1 files changed, 131 insertions, 96 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c
index a42763e1429d..fe174a4857be 100644
--- a/drivers/gpu/drm/scheduler/sched_entity.c
+++ b/drivers/gpu/drm/scheduler/sched_entity.c
@@ -21,17 +21,16 @@
  *
  */
 
-#include <linux/kthread.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/completion.h>
 
 #include <drm/drm_print.h>
 #include <drm/gpu_scheduler.h>
 
-#include "gpu_scheduler_trace.h"
+#include "sched_internal.h"
 
-#define to_drm_sched_job(sched_job)		\
-		container_of((sched_job), struct drm_sched_job, queue_node)
+#include "gpu_scheduler_trace.h"
 
 /**
  * drm_sched_entity_init - Init a context entity used by scheduler when
@@ -51,7 +50,7 @@
  * drm_sched_entity_set_priority(). For changing the set of schedulers
  * @sched_list at runtime see drm_sched_entity_modify_sched().
  *
- * An entity is cleaned up by callind drm_sched_entity_fini(). See also
+ * An entity is cleaned up by calling drm_sched_entity_fini(). See also
  * drm_sched_entity_destroy().
  *
  * Returns 0 on success or a negative error code on failure.
@@ -71,19 +70,42 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 	entity->guilty = guilty;
 	entity->num_sched_list = num_sched_list;
 	entity->priority = priority;
+	entity->last_user = current->group_leader;
+	/*
+	 * It's perfectly valid to initialize an entity without having a valid
+	 * scheduler attached. It's just not valid to use the scheduler before it
+	 * is initialized itself.
+	 */
 	entity->sched_list = num_sched_list > 1 ? sched_list : NULL;
 	RCU_INIT_POINTER(entity->last_scheduled, NULL);
 	RB_CLEAR_NODE(&entity->rb_tree_node);
 
-	if(num_sched_list)
-		entity->rq = &sched_list[0]->sched_rq[entity->priority];
+	if (num_sched_list && !sched_list[0]->sched_rq) {
+		/* Since every entry covered by num_sched_list
+		 * should be non-NULL and therefore we warn drivers
+		 * not to do this and to fix their DRM calling order.
+		 */
+		pr_warn("%s: called with uninitialized scheduler\n", __func__);
+	} else if (num_sched_list) {
+		/* The "priority" of an entity cannot exceed the number of run-queues of a
+		 * scheduler. Protect against num_rqs being 0, by converting to signed. Choose
+		 * the lowest priority available.
+		 */
+		if (entity->priority >= sched_list[0]->num_rqs) {
+			dev_err(sched_list[0]->dev, "entity has out-of-bounds priority: %u. num_rqs: %u\n",
+				entity->priority, sched_list[0]->num_rqs);
+			entity->priority = max_t(s32, (s32) sched_list[0]->num_rqs - 1,
+						 (s32) DRM_SCHED_PRIORITY_KERNEL);
+		}
+		entity->rq = sched_list[0]->sched_rq[entity->priority];
+	}
 
 	init_completion(&entity->entity_idle);
 
 	/* We start in an idle state. */
 	complete_all(&entity->entity_idle);
 
-	spin_lock_init(&entity->rq_lock);
+	spin_lock_init(&entity->lock);
 	spsc_queue_init(&entity->job_queue);
 
 	atomic_set(&entity->fence_seq, 0);
@@ -111,8 +133,10 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity,
 {
 	WARN_ON(!num_sched_list || !sched_list);
 
+	spin_lock(&entity->lock);
 	entity->sched_list = sched_list;
 	entity->num_sched_list = num_sched_list;
+	spin_unlock(&entity->lock);
 }
 EXPORT_SYMBOL(drm_sched_entity_modify_sched);
 
@@ -128,18 +152,6 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
 	return false;
 }
 
