Currently 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.tui...@amd.com>
Cc: Mukul Joshi <mukul.jo...@amd.com>
Signed-off-by: Kent Russell <kent.russ...@amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index f4c05ff4b26c..1ede0f0d6f55 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1071,12 +1071,29 @@ int amdgpu_ras_eeprom_init(struct
amdgpu_ras_eeprom_control *control,
control->ras_fri = RAS_OFFSET_TO_INDEX(control, hdr->first_rec_offset);
if (hdr->header == RAS_TABLE_HDR_VAL) {
+ int threshold = 0;
DRM_DEBUG_DRIVER("Found existing EEPROM table with %d records",
control->ras_num_recs);
res = __verify_ras_table_checksum(control);
if (res)
DRM_ERROR("RAS table incorrect checksum or error:%d\n",
res);
+
+ /* threshold = 0 means that page retirement is disabled, while
+ * threshold = -1 means default behaviour
+ */
+ if (amdgpu_bad_page_threshold == -1)
+ threshold = ras->bad_page_cnt_threshold;
+ else if (amdgpu_bad_page_threshold > 0)
+ threshold = amdgpu_bad_page_threshold;
+
+ /* Since multiplcation is transitive, a = 9b/10 is the same
+ * as 10a = 9b. Use this for our 90% limit to avoid rounding
+ */
+ if (threshold > 0 && ((control->ras_num_recs * 10) >=
(threshold * 9)))
+ DRM_WARN("RAS records:%u exceeds 90%% of threshold:%d",
+ control->ras_num_recs,
+ threshold);
} else if (hdr->header == RAS_TABLE_HDR_BAD &&
amdgpu_bad_page_threshold != 0) {
res = __verify_ras_table_checksum(control);
--
2.25.1
