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: Vitaly Prosyak <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

1 files changed, 19 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 908e13455152..c2de3fd17245 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -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));