Commit 676d8c24 authored by Monk Liu's avatar Monk Liu Committed by Alex Deucher

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: default avatarMonk Liu <Monk.Liu@amd.com>
Reviewed-by: default avatarChunming Zhou <david1.zhou@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 73cfa5f5
......@@ -70,9 +70,12 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
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);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment