* Pointer to RQ channel object, which includes the channel fd
*
* @param[out] fd
- * The file descriptor (representing the intetrrupt) used in this channel.
+ * The file descriptor (representing the interrupt) used in this channel.
*
* @return
* 0 on successfully setting the fd to non-blocking, non-zero otherwise.
flow_dv_dest_array_clone_free_cb);
if (!sh->dest_array_list)
goto error;
+ /* Init shared flex parsers list, no need lcore_share */
+ snprintf(s, sizeof(s), "%s_flex_parsers_list", sh->ibdev_name);
+ sh->flex_parsers_dv = mlx5_list_create(s, sh, false,
+ mlx5_flex_parser_create_cb,
+ mlx5_flex_parser_match_cb,
+ mlx5_flex_parser_remove_cb,
+ mlx5_flex_parser_clone_cb,
+ mlx5_flex_parser_clone_free_cb);
+ if (!sh->flex_parsers_dv)
+ goto error;
#endif
#ifdef HAVE_MLX5DV_DR
void *domain;
mlx5_glue->dr_create_flow_action_default_miss();
if (!sh->default_miss_action)
DRV_LOG(WARNING, "Default miss action is not supported.");
+ LIST_INIT(&sh->shared_rxqs);
return 0;
error:
/* Rollback the created objects. */
MLX5_ASSERT(sh && sh->refcnt);
if (sh->refcnt > 1)
return;
+ MLX5_ASSERT(LIST_EMPTY(&sh->shared_rxqs));
#ifdef HAVE_MLX5DV_DR
if (sh->rx_domain) {
mlx5_glue->dr_destroy_domain(sh->rx_domain);
* 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
+ if (!priv->sh->drop_action_check_flag) {
+ if (!mlx5_flow_discover_dr_action_support(dev))
+ priv->sh->dr_drop_action_en = 1;
+ priv->sh->drop_action_check_flag = 1;
+ }
+ if (priv->sh->dr_drop_action_en)
priv->root_drop_action = priv->sh->dr_drop_action;
+ else
+ priv->root_drop_action = priv->drop_queue.hrxq->action;
#endif
}
return false;
}
-
/**
* Spawn an Ethernet device from Verbs information.
*
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;
mprq_caps.max_single_wqe_log_num_of_strides);
DRV_LOG(DEBUG, "\tsupported_qpts: %d",
mprq_caps.supported_qpts);
+ DRV_LOG(DEBUG, "\tmin_stride_wqe_log_size: %d",
+ config->mprq.log_min_stride_wqe_size);
DRV_LOG(DEBUG, "device supports Multi-Packet RQ");
mprq = 1;
- mprq_min_stride_size_n =
+ config->mprq.log_min_stride_size =
mprq_caps.min_single_stride_log_num_of_bytes;
- mprq_max_stride_size_n =
+ config->mprq.log_max_stride_size =
mprq_caps.max_single_stride_log_num_of_bytes;
- mprq_min_stride_num_n =
+ config->mprq.log_min_stride_num =
mprq_caps.min_single_wqe_log_num_of_strides;
- mprq_max_stride_num_n =
+ config->mprq.log_max_stride_num =
mprq_caps.max_single_wqe_log_num_of_strides;
}
#endif
* Remove this check once DPDK supports larger/variable
* indirection tables.
*/
- if (config->ind_table_max_size > (unsigned int)ETH_RSS_RETA_SIZE_512)
- config->ind_table_max_size = ETH_RSS_RETA_SIZE_512;
+ if (config->ind_table_max_size > (unsigned int)RTE_ETH_RSS_RETA_SIZE_512)
+ config->ind_table_max_size = RTE_ETH_RSS_RETA_SIZE_512;
DRV_LOG(DEBUG, "maximum Rx indirection table size is %u",
config->ind_table_max_size);
config->hw_vlan_strip = !!(sh->device_attr.raw_packet_caps &
goto error;
#endif
}
+ if (config->std_delay_drop || config->hp_delay_drop) {
+ if (!config->hca_attr.rq_delay_drop) {
+ config->std_delay_drop = 0;
+ config->hp_delay_drop = 0;
+ DRV_LOG(WARNING,
+ "dev_port-%u: Rxq delay drop is not supported",
+ priv->dev_port);
+ }
+ }
if (sh->devx) {
uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];
/*
* If HW has bug working with tunnel packet decapsulation and
* scatter FCS, and decapsulation is needed, clear the hw_fcs_strip
- * bit. Then DEV_RX_OFFLOAD_KEEP_CRC bit will not be set anymore.
