diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e20dce438d37..d7dddb936f84 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3313,17 +3313,15 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
 		if (!ring || !ring->sched.thread)
 			continue;
 
-		kthread_park(ring->sched.thread);
-
-		if (job && job->base.sched != &ring->sched)
-			continue;
-
-		drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
+		drm_sched_stop(&ring->sched);
 
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
 	}
 
+	if(job)
+		drm_sched_increase_karma(&job->base);
+
 
 
 	if (!amdgpu_sriov_vf(adev)) {
@@ -3469,14 +3467,10 @@ static void amdgpu_device_post_asic_reset(struct amdgpu_device *adev,
 		if (!ring || !ring->sched.thread)
 			continue;
 
-		/* only need recovery sched of the given job's ring
-		 * or all rings (in the case @job is NULL)
-		 * after above amdgpu_reset accomplished
-		 */
-		if ((!job || job->base.sched == &ring->sched) && !adev->asic_reset_res)
-			drm_sched_job_recovery(&ring->sched);
+		if (!adev->asic_reset_res)
+			drm_sched_resubmit_jobs(&ring->sched);
 
-		kthread_unpark(ring->sched.thread);
+		drm_sched_start(&ring->sched, !adev->asic_reset_res);
 	}
 
 	if (!amdgpu_device_has_dc_support(adev)) {
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 49a6763693f1..67ae26602024 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -109,16 +109,19 @@ static void etnaviv_sched_timedout_job(struct drm_sched_job *sched_job)
 	}
 
 	/* block scheduler */
-	kthread_park(gpu->sched.thread);
-	drm_sched_hw_job_reset(&gpu->sched, sched_job);
+	drm_sched_stop(&gpu->sched);
+
+	if(sched_job)
+		drm_sched_increase_karma(sched_job);
 
 	/* get the GPU back into the init state */
 	etnaviv_core_dump(gpu);
 	etnaviv_gpu_recover_hang(gpu);
 
+	drm_sched_resubmit_jobs(&gpu->sched);
+
 	/* restart scheduler after GPU is usable again */
-	drm_sched_job_recovery(&gpu->sched);
-	kthread_unpark(gpu->sched.thread);
+	drm_sched_start(&gpu->sched, true);
 }
 
 static void etnaviv_sched_free_job(struct drm_sched_job *sched_job)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index dbb69063b3d5..4bb18511ac75 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -60,8 +60,6 @@
 
 static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
 
-static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job);
-
 /**
  * drm_sched_rq_init - initialize a given run queue struct
  *
@@ -335,45 +333,38 @@ static void drm_sched_job_timedout(struct work_struct *work)
 	spin_unlock_irqrestore(&sched->job_list_lock, flags);
 }
 
-/**
- * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
- *
- * @sched: scheduler instance
- * @bad: bad scheduler job
- *
- */
-void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
+ /**
+  * drm_sched_increase_karma - Update sched_entity guilty flag
+  *
+  * @bad: The job guilty of time out
+  *
+  * Increment on every hang caused by the 'bad' job. If this exceeds the hang
+  * limit of the scheduler then the respective sched entity is marked guilty and
+  * jobs from it will not be scheduled further
+  */
+void drm_sched_increase_karma(struct drm_sched_job *bad)
 {
-	struct drm_sched_job *s_job;
-	struct drm_sched_entity *entity, *tmp;
-	unsigned long flags;
 	int i;
+	struct drm_sched_entity *tmp;
+	struct drm_sched_entity *entity;
+	struct drm_gpu_scheduler *sched = bad->sched;
 
-	spin_lock_irqsave(&sched->job_list_lock, flags);
-	list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
-		if (s_job->s_fence->parent &&
-		    dma_fence_remove_callback(s_job->s_fence->parent,
-					      &s_job->s_fence->cb)) {
-			dma_fence_put(s_job->s_fence->parent);
-			s_job->s_fence->parent = NULL;
-			atomic_dec(&sched->hw_rq_count);
-		}
-	}
-	spin_unlock_irqrestore(&sched->job_list_lock, flags);
-
-	if (bad && bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
+	/* don't increase @bad's karma if it's from KERNEL RQ,
+	 * because sometimes GPU hang would cause kernel jobs (like VM updating jobs)
+	 * corrupt but keep in mind that kernel jobs always considered good.
+	 */
+	if (bad->s_priority != DRM_SCHED_PRIORITY_KERNEL) {
 		atomic_inc(&bad->karma);
-		/* don't increase @bad's karma if it's from KERNEL RQ,
-		 * becuase sometimes GPU hang would cause kernel jobs (like VM updating jobs)
-		 * corrupt but keep in mind that kernel jobs always considered good.
-		 */
-		for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL; i++ ) {
+		for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_KERNEL;
+		     i++) {
 			struct drm_sched_rq *rq = &sched->sched_rq[i];
 
