X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;ds=inline;f=drivers%2Fnet%2Fmlx5%2Fmlx5.c;h=237d05bc77a608163ab19ee215cdd21c1e951bf1;hb=5382d28c2110ceac10051e32a0be97bb59b82555;hp=ac6e841fda71a89ff93444b19a887bc2a2833f1b;hpb=17e19bc4dde71079a18b188ab8523035e6df0b3e;p=dpdk.git diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index ac6e841fda..237d05bc77 100644 --- a/drivers/net/mlx5/mlx5.c +++ b/drivers/net/mlx5/mlx5.c @@ -101,15 +101,24 @@ /* Allow L3 VXLAN flow creation. */ #define MLX5_L3_VXLAN_EN "l3_vxlan_en" +/* Activate DV E-Switch flow steering. */ +#define MLX5_DV_ESW_EN "dv_esw_en" + /* Activate DV flow steering. */ #define MLX5_DV_FLOW_EN "dv_flow_en" /* Activate Netlink support in VF mode. */ #define MLX5_VF_NL_EN "vf_nl_en" +/* Enable extending memsegs when creating a MR. */ +#define MLX5_MR_EXT_MEMSEG_EN "mr_ext_memseg_en" + /* Select port representors to instantiate. */ #define MLX5_REPRESENTOR "representor" +/* Device parameter to configure the maximum number of dump files per queue. */ +#define MLX5_MAX_DUMP_FILES_NUM "max_dump_files_num" + #ifndef HAVE_IBV_MLX5_MOD_MPW #define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2) #define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3) @@ -127,6 +136,9 @@ struct mlx5_shared_data *mlx5_shared_data; /* Spinlock for mlx5_shared_data allocation. */ static rte_spinlock_t mlx5_shared_data_lock = RTE_SPINLOCK_INITIALIZER; +/* Process local data for secondary processes. */ +static struct mlx5_local_data mlx5_local_data; + /** Driver-specific log messages type. */ int mlx5_logtype; @@ -138,18 +150,102 @@ struct mlx5_dev_spawn_data { struct mlx5_switch_info info; /**< Switch information. */ struct ibv_device *ibv_dev; /**< Associated IB device. */ struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */ + struct rte_pci_device *pci_dev; /**< Backend PCI device. */ }; static LIST_HEAD(, mlx5_ibv_shared) mlx5_ibv_list = LIST_HEAD_INITIALIZER(); static pthread_mutex_t mlx5_ibv_list_mutex = PTHREAD_MUTEX_INITIALIZER; +/** + * Initialize the counters management structure. + * + * @param[in] sh + * Pointer to mlx5_ibv_shared object to free + */ +static void +mlx5_flow_counters_mng_init(struct mlx5_ibv_shared *sh) +{ + uint8_t i; + + TAILQ_INIT(&sh->cmng.flow_counters); + for (i = 0; i < RTE_DIM(sh->cmng.ccont); ++i) + TAILQ_INIT(&sh->cmng.ccont[i].pool_list); +} + +/** + * Destroy all the resources allocated for a counter memory management. + * + * @param[in] mng + * Pointer to the memory management structure. + */ +static void +mlx5_flow_destroy_counter_stat_mem_mng(struct mlx5_counter_stats_mem_mng *mng) +{ + uint8_t *mem = (uint8_t *)(uintptr_t)mng->raws[0].data; + + LIST_REMOVE(mng, next); + claim_zero(mlx5_devx_cmd_destroy(mng->dm)); + claim_zero(mlx5_glue->devx_umem_dereg(mng->umem)); + rte_free(mem); +} + +/** + * Close and release all the resources of the counters management. + * + * @param[in] sh + * Pointer to mlx5_ibv_shared object to free. + */ +static void +mlx5_flow_counters_mng_close(struct mlx5_ibv_shared *sh) +{ + struct mlx5_counter_stats_mem_mng *mng; + uint8_t i; + int j; + + for (i = 0; i < RTE_DIM(sh->cmng.ccont); ++i) { + struct mlx5_flow_counter_pool *pool; + uint32_t batch = !!(i % 2); + + if (!sh->cmng.ccont[i].pools) + continue; + pool = TAILQ_FIRST(&sh->cmng.ccont[i].pool_list); + while (pool) { + if (batch) { + if (pool->min_dcs) + claim_zero + (mlx5_devx_cmd_destroy(pool->min_dcs)); + } + for (j = 0; j < MLX5_COUNTERS_PER_POOL; ++j) { + if (pool->counters_raw[j].action) + claim_zero + (mlx5_glue->destroy_flow_action + (pool->counters_raw[j].action)); + if (!batch && pool->counters_raw[j].dcs) + claim_zero(mlx5_devx_cmd_destroy + (pool->counters_raw[j].dcs)); + } + TAILQ_REMOVE(&sh->cmng.ccont[i].pool_list, pool, + next); + rte_free(pool); + pool = TAILQ_FIRST(&sh->cmng.ccont[i].pool_list); + } + rte_free(sh->cmng.ccont[i].pools); + } + mng = LIST_FIRST(&sh->cmng.mem_mngs); + while (mng) { + mlx5_flow_destroy_counter_stat_mem_mng(mng); + mng = LIST_FIRST(&sh->cmng.mem_mngs); + } + memset(&sh->cmng, 0, sizeof(sh->cmng)); +} + /** * Allocate shared IB device context. If there is multiport device the * master and representors will share this context, if there is single * port dedicated IB device, the context will be used by only given * port due to unification. * - * Routine first searches the context for the spesified IB device name, + * Routine first searches the context for the specified IB device name, * if found the shared context assumed and reference counter is incremented. * If no context found the new one is created and initialized with specified * IB device context and parameters. @@ -166,6 +262,7 @@ mlx5_alloc_shared_ibctx(const struct mlx5_dev_spawn_data *spawn) { struct mlx5_ibv_shared *sh; int err = 0; + uint32_t i; assert(spawn); /* Secondary process should not create the shared context. */ @@ -178,7 +275,7 @@ mlx5_alloc_shared_ibctx(const struct mlx5_dev_spawn_data *spawn) goto exit; } } - /* No device found, we have to create new sharted context. */ + /* No device found, we have to create new shared context. */ assert(spawn->max_port); sh = rte_zmalloc("ethdev shared ib context", sizeof(struct mlx5_ibv_shared) + @@ -215,12 +312,38 @@ mlx5_alloc_shared_ibctx(const struct mlx5_dev_spawn_data *spawn) sizeof(sh->ibdev_name)); strncpy(sh->ibdev_path, sh->ctx->device->ibdev_path, sizeof(sh->ibdev_path)); + sh->pci_dev = spawn->pci_dev; + pthread_mutex_init(&sh->intr_mutex, NULL); + /* + * Setting port_id to max unallowed value means + * there is no interrupt subhandler installed for + * the given port index i. + */ + for (i = 0; i < sh->max_port; i++) + sh->port[i].ih_port_id = RTE_MAX_ETHPORTS; sh->pd = mlx5_glue->alloc_pd(sh->ctx); if (sh->pd == NULL) { DRV_LOG(ERR, "PD allocation failure"); err = ENOMEM; goto error; } + /* + * Once the device is added to the list of memory event + * callback, its global MR cache table cannot be expanded + * on the fly because of deadlock. If it overflows, lookup + * should be done by searching MR list linearly, which is slow. + * + * At this point the device is not added to the memory + * event list yet, context is just being created. + */ + err = mlx5_mr_btree_init(&sh->mr.cache, + MLX5_MR_BTREE_CACHE_N * 2, + sh->pci_dev->device.numa_node); + if (err) { + err = rte_errno; + goto error; + } + mlx5_flow_counters_mng_init(sh); LIST_INSERT_HEAD(&mlx5_ibv_list, sh, next); exit: pthread_mutex_unlock(&mlx5_ibv_list_mutex); @@ -268,7 +391,19 @@ mlx5_free_shared_ibctx(struct mlx5_ibv_shared *sh) assert(rte_eal_process_type() == RTE_PROC_PRIMARY); if (--sh->refcnt) goto exit; + /* Release created Memory Regions. */ + mlx5_mr_release(sh); LIST_REMOVE(sh, next); + /* + * Ensure there is no async event handler installed. + * Only primary process handles async device events. + **/ + mlx5_flow_counters_mng_close(sh); + assert(!sh->intr_cnt); + if (sh->intr_cnt) + mlx5_intr_callback_unregister + (&sh->intr_handle, mlx5_dev_interrupt_handler, sh); + pthread_mutex_destroy(&sh->intr_mutex); if (sh->pd) claim_zero(mlx5_glue->dealloc_pd(sh->pd)); if (sh->ctx) @@ -278,14 +413,150 @@ exit: pthread_mutex_unlock(&mlx5_ibv_list_mutex); } +/** + * Initialize DR related data within private structure. + * Routine checks the reference counter and does actual + * resources creation/initialization only if counter is zero. + * + * @param[in] priv + * Pointer to the private device data structure. + * + * @return + * Zero on success, positive error code otherwise. + */ +static int +mlx5_alloc_shared_dr(struct mlx5_priv *priv) +{ +#ifdef HAVE_MLX5DV_DR + struct mlx5_ibv_shared *sh = priv->sh; + int err = 0; + void *domain; + + assert(sh); + if (sh->dv_refcnt) { + /* Shared DV/DR structures is already initialized. */ + sh->dv_refcnt++; + priv->dr_shared = 1; + return 0; + } + /* Reference counter is zero, we should initialize structures. */ + domain = mlx5_glue->dr_create_domain(sh->ctx, + MLX5DV_DR_DOMAIN_TYPE_NIC_RX); + if (!domain) { + DRV_LOG(ERR, "ingress mlx5dv_dr_create_domain failed"); + err = errno; + goto error; + } + sh->rx_domain = domain; + domain = mlx5_glue->dr_create_domain(sh->ctx, + MLX5DV_DR_DOMAIN_TYPE_NIC_TX); + if (!domain) { + DRV_LOG(ERR, "egress mlx5dv_dr_create_domain failed"); + err = errno; + goto error; + } + pthread_mutex_init(&sh->dv_mutex, NULL); + sh->tx_domain = domain; +#ifdef HAVE_MLX5DV_DR_ESWITCH + if (priv->config.dv_esw_en) { + domain = mlx5_glue->dr_create_domain + (sh->ctx, MLX5DV_DR_DOMAIN_TYPE_FDB); + if (!domain) { + DRV_LOG(ERR, "FDB mlx5dv_dr_create_domain failed"); + err = errno; + goto error; + } + sh->fdb_domain = domain; + sh->esw_drop_action = mlx5_glue->dr_create_flow_action_drop(); + } +#endif + sh->dv_refcnt++; + priv->dr_shared = 1; + return 0; + +error: + /* Rollback the created objects. */ + if (sh->rx_domain) { + mlx5_glue->dr_destroy_domain(sh->rx_domain); + sh->rx_domain = NULL; + } + if (sh->tx_domain) { + mlx5_glue->dr_destroy_domain(sh->tx_domain); + sh->tx_domain = NULL; + } + if (sh->fdb_domain) { + 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; + } + return err; +#else + (void)priv; + return 0; +#endif +} /** - * Prepare shared data between primary and secondary process. + * Destroy DR related data within private structure. + * + * @param[in] priv + * Pointer to the private device data structure. */ static void -mlx5_prepare_shared_data(void) +mlx5_free_shared_dr(struct mlx5_priv *priv) +{ +#ifdef HAVE_MLX5DV_DR + struct mlx5_ibv_shared *sh; + + if (!priv->dr_shared) + return; + priv->dr_shared = 0; + sh = priv->sh; + assert(sh); + assert(sh->dv_refcnt); + if (sh->dv_refcnt && --sh->dv_refcnt) + return; + if (sh->rx_domain) { + mlx5_glue->dr_destroy_domain(sh->rx_domain); + sh->rx_domain = NULL; + } + if (sh->tx_domain) { + mlx5_glue->dr_destroy_domain(sh->tx_domain); + sh->tx_domain = NULL; + } +#ifdef HAVE_MLX5DV_DR_ESWITCH + if (sh->fdb_domain) { + 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; + } +#endif + pthread_mutex_destroy(&sh->dv_mutex); +#else + (void)priv; +#endif +} + +/** + * Initialize shared data between primary and secondary process. + * + * A memzone is reserved by primary process and secondary processes attach to + * the memzone. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +static int +mlx5_init_shared_data(void) { const struct rte_memzone *mz; + int ret = 0; rte_spinlock_lock(&mlx5_shared_data_lock); if (mlx5_shared_data == NULL) { @@ -294,22 +565,31 @@ mlx5_prepare_shared_data(void) mz = rte_memzone_reserve(MZ_MLX5_PMD_SHARED_DATA, sizeof(*mlx5_shared_data), SOCKET_ID_ANY, 0); + if (mz == NULL) { + DRV_LOG(ERR, + "Cannot allocate mlx5 shared data\n"); + ret = -rte_errno; + goto error; + } + mlx5_shared_data = mz->addr; + memset(mlx5_shared_data, 0, sizeof(*mlx5_shared_data)); + rte_spinlock_init(&mlx5_shared_data->lock); } else { /* Lookup allocated shared memory. */ mz = rte_memzone_lookup(MZ_MLX5_PMD_SHARED_DATA); + if (mz == NULL) { + DRV_LOG(ERR, + "Cannot attach mlx5 shared data\n"); + ret = -rte_errno; + goto error; + } + mlx5_shared_data = mz->addr; + memset(&mlx5_local_data, 0, sizeof(mlx5_local_data)); } - if (mz == NULL) - rte_panic("Cannot allocate mlx5 shared data\n"); - mlx5_shared_data = mz->addr; - /* Initialize shared data. */ - if (rte_eal_process_type() == RTE_PROC_PRIMARY) { - LIST_INIT(&mlx5_shared_data->mem_event_cb_list); - rte_rwlock_init(&mlx5_shared_data->mem_event_rwlock); - } - rte_mem_event_callback_register("MLX5_MEM_EVENT_CB", - mlx5_mr_mem_event_cb, NULL); } +error: rte_spinlock_unlock(&mlx5_shared_data_lock); + return ret; } /** @@ -385,6 +665,54 @@ mlx5_free_verbs_buf(void *ptr, void *data __rte_unused) rte_free(ptr); } +/** + * Initialize process private data structure. + * + * @param dev + * Pointer to Ethernet device structure. