static LIST_HEAD(, mlx5_ibv_shared) mlx5_ibv_list = LIST_HEAD_INITIALIZER();
static pthread_mutex_t mlx5_ibv_list_mutex = PTHREAD_MUTEX_INITIALIZER;
+#define MLX5_FLOW_MIN_ID_POOL_SIZE 512
+#define MLX5_ID_GENERATION_ARRAY_FACTOR 16
+
+/**
+ * Allocate ID pool structure.
+ *
+ * @return
+ * Pointer to pool object, NULL value otherwise.
+ */
+struct mlx5_flow_id_pool *
+mlx5_flow_id_pool_alloc(void)
+{
+ struct mlx5_flow_id_pool *pool;
+ void *mem;
+
+ pool = rte_zmalloc("id pool allocation", sizeof(*pool),
+ RTE_CACHE_LINE_SIZE);
+ if (!pool) {
+ DRV_LOG(ERR, "can't allocate id pool");
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+ mem = rte_zmalloc("", MLX5_FLOW_MIN_ID_POOL_SIZE * sizeof(uint32_t),
+ RTE_CACHE_LINE_SIZE);
+ if (!mem) {
+ DRV_LOG(ERR, "can't allocate mem for id pool");
+ rte_errno = ENOMEM;
+ goto error;
+ }
+ pool->free_arr = mem;
+ pool->curr = pool->free_arr;
+ pool->last = pool->free_arr + MLX5_FLOW_MIN_ID_POOL_SIZE;
+ pool->base_index = 0;
+ return pool;
+error:
+ rte_free(pool);
+ return NULL;
+}
+
+/**
+ * Release ID pool structure.
+ *
+ * @param[in] pool
+ * Pointer to flow id pool object to free.
+ */
+void
+mlx5_flow_id_pool_release(struct mlx5_flow_id_pool *pool)
+{
+ rte_free(pool->free_arr);
+ rte_free(pool);
+}
+
+/**
+ * Generate ID.
+ *
+ * @param[in] pool
+ * Pointer to flow id pool.
+ * @param[out] id
+ * The generated ID.
+ *
+ * @return
+ * 0 on success, error value otherwise.
+ */
+uint32_t
+mlx5_flow_id_get(struct mlx5_flow_id_pool *pool, uint32_t *id)
+{
+ if (pool->curr == pool->free_arr) {
+ if (pool->base_index == UINT32_MAX) {
+ rte_errno = ENOMEM;
+ DRV_LOG(ERR, "no free id");
+ return -rte_errno;
+ }
+ *id = ++pool->base_index;
+ return 0;
+ }
+ *id = *(--pool->curr);
+ return 0;
+}
+
+/**
+ * Release ID.
+ *
+ * @param[in] pool
+ * Pointer to flow id pool.
+ * @param[out] id
+ * The generated ID.
+ *
+ * @return
+ * 0 on success, error value otherwise.
+ */
+uint32_t
+mlx5_flow_id_release(struct mlx5_flow_id_pool *pool, uint32_t id)
+{
+ uint32_t size;
+ uint32_t size2;
+ void *mem;
+
+ if (pool->curr == pool->last) {
+ size = pool->curr - pool->free_arr;
+ size2 = size * MLX5_ID_GENERATION_ARRAY_FACTOR;
+ assert(size2 > size);
+ mem = rte_malloc("", size2 * sizeof(uint32_t), 0);
+ if (!mem) {
+ DRV_LOG(ERR, "can't allocate mem for id pool");
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ memcpy(mem, pool->free_arr, size * sizeof(uint32_t));
+ rte_free(pool->free_arr);
+ pool->free_arr = mem;
+ pool->curr = pool->free_arr + size;
+ pool->last = pool->free_arr + size2;
+ }
+ *pool->curr = id;
+ pool->curr++;
+ return 0;
+}
+
/**
* Initialize the counters management structure.
*
struct mlx5_ibv_shared *sh;
int err = 0;
uint32_t i;
+#ifdef HAVE_IBV_FLOW_DV_SUPPORT
+ struct mlx5_devx_tis_attr tis_attr = { 0 };
+#endif
- assert(spawn);
+assert(spawn);
/* Secondary process should not create the shared context. */
assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
pthread_mutex_lock(&mlx5_ibv_list_mutex);
* there is no interrupt subhandler installed for
* the given port index i.
*/
- for (i = 0; i < sh->max_port; i++)
+ for (i = 0; i < sh->max_port; i++) {
sh->port[i].ih_port_id = RTE_MAX_ETHPORTS;
+ sh->port[i].devx_ih_port_id = RTE_MAX_ETHPORTS;
+ }
sh->pd = mlx5_glue->alloc_pd(sh->ctx);
if (sh->pd == NULL) {
DRV_LOG(ERR, "PD allocation failure");
goto error;
}
#ifdef HAVE_IBV_FLOW_DV_SUPPORT
- err = mlx5_get_pdn(sh->pd, &sh->pdn);
- if (err) {
- DRV_LOG(ERR, "Fail to extract pdn from PD");
+ if (sh->devx) {
+ err = mlx5_get_pdn(sh->pd, &sh->pdn);
+ if (err) {
+ DRV_LOG(ERR, "Fail to extract pdn from PD");
+ goto error;
+ }
+ sh->td = mlx5_devx_cmd_create_td(sh->ctx);
+ if (!sh->td) {
+ DRV_LOG(ERR, "TD allocation failure");
+ err = ENOMEM;
+ goto error;
+ }
+ tis_attr.transport_domain = sh->td->id;
+ sh->tis = mlx5_devx_cmd_create_tis(sh->ctx, &tis_attr);
+ if (!sh->tis) {
+ DRV_LOG(ERR, "TIS allocation failure");
+ err = ENOMEM;
+ goto error;
+ }
+ }
+ sh->flow_id_pool = mlx5_flow_id_pool_alloc();
+ if (!sh->flow_id_pool) {
+ DRV_LOG(ERR, "can't create flow id pool");
+ err = ENOMEM;
goto error;
}
#endif /* HAVE_IBV_FLOW_DV_SUPPORT */
error:
pthread_mutex_unlock(&mlx5_ibv_list_mutex);
assert(sh);
+ if (sh->tis)
+ claim_zero(mlx5_devx_cmd_destroy(sh->tis));
+ if (sh->td)
+ claim_zero(mlx5_devx_cmd_destroy(sh->td));
if (sh->pd)
claim_zero(mlx5_glue->dealloc_pd(sh->pd));
if (sh->ctx)
claim_zero(mlx5_glue->close_device(sh->ctx));
+ if (sh->flow_id_pool)
+ mlx5_flow_id_pool_release(sh->flow_id_pool);
rte_free(sh);
assert(err > 0);
rte_errno = err;
if (sh->intr_cnt)
mlx5_intr_callback_unregister
(&sh->intr_handle, mlx5_dev_interrupt_handler, sh);
+#ifdef HAVE_MLX5_DEVX_ASYNC_SUPPORT
+ if (sh->devx_intr_cnt) {
+ if (sh->intr_handle_devx.fd)
+ rte_intr_callback_unregister(&sh->intr_handle_devx,
+ mlx5_dev_interrupt_handler_devx, sh);
+ if (sh->devx_comp)
+ mlx5dv_devx_destroy_cmd_comp(sh->devx_comp);
+ }
+#endif
pthread_mutex_destroy(&sh->intr_mutex);
if (sh->pd)
claim_zero(mlx5_glue->dealloc_pd(sh->pd));
+ if (sh->tis)
+ claim_zero(mlx5_devx_cmd_destroy(sh->tis));
+ if (sh->td)
+ claim_zero(mlx5_devx_cmd_destroy(sh->td));
if (sh->ctx)
claim_zero(mlx5_glue->close_device(sh->ctx));
+ if (sh->flow_id_pool)
+ mlx5_flow_id_pool_release(sh->flow_id_pool);
rte_free(sh);
exit:
pthread_mutex_unlock(&mlx5_ibv_list_mutex);
((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);
mlx5_traffic_disable(dev);
mlx5_flow_flush(dev, NULL);
/* Prevent crashes when queues are still in use. */
if (ret)
DRV_LOG(WARNING, "port %u some Rx queues still remain",
dev->data->port_id);
- ret = mlx5_txq_ibv_verify(dev);
+ ret = mlx5_txq_obj_verify(dev);
if (ret)
DRV_LOG(WARNING, "port %u some Verbs Tx queue still remain",
dev->data->port_id);
unsigned int c = 0;
uint16_t port_id;
- MLX5_ETH_FOREACH_DEV(port_id) {
+ MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
struct mlx5_priv *opriv =
rte_eth_devices[port_id].data->dev_private;
.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,
.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,
};
/* Available operations from secondary process. */
.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,
.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,
};
/**
return ret;
}
+/**
+ * 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;
+
+ 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;
+
+ if (opriv && opriv != priv && opriv->sh == sh) {
+ sh_conf = &opriv->config;
+ break;
+ }
+ }
+ if (!sh_conf)
+ return 0;
+ if (sh_conf->dv_flow_en ^ config->dv_flow_en) {
+ DRV_LOG(ERR, "\"dv_flow_en\" configuration mismatch"
+ " for shared %s context", sh->ibdev_name);
+ rte_errno = EINVAL;
+ return rte_errno;
+ }
+ return 0;
+}
/**
* Spawn an Ethernet device from Verbs information.
*
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
*/
devx_port.comp_mask = MLX5DV_DEVX_PORT_VPORT |
MLX5DV_DEVX_PORT_MATCH_REG_C_0;
- err = mlx5dv_query_devx_port(sh->ctx, spawn->ibv_port, &devx_port);
+ 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\n",
spawn->ibv_port, spawn->ibv_dev->name);
* Look for sibling devices in order to reuse their switch domain
* if any, otherwise allocate one.
*/
- MLX5_ETH_FOREACH_DEV(port_id) {
+ MLX5_ETH_FOREACH_DEV(port_id, priv->pci_dev) {
const struct mlx5_priv *opriv =
rte_eth_devices[port_id].data->dev_private;
strerror(rte_errno));
goto error;
}
+ err = mlx5_dev_check_sibling_config(priv, &config);
+ if (err)
+ goto error;
config.hw_csum = !!(sh->device_attr.device_cap_flags_ex &
IBV_DEVICE_RAW_IP_CSUM);
DRV_LOG(DEBUG, "checksum offloading is %ssupported",
if (priv->counter_fallback)
DRV_LOG(INFO, "Use fall-back DV counter management\n");
/* Check for LRO support. */
- if (config.dest_tir && config.hca_attr.lro_cap) {
+ if (config.dest_tir && config.hca_attr.lro_cap &&
+ config.dv_flow_en) {
/* TBD check tunnel lro caps. */
config.lro.supported = config.hca_attr.lro_cap;
DRV_LOG(DEBUG, "Device supports LRO");
rte_eth_copy_pci_info(list[i].eth_dev, pci_dev);
/* Restore non-PCI flags cleared by the above call. */
list[i].eth_dev->data->dev_flags |= restore;
+ mlx5_dev_interrupt_handler_devx_install(list[i].eth_dev);
rte_eth_dev_probing_finish(list[i].eth_dev);
}
if (i != ns) {
return ret;
}
+/**
+ * Look for the ethernet device belonging to mlx5 driver.
+ *
+ * @param[in] port_id
+ * port_id to start looking for device.
+ * @param[in] pci_dev
+ * Pointer to the hint PCI device. When device is being probed
+ * the its siblings (master and preceding representors might
+ * not have assigned driver yet (because the mlx5_pci_probe()
+ * is not completed yet, for this case match on hint PCI
+ * device may be used to detect sibling device.
+ *
+ * @return
+ * port_id of found device, RTE_MAX_ETHPORT if not found.
+ */
uint16_t
-mlx5_eth_find_next(uint16_t port_id)
+mlx5_eth_find_next(uint16_t port_id, struct rte_pci_device *pci_dev)
{
while (port_id < RTE_MAX_ETHPORTS) {
struct rte_eth_dev *dev = &rte_eth_devices[port_id];
if (dev->state != RTE_ETH_DEV_UNUSED &&
dev->device &&
- dev->device->driver &&
- dev->device->driver->name &&
- !strcmp(dev->device->driver->name, MLX5_DRIVER_NAME))
+ (dev->device == &pci_dev->device ||
+ (dev->device->driver &&
+ dev->device->driver->name &&
+ !strcmp(dev->device->driver->name, MLX5_DRIVER_NAME))))
break;
port_id++;
}