dev * Pointer to primary PCI address structure to match. * @param[in] nl_rdma * Netlink RDMA group socket handle. * @param[in] owner - * Rerepsentor owner PF index. + * Representor owner PF index. * @param[out] bond_info * Pointer to bonding information. * @@ -2000,7 +1876,7 @@ mlx5_dev_spawn_data_cmp(const void *a, const void *b) * positive index of slave PF in bonding. */ static int -mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, +mlx5_device_bond_pci_match(const char *ibdev_name, const struct rte_pci_addr *pci_dev, int nl_rdma, uint16_t owner, struct mlx5_bond_info *bond_info) @@ -2011,29 +1887,31 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, FILE *bond_file = NULL, *file; int pf = -1; int ret; + uint8_t cur_guid[32] = {0}; + uint8_t guid[32] = {0}; /* - * Try to get master device name. If something goes - * wrong suppose the lack of kernel support and no - * bonding devices. + * 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")) + if (!strstr(ibdev_name, "bond")) return -1; - np = mlx5_nl_portnum(nl_rdma, ibv_dev->name); + np = mlx5_nl_portnum(nl_rdma, ibdev_name); if (!np) return -1; + if (mlx5_get_device_guid(pci_dev, cur_guid, sizeof(cur_guid)) < 0) + return -1; /* - * The Master device might not be on the predefined - * port (not on port index 1, it is not garanted), - * we have to scan all Infiniband device port and - * find master. + * The master device might not be on the predefined port(not on port + * index 1, it is not guaranteed), we have to scan all Infiniband + * device ports and find master. */ for (i = 1; i <= np; ++i) { /* Check whether Infiniband port is populated. */ - ifindex = mlx5_nl_ifindex(nl_rdma, ibv_dev->name, i); + ifindex = mlx5_nl_ifindex(nl_rdma, ibdev_name, i); if (!ifindex) continue; if (!if_indextoname(ifindex, ifname)) @@ -2053,13 +1931,15 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, char tmp_str[IF_NAMESIZE + 32]; struct rte_pci_addr pci_addr; struct mlx5_switch_info info; + int ret; /* Process slave interface names in the loop. */ snprintf(tmp_str, sizeof(tmp_str), "/sys/class/net/%s", ifname); if (mlx5_get_pci_addr(tmp_str, &pci_addr)) { - DRV_LOG(WARNING, "can not get PCI address" - " for netdev \"%s\"", ifname); + DRV_LOG(WARNING, + "Cannot get PCI address for netdev \"%s\".", + ifname); continue; } /* Slave interface PCI address match found. */ @@ -2083,15 +1963,6 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, tmp_str); break; } - /* Match PCI address, allows BDF0+pfx or BDFx+pfx. */ - if (pci_dev->domain == pci_addr.domain && - pci_dev->bus == pci_addr.bus && - pci_dev->devid == pci_addr.devid && - ((pci_dev->function == 0 && - pci_dev->function + owner == pci_addr.function) || - (pci_dev->function == owner && - pci_addr.function == owner))) - pf = info.port_name; /* Get ifindex. */ snprintf(tmp_str, sizeof(tmp_str), "/sys/class/net/%s/ifindex", ifname); @@ -2108,6 +1979,30 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, bond_info->ports[info.port_name].pci_addr = pci_addr; bond_info->ports[info.port_name].ifindex = ifindex; bond_info->n_port++; + /* + * Under socket direct mode, bonding will use + * system_image_guid as identification. + * After OFED 5.4, guid is readable (ret >= 0) under sysfs. + * All bonding members should have the same guid even if driver + * is using PCIe BDF. + */ + ret = mlx5_get_device_guid(&pci_addr, guid, sizeof(guid)); + if (ret < 0) + break; + else if (ret > 0) { + if (!memcmp(guid, cur_guid, sizeof(guid)) && + owner == info.port_name && + (owner != 0 || (owner == 0 && + !rte_pci_addr_cmp(pci_dev, &pci_addr)))) + pf = info.port_name; + } else if (pci_dev->domain == pci_addr.domain && + pci_dev->bus == pci_addr.bus && + pci_dev->devid == pci_addr.devid && + ((pci_dev->function == 0 && + pci_dev->function + owner == pci_addr.function) || + (pci_dev->function == owner && + pci_addr.function == owner))) + pf = info.port_name; } if (pf >= 0) { /* Get bond interface info */ @@ -2120,28 +2015,40 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, DRV_LOG(INFO, "PF device %u, bond device %u(%s)", ifindex, bond_info->ifindex, bond_info->ifname); } + if (owner == 0 && pf != 0) { + DRV_LOG(INFO, "PCIe instance %04x:%02x:%02x.