+ const struct rte_memzone *mz;
+ int ret = 0;
+
+ rte_spinlock_lock(&mlx5_shared_data_lock);
+ if (mlx5_shared_data == NULL) {
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ /* Allocate shared memory. */
+ 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");
+ 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");
+ ret = -rte_errno;
+ goto error;
+ }
+ mlx5_shared_data = mz->addr;
+ memset(&mlx5_local_data, 0, sizeof(mlx5_local_data));
+ }
+ }
+error:
+ rte_spinlock_unlock(&mlx5_shared_data_lock);
+ return ret;
+}
+
+/**
+ * Retrieve integer value from environment variable.
+ *
+ * @param[in] name
+ * Environment variable name.
+ *
+ * @return
+ * Integer value, 0 if the variable is not set.
+ */
+int
+mlx5_getenv_int(const char *name)
+{
+ const char *val = getenv(name);
+
+ if (val == NULL)
+ return 0;
+ return atoi(val);
+}
+
+/**
+ * Verbs callback to allocate a memory. This function should allocate the space
+ * according to the size provided residing inside a huge page.
+ * Please note that all allocation must respect the alignment from libmlx5
+ * (i.e. currently sysconf(_SC_PAGESIZE)).
+ *
+ * @param[in] size
+ * The size in bytes of the memory to allocate.
+ * @param[in] data
+ * A pointer to the callback data.
+ *
+ * @return
+ * Allocated buffer, NULL otherwise and rte_errno is set.
+ */
+static void *
+mlx5_alloc_verbs_buf(size_t size, void *data)
+{
+ struct mlx5_priv *priv = data;
+ void *ret;
+ size_t alignment = sysconf(_SC_PAGESIZE);
+ unsigned int socket = SOCKET_ID_ANY;
+
+ if (priv->verbs_alloc_ctx.type == MLX5_VERBS_ALLOC_TYPE_TX_QUEUE) {
+ const struct mlx5_txq_ctrl *ctrl = priv->verbs_alloc_ctx.obj;
+
+ socket = ctrl->socket;
+ } else if (priv->verbs_alloc_ctx.type ==
+ MLX5_VERBS_ALLOC_TYPE_RX_QUEUE) {
+ const struct mlx5_rxq_ctrl *ctrl = priv->verbs_alloc_ctx.obj;
+
+ socket = ctrl->socket;
+ }
+ MLX5_ASSERT(data != NULL);
+ ret = rte_malloc_socket(__func__, size, alignment, socket);
+ if (!ret && size)
+ rte_errno = ENOMEM;
+ return ret;
+}
+
+/**
+ * Verbs callback to free a memory.
+ *
+ * @param[in] ptr
+ * A pointer to the memory to free.
+ * @param[in] data
+ * A pointer to the callback data.
+ */
+static void
+mlx5_free_verbs_buf(void *ptr, void *data __rte_unused)
+{
+ MLX5_ASSERT(data != NULL);
+ rte_free(ptr);
+}
+
+/**
+ * DPDK callback to add udp tunnel port
+ *
+ * @param[in] dev
+ * A pointer to eth_dev
+ * @param[in] udp_tunnel
+ * A pointer to udp tunnel
+ *
+ * @return
+ * 0 on valid udp ports and tunnels, -ENOTSUP otherwise.
+ */
+int
+mlx5_udp_tunnel_port_add(struct rte_eth_dev *dev __rte_unused,
+ struct rte_eth_udp_tunnel *udp_tunnel)
+{
+ MLX5_ASSERT(udp_tunnel != NULL);
+ if (udp_tunnel->prot_type == RTE_TUNNEL_TYPE_VXLAN &&
+ udp_tunnel->udp_port == 4789)
+ return 0;
+ if (udp_tunnel->prot_type == RTE_TUNNEL_TYPE_VXLAN_GPE &&
+ udp_tunnel->udp_port == 4790)
+ return 0;
+ return -ENOTSUP;
+}
+
+/**
+ * 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.
+ *
+ * Destroy all queues and objects, free memory.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ */
+static void
+mlx5_dev_close(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ unsigned int i;
+ int ret;
+
+ DRV_LOG(DEBUG, "port %u closing device \"%s\"",
+ dev->data->port_id,
+ ((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_dev_interrupt_handler_devx_uninstall(dev);
+ /*
+ * If default mreg copy action is removed at the stop stage,
+ * the search will return none and nothing will be done anymore.
