github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-05-25 15:41:52 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/amdgpu: increase RAS bad page threshold

Browse Source 
For default policy, driver will issue an RMA event when the number of
bad pages is greater than 8 physical rows, rather than reaches 8
physical rows, don't rely on threshold configurable parameters in
default mode.

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>
This commit is contained in:
Tao Zhou 2025-03-06 11:36:49 +08:00 committed by Alex Deucher
parent fe2fa3be3d
commit 334dc5fcc3
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
View File

@ -747,7 +747,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
/* Modify the header if it exceeds.
*/
if (amdgpu_bad_page_threshold != 0 &&
control->ras_num_bad_pages >= ras->bad_page_cnt_threshold) {
control->ras_num_bad_pages > ras->bad_page_cnt_threshold) {
dev_warn(adev->dev,
"Saved bad pages %d reaches threshold value %d\n",
control->ras_num_bad_pages, ras->bad_page_cnt_threshold);
@ -806,7 +806,7 @@ amdgpu_ras_eeprom_update_header(struct amdgpu_ras_eeprom_control *control)
*/
if (amdgpu_bad_page_threshold != 0 &&
control->tbl_hdr.version == RAS_TABLE_VER_V2_1 &&
control->ras_num_bad_pages < ras->bad_page_cnt_threshold)
control->ras_num_bad_pages <= ras->bad_page_cnt_threshold)
control->tbl_rai.health_percent = ((ras->bad_page_cnt_threshold -
control->ras_num_bad_pages) * 100) /
ras->bad_page_cnt_threshold;
@ -1456,7 +1456,7 @@ int amdgpu_ras_eeprom_check(struct amdgpu_ras_eeprom_control *control)
res);
return -EINVAL;
}
if (ras->bad_page_cnt_threshold > control->ras_num_bad_pages) {
if (ras->bad_page_cnt_threshold >= control->ras_num_bad_pages) {
/* This means that, the threshold was increased since
* the last time the system was booted, and now,
* ras->bad_page_cnt_threshold - control->num_recs > 0,