diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index 3f7f761df4cd267e42ec73a6e7ffb61f06ea3d6b..3d5c94496aa3b6c26fd1b8f7c09a4170e35f96cc 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -73,6 +73,9 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 
 	init_completion(&entity->entity_idle);
 
+	/* We start in an idle state. */
+	complete_all(&entity->entity_idle);
+
 	spin_lock_init(&entity->rq_lock);
 	spsc_queue_init(&entity->job_queue);
 
@@ -138,6 +141,73 @@ bool drm_sched_entity_is_ready(struct drm_sched_entity *entity)
 	return true;
 }
 
+static void drm_sched_entity_kill_jobs_work(struct work_struct *wrk)
+{
+	struct drm_sched_job *job = container_of(wrk, typeof(*job), work);
+
+	drm_sched_fence_finished(job->s_fence);
+	WARN_ON(job->s_fence->parent);
+	job->sched->ops->free_job(job);
+}
+
+/* Signal the scheduler finished fence when the entity in question is killed. */
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb)
+{
+	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
+						 finish_cb);
+	int r;
+
+	dma_fence_put(f);
+
+	/* Wait for all dependencies to avoid data corruptions */
+	while (!xa_empty(&job->dependencies)) {
+		f = xa_erase(&job->dependencies, job->last_dependency++);
+		r = dma_fence_add_callback(f, &job->finish_cb,
+					   drm_sched_entity_kill_jobs_cb);
+		if (!r)
+			return;
+
+		dma_fence_put(f);
+	}
+
+	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
+	schedule_work(&job->work);
+}
+
+/* Remove the entity from the scheduler and kill all pending jobs */
+static void drm_sched_entity_kill(struct drm_sched_entity *entity)
+{
+	struct drm_sched_job *job;
+	struct dma_fence *prev;
+
+	if (!entity->rq)
+		return;
+
+	spin_lock(&entity->rq_lock);
+	entity->stopped = true;
+	drm_sched_rq_remove_entity(entity->rq, entity);
+	spin_unlock(&entity->rq_lock);
+
+	/* Make sure this entity is not used by the scheduler at the moment */
+	wait_for_completion(&entity->entity_idle);
+
+	prev = dma_fence_get(entity->last_scheduled);
+	while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) {
+		struct drm_sched_fence *s_fence = job->s_fence;
+
+		dma_fence_set_error(&s_fence->finished, -ESRCH);
+
+		dma_fence_get(&s_fence->finished);
+		if (!prev || dma_fence_add_callback(prev, &job->finish_cb,
+					   drm_sched_entity_kill_jobs_cb))
+			drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
+
+		prev = &s_fence->finished;
+	}
+	dma_fence_put(prev);
+}
+
 /**
  * drm_sched_entity_flush - Flush a context entity
  *
@@ -178,80 +248,13 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 	/* For killed process disable any more IBs enqueue right now */
 	last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
 	if ((!last_user || last_user == current->group_leader) &&
-	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL)) {
-		spin_lock(&entity->rq_lock);
-		entity->stopped = true;
-		drm_sched_rq_remove_entity(entity->rq, entity);
-		spin_unlock(&entity->rq_lock);
-	}
+	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
+		drm_sched_entity_kill(entity);
 
 	return ret;
 }
 EXPORT_SYMBOL(drm_sched_entity_flush);
 