-/* Return true if entity could provide a job. */
-bool drm_sched_entity_is_ready(struct drm_sched_entity *entity)
-{
-	if (spsc_queue_peek(&entity->job_queue) == NULL)
-		return false;
-
-	if (READ_ONCE(entity->dependency))
-		return false;
-
-	return true;
-}
-
 /**
  * drm_sched_entity_error - return error of last scheduled job
  * @entity: scheduler entity to check
@@ -161,25 +173,15 @@ int drm_sched_entity_error(struct drm_sched_entity *entity)
 }
 EXPORT_SYMBOL(drm_sched_entity_error);
 
+static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
+					  struct dma_fence_cb *cb);
+
 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, -ESRCH);
-	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);
+	struct dma_fence *f;
 	unsigned long index;
 
-	dma_fence_put(f);
-
 	/* Wait for all dependencies to avoid data corruptions */
 	xa_for_each(&job->dependencies, index, f) {
 		struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
@@ -207,6 +209,21 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 		dma_fence_put(f);
 	}
 
+	drm_sched_fence_scheduled(job->s_fence, NULL);
+	drm_sched_fence_finished(job->s_fence, -ESRCH);
+	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);
+
+	dma_fence_put(f);
+
 	INIT_WORK(&job->work, drm_sched_entity_kill_jobs_work);
 	schedule_work(&job->work);
 }
@@ -220,10 +237,10 @@ static void drm_sched_entity_kill(struct drm_sched_entity *entity)
 	if (!entity->rq)
 		return;
 
-	spin_lock(&entity->rq_lock);
+	spin_lock(&entity->lock);
 	entity->stopped = true;
 	drm_sched_rq_remove_entity(entity->rq, entity);
-	spin_unlock(&entity->rq_lock);
+	spin_unlock(&entity->lock);
 
 	/* Make sure this entity is not used by the scheduler at the moment */
 	wait_for_completion(&entity->entity_idle);
@@ -231,13 +248,20 @@ static void drm_sched_entity_kill(struct drm_sched_entity *entity)
 	/* The entity is guaranteed to not be used by the scheduler */
 	prev = rcu_dereference_check(entity->last_scheduled, true);
 	dma_fence_get(prev);
-	while ((job = to_drm_sched_job(spsc_queue_pop(&entity->job_queue)))) {
+	while ((job = drm_sched_entity_queue_pop(entity))) {
 		struct drm_sched_fence *s_fence = job->s_fence;
 
 		dma_fence_get(&s_fence->finished);
-		if (!prev || dma_fence_add_callback(prev, &job->finish_cb,
-					   drm_sched_entity_kill_jobs_cb))
+		if (!prev ||
+		    dma_fence_add_callback(prev, &job->finish_cb,
+					   drm_sched_entity_kill_jobs_cb)) {
+			/*
+			 * Adding callback above failed.
+			 * dma_fence_put() checks for NULL.
+			 */
+			dma_fence_put(prev);
 			drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
+		}
 
 		prev = &s_fence->finished;
 	}
@@ -266,9 +290,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 		return 0;
 
 	sched = entity->rq->sched;
-	/**
-	 * The client will not queue more IBs during this fini, consume existing
-	 * queued IBs or discard them on SIGKILL
+	/*
+	 * The client will not queue more jobs during this fini - consume
+	 * existing queued ones, or discard them on SIGKILL.
 	 */
 	if (current->flags & PF_EXITING) {
 		if (timeout)
@@ -281,9 +305,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 				    drm_sched_entity_is_idle(entity));
 	}
 
-	/* For killed process disable any more IBs enqueue right now */
+	/* For a killed process disallow further enqueueing of jobs. */
 	last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
-	if ((!last_user || last_user == current->group_leader) &&
+	if (last_user == current->group_leader &&
 	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
 		drm_sched_entity_kill(entity);
 
@@ -305,9 +329,9 @@ EXPORT_SYMBOL(drm_sched_entity_flush);
 void drm_sched_entity_fini(struct drm_sched_entity *entity)
 {
 	/*
-	 * 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 consumption of existing jobs wasn't completed forcefully remove
+	 * them. Also makes sure that the scheduler won't touch this entity any
+	 * more.
 	 */
 	drm_sched_entity_kill(entity);
 