%x isn't bonding owner", + pci_dev->domain, pci_dev->bus, pci_dev->devid, + pci_dev->function); + } return pf; } static void -mlx5_os_config_default(struct mlx5_dev_config *config) +mlx5_os_config_default(struct mlx5_dev_config *config, + struct mlx5_common_dev_config *cconf) { memset(config, 0, sizeof(*config)); config->mps = MLX5_ARG_UNSET; - config->dbnc = MLX5_ARG_UNSET; + config->cqe_comp = 1; config->rx_vec_en = 1; config->txq_inline_max = MLX5_ARG_UNSET; config->txq_inline_min = MLX5_ARG_UNSET; config->txq_inline_mpw = MLX5_ARG_UNSET; config->txqs_inline = MLX5_ARG_UNSET; config->vf_nl_en = 1; - config->mr_ext_memseg_en = 1; config->mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN; config->mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS; + config->mprq.log_min_stride_wqe_size = cconf->devx ? + cconf->hca_attr.log_min_stride_wqe_sz : + MLX5_MPRQ_LOG_MIN_STRIDE_WQE_SIZE; + config->mprq.log_stride_num = MLX5_MPRQ_DEFAULT_LOG_STRIDE_NUM; config->dv_esw_en = 1; config->dv_flow_en = 1; config->decap_en = 1; config->log_hp_size = MLX5_ARG_UNSET; + config->allow_duplicate_pattern = 1; + config->std_delay_drop = 0; + config->hp_delay_drop = 0; } /** @@ -2150,8 +2057,8 @@ mlx5_os_config_default(struct mlx5_dev_config *config) * This function spawns Ethernet devices out of a given PCI device and * bonding owner PF index. * - * @param[in] pci_dev - * PCI device information. + * @param[in] cdev + * Pointer to common mlx5 device structure. * @param[in] req_eth_da * Requested ethdev device argument. * @param[in] owner_id @@ -2161,7 +2068,7 @@ mlx5_os_config_default(struct mlx5_dev_config *config) * 0 on success, a negative errno value otherwise and rte_errno is set. */ static int -mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, +mlx5_os_pci_probe_pf(struct mlx5_common_device *cdev, struct rte_eth_devargs *req_eth_da, uint16_t owner_id) { @@ -2190,9 +2097,9 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, * >= 0 - bonding device (value is slave PF index) */ int bd = -1; + struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(cdev->dev); struct mlx5_dev_spawn_data *list = NULL; struct mlx5_dev_config dev_config; - 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; @@ -2202,7 +2109,7 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, ibv_list = mlx5_glue->get_device_list(&ret); if (!ibv_list) { rte_errno = errno ? errno : ENOSYS; - DRV_LOG(ERR, "cannot list devices, is ib_uverbs loaded?"); + DRV_LOG(ERR, "Cannot list devices, is ib_uverbs loaded?"); return -rte_errno; } /* @@ -2217,10 +2124,9 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, while (ret-- > 0) { struct rte_pci_addr pci_addr; - DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name); - bd = mlx5_device_bond_pci_match - (ibv_list[ret], &owner_pci, nl_rdma, owner_id, - &bond_info); + DRV_LOG(DEBUG, "Checking device \"%s\"", ibv_list[ret]->name); + bd = mlx5_device_bond_pci_match(ibv_list[ret]->name, &owner_pci, + nl_rdma, owner_id, &bond_info); if (bd >= 0) { /* * Bonding device detected. Only one match is allowed, @@ -2240,9 +2146,9 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, /* 