+ /* Get actual MTU if possible. */
+ err = mlx5_get_mtu(eth_dev, &priv->mtu);
+ if (err) {
+ err = rte_errno;
+ goto error;
+ }
+ DRV_LOG(DEBUG, "port %u MTU is %u", eth_dev->data->port_id,
+ priv->mtu);
+ /* Initialize burst functions to prevent crashes before link-up. */
+ eth_dev->rx_pkt_burst = removed_rx_burst;
+ eth_dev->tx_pkt_burst = removed_tx_burst;
+ eth_dev->dev_ops = &mlx5_dev_ops;
+ /* Register MAC address. */
+ 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 */
+ struct mlx5dv_ctx_allocators alctr = {
+ .alloc = &mlx5_alloc_verbs_buf,
+ .free = &mlx5_free_verbs_buf,
+ .data = priv,
+ };
+ mlx5_glue->dv_set_context_attr(ctx, MLX5DV_CTX_ATTR_BUF_ALLOCATORS,
+ (void *)((uintptr_t)&alctr));
+ /* Bring Ethernet device 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;
+ /* Supported Verbs flow priority number detection. */
+ err = mlx5_flow_discover_priorities(eth_dev);
+ if (err < 0)
+ 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);
+ rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
+ return eth_dev;
+error:
+ if (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);
+ if (eth_dev != NULL)
+ eth_dev->data->dev_private = NULL;
+ }
+ if (pd)
+ claim_zero(mlx5_glue->dealloc_pd(pd));
+ if (eth_dev != NULL) {
+ /* mac_addrs must not be freed alone because part of dev_private */
+ eth_dev->data->mac_addrs = NULL;
+ rte_eth_dev_release_port(eth_dev);
+ }
+ if (ctx)
+ claim_zero(mlx5_glue->close_device(ctx));
+ assert(err > 0);
+ rte_errno = err;
+ return NULL;
+}
+
+/** Data associated with devices to spawn. */
+struct mlx5_dev_spawn_data {
+ unsigned int ifindex; /**< Network interface index. */
+ struct mlx5_switch_info info; /**< Switch information. */
+ struct ibv_device *ibv_dev; /**< Associated IB device. */
+ struct rte_eth_dev *eth_dev; /**< Associated Ethernet device. */
+};
+
+/**
+ * Comparison callback to sort device data.
+ *
+ * This is meant to be used with qsort().
+ *
+ * @param a[in]
+ * Pointer to pointer to first data object.
+ * @param b[in]
+ * Pointer to pointer to second data object.
+ *
+ * @return
+ * 0 if both objects are equal, less than 0 if the first argument is less
+ * than the second, greater than 0 otherwise.
+ */
+static int
+mlx5_dev_spawn_data_cmp(const void *a, const void *b)
+{
+ const struct mlx5_switch_info *si_a =
+ &((const struct mlx5_dev_spawn_data *)a)->info;
+ const struct mlx5_switch_info *si_b =
+ &((const struct mlx5_dev_spawn_data *)b)->info;
+ int ret;
+
+ /* Master device first. */
+ ret = si_b->master - si_a->master;
+ if (ret)
+ return ret;
+ /* Then representor devices. */
+ ret = si_b->representor - si_a->representor;
+ if (ret)
+ return ret;
+ /* Unidentified devices come last in no specific order. */
+ if (!si_a->representor)
+ return 0;
+ /* Order representors by name. */
+ return si_a->port_name - si_b->port_name;
+}
+
+/**
+ * DPDK callback to register a PCI device.
+ *
+ * This function spawns Ethernet devices out of a given PCI device.
+ *
+ * @param[in] pci_drv
+ * PCI driver structure (mlx5_driver).
+ * @param[in] pci_dev
+ * PCI device information.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
+ struct rte_pci_device *pci_dev)
+{
+ struct ibv_device **ibv_list;
+ unsigned int n = 0;
+ struct mlx5_dev_config dev_config;
+ int ret;
+
+ assert(pci_drv == &mlx5_driver);
+ errno = 0;
+ ibv_list = mlx5_glue->get_device_list(&ret);
+ if (!ibv_list) {
+ rte_errno = errno ? errno : ENOSYS;
+ DRV_LOG(ERR, "cannot list devices, is ib_uverbs loaded?");
+ return -rte_errno;
+ }
+
+ struct ibv_device *ibv_match[ret + 1];
+
+ while (ret-- > 0) {
+ struct rte_pci_addr pci_addr;
+
+ DRV_LOG(DEBUG, "checking device \"%s\"", ibv_list[ret]->name);
+ if (mlx5_ibv_device_to_pci_addr(ibv_list[ret], &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[n++] = ibv_list[ret];
+ }
+ ibv_match[n] = NULL;