diff options
| author | Candice Li <candice.li@amd.com> | 2024-01-10 15:30:31 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2024-01-15 18:35:37 -0500 |
| commit | 9c97bf88f4a71c1547e6d4a347597fa77f63abbb (patch) | |
| tree | b3072781f844a0d9a05e7ea1d0f3a6be6cb8696f /drivers/gpu/drm | |
| parent | bbcbfd4363e9447088e98932c41f417f3bb08050 (diff) | |
drm/amdgpu: Do bad page retirement for deferred errors
Needs to do bad page retirement for deferred errors.
v2: Drop unused dev_info.
Signed-off-by: YiPeng Chai <YiPeng.Chai@amd.com>
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Diffstat (limited to 'drivers/gpu/drm')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c | 10 |
1 files changed, 4 insertions, 6 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c index d65e21914d8c..3932ac81a67c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c @@ -93,6 +93,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev, struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status; struct amdgpu_ras *con = amdgpu_ras_get_context(adev); int ret = 0; + unsigned long err_count; kgd2kfd_set_sram_ecc_flag(adev->kfd.dev); ret = amdgpu_dpm_get_ecc_info(adev, (void *)&(con->umc_ecc)); @@ -147,16 +148,13 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev, } /* only uncorrectable error needs gpu reset */ - if (err_data->ue_count) { - dev_info(adev->dev, "%ld uncorrectable hardware errors " - "detected in UMC block\n", - err_data->ue_count); - + if (err_data->ue_count || err_data->de_count) { + err_count = err_data->ue_count + err_data->de_count; if ((amdgpu_bad_page_threshold != 0) && 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, &(err_data->ue_count)); + amdgpu_ras_save_bad_pages(adev, &err_count); amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs); |