Commit 15789fa0 authored by Alex Deucher's avatar Alex Deucher
Browse files

drm/amdgpu: add per ring reset support (v5) 



If a specific job is hung, try and reset just the
ring associated with the job.

v2: move to amdgpu_job.c
v3: fix drm_sched_stop() handling when ring reset fails
v4: drop unnecessary amdgpu_fence_driver_clear_job_fences() and
    drm_sched_increase_karma()
v5: rework sched_stop handling

Acked-by: default avatarVitaly Prosyak <vitaly.prosyak@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 57a372f6

drivers/gpu/drm/amd/amdgpu/amdgpu_job.c

+19 −0
Original line number Diff line number Diff line
@@ -72,6 +72,25 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) 


	dma_fence_set_error(&s_job->s_fence->finished, -ETIME);



	/* attempt a per ring reset */

	if (amdgpu_gpu_recovery &&

	    ring->funcs->reset) {

		/* stop the scheduler, but don't mess with the

		 * bad job yet because if ring reset fails

		 * we'll fall back to full GPU reset.

		 */

		drm_sched_wqueue_stop(&ring->sched);

		r = amdgpu_ring_reset(ring, job->vmid);

		if (!r) {

			if (amdgpu_ring_sched_ready(ring))

				drm_sched_stop(&ring->sched, s_job);

			amdgpu_fence_driver_force_completion(ring);

			if (amdgpu_ring_sched_ready(ring))

				drm_sched_start(&ring->sched, true);

			goto exit;

		}

	}



	if (amdgpu_device_should_recover_gpu(ring->adev)) {

		struct amdgpu_reset_context reset_context;

		memset(&reset_context, 0, sizeof(reset_context));