+ */
+ mlx5_flow_stop_default(dev);
+ mlx5_traffic_disable(dev);
+ /*
+ * If all the flows are already flushed in the device stop stage,
+ * then this will return directly without any action.
+ */
+ mlx5_flow_list_flush(dev, &priv->flows, true);
+ mlx5_flow_meter_flush(dev, NULL);
+ /* Free the intermediate buffers for flow creation. */
+ mlx5_flow_free_intermediate(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);
+ for (i = 0; (i != priv->rxqs_n); ++i)
+ mlx5_rxq_release(dev, i);
+ priv->rxqs_n = 0;
+ priv->rxqs = NULL;
+ }
+ if (priv->txqs != NULL) {
+ /* XXX race condition if mlx5_tx_burst() is still running. */
+ usleep(1000);
+ for (i = 0; (i != priv->txqs_n); ++i)
+ mlx5_txq_release(dev, i);
+ priv->txqs_n = 0;
+ priv->txqs = NULL;
+ }
+ mlx5_proc_priv_uninit(dev);
+ if (priv->mreg_cp_tbl)
+ mlx5_hlist_destroy(priv->mreg_cp_tbl, NULL, NULL);
+ mlx5_mprq_free_mp(dev);
+ 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->config.vf)
+ mlx5_nl_mac_addr_flush(priv->nl_socket_route, mlx5_ifindex(dev),
+ dev->data->mac_addrs,
+ MLX5_MAX_MAC_ADDRESSES, priv->mac_own);
+ if (priv->nl_socket_route >= 0)
+ close(priv->nl_socket_route);
+ if (priv->nl_socket_rdma >= 0)
+ close(priv->nl_socket_rdma);
+ if (priv->vmwa_context)
+ mlx5_vlan_vmwa_exit(priv->vmwa_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_verify(dev);
+ if (ret)
+ DRV_LOG(WARNING, "port %u some hash Rx queue still remain",
+ dev->data->port_id);
+ ret = mlx5_ind_table_obj_verify(dev);
+ if (ret)
+ DRV_LOG(WARNING, "port %u some indirection table still remain",
+ dev->data->port_id);
+ ret = mlx5_rxq_obj_verify(dev);
+ if (ret)
+ DRV_LOG(WARNING, "port %u some Rx queue objects still remain",
+ dev->data->port_id);
+ ret = mlx5_rxq_verify(dev);
+ if (ret)
+ DRV_LOG(WARNING, "port %u some Rx queues still remain",
+ dev->data->port_id);
+ ret = mlx5_txq_obj_verify(dev);
+ if (ret)
+ DRV_LOG(WARNING, "port %u some Verbs Tx queue still remain",
+ dev->data->port_id);
+ ret = mlx5_txq_verify(dev);
+ if (ret)
+ DRV_LOG(WARNING, "port %u some Tx queues still remain",
+ dev->data->port_id);
+ ret = mlx5_flow_verify(dev);
+ if (ret)
+ DRV_LOG(WARNING, "port %u some flows still remain",
+ dev->data->port_id);
+ if (priv->domain_id != RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID) {
+ unsigned int c = 0;
+ uint16_t port_id;
+
+ MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
+ struct mlx5_priv *opriv =
+ rte_eth_devices[port_id].data->dev_private;
+
+ if (!opriv ||
+ opriv->domain_id != priv->domain_id ||
+ &rte_eth_devices[port_id] == dev)
+ continue;
+ ++c;
+ break;
+ }
+ if (!c)
+ claim_zero(rte_eth_switch_domain_free(priv->domain_id));
+ }
+ memset(priv, 0, sizeof(*priv));
+ priv->domain_id = RTE_ETH_DEV_SWITCH_DOMAIN_ID_INVALID;
+ /*
+ * Reset mac_addrs to NULL such that it is not freed as part of
+ * rte_eth_dev_release_port(). mac_addrs is part of dev_private so
+ * it is freed when dev_private is freed.
