diff options
Diffstat (limited to '')
-rw-r--r-- | drivers/net/ethernet/mellanox/mlx5/core/main.c | 121 |
1 files changed, 85 insertions, 36 deletions
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index a92a92a52346..2c774f367199 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -98,6 +98,8 @@ enum { MLX5_ATOMIC_REQ_MODE_HOST_ENDIANNESS = 0x1, }; +#define LOG_MAX_SUPPORTED_QPS 0xff + static struct mlx5_profile profile[] = { [0] = { .mask = 0, @@ -109,7 +111,7 @@ static struct mlx5_profile profile[] = { [2] = { .mask = MLX5_PROF_MASK_QP_SIZE | MLX5_PROF_MASK_MR_CACHE, - .log_max_qp = 18, + .log_max_qp = LOG_MAX_SUPPORTED_QPS, .mr_cache[0] = { .size = 500, .limit = 250 @@ -484,10 +486,26 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev, void *set_ctx) return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_ODP); } +static int max_uc_list_get_devlink_param(struct mlx5_core_dev *dev) +{ + struct devlink *devlink = priv_to_devlink(dev); + union devlink_param_value val; + int err; + + err = devlink_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MAX_MACS, + &val); + if (!err) + return val.vu32; + mlx5_core_dbg(dev, "Failed to get param. err = %d\n", err); + return err; +} + static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) { struct mlx5_profile *prof = &dev->profile; void *set_hca_cap; + int max_uc_list; int err; err = mlx5_core_get_caps(dev, MLX5_CAP_GENERAL); @@ -507,7 +525,9 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) to_fw_pkey_sz(dev, 128)); /* Check log_max_qp from HCA caps to set in current profile */ - if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { + if (prof->log_max_qp == LOG_MAX_SUPPORTED_QPS) { + prof->log_max_qp = MLX5_CAP_GEN_MAX(dev, log_max_qp); + } else if (MLX5_CAP_GEN_MAX(dev, log_max_qp) < prof->log_max_qp) { mlx5_core_warn(dev, "log_max_qp value in current profile is %d, changing it to HCA capability limit (%d)\n", prof->log_max_qp, MLX5_CAP_GEN_MAX(dev, log_max_qp)); @@ -561,6 +581,11 @@ static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) if (MLX5_CAP_GEN(dev, roce_rw_supported)) MLX5_SET(cmd_hca_cap, set_hca_cap, roce, mlx5_is_roce_init_enabled(dev)); + max_uc_list = max_uc_list_get_devlink_param(dev); + if (max_uc_list > 0) + MLX5_SET(cmd_hca_cap, set_hca_cap, log_max_current_uc_list, + ilog2(max_uc_list)); + return set_caps(dev, set_ctx, MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE); } @@ -992,11 +1017,7 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (mlx5_core_is_pf(dev)) pcie_print_link_status(dev->pdev); - err = mlx5_tout_init(dev); - if (err) { - mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); - return err; - } + mlx5_tout_set_def_val(dev); /* wait for firmware to accept initialization segments configurations */ @@ -1005,13 +1026,13 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) if (err) { mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n", mlx5_tout_ms(dev, FW_PRE_INIT_TIMEOUT)); - goto err_tout_cleanup; + return err; } err = mlx5_cmd_init(dev); if (err) { mlx5_core_err(dev, "Failed initializing command interface, aborting\n"); - goto err_tout_cleanup; + return err; } mlx5_tout_query_iseg(dev); @@ -1075,18 +1096,16 @@ static int mlx5_function_setup(struct mlx5_core_dev *dev, bool boot) mlx5_set_driver_version(dev); - mlx5_start_health_poll(dev); - err = mlx5_query_hca_caps(dev); if (err) { mlx5_core_err(dev, "query hca failed\n"); - goto stop_health; + goto reclaim_boot_pages; } + mlx5_start_health_poll(dev); + return 0; -stop_health: - mlx5_stop_health_poll(dev, boot); reclaim_boot_pages: mlx5_reclaim_startup_pages(dev); err_disable_hca: @@ -1094,8 +1113,6 @@ err_disable_hca: err_cmd_cleanup: mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); -err_tout_cleanup: - mlx5_tout_cleanup(dev); return err; } @@ -1114,7 +1131,6 @@ static int mlx5_function_teardown(struct mlx5_core_dev *dev, bool boot) mlx5_core_disable_hca(dev, 0); mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN); mlx5_cmd_cleanup(dev); - mlx5_tout_cleanup(dev); return 0; } @@ -1476,6 +1492,12 @@ int mlx5_mdev_init(struct mlx5_core_dev *dev, int profile_idx) mlx5_debugfs_root); INIT_LIST_HEAD(&priv->traps); + err = mlx5_tout_init(dev); + if (err) { + mlx5_core_err(dev, "Failed