-static struct rte_eth_dev *
-mlx5_dev_spawn(struct rte_device *dpdk_dev,
- struct mlx5_dev_spawn_data *spawn,
- struct mlx5_dev_config config)
-{
- const struct mlx5_switch_info *switch_info = &spawn->info;
- struct mlx5_ibv_shared *sh = NULL;
- struct ibv_port_attr port_attr;
- struct mlx5dv_context dv_attr = { .comp_mask = 0 };
- struct rte_eth_dev *eth_dev = NULL;
- struct mlx5_priv *priv = NULL;
- int err = 0;
- unsigned int hw_padding = 0;
- unsigned int mps;
- unsigned int cqe_comp;
- unsigned int cqe_pad = 0;
- unsigned int tunnel_en = 0;
- unsigned int mpls_en = 0;
- unsigned int swp = 0;
- unsigned int mprq = 0;
- unsigned int mprq_min_stride_size_n = 0;
- unsigned int mprq_max_stride_size_n = 0;
- unsigned int mprq_min_stride_num_n = 0;
- unsigned int mprq_max_stride_num_n = 0;
- struct rte_ether_addr mac;
- char name[RTE_ETH_NAME_MAX_LEN];
- int own_domain_id = 0;
- uint16_t port_id;
- unsigned int i;
-#ifdef HAVE_MLX5DV_DR_DEVX_PORT
- struct mlx5dv_devx_port devx_port = { .comp_mask = 0 };
-#endif
-
- /* 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;
- }
- 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;
- }
- }
- /* Build device name. */
- 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);
- } else {
- /* Bonding device. */
- if (!switch_info->representor)
- snprintf(name, sizeof(name), "%s_%s",
- dpdk_dev->name, spawn->ibv_dev->name);
- else
- snprintf(name, sizeof(name), "%s_%s_representor_%u",
- dpdk_dev->name, spawn->ibv_dev->name,
- switch_info->port_name);
- }
- /* check if the device is already spawned */
- if (rte_eth_dev_get_port_by_name(name, &port_id) == 0) {
- rte_errno = EEXIST;
- return NULL;
- }
- DRV_LOG(DEBUG, "naming Ethernet device \"%s\"", name);
- if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
- eth_dev = rte_eth_dev_attach_secondary(name);
- if (eth_dev == NULL) {
- DRV_LOG(ERR, "can not attach rte ethdev");
- rte_errno = ENOMEM;
- return NULL;
- }
- eth_dev->device = dpdk_dev;
- eth_dev->dev_ops = &mlx5_dev_sec_ops;
- err = mlx5_proc_priv_init(eth_dev);
- if (err)
- return NULL;
- /* Receive command fd from primary process */
- err = mlx5_mp_req_verbs_cmd_fd(eth_dev);
- if (err < 0)
- return NULL;
- /* Remap UAR for Tx queues. */
- err = mlx5_tx_uar_init_secondary(eth_dev, err);
- if (err)
- return NULL;
- /*
- * Ethdev pointer is still required as input since
- * the primary device is not accessible from the
- * secondary process.
- */
- eth_dev->rx_pkt_burst = mlx5_select_rx_function(eth_dev);
- eth_dev->tx_pkt_burst = mlx5_select_tx_function(eth_dev);
- return eth_dev;
- }
- /*
- * Some parameters ("tx_db_nc" in particularly) are needed in
- * advance to create dv/verbs device context. We proceed the
- * devargs here to get ones, and later proceed devargs again
- * to override some hardware settings.
- */
- err = mlx5_args(&config, dpdk_dev->devargs);
- if (err) {
- err = rte_errno;
- DRV_LOG(ERR, "failed to process device arguments: %s",
- strerror(rte_errno));
- goto error;
- }
- sh = mlx5_alloc_shared_ibctx(spawn, &config);
- if (!sh)
- return NULL;
- config.devx = sh->devx;
-#ifdef HAVE_MLX5DV_DR_ACTION_DEST_DEVX_TIR
- config.dest_tir = 1;
-#endif
-#ifdef HAVE_IBV_MLX5_MOD_SWP
- dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_SWP;
-#endif
- /*
- * Multi-packet send is supported by ConnectX-4 Lx PF as well
- * as all ConnectX-5 devices.
