torvalds/linux
3
0
Fork 0
mirror of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-03-21 23:16:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

drm/xe: Trigger queue cleanup if not in wedged mode 2

Browse Source 
The intent of wedging a device is to allow queues to continue running
only in wedged mode 2. In other modes, queues should initiate cleanup
and signal all remaining fences. Fix xe_guc_submit_wedge to correctly
clean up queues when wedge mode != 2.

Fixes: 7dbe8af13c ("drm/xe: Wedge the entire device")
Cc: stable@vger.kernel.org
Reviewed-by: Zhanjun Dong <zhanjun.dong@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patch.msgid.link/20260310225039.1320161-4-zhanjun.dong@intel.com
(cherry picked from commit e25ba41c8227c5393c16e4aab398076014bd345f)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
This commit is contained in:
Matthew Brost
2026-03-10 18:50:35 -04:00
committed by Thomas Hellström
parent fb3738693c
commit e0f82655df
1 changed files with 22 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
drivers/gpu/drm/xe/xe_guc_submit.c
View File

@@ -1271,6 +1271,7 @@ static void disable_scheduling_deregister(struct xe_guc *guc,
*/
void xe_guc_submit_wedge(struct xe_guc *guc)
{
struct xe_device *xe = guc_to_xe(guc);
struct xe_gt *gt = guc_to_gt(guc);
struct xe_exec_queue *q;
unsigned long index;
@@ -1285,20 +1286,28 @@ void xe_guc_submit_wedge(struct xe_guc *guc)
if (!guc->submission_state.initialized)
return;
err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
guc_submit_wedged_fini, guc);
if (err) {
xe_gt_err(gt, "Failed to register clean-up in wedged.mode=%s; "
"Although device is wedged.\n",
xe_wedged_mode_to_string(XE_WEDGED_MODE_UPON_ANY_HANG_NO_RESET));
return;
}
if (xe->wedged.mode == 2) {
err = devm_add_action_or_reset(guc_to_xe(guc)->drm.dev,
guc_submit_wedged_fini, guc);
if (err) {
xe_gt_err(gt, "Failed to register clean-up on wedged.mode=2; "
"Although device is wedged.\n");
return;
}
mutex_lock(&guc->submission_state.lock);
xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
if (xe_exec_queue_get_unless_zero(q))
set_exec_queue_wedged(q);
mutex_unlock(&guc->submission_state.lock);
mutex_lock(&guc->submission_state.lock);
xa_for_each(&guc->submission_state.exec_queue_lookup, index, q)
if (xe_exec_queue_get_unless_zero(q))
set_exec_queue_wedged(q);
mutex_unlock(&guc->submission_state.lock);
} else {
/* Forcefully kill any remaining exec queues, signal fences */
guc_submit_reset_prepare(guc);
xe_guc_submit_stop(guc);
xe_guc_softreset(guc);
xe_uc_fw_sanitize(&guc->fw);
xe_guc_submit_pause_abort(guc);
}
}
static bool guc_submit_hint_wedged(struct xe_guc *guc)