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); + 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 { @@ -2264,7 +2170,7 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, if (!nd) { /* No device matches, just complain and bail out. */ DRV_LOG(WARNING, - "no Verbs device matches PCI device " PCI_PRI_FMT "," + "No Verbs device matches PCI device " PCI_PRI_FMT "," " are kernel drivers loaded?", owner_pci.domain, owner_pci.bus, owner_pci.devid, owner_pci.function); @@ -2281,26 +2187,22 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, if (nl_rdma >= 0) np = mlx5_nl_portnum(nl_rdma, ibv_match[0]->name); if (!np) - DRV_LOG(WARNING, "can not get IB device \"%s\"" - " ports number", ibv_match[0]->name); + DRV_LOG(WARNING, + "Cannot get IB device \"%s\" ports number.", + ibv_match[0]->name); if (bd >= 0 && !np) { - DRV_LOG(ERR, "can not get ports" - " for bonding device"); + DRV_LOG(ERR, "Cannot get ports for bonding device."); rte_errno = ENOENT; ret = -rte_errno; goto exit; } } - /* - * Now we can determine the maximal - * amount of devices to be spawned. - */ + /* Now we can determine the maximal amount of devices to be spawned. */ list = mlx5_malloc(MLX5_MEM_ZERO, - sizeof(struct mlx5_dev_spawn_data) * - (np ? np : nd), + sizeof(struct mlx5_dev_spawn_data) * (np ? np : nd), RTE_CACHE_LINE_SIZE, SOCKET_ID_ANY); if (!list) { - DRV_LOG(ERR, "spawn data array allocation failure"); + DRV_LOG(ERR, "Spawn data array allocation failure."); rte_errno = ENOMEM; ret = -rte_errno; goto exit; @@ -2319,14 +2221,14 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, list[ns].bond_info = &bond_info; list[ns].max_port = np; list[ns].phys_port = i; - list[ns].phys_dev = ibv_match[0]; + list[ns].phys_dev_name = ibv_match[0]->name; list[ns].eth_dev = NULL; list[ns].pci_dev = pci_dev; + list[ns].cdev = cdev; list[ns].pf_bond = bd; - list[ns].ifindex = mlx5_nl_ifindex - (nl_rdma, - mlx5_os_get_dev_device_name - (list[ns].phys_dev), i); + list[ns].ifindex = mlx5_nl_ifindex(nl_rdma, + ibv_match[0]->name, + i); if (!list[ns].ifindex) { /* * No network interface index found for the @@ -2339,10 +2241,9 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, } ret = -1; if (nl_route >= 0) - ret = mlx5_nl_switch_info - (nl_route, - list[ns].ifindex, - &list[ns].info); + ret = mlx5_nl_switch_info(nl_route, + list[ns].ifindex, + &list[ns].info); if (ret || (!list[ns].info.representor && !list[ns].info.master)) { /* @@ -2350,9 +2251,8 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, * Netlink, let's try to perform the task * with sysfs. */ - ret = mlx5_sysfs_switch_info - (list[ns].ifindex, - &list[ns].info); + ret = mlx5_sysfs_switch_info(list[ns].ifindex, + &list[ns].info); } if (!ret && bd >= 0) { switch (list[ns].info.name_type) { @@ -2361,7 +2261,7 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, /* * Force standalone bonding * device for ROCE LAG - * confgiurations. + * configurations. */ list[ns].info.master = 0; list[ns].info.representor = 0; @@ -2388,8 +2288,7 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, } if (!ns) { DRV_LOG(ERR, - "unable to recognize master/representors" - " on the IB device with multiple ports"); + "Unable to recognize master/representors on the IB device with multiple ports."); rte_errno = ENOENT; ret = -rte_errno; goto exit; @@ -2417,16 +2316,17 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, list[ns].bond_info = NULL; list[ns].max_port = 1; list[ns].phys_port = 1; - list[ns].phys_dev = ibv_match[i]; + list[ns].phys_dev_name = ibv_match[i]->name; list[ns].eth_dev = NULL; list[ns].pci_dev = pci_dev; + list[ns].cdev = cdev; list[ns].pf_bond = -1; list[ns].ifindex = 0; if (nl_rdma >= 0) list[ns].ifindex = mlx5_nl_ifindex - (nl_rdma, - mlx5_os_get_dev_device_name - (list[ns].phys_dev), 1); + (nl_rdma, + ibv_match[i]->name, + 1); if (!list[ns].ifindex) { char ifname[IF_NAMESIZE]; @@ -2465,10 +2365,9 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, } ret = -1; if (nl_route >= 0) - ret = mlx5_nl_switch_info - (nl_route, - list[ns].ifindex, - &list[ns].info); + ret = mlx5_nl_switch_info(nl_route, + list[ns].ifindex, + &list[ns].info); if (ret || (!list[ns].info.representor && !list[ns].info.master)) { /* @@ -2476,9 +2375,8 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, * Netlink, let's try to perform the task * with sysfs. */ - ret = mlx5_sysfs_switch_info - (list[ns].ifindex, - &list[ns].info); + ret = mlx5_sysfs_switch_info(list[ns].ifindex, + &list[ns].info); } if (!ret && (list[ns].info.representor ^ list[ns].info.master)) { @@ -2487,31 +2385,28 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, !list[ns].info.representor && !list[ns].info.master) { /* - * Single IB device with - * one physical port and + * Single IB device with one physical port and * attached network device. - * May be SRIOV is not enabled - * or there is no representors. + * May be SRIOV is not enabled or there is no + * representors. */ - DRV_LOG(INFO, "no E-Switch support detected"); + DRV_LOG(INFO, "No E-Switch support detected."); ns++; break; } } if (!ns) { DRV_LOG(ERR, - "unable to recognize master/representors" - " on the multiple IB devices"); + "Unable to recognize master/representors on the multiple IB devices."); rte_errno = ENOENT; ret = -rte_errno; goto exit; } /* * New kernels may add the switch_id attribute for the case - * there is no E-Switch and we wrongly recognized the - * only device as master. Override this if there is the - * single device with single port and new device name - * format present. + * there is no E-Switch and we wrongly recognized the only + * device as master. Override this if there is the single + * device with single port and new device name format present. */ if (nd == 1 && list[0].info.name_type == MLX5_PHYS_PORT_NAME_TYPE_UPLINK) { @@ -2525,21 +2420,6 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, * (i.e. master first, then representors from lowest to highest ID). */ qsort(list, ns, sizeof(*list), mlx5_dev_spawn_data_cmp); - /* Device specific configuration. */ - switch (pci_dev->id.device_id) { - case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF: - case PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF: - case PCI_DEVICE_ID_MELLANOX_CONNECTX5VF: - case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF: - case PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF: - case PCI_DEVICE_ID_MELLANOX_CONNECTX6VF: - 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) { @@ -2562,14 +2442,10 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, uint32_t restore; /* Default configuration. */ - mlx5_os_config_default(&dev_config); - dev_config.vf = dev_config_vf; - dev_config.allow_duplicate_pattern = 1; - list[i].numa_node = pci_dev->device.numa_node; - list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device, - &list[i], - &dev_config, - ð_da); + mlx5_os_config_default(&dev_config, &cdev->config); + dev_config.vf = mlx5_dev_is_vf_pci(pci_dev); + list[i].eth_dev = mlx5_dev_spawn(cdev->dev, &list[i], + &dev_config, ð_da); if (!list[i].eth_dev) { if (rte_errno != EBUSY && rte_errno != EEXIST) break; @@ -2588,11 +2464,9 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, * Representor interrupts handle is released in mlx5_dev_stop(). */ if (list[i].info.representor) { - struct