- */
-#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
- dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS;
-#endif
-#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
- dv_attr.comp_mask |= MLX5DV_CONTEXT_MASK_STRIDING_RQ;
-#endif
- mlx5_glue->dv_query_device(sh->ctx, &dv_attr);
- if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_MPW_ALLOWED) {
- if (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_ENHANCED_MPW) {
- DRV_LOG(DEBUG, "enhanced MPW is supported");
- mps = MLX5_MPW_ENHANCED;
- } else {
- DRV_LOG(DEBUG, "MPW is supported");
- mps = MLX5_MPW;
- }
- } else {
- DRV_LOG(DEBUG, "MPW isn't supported");
- mps = MLX5_MPW_DISABLED;
- }
-#ifdef HAVE_IBV_MLX5_MOD_SWP
- if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_SWP)
- swp = dv_attr.sw_parsing_caps.sw_parsing_offloads;
- DRV_LOG(DEBUG, "SWP support: %u", swp);
-#endif
- config.swp = !!swp;
-#ifdef HAVE_IBV_DEVICE_STRIDING_RQ_SUPPORT
- if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_STRIDING_RQ) {
- struct mlx5dv_striding_rq_caps mprq_caps =
- dv_attr.striding_rq_caps;
-
- DRV_LOG(DEBUG, "\tmin_single_stride_log_num_of_bytes: %d",
- mprq_caps.min_single_stride_log_num_of_bytes);
- DRV_LOG(DEBUG, "\tmax_single_stride_log_num_of_bytes: %d",
- mprq_caps.max_single_stride_log_num_of_bytes);
- DRV_LOG(DEBUG, "\tmin_single_wqe_log_num_of_strides: %d",
- mprq_caps.min_single_wqe_log_num_of_strides);
- DRV_LOG(DEBUG, "\tmax_single_wqe_log_num_of_strides: %d",
- mprq_caps.max_single_wqe_log_num_of_strides);
- DRV_LOG(DEBUG, "\tsupported_qpts: %d",
- mprq_caps.supported_qpts);
- DRV_LOG(DEBUG, "device supports Multi-Packet RQ");
- mprq = 1;
- mprq_min_stride_size_n =
- mprq_caps.min_single_stride_log_num_of_bytes;
- mprq_max_stride_size_n =
- mprq_caps.max_single_stride_log_num_of_bytes;
- mprq_min_stride_num_n =
- mprq_caps.min_single_wqe_log_num_of_strides;
- mprq_max_stride_num_n =
- mprq_caps.max_single_wqe_log_num_of_strides;
- config.mprq.stride_num_n = RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N,
- mprq_min_stride_num_n);
- }
-#endif
- if (RTE_CACHE_LINE_SIZE == 128 &&
- !(dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_COMP))
- cqe_comp = 0;
- else
- cqe_comp = 1;
- config.cqe_comp = cqe_comp;
-#ifdef HAVE_IBV_MLX5_MOD_CQE_128B_PAD
- /* Whether device supports 128B Rx CQE padding. */
- cqe_pad = RTE_CACHE_LINE_SIZE == 128 &&
- (dv_attr.flags & MLX5DV_CONTEXT_FLAGS_CQE_128B_PAD);
-#endif
-#ifdef HAVE_IBV_DEVICE_TUNNEL_SUPPORT
- if (dv_attr.comp_mask & MLX5DV_CONTEXT_MASK_TUNNEL_OFFLOADS) {
- tunnel_en = ((dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_VXLAN) &&
- (dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GRE) &&
- (dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_GENEVE));
- }
- DRV_LOG(DEBUG, "tunnel offloading is %ssupported",
- tunnel_en ? "" : "not ");
-#else
- DRV_LOG(WARNING,
- "tunnel offloading disabled due to old OFED/rdma-core version");
-#endif
- config.tunnel_en = tunnel_en;
-#ifdef HAVE_IBV_DEVICE_MPLS_SUPPORT
- mpls_en = ((dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_GRE) &&
