drm/amdgpu:use job's list instead of check fence

because if the fence is really signaled, it could already
released so the fence pointer is a wild pointer, but if
we use job->base.node we are safe because job will not
be released untill amdgpu_job_timedout finished.

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 2 insertions, 2 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 8b0f4864a885..d1385eba6f43 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2644,9 +2644,9 @@ int amdgpu_sriov_gpu_reset(struct amdgpu_device *adev, struct amdgpu_job *job)
                 if (job && j != i)
                         continue;
 
-                /* here give the last chance to check if fence signaled
+                /* here give the last chance to check if job removed from mirror-list
                  * since we already pay some time on kthread_park */
-                if (job && dma_fence_is_signaled(&job->base.s_fence->finished)) {
+                if (job && list_empty(&job->base.node)) {
                         kthread_unpark(ring->sched.thread);
                         goto give_up_reset;
                 }