X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=drivers%2Fnet%2Fmlx5%2Fmlx5.c;h=42b019ba6fd5d33ec940f761ca94fc88d6f88c95;hb=d561b5dc133fd98ddfa2dde237b1aa1d73e4df76;hp=4f776497cbe9ef620a13950aa58d8dcc5d422513;hpb=a6d83b6a9209a198fa5a7d2f9cbb37190e256f9c;p=dpdk.git diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index 4f776497cb..42b019ba6f 100644 --- a/drivers/net/mlx5/mlx5.c +++ b/drivers/net/mlx5/mlx5.c @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: BSD-3-Clause * Copyright 2015 6WIND S.A. - * Copyright 2015 Mellanox. + * Copyright 2015 Mellanox Technologies, Ltd */ #include @@ -13,6 +13,7 @@ #include #include #include +#include /* Verbs header. */ /* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */ @@ -68,6 +69,12 @@ /* Device parameter to enable hardware Rx vector. */ #define MLX5_RX_VEC_EN "rx_vec_en" +/* Allow L3 VXLAN flow creation. */ +#define MLX5_L3_VXLAN_EN "l3_vxlan_en" + +/* Activate Netlink support in VF mode. */ +#define MLX5_VF_NL_EN "vf_nl_en" + #ifndef HAVE_IBV_MLX5_MOD_MPW #define MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED (1 << 2) #define MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW (1 << 3) @@ -77,6 +84,9 @@ #define MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP (1 << 4) #endif +/** Driver-specific log messages type. */ +int mlx5_logtype; + /** * Retrieve integer value from environment variable. * @@ -132,7 +142,6 @@ mlx5_alloc_verbs_buf(size_t size, void *data) ret = rte_malloc_socket(__func__, size, alignment, socket); if (!ret && size) rte_errno = ENOMEM; - DEBUG("Extern alloc size: %lu, align: %lu: %p", size, alignment, ret); return ret; } @@ -148,7 +157,6 @@ static void mlx5_free_verbs_buf(void *ptr, void *data __rte_unused) { assert(data != NULL); - DEBUG("Extern free request: %p", ptr); rte_free(ptr); } @@ -167,9 +175,9 @@ mlx5_dev_close(struct rte_eth_dev *dev) unsigned int i; int ret; - DEBUG("%p: closing device \"%s\"", - (void *)dev, - ((priv->ctx != NULL) ? priv->ctx->device->name : "")); + DRV_LOG(DEBUG, "port %u closing device \"%s\"", + dev->data->port_id, + ((priv->ctx != NULL) ? priv->ctx->device->name : "")); /* In case mlx5_dev_stop() has not been called. */ mlx5_dev_interrupt_handler_uninstall(dev); mlx5_traffic_disable(dev); @@ -192,6 +200,7 @@ mlx5_dev_close(struct rte_eth_dev *dev) priv->txqs_n = 0; priv->txqs = NULL; } + mlx5_flow_delete_drop_queue(dev); if (priv->pd != NULL) { assert(priv->ctx != NULL); claim_zero(mlx5_glue->dealloc_pd(priv->pd)); @@ -204,30 +213,38 @@ mlx5_dev_close(struct rte_eth_dev *dev) 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 >= 0) + close(priv->nl_socket); ret = mlx5_hrxq_ibv_verify(dev); if (ret) - WARN("%p: some Hash Rx queue still remain", (void *)dev); + DRV_LOG(WARNING, "port %u some hash Rx queue still remain", + dev->data->port_id); ret = mlx5_ind_table_ibv_verify(dev); if (ret) - WARN("%p: some Indirection table still remain", (void *)dev); + DRV_LOG(WARNING, "port %u some indirection table still remain", + dev->data->port_id); ret = mlx5_rxq_ibv_verify(dev); if (ret) - WARN("%p: some Verbs Rx queue still remain", (void *)dev); + DRV_LOG(WARNING, "port %u some Verbs Rx queue still remain", + dev->data->port_id); ret = mlx5_rxq_verify(dev); if (ret) - WARN("%p: some Rx Queues still remain", (void *)dev); + DRV_LOG(WARNING, "port %u some Rx queues still remain", + dev->data->port_id); ret = mlx5_txq_ibv_verify(dev); if (ret) - WARN("%p: some Verbs Tx queue still remain", (void *)dev); + DRV_LOG(WARNING, "port %u some Verbs Tx queue still remain", + dev->data->port_id); ret = mlx5_txq_verify(dev); if (ret) - WARN("%p: some Tx Queues still remain", (void *)dev); + DRV_LOG(WARNING, "port %u some Tx queues still remain", + dev->data->port_id); ret = mlx5_flow_verify(dev); if (ret) - WARN("%p: some flows still remain", (void *)dev); - ret = mlx5_mr_verify(dev); - if (ret) - WARN("%p: some Memory Region still remain", (void *)dev); + DRV_LOG(WARNING, "port %u some flows still remain", + dev->data->port_id); memset(priv, 0, sizeof(*priv)); } @@ -260,6 +277,7 @@ const struct eth_dev_ops mlx5_dev_ops = { .mac_addr_remove = mlx5_mac_addr_remove, .mac_addr_add = mlx5_mac_addr_add, .mac_addr_set = mlx5_mac_addr_set, + .set_mc_addr_list = mlx5_set_mc_addr_list, .mtu_set = mlx5_dev_set_mtu, .vlan_strip_queue_set = mlx5_vlan_strip_queue_set, .vlan_offload_set = mlx5_vlan_offload_set, @@ -312,6 +330,7 @@ const struct eth_dev_ops mlx5_dev_ops_isolate = { .mac_addr_remove = mlx5_mac_addr_remove, .mac_addr_add = mlx5_mac_addr_add, .mac_addr_set = mlx5_mac_addr_set, + .set_mc_addr_list = mlx5_set_mc_addr_list, .mtu_set = mlx5_dev_set_mtu, .vlan_strip_queue_set = mlx5_vlan_strip_queue_set, .vlan_offload_set = mlx5_vlan_offload_set, @@ -379,7 +398,7 @@ mlx5_args_check(const char *key, const char *val, void *opaque) tmp = strtoul(val, NULL, 0); if (errno) { rte_errno = errno; - WARN("%s: \"%s\" is not a valid integer", key, val); + DRV_LOG(WARNING, "%s: \"%s\" is not a valid integer", key, val); return -rte_errno; } if (strcmp(MLX5_RXQ_CQE_COMP_EN, key) == 0) { @@ -398,8 +417,12 @@ mlx5_args_check(const char *key, const char *val, void *opaque) config->tx_vec_en = !!tmp; } else if (strcmp(MLX5_RX_VEC_EN, key) == 0) { config->rx_vec_en = !!tmp; + } else if (strcmp(MLX5_L3_VXLAN_EN, key) == 0) { + config->l3_vxlan_en = !!tmp; + } else if (strcmp(MLX5_VF_NL_EN, key) == 0) { + config->vf_nl_en = !!tmp; } else { - WARN("%s: unknown parameter", key); + DRV_LOG(WARNING, "%s: unknown parameter", key); rte_errno = EINVAL; return -rte_errno; } @@ -429,6 +452,8 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs) MLX5_TXQ_MAX_INLINE_LEN, MLX5_TX_VEC_EN, MLX5_RX_VEC_EN, + MLX5_L3_VXLAN_EN, + MLX5_VF_NL_EN, NULL, }; struct rte_kvargs *kvlist; @@ -468,6 +493,20 @@ static struct rte_pci_driver mlx5_driver; */ static void *uar_base; +static int +find_lower_va_bound(const struct rte_memseg_list *msl __rte_unused, + const struct rte_memseg *ms, void *arg) +{ + void **addr = arg; + + if (*addr == NULL) + *addr = ms->addr; + else + *addr = RTE_MIN(*addr, ms->addr); + + return 0; +} + /** * Reserve UAR address space for primary process. * @@ -482,36 +521,32 @@ mlx5_uar_init_primary(struct rte_eth_dev *dev) { struct priv *priv = dev->data->dev_private; void *addr = (void *)0; - int i; - const struct rte_mem_config *mcfg; if (uar_base) { /* UAR address space mapped. */ priv->uar_base = uar_base; return 0; } /* find out lower bound of hugepage segments */ - mcfg = rte_eal_get_configuration()->mem_config; - for (i = 0; i < RTE_MAX_MEMSEG && mcfg->memseg[i].addr; i++) { - if (addr) - addr = RTE_MIN(addr, mcfg->memseg[i].addr); - else - addr = mcfg->memseg[i].addr; - } + rte_memseg_walk(find_lower_va_bound, &addr); + /* keep distance to hugepages to minimize potential conflicts. */ addr = RTE_PTR_SUB(addr, 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) { - ERROR("Failed to reserve UAR address space, please adjust " - "MLX5_UAR_SIZE or try --base-virtaddr"); + 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. */ - INFO("Reserved UAR address space: %p", addr); + 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; @@ -542,20 +577,23 @@ mlx5_uar_init_secondary(struct rte_eth_dev *dev) addr = mmap(priv->uar_base, MLX5_UAR_SIZE, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (addr == MAP_FAILED) { - ERROR("UAR mmap failed: %p size: %llu", - priv->uar_base, MLX5_UAR_SIZE); + 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) { - ERROR("UAR address %p size %llu occupied, please adjust " - "MLX5_UAR_OFFSET or try EAL parameter --base-virtaddr", - priv->uar_base, MLX5_UAR_SIZE); + 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; return -rte_errno; } uar_base = addr; /* process local, don't reserve again */ - INFO("Reserved UAR address space: %p", addr); + DRV_LOG(INFO, "port %u reserved UAR address space: %p", + dev->data->port_id, addr); return 0; } @@ -582,9 +620,12 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, int err = 0; struct ibv_context *attr_ctx = NULL; struct ibv_device_attr_ex device_attr; + unsigned int vf; unsigned int mps; unsigned int cqe_comp; unsigned int tunnel_en = 0; + unsigned int swp = 0; + unsigned int verb_priorities = 0; int idx; int i; struct mlx5dv_context attrs_out = {0}; @@ -596,11 +637,11 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, /* Get mlx5_dev[] index. */ idx = mlx5_dev_idx(&pci_dev->addr); if (idx == -1) { - ERROR("this driver cannot support any more adapters"); + DRV_LOG(ERR, "this driver cannot support any more adapters"); err = ENOMEM; goto error; } - DEBUG("using driver device index %d", idx); + DRV_LOG(DEBUG, "using driver device index %d", idx); /* Save PCI address. */ mlx5_dev[idx].pci_addr = pci_dev->addr; list = mlx5_glue->get_device_list(&i); @@ -608,7 +649,8 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, assert(errno); err = errno; if (errno == ENOSYS) - ERROR("cannot list devices, is ib_uverbs loaded?"); + DRV_LOG(ERR, + "cannot list devices, is ib_uverbs loaded?"); goto error; } assert(i >= 0); @@ -620,7 +662,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct rte_pci_addr pci_addr; --i; - DEBUG("checking device \"%s\"", list[i]->name); + DRV_LOG(DEBUG, "checking device \"%s\"", list[i]->name); if (mlx5_ibv_device_to_pci_addr(list[i], &pci_addr)) continue; if ((pci_dev->addr.domain != pci_addr.domain) || @@ -628,27 +670,40 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, (pci_dev->addr.devid != pci_addr.devid) || (pci_dev->addr.function != pci_addr.function)) continue; - INFO("PCI information matches, using device \"%s\"", - list[i]->name); + DRV_LOG(INFO, "PCI information matches, using device \"%s\"", + list[i]->name); + vf = ((pci_dev->id.device_id == + PCI_DEVICE_ID_MELLANOX_CONNECTX4VF) || + (pci_dev->id.device_id == + PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF) || + (pci_dev->id.device_id == + PCI_DEVICE_ID_MELLANOX_CONNECTX5VF) || + (pci_dev->id.device_id == + PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF)); attr_ctx = mlx5_glue->open_device(list[i]); rte_errno = errno; err = rte_errno; break; } if (attr_ctx == NULL) { - mlx5_glue->free_device_list(list); switch (err) { case 0: - ERROR("cannot access device, is mlx5_ib loaded?"); + DRV_LOG(ERR, + "cannot access device, is mlx5_ib loaded?"); err = ENODEV; - goto error; + break; case EINVAL: - ERROR("cannot use device, are drivers up to date?"); - goto error; + DRV_LOG(ERR, + "cannot use device, are drivers up to date?"); + break; } + goto error; } ibv_dev = list[i]; - DEBUG("device opened"); + DRV_LOG(DEBUG, "device opened"); +#ifdef HAVE_IBV_MLX5_MOD_SWP + attrs_out.comp_mask |= MLX5DV_CONTEXT_MASK_SWP; +#endif /* * Multi-packet send is supported by ConnectX-4 Lx PF as well * as all ConnectX-5 devices. @@ -659,16 +714,21 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, mlx5_glue->dv_query_device(attr_ctx, &attrs_out); if (attrs_out.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) { if (attrs_out.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) { - DEBUG("Enhanced MPW is supported"); + DRV_LOG(DEBUG, "enhanced MPW is supported"); mps = MLX5_MPW_ENHANCED; } else { - DEBUG("MPW is supported"); + DRV_LOG(DEBUG, "MPW is supported"); mps = MLX5_MPW; } } else { - DEBUG("MPW isn't supported"); + DRV_LOG(DEBUG, "MPW isn't supported"); mps = MLX5_MPW_DISABLED; } +#ifdef HAVE_IBV_MLX5_MOD_SWP + if (attrs_out.comp_mask & MLX5DV_CONTEXT_MASK_SWP) + swp = attrs_out.sw_parsing_caps.sw_parsing_offloads; + DRV_LOG(DEBUG, "SWP support: %u", swp); +#endif if (RTE_CACHE_LINE_SIZE == 128 && !(attrs_out.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP)) cqe_comp = 0; @@ -681,15 +741,19 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, (attrs_out.tunnel_offloads_caps & MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE)); } - DEBUG("Tunnel offloading is %ssupported", tunnel_en ? "" : "not "); + DRV_LOG(DEBUG, "tunnel offloading is %ssupported", + tunnel_en ? "" : "not "); #else - WARN("Tunnel offloading disabled due to old OFED/rdma-core version"); + DRV_LOG(WARNING, + "tunnel offloading disabled due to old OFED/rdma-core version"); #endif - if (mlx5_glue->query_device_ex(attr_ctx, NULL, &device_attr)) { - err = errno; + err = mlx5_glue->query_device_ex(attr_ctx, NULL, &device_attr); + if (err) { + DEBUG("ibv_query_device_ex() failed"); goto error; } - INFO("%u port(s) detected", device_attr.orig_attr.phys_port_cnt); + DRV_LOG(INFO, "%u port(s) detected", + device_attr.orig_attr.phys_port_cnt); for (i = 0; i < device_attr.orig_attr.phys_port_cnt; i++) { char name[RTE_ETH_NAME_MAX_LEN]; int len; @@ -702,7 +766,6 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, struct rte_eth_dev *eth_dev = NULL; struct ibv_device_attr_ex device_attr_ex; struct ether_addr mac; - struct ibv_device_attr_ex device_attr; struct mlx5_dev_config config = { .cqe_comp = cqe_comp, .mps = mps, @@ -713,6 +776,8 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, .txq_inline = MLX5_ARG_UNSET, .txqs_inline = MLX5_ARG_UNSET, .inline_max_packet_sz = MLX5_ARG_UNSET, + .vf_nl_en = 1, + .swp = !!swp, }; len = snprintf(name, sizeof(name), PCI_PRI_FMT, @@ -724,7 +789,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, if (rte_eal_process_type() == RTE_PROC_SECONDARY) { eth_dev = rte_eth_dev_attach_secondary(name); if (eth_dev == NULL) { - ERROR("can not attach rte ethdev"); + DRV_LOG(ERR, "can not attach rte ethdev"); rte_errno = ENOMEM; err = rte_errno; goto error; @@ -732,16 +797,22 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, eth_dev->device = &pci_dev->device; eth_dev->dev_ops = &mlx5_dev_sec_ops; err = mlx5_uar_init_secondary(eth_dev); - if (err) + if (err) { + err = rte_errno; goto error; + } /* Receive command fd from primary process */ err = mlx5_socket_connect(eth_dev); - if (err) + if (err < 0) { + err = rte_errno; goto error; + } /* Remap UAR for Tx queues. */ err = mlx5_tx_uar_remap(eth_dev, err); - if (err) + if (err) { + err = rte_errno; goto error; + } /* * Ethdev pointer is still required as input since * the primary device is not accessible from the @@ -753,33 +824,34 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, mlx5_select_tx_function(eth_dev); continue; } - DEBUG("using port %u (%08" PRIx32 ")", port, test); + DRV_LOG(DEBUG, "using port %u (%08" PRIx32 ")", port, test); ctx = mlx5_glue->open_device(ibv_dev); if (ctx == NULL) { err = ENODEV; goto port_error; } - mlx5_glue->query_device_ex(ctx, NULL, &device_attr); /* Check port status. */ err = mlx5_glue->query_port(ctx, port, &port_attr); if (err) { - ERROR("port query failed: %s", strerror(err)); + DRV_LOG(ERR, "port query failed: %s", strerror(err)); goto port_error; } if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) { - ERROR("port %d is not configured in Ethernet mode", - port); + DRV_LOG(ERR, + "port %d is not configured in Ethernet mode", + port); err = EINVAL; goto port_error; } if (port_attr.state != IBV_PORT_ACTIVE) - DEBUG("port %d is not active: \"%s\" (%d)", - port, mlx5_glue->port_state_str(port_attr.state), - port_attr.state); + DRV_LOG(DEBUG, "port %d is not active: \"%s\" (%d)", + port, + mlx5_glue->port_state_str(port_attr.state), + port_attr.state); /* Allocate protection domain. */ pd = mlx5_glue->alloc_pd(ctx); if (pd == NULL) { - ERROR("PD allocation failure"); + DRV_LOG(ERR, "PD allocation failure"); err = ENOMEM; goto port_error; } @@ -789,7 +861,7 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, sizeof(*priv), RTE_CACHE_LINE_SIZE); if (priv == NULL) { - ERROR("priv allocation failure"); + DRV_LOG(ERR, "priv allocation failure"); err = ENOMEM; goto port_error; } @@ -802,25 +874,27 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, priv->mtu = ETHER_MTU; err = mlx5_args(&config, pci_dev->device.devargs); if (err) { - ERROR("failed to process device arguments: %s", - strerror(err)); + DRV_LOG(ERR, "failed to process device arguments: %s", + strerror(err)); + err = rte_errno; goto port_error; } - if (mlx5_glue->query_device_ex(ctx, NULL, &device_attr_ex)) { - ERROR("ibv_query_device_ex() failed"); - err = errno; + err = mlx5_glue->query_device_ex(ctx, NULL, &device_attr_ex); + if (err) { + DRV_LOG(ERR, "ibv_query_device_ex() failed"); goto port_error; } config.hw_csum = !!