diff options
author | Thomas Zimmermann <tzimmermann@suse.de> | 2020-08-12 19:17:18 +0200 |
---|---|---|
committer | Thomas Zimmermann <tzimmermann@suse.de> | 2020-08-12 20:42:08 +0200 |
commit | 534b1f9071d95325044c21d47d9f63a45cdf425e (patch) | |
tree | 5c2aa3cd65bfb6b9e73d9ad22c021d800380f0f6 /drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | |
parent | 82dd18096c718962379e61cd8a7a0dc219db174f (diff) | |
parent | 62975d27d647a40c58d3b96c29b911fc4f33c310 (diff) |
Merge drm/drm-next into drm-misc-next
Backmerging drm-next into drm-misc-next for nouveau and panel updates.
Resolves a conflict between ttm and nouveau, where struct ttm_mem_res got
renamed to struct ttm_resource.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 46 |
1 files changed, 31 insertions, 15 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 50fe08bf2f72..bcce4c0be462 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -86,7 +86,7 @@ void amdgpu_ras_set_error_query_ready(struct amdgpu_device *adev, bool ready) amdgpu_ras_get_context(adev)->error_query_ready = ready; } -bool amdgpu_ras_get_error_query_ready(struct amdgpu_device *adev) +static bool amdgpu_ras_get_error_query_ready(struct amdgpu_device *adev) { if (adev && amdgpu_ras_get_context(adev)) return amdgpu_ras_get_context(adev)->error_query_ready; @@ -318,6 +318,9 @@ static ssize_t amdgpu_ras_debugfs_ctrl_write(struct file *f, const char __user * case 2: if ((data.inject.address >= adev->gmc.mc_vram_size) || (data.inject.address >= RAS_UMC_INJECT_ADDR_LIMIT)) { + dev_warn(adev->dev, "RAS WARN: input address " + "0x%llx is invalid.", + data.inject.address); ret = -EINVAL; break; } @@ -502,7 +505,7 @@ struct ras_manager *amdgpu_ras_find_obj(struct amdgpu_device *adev, } /* obj end */ -void amdgpu_ras_parse_status_code(struct amdgpu_device* adev, +static void amdgpu_ras_parse_status_code(struct amdgpu_device *adev, const char* invoke_type, const char* block_name, enum ta_ras_status ret) @@ -812,7 +815,7 @@ int amdgpu_ras_error_query(struct amdgpu_device *adev, } /* Trigger XGMI/WAFL error */ -int amdgpu_ras_error_inject_xgmi(struct amdgpu_device *adev, +static int amdgpu_ras_error_inject_xgmi(struct amdgpu_device *adev, struct ta_ras_trigger_error_input *block_info) { int ret; @@ -1615,7 +1618,7 @@ static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev) data = con->eh_data; save_count = data->count - control->num_recs; /* only new entries are saved */ - if (save_count > 0) + if (save_count > 0) { if (amdgpu_ras_eeprom_process_recods(control, &data->bps[control->num_recs], true, @@ -1624,6 +1627,9 @@ static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev) return -EIO; } + dev_info(adev->dev, "Saved %d pages to EEPROM table.\n", save_count); + } + return 0; } @@ -1914,9 +1920,8 @@ int amdgpu_ras_init(struct amdgpu_device *adev) amdgpu_ras_check_supported(adev, &con->hw_supported, &con->supported); if (!con->hw_supported) { - amdgpu_ras_set_context(adev, NULL); - kfree(con); - return 0; + r = 0; + goto err_out; } con->features = 0; @@ -1927,29 +1932,29 @@ int amdgpu_ras_init(struct amdgpu_device *adev) if (adev->nbio.funcs->init_ras_controller_interrupt) { r = adev->nbio.funcs->init_ras_controller_interrupt(adev); if (r) - return r; + goto err_out; } if (adev->nbio.funcs->init_ras_err_event_athub_interrupt) { r = adev->nbio.funcs->init_ras_err_event_athub_interrupt(adev); if (r) - return r; + goto err_out; } - amdgpu_ras_mask &= AMDGPU_RAS_BLOCK_MASK; - - if (amdgpu_ras_fs_init(adev)) - goto fs_out; + if (amdgpu_ras_fs_init(adev)) { + r = -EINVAL; + goto err_out; + } dev_info(adev->dev, "RAS INFO: ras initialized successfully, " "hardware ability[%x] ras_mask[%x]\n", con->hw_supported, con->supported); return 0; -fs_out: +err_out: amdgpu_ras_set_context(adev, NULL); kfree(con); - return -EINVAL; + return r; } /* helper function to handle common stuff in ip late init phase */ @@ -2129,3 +2134,14 @@ void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev) amdgpu_ras_reset_gpu(adev); } } + +bool amdgpu_ras_need_emergency_restart(struct amdgpu_device *adev) +{ + if (adev->asic_type == CHIP_VEGA20 && + adev->pm.fw_version <= 0x283400) { + return !(amdgpu_asic_reset_method(adev) == AMD_RESET_METHOD_BACO) && + amdgpu_ras_intr_triggered(); + } + + return false; +} |