X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Flinux%2Fmlx5_os.c;h=db44169b844bf45b9eea0789eef62cad0646530d;hb=cdfdb82d0b361d9e0848917b0ed6e9cf30e46dd1;hp=1217b510b6ae2464c119109787c473776c95899a;hpb=1b9e9826ad80e5ae56b484c6f6c4bb2df6e8fa70;p=dpdk.git diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5/linux/mlx5_os.c index 1217b510b6..db44169b84 100644 --- a/drivers/net/mlx5/linux/mlx5_os.c +++ b/drivers/net/mlx5/linux/mlx5_os.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -40,6 +41,8 @@ #include "mlx5_common_os.h" #include "mlx5_utils.h" #include "mlx5_rxtx.h" +#include "mlx5_rx.h" +#include "mlx5_tx.h" #include "mlx5_autoconf.h" #include "mlx5_mr.h" #include "mlx5_flow.h" @@ -48,8 +51,6 @@ #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) @@ -67,6 +68,44 @@ 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. * @@ -152,6 +191,8 @@ 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; } @@ -189,6 +230,79 @@ 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. * @@ -219,7 +333,7 @@ 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); @@ -230,70 +344,46 @@ 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; @@ -325,10 +415,20 @@ 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) + 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); @@ -341,6 +441,17 @@ 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(); @@ -361,9 +472,9 @@ 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); @@ -387,6 +498,22 @@ 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; } @@ -418,9 +545,9 @@ 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) { @@ -448,9 +575,23 @@ 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; + } } /** @@ -692,6 +833,76 @@ mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev) "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. * @@ -701,6 +912,8 @@ mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev) * 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 @@ -712,7 +925,8 @@ mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev) 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; @@ -735,62 +949,43 @@ 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 + 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) { - 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; - } - if (eth_da.type == RTE_ETH_REPRESENTOR_NONE) { - /* Representor not specified. */ - rte_errno = EBUSY; - return NULL; - } - if (eth_da.type != RTE_ETH_REPRESENTOR_VF) { - rte_errno = ENOTSUP; - DRV_LOG(ERR, "unsupported representor type: %s", - dpdk_dev->devargs->args); - 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; @@ -806,13 +1001,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, rte_errno = ENOMEM; return NULL; } - priv = eth_dev->data->dev_private; - if (priv->sh->bond_dev != UINT16_MAX) - /* For bonding port, use primary PCI device. */ - eth_dev->device = - rte_eth_devices[priv->sh->bond_dev].device; - else - eth_dev->device = dpdk_dev; + eth_dev->device = dpdk_dev; 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; @@ -992,29 +1181,27 @@ 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", @@ -1034,9 +1221,10 @@ 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, @@ -1044,33 +1232,28 @@ 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 - /* 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. */ - 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; @@ -1111,6 +1294,12 @@ err_secondary: 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; /* @@ -1173,6 +1362,9 @@ err_secondary: 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) { @@ -1192,7 +1384,9 @@ 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) { @@ -1227,6 +1421,25 @@ err_secondary: priv->mtr_color_reg); } } + if (config->hca_attr.qos.sup && + config->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) + sh->meter_aso_en = 1; + } + 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 && @@ -1240,6 +1453,19 @@ 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) { @@ -1422,33 +1648,10 @@ err_secondary: */ MLX5_ASSERT(spawn->ifindex); priv->if_index = spawn->ifindex; - if (priv->pf_bond >= 0 && priv->master) { - /* Get bond interface info */ - err = mlx5_sysfs_bond_info(priv->if_index, - &priv->bond_ifindex, - priv->bond_name); - if (err) - DRV_LOG(ERR, "unable to get bond info: %s", - strerror(rte_errno)); - else - DRV_LOG(INFO, "PF device %u, bond device %u(%s)", - priv->if_index, priv->bond_ifindex, - priv->bond_name); - } eth_dev->data->dev_private = priv; priv->dev_data = eth_dev->data; eth_dev->data->mac_addrs = priv->mac; - if (spawn->pf_bond < 0) { - eth_dev->device = dpdk_dev; - } else { - /* Use primary bond PCI as device. */ - if (sh->bond_dev == UINT16_MAX) { - sh->bond_dev = eth_dev->data->port_id; - eth_dev->device = dpdk_dev; - } else { - eth_dev->device = rte_eth_devices[sh->bond_dev].device; - } - } + 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)) { @@ -1499,11 +1702,12 @@ 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, @@ -1533,6 +1737,14 @@ 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) { @@ -1557,7 +1769,10 @@ 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; } @@ -1586,10 +1801,15 @@ 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) { @@ -1614,15 +1834,16 @@ 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); @@ -1643,9 +1864,12 @@ 