+ */
+ dev->data->mac_addrs = NULL;
+}
+
+const struct eth_dev_ops mlx5_dev_ops = {
+ .dev_configure = mlx5_dev_configure,
+ .dev_start = mlx5_dev_start,
+ .dev_stop = mlx5_dev_stop,
+ .dev_set_link_down = mlx5_set_link_down,
+ .dev_set_link_up = mlx5_set_link_up,
+ .dev_close = mlx5_dev_close,
+ .promiscuous_enable = mlx5_promiscuous_enable,
+ .promiscuous_disable = mlx5_promiscuous_disable,
+ .allmulticast_enable = mlx5_allmulticast_enable,
+ .allmulticast_disable = mlx5_allmulticast_disable,
+ .link_update = mlx5_link_update,
+ .stats_get = mlx5_stats_get,
+ .stats_reset = mlx5_stats_reset,
+ .xstats_get = mlx5_xstats_get,
+ .xstats_reset = mlx5_xstats_reset,
+ .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,
+ .rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
+ .tx_queue_setup = mlx5_tx_queue_setup,
+ .tx_hairpin_queue_setup = mlx5_tx_hairpin_queue_setup,
+ .rx_queue_release = mlx5_rx_queue_release,
+ .tx_queue_release = mlx5_tx_queue_release,
+ .flow_ctrl_get = mlx5_dev_get_flow_ctrl,
+ .flow_ctrl_set = mlx5_dev_set_flow_ctrl,
+ .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,
+ .reta_update = mlx5_dev_rss_reta_update,
+ .reta_query = mlx5_dev_rss_reta_query,
+ .rss_hash_update = mlx5_rss_hash_update,
+ .rss_hash_conf_get = mlx5_rss_hash_conf_get,
+ .filter_ctrl = mlx5_dev_filter_ctrl,
+ .rx_descriptor_status = mlx5_rx_descriptor_status,
+ .tx_descriptor_status = mlx5_tx_descriptor_status,
+ .rxq_info_get = mlx5_rxq_info_get,
+ .txq_info_get = mlx5_txq_info_get,
+ .rx_burst_mode_get = mlx5_rx_burst_mode_get,
+ .tx_burst_mode_get = mlx5_tx_burst_mode_get,
+ .rx_queue_count = mlx5_rx_queue_count,
+ .rx_queue_intr_enable = mlx5_rx_intr_enable,
+ .rx_queue_intr_disable = mlx5_rx_intr_disable,
+ .is_removed = mlx5_is_removed,
+ .udp_tunnel_port_add = mlx5_udp_tunnel_port_add,
+ .get_module_info = mlx5_get_module_info,
+ .get_module_eeprom = mlx5_get_module_eeprom,
+ .hairpin_cap_get = mlx5_hairpin_cap_get,
+ .mtr_ops_get = mlx5_flow_meter_ops_get,
+};
+
+/* Available operations from secondary process. */
+static const struct eth_dev_ops mlx5_dev_sec_ops = {
+ .stats_get = mlx5_stats_get,
+ .stats_reset = mlx5_stats_reset,
+ .xstats_get = mlx5_xstats_get,
+ .xstats_reset = mlx5_xstats_reset,
+ .xstats_get_names = mlx5_xstats_get_names,
+ .fw_version_get = mlx5_fw_version_get,
+ .dev_infos_get = mlx5_dev_infos_get,
+ .rx_descriptor_status = mlx5_rx_descriptor_status,
+ .tx_descriptor_status = mlx5_tx_descriptor_status,
+ .rxq_info_get = mlx5_rxq_info_get,
+ .txq_info_get = mlx5_txq_info_get,
+ .rx_burst_mode_get = mlx5_rx_burst_mode_get,
+ .tx_burst_mode_get = mlx5_tx_burst_mode_get,
+ .get_module_info = mlx5_get_module_info,
+ .get_module_eeprom = mlx5_get_module_eeprom,
+};
+
+/* Available operations in flow isolated mode. */
+const struct eth_dev_ops mlx5_dev_ops_isolate = {
+ .dev_configure = mlx5_dev_configure,
+ .dev_start = mlx5_dev_start,
+ .dev_stop = mlx5_dev_stop,
+ .dev_set_link_down = mlx5_set_link_down,
+ .dev_set_link_up = mlx5_set_link_up,
+ .dev_close = mlx5_dev_close,
+ .promiscuous_enable = mlx5_promiscuous_enable,
+ .promiscuous_disable = mlx5_promiscuous_disable,
+ .allmulticast_enable = mlx5_allmulticast_enable,
