[PATCH] drm/amdgpu: refine ras error kernel log print
Yang Wang
kevinyang.wang at amd.com
Thu Oct 19 12:51:15 UTC 2023
refine ras error kernel log to avoid user-ridden ambiguity.
Signed-off-by: Yang Wang <kevinyang.wang at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 5b831ba0ebb3..cebc19d810e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1034,10 +1034,11 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
struct ras_err_info *err_info;
if (is_ue)
- dev_info(adev->dev, "%ld uncorrectable hardware errors detected in %s block\n",
+ dev_info(adev->dev, "%ld uncorrectable hardware errors detected in total in %s block\n",
ras_mgr->err_data.ue_count, blk_name);
else
- dev_info(adev->dev, "%ld correctable hardware errors detected in %s block\n",
+ dev_info(adev->dev, "%ld correctable hardware errors detected in total in %s block, "
+ "no user action is needed.\n",
ras_mgr->err_data.ce_count, blk_name);
for_each_ras_error(err_node, err_data) {
@@ -1045,14 +1046,15 @@ static void amdgpu_ras_error_print_error_data(struct amdgpu_device *adev,
mcm_info = &err_info->mcm_info;
if (is_ue && err_info->ue_count) {
dev_info(adev->dev, "socket: %d, die: %d "
- "%lld uncorrectable hardware errors detected in %s block\n",
+ "new %lld uncorrectable hardware errors detected in %s block\n",
mcm_info->socket_id,
mcm_info->die_id,
err_info->ue_count,
blk_name);
} else if (!is_ue && err_info->ce_count) {
dev_info(adev->dev, "socket: %d, die: %d "
- "%lld correctable hardware errors detected in %s block\n",
+ "new %lld correctable hardware errors detected in %s block, "
+ "no user action is needed.\n",
mcm_info->socket_id,
mcm_info->die_id,
err_info->ce_count,
--
2.34.1
More information about the amd-gfx
mailing list