X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Flinux%2Fmlx5_os.c;h=4ab30fd244f6953cdf18d1fdc5c0dfec9abb012d;hb=56bb3c84e98236d4fe197519d8e33f60ee46d964;hp=336cdbe3a8879c67b2c6dda3699e05fe45eb3e9e;hpb=29efa63a7ed3477e249e685413db8aa430b7ec56;p=dpdk.git diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c index 336cdbe3a8..4ab30fd244 100644 --- a/drivers/net/mlx5/linux/mlx5_os.c +++ b/drivers/net/mlx5/linux/mlx5_os.c @@ -50,8 +50,6 @@ #include "mlx5_nl.h" #include "mlx5_devx.h" -#define MLX5_TAGS_HLIST_ARRAY_SIZE 8192 - #ifndef HAVE_IBV_MLX5_MOD_MPW #define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2) #define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3) @@ -69,6 +67,44 @@ 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; +/* rte flow indexed pool configuration. */ +static struct mlx5_indexed_pool_config icfg[] = { + { + .size = sizeof(struct rte_flow), + .trunk_size = 64, + .need_lock = 1, + .release_mem_en = 0, + .malloc = mlx5_malloc, + .free = mlx5_free, + .per_core_cache = 0, + .type = "ctl_flow_ipool", + }, + { + .size = sizeof(struct rte_flow), + .trunk_size = 64, + .grow_trunk = 3, + .grow_shift = 2, + .need_lock = 1, + .release_mem_en = 0, + .malloc = mlx5_malloc, + .free = mlx5_free, + .per_core_cache = 1 << 14, + .type = "rte_flow_ipool", + }, + { + .size = sizeof(struct rte_flow), + .trunk_size = 64, + .grow_trunk = 3, + .grow_shift = 2, + .need_lock = 1, + .release_mem_en = 0, + .malloc = mlx5_malloc, + .free = mlx5_free, + .per_core_cache = 0, + .type = "mcp_flow_ipool", + }, +}; + /** * Set the completion channel file descriptor interrupt as non-blocking. * @@ -154,6 +190,8 @@ mlx5_os_get_dev_attr(void *ctx, struct mlx5_dev_attr *device_attr) #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; } @@ -191,6 +229,79 @@ mlx5_alloc_verbs_buf(size_t size, void *data) return ret; } +/** + * Detect misc5 support or not + * + * @param[in] priv + * Device private data pointer + */ +#ifdef HAVE_MLX5DV_DR +static void +__mlx5_discovery_misc5_cap(struct mlx5_priv *priv) +{ +#ifdef HAVE_IBV_FLOW_DV_SUPPORT + /* Dummy VxLAN matcher to detect rdma-core misc5 cap + * Case: IPv4--->UDP--->VxLAN--->vni + */ + void *tbl; + struct mlx5_flow_dv_match_params matcher_mask; + void *match_m; + void *matcher; + void *headers_m; + void *misc5_m; + uint32_t *tunnel_header_m; + struct mlx5dv_flow_matcher_attr dv_attr; + + memset(&matcher_mask, 0, sizeof(matcher_mask)); + matcher_mask.size = sizeof(matcher_mask.buf); + match_m = matcher_mask.buf; + headers_m = MLX5_ADDR_OF(fte_match_param, match_m, outer_headers); + misc5_m = MLX5_ADDR_OF(fte_match_param, + match_m, misc_parameters_5); + tunnel_header_m = (uint32_t *) + MLX5_ADDR_OF(fte_match_set_misc5, + misc5_m, tunnel_header_1); + MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_protocol, 0xff); + MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 4); + MLX5_SET(fte_match_set_lyr_2_4, headers_m, udp_dport, 0xffff); + *tunnel_header_m = 0xffffff; + + tbl = mlx5_glue->dr_create_flow_tbl(priv->sh->rx_domain, 1); + if (!tbl) { + DRV_LOG(INFO, "No SW steering support"); + return; + } + dv_attr.type = IBV_FLOW_ATTR_NORMAL, + dv_attr.match_mask = (void *)&matcher_mask, + dv_attr.match_criteria_enable = + (1 << MLX5_MATCH_CRITERIA_ENABLE_OUTER_BIT) | + (1 << MLX5_MATCH_CRITERIA_ENABLE_MISC5_BIT); + dv_attr.priority = 3; +#ifdef HAVE_MLX5DV_DR_ESWITCH + void *misc2_m; + if (priv->config.dv_esw_en) { + /* FDB enabled reg_c_0 */ + dv_attr.match_criteria_enable |= + (1 << MLX5_MATCH_CRITERIA_ENABLE_MISC2_BIT); + misc2_m = MLX5_ADDR_OF(fte_match_param, + match_m, misc_parameters_2); + MLX5_SET(fte_match_set_misc2, misc2_m, + metadata_reg_c_0, 0xffff); + } +#endif + matcher = mlx5_glue->dv_create_flow_matcher(priv->sh->ctx, + &dv_attr, tbl); + if (matcher) { + priv->sh->misc5_cap = 1; + mlx5_glue->dv_destroy_flow_matcher(matcher); + } + mlx5_glue->dr_destroy_flow_tbl(tbl); +#else + RTE_SET_USED(priv); +#endif +} +#endif + /** * Verbs callback to free a memory. * @@ -221,7 +332,7 @@ static int mlx5_alloc_shared_dr(struct mlx5_priv *priv) { struct mlx5_dev_ctx_shared *sh = priv->sh; - char s[MLX5_HLIST_NAMESIZE] __rte_unused; + char s[MLX5_NAME_SIZE] __rte_unused; int err; MLX5_ASSERT(sh && sh->refcnt); @@ -232,70 +343,46 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) 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, 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; + /* Init port id action list. */ + snprintf(s, sizeof(s), "%s_port_id_action_list", sh->ibdev_name); + sh->port_id_action_list = mlx5_list_create(s, sh, true, + flow_dv_port_id_create_cb, + flow_dv_port_id_match_cb, + flow_dv_port_id_remove_cb, + flow_dv_port_id_clone_cb, + flow_dv_port_id_clone_free_cb); + if (!sh->port_id_action_list) 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; + /* Init push vlan action list. */ + snprintf(s, sizeof(s), "%s_push_vlan_action_list", sh->ibdev_name); + sh->push_vlan_action_list = mlx5_list_create(s, sh, true, + flow_dv_push_vlan_create_cb, + flow_dv_push_vlan_match_cb, + flow_dv_push_vlan_remove_cb, + flow_dv_push_vlan_clone_cb, + flow_dv_push_vlan_clone_free_cb); + if (!sh->push_vlan_action_list) 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; + /* Init sample action list. */ + snprintf(s, sizeof(s), "%s_sample_action_list", sh->ibdev_name); + sh->sample_action_list = mlx5_list_create(s, sh, true, + flow_dv_sample_create_cb, + flow_dv_sample_match_cb, + flow_dv_sample_remove_cb, + flow_dv_sample_clone_cb, + flow_dv_sample_clone_free_cb); + if (!sh->sample_action_list) + goto error; + /* Init dest array action list. */ + snprintf(s, sizeof(s), "%s_dest_array_list", sh->ibdev_name); + sh->dest_array_list = mlx5_list_create(s, sh, true, + flow_dv_dest_array_create_cb, + flow_dv_dest_array_match_cb, + flow_dv_dest_array_remove_cb, + flow_dv_dest_array_clone_cb, + flow_dv_dest_array_clone_free_cb); + if (!sh->dest_array_list) goto error; - } - sh->encaps_decaps->ctx = sh; #endif #ifdef HAVE_MLX5DV_DR void *domain; @@ -340,7 +427,7 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) goto error; } #endif - if (!sh->tunnel_hub) + if (!sh->tunnel_hub && priv->config.dv_miss_info) err = mlx5_alloc_tunnel_hub(sh); if (err) { DRV_LOG(ERR, "mlx5_alloc_tunnel_hub failed err=%d", err); @@ -353,6 +440,17 @@ mlx5_alloc_shared_dr(struct mlx5_priv *priv) mlx5_glue->dr_reclaim_domain_memory(sh->fdb_domain, 1); } sh->pop_vlan_action = mlx5_glue->dr_create_flow_action_pop_vlan(); + if (!priv->config.allow_duplicate_pattern) { +#ifndef HAVE_MLX5_DR_ALLOW_DUPLICATE + DRV_LOG(WARNING, "Disallow duplicate pattern is not supported - maybe old rdma-core version?"); +#endif + mlx5_glue->dr_allow_duplicate_rules(sh->rx_domain, 0); + mlx5_glue->dr_allow_duplicate_rules(sh->tx_domain, 0); + if (sh->fdb_domain) + mlx5_glue->dr_allow_duplicate_rules(sh->fdb_domain, 0); + } + + __mlx5_discovery_misc5_cap(priv); #endif /* HAVE_MLX5DV_DR */ sh->default_miss_action = mlx5_glue->dr_create_flow_action_default_miss(); @@ -399,6 +497,22 @@ error: sh->tunnel_hub = NULL; } mlx5_free_table_hash_list(priv); + if (sh->port_id_action_list) { + mlx5_list_destroy(sh->port_id_action_list); + sh->port_id_action_list = NULL; + } + if (sh->push_vlan_action_list) { + mlx5_list_destroy(sh->push_vlan_action_list); + sh->push_vlan_action_list = NULL; + } + if (sh->sample_action_list) { + mlx5_list_destroy(sh->sample_action_list); + sh->sample_action_list = NULL; + } + if (sh->dest_array_list) { + mlx5_list_destroy(sh->dest_array_list); + sh->dest_array_list = NULL; + } return err; } @@ -460,9 +574,23 @@ mlx5_os_free_shared_dr(struct mlx5_priv *priv) 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); + if (sh->port_id_action_list) { + mlx5_list_destroy(sh->port_id_action_list); + sh->port_id_action_list = NULL; + } + if (sh->push_vlan_action_list) { + mlx5_list_destroy(sh->push_vlan_action_list); + sh->push_vlan_action_list = NULL; + } + if (sh->sample_action_list) { + mlx5_list_destroy(sh->sample_action_list); + sh->sample_action_list = NULL; + } + if (sh->dest_array_list) { + mlx5_list_destroy(sh->dest_array_list); + sh->dest_array_list = NULL; + } } /** @@ -820,9 +948,8 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, char name[RTE_ETH_NAME_MAX_LEN]; int own_domain_id = 0; uint16_t port_id; -#ifdef HAVE_MLX5DV_DR_DEVX_PORT - struct mlx5dv_devx_port devx_port = { .comp_mask = 0 }; -#endif + struct mlx5_port_info vport_info = { .query_flags = 0 }; + int i; /* Determine if this port representor is supposed to be spawned. */ if (switch_info->representor && dpdk_dev->devargs && @@ -1053,29 +1180,27 @@ err_secondary: priv->vport_meta_tag = 0; priv->vport_meta_mask = 0; priv->pf_bond = spawn->pf_bond; -#ifdef HAVE_MLX5DV_DR_DEVX_PORT /* - * The DevX port query API is implemented. E-Switch may use - * either vport or reg_c[0] metadata register to match on - * vport index. The engaged part of metadata register is - * defined by mask. + * If we have E-Switch we should determine the vport attributes. + * E-Switch may use either source vport field or reg_c[0] metadata + * register to match on vport index. The engaged part of metadata + * register is defined by mask. */ if (switch_info->representor || switch_info->master) { - devx_port.comp_mask = MLX5DV_DEVX_PORT_VPORT | - MLX5DV_DEVX_PORT_MATCH_REG_C_0; - err = mlx5_glue->devx_port_query(sh->ctx, spawn->phys_port, - &devx_port); + err = mlx5_glue->devx_port_query(sh->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)); - devx_port.comp_mask = 0; + vport_info.query_flags = 0; } } - if (devx_port.comp_mask & MLX5DV_DEVX_PORT_MATCH_REG_C_0) { - priv->vport_meta_tag = devx_port.reg_c_0.value; - priv->vport_meta_mask = devx_port.reg_c_0.mask; + if (vport_info.query_flags & MLX5_PORT_QUERY_REG_C0) { + 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", @@ -1095,9 +1220,10 @@ err_secondary: goto error; } } - if (devx_port.comp_mask & MLX5DV_DEVX_PORT_VPORT) { - priv->vport_id = devx_port.vport_num; - } else if (spawn->pf_bond >= 0) { + if (vport_info.query_flags & MLX5_PORT_QUERY_VPORT) { + 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, @@ -1105,32 +1231,28 @@ err_secondary: err = ENOTSUP; goto error; } else { - /* Suppose vport index in