@@ -336,20 +360,9 @@ void drm_sched_entity_destroy(struct drm_sched_entity *entity)
 }
 EXPORT_SYMBOL(drm_sched_entity_destroy);
 
-/* drm_sched_entity_clear_dep - callback to clear the entities dependency */
-static void drm_sched_entity_clear_dep(struct dma_fence *f,
-				       struct dma_fence_cb *cb)
-{
-	struct drm_sched_entity *entity =
-		container_of(cb, struct drm_sched_entity, cb);
-
-	entity->dependency = NULL;
-	dma_fence_put(f);
-}
-
 /*
- * drm_sched_entity_clear_dep - callback to clear the entities dependency and
- * wake up scheduler
+ * drm_sched_entity_wakeup - callback to clear the entity's dependency and
+ * wake up the scheduler
  */
 static void drm_sched_entity_wakeup(struct dma_fence *f,
 				    struct dma_fence_cb *cb)
@@ -357,8 +370,9 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
 	struct drm_sched_entity *entity =
 		container_of(cb, struct drm_sched_entity, cb);
 
-	drm_sched_entity_clear_dep(f, cb);
-	drm_sched_wakeup_if_can_queue(entity->rq->sched);
+	entity->dependency = NULL;
+	dma_fence_put(f);
+	drm_sched_wakeup(entity->rq->sched);
 }
 
 /**
@@ -367,14 +381,14 @@ static void drm_sched_entity_wakeup(struct dma_fence *f,
  * @entity: scheduler entity
  * @priority: scheduler priority
  *
- * Update the priority of runqueus used for the entity.
+ * Update the priority of runqueues used for the entity.
  */
 void drm_sched_entity_set_priority(struct drm_sched_entity *entity,
 				   enum drm_sched_priority priority)
 {
-	spin_lock(&entity->rq_lock);
+	spin_lock(&entity->lock);
 	entity->priority = priority;
-	spin_unlock(&entity->rq_lock);
+	spin_unlock(&entity->lock);
 }
 EXPORT_SYMBOL(drm_sched_entity_set_priority);
 
@@ -382,7 +396,8 @@ EXPORT_SYMBOL(drm_sched_entity_set_priority);
  * Add a callback to the current dependency of the entity to wake up the
  * scheduler when the entity becomes available.
  */
-static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
+static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity,
+					       struct drm_sched_job *sched_job)
 {
 	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct dma_fence *fence = entity->dependency;
@@ -410,15 +425,12 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 		fence = dma_fence_get(&s_fence->scheduled);
 		dma_fence_put(entity->dependency);
 		entity->dependency = fence;
-		if (!dma_fence_add_callback(fence, &entity->cb,
-					    drm_sched_entity_clear_dep))
-			return true;
-
-		/* Ignore it when it is already scheduled */
-		dma_fence_put(fence);
-		return false;
 	}
 
+	if (trace_drm_sched_job_unschedulable_enabled() &&
+	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &entity->dependency->flags))
+		trace_drm_sched_job_unschedulable(sched_job, entity->dependency);
+
 	if (!dma_fence_add_callback(entity->dependency, &entity->cb,
 				    drm_sched_entity_wakeup))
 		return true;
@@ -453,15 +465,13 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 {
 	struct drm_sched_job *sched_job;
 
-	sched_job = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
+	sched_job = drm_sched_entity_queue_peek(entity);
 	if (!sched_job)
 		return NULL;
 
 	while ((entity->dependency =
 			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))
+		if (drm_sched_entity_add_dependency_cb(entity, sched_job))
 			return NULL;
 	}
 
@@ -489,9 +499,18 @@ struct drm_sched_job *drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 	if (drm_sched_policy == DRM_SCHED_POLICY_FIFO) {
 		struct drm_sched_job *next;
 
-		next = to_drm_sched_job(spsc_queue_peek(&entity->job_queue));
-		if (next)
-			drm_sched_rq_update_fifo(entity, next->submit_ts);
+		next = drm_sched_entity_queue_peek(entity);
+		if (next) {
+			struct drm_sched_rq *rq;
+
+			spin_lock(&entity->lock);
+			rq = entity->rq;
+			spin_lock(&rq->lock);
+			drm_sched_rq_update_fifo_locked(entity, rq,
+							next->submit_ts);
+			spin_unlock(&rq->lock);
+			spin_unlock(&entity->lock);
+		}
 	}
 
