+ if (sh->port_id_action_list) {
+ mlx5_list_destroy(sh->port_id_action_list);
+ sh->port_id_action_list = NULL;
+ }
+ if (sh->push_vlan_action_list) {
+ mlx5_list_destroy(sh->push_vlan_action_list);
+ sh->push_vlan_action_list = NULL;
+ }
+ if (sh->sample_action_list) {
+ mlx5_list_destroy(sh->sample_action_list);
+ sh->sample_action_list = NULL;
+ }
+ if (sh->dest_array_list) {
+ mlx5_list_destroy(sh->dest_array_list);
+ sh->dest_array_list = NULL;
+ }
+}
+
+/**
+ * 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) {
+ 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;
+}
+
+/**
+ * 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(MLX5_MP_NAME,
+ mlx5_mp_os_primary_handle);
+ if (ret)
+ goto out;
+ sd->init_done = true;
+ break;
+ case RTE_PROC_SECONDARY:
+ if (ld->init_done)
+ break;
+ ret = mlx5_mp_init_secondary(MLX5_MP_NAME,
+ mlx5_mp_os_secondary_handle);
+ if (ret)
+ goto out;
+ ++sd->secondary_cnt;
+ ld->init_done = true;
+ break;
+ default:
+ break;
+ }
+out:
+ rte_spinlock_unlock(&sd->lock);
+ return ret;
+}
+
+/**
+ * Create the Tx queue DevX/Verbs object.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param idx
+ * Queue index in DPDK Tx queue array.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx5_os_txq_obj_new(struct rte_eth_dev *dev, uint16_t idx)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_txq_data *txq_data = (*priv->txqs)[idx];
+ struct mlx5_txq_ctrl *txq_ctrl =
+ container_of(txq_data, struct mlx5_txq_ctrl, txq);
+
+ if (txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN)
+ return mlx5_txq_devx_obj_new(dev, idx);
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+ if (!priv->config.dv_esw_en)
+ return mlx5_txq_devx_obj_new(dev, idx);
+#endif
+ return mlx5_txq_ibv_obj_new(dev, idx);
+}
+
+/**
+ * Release an Tx DevX/verbs queue object.
+ *
+ * @param txq_obj
+ * DevX/Verbs Tx queue object.
+ */
+static void
+mlx5_os_txq_obj_release(struct mlx5_txq_obj *txq_obj)
+{
+ if (txq_obj->txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN) {
+ mlx5_txq_devx_obj_release(txq_obj);
+ return;
+ }
+#ifdef HAVE_MLX5DV_DEVX_UAR_OFFSET
+ if (!txq_obj->txq_ctrl->priv->config.dv_esw_en) {
+ mlx5_txq_devx_obj_release(txq_obj);
+ return;
+ }
+#endif
+ mlx5_txq_ibv_obj_release(txq_obj);
+}
+
+/**
+ * DV flow counter mode detect and config.
+ *
+ * @param dev
+ * Pointer to rte_eth_dev structure.
+ *
+ */
+static void
+mlx5_flow_counter_mode_config(struct rte_eth_dev *dev __rte_unused)
+{
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ struct mlx5_priv *priv = dev->data->dev_private;
+ struct mlx5_dev_ctx_shared *sh = priv->sh;
+ bool fallback;
+
+#ifndef HAVE_IBV_DEVX_ASYNC
+ fallback = true;
+#else
+ fallback = false;
+ if (!priv->config.devx || !priv->config.dv_flow_en ||
+ !priv->config.hca_attr.flow_counters_dump ||
+ !(priv->config.hca_attr.flow_counter_bulk_alloc_bitmap & 0x4) ||
+ (mlx5_flow_dv_discover_counter_offset_support(dev) == -ENOTSUP))
+ fallback = true;
+#endif
+ if (fallback)
+ DRV_LOG(INFO, "Use fall-back DV counter management. Flow "
+ "counter dump:%d, bulk_alloc_bitmap:0x%hhx.",
+ priv->config.hca_attr.flow_counters_dump,
+ priv->config.hca_attr.flow_counter_bulk_alloc_bitmap);
+ /* Initialize fallback mode only on the port initializes sh. */
+ if (sh->refcnt == 1)
+ sh->cmng.counter_fallback = fallback;
+ else if (fallback != sh->cmng.counter_fallback)
+ DRV_LOG(WARNING, "Port %d in sh has different fallback mode "
+ "with others:%d.", PORT_ID(priv), fallback);
+#endif
+}
+
+/**
+ * DR flow drop action support detect.
+ *
+ * @param dev
+ * Pointer to rte_eth_dev structure.
+ *
+ */
+static void
+mlx5_flow_drop_action_config(struct rte_eth_dev *dev __rte_unused)
+{
+#ifdef HAVE_MLX5DV_DR
+ struct mlx5_priv *priv = dev->data->dev_private;
+
+ if (!priv->config.dv_flow_en || !priv->sh->dr_drop_action)
+ return;
+ /**
+ * DR supports drop action placeholder when it is supported;
+ * otherwise, use the queue drop action.
