[PATCH] drm/amdgpu:fix gpu recover missing skipping

Monk Liu Monk.Liu at amd.com
Wed Nov 8 06:39:08 UTC 2017

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
 	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
 			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);

More information about the amd-gfx mailing list