drm/amdgpu: use sched fence if possible
when preemption feature lands, the SA bo should rely on sched
fence, because hw fence will be invalid after its job preempted
or skipped.
Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 063064c..9c9b19e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -70,9 +70,12 @@
void amdgpu_job_free(struct amdgpu_job *job)
{
unsigned i;
+ struct fence *f;
+ /* use sched fence if available */
+ f = (job->base.s_fence)? &job->base.s_fence->base : job->fence;
for (i = 0; i < job->num_ibs; ++i)
- amdgpu_sa_bo_free(job->adev, &job->ibs[i].sa_bo, job->fence);
+ amdgpu_sa_bo_free(job->adev, &job->ibs[i].sa_bo, f);
fence_put(job->fence);
amdgpu_bo_unref(&job->uf.bo);