(device_attr_ex.device_cap_flags_ex & IBV_DEVICE_RAW_IP_CSUM); - DEBUG("checksum offloading is %ssupported", - (config.hw_csum ? "" : "not ")); + DRV_LOG(DEBUG, "checksum offloading is %ssupported", + (config.hw_csum ? "" : "not ")); #ifdef HAVE_IBV_DEVICE_COUNTERS_SET_SUPPORT config.flow_counter_en = !!(device_attr.max_counter_sets); mlx5_glue->describe_counter_set(ctx, 0, &cs_desc); - DEBUG("counter type = %d, num of cs = %ld, attributes = %d", - cs_desc.counter_type, cs_desc.num_of_cs, - cs_desc.attributes); + DRV_LOG(DEBUG, + "counter type = %d, num of cs = %ld, attributes = %d", + cs_desc.counter_type, cs_desc.num_of_cs, + cs_desc.attributes); #endif config.ind_table_max_size = device_attr_ex.rss_caps.max_rwq_indirection_table_size; @@ -829,23 +903,25 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, if (config.ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512) config.ind_table_max_size = ETH_RSS_RETA_SIZE_512; - DEBUG("maximum RX indirection table size is %u", - config.ind_table_max_size); + DRV_LOG(DEBUG, "maximum Rx indirection table size is %u", + config.ind_table_max_size); config.hw_vlan_strip = !!(device_attr_ex.raw_packet_caps & IBV_RAW_PACKET_CAP_CVLAN_STRIPPING); - DEBUG("VLAN stripping is %ssupported", - (config.hw_vlan_strip ? "" : "not ")); + DRV_LOG(DEBUG, "VLAN stripping is %ssupported", + (config.hw_vlan_strip ? "" : "not ")); config.hw_fcs_strip = !!(device_attr_ex.raw_packet_caps & IBV_RAW_PACKET_CAP_SCATTER_FCS); - DEBUG("FCS stripping configuration is %ssupported", - (config.hw_fcs_strip ? "" : "not ")); + DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported", + (config.hw_fcs_strip ? "" : "not ")); #ifdef HAVE_IBV_WQ_FLAG_RX_END_PADDING config.hw_padding = !!device_attr_ex.rx_pad_end_addr_align; #endif - DEBUG("hardware RX end alignment padding is %ssupported", - (config.hw_padding ? "" : "not ")); + DRV_LOG(DEBUG, + "hardware Rx end alignment padding is %ssupported", + (config.hw_padding ? "" : "not ")); + config.vf = vf; config.tso = ((device_attr_ex.tso_caps.max_tso > 0) && (device_attr_ex.tso_caps.supported_qpts & (1 << IBV_QPT_RAW_PACKET))); @@ -853,61 +929,72 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, config.tso_max_payload_sz = device_attr_ex.tso_caps.max_tso; if (config.mps && !mps) { - ERROR("multi-packet send not supported on this device" - " (" MLX5_TXQ_MPW_EN ")"); + DRV_LOG(ERR, + "multi-packet send not supported on this device" + " (" MLX5_TXQ_MPW_EN ")"); err = ENOTSUP; goto port_error; } - INFO("%sMPS is %s", - config.mps == MLX5_MPW_ENHANCED ? "Enhanced " : "", - config.mps != MLX5_MPW_DISABLED ? "enabled" : "disabled"); + DRV_LOG(INFO, "%s MPS is %s", + config.mps == MLX5_MPW_ENHANCED ? "enhanced " : "", + config.mps != MLX5_MPW_DISABLED ? "enabled" : + "disabled"); if (config.cqe_comp && !cqe_comp) { - WARN("Rx CQE compression isn't supported"); + DRV_LOG(WARNING, "Rx CQE compression isn't supported"); config.cqe_comp = 0; } eth_dev = rte_eth_dev_allocate(name); if (eth_dev == NULL) { - ERROR("can not allocate rte ethdev"); + DRV_LOG(ERR, "can not allocate rte ethdev"); err = ENOMEM; goto port_error; } eth_dev->data->dev_private = priv; - priv->dev = eth_dev; + priv->dev_data = eth_dev->data; eth_dev->data->mac_addrs = priv->mac; eth_dev->device = &pci_dev->device; rte_eth_copy_pci_info(eth_dev, pci_dev); eth_dev->device->driver = &mlx5_driver.driver; err = mlx5_uar_init_primary(eth_dev); - if (err) + if (err) { + err = rte_errno; goto port_error; + } /* Configure the first MAC address by default. */ if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) { - ERROR("cannot get MAC address, is mlx5_en loaded?" - " (errno: %s)", strerror(errno)); + DRV_LOG(ERR, + "port %u cannot get MAC address, is mlx5_en" + " loaded? (errno: %s)", + eth_dev->data->port_id, strerror(errno)); err = ENODEV; goto port_error; } - INFO("port %u MAC address is %02x:%02x:%02x:%02x:%02x:%02x", - priv->port, - mac.addr_bytes[0], mac.addr_bytes[1], - mac.addr_bytes[2], mac.addr_bytes[3], - mac.addr_bytes[4], mac.addr_bytes[5]); + DRV_LOG(INFO, + "port %u MAC address is %02x:%02x:%02x:%02x:%02x:%02x", + eth_dev->data->port_id, + mac.addr_bytes[0], mac.addr_bytes[1], + mac.addr_bytes[2], mac.addr_bytes[3], + mac.addr_bytes[4], mac.addr_bytes[5]); #ifndef NDEBUG { char ifname[IF_NAMESIZE]; if (mlx5_get_ifname(eth_dev, &ifname) == 0) - DEBUG("port %u ifname is \"%s\"", - priv->port, ifname); + DRV_LOG(DEBUG, "port %u ifname is \"%s\"", + eth_dev->data->port_id, ifname); else - DEBUG("port %u ifname is unknown", priv->port); + DRV_LOG(DEBUG, "port %u ifname is unknown", + eth_dev->data->port_id); } #endif /* Get actual MTU if possible. */ err = mlx5_get_mtu(eth_dev, &priv->mtu); - if (err) + if (err) { + err = rte_errno; goto port_error; - DEBUG("port %u MTU is %u", priv->port, priv->mtu); + } + DRV_LOG(DEBUG, "port %u MTU is %u", eth_dev->data->port_id, + priv->mtu); /* * Initialize burst functions to prevent crashes before link-up. */ @@ -916,6 +1003,14 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, eth_dev->dev_ops = &mlx5_dev_ops; /* Register MAC address. */ claim_zero(mlx5_mac_addr_add(eth_dev, &mac, 0, 0)); + priv->nl_socket = -1; + priv->nl_sn = 0; + if (vf && config.vf_nl_en) { + priv->nl_socket = mlx5_nl_init(RTMGRP_LINK); + if (priv->nl_socket < 0) + priv->nl_socket = -1; + mlx5_nl_mac_addr_sync(eth_dev); + } TAILQ_INIT(&priv->flows); TAILQ_INIT(&priv->ctrl_flows); /* Hint libmlx5 to use PMD allocator for data plane resources */ @@ -928,10 +1023,34 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused, MLX5DV_CTX_ATTR_BUF_ALLOCATORS, (void *)((uintptr_t)&alctr)); /* Bring Ethernet device up. */ - DEBUG("forcing Ethernet interface up"); - mlx5_set_flags(eth_dev, ~IFF_UP, IFF_UP); + DRV_LOG(DEBUG, "port %u forcing Ethernet interface up", + eth_dev->data->port_id); + mlx5_set_link_up(eth_dev); + /* + * Even though the interrupt handler is not installed yet, + * interrupts will still trigger on the asyn_fd from + * Verbs context returned by ibv_open_device(). + */ + mlx5_link_update(eth_dev, 0); /* Store device configuration on private structure. */ priv->config = config; + /* Create drop queue. */ + err = mlx5_flow_create_drop_queue(eth_dev); + if (err) { + DRV_LOG(ERR, "port %u drop queue allocation failed: %s", + eth_dev->data->port_id, strerror(rte_errno)); + err = rte_errno; + goto port_error; + } + /* Supported Verbs flow priority number detection. */ + if (verb_priorities == 0) + verb_priorities = mlx5_get_max_verbs_prio(eth_dev); + if (verb_priorities < MLX5_VERBS_FLOW_PRIO_8) { + DRV_LOG(ERR, "port %u wrong Verbs flow priorities: %u", + eth_dev->data->port_id, verb_priorities); + goto port_error; + } + priv->config.max_verbs_prio = verb_priorities; continue; port_error: if (priv) @@ -940,6 +1059,8 @@ port_error: claim_zero(mlx5_glue->dealloc_pd(pd)); if (ctx) claim_zero(mlx5_glue->close_device(ctx)); + if (eth_dev && rte_eal_process_type() == RTE_PROC_PRIMARY) + rte_eth_dev_release_port(eth_dev); break; } /* @@ -1049,9 +1170,10 @@ mlx5_glue_path(char *buf, size_t size) goto error; return buf; error: - ERROR("unable to append \"-glue\" to last component of" - " RTE_EAL_PMD_PATH (\"" RTE_EAL_PMD_PATH "\")," - " please re-configure DPDK"); + DRV_LOG(ERR, + "unable to append \"-glue\" to last component of" + " RTE_EAL_PMD_PATH (\"" RTE_EAL_PMD_PATH "\")," + " please re-configure DPDK"); return NULL; } @@ -1106,7 +1228,8 @@ mlx5_glue_init(void) break; if (sizeof(name) != (size_t)ret + 1) continue; - DEBUG("looking for rdma-core glue as \"%s\"", name); + DRV_LOG(DEBUG, "looking for rdma-core glue as \"%s\"", + name); handle = dlopen(name, RTLD_LAZY); break; } while (1); @@ -1118,7 +1241,7 @@ mlx5_glue_init(void) rte_errno = EINVAL; dlmsg = dlerror(); if (dlmsg) - WARN("cannot load glue library: %s", dlmsg); + DRV_LOG(WARNING, "cannot load glue library: %s", dlmsg); goto glue_error; } sym = dlsym(handle, "mlx5_glue"); @@ -1126,7 +1249,7 @@ mlx5_glue_init(void) rte_errno = EINVAL; dlmsg = dlerror(); if (dlmsg) - ERROR("cannot resolve glue symbol: %s", dlmsg); + DRV_LOG(ERR, "cannot resolve glue symbol: %s", dlmsg); goto glue_error; } mlx5_glue = *sym; @@ -1134,9 +1257,9 @@ mlx5_glue_init(void) glue_error: if (handle) dlclose(handle); - WARN("cannot initialize PMD due to missing run-time" - " dependency on rdma-core libraries (libibverbs," - " libmlx5)"); + DRV_LOG(WARNING, + "cannot initialize PMD due to missing run-time dependency on" + " rdma-core libraries (libibverbs, libmlx5)"); return -rte_errno; } @@ -1149,8 +1272,10 @@ RTE_INIT(rte_mlx5_pmd_init); static void rte_mlx5_pmd_init(void) { - /* Build the static table for ptype conversion. */ + /* Build the static tables for Verbs conversion. */ mlx5_set_ptype_table(); + mlx5_set_cksum_table(); + mlx5_set_swp_types_table(); /* * RDMAV_HUGEPAGES_SAFE tells ibv_fork_init() we intend to use * huge pages. Calling ibv_fork_init() during init allows @@ -1176,8 +1301,9 @@ rte_mlx5_pmd_init(void) } #endif if (strcmp(mlx5_glue->version, MLX5_GLUE_VERSION)) { - ERROR("rdma-core glue \"%s\" mismatch: \"%s\" is required", - mlx5_glue->version, MLX5_GLUE_VERSION); + DRV_LOG(ERR, + "rdma-core glue \"%s\" mismatch: \"%s\" is required", + mlx5_glue->version, MLX5_GLUE_VERSION); return; } mlx5_glue->fork_init(); @@ -1187,3 +1313,11 @@ rte_mlx5_pmd_init(void) RTE_PMD_EXPORT_NAME(net_mlx5, __COUNTER__); RTE_PMD_REGISTER_PCI_TABLE(net_mlx5, mlx5_pci_id_map); RTE_PMD_REGISTER_KMOD_DEP(net_mlx5, "* ib_uverbs & mlx5_core & mlx5_ib"); + +/** Initialize driver log type. */ +RTE_INIT(vdev_netvsc_init_log) +{ + mlx5_logtype = rte_log_register("pmd.net.mlx5"); + if (mlx5_logtype >= 0) + rte_log_set_level(mlx5_logtype, RTE_LOG_NOTICE); +}