+ * bit. Then RTE_ETH_RX_OFFLOAD_KEEP_CRC bit will not be set anymore.
*/
if (config->hca_attr.scatter_fcs_w_decap_disable && config->decap_en)
config->hw_fcs_strip = 0;
DRV_LOG(DEBUG, "FCS stripping configuration is %ssupported",
(config->hw_fcs_strip ? "" : "not "));
- if (config->mprq.enabled && mprq) {
- if (config->mprq.stride_num_n &&
- (config->mprq.stride_num_n > mprq_max_stride_num_n ||
- config->mprq.stride_num_n < mprq_min_stride_num_n)) {
- config->mprq.stride_num_n =
- RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_NUM_N,
- mprq_min_stride_num_n),
- mprq_max_stride_num_n);
- DRV_LOG(WARNING,
- "the number of strides"
- " for Multi-Packet RQ is out of range,"
- " setting default value (%u)",
- 1 << config->mprq.stride_num_n);
- }
- if (config->mprq.stride_size_n &&
- (config->mprq.stride_size_n > mprq_max_stride_size_n ||
- config->mprq.stride_size_n < mprq_min_stride_size_n)) {
- config->mprq.stride_size_n =
- RTE_MIN(RTE_MAX(MLX5_MPRQ_STRIDE_SIZE_N,
- mprq_min_stride_size_n),
- mprq_max_stride_size_n);
- DRV_LOG(WARNING,
- "the size of a stride"
- " for Multi-Packet RQ is out of range,"
- " setting default value (%u)",
- 1 << config->mprq.stride_size_n);
- }
- config->mprq.min_stride_size_n = mprq_min_stride_size_n;
- config->mprq.max_stride_size_n = mprq_max_stride_size_n;
- } else if (config->mprq.enabled && !mprq) {
+ if (config->mprq.enabled && !mprq) {
DRV_LOG(WARNING, "Multi-Packet RQ isn't supported");
config->mprq.enabled = 0;
}
*/
MLX5_ASSERT(spawn->ifindex);
priv->if_index = spawn->ifindex;
+ priv->lag_affinity_idx = sh->refcnt - 1;
eth_dev->data->dev_private = priv;
priv->dev_data = eth_dev->data;
eth_dev->data->mac_addrs = priv->mac;
err = mlx5_alloc_shared_dr(priv);
if (err)
goto error;
+ if (mlx5_flex_item_port_init(eth_dev) < 0)
+ goto error;
}
if (sh->devx && config->dv_flow_en && config->dest_tir) {
priv->obj_ops = devx_obj_ops;
- priv->obj_ops.drop_action_create =
- ibv_obj_ops.drop_action_create;
- priv->obj_ops.drop_action_destroy =
- ibv_obj_ops.drop_action_destroy;
mlx5_queue_counter_id_prepare(eth_dev);
priv->obj_ops.lb_dummy_queue_create =
mlx5_rxq_ibv_obj_dummy_lb_create;
priv->obj_ops = ibv_obj_ops;
}
if (config->tx_pp &&
- (priv->config.dv_esw_en ||
- priv->obj_ops.txq_obj_new != mlx5_txq_devx_obj_new)) {
+ priv->obj_ops.txq_obj_new != mlx5_txq_devx_obj_new) {
/*
* HAVE_MLX5DV_DEVX_UAR_OFFSET is required to support
* packet pacing and already checked above.