+ .allmulticast_disable = mlx5_allmulticast_disable,
+ .link_update = mlx5_link_update,
+ .stats_get = mlx5_stats_get,
+ .stats_reset = mlx5_stats_reset,
+ .xstats_get = mlx5_xstats_get,
+ .xstats_reset = mlx5_xstats_reset,
+ .xstats_get_names = mlx5_xstats_get_names,
+ .fw_version_get = mlx5_fw_version_get,
+ .dev_infos_get = mlx5_dev_infos_get,
+ .dev_supported_ptypes_get = mlx5_dev_supported_ptypes_get,
+ .vlan_filter_set = mlx5_vlan_filter_set,
+ .rx_queue_setup = mlx5_rx_queue_setup,
+ .rx_hairpin_queue_setup = mlx5_rx_hairpin_queue_setup,
+ .tx_queue_setup = mlx5_tx_queue_setup,
+ .tx_hairpin_queue_setup = mlx5_tx_hairpin_queue_setup,
+ .rx_queue_release = mlx5_rx_queue_release,
+ .tx_queue_release = mlx5_tx_queue_release,
+ .flow_ctrl_get = mlx5_dev_get_flow_ctrl,
+ .flow_ctrl_set = mlx5_dev_set_flow_ctrl,
+ .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,
+ .filter_ctrl = mlx5_dev_filter_ctrl,
+ .rx_descriptor_status = mlx5_rx_descriptor_status,
+ .tx_descriptor_status = mlx5_tx_descriptor_status,
+ .rxq_info_get = mlx5_rxq_info_get,
+ .txq_info_get = mlx5_txq_info_get,
+ .rx_burst_mode_get = mlx5_rx_burst_mode_get,
+ .tx_burst_mode_get = mlx5_tx_burst_mode_get,
+ .rx_queue_intr_enable = mlx5_rx_intr_enable,
+ .rx_queue_intr_disable = mlx5_rx_intr_disable,
+ .is_removed = mlx5_is_removed,
+ .get_module_info = mlx5_get_module_info,
+ .get_module_eeprom = mlx5_get_module_eeprom,
+ .hairpin_cap_get = mlx5_hairpin_cap_get,
+ .mtr_ops_get = mlx5_flow_meter_ops_get,
+};
+
+/**
+ * Verify and store value for device argument.
+ *
+ * @param[in] key
+ * Key argument to verify.
+ * @param[in] val
+ * Value associated with key.
+ * @param opaque
+ * User data.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_args_check(const char *key, const char *val, void *opaque)
+{
+ struct mlx5_dev_config *config = opaque;
+ unsigned long tmp;
+
+ /* No-op, port representors are processed in mlx5_dev_spawn(). */
+ if (!strcmp(MLX5_REPRESENTOR, key))
+ return 0;
+ errno = 0;
+ tmp = strtoul(val, NULL, 0);
+ if (errno) {
+ rte_errno = errno;
+ DRV_LOG(WARNING, "%s: \"%s\" is not a valid integer", key, val);
+ return -rte_errno;
+ }
+ if (strcmp(MLX5_RXQ_CQE_COMP_EN, key) == 0) {
+ config->cqe_comp = !!tmp;
+ } else if (strcmp(MLX5_RXQ_CQE_PAD_EN, key) == 0) {
+ config->cqe_pad = !!tmp;
+ } else if (strcmp(MLX5_RXQ_PKT_PAD_EN, key) == 0) {
+ config->hw_padding = !!tmp;
+ } else if (strcmp(MLX5_RX_MPRQ_EN, key) == 0) {
+ config->mprq.enabled = !!tmp;
+ } else if (strcmp(MLX5_RX_MPRQ_LOG_STRIDE_NUM, key) == 0) {
+ config->mprq.stride_num_n = tmp;
+ } else if (strcmp(MLX5_RX_MPRQ_MAX_MEMCPY_LEN, key) == 0) {
+ config->mprq.max_memcpy_len = tmp;
+ } else if (strcmp(MLX5_RXQS_MIN_MPRQ, key) == 0) {
+ config->mprq.min_rxqs_num = tmp;
+ } else if (strcmp(MLX5_TXQ_INLINE, key) == 0) {
+ DRV_LOG(WARNING, "%s: deprecated parameter,"
+ " converted to txq_inline_max", key);
+ config->txq_inline_max = tmp;
+ } else if (strcmp(MLX5_TXQ_INLINE_MAX, key) == 0) {
+ config->txq_inline_max = tmp;
+ } else if (strcmp(MLX5_TXQ_INLINE_MIN, key) == 0) {
+ config->txq_inline_min = tmp;
+ } else if (strcmp(MLX5_TXQ_INLINE_MPW, key) == 0) {
+ config->txq_inline_mpw = tmp;
+ } else if (strcmp(MLX5_TXQS_MIN_INLINE, key) == 0) {
