From: Dennis Li Date: Mon, 19 Oct 2020 06:19:57 +0000 (+0800) Subject: drm/amdgpu: change to save bad pages in UMC error interrupt callback X-Git-Tag: baikal/mips/sdk5.9~12066^2~12^2~116 X-Git-Url: https://git.baikalelectronics.ru/sdk/?a=commitdiff_plain;h=53b043163639429db487070ee5f6b311901bf9c3;p=kernel.git drm/amdgpu: change to save bad pages in UMC error interrupt callback Instead of saving bad pages in amdgpu_ras_reset_gpu, it will reduce the unnecessary calling of amdgpu_ras_save_bad_pages. Signed-off-by: Dennis Li Reviewed-by: Hawking Zhang Signed-off-by: Alex Deucher --- diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index 4e36551ab50ba..95d6b34027ca9 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1668,7 +1668,7 @@ out: * write error record array to eeprom, the function should be * protected by recovery_lock */ -static int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev) +int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev) { struct amdgpu_ras *con = amdgpu_ras_get_context(adev); struct ras_err_handler_data *data; @@ -1841,9 +1841,6 @@ int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev) data->last_reserved = i + 1; bo = NULL; } - - /* continue to save bad pages to eeprom even reesrve_vram fails */ - ret = amdgpu_ras_save_bad_pages(adev); out: mutex_unlock(&con->recovery_lock); return ret; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h index 6b8d7bb83bb3c..0926c0770d7ab 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h @@ -506,6 +506,7 @@ bool amdgpu_ras_check_err_threshold(struct amdgpu_device *adev); int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev, struct eeprom_table_record *bps, int pages); +int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev); int amdgpu_ras_reserve_bad_pages(struct amdgpu_device *adev); static inline int amdgpu_ras_reset_gpu(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index 262baf0f61ea0..a2975c8092a91 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -126,10 +126,11 @@ int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev, err_data->ue_count); if ((amdgpu_bad_page_threshold != 0) && - err_data->err_addr_cnt && + err_data->err_addr_cnt) { amdgpu_ras_add_bad_pages(adev, err_data->err_addr, - err_data->err_addr_cnt)) - dev_warn(adev->dev, "Failed to add ras bad page!\n"); + err_data->err_addr_cnt); + amdgpu_ras_save_bad_pages(adev); + } amdgpu_ras_reset_gpu(adev); }