 	/* Jobs and entities might have different lifecycles. Since we're
@@ -518,10 +537,10 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
 		return;
 
 	/*
-	 * Only when the queue is empty are we guaranteed that the scheduler
-	 * thread cannot change ->last_scheduled. To enforce ordering we need
-	 * a read barrier here. See drm_sched_entity_pop_job() for the other
-	 * side.
+	 * Only when the queue is empty are we guaranteed that
+	 * drm_sched_run_job_work() cannot change entity->last_scheduled. To
+	 * enforce ordering we need a read barrier here. See
+	 * drm_sched_entity_pop_job() for the other side.
 	 */
 	smp_rmb();
 
@@ -531,17 +550,18 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
 	if (fence && !dma_fence_is_signaled(fence))
 		return;
 
-	spin_lock(&entity->rq_lock);
+	spin_lock(&entity->lock);
 	sched = drm_sched_pick_best(entity->sched_list, entity->num_sched_list);
-	rq = sched ? &sched->sched_rq[entity->priority] : NULL;
+	rq = sched ? sched->sched_rq[entity->priority] : NULL;
 	if (rq != entity->rq) {
 		drm_sched_rq_remove_entity(entity->rq, entity);
 		entity->rq = rq;
 	}
-	spin_unlock(&entity->rq_lock);
 
 	if (entity->num_sched_list == 1)
 		entity->sched_list = NULL;
+
+	spin_unlock(&entity->lock);
 }
 
 /**
@@ -552,8 +572,6 @@ void drm_sched_entity_select_rq(struct drm_sched_entity *entity)
  * fence sequence number this function should be called with drm_sched_job_arm()
  * under common lock for the struct drm_sched_entity that was set up for
  * @sched_job in drm_sched_job_init().
- *
- * Returns 0 for success, negative error code otherwise.
  */
 void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 {
@@ -561,7 +579,15 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 	bool first;
 	ktime_t submit_ts;
 
-	trace_drm_sched_job(sched_job, entity);
+	trace_drm_sched_job_queue(sched_job, entity);
+
+	if (trace_drm_sched_job_add_dep_enabled()) {
+		struct dma_fence *entry;
+		unsigned long index;
+
+		xa_for_each(&sched_job->dependencies, index, entry)
+			trace_drm_sched_job_add_dep(sched_job, entry);
+	}
 	atomic_inc(entity->rq->sched->score);
 	WRITE_ONCE(entity->last_user, current->group_leader);
 
@@ -575,22 +601,31 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job)
 
 	/* first job wakes up scheduler */
 	if (first) {
+		struct drm_gpu_scheduler *sched;
+		struct drm_sched_rq *rq;
+
 		/* Add the entity to the run queue */
-		spin_lock(&entity->rq_lock);
+		spin_lock(&entity->lock);
 		if (entity->stopped) {
-			spin_unlock(&entity->rq_lock);
+			spin_unlock(&entity->lock);
 
 			DRM_ERROR("Trying to push to a killed entity\n");
 			return;
 		}
 
-		drm_sched_rq_add_entity(entity->rq, entity);
-		spin_unlock(&entity->rq_lock);
+		rq = entity->rq;
+		sched = rq->sched;
+
+		spin_lock(&rq->lock);
+		drm_sched_rq_add_entity(rq, entity);
 
 		if (drm_sched_policy == DRM_SCHED_POLICY_FIFO)
-			drm_sched_rq_update_fifo(entity, submit_ts);
+			drm_sched_rq_update_fifo_locked(entity, rq, submit_ts);
+
+		spin_unlock(&rq->lock);
+		spin_unlock(&entity->lock);
 
-		drm_sched_wakeup_if_can_queue(entity->rq->sched);
+		drm_sched_wakeup(sched);
 	}
 }
 EXPORT_SYMBOL(drm_sched_entity_push_job);