From 4d33e0f1340b3d08002ff8f9bcbf256cfdc4f3ba Mon Sep 17 00:00:00 2001 From: Tao Zhou Date: Fri, 10 Feb 2023 16:33:58 +0800 Subject: drm/amdgpu: exclude duplicate pages from UMC RAS UE count If a UMC bad page is reserved but not freed by an application, the application may trigger uncorrectable error repeatly by accessing the page. v2: add specific function to do the check. v3: remove duplicate pages, calculate new added bad page number. v4: reuse save_bad_pages to calculate new added bad page number. Signed-off-by: Tao Zhou Reviewed-by: Stanley.Yang Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index 1c7fcb4f2380..1b8574bc4463 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -68,7 +68,7 @@ int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev, if (amdgpu_bad_page_threshold != 0) { amdgpu_ras_add_bad_pages(adev, err_data.err_addr, err_data.err_addr_cnt); - amdgpu_ras_save_bad_pages(adev); + amdgpu_ras_save_bad_pages(adev, NULL); } out: @@ -147,7 +147,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev, err_data->err_addr_cnt) { amdgpu_ras_add_bad_pages(adev, err_data->err_addr, err_data->err_addr_cnt); - amdgpu_ras_save_bad_pages(adev); + amdgpu_ras_save_bad_pages(adev, &(err_data->ue_count)); amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs); -- cgit v1.2.3-70-g09d2