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.tuikov@xxxxxxx>
Cc: Mukul Joshi <Mukul.Joshi@xxxxxxx>
Signed-off-by: Kent Russell <kent.russell@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index 98732518543e..8270aad23a06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -1077,6 +1077,16 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
if (res)
DRM_ERROR("RAS table incorrect checksum or error:%d\n",
res);
+
+ /* threshold = -1 is automatic, threshold = 0 means that page
+ * retirement is disabled.
+ */
+ if (amdgpu_bad_page_threshold > 0 &&
+ control->ras_num_recs >= 0 &&
+ control->ras_num_recs >= (amdgpu_bad_page_threshold * 9 / 10))
+ DRM_WARN("RAS records:%u approaching threshold:%d",
+ control->ras_num_recs,
+ amdgpu_bad_page_threshold);
} else if (hdr->header == RAS_TABLE_HDR_BAD &&
amdgpu_bad_page_threshold != 0) {
res = __verify_ras_table_checksum(control);
--
2.25.1
