if app close CTX right after IB submit, gpu recover
will failed to find out the entity/ctx behind the guilty
job thus lead to bad job skipping in scheduler failed
to fix this corner case just move the job->karma increasing
out of the condition that the backing entity was found
that way the job itself will be "guilty" anyway
Change-Id: Ia30f02df9297a343d6d8dace496e237827dd1548
Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
drivers/gpu/drm/amd/scheduler/gpu_scheduler.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
index 7aa6455..720fd1b 100644
--- a/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/amd/scheduler/gpu_scheduler.c
@@ -464,6 +464,7 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched, struct amd_sched_jo
spin_unlock(&sched->job_list_lock);
if (bad) {
+ atomic_inc(&bad->karma);
/* don't increase @bad's karma if it's from KERNEL RQ,
* becuase sometimes GPU hang would cause kernel jobs (like VM updating jobs)
* corrupt but keep in mind that kernel jobs always considered good.
@@ -474,7 +475,7 @@ void amd_sched_hw_job_reset(struct amd_gpu_scheduler *sched, struct amd_sched_jo
spin_lock(&rq->lock);
list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
if (bad->s_fence->scheduled.context == entity->fence_context) {
- if (atomic_inc_return(&bad->karma) > bad->sched->hang_limit)
+ if (atomic_read(&bad->karma) > bad->sched->hang_limit)
if (entity->guilty)
atomic_set(entity->guilty, 1);
break;
--
2.7.4