rte_intr_handle *intr_handle; - intr_handle = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO, - sizeof(*intr_handle), 0, - SOCKET_ID_ANY); - if (!intr_handle) { + struct rte_intr_handle *intr_handle = + rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED); + if (intr_handle == NULL) { DRV_LOG(ERR, "port %u failed to allocate memory for interrupt handler " "Rx interrupts will not be supported", @@ -2681,41 +2555,54 @@ mlx5_os_parse_eth_devargs(struct rte_device *dev, * * This function spawns Ethernet devices out of a given PCI device. * - * @param[in] pci_dev - * PCI device information. + * @param[in] cdev + * Pointer to common mlx5 device structure. * * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ static int -mlx5_os_pci_probe(struct rte_pci_device *pci_dev) +mlx5_os_pci_probe(struct mlx5_common_device *cdev) { + struct rte_pci_device *pci_dev = RTE_DEV_TO_PCI(cdev->dev); struct rte_eth_devargs eth_da = { .nb_ports = 0 }; int ret = 0; uint16_t p; - ret = mlx5_os_parse_eth_devargs(&pci_dev->device, ð_da); + ret = mlx5_os_parse_eth_devargs(cdev->dev, ð_da); if (ret != 0) return ret; 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, + for (p = 0; p < eth_da.nb_ports; p++) { + ret = mlx5_os_pci_probe_pf(cdev, ð_da, eth_da.ports[p]); + if (ret) + break; + } + if (ret) { + DRV_LOG(ERR, "Probe of PCI device " PCI_PRI_FMT " " + "aborted due to prodding failure of PF %u", + pci_dev->addr.domain, pci_dev->addr.bus, + pci_dev->addr.devid, pci_dev->addr.function, + eth_da.ports[p]); + mlx5_net_remove(cdev); + } } else { - ret = mlx5_os_pci_probe_pf(pci_dev, ð_da, 0); + ret = mlx5_os_pci_probe_pf(cdev, ð_da, 0); } return ret; } /* Probe a single SF device on auxiliary bus, no representor support. */ static int -mlx5_os_auxiliary_probe(struct rte_device *dev) +mlx5_os_auxiliary_probe(struct mlx5_common_device *cdev) { struct rte_eth_devargs eth_da = { .nb_ports = 0 }; struct mlx5_dev_config config; struct mlx5_dev_spawn_data spawn = { .pf_bond = -1 }; + struct rte_device *dev = cdev->dev; struct rte_auxiliary_device *adev = RTE_DEV_TO_AUXILIARY(dev); struct rte_eth_dev *eth_dev; int ret = 0; @@ -2725,27 +2612,25 @@ mlx5_os_auxiliary_probe(struct rte_device *dev) if (ret != 0) return ret; /* Set default config data. */ - mlx5_os_config_default(&config); + mlx5_os_config_default(&config, &cdev->config); config.sf = 1; /* Init spawn data. */ spawn.max_port = 1; spawn.phys_port = 1; - spawn.phys_dev = mlx5_os_get_ibv_dev(dev); - if (spawn.phys_dev == NULL) - return -rte_errno; + spawn.phys_dev_name = mlx5_os_get_ctx_device_name(cdev->ctx); ret = mlx5_auxiliary_get_ifindex(dev->name); if (ret < 0) { DRV_LOG(ERR, "failed to get ethdev ifindex: %s", dev->name); return ret; } spawn.ifindex = ret; - spawn.numa_node = dev->numa_node; + spawn.cdev = cdev; /* Spawn device. */ eth_dev = mlx5_dev_spawn(dev, &spawn, &config, ð_da); if (eth_dev == NULL) return -rte_errno; /* Post create. */ - eth_dev->intr_handle = &adev->intr_handle; + eth_dev->intr_handle = adev->intr_handle; if (rte_eal_process_type() == RTE_PROC_PRIMARY) { eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC; eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_RMV; @@ -2760,14 +2645,14 @@ mlx5_os_auxiliary_probe(struct rte_device *dev) * * This function probe PCI bus device(s) or a single SF on auxiliary bus. * - * @param[in] dev - * Pointer to the generic device. + * @param[in] cdev + * Pointer to the common mlx5 device. * * @return - * 0 on success, the function cannot fail. + * 0 on success, a negative errno value otherwise and rte_errno is set. */ int -mlx5_os_net_probe(struct rte_device *dev) +mlx5_os_net_probe(struct mlx5_common_device *cdev) { int ret; @@ -2775,144 +2660,23 @@ mlx5_os_net_probe(struct rte_device *dev) mlx5_pmd_socket_init(); ret = mlx5_init_once(); if (ret) { - DRV_LOG(ERR, "unable to init PMD global data: %s", + DRV_LOG(ERR, "Unable to init PMD global data: %s", strerror(rte_errno)); return -rte_errno; } - if (mlx5_dev_is_pci(dev)) - return mlx5_os_pci_probe(RTE_DEV_TO_PCI(dev)); + if (mlx5_dev_is_pci(cdev->dev)) + return mlx5_os_pci_probe(cdev); else - return mlx5_os_auxiliary_probe(dev); -} - -static int -mlx5_config_doorbell_mapping_env(const struct mlx5_dev_config *config) -{ - char *env; - int value; - - MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY); - /* Get environment variable to store. */ - env = getenv(MLX5_SHUT_UP_BF); - value = env ? !!strcmp(env, "0") : MLX5_ARG_UNSET; - if (config->dbnc == MLX5_ARG_UNSET) - setenv(MLX5_SHUT_UP_BF, MLX5_SHUT_UP_BF_DEFAULT, 1); - else - setenv(MLX5_SHUT_UP_BF, - config->dbnc == MLX5_TXDB_NCACHED ? "1" : "0", 1); - return value; -} - -static void -mlx5_restore_doorbell_mapping_env(int value) -{ - MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY); - /* Restore the original environment variable state. */ - if (value == MLX5_ARG_UNSET) - unsetenv(MLX5_SHUT_UP_BF); - else - setenv(MLX5_SHUT_UP_BF, value ? "1" : "0", 1); -} - -/** - * Extract pdn of PD object using DV API. - * - * @param[in] pd - * Pointer to the verbs PD object. - * @param[out] pdn - * Pointer to the PD object number variable. - * - * @return - * 0 on success, error value otherwise. - */ -int -mlx5_os_get_pdn(void *pd, uint32_t *pdn) -{ -#ifdef HAVE_IBV_FLOW_DV_SUPPORT - struct mlx5dv_obj obj; - struct mlx5dv_pd pd_info; - int ret = 0; - - obj.pd.in = pd; - obj.pd.out = &pd_info; - ret = mlx5_glue->dv_init_obj(&obj, MLX5DV_OBJ_PD); - if (ret) { - DRV_LOG(DEBUG, "Fail to get PD object info"); - return ret; - } - *pdn = pd_info.pdn; - return 0; -#else - (void)pd; - (void)pdn; - return -ENOTSUP; -#endif /* HAVE_IBV_FLOW_DV_SUPPORT */ + return mlx5_os_auxiliary_probe(cdev); } /** - * Function API to open IB device. - * - * This function calls the Linux glue APIs to open a device. - * - * @param[in] spawn - * Pointer to the IB device attributes (name, port, etc). - * @param[out] config - * Pointer to device configuration structure. - * @param[out] sh - * Pointer to shared context structure. - * - * @return - * 0 on success, a positive error value otherwise. + * Cleanup resources when the last device is closed. */ -int -mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn, - const struct mlx5_dev_config *config, - struct mlx5_dev_ctx_shared *sh) +void +mlx5_os_net_cleanup(void) { - int dbmap_env; - int err = 0; - - pthread_mutex_init(&sh->txpp.mutex, NULL); - /* - * Configure environment variable "MLX5_BF_SHUT_UP" - * before the device creation. The rdma_core library - * checks the variable at device creation and - * stores the result internally. - */ - dbmap_env = mlx5_config_doorbell_mapping_env(config); - /* Try to open IB device with DV first, then usual Verbs. */ - errno = 0; - sh->ctx = mlx5_glue->dv_open_device(spawn->phys_dev); - if (sh->ctx) { - sh->devx = 1; - DRV_LOG(DEBUG, "DevX is supported"); - /* The device is created, no need for environment. */ - mlx5_restore_doorbell_mapping_env(dbmap_env); - } else { - /* The environment variable is still configured. */ - sh->ctx = mlx5_glue->open_device(spawn->phys_dev); - err = errno ? errno : ENODEV; - /* - * The environment variable is not needed anymore, - * all device creation attempts are completed. - */ - mlx5_restore_doorbell_mapping_env(dbmap_env); - if (!sh->ctx) - return err; - 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; + mlx5_pmd_socket_uninit(); } /** @@ -2928,28 +2692,41 @@ mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh) { int ret; int flags; + struct ibv_context *ctx = sh->cdev->ctx; - sh->intr_handle.fd = -1; - flags = fcntl(((struct ibv_context *)sh->ctx)->async_fd, F_GETFL); - ret = fcntl(((struct ibv_context *)sh->ctx)->async_fd, - F_SETFL, flags | O_NONBLOCK); + sh->intr_handle = rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED); + if (sh->intr_handle == NULL) { + DRV_LOG(ERR, "Fail to allocate intr_handle"); + rte_errno = ENOMEM; + return; + } + rte_intr_fd_set(sh->intr_handle, -1); + + flags = fcntl(ctx->async_fd, F_GETFL); + ret = fcntl(ctx->async_fd, F_SETFL, flags | O_NONBLOCK); if (ret) { DRV_LOG(INFO, "failed to change file descriptor async event" " queue"); } else { - sh->intr_handle.fd = ((struct ibv_context *)sh->ctx)->async_fd; - sh->intr_handle.type = RTE_INTR_HANDLE_EXT; - if (rte_intr_callback_register(&sh->intr_handle, + rte_intr_fd_set(sh->intr_handle, ctx->async_fd); + rte_intr_type_set(sh->intr_handle, RTE_INTR_HANDLE_EXT); + if (rte_intr_callback_register(sh->intr_handle, mlx5_dev_interrupt_handler, sh)) { DRV_LOG(INFO, "Fail to install the shared interrupt."); - sh->intr_handle.fd = -1; + rte_intr_fd_set(sh->intr_handle, -1); } } - if (sh->devx) { + if (sh->cdev->config.devx) { #ifdef HAVE_IBV_DEVX_ASYNC - sh->intr_handle_devx.fd = -1; - sh->devx_comp = - (void *)mlx5_glue->devx_create_cmd_comp(sh->ctx); + sh->intr_handle_devx = + rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED); + if (!sh->intr_handle_devx) { + DRV_LOG(ERR, "Fail to allocate intr_handle"); + rte_errno = ENOMEM; + return; + } + rte_intr_fd_set(sh->intr_handle_devx, -1); + sh->devx_comp = (void *)mlx5_glue->devx_create_cmd_comp(ctx); struct mlx5dv_devx_cmd_comp *devx_comp = sh->devx_comp; if (!devx_comp) { DRV_LOG(INFO, "failed to allocate devx_comp."); @@ -2962,13 +2739,14 @@ mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh) " devx comp"); return; } - sh->intr_handle_devx.fd = devx_comp->fd; - sh->intr_handle_devx.type = RTE_INTR_HANDLE_EXT; - if (rte_intr_callback_register(&sh->intr_handle_devx, + rte_intr_fd_set(sh->intr_handle_devx, devx_comp->fd); + rte_intr_type_set(sh->intr_handle_devx, + RTE_INTR_HANDLE_EXT); + if (rte_intr_callback_register(sh->intr_handle_devx, mlx5_dev_interrupt_handler_devx, sh)) { DRV_LOG(INFO, "Fail to install the devx shared" " interrupt."); - sh->intr_handle_devx.fd = -1; + rte_intr_fd_set(sh->intr_handle_devx, -1); } #endif /* HAVE_IBV_DEVX_ASYNC */ } @@ -2985,13 +2763,15 @@ mlx5_os_dev_shared_handler_install(struct mlx5_dev_ctx_shared *sh) void mlx5_os_dev_shared_handler_uninstall(struct mlx5_dev_ctx_shared *sh) { - if (sh->intr_handle.fd >= 0) - mlx5_intr_callback_unregister(&sh->intr_handle, + if (rte_intr_fd_get(sh->intr_handle) >= 0) + mlx5_intr_callback_unregister(sh->intr_handle, mlx5_dev_interrupt_handler, sh); + rte_intr_instance_free(sh->intr_handle); #ifdef HAVE_IBV_DEVX_ASYNC - if (sh->intr_handle_devx.fd >= 0) - rte_intr_callback_unregister(&sh->intr_handle_devx, + if (rte_intr_fd_get(sh->intr_handle_devx) >= 0) + rte_intr_callback_unregister(sh->intr_handle_devx, mlx5_dev_interrupt_handler_devx, sh); + rte_intr_instance_free(sh->intr_handle_devx); if (sh->devx_comp) mlx5_glue->devx_destroy_cmd_comp(sh->devx_comp); #endif @@ -3052,23 +2832,6 @@ mlx5_os_read_dev_stat(struct mlx5_priv *priv, const char *ctr_name, return 1; } -/** - * Set the reg_mr and dereg_mr call backs - * - * @param reg_mr_cb[out] - * Pointer to reg_mr func - * @param dereg_mr_cb[out] - * Pointer to dereg_mr func - * - */ -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 *