priv->drop_queue.hrxq = mlx5_drop_action_create(eth_dev);
if (!priv->drop_queue.hrxq)
goto error;
- /* Supported Verbs flow priority number detection. */
- err = mlx5_flow_discover_priorities(eth_dev);
+ /* Port representor shares the same max priority with pf port. */
+ if (!priv->sh->flow_priority_check_flag) {
+ /* Supported Verbs flow priority number detection. */
+ err = mlx5_flow_discover_priorities(eth_dev);
+ priv->sh->flow_max_priority = err;
+ priv->sh->flow_priority_check_flag = 1;
+ } else {
+ err = priv->sh->flow_max_priority;
+ }
if (err < 0) {
err = -err;
goto error;
}
- priv->config.flow_prio = err;
if (!priv->config.dv_esw_en &&
priv->config.dv_xmeta_en != MLX5_XMETA_MODE_LEGACY) {
DRV_LOG(WARNING, "metadata mode %u is not supported "
goto error;
rte_rwlock_init(&priv->ind_tbls_lock);
/* Query availability of metadata reg_c's. */
- err = mlx5_flow_discover_mreg_c(eth_dev);
- if (err < 0) {
- err = -err;
- goto error;
+ if (!priv->sh->metadata_regc_check_flag) {
+ err = mlx5_flow_discover_mreg_c(eth_dev);
+ if (err < 0) {
+ err = -err;
+ goto error;
+ }
}
if (!mlx5_flow_ext_mreg_supported(eth_dev)) {
DRV_LOG(DEBUG,
claim_zero(rte_eth_switch_domain_free(priv->domain_id));
if (priv->hrxqs)
mlx5_list_destroy(priv->hrxqs);
+ if (eth_dev && priv->flex_item_map)
+ mlx5_flex_item_port_cleanup(eth_dev);
mlx5_free(priv);
if (eth_dev != NULL)
eth_dev->data->dev_private = NULL;
FILE *bond_file = NULL, *file;
int pf = -1;
int ret;
+ uint8_t cur_guid[32] = {0};
+ uint8_t guid[32] = {0};
/*
* Try to get master device name. If something goes wrong suppose
np = mlx5_nl_portnum(nl_rdma, ibdev_name);
if (!np)
return -1;
+ if (mlx5_get_device_guid(pci_dev, cur_guid, sizeof(cur_guid)) < 0)
+ return -1;
/*
* The master device might not be on the predefined port(not on port
* index 1, it is not guaranteed), we have to scan all Infiniband
char tmp_str[IF_NAMESIZE + 32];
struct rte_pci_addr pci_addr;
struct mlx5_switch_info info;
+ int ret;
/* Process slave interface names in the loop. */
snprintf(tmp_str, sizeof(tmp_str),
tmp_str);
break;
}
- /* Match PCI address, allows BDF0+pfx or BDFx+pfx. */
- if (pci_dev->domain == pci_addr.domain &&
- pci_dev->bus == pci_addr.bus &&
- pci_dev->devid == pci_addr.devid &&
- ((pci_dev->function == 0 &&
- pci_dev->function + owner == pci_addr.function) ||
- (pci_dev->function == owner &&
- pci_addr.function == owner)))
- pf = info.port_name;
/* Get ifindex. */
snprintf(tmp_str, sizeof(tmp_str),
"/sys/class/net/%s/ifindex", ifname);
bond_info->ports[info.port_name].pci_addr = pci_addr;
bond_info->ports[info.port_name].ifindex = ifindex;
bond_info->n_port++;
+ /*
+ * Under socket direct mode, bonding will use
+ * system_image_guid as identification.
+ * After OFED 5.4, guid is readable (ret >= 0) under sysfs.
+ * All bonding members should have the same guid even if driver
+ * is using PCIe BDF.