 			spin_lock(&rq->lock);
 			list_for_each_entry_safe(entity, tmp, &rq->entities, list) {
-				if (bad->s_fence->scheduled.context == entity->fence_context) {
-				    if (atomic_read(&bad->karma) > bad->sched->hang_limit)
+				if (bad->s_fence->scheduled.context ==
+				    entity->fence_context) {
+					if (atomic_read(&bad->karma) >
+					    bad->sched->hang_limit)
 						if (entity->guilty)
 							atomic_set(entity->guilty, 1);
 					break;
@@ -385,7 +376,51 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo
 		}
 	}
 }
-EXPORT_SYMBOL(drm_sched_hw_job_reset);
+EXPORT_SYMBOL(drm_sched_increase_karma);
+
+/**
+ * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
+ *
+ * @sched: scheduler instance
+ * @bad: bad scheduler job
+ *
+ */
+void drm_sched_stop(struct drm_gpu_scheduler *sched)
+{
+	struct drm_sched_job *s_job;
+	unsigned long flags;
+	struct dma_fence *last_fence =  NULL;
+
+	kthread_park(sched->thread);
+
+	/*
+	 * Verify all the signaled jobs in mirror list are removed from the ring
+	 * by waiting for the latest job to enter the list. This should insure that
+	 * also all the previous jobs that were in flight also already singaled
+	 * and removed from the list.
+	 */
+	spin_lock_irqsave(&sched->job_list_lock, flags);
+	list_for_each_entry_reverse(s_job, &sched->ring_mirror_list, node) {
+		if (s_job->s_fence->parent &&
+		    dma_fence_remove_callback(s_job->s_fence->parent,
+					      &s_job->s_fence->cb)) {
+			dma_fence_put(s_job->s_fence->parent);
+			s_job->s_fence->parent = NULL;
+			atomic_dec(&sched->hw_rq_count);
+		} else {
+			 last_fence = dma_fence_get(&s_job->s_fence->finished);
+			 break;
+		}
+	}
+	spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
+	if (last_fence) {
+		dma_fence_wait(last_fence, false);
+		dma_fence_put(last_fence);
+	}
+}
+
+EXPORT_SYMBOL(drm_sched_stop);
 
 /**
  * drm_sched_job_recovery - recover jobs after a reset
@@ -393,18 +428,55 @@ EXPORT_SYMBOL(drm_sched_hw_job_reset);
  * @sched: scheduler instance
  *
  */
-void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
+void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery)
 {
 	struct drm_sched_job *s_job, *tmp;
-	bool found_guilty = false;
 	unsigned long flags;
 	int r;
 
+	if (!full_recovery)
+		goto unpark;
+
 	spin_lock_irqsave(&sched->job_list_lock, flags);
 	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
 		struct drm_sched_fence *s_fence = s_job->s_fence;
-		struct dma_fence *fence;
-		uint64_t guilty_context;
+		struct dma_fence *fence = s_job->s_fence->parent;
+
+		if (fence) {
+			r = dma_fence_add_callback(fence, &s_fence->cb,
+						   drm_sched_process_job);
+			if (r == -ENOENT)
+				drm_sched_process_job(fence, &s_fence->cb);
+			else if (r)
+				DRM_ERROR("fence add callback failed (%d)\n",
+					  r);
+		} else
+			drm_sched_process_job(NULL, &s_fence->cb);
+	}
+
+	drm_sched_start_timeout(sched);
+	spin_unlock_irqrestore(&sched->job_list_lock, flags);
+
+unpark:
+	kthread_unpark(sched->thread);
+}
+EXPORT_SYMBOL(drm_sched_start);
+
+/**
+ * drm_sched_resubmit_jobs - helper to relunch job from mirror ring list
+ *
+ * @sched: scheduler instance
+ *
+ */
+void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched)
+{
+	struct drm_sched_job *s_job, *tmp;
+	uint64_t guilty_context;
+	bool found_guilty = false;
+
+	/*TODO DO we need spinlock here ? */
+	list_for_each_entry_safe(s_job, tmp, &sched->ring_mirror_list, node) {
+		struct drm_sched_fence *s_fence = s_job->s_fence;
 
 		if (!found_guilty && atomic_read(&s_job->karma) > sched->hang_limit) {
 			found_guilty = true;
@@ -414,31 +486,11 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 		if (found_guilty && s_job->s_fence->scheduled.context == guilty_context)
 			dma_fence_set_error(&s_fence->finished, -ECANCELED);
 