+ config->txqs_inline = tmp;
+ } else if (strcmp(MLX5_TXQS_MAX_VEC, key) == 0) {
+ DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
+ } else if (strcmp(MLX5_TXQ_MPW_EN, key) == 0) {
+ config->mps = !!tmp;
+ } else if (strcmp(MLX5_TX_DB_NC, key) == 0) {
+ if (tmp != MLX5_TXDB_CACHED &&
+ tmp != MLX5_TXDB_NCACHED &&
+ tmp != MLX5_TXDB_HEURISTIC) {
+ DRV_LOG(ERR, "invalid Tx doorbell "
+ "mapping parameter");
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ config->dbnc = tmp;
+ } else if (strcmp(MLX5_TXQ_MPW_HDR_DSEG_EN, key) == 0) {
+ DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
+ } else if (strcmp(MLX5_TXQ_MAX_INLINE_LEN, key) == 0) {
+ DRV_LOG(WARNING, "%s: deprecated parameter,"
+ " converted to txq_inline_mpw", key);
+ config->txq_inline_mpw = tmp;
+ } else if (strcmp(MLX5_TX_VEC_EN, key) == 0) {
+ DRV_LOG(WARNING, "%s: deprecated parameter, ignored", key);
+ } 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 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_DV_XMETA_EN, key) == 0) {
+ if (tmp != MLX5_XMETA_MODE_LEGACY &&
+ tmp != MLX5_XMETA_MODE_META16 &&
+ tmp != MLX5_XMETA_MODE_META32) {
+ DRV_LOG(ERR, "invalid extensive "
+ "metadata parameter");
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ config->dv_xmeta_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 if (strcmp(MLX5_LRO_TIMEOUT_USEC, key) == 0) {
+ config->lro.timeout = tmp;
+ } else if (strcmp(MLX5_CLASS_ARG_NAME, key) == 0) {
+ DRV_LOG(DEBUG, "class argument is %s.", val);
+ } else if (strcmp(MLX5_HP_BUF_SIZE, key) == 0) {
+ config->log_hp_size = tmp;
+ } else {
+ DRV_LOG(WARNING, "%s: unknown parameter", key);
+ rte_errno = EINVAL;
+ return -rte_errno;
+ }
+ return 0;
+}
+
+/**
+ * Parse device parameters.
+ *
+ * @param config
+ * Pointer to device configuration structure.
+ * @param devargs
+ * Device arguments structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs)
+{
+ const char **params = (const char *[]){
+ MLX5_RXQ_CQE_COMP_EN,
+ MLX5_RXQ_CQE_PAD_EN,
+ MLX5_RXQ_PKT_PAD_EN,
+ MLX5_RX_MPRQ_EN,
+ MLX5_RX_MPRQ_LOG_STRIDE_NUM,
+ MLX5_RX_MPRQ_MAX_MEMCPY_LEN,
+ MLX5_RXQS_MIN_MPRQ,
+ MLX5_TXQ_INLINE,
+ MLX5_TXQ_INLINE_MIN,
+ MLX5_TXQ_INLINE_MAX,
+ MLX5_TXQ_INLINE_MPW,
+ MLX5_TXQS_MIN_INLINE,
+ MLX5_TXQS_MAX_VEC,
+ MLX5_TXQ_MPW_EN,
+ MLX5_TXQ_MPW_HDR_DSEG_EN,
+ MLX5_TXQ_MAX_INLINE_LEN,
+ MLX5_TX_DB_NC,
+ MLX5_TX_VEC_EN,
+ MLX5_RX_VEC_EN,
+ MLX5_L3_VXLAN_EN,
+ MLX5_VF_NL_EN,
+ MLX5_DV_ESW_EN,
+ MLX5_DV_FLOW_EN,
+ MLX5_DV_XMETA_EN,
+ MLX5_MR_EXT_MEMSEG_EN,
+ MLX5_REPRESENTOR,
+ MLX5_MAX_DUMP_FILES_NUM,
+ MLX5_LRO_TIMEOUT_USEC,
+ MLX5_CLASS_ARG_NAME,
+ MLX5_HP_BUF_SIZE,
+ NULL,
+ };
+ struct rte_kvargs *kvlist;
+ int ret = 0;
+ int i;
+
+ if (devargs == NULL)
+ return 0;
+ /* Following UGLY cast is done to pass checkpatch. */
+ kvlist = rte_kvargs_parse(devargs->args, params);
+ 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])) {
+ ret = rte_kvargs_process(kvlist, params[i],
+ mlx5_args_check, config);
+ if (ret) {
+ rte_errno = EINVAL;
+ rte_kvargs_free(kvlist);
+ return -rte_errno;
+ }
+ }
+ }
+ rte_kvargs_free(kvlist);
+ return 0;
+}
+
+static struct rte_pci_driver mlx5_driver;
+
+/**
+ * PMD global initialization.