-/**
- * drm_sched_entity_kill_jobs - helper for drm_sched_entity_kill_jobs
- *
- * @f: signaled fence
- * @cb: our callback structure
- *
- * Signal the scheduler finished fence when the entity in question is killed.
- */
-static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
-					  struct dma_fence_cb *cb)
-{
-	struct drm_sched_job *job = container_of(cb, struct drm_sched_job,
-						 finish_cb);
-
-	drm_sched_fence_finished(job->s_fence);
-	WARN_ON(job->s_fence->parent);
-	job->sched->ops->free_job(job);
-}
-
-/**
- * drm_sched_entity_kill_jobs - Make sure all remaining jobs are killed
- *
- * @entity: entity which is cleaned up
- *
- * Makes sure that all remaining jobs in an entity are killed before it is
- * destroyed.
- */
-static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
-{
-	struct drm_sched_job *job;
-	struct dma_fence *f;
-	int r;
-
-	while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) {
-		struct drm_sched_fence *s_fence = job->s_fence;
-
-		/* Wait for all dependencies to avoid data corruptions */
-		while ((f = job->sched->ops->dependency(job, entity)))
-			dma_fence_wait(f, false);
-
-		drm_sched_fence_scheduled(s_fence);
-		dma_fence_set_error(&s_fence->finished, -ESRCH);
-
-		/*
-		 * When pipe is hanged by older entity, new entity might
-		 * not even have chance to submit it's first job to HW
-		 * and so entity->last_scheduled will remain NULL
-		 */
-		if (!entity->last_scheduled) {
-			drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
-			continue;
-		}
-
-		r = dma_fence_add_callback(entity->last_scheduled,
-					   &job->finish_cb,
-					   drm_sched_entity_kill_jobs_cb);
-		if (r == -ENOENT)
-			drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
-		else if (r)
-			DRM_ERROR("fence add callback failed (%d)\n", r);
-	}
-}
-
 /**
  * drm_sched_entity_cleanup - Destroy a context entity
  *
@@ -263,33 +266,17 @@ static void drm_sched_entity_kill_jobs(struct drm_sched_entity *entity)
  */
 void drm_sched_entity_fini(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = NULL;
-
-	if (entity->rq) {
-		sched = entity->rq->sched;
-		drm_sched_rq_remove_entity(entity->rq, entity);
-	}
-
-	/* Consumption of existing IBs wasn't completed. Forcefully
-	 * remove them here.
+	/*
+	 * If consumption of existing IBs wasn't completed. Forcefully remove
+	 * them here. Also makes sure that the scheduler won't touch this entity
+	 * any more.
 	 */
-	if (spsc_queue_count(&entity->job_queue)) {
-		if (sched) {
-			/*
-			 * Wait for thread to idle to make sure it isn't processing
-			 * this entity.
-			 */
-			wait_for_completion(&entity->entity_idle);
-
-		}
-		if (entity->dependency) {
-			dma_fence_remove_callback(entity->dependency,
-						  &entity->cb);
-			dma_fence_put(entity->dependency);
-			entity->dependency = NULL;
-		}
+	drm_sched_entity_kill(entity);
 
-		drm_sched_entity_kill_jobs(entity);
+	if (entity->dependency) {
+		dma_fence_remove_callback(entity->dependency, &entity->cb);
+		dma_fence_put(entity->dependency);
+		entity->dependency = NULL;
 	}
 
 	dma_fence_put(entity->last_scheduled);
@@ -381,7 +368,7 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 	}
 
 	s_fence = to_drm_sched_fence(fence);
-	if (s_fence && s_fence->sched == sched) {
+	if (!fence->error && s_fence && s_fence->sched == sched) {
 
 		/*
 		 * Fence is from the same scheduler, only need to wait for
@@ -407,6 +394,19 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 	return false;
 }
 
+static struct dma_fence *
+drm_sched_job_dependency(struct drm_sched_job *job,
+			 struct drm_sched_entity *entity)
+{
+	if (!xa_empty(&job->dependencies))
+		return xa_erase(&job->dependencies, job->last_dependency++);
+
+	if (job->sched->ops->dependency)
+		return job->sched->ops->dependency(job, entity);
+
+	return NULL;
+}
+
 /**
  * drm_sched_entity_pop_job - get a ready to be scheduled job from the entity
  *
@@ -416,7 +416,6 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
  */
 struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct drm_sched_job *sched_job;
 
 	sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
@@ -424,7 +423,7 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 		return NULL;
 
 	while ((entity->dependency =
-			sched->ops->dependency(sched_job, entity))) {
+			drm_sched_job_dependency(sched_job, entity))) {
 		trace_drm_sched_job_wait_dep(sched_job, entity->dependency);
 
 		if (drm_sched_entity_add_dependency_cb(entity))
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index b6c2757c3d83f51b075a3bbab3fc3394304eaef2..936e87ad3feb2c3ef1ca1bfabf17cbee29d97eeb 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -48,9 +48,11 @@
 #include <linux/wait.h>
 #include <linux/sched.h>
 #include <linux/completion.h>
+#include <linux/dma-resv.h>
 #include <uapi/linux/sched/types.h>
 
