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

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>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
index f4c05ff4b26c5d7fa8ba7e66da8df216fefa61a4..3978152e5ccc78630865aeae756f8030c5ebfa18 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras_eeprom.c
@@ -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);