-		spin_unlock_irqrestore(&sched->job_list_lock, flags);
-		fence = sched->ops->run_job(s_job);
+		s_job->s_fence->parent = sched->ops->run_job(s_job);
 		atomic_inc(&sched->hw_rq_count);
-
-		if (fence) {
-			s_fence->parent = dma_fence_get(fence);
-			r = dma_fence_add_callback(fence, &s_fence->cb,
-						   drm_sched_process_job);
-			if (r == -ENOENT)
-				drm_sched_process_job(fence, &s_fence->cb);
-			else if (r)
-				DRM_ERROR("fence add callback failed (%d)\n",
-					  r);
-			dma_fence_put(fence);
-		} else {
-			if (s_fence->finished.error < 0)
-				drm_sched_expel_job_unlocked(s_job);
-			drm_sched_process_job(NULL, &s_fence->cb);
-		}
-		spin_lock_irqsave(&sched->job_list_lock, flags);
 	}
-	drm_sched_start_timeout(sched);
-	spin_unlock_irqrestore(&sched->job_list_lock, flags);
 }
-EXPORT_SYMBOL(drm_sched_job_recovery);
+EXPORT_SYMBOL(drm_sched_resubmit_jobs);
 
 /**
  * drm_sched_job_init - init a scheduler job
@@ -634,26 +686,14 @@ static int drm_sched_main(void *param)
 				DRM_ERROR("fence add callback failed (%d)\n",
 					  r);
 			dma_fence_put(fence);
-		} else {
-			if (s_fence->finished.error < 0)
-				drm_sched_expel_job_unlocked(sched_job);
+		} else
 			drm_sched_process_job(NULL, &s_fence->cb);
-		}
 
 		wake_up(&sched->job_scheduled);
 	}
 	return 0;
 }
 
-static void drm_sched_expel_job_unlocked(struct drm_sched_job *s_job)
-{
-	struct drm_gpu_scheduler *sched = s_job->sched;
-
-	spin_lock(&sched->job_list_lock);
-	list_del_init(&s_job->node);
-	spin_unlock(&sched->job_list_lock);
-}
-
 /**
  * drm_sched_init - Init a gpu scheduler instance
  *
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index f7508e907536..4704b2df3688 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -234,18 +234,21 @@ v3d_gpu_reset_for_timeout(struct v3d_dev *v3d, struct drm_sched_job *sched_job)
 	for (q = 0; q < V3D_MAX_QUEUES; q++) {
 		struct drm_gpu_scheduler *sched = &v3d->queue[q].sched;
 
-		kthread_park(sched->thread);
-		drm_sched_hw_job_reset(sched, (sched_job->sched == sched ?
-					       sched_job : NULL));
+		drm_sched_stop(sched);
+
+		if(sched_job)
+			drm_sched_increase_karma(sched_job);
 	}
 
 	/* get the GPU back into the init state */
 	v3d_reset(v3d);
 
+	for (q = 0; q < V3D_MAX_QUEUES; q++)
+		drm_sched_resubmit_jobs(sched_job->sched);
+
 	/* Unblock schedulers and restart their jobs. */
 	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		drm_sched_job_recovery(&v3d->queue[q].sched);
-		kthread_unpark(v3d->queue[q].sched.thread);
+		drm_sched_start(&v3d->queue[q].sched, true);
 	}
 
 	mutex_unlock(&v3d->reset_lock);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 47e19796c450..c567bba91ba0 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -298,9 +298,10 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		       void *owner);
 void drm_sched_job_cleanup(struct drm_sched_job *job);
 void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
-void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched,
-			    struct drm_sched_job *job);
-void drm_sched_job_recovery(struct drm_gpu_scheduler *sched);
+void drm_sched_stop(struct drm_gpu_scheduler *sched);
+void drm_sched_start(struct drm_gpu_scheduler *sched, bool full_recovery);
+void drm_sched_resubmit_jobs(struct drm_gpu_scheduler *sched);
+void drm_sched_increase_karma(struct drm_sched_job *bad);
 bool drm_sched_dependency_optimized(struct dma_fence* fence,
 				    struct drm_sched_entity *entity);
 void drm_sched_fault(struct drm_gpu_scheduler *sched);