1 files changed, 11 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index aaf5477fcd7a..d7c1ffbf7626 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -92,6 +92,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	struct drm_wedge_task_info *info = NULL;
 	struct amdgpu_task_info *ti = NULL;
 	struct amdgpu_device *adev = ring->adev;
+	enum drm_gpu_sched_stat status = DRM_GPU_SCHED_STAT_RESET;
 	int idx, r;
 
 	if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
@@ -135,13 +136,19 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 	    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, job->hw_fence);
 		if (!r) {
+			/* Start the scheduler again */
+			drm_sched_wqueue_start(&ring->sched);
 			atomic_inc(&ring->adev->gpu_reset_counter);
 			dev_err(adev->dev, "Ring %s reset succeeded\n",
 				ring->sched.name);
 			drm_dev_wedged_event(adev_to_drm(adev),
 					     DRM_WEDGE_RECOVERY_NONE, info);
+			/* This is needed to add the job back to the pending list */
+			status = DRM_GPU_SCHED_STAT_NO_HANG;
 			goto exit;
 		}
 		dev_err(adev->dev, "Ring %s reset failed\n", ring->sched.name);
@@ -177,7 +184,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
 exit:
 	amdgpu_vm_put_task_info(ti);
 	drm_dev_exit(idx);
-	return DRM_GPU_SCHED_STAT_RESET;
+	return status;
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
@@ -191,18 +198,18 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	if (num_ibs == 0)
 		return -EINVAL;
 
-	*job = kzalloc(struct_size(*job, ibs, num_ibs), GFP_KERNEL);
+	*job = kzalloc_flex(**job, ibs, num_ibs);
 	if (!*job)
 		return -ENOMEM;
 
-	af = kzalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	af = kzalloc_obj(struct amdgpu_fence);
 	if (!af) {
 		r = -ENOMEM;
 		goto err_job;
 	}
 	(*job)->hw_fence = af;
 
-	af = kzalloc(sizeof(struct amdgpu_fence), GFP_KERNEL);
+	af = kzalloc_obj(struct amdgpu_fence);
 	if (!af) {
 		r = -ENOMEM;
 		goto err_fence;