- (dv_attr.tunnel_offloads_caps &
- MLX5DV_RAW_PACKET_CAP_TUNNELED_OFFLOAD_CW_MPLS_OVER_UDP));
- DRV_LOG(DEBUG, "MPLS over GRE/UDP tunnel offloading is %ssupported",
- mpls_en ? "" : "not ");
-#else
- DRV_LOG(WARNING, "MPLS over GRE/UDP tunnel offloading disabled due to"
- " old OFED/rdma-core version or firmware configuration");
-#endif
- config.mpls_en = mpls_en;
- /* Check port status. */
- err = mlx5_glue->query_port(sh->ctx, spawn->ibv_port, &port_attr);
- if (err) {
- DRV_LOG(ERR, "port query failed: %s", strerror(err));
- goto error;
- }
- if (port_attr.link_layer != IBV_LINK_LAYER_ETHERNET) {
- DRV_LOG(ERR, "port is not configured in Ethernet mode");
- err = EINVAL;
- goto error;
- }
- if (port_attr.state != IBV_PORT_ACTIVE)
- DRV_LOG(DEBUG, "port is not active: \"%s\" (%d)",
- mlx5_glue->port_state_str(port_attr.state),
- port_attr.state);
- /* Allocate private eth device data. */
- priv = rte_zmalloc("ethdev private structure",
- sizeof(*priv),
- RTE_CACHE_LINE_SIZE);
- if (priv == NULL) {
- DRV_LOG(ERR, "priv allocation failure");
- err = ENOMEM;
- goto error;
- }
- priv->sh = sh;
- priv->ibv_port = spawn->ibv_port;
- priv->pci_dev = spawn->pci_dev;
- priv->mtu = RTE_ETHER_MTU;
-#ifndef RTE_ARCH_64
- /* Initialize UAR access locks for 32bit implementations. */
- rte_spinlock_init(&priv->uar_lock_cq);
- for (i = 0; i < MLX5_UAR_PAGE_NUM_MAX; i++)
- rte_spinlock_init(&priv->uar_lock[i]);
-#endif
- /* Some internal functions rely on Netlink sockets, open them now. */
- priv->nl_socket_rdma = mlx5_nl_init(NETLINK_RDMA);
- priv->nl_socket_route = mlx5_nl_init(NETLINK_ROUTE);
- priv->nl_sn = 0;
- priv->representor = !!switch_info->representor;
- priv->master = !!switch_info->master;
- priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
- 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 (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->ibv_port,
- &devx_port);
- if (err) {
- DRV_LOG(WARNING,
- "can't query devx port %d on device %s",
- spawn->ibv_port, spawn->ibv_dev->name);
- devx_port.comp_mask = 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 (!priv->vport_meta_mask) {
- DRV_LOG(ERR, "vport zero mask for port %d"
- " on bonding device %s",
- spawn->ibv_port, spawn->ibv_dev->name);
- err = ENOTSUP;
- goto error;
- }
- if (priv->vport_meta_tag & ~priv->vport_meta_mask) {
- DRV_LOG(ERR, "invalid vport tag for port %d"
- " on bonding device %s",
- spawn->ibv_port, spawn->ibv_dev->name);
- err = ENOTSUP;
- goto error;
- }
- }
- if (devx_port.comp_mask & MLX5DV_DEVX_PORT_VPORT) {
- priv->vport_id = devx_port.vport_num;
- } else if (spawn->pf_bond >= 0) {
- DRV_LOG(ERR, "can't deduce vport index for port %d"
- " on bonding device %s",
- spawn->ibv_port, spawn->ibv_dev->name);
- err = ENOTSUP;
- goto error;
- } else {
- /* Suppose vport index in compatible way. */
- 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;
- /*
- * 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) {
- const struct mlx5_priv *opriv =
- rte_eth_devices[port_id].data->dev_private;