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; @@ -1708,9 +1932,13 @@ 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 @@ -1718,20 +1946,23 @@ 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")) @@ -1755,15 +1986,15 @@ 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; @@ -1771,18 +2002,12 @@ 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; } - 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"); @@ -1791,32 +2016,99 @@ 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, 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; - 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; } +static void +mlx5_os_config_default(struct mlx5_dev_config *config) +{ + memset(config, 0, sizeof(*config)); + config->mps = MLX5_ARG_UNSET; + config->dbnc = MLX5_ARG_UNSET; + 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->dv_esw_en = 1; + config->dv_flow_en = 1; + config->decap_en = 1; + config->log_hp_size = MLX5_ARG_UNSET; +} + /** - * 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; /* @@ -1846,16 +2138,11 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct mlx5_dev_spawn_data *list = NULL; struct mlx5_dev_config dev_config; unsigned int dev_config_vf; - int ret; + 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 (rte_eal_process_type() == RTE_PROC_PRIMARY) - mlx5_pmd_socket_init(); - ret = mlx5_init_once(); - if (ret) { - DRV_LOG(ERR, "unable to init PMD global data: %s", - strerror(rte_errno)); - return -rte_errno; - } errno = 0; ibv_list = mlx5_glue->get_device_list(&ret); if (!ibv_list) { @@ -1877,7 +2164,8 @@ 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, @@ -1894,23 +2182,28 @@ 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_get_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) { @@ -1918,8 +2211,8 @@ 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; @@ -1981,6 +2274,7 @@ 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]; @@ -2028,6 +2322,8 @@ 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; @@ -2069,6 +2365,7 @@ 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]; @@ -2160,6 +2457,18 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, 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); /* @@ -2182,30 +2491,36 @@ mlx5_os_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, 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)); + mlx5_os_config_default(&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; + 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); + &dev_config, + ð_da); if (!list[i].eth_dev) { if (rte_errno != EBUSY && rte_errno != EEXIST) break; @@ -2222,8 +2537,8 @@ 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. */ @@ -2258,6 +2573,144 @@ exit: return ret; } +static int +mlx5_os_parse_eth_devargs(struct rte_device *dev, + struct rte_eth_devargs *eth_da) +{ + int ret = 0; + + if (dev->devargs == NULL) + return 0; + memset(eth_da, 0, sizeof(*eth_da)); + /* Parse representor information first from class argument. */ + if (dev->devargs->cls_str) + ret = rte_eth_devargs_parse(dev->devargs->cls_str, eth_da); + if (ret != 0) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + dev->devargs->cls_str); + return -rte_errno; + } + if (eth_da->type == RTE_ETH_REPRESENTOR_NONE) { + /* Parse legacy device argument */ + ret = rte_eth_devargs_parse(dev->devargs->args, eth_da); + if (ret) { + DRV_LOG(ERR, "failed to parse device arguments: %s", + dev->devargs->args); + return -rte_errno; + } + } + return 0; +} + +/** + * Callback to register a PCI device. + * + * This function spawns Ethernet devices out of a given PCI device. + * + * @param[in] pci_dev + * PCI device information. + * + * @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) +{ + 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); + 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, + eth_da.ports[p]); + } else { + ret = mlx5_os_pci_probe_pf(pci_dev, 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) +{ + 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_auxiliary_device *adev = RTE_DEV_TO_AUXILIARY(dev); + struct rte_eth_dev *eth_dev; + int ret = 0; + + /* Parse ethdev devargs. */ + ret = mlx5_os_parse_eth_devargs(dev, ð_da); + if (ret != 0) + return ret; + /* Set default config data. */ + mlx5_os_config_default(&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; + 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 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; + 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; + eth_dev->data->numa_node = dev->numa_node; + } + rte_eth_dev_probing_finish(eth_dev); + return 0; +} + +/** + * Net class driver callback to probe a device. + * + * This function probe PCI bus device(s) or a single SF on auxiliary bus. + * + * @param[in] dev + * Pointer to the generic device. + * + * @return + * 0 on success, the function cannot fail. + */ +int +mlx5_os_net_probe(struct rte_device *dev) +{ + int ret; + + if (rte_eal_process_type() == RTE_PROC_PRIMARY) + mlx5_pmd_socket_init(); + ret = mlx5_init_once(); + if (ret) { + 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)); + else + return mlx5_os_auxiliary_probe(dev); +} + static int mlx5_config_doorbell_mapping_env(const struct mlx5_dev_config *config) { @@ -2345,7 +2798,6 @@ 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" @@ -2494,8 +2946,8 @@ 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,