compatible way. */ + /* + * Suppose vport index in compatible way. Kernel/rdma_core + * support single E-Switch per PF configurations only and + * vport_id field contains the vport index for associated VF, + * which is deduced from representor port name. + * For example, let's have the IB device port 10, it has + * attached network device eth0, which has port name attribute + * pf0vf2, we can deduce the VF number as 2, and set vport index + * as 3 (2+1). This assigning schema should be changed if the + * multiple E-Switch instances per PF configurations or/and PCI + * subfunctions are added. + */ priv->vport_id = switch_info->representor ? switch_info->port_name + 1 : -1; } -#else - /* - * Kernel/rdma_core support single E-Switch per PF configurations - * only and vport_id field contains the vport index for - * associated VF, which is deduced from representor port name. - * For example, let's have the IB device port 10, it has - * attached network device eth0, which has port name attribute - * pf0vf2, we can deduce the VF number as 2, and set vport index - * as 3 (2+1). This assigning schema should be changed if the - * multiple E-Switch instances per PF configurations or/and PCI - * subfunctions are added. - */ - priv->vport_id = switch_info->representor ? - switch_info->port_name + 1 : -1; -#endif 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. */ - MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) { + MLX5_ETH_FOREACH_DEV(port_id, NULL) { const struct mlx5_priv *opriv = rte_eth_devices[port_id].data->dev_private; @@ -1255,7 +1377,9 @@ err_secondary: "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 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 && config->dv_flow_en) { @@ -1297,15 +1421,18 @@ err_secondary: if (log_obj_size >= config->hca_attr.qos.log_meter_aso_granularity && log_obj_size <= - config->hca_attr.qos.log_meter_aso_max_alloc) { + config->hca_attr.qos.log_meter_aso_max_alloc) sh->meter_aso_en = 1; - err = mlx5_aso_flow_mtrs_mng_init(priv); - if (err) { - err = -err; - goto error; - } + } + if (priv->mtr_en) { + err = mlx5_aso_flow_mtrs_mng_init(priv->sh); + if (err) { + err = -err; + goto error; } } + if (config->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 && @@ -1319,6 +1446,19 @@ err_secondary: DRV_LOG(DEBUG, "Flow Hit ASO is supported."); } #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) { + err = mlx5_flow_aso_ct_mng_init(sh); + if (err) { + err = -err; + goto error; + } + DRV_LOG(DEBUG, "CT ASO is supported."); + sh->ct_aso_en = 1; + } +#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 && config->dv_flow_en) { @@ -1555,11 +1695,12 @@ err_secondary: 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); + 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, @@ -1589,6 +1730,14 @@ err_secondary: mlx5_set_min_inline(spawn, config); /* Store device configuration on private structure. */ priv->config = *config; + for (i = 0; i < MLX5_FLOW_TYPE_MAXI; i++) { + icfg[i].release_mem_en = !!config->reclaim_mode; + if (config->reclaim_mode) + icfg[i].per_core_cache = 0; + priv->flows[i] = mlx5_ipool_create(&icfg[i]); + if (!priv->flows[i]) + goto error; + } /* Create context for virtual machine VLAN workaround. */ priv->vmwa_context = mlx5_vlan_vmwa_init(eth_dev, spawn->ifindex); if (config->dv_flow_en) { @@ -1613,7 +1762,10 @@ err_secondary: 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 { priv->obj_ops = ibv_obj_ops; } @@ -1642,10 +1794,15 @@ err_secondary: err = ENOTSUP; goto error; } - mlx5_cache_list_init(&priv->hrxqs, "hrxq", 0, eth_dev, - mlx5_hrxq_create_cb, - mlx5_hrxq_match_cb, - mlx5_hrxq_remove_cb); + priv->hrxqs = mlx5_list_create("hrxq", eth_dev, true, + mlx5_hrxq_create_cb, + mlx5_hrxq_match_cb, + mlx5_hrxq_remove_cb, + mlx5_hrxq_clone_cb, + mlx5_hrxq_clone_free_cb); + if (!priv->hrxqs) + 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) { @@ -1670,15 +1827,16 @@ err_secondary: priv->sh->dv_regc0_mask) { priv->mreg_cp_tbl = mlx5_hlist_create(MLX5_FLOW_MREG_HNAME, MLX5_FLOW_MREG_HTABLE_SZ, - 0, 0, + false, true, eth_dev, flow_dv_mreg_create_cb, flow_dv_mreg_match_cb, - flow_dv_mreg_remove_cb); + flow_dv_mreg_remove_cb, + flow_dv_mreg_clone_cb, + flow_dv_mreg_clone_free_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); @@ -1699,9 +1857,12 @@ error: mlx5_vlan_vmwa_exit(priv->vmwa_context); if (eth_dev && priv->drop_queue.hrxq) mlx5_drop_action_destroy(eth_dev); + if (priv->mtr_profile_tbl) + mlx5_l3t_destroy(priv->mtr_profile_tbl); if (own_domain_id) claim_zero(rte_eth_switch_domain_free(priv->domain_id)); - mlx5_cache_list_destroy(&priv->hrxqs); + if (priv->hrxqs) + mlx5_list_destroy(priv->hrxqs); mlx5_free(priv); if (eth_dev != NULL) eth_dev->data->dev_private = NULL; @@ -1834,7 +1995,7 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, /* Process slave interface names in the loop. */ snprintf(tmp_str, sizeof(tmp_str), "/sys/class/net/%s", ifname); - if (mlx5_dev_to_pci_addr(tmp_str, &pci_addr)) { + if (mlx5_get_pci_addr(tmp_str, &pci_addr)) { DRV_LOG(WARNING, "can not get PCI address" " for netdev \"%s\"", ifname); continue; @@ -1860,11 +2021,14 @@ mlx5_device_bond_pci_match(const struct ibv_device *ibv_dev, tmp_str); break; } - /* Match PCI address. */ + /* 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 + owner == pci_addr.function) + ((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), @@ -2008,8 +2172,8 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, break; } else { /* Bonding device not found. */ - if (mlx5_dev_to_pci_addr - (ibv_list[ret]->ibdev_path, &pci_addr)) + if (mlx5_get_pci_addr(ibv_list[ret]->ibdev_path, + &pci_addr)) continue; if (owner_pci.domain != pci_addr.domain || owner_pci.bus != pci_addr.bus || @@ -2273,6 +2437,18 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, 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. + */ + if (nd == 1 && + list[0].info.name_type == MLX5_PHYS_PORT_NAME_TYPE_UPLINK) { + list[0].info.master = 0; + list[0].info.representor = 0; + } } MLX5_ASSERT(ns); /* @@ -2334,6 +2510,8 @@ mlx5_os_pci_probe_pf(struct rte_pci_device *pci_dev, dev_config.dv_flow_en = 1; dev_config.decap_en = 1; dev_config.log_hp_size = MLX5_ARG_UNSET; + 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, @@ -2531,7 +2709,6 @@ mlx5_os_open_device(const struct mlx5_dev_spawn_data *spawn, int dbmap_env; int err = 0; - sh->numa_node = spawn->pci_dev->device.numa_node; pthread_mutex_init(&sh->txpp.mutex, NULL); /* * Configure environment variable "MLX5_BF_SHUT_UP" @@ -2680,8 +2857,8 @@ mlx5_os_read_dev_stat(struct mlx5_priv *priv, const char *ctr_name, 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); + return mlx5_devx_cmd_queue_counter_query + (priv->q_counters, 0, (uint32_t *)stat); MKSTR(path, "%s/ports/%d/hw_counters/%s", priv->sh->ibdev_path, priv->dev_port,