diff options
| author | Tao Zhou <tao.zhou1@amd.com> | 2024-05-23 11:23:20 +0800 |
|---|---|---|
| committer | Alex Deucher <alexander.deucher@amd.com> | 2024-06-05 11:25:14 -0400 |
| commit | b95fa494d6b74c30eeb4a50481aa1041c631754e (patch) | |
| tree | b5f6a3167531f119d94551f4fe6f328702fc8be8 /drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | |
| parent | 15c2990e0f0108b9c3752d7072a97d45d4283aea (diff) | |
drm/amdgpu: add RAS is_rma flag
Set the flag to true if bad page number reaches threshold.
Signed-off-by: Tao Zhou <tao.zhou1@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/amd/amdgpu/amdgpu_ras_eeprom.c')
| -rw-r--r-- | drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 10 |
1 files changed, 6 insertions, 4 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c index 9b789dcc2bd1..eae0a555df3c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c @@ -750,6 +750,9 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control) control->tbl_rai.health_percent = 0; } + if (amdgpu_bad_page_threshold != -1) + ras->is_rma = true; + /* ignore the -ENOTSUPP return value */ amdgpu_dpm_send_rma_reason(adev); } @@ -1321,8 +1324,7 @@ Out: return res == RAS_TABLE_V2_1_INFO_SIZE ? 0 : res; } -int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control, - bool *exceed_err_limit) +int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control) { struct amdgpu_device *adev = to_amdgpu_device(control); unsigned char buf[RAS_TABLE_HEADER_SIZE] = { 0 }; @@ -1330,7 +1332,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control, struct amdgpu_ras *ras = amdgpu_ras_get_context(adev); int res; - *exceed_err_limit = false; + ras->is_rma = false; if (!__is_ras_eeprom_supported(adev)) return 0; @@ -1422,7 +1424,7 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control, dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -1."); res = 0; } else { - *exceed_err_limit = true; + ras->is_rma = true; dev_err(adev->dev, "RAS records:%d exceed threshold:%d, " "GPU will not be initialized. Replace this GPU or increase the threshold", |