 #include <drm/drm_print.h>
+#include <drm/drm_gem.h>
 #include <drm/gpu_scheduler.h>
 #include <drm/spsc_queue.h>
 
@@ -567,10 +569,104 @@ int drm_sched_job_init(struct drm_sched_job *job,
 
 	INIT_LIST_HEAD(&job->node);
 
+	xa_init_flags(&job->dependencies, XA_FLAGS_ALLOC);
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_sched_job_init);
 
+/**
+ * drm_sched_job_add_dependency - adds the fence as a job dependency
+ * @job: scheduler job to add the dependencies to
+ * @fence: the dma_fence to add to the list of dependencies.
+ *
+ * Note that @fence is consumed in both the success and error cases.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_add_dependency(struct drm_sched_job *job,
+				 struct dma_fence *fence)
+{
+	struct dma_fence *entry;
+	unsigned long index;
+	u32 id = 0;
+	int ret;
+
+	if (!fence)
+		return 0;
+
+	/* Deduplicate if we already depend on a fence from the same context.
+	 * This lets the size of the array of deps scale with the number of
+	 * engines involved, rather than the number of BOs.
+	 */
+	xa_for_each(&job->dependencies, index, entry) {
+		if (entry->context != fence->context)
+			continue;
+
+		if (dma_fence_is_later(fence, entry)) {
+			dma_fence_put(entry);
+			xa_store(&job->dependencies, index, fence, GFP_KERNEL);
+		} else {
+			dma_fence_put(fence);
+		}
+		return 0;
+	}
+
+	ret = xa_alloc(&job->dependencies, &id, fence, xa_limit_32b, GFP_KERNEL);
+	if (ret != 0)
+		dma_fence_put(fence);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_add_dependency);
+
+/**
+ * drm_sched_job_add_implicit_dependencies - adds implicit dependencies as job
+ *   dependencies
+ * @job: scheduler job to add the dependencies to
+ * @obj: the gem object to add new dependencies from.
+ * @write: whether the job might write the object (so we need to depend on
+ * shared fences in the reservation object).
+ *
+ * This should be called after drm_gem_lock_reservations() on your array of
+ * GEM objects used in the job but before updating the reservations with your
+ * own fences.
+ *
+ * Returns:
+ * 0 on success, or an error on failing to expand the array.
+ */
+int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job,
+					    struct drm_gem_object *obj,
+					    bool write)
+{
+	int ret;
+	struct dma_fence **fences;
+	unsigned int i, fence_count;
+
+	if (!write) {
+		struct dma_fence *fence = dma_resv_get_excl_rcu(obj->resv);
+
+		return drm_sched_job_add_dependency(job, fence);
+	}
+
+	ret = dma_resv_get_fences_rcu(obj->resv, NULL, &fence_count, &fences);
+	if (ret || !fence_count)
+		return ret;
+
+	for (i = 0; i < fence_count; i++) {
+		ret = drm_sched_job_add_dependency(job, fences[i]);
+		if (ret)
+			break;
+	}
+
+	for (; i < fence_count; i++)
+		dma_fence_put(fences[i]);
+	kfree(fences);
+	return ret;
+}
+EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies);
+
 /**
  * drm_sched_job_cleanup - clean up scheduler job resources
  *
@@ -578,8 +674,16 @@ EXPORT_SYMBOL(drm_sched_job_init);
  */
 void drm_sched_job_cleanup(struct drm_sched_job *job)
 {
+	struct dma_fence *fence;
+	unsigned long index;
+
 	dma_fence_put(&job->s_fence->finished);
 	job->s_fence = NULL;
+
+	xa_for_each(&job->dependencies, index, fence) {
+		dma_fence_put(fence);
+	}
+	xa_destroy(&job->dependencies);
 }
 EXPORT_SYMBOL(drm_sched_job_cleanup);
 