+ */
+ if (mlx5_flow_discover_dr_action_support(dev))
+ priv->root_drop_action = priv->drop_queue.hrxq->action;
+ else
+ priv->root_drop_action = priv->sh->dr_drop_action;
+#endif
+}
+
+static void
+mlx5_queue_counter_id_prepare(struct rte_eth_dev *dev)
+{
+ struct mlx5_priv *priv = dev->data->dev_private;
+ void *ctx = priv->sh->ctx;
+
+ priv->q_counters = mlx5_devx_cmd_queue_counter_alloc(ctx);
+ if (!priv->q_counters) {
+ struct ibv_cq *cq = mlx5_glue->create_cq(ctx, 1, NULL, NULL, 0);
+ struct ibv_wq *wq;
+
+ DRV_LOG(DEBUG, "Port %d queue counter object cannot be created "
+ "by DevX - fall-back to use the kernel driver global "
+ "queue counter.", dev->data->port_id);
+ /* Create WQ by kernel and query its queue counter ID. */
+ if (cq) {
+ wq = mlx5_glue->create_wq(ctx,
+ &(struct ibv_wq_init_attr){
+ .wq_type = IBV_WQT_RQ,
+ .max_wr = 1,
+ .max_sge = 1,
+ .pd = priv->sh->pd,
+ .cq = cq,
+ });
+ if (wq) {
+ /* Counter is assigned only on RDY state. */
+ int ret = mlx5_glue->modify_wq(wq,
+ &(struct ibv_wq_attr){
+ .attr_mask = IBV_WQ_ATTR_STATE,
+ .wq_state = IBV_WQS_RDY,
+ });
+
+ if (ret == 0)
+ mlx5_devx_cmd_wq_query(wq,
+ &priv->counter_set_id);
+ claim_zero(mlx5_glue->destroy_wq(wq));
+ }
+ claim_zero(mlx5_glue->destroy_cq(cq));
+ }
+ } else {
+ priv->counter_set_id = priv->q_counters->id;
+ }
+ if (priv->counter_set_id == 0)
+ DRV_LOG(INFO, "Part of the port %d statistics will not be "
+ "available.", dev->data->port_id);
+}
+
+/**
+ * Check if representor spawn info match devargs.
+ *
+ * @param spawn
+ * Verbs device parameters (name, port, switch_info) to spawn.
+ * @param eth_da
+ * Device devargs to probe.
+ *
+ * @return
+ * Match result.
+ */
+static bool
+mlx5_representor_match(struct mlx5_dev_spawn_data *spawn,
+ struct rte_eth_devargs *eth_da)
+{
+ struct mlx5_switch_info *switch_info = &spawn->info;
+ unsigned int p, f;
+ uint16_t id;
+ uint16_t repr_id = mlx5_representor_id_encode(switch_info,
+ eth_da->type);
+
+ switch (eth_da->type) {
+ case RTE_ETH_REPRESENTOR_SF:
+ if (!(spawn->info.port_name == -1 &&
+ switch_info->name_type ==
+ MLX5_PHYS_PORT_NAME_TYPE_PFHPF) &&
+ switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFSF) {
+ rte_errno = EBUSY;
+ return false;
+ }
+ break;
+ case RTE_ETH_REPRESENTOR_VF:
+ /* Allows HPF representor index -1 as exception. */
+ if (!(spawn->info.port_name == -1 &&
+ switch_info->name_type ==
+ MLX5_PHYS_PORT_NAME_TYPE_PFHPF) &&
+ switch_info->name_type != MLX5_PHYS_PORT_NAME_TYPE_PFVF) {
+ rte_errno = EBUSY;
+ return false;
+ }
+ break;
+ case RTE_ETH_REPRESENTOR_NONE:
+ rte_errno = EBUSY;
+ return false;
+ default:
+ rte_errno = ENOTSUP;
+ DRV_LOG(ERR, "unsupported representor type");
+ return false;
+ }
+ /* Check representor ID: */
+ for (p = 0; p < eth_da->nb_ports; ++p) {
+ if (spawn->pf_bond < 0) {
+ /* For non-LAG mode, allow and ignore pf. */
+ switch_info->pf_num = eth_da->ports[p];
+ repr_id = mlx5_representor_id_encode(switch_info,
+ eth_da->type);
+ }
+ for (f = 0; f < eth_da->nb_representor_ports; ++f) {
+ id = MLX5_REPRESENTOR_ID
+ (eth_da->ports[p], eth_da->type,
+ eth_da->representor_ports[f]);
+ if (repr_id == id)
+ return true;
+ }
+ }
+ rte_errno = EBUSY;
+ return false;