When a job is timeout, try to print the related process information
for debugging
Signed-off-by: Trigger Huang <Trigger.Huang@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index e0af44f..915310d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -32,6 +32,7 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
{
struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
struct amdgpu_job *job = to_amdgpu_job(s_job);
+ struct amdgpu_task_info ti = { 0 };
if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
DRM_ERROR("ring %s timeout, but soft recovered\n",
@@ -39,9 +40,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
return;
}
+ amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti);
DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",
job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
ring->fence_drv.sync_seq);
+ DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n",
+ ti.process_name, ti.tgid, ti.task_name, ti.pid);
if (amdgpu_device_should_recover_gpu(ring->adev))
amdgpu_device_gpu_recover(ring->adev, job);
--
2.7.4
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