@@ -791,10 +895,10 @@ static int drm_sched_main(void *param)
 
 		sched_job = drm_sched_entity_pop_job(entity);
 
-		complete(&entity->entity_idle);
-
-		if (!sched_job)
+		if (!sched_job) {
+			complete_all(&entity->entity_idle);
 			continue;
+		}
 
 		s_fence = sched_job->s_fence;
 
@@ -803,6 +907,7 @@ static int drm_sched_main(void *param)
 
 		trace_drm_run_job(sched_job, entity);
 		fence = sched->ops->run_job(sched_job);
+		complete_all(&entity->entity_idle);
 		drm_sched_fence_scheduled(s_fence);
 
 		if (!IS_ERR_OR_NULL(fence)) {
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 92436553fd6a8124f25be33a49df7c5bb4881e4b..ba955f5f957b8dfee84a02efa216470c6bd2ab68 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -27,9 +27,13 @@
 #include <drm/spsc_queue.h>
 #include <linux/dma-fence.h>
 #include <linux/completion.h>
+#include <linux/xarray.h>
+#include <linux/workqueue.h>
 
 #define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
 
+struct drm_gem_object;
+
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
@@ -191,13 +195,33 @@ struct drm_sched_job {
 	struct spsc_node		queue_node;
 	struct drm_gpu_scheduler	*sched;
 	struct drm_sched_fence		*s_fence;
-	struct dma_fence_cb		finish_cb;
+
+	/*
+	 * work is used only after finish_cb has been used and will not be
+	 * accessed anymore.
+	 */
+	union {
+		struct dma_fence_cb		finish_cb;
+		struct work_struct 		work;
+	};
+
 	struct list_head		node;
 	uint64_t			id;
 	atomic_t			karma;
 	enum drm_sched_priority		s_priority;
 	struct drm_sched_entity  *entity;
 	struct dma_fence_cb		cb;
+	/**
+	 * @dependencies:
+	 *
+	 * Contains the dependencies as struct dma_fence for this job, see
+	 * drm_sched_job_add_dependency() and
+	 * drm_sched_job_add_implicit_dependencies().
+	 */
+	struct xarray			dependencies;
+
+	/** @last_dependency: tracks @dependencies as they signal */
+	unsigned long			last_dependency;
 };
 
 static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
@@ -214,9 +238,15 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
  */
 struct drm_sched_backend_ops {
 	/**
-         * @dependency: Called when the scheduler is considering scheduling
-         * this job next, to get another struct dma_fence for this job to
-	 * block on.  Once it returns NULL, run_job() may be called.
+	 * @dependency:
+	 *
+	 * Called when the scheduler is considering scheduling this job next, to
+	 * get another struct dma_fence for this job to block on.  Once it
+	 * returns NULL, run_job() may be called.
+	 *
+	 * If a driver exclusively uses drm_sched_job_add_dependency() and
+	 * drm_sched_job_add_implicit_dependencies() this can be ommitted and
+	 * left as NULL.
 	 */
 	struct dma_fence *(*dependency)(struct drm_sched_job *sched_job,
 					struct drm_sched_entity *s_entity);
@@ -299,6 +329,13 @@ void drm_sched_fini(struct drm_gpu_scheduler *sched);
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner);
+int drm_sched_job_add_dependency(struct drm_sched_job *job,
+				 struct dma_fence *fence);
+int drm_sched_job_add_implicit_dependencies(struct drm_sched_job *job,
+					    struct drm_gem_object *obj,
+					    bool write);
+
+
 void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
 				    struct drm_gpu_scheduler **sched_list,
                                    unsigned int num_sched_list);