+ *
+ * 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_init_once(void)
+{
+ struct mlx5_shared_data *sd;
+ struct mlx5_local_data *ld = &mlx5_local_data;
+ int ret = 0;
+
+ if (mlx5_init_shared_data())
+ return -rte_errno;
+ sd = mlx5_shared_data;
+ MLX5_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;
+ }
+out:
+ rte_spinlock_unlock(&sd->lock);
+ return ret;
+}
+
+/**
+ * Configures the minimal amount of data to inline into WQE
+ * while sending packets.
+ *
+ * - the txq_inline_min has the maximal priority, if this
+ * key is specified in devargs
+ * - if DevX is enabled the inline mode is queried from the
+ * device (HCA attributes and NIC vport context if needed).
+ * - otherwise L2 mode (18 bytes) is assumed for ConnectX-4/4 Lx
+ * and none (0 bytes) for other NICs
+ *
+ * @param spawn
+ * Verbs device parameters (name, port, switch_info) to spawn.
+ * @param config
+ * Device configuration parameters.
+ */
+static void
+mlx5_set_min_inline(struct mlx5_dev_spawn_data *spawn,
+ struct mlx5_dev_config *config)
+{
+ if (config->txq_inline_min != MLX5_ARG_UNSET) {
+ /* Application defines size of inlined data explicitly. */
+ switch (spawn->pci_dev->id.device_id) {
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
+ if (config->txq_inline_min <
+ (int)MLX5_INLINE_HSIZE_L2) {
+ DRV_LOG(DEBUG,
+ "txq_inline_mix aligned to minimal"
+ " ConnectX-4 required value %d",
+ (int)MLX5_INLINE_HSIZE_L2);
+ config->txq_inline_min = MLX5_INLINE_HSIZE_L2;
+ }
+ break;
+ }
+ goto exit;
+ }
+ if (config->hca_attr.eth_net_offloads) {
+ /* We have DevX enabled, inline mode queried successfully. */
+ switch (config->hca_attr.wqe_inline_mode) {
+ case MLX5_CAP_INLINE_MODE_L2:
+ /* outer L2 header must be inlined. */
+ config->txq_inline_min = MLX5_INLINE_HSIZE_L2;
+ goto exit;
+ case MLX5_CAP_INLINE_MODE_NOT_REQUIRED:
+ /* No inline data are required by NIC. */
+ config->txq_inline_min = MLX5_INLINE_HSIZE_NONE;
+ config->hw_vlan_insert =
+ config->hca_attr.wqe_vlan_insert;
+ DRV_LOG(DEBUG, "Tx VLAN insertion is supported");
+ goto exit;
+ case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT:
+ /* inline mode is defined by NIC vport context. */
+ if (!config->hca_attr.eth_virt)
+ break;
+ switch (config->hca_attr.vport_inline_mode) {
+ case MLX5_INLINE_MODE_NONE:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_NONE;
+ goto exit;
+ case MLX5_INLINE_MODE_L2:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_L2;
+ goto exit;
+ case MLX5_INLINE_MODE_IP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_L3;
+ goto exit;
+ case MLX5_INLINE_MODE_TCP_UDP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_L4;
+ goto exit;
+ case MLX5_INLINE_MODE_INNER_L2:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_INNER_L2;
+ goto exit;
+ case MLX5_INLINE_MODE_INNER_IP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_INNER_L3;
+ goto exit;
+ case MLX5_INLINE_MODE_INNER_TCP_UDP:
+ config->txq_inline_min =
+ MLX5_INLINE_HSIZE_INNER_L4;
+ goto exit;
+ }
+ }
+ }
+ /*
+ * We get here if we are unable to deduce
+ * inline data size with DevX. Try PCI ID
+ * to determine old NICs.
+ */
+ switch (spawn->pci_dev->id.device_id) {
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4VF:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4LX:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX4LXVF:
+ config->txq_inline_min = MLX5_INLINE_HSIZE_L2;
+ config->hw_vlan_insert = 0;
+ break;
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX5:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX5VF:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX5EX:
+ case PCI_DEVICE_ID_MELLANOX_CONNECTX5EXVF:
+ /*
+ * These NICs support VLAN insertion from WQE and
+ * report the wqe_vlan_insert flag. But there is the bug
+ * and PFC control may be broken, so disable feature.