initializing timeouts, aborting\n"); + goto err_timeout_init; + } + err = mlx5_health_init(dev); if (err) goto err_health_init; @@ -1501,6 +1523,8 @@ err_adev_init: err_pagealloc_init: mlx5_health_cleanup(dev); err_health_init: + mlx5_tout_cleanup(dev); +err_timeout_init: debugfs_remove(dev->priv.dbg_root); mutex_destroy(&priv->pgdir_mutex); mutex_destroy(&priv->alloc_mutex); @@ -1518,6 +1542,7 @@ void mlx5_mdev_uninit(struct mlx5_core_dev *dev) mlx5_adev_cleanup(dev); mlx5_pagealloc_cleanup(dev); mlx5_health_cleanup(dev); + mlx5_tout_cleanup(dev); debugfs_remove_recursive(dev->priv.dbg_root); mutex_destroy(&priv->pgdir_mutex); mutex_destroy(&priv->alloc_mutex); @@ -1604,12 +1629,28 @@ static void remove_one(struct pci_dev *pdev) mlx5_devlink_free(devlink); } +#define mlx5_pci_trace(dev, fmt, ...) ({ \ + struct mlx5_core_dev *__dev = (dev); \ + mlx5_core_info(__dev, "%s Device state = %d health sensors: %d pci_status: %d. " fmt, \ + __func__, __dev->state, mlx5_health_check_fatal_sensors(__dev), \ + __dev->pci_status, ##__VA_ARGS__); \ +}) + +static const char *result2str(enum pci_ers_result result) +{ + return result == PCI_ERS_RESULT_NEED_RESET ? "need reset" : + result == PCI_ERS_RESULT_DISCONNECT ? "disconnect" : + result == PCI_ERS_RESULT_RECOVERED ? "recovered" : + "unknown"; +} + static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t state) { struct mlx5_core_dev *dev = pci_get_drvdata(pdev); + enum pci_ers_result res; - mlx5_core_info(dev, "%s was called\n", __func__); + mlx5_pci_trace(dev, "Enter, pci channel state = %d\n", state); mlx5_enter_error_state(dev, false); mlx5_error_sw_reset(dev); @@ -1617,8 +1658,11 @@ static pci_ers_result_t mlx5_pci_err_detected(struct pci_dev *pdev, mlx5_drain_health_wq(dev); mlx5_pci_disable_device(dev); - return state == pci_channel_io_perm_failure ? + res = state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; + + mlx5_pci_trace(dev, "Exit, result = %d, %s\n", res, result2str(res)); + return res; } /* wait for the device to show vital signs by waiting @@ -1652,28 +1696,34 @@ static int wait_vital(struct pci_dev *pdev) static pci_ers_result_t mlx5_pci_slot_reset(struct pci_dev *pdev) { + enum pci_ers_result res = PCI_ERS_RESULT_DISCONNECT; struct mlx5_core_dev *dev = pci_get_drvdata(pdev); int err; - mlx5_core_info(dev, "%s was called\n", __func__); + mlx5_pci_trace(dev, "Enter\n"); err = mlx5_pci_enable_device(dev); if (err) { mlx5_core_err(dev, "%s: mlx5_pci_enable_device failed with error code: %d\n", __func__, err); - return PCI_ERS_RESULT_DISCONNECT; + goto out; } pci_set_master(pdev); pci_restore_state(pdev); pci_save_state(pdev); - if (wait_vital(pdev)) { - mlx5_core_err(dev, "%s: wait_vital timed out\n", __func__); - return PCI_ERS_RESULT_DISCONNECT; + err = wait_vital(pdev); + if (err) { + mlx5_core_err(dev, "%s: wait vital failed with error code: %d\n", + __func__, err); + goto out; } - return PCI_ERS_RESULT_RECOVERED; + res = PCI_ERS_RESULT_RECOVERED; +out: + mlx5_pci_trace(dev, "Exit, err = %d, result = %d, %s\n", err, res, result2str(res)); + return res; } static void mlx5_pci_resume(struct pci_dev *pdev) @@ -1681,14 +1731,12 @@ static void mlx5_pci_resume(struct pci_dev *pdev) struct mlx5_core_dev *dev = pci_get_drvdata(pdev); int err; - mlx5_core_info(dev, "%s was called\n", __func__); + mlx5_pci_trace(dev, "Enter, loading driver..\n"); err = mlx5_load_one(dev); - if (err) - mlx5_core_err(dev, "%s: mlx5_load_one failed with error code: %d\n", - __func__, err); - else - mlx5_core_info(dev, "%s: device recovered\n", __func__); + + mlx5_pci_trace(dev, "Done, err = %d, device %s\n", err, + !err ? "recovered" : "Failed"); } static const struct pci_error_handlers mlx5_err_handler = { @@ -1809,12 +1857,13 @@ void mlx5_disable_device(struct mlx5_core_dev *dev) int mlx5_recover_device(struct mlx5_core_dev *dev) { - int ret = -EIO; + if (!mlx5_core_is_sf(dev)) { + mlx5_pci_disable_device(dev); + if (mlx5_pci_slot_reset(dev->pdev) != PCI_ERS_RESULT_RECOVERED) + return -EIO; + } - mlx5_pci_disable_device(dev); - if (mlx5_pci_slot_reset(dev->pdev) == PCI_ERS_RESULT_RECOVERED) - ret = mlx5_load_one(dev); - return ret; + return mlx5_load_one(dev); } static struct pci_driver mlx5_core_driver = { |