github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-07-28 18:21:24 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

drm/amdgpu: Fixup detect and reset

Browse Source 
Identify hung queues by comparing doorbells shown in hqd_info from MES
with doorbells stored in the driver to find matching queues.

Suggested-by: Jonathan Kim <jonathan.kim@amd.com>
Signed-off-by: Amber Lin <Amber.Lin@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Amber Lin 2026-03-13 05:35:55 -04:00 committed by Alex Deucher
parent a132fc9bc2
commit 6404825255
1 changed files with 26 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
View File

@ -466,23 +466,35 @@ int amdgpu_mes_detect_and_reset_hung_queues(struct amdgpu_device *adev,
r = adev->mes.funcs->detect_and_reset_hung_queues(&adev->mes,
&input);
if (r) {
dev_err(adev->dev, "failed to detect and reset\n");
} else {
*hung_db_num = 0;
for (i = 0; i < adev->mes.hung_queue_hqd_info_offset; i++) {
if (db_array[i] != AMDGPU_MES_INVALID_DB_OFFSET) {
hung_db_array[i] = db_array[i];
*hung_db_num += 1;
}
}
/*
* TODO: return HQD info for MES scheduled user compute queue reset cases
* stored in hung_db_array hqd info offset to full array size
*/
if (r && detect_only) {
dev_err(adev->dev, "Failed to detect hung queues\n");
return r;
}
*hung_db_num = 0;
/* MES passes hung queues' doorbell to driver */
for (i = 0; i < adev->mes.hung_queue_hqd_info_offset; i++) {
/* Finding hung queues where db_array[i] is a valid doorbell */
if (db_array[i] != AMDGPU_MES_INVALID_DB_OFFSET) {
hung_db_array[i] = db_array[i];
*hung_db_num += 1;
}
}
if (r && !hung_db_num) {
dev_err(adev->dev, "Failed to detect and reset hung queues\n");
return r;
}
/*
* TODO: return HQD info for MES scheduled user compute queue reset cases
* stored in hung_db_array hqd info offset to full array size
*/
if (r)
dev_err(adev->dev, "failed to reset\n");
return r;
}