[PATCH 1/5] drm/amdgpu: rework queue reset scheduler interaction

[Christian König]

Stopping the scheduler for queue reset is generally a good idea because
it prevents any worker from touching the ring buffer.

But using amdgpu_fence_driver_force_completion() before restarting it was
a really bad idea because it marked fences as failed while the work was
potentially still running.

Stop doing that and cleanup the comment a bit.

Signed-off-by: Christian König <christian.koenig at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 685c61a05af8..400e27ec14d4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -133,25 +133,24 @@ 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) {
-		dev_err(adev->dev, "Starting %s ring reset\n", s_job->sched->name);
-		/* 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.
+	if (amdgpu_gpu_recovery && ring->funcs->reset) {
+		dev_err(adev->dev, "Starting %s ring reset\n",
+			s_job->sched->name);
+
+		/*
+		 * Stop the scheduler to prevent anybody else from touching the
+		 * ring buffer.
 		 */
 		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);
 			atomic_inc(&ring->adev->gpu_reset_counter);
-			amdgpu_fence_driver_force_completion(ring);
-			if (amdgpu_ring_sched_ready(ring))
-				drm_sched_start(&ring->sched, 0);
+			drm_sched_wqueue_start(&ring->sched);
+			dev_err(adev->dev, "Ring %s reset worked\n",
+				ring->sched.name);
 			goto exit;
 		}
-		dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
+		dev_err(adev->dev, "Ring %s reset failed\n", ring->sched.name);
 	}
 
 	if (amdgpu_device_should_recover_gpu(ring->adev)) {
-- 
2.34.1