+ */
+ config->hw_vlan_insert = 0;
+ config->txq_inline_min = MLX5_INLINE_HSIZE_NONE;
+ break;
+ default:
+ config->txq_inline_min = MLX5_INLINE_HSIZE_NONE;
+ break;
+ }
+exit:
+ DRV_LOG(DEBUG, "min tx inline configured: %d", config->txq_inline_min);
+}
+
+/**
+ * Configures the metadata mask fields in the shared context.
+ *
+ * @param [in] dev
+ * Pointer to Ethernet device.
+ */
+static void
+mlx5_set_metadata_mask(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_ibv_shared *sh = priv->sh;
+ uint32_t meta, mark, reg_c0;
+
+ reg_c0 = ~priv->vport_meta_mask;
+ switch (priv->config.dv_xmeta_en) {
+ case MLX5_XMETA_MODE_LEGACY:
+ meta = UINT32_MAX;
+ mark = MLX5_FLOW_MARK_MASK;
+ break;
+ case MLX5_XMETA_MODE_META16:
+ meta = reg_c0 >> rte_bsf32(reg_c0);
+ mark = MLX5_FLOW_MARK_MASK;
+ break;
+ case MLX5_XMETA_MODE_META32:
+ meta = UINT32_MAX;
+ mark = (reg_c0 >> rte_bsf32(reg_c0)) & MLX5_FLOW_MARK_MASK;
+ break;
+ default:
+ meta = 0;
+ mark = 0;
+ MLX5_ASSERT(false);
+ break;
+ }
+ if (sh->dv_mark_mask && sh->dv_mark_mask != mark)
+ DRV_LOG(WARNING, "metadata MARK mask mismatche %08X:%08X",
+ sh->dv_mark_mask, mark);
+ else
+ sh->dv_mark_mask = mark;
+ if (sh->dv_meta_mask && sh->dv_meta_mask != meta)
+ DRV_LOG(WARNING, "metadata META mask mismatche %08X:%08X",
+ sh->dv_meta_mask, meta);
+ else
+ sh->dv_meta_mask = meta;
+ if (sh->dv_regc0_mask && sh->dv_regc0_mask != reg_c0)
+ DRV_LOG(WARNING, "metadata reg_c0 mask mismatche %08X:%08X",
+ sh->dv_meta_mask, reg_c0);
+ else
+ sh->dv_regc0_mask = reg_c0;
+ DRV_LOG(DEBUG, "metadata mode %u", priv->config.dv_xmeta_en);
+ DRV_LOG(DEBUG, "metadata MARK mask %08X", sh->dv_mark_mask);
+ DRV_LOG(DEBUG, "metadata META mask %08X", sh->dv_meta_mask);
+ DRV_LOG(DEBUG, "metadata reg_c0 mask %08X", sh->dv_regc0_mask);
+}
+
+/**
+ * Allocate page of door-bells and register it using DevX API.
+ *
+ * @param [in] dev
+ * Pointer to Ethernet device.
+ *
+ * @return
+ * Pointer to new page on success, NULL otherwise.
+ */
+static struct mlx5_devx_dbr_page *
+mlx5_alloc_dbr_page(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_devx_dbr_page *page;
+
+ /* Allocate space for door-bell page and management data. */
+ page = rte_calloc_socket(__func__, 1, sizeof(struct mlx5_devx_dbr_page),
+ RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+ if (!page) {
+ DRV_LOG(ERR, "port %u cannot allocate dbr page",
+ dev->data->port_id);
+ return NULL;
+ }
+ /* Register allocated memory. */
+ page->umem = mlx5_glue->devx_umem_reg(priv->sh->ctx, page->dbrs,
+ MLX5_DBR_PAGE_SIZE, 0);
+ if (!page->umem) {
+ DRV_LOG(ERR, "port %u cannot umem reg dbr page",
+ dev->data->port_id);
+ rte_free(page);
+ return NULL;
+ }
+ return page;
+}
+
+/**
+ * Find the next available door-bell, allocate new page if needed.
+ *
+ * @param [in] dev
+ * Pointer to Ethernet device.
+ * @param [out] dbr_page
+ * Door-bell page containing the page data.
