The purpose of halt_if_hws_hang is to preserve GPU state for driver
debugging when queue preemption fails. Issuing per-queue reset may
kill wavefronts which caused the preemption failure.
Signed-off-by: Jay Cornwall <jay.cornwall@xxxxxxx>
Cc: Jonathan Kim <Jonathan.Kim@xxxxxxx>
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f157494bfdb1..195085079eb2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -2327,9 +2327,9 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
*/
mqd_mgr = dqm->mqd_mgrs[KFD_MQD_TYPE_HIQ];
if (mqd_mgr->check_preemption_failed(mqd_mgr, dqm->packet_mgr.priv_queue->queue->mqd)) {
+ while (halt_if_hws_hang)
+ schedule();
if (reset_queues_on_hws_hang(dqm)) {
- while (halt_if_hws_hang)
- schedule();
dqm->is_hws_hang = true;
kfd_hws_hang(dqm);
retval = -ETIME;
--
2.34.1
