1 files changed, 157 insertions, 28 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 67382621b429..5bc5f775abe1 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>
 
@@ -564,7 +566,6 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext);
 
 /**
  * drm_sched_job_init - init a scheduler job
- *
  * @job: scheduler job to init
  * @entity: scheduler entity to use
  * @owner: job owner for debugging
@@ -572,43 +573,179 @@ EXPORT_SYMBOL(drm_sched_resubmit_jobs_ext);
  * Refer to drm_sched_entity_push_job() documentation
  * for locking considerations.
  *
+ * Drivers must make sure drm_sched_job_cleanup() if this function returns
+ * successfully, even when @job is aborted before drm_sched_job_arm() is called.
+ *
+ * WARNING: amdgpu abuses &drm_sched.ready to signal when the hardware
+ * has died, which can mean that there's no valid runqueue for a @entity.
+ * This function returns -ENOENT in this case (which probably should be -EIO as
+ * a more meanigful return value).
+ *
  * Returns 0 for success, negative error code otherwise.
  */
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
-	struct drm_gpu_scheduler *sched;
-
 	drm_sched_entity_select_rq(entity);
 	if (!entity->rq)
 		return -ENOENT;
 
-	sched = entity->rq->sched;
-
-	job->sched = sched;
 	job->entity = entity;
-	job->s_priority = entity->rq - sched->sched_rq;
-	job->s_fence = drm_sched_fence_create(entity, owner);
+	job->s_fence = drm_sched_fence_alloc(entity, owner);
 	if (!job->s_fence)
 		return -ENOMEM;
-	job->id = atomic64_inc_return(&sched->job_id_count);
 
 	INIT_LIST_HEAD(&job->list);
 
+	xa_init_flags(&job->dependencies, XA_FLAGS_ALLOC);
+
 	return 0;
 }
 EXPORT_SYMBOL(drm_sched_job_init);
 
 /**
- * drm_sched_job_cleanup - clean up scheduler job resources
+ * drm_sched_job_arm - arm a scheduler job for execution
+ * @job: scheduler job to arm
+ *
+ * This arms a scheduler job for execution. Specifically it initializes the
+ * &drm_sched_job.s_fence of @job, so that it can be attached to struct dma_resv
+ * or other places that need to track the completion of this job.
+ *
+ * Refer to drm_sched_entity_push_job() documentation for locking
+ * considerations.
+ *
+ * This can only be called if drm_sched_job_init() succeeded.
+ */
+void drm_sched_job_arm(struct drm_sched_job *job)
+{
+	struct drm_gpu_scheduler *sched;
+	struct drm_sched_entity *entity = job->entity;
+
+	BUG_ON(!entity);
+
+	sched = entity->rq->sched;
+
+	job->sched = sched;
+	job->s_priority = entity->rq - sched->sched_rq;
+	job->id = atomic64_inc_return(&sched->job_id_count);
+
+	drm_sched_fence_init(job->s_fence, job->entity);
+}
+EXPORT_SYMBOL(drm_sched_job_arm);
+
+/**
+ * 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)
+{
+	struct dma_resv_iter cursor;
+	struct dma_fence *fence;
+	int ret;
+
+	dma_resv_for_each_fence(&cursor, obj->resv, write, fence) {
+		ret = drm_sched_job_add_dependency(job, fence);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(drm_sched_job_add_implicit_dependencies);
+
+
+/**
+ * drm_sched_job_cleanup - clean up scheduler job resources
  * @job: scheduler job to clean up
+ *
+ * Cleans up the resources allocated with drm_sched_job_init().
+ *
+ * Drivers should call this from their error unwind code if @job is aborted
+ * before drm_sched_job_arm() is called.
+ *
+ * After that point of no return @job is committed to be executed by the
+ * scheduler, and this function should be called from the
+ * &drm_sched_backend_ops.free_job callback.
  */
 void drm_sched_job_cleanup(struct drm_sched_job *job)
 {
-	dma_fence_put(&job->s_fence->finished);
+	struct dma_fence *fence;
+	unsigned long index;
+
+	if (kref_read(&job->s_fence->finished.refcount)) {
+		/* drm_sched_job_arm() has been called */
+		dma_fence_put(&job->s_fence->finished);
+	} else {
+		/* aborted job before committing to run it */
+		drm_sched_fence_free(job->s_fence);
+	}
+
 	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);
 
@@ -676,15 +813,6 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 {
 	struct drm_sched_job *job, *next;
 
-	/*
-	 * Don't destroy jobs while the timeout worker is running  OR thread
-	 * is being parked and hence assumed to not touch pending_list
-	 */
-	if ((sched->timeout != MAX_SCHEDULE_TIMEOUT &&
-	    !cancel_delayed_work(&sched->work_tdr)) ||
-	    kthread_should_park())
-		return NULL;
-
 	spin_lock(&sched->job_list_lock);
 
 	job = list_first_entry_or_null(&sched->pending_list,
@@ -693,17 +821,21 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
 	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
 		/* remove job from pending_list */
 		list_del_init(&job->list);
+
+		/* cancel this job's TO timer */
+		cancel_delayed_work(&sched->work_tdr);
 		/* make the scheduled timestamp more accurate */
 		next = list_first_entry_or_null(&sched->pending_list,
 						typeof(*next), list);
-		if (next)
+
+		if (next) {
 			next->s_fence->scheduled.timestamp =
 				job->s_fence->finished.timestamp;
-
+			/* start TO timer for next job */
+			drm_sched_start_timeout(sched);
+		}
 	} else {
 		job = NULL;
-		/* queue timeout for next job */
-		drm_sched_start_timeout(sched);
 	}
 
 	spin_unlock(&sched->job_list_lock);
@@ -791,11 +923,8 @@ static int drm_sched_main(void *param)
 					  (entity = drm_sched_select_entity(sched))) ||
 					 kthread_should_stop());
 
-		if (cleanup_job) {
+		if (cleanup_job)
 			sched->ops->free_job(cleanup_job);
-			/* queue timeout for next job */
-			drm_sched_start_timeout(sched);
-		}
 
 		if (!entity)
 			continue;