+ *
+ * @return
+ * Door-bell address offset on success, a negative error value otherwise.
+ */
+int64_t
+mlx5_get_dbr(struct rte_eth_dev *dev, struct mlx5_devx_dbr_page **dbr_page)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_devx_dbr_page *page = NULL;
+ uint32_t i, j;
+
+ LIST_FOREACH(page, &priv->dbrpgs, next)
+ if (page->dbr_count < MLX5_DBR_PER_PAGE)
+ break;
+ if (!page) { /* No page with free door-bell exists. */
+ page = mlx5_alloc_dbr_page(dev);
+ if (!page) /* Failed to allocate new page. */
+ return (-1);
+ LIST_INSERT_HEAD(&priv->dbrpgs, page, next);
+ }
+ /* Loop to find bitmap part with clear bit. */
+ for (i = 0;
+ i < MLX5_DBR_BITMAP_SIZE && page->dbr_bitmap[i] == UINT64_MAX;
+ i++)
+ ; /* Empty. */
+ /* Find the first clear bit. */
+ j = rte_bsf64(~page->dbr_bitmap[i]);
+ MLX5_ASSERT(i < (MLX5_DBR_PER_PAGE / 64));
+ page->dbr_bitmap[i] |= (1 << j);
+ page->dbr_count++;
+ *dbr_page = page;
+ return (((i * 64) + j) * sizeof(uint64_t));
+}
+
+/**
+ * Release a door-bell record.
+ *
+ * @param [in] dev
+ * Pointer to Ethernet device.
+ * @param [in] umem_id
+ * UMEM ID of page containing the door-bell record to release.
+ * @param [in] offset
+ * Offset of door-bell record in page.
+ *
+ * @return
+ * 0 on success, a negative error value otherwise.
+ */
+int32_t
+mlx5_release_dbr(struct rte_eth_dev *dev, uint32_t umem_id, uint64_t offset)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_devx_dbr_page *page = NULL;
+ int ret = 0;
+
+ LIST_FOREACH(page, &priv->dbrpgs, next)
+ /* Find the page this address belongs to. */
+ if (page->umem->umem_id == umem_id)
+ break;
+ if (!page)
+ return -EINVAL;
+ page->dbr_count--;
+ if (!page->dbr_count) {
+ /* Page not used, free it and remove from list. */
+ LIST_REMOVE(page, next);
+ if (page->umem)
+ ret = -mlx5_glue->devx_umem_dereg(page->umem);
+ rte_free(page);
+ } else {
+ /* Mark in bitmap that this door-bell is not in use. */
+ offset /= MLX5_DBR_SIZE;
+ int i = offset / 64;
+ int j = offset % 64;
+
+ page->dbr_bitmap[i] &= ~(1 << j);
+ }
+ return ret;
+}
+
+int
+rte_pmd_mlx5_get_dyn_flag_names(char *names[], unsigned int n)
+{
+ static const char *const dynf_names[] = {
+ RTE_PMD_MLX5_FINE_GRANULARITY_INLINE,
+ RTE_MBUF_DYNFLAG_METADATA_NAME
+ };
+ unsigned int i;
+
+ if (n < RTE_DIM(dynf_names))
+ return -ENOMEM;
+ for (i = 0; i < RTE_DIM(dynf_names); i++) {
+ if (names[i] == NULL)
+ return -EINVAL;
+ strcpy(names[i], dynf_names[i]);
+ }
+ return RTE_DIM(dynf_names);
+}
+
+/**
+ * Check sibling device configurations.
+ *
+ * Sibling devices sharing the Infiniband device context
+ * should have compatible configurations. This regards
+ * representors and bonding slaves.
+ *
+ * @param priv
+ * Private device descriptor.
+ * @param config
+ * Configuration of the device is going to be created.
+ *
+ * @return
+ * 0 on success, EINVAL otherwise
+ */
+static int
+mlx5_dev_check_sibling_config(struct mlx5_priv *priv,
+ struct mlx5_dev_config *config)
+{
+ struct mlx5_ibv_shared *sh = priv->sh;
+ struct mlx5_dev_config *sh_conf = NULL;
+ uint16_t port_id;
+
+ MLX5_ASSERT(sh);
+ /* Nothing to compare for the single/first device. */
+ if (sh->refcnt == 1)
+ return 0;
+ /* Find the device with shared context. */
+ MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
+ struct mlx5_priv *opriv =
+ rte_eth_devices[port_id].data->dev_private;