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +mlx5_proc_priv_init(struct rte_eth_dev *dev) +{ + struct mlx5_priv *priv = dev->data->dev_private; + struct mlx5_proc_priv *ppriv; + size_t ppriv_size; + + /* + * UAR register table follows the process private structure. BlueFlame + * registers for Tx queues are stored in the table. + */ + ppriv_size = + sizeof(struct mlx5_proc_priv) + priv->txqs_n * sizeof(void *); + ppriv = rte_malloc_socket("mlx5_proc_priv", ppriv_size, + RTE_CACHE_LINE_SIZE, dev->device->numa_node); + if (!ppriv) { + rte_errno = ENOMEM; + return -rte_errno; + } + ppriv->uar_table_sz = ppriv_size; + dev->process_private = ppriv; + return 0; +} + +/** + * Un-initialize process private data structure. + * + * @param dev + * Pointer to Ethernet device structure. + */ +static void +mlx5_proc_priv_uninit(struct rte_eth_dev *dev) +{ + if (!dev->process_private) + return; + rte_free(dev->process_private); + dev->process_private = NULL; +} + /** * DPDK callback to close the device. * @@ -402,7 +730,7 @@ mlx5_dev_close(struct rte_eth_dev *dev) DRV_LOG(DEBUG, "port %u closing device \"%s\"", dev->data->port_id, - ((priv->ctx != NULL) ? priv->ctx->device->name : "")); + ((priv->sh->ctx != NULL) ? priv->sh->ctx->device->name : "")); /* In case mlx5_dev_stop() has not been called. */ mlx5_dev_interrupt_handler_uninstall(dev); mlx5_traffic_disable(dev); @@ -410,6 +738,9 @@ mlx5_dev_close(struct rte_eth_dev *dev) /* Prevent crashes when queues are still in use. */ dev->rx_pkt_burst = removed_rx_burst; dev->tx_pkt_burst = removed_tx_burst; + rte_wmb(); + /* Disable datapath on secondary process. */ + mlx5_mp_req_stop_rxtx(dev); if (priv->rxqs != NULL) { /* XXX race condition if mlx5_rx_burst() is still running. */ usleep(1000); @@ -426,26 +757,34 @@ mlx5_dev_close(struct rte_eth_dev *dev) priv->txqs_n = 0; priv->txqs = NULL; } + mlx5_proc_priv_uninit(dev); mlx5_mprq_free_mp(dev); - mlx5_mr_release(dev); + /* Remove from memory callback device list. */ + rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock); assert(priv->sh); - if (priv->sh) - mlx5_free_shared_ibctx(priv->sh); - priv->sh = NULL; + LIST_REMOVE(priv->sh, mem_event_cb); + rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock); + mlx5_free_shared_dr(priv); if (priv->rss_conf.rss_key != NULL) rte_free(priv->rss_conf.rss_key); if (priv->reta_idx != NULL) rte_free(priv->reta_idx); - if (priv->primary_socket) - mlx5_socket_uninit(dev); if (priv->config.vf) mlx5_nl_mac_addr_flush(dev); if (priv->nl_socket_route >= 0) close(priv->nl_socket_route); if (priv->nl_socket_rdma >= 0) close(priv->nl_socket_rdma); - if (priv->tcf_context) - mlx5_flow_tcf_context_destroy(priv->tcf_context); + if (priv->sh) { + /* + * Free the shared context in last turn, because the cleanup + * routines above may use some shared fields, like + * mlx5_nl_mac_addr_flush() uses ibdev_path for retrieveing + * ifindex if Netlink fails. + */ + mlx5_free_shared_ibctx(priv->sh); + priv->sh = NULL; + } ret = mlx5_hrxq_ibv_verify(dev); if (ret) DRV_LOG(WARNING, "port %u some hash Rx queue still remain", @@ -476,17 +815,15 @@ mlx5_dev_close(struct rte_eth_dev *dev) dev->data->port_id); if (priv->domain_id != RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) { unsigned int c = 0; - unsigned int i = mlx5_dev_to_port_id(dev->device, NULL, 0); - uint16_t port_id[i]; + uint16_t port_id; - i = RTE_MIN(mlx5_dev_to_port_id(dev->device, port_id, i), i); - while (i--) { + RTE_ETH_FOREACH_DEV_OF(port_id, dev->device) { struct mlx5_priv *opriv = - rte_eth_devices[port_id[i]].data->dev_private; + rte_eth_devices[port_id].data->dev_private; if (!opriv || opriv->domain_id != priv->domain_id || - &rte_eth_devices[port_id[i]] == dev) + &rte_eth_devices[port_id] == dev) continue; ++c; } @@ -522,6 +859,7 @@ const struct eth_dev_ops mlx5_dev_ops = { .xstats_get_names = mlx5_xstats_get_names, .fw_version_get = mlx5_fw_version_get, .dev_infos_get = mlx5_dev_infos_get, + .read_clock = mlx5_read_clock, .dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get, .vlan_filter_set = mlx5_vlan_filter_set, .rx_queue_setup = mlx5_rx_queue_setup, @@ -669,8 +1007,14 @@ mlx5_args_check(const char *key, const char *val, void *opaque) config->l3_vxlan_en = !!tmp; } else if (strcmp(MLX5_VF_NL_EN, key) == 0) { config->vf_nl_en = !!tmp; + } else if (strcmp(MLX5_DV_ESW_EN, key) == 0) { + config->dv_esw_en = !!tmp; } else if (strcmp(MLX5_DV_FLOW_EN, key) == 0) { config->dv_flow_en = !!tmp; + } else if (strcmp(MLX5_MR_EXT_MEMSEG_EN, key) == 0) { + config->mr_ext_memseg_en = !!tmp; + } else if (strcmp(MLX5_MAX_DUMP_FILES_NUM, key) == 0) { + config->max_dump_files_num = tmp; } else { DRV_LOG(WARNING, "%s: unknown parameter", key); rte_errno = EINVAL; @@ -711,8 +1055,11 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs) MLX5_RX_VEC_EN, MLX5_L3_VXLAN_EN, MLX5_VF_NL_EN, + MLX5_DV_ESW_EN, MLX5_DV_FLOW_EN, + MLX5_MR_EXT_MEMSEG_EN, MLX5_REPRESENTOR, + MLX5_MAX_DUMP_FILES_NUM, NULL, }; struct rte_kvargs *kvlist; @@ -723,8 +1070,10 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs) return 0; /* Following UGLY cast is done to pass checkpatch. */ kvlist = rte_kvargs_parse(devargs->args, params); - if (kvlist == NULL) - return 0; + if (kvlist == NULL) { + rte_errno = EINVAL; + return -rte_errno; + } /* Process parameters. */ for (i = 0; (params[i] != NULL); ++i) { if (rte_kvargs_count(kvlist, params[i])) { @@ -743,119 +1092,56 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs) static struct rte_pci_driver mlx5_driver; -/* - * Reserved UAR address space for TXQ UAR(hw doorbell) mapping, process - * local resource used by both primary and secondary to avoid duplicate - * reservation. - * The space has to be available on both primary and secondary process, - * TXQ UAR maps to this area using fixed mmap w/o double check. - */ -static void *uar_base; - -static int -find_lower_va_bound(const struct rte_memseg_list *msl, - const struct rte_memseg *ms, void *arg) -{ - void **addr = arg; - - if (msl->external) - return 0; - if (*addr == NULL) - *addr = ms->addr; - else - *addr = RTE_MIN(*addr, ms->addr); - - return 0; -} - -/** - * Reserve UAR address space for primary process. - * - * @param[in] dev - * Pointer to Ethernet device. - * - * @return - * 0 on success, a negative errno value otherwise and rte_errno is set. - */ -static int -mlx5_uar_init_primary(struct rte_eth_dev *dev) -{ - struct mlx5_priv *priv = dev->data->dev_private; - void *addr = (void *)0; - - if (uar_base) { /* UAR address space mapped. */ - priv->uar_base = uar_base; - return 0; - } - /* find out lower bound of hugepage segments */ - rte_memseg_walk(find_lower_va_bound, &addr); - - /* keep distance to hugepages to minimize potential conflicts. */ - addr = RTE_PTR_SUB(addr, (uintptr_t)(MLX5_UAR_OFFSET + MLX5_UAR_SIZE)); - /* anonymous mmap, no real memory consumption. */ - addr = mmap(addr, MLX5_UAR_SIZE, - PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - if (addr == MAP_FAILED) { - DRV_LOG(ERR, - "port %u failed to reserve UAR address space, please" - " adjust MLX5_UAR_SIZE or try --base-virtaddr", - dev->data->port_id); - rte_errno = ENOMEM; - return -rte_errno; - } - /* Accept either same addr or a new addr returned from mmap if target - * range occupied. - */ - DRV_LOG(INFO, "port %u reserved UAR address space: %p", - dev->data->port_id, addr); - priv->uar_base = addr; /* for primary and secondary UAR re-mmap. */ - uar_base = addr; /* process local, don't reserve again. */ - return 0; -} - /** - * Reserve UAR address space for secondary process, align with - * primary process. + * PMD global initialization. * - * @param[in] dev - * Pointer to Ethernet device. + * Independent from individual device, this function initializes global + * per-PMD data structures distinguishing primary and secondary processes. + * Hence, each initialization is called once per a process. * * @return * 0 on success, a negative errno value otherwise and rte_errno is set. */ static int -mlx5_uar_init_secondary(struct rte_eth_dev *dev) +mlx5_init_once(void) { - struct mlx5_priv *priv = dev->data->dev_private; - void *addr; + struct mlx5_shared_data *sd; + struct mlx5_local_data *ld = &mlx5_local_data; + int ret = 0; - assert(priv->uar_base); - if (uar_base) { /* already reserved. */ - assert(uar_base == priv->uar_base); - return 0; - } - /* anonymous mmap, no real memory consumption. */ - addr = mmap(priv->uar_base, MLX5_UAR_SIZE, - PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); - if (addr == MAP_FAILED) { - DRV_LOG(ERR, "port %u UAR mmap failed: %p size: %llu", - dev->data->port_id, priv->uar_base, MLX5_UAR_SIZE); - rte_errno = ENXIO; - return -rte_errno; - } - if (priv->uar_base != addr) { - DRV_LOG(ERR, - "port %u UAR address %p size %llu occupied, please" - " adjust MLX5_UAR_OFFSET or try EAL parameter" - " --base-virtaddr", - dev->data->port_id, priv->uar_base, MLX5_UAR_SIZE); - rte_errno = ENXIO; + if (mlx5_init_shared_data()) return -rte_errno; + sd = mlx5_shared_data; + assert(sd); + rte_spinlock_lock(&sd->lock); + switch (rte_eal_process_type()) { + case RTE_PROC_PRIMARY: + if (sd->init_done) + break; + LIST_INIT(&sd->mem_event_cb_list); + rte_rwlock_init(&sd->mem_event_rwlock); + rte_mem_event_callback_register("MLX5_MEM_EVENT_CB", + mlx5_mr_mem_event_cb, NULL); + ret = mlx5_mp_init_primary(); + if (ret) + goto out; + sd->init_done = true; + break; + case RTE_PROC_SECONDARY: + if (ld->init_done) + break; + ret = mlx5_mp_init_secondary(); + if (ret) + goto out; + ++sd->secondary_cnt; + ld->init_done = true; + break; + default: + break; } - uar_base = addr; /* process local, don't reserve again */ - DRV_LOG(INFO, "port %u reserved UAR address space: %p", - dev->data->port_id, addr); - return 0; +out: + rte_spinlock_unlock(&sd->lock); + return ret; } /** @@ -899,7 +1185,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, 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 ether_addr mac; + struct rte_ether_addr mac; char name[RTE_ETH_NAME_MAX_LEN]; int own_domain_id = 0; uint16_t port_id; @@ -936,8 +1222,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, rte_errno = EEXIST; return NULL; } - /* Prepare shared data between primary and secondary process. */ - mlx5_prepare_shared_data(); DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name); if (rte_eal_process_type() == RTE_PROC_SECONDARY) { eth_dev = rte_eth_dev_attach_secondary(name); @@ -948,15 +1232,15 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, } eth_dev->device = dpdk_dev; eth_dev->dev_ops = &mlx5_dev_sec_ops; - err = mlx5_uar_init_secondary(eth_dev); + err = mlx5_proc_priv_init(eth_dev); if (err) return NULL; /* Receive command fd from primary process */ - err = mlx5_socket_connect(eth_dev); + err = mlx5_mp_req_verbs_cmd_fd(eth_dev); if (err < 0) return NULL; /* Remap UAR for Tx queues. */ - err = mlx5_tx_uar_remap(eth_dev, err); + err = mlx5_tx_uar_init_secondary(eth_dev, err); if (err) return NULL; /* @@ -1095,11 +1379,8 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, goto error; } priv->sh = sh; - priv->ctx = sh->ctx; priv->ibv_port = spawn->ibv_port; - priv->device_attr = sh->device_attr; - priv->pd = sh->pd; - priv->mtu = ETHER_MTU; + priv->mtu = RTE_ETHER_MTU; #ifndef RTE_ARCH_64 /* Initialize UAR access locks for 32bit implementations. */ rte_spinlock_init(&priv->uar_lock_cq); @@ -1117,7 +1398,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, * Currently we 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 exapmple, let's have the IB device port 10, it has + * 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 @@ -1133,22 +1414,16 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, * Look for sibling devices in order to reuse their switch domain * if any, otherwise allocate one. */ - i = mlx5_dev_to_port_id(dpdk_dev, NULL, 0); - if (i > 0) { - uint16_t port_id[i]; - - i = RTE_MIN(mlx5_dev_to_port_id(dpdk_dev, port_id, i), i); - while (i--) { - const struct mlx5_priv *opriv = - rte_eth_devices[port_id[i]].data->dev_private; + RTE_ETH_FOREACH_DEV_OF(port_id, dpdk_dev) { + const struct mlx5_priv *opriv = + rte_eth_devices[port_id].data->dev_private; - if (!opriv || - opriv->domain_id == - RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) - continue; - priv->domain_id = opriv->domain_id; - break; - } + if (!opriv || + opriv->domain_id == + RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) + continue; + priv->domain_id = opriv->domain_id; + break; } if (priv->domain_id == RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) { err = rte_eth_switch_domain_alloc(&priv->domain_id); @@ -1256,6 +1531,8 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, DRV_LOG(WARNING, "Multi-Packet RQ isn't supported"); config.mprq.enabled = 0; } + if (config.max_dump_files_num == 0) + config.max_dump_files_num = 128; eth_dev = rte_eth_dev_allocate(name); if (eth_dev == NULL) { DRV_LOG(ERR, "can not allocate rte ethdev"); @@ -1272,11 +1549,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, priv->dev_data = eth_dev->data; eth_dev->data->mac_addrs = priv->mac; eth_dev->device = dpdk_dev; - err = mlx5_uar_init_primary(eth_dev); - if (err) { - err = rte_errno; - goto error; - } /* Configure the first MAC address by default. */ if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) { DRV_LOG(ERR, @@ -1320,34 +1592,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0)); if (config.vf && config.vf_nl_en) mlx5_nl_mac_addr_sync(eth_dev); - priv->tcf_context = mlx5_flow_tcf_context_create(); - if (!priv->tcf_context) { - err = -rte_errno; - DRV_LOG(WARNING, - "flow rules relying on switch offloads will not be" - " supported: cannot open libmnl socket: %s", - strerror(rte_errno)); - } else { - struct rte_flow_error error; - unsigned int ifindex = mlx5_ifindex(eth_dev); - - if (!ifindex) { - err = -rte_errno; - error.message = - "cannot retrieve network interface index"; - } else { - err = mlx5_flow_tcf_init(priv->tcf_context, - ifindex, &error); - } - if (err) { - DRV_LOG(WARNING, - "flow rules relying on switch offloads will" - " not be supported: %s: %s", - error.message, strerror(rte_errno)); - mlx5_flow_tcf_context_destroy(priv->tcf_context); - priv->tcf_context = NULL; - } - } TAILQ_INIT(&priv->flows); TAILQ_INIT(&priv->ctrl_flows); /* Hint libmlx5 to use PMD allocator for data plane resources */ @@ -1365,12 +1609,33 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, mlx5_set_link_up(eth_dev); /* * Even though the interrupt handler is not installed yet, - * interrupts will still trigger on the asyn_fd from + * interrupts will still trigger on the async_fd from * Verbs context returned by ibv_open_device(). */ mlx5_link_update(eth_dev, 0); +#ifdef HAVE_IBV_DEVX_OBJ + if (config.devx) { + err = mlx5_devx_cmd_query_hca_attr(sh->ctx, &config.hca_attr); + if (err) { + err = -err; + goto error; + } + } +#endif +#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 /* Store device configuration on private structure. */ priv->config = config; + if (config.dv_flow_en) { + err = mlx5_alloc_shared_dr(priv); + if (err) + goto error; + } /* Supported Verbs flow priority number detection. */ err = mlx5_flow_discover_priorities(eth_dev); if (err < 0) { @@ -1378,33 +1643,20 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev, goto error; } priv->config.flow_prio = err; - /* - * Once the device is added to the list of memory event - * callback, its global MR cache table cannot be expanded - * on the fly because of deadlock. If it overflows, lookup - * should be done by searching MR list linearly, which is slow. - */ - err = mlx5_mr_btree_init(&priv->mr.cache, - MLX5_MR_BTREE_CACHE_N * 2, - eth_dev->device->numa_node); - if (err) { - err = rte_errno; - goto error; - } /* Add device to memory callback list. */ rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock); LIST_INSERT_HEAD(&mlx5_shared_data->mem_event_cb_list, - priv, mem_event_cb); + sh, mem_event_cb); rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock); return eth_dev; error: if (priv) { + if (priv->sh) + mlx5_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->tcf_context) - mlx5_flow_tcf_context_destroy(priv->tcf_context); if (own_domain_id) claim_zero(rte_eth_switch_domain_free(priv->domain_id)); rte_free(priv); @@ -1500,6 +1752,12 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct mlx5_dev_config dev_config; int ret; + ret = mlx5_init_once(); + if (ret) { + DRV_LOG(ERR, "unable to init PMD global data: %s", + strerror(rte_errno)); + return -rte_errno; + } assert(pci_drv == &mlx5_driver); errno = 0; ibv_list = mlx5_glue->get_device_list(&ret); @@ -1534,7 +1792,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, } ibv_match[nd] = NULL; if (!nd) { - /* No device macthes, just complain and bail out. */ + /* No device matches, just complain and bail out. */ mlx5_glue->free_device_list(ibv_list); DRV_LOG(WARNING, "no Verbs device matches PCI device " PCI_PRI_FMT "," @@ -1567,7 +1825,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, if (np > 1) { /* - * Signle IB device with multiple ports found, + * Single IB device with multiple ports found, * it may be E-Switch master device and representors. * We have to perform identification trough the ports. */ @@ -1579,6 +1837,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, list[ns].ibv_port = i; list[ns].ibv_dev = ibv_match[0]; list[ns].eth_dev = NULL; + list[ns].pci_dev = pci_dev; list[ns].ifindex = mlx5_nl_ifindex (nl_rdma, list[ns].ibv_dev->name, i); if (!list[ns].ifindex) { @@ -1645,17 +1904,46 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, list[ns].ibv_port = 1; list[ns].ibv_dev = ibv_match[i]; list[ns].eth_dev = NULL; + list[ns].pci_dev = pci_dev; list[ns].ifindex = 0; if (nl_rdma >= 0) list[ns].ifindex = mlx5_nl_ifindex (nl_rdma, list[ns].ibv_dev->name, 1); if (!list[ns].ifindex) { + char ifname[IF_NAMESIZE]; + /* - * No network interface index found for the - * specified device, it means there it is not - * a representor/master. + * Netlink failed, it may happen with old + * ib_core kernel driver (before 4.16). + * We can assume there is old driver because + * here we are processing single ports IB + * devices. Let's try sysfs to retrieve + * the ifindex. The method works for + * master device only. */ - continue; + if (nd > 1) { + /* + * Multiple devices found, assume + * representors, can not distinguish + * master/representor and retrieve + * ifindex via sysfs. + */ + continue; + } + ret = mlx5_get_master_ifname + (ibv_match[i]->ibdev_path, &ifname); + if (!ret) + list[ns].ifindex = + if_nametoindex(ifname); + if (!list[ns].ifindex) { + /* + * No network interface index found + * for the specified device, it means + * there it is neither representor + * nor master. + */ + continue; + } } ret = -1; if (nl_route >= 0) @@ -1718,12 +2006,14 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, .txqs_vec = MLX5_ARG_UNSET, .inline_max_packet_sz = MLX5_ARG_UNSET, .vf_nl_en = 1, + .mr_ext_memseg_en = 1, .mprq = { .enabled = 0, /* Disabled by default. */ .stride_num_n = MLX5_MPRQ_STRIDE_NUM_N, .max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN, .min_rxqs_num = MLX5_MPRQ_MIN_RXQS, }, + .dv_esw_en = 1, }; /* Device specific configuration. */ switch (pci_dev->id.device_id) { @@ -1812,14 +2102,9 @@ static int mlx5_pci_remove(struct rte_pci_device *pci_dev) { uint16_t port_id; - struct rte_eth_dev *port; - for (port_id = 0; port_id < RTE_MAX_ETHPORTS; port_id++) { - port = &rte_eth_devices[port_id]; - if (port->state != RTE_ETH_DEV_UNUSED && - port->device == &pci_dev->device) - rte_eth_dev_close(port_id); - } + RTE_ETH_FOREACH_DEV_OF(port_id, &pci_dev->device) + rte_eth_dev_close(port_id); return 0; } @@ -1886,8 +2171,8 @@ static struct rte_pci_driver mlx5_driver = { .remove = mlx5_pci_remove, .dma_map = mlx5_dma_map, .dma_unmap = mlx5_dma_unmap, - .drv_flags = (RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV | - RTE_PCI_DRV_PROBE_AGAIN), + .drv_flags = RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_INTR_RMV | + RTE_PCI_DRV_PROBE_AGAIN, }; #ifdef RTE_IBVERBS_LINK_DLOPEN