public-mirrors/linux
1
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2025-08-05 16:54:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

drm/amdgpu: Warn when bad pages approaches 90% threshold

Browse source 
dmesg doesn't warn when the number of bad pages approaches the
threshold for page retirement. WARN when the number of bad pages
is at 90% or greater for easier checks and planning, instead of waiting
until the GPU is full of bad pages.

Cc: Luben Tuikov <luben.tuikov@amd.com>
Cc: Mukul Joshi <Mukul.Joshi@amd.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Luben Tuikov <luben.tuikov@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Kent Russell 2021-10-12 16:49:24 -04:00 • committed by Alex Deucher
parent 31fa8cbce4
commit 8483fdfea7
1 changed files with 7 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
View file

@ -1077,6 +1077,13 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
if (res)
DRM_ERROR("RAS table incorrect checksum or error:%d\n",
res);
/* Warn if we are at 90% of the threshold or above
*/
if (10 * control->ras_num_recs >= 9 * ras->bad_page_cnt_threshold)
dev_warn(adev->dev, "RAS records:%u exceeds 90%% of threshold:%d",
control->ras_num_recs,
ras->bad_page_cnt_threshold);
} else if (hdr->header == RAS_TABLE_HDR_BAD &&
amdgpu_bad_page_threshold != 0) {
res = __verify_ras_table_checksum(control);