+ */
+ ret = mlx5_get_device_guid(&pci_addr, guid, sizeof(guid));
+ if (ret < 0)
+ break;
+ else if (ret > 0) {
+ if (!memcmp(guid, cur_guid, sizeof(guid)) &&
+ owner == info.port_name &&
+ (owner != 0 || (owner == 0 &&
+ !rte_pci_addr_cmp(pci_dev, &pci_addr))))
+ pf = info.port_name;
+ } else if (pci_dev->domain == pci_addr.domain &&
+ pci_dev->bus == pci_addr.bus &&
+ pci_dev->devid == pci_addr.devid &&
+ ((pci_dev->function == 0 &&
+ pci_dev->function + owner == pci_addr.function) ||
+ (pci_dev->function == owner &&
+ pci_addr.function == owner)))
+ pf = info.port_name;
}
if (pf >= 0) {
/* Get bond interface info */
DRV_LOG(INFO, "PF device %u, bond device %u(%s)",
ifindex, bond_info->ifindex, bond_info->ifname);
}
+ if (owner == 0 && pf != 0) {
+ DRV_LOG(INFO, "PCIe instance %04x:%02x:%02x.%x isn't bonding owner",
+ pci_dev->domain, pci_dev->bus, pci_dev->devid,
+ pci_dev->function);
+ }
return pf;
}
static void
-mlx5_os_config_default(struct mlx5_dev_config *config)
+mlx5_os_config_default(struct mlx5_dev_config *config,
+ struct mlx5_common_dev_config *cconf)
{
memset(config, 0, sizeof(*config));
config->mps = MLX5_ARG_UNSET;
config->vf_nl_en = 1;
config->mprq.max_memcpy_len = MLX5_MPRQ_MEMCPY_DEFAULT_LEN;
config->mprq.min_rxqs_num = MLX5_MPRQ_MIN_RXQS;
+ config->mprq.log_min_stride_wqe_size = cconf->devx ?
+ cconf->hca_attr.log_min_stride_wqe_sz :
+ MLX5_MPRQ_LOG_MIN_STRIDE_WQE_SIZE;
+ config->mprq.log_stride_num = MLX5_MPRQ_DEFAULT_LOG_STRIDE_NUM;
config->dv_esw_en = 1;
config->dv_flow_en = 1;
config->decap_en = 1;
config->log_hp_size = MLX5_ARG_UNSET;
config->allow_duplicate_pattern = 1;
+ config->std_delay_drop = 0;
+ config->hp_delay_drop = 0;
}
/**
/*
* Force standalone bonding
* device for ROCE LAG
- * confgiurations.
+ * configurations.
*/
list[ns].info.master = 0;
list[ns].info.representor = 0;
uint32_t restore;
/* Default configuration. */
- mlx5_os_config_default(&dev_config);
+ mlx5_os_config_default(&dev_config, &cdev->config);
dev_config.vf = dev_config_vf;
list[i].eth_dev = mlx5_dev_spawn(cdev->dev, &list[i],
&dev_config, ð_da);
* Representor interrupts handle is released in mlx5_dev_stop().
*/
if (list[i].info.representor) {
- struct rte_intr_handle *intr_handle;
- intr_handle = mlx5_malloc(MLX5_MEM_SYS | MLX5_MEM_ZERO,
- sizeof(*intr_handle), 0,
- SOCKET_ID_ANY);
- if (!intr_handle) {
+ struct rte_intr_handle *intr_handle =
+ rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED);
+ if (intr_handle == NULL) {
DRV_LOG(ERR,
"port %u failed to allocate memory for interrupt handler "
"Rx interrupts will not be supported",
}
if (ret) {
DRV_LOG(ERR, "Probe of PCI device " PCI_PRI_FMT " "
- "aborted due to proding failure of PF %u",
+ "aborted due to prodding failure of PF %u",
pci_dev->addr.domain, pci_dev->addr.bus,
pci_dev->addr.devid, pci_dev->addr.function,
eth_da.ports[p]);
if (ret != 0)
return ret;
/* Set default config data. */
- mlx5_os_config_default(&config);
+ mlx5_os_config_default(&config, &cdev->config);
config.sf = 1;
/* Init spawn data. */
spawn.max_port = 1;
if (eth_dev == NULL)
return -rte_errno;
/* Post create. */
- eth_dev->intr_handle = &adev->intr_handle;
+ eth_dev->intr_handle = adev->intr_handle;
if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_LSC;
eth_dev->data->dev_flags |= RTE_ETH_DEV_INTR_RMV;
return mlx5_os_auxiliary_probe(cdev);
}
+/**
+ * Cleanup resources when the last device is closed.
+ */
+void
+mlx5_os_net_cleanup(void)
+{
+ mlx5_pmd_socket_uninit();
+}
+
/**
* Install shared asynchronous device events handler.
