admin/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2025-12-07 20:06:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

drm/amdgpu: add check function for pmfw eeprom

Browse Source 
add check function for pmfw eeprom

Signed-off-by: Gangliang Xie <ganglxie@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Gangliang Xie
2025-09-04 18:09:40 +08:00
committed by Alex Deucher
parent 19c815d516
commit cd5b28a040
1 changed files with 44 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
View File

@@ -1499,6 +1499,47 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control)
return 0;
}
static int amdgpu_ras_smu_eeprom_check(struct amdgpu_ras_eeprom_control *control)
{
struct amdgpu_device *adev = to_amdgpu_device(control);
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
if (!__is_ras_eeprom_supported(adev))
return 0;
control->ras_num_bad_pages = ras->bad_page_num;
if ((ras->bad_page_cnt_threshold < control->ras_num_bad_pages) &&
amdgpu_bad_page_threshold != 0) {
dev_warn(adev->dev,
"RAS records:%d exceed threshold:%d\n",
control->ras_num_bad_pages, ras->bad_page_cnt_threshold);
if ((amdgpu_bad_page_threshold == -1) ||
(amdgpu_bad_page_threshold == -2)) {
dev_warn(adev->dev,
"Please consult AMD Service Action Guide (SAG) for appropriate service procedures\n");
} else {
ras->is_rma = true;
dev_warn(adev->dev,
"User defined threshold is set, runtime service will be halt when threshold is reached\n");
}
return 0;
}
dev_dbg(adev->dev,
"Found existing EEPROM table with %d records",
control->ras_num_bad_pages);
/* Warn if we are at 90% of the threshold or above
*/
if (10 * control->ras_num_bad_pages >= 9 * ras->bad_page_cnt_threshold)
dev_warn(adev->dev, "RAS records:%u exceeds 90%% of threshold:%d",
control->ras_num_bad_pages,
ras->bad_page_cnt_threshold);
return 0;
}
int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
{
struct amdgpu_device *adev = to_amdgpu_device(control);
@@ -1506,6 +1547,9 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
int res = 0;
if (amdgpu_ras_smu_eeprom_supported(adev))
return amdgpu_ras_smu_eeprom_check(control);
if (!__is_ras_eeprom_supported(adev))
return 0;