drm/amdgpu: fix possible fence leaks from job structure

If we don't end up initializing the fences, free them when
we free the job.  We can't set the hw_fence to NULL after
emitting it because we need it in the cleanup path for the
submit direct case.

v2: take a reference to the fences if we emit them
v3: handle non-job fence in error paths

Fixes: db36632ea5 ("drm/amdgpu: clean up and unify hw fence handling")
Reviewed-by: Jesse Zhang <Jesse.Zhang@amd.com> (v1)
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher
2025-10-22 17:11:38 -04:00
parent d95ca7f515
commit f903b85ed0
3 changed files with 35 additions and 4 deletions

View File

@@ -293,6 +293,15 @@ static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
amdgpu_sync_free(&job->explicit_sync);
if (job->hw_fence->base.ops)
dma_fence_put(&job->hw_fence->base);
else
kfree(job->hw_fence);
if (job->hw_vm_fence->base.ops)
dma_fence_put(&job->hw_vm_fence->base);
else
kfree(job->hw_vm_fence);
kfree(job);
}
@@ -322,6 +331,15 @@ void amdgpu_job_free(struct amdgpu_job *job)
if (job->gang_submit != &job->base.s_fence->scheduled)
dma_fence_put(job->gang_submit);
if (job->hw_fence->base.ops)
dma_fence_put(&job->hw_fence->base);
else
kfree(job->hw_fence);
if (job->hw_vm_fence->base.ops)
dma_fence_put(&job->hw_vm_fence->base);
else
kfree(job->hw_vm_fence);
kfree(job);
}