* This function is implemented to support event sharing
int flags;
struct ibv_context *ctx = sh->cdev->ctx;
- sh->intr_handle.fd = -1;
+ sh->intr_handle = rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED);
+ if (sh->intr_handle == NULL) {
+ DRV_LOG(ERR, "Fail to allocate intr_handle");
+ rte_errno = ENOMEM;
+ return;
+ }
+ rte_intr_fd_set(sh->intr_handle, -1);
+
flags = fcntl(ctx->async_fd, F_GETFL);
ret = fcntl(ctx->async_fd, F_SETFL, flags | O_NONBLOCK);
if (ret) {
DRV_LOG(INFO, "failed to change file descriptor async event"
" queue");
} else {
- sh->intr_handle.fd = ctx->async_fd;
- sh->intr_handle.type = RTE_INTR_HANDLE_EXT;
- if (rte_intr_callback_register(&sh->intr_handle,
+ rte_intr_fd_set(sh->intr_handle, ctx->async_fd);
+ rte_intr_type_set(sh->intr_handle, RTE_INTR_HANDLE_EXT);
+ if (rte_intr_callback_register(sh->intr_handle,
mlx5_dev_interrupt_handler, sh)) {
DRV_LOG(INFO, "Fail to install the shared interrupt.");
- sh->intr_handle.fd = -1;
+ rte_intr_fd_set(sh->intr_handle, -1);
}
}
if (sh->devx) {
#ifdef HAVE_IBV_DEVX_ASYNC
- sh->intr_handle_devx.fd = -1;
+ sh->intr_handle_devx =
+ rte_intr_instance_alloc(RTE_INTR_INSTANCE_F_SHARED);
+ if (!sh->intr_handle_devx) {
+ DRV_LOG(ERR, "Fail to allocate intr_handle");
+ rte_errno = ENOMEM;
+ return;
+ }
+ rte_intr_fd_set(sh->intr_handle_devx, -1);
sh->devx_comp = (void *)mlx5_glue->devx_create_cmd_comp(ctx);
struct mlx5dv_devx_cmd_comp *devx_comp = sh->devx_comp;
if (!devx_comp) {
" devx comp");
return;
}
- sh->intr_handle_devx.fd = devx_comp->fd;
- sh->intr_handle_devx.type = RTE_INTR_HANDLE_EXT;
- if (rte_intr_callback_register(&sh->intr_handle_devx,
+ rte_intr_fd_set(sh->intr_handle_devx, devx_comp->fd);
+ rte_intr_type_set(sh->intr_handle_devx,
+ RTE_INTR_HANDLE_EXT);
+ if (rte_intr_callback_register(sh->intr_handle_devx,
mlx5_dev_interrupt_handler_devx, sh)) {
DRV_LOG(INFO, "Fail to install the devx shared"
" interrupt.");
- sh->intr_handle_devx.fd = -1;
+ rte_intr_fd_set(sh->intr_handle_devx, -1);
}
#endif /* HAVE_IBV_DEVX_ASYNC */
}
void
mlx5_os_dev_shared_handler_uninstall(struct mlx5_dev_ctx_shared *sh)
{
- if (sh->intr_handle.fd >= 0)
- mlx5_intr_callback_unregister(&sh->intr_handle,
+ if (rte_intr_fd_get(sh->intr_handle) >= 0)
+ mlx5_intr_callback_unregister(sh->intr_handle,
mlx5_dev_interrupt_handler, sh);
+ rte_intr_instance_free(sh->intr_handle);
#ifdef HAVE_IBV_DEVX_ASYNC
- if (sh->intr_handle_devx.fd >= 0)
- rte_intr_callback_unregister(&sh->intr_handle_devx,
+ if (rte_intr_fd_get(sh->intr_handle_devx) >= 0)
+ rte_intr_callback_unregister(sh->intr_handle_devx,
mlx5_dev_interrupt_handler_devx, sh);
+ rte_intr_instance_free(sh->intr_handle_devx);
if (sh->devx_comp)
mlx5_glue->devx_destroy_cmd_comp(sh->devx_comp);
#endif