1 files changed, 97 insertions, 37 deletions

diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index 69de2c76731f..9391d6f0dc01 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -21,7 +21,7 @@
  *
  */
 
-#include <linux/kthread.h>
+#include <linux/export.h>
 #include <linux/module.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
@@ -29,13 +29,13 @@
 
 #include <drm/gpu_scheduler.h>
 
+#include "sched_internal.h"
+
 static struct kmem_cache *sched_fence_slab;
 
 static int __init drm_sched_fence_slab_init(void)
 {
-	sched_fence_slab = kmem_cache_create(
-		"drm_sched_fence", sizeof(struct drm_sched_fence), 0,
-		SLAB_HWCACHE_ALIGN, NULL);
+	sched_fence_slab = KMEM_CACHE(drm_sched_fence, SLAB_HWCACHE_ALIGN);
 	if (!sched_fence_slab)
 		return -ENOMEM;
 
@@ -48,28 +48,40 @@ static void __exit drm_sched_fence_slab_fini(void)
 	kmem_cache_destroy(sched_fence_slab);
 }
 
-void drm_sched_fence_scheduled(struct drm_sched_fence *fence)
+static void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
+				       struct dma_fence *fence)
+{
+	/*
+	 * smp_store_release() to ensure another thread racing us
+	 * in drm_sched_fence_set_deadline_finished() sees the
+	 * fence's parent set before test_bit()
+	 */
+	smp_store_release(&s_fence->parent, dma_fence_get(fence));
+	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT,
+		     &s_fence->finished.flags))
+		dma_fence_set_deadline(fence, s_fence->deadline);
+}
+
+void drm_sched_fence_scheduled(struct drm_sched_fence *fence,
+			       struct dma_fence *parent)
 {
-	int ret = dma_fence_signal(&fence->scheduled);
-
-	if (!ret)
-		DMA_FENCE_TRACE(&fence->scheduled,
-				"signaled from irq context\n");
-	else
-		DMA_FENCE_TRACE(&fence->scheduled,
-				"was already signaled\n");
+	/* Set the parent before signaling the scheduled fence, such that,
+	 * any waiter expecting the parent to be filled after the job has
+	 * been scheduled (which is the case for drivers delegating waits
+	 * to some firmware) doesn't have to busy wait for parent to show
+	 * up.
+	 */
+	if (!IS_ERR_OR_NULL(parent))
+		drm_sched_fence_set_parent(fence, parent);
+
+	dma_fence_signal(&fence->scheduled);
 }
 
-void drm_sched_fence_finished(struct drm_sched_fence *fence)
+void drm_sched_fence_finished(struct drm_sched_fence *fence, int result)
 {
-	int ret = dma_fence_signal(&fence->finished);
-
-	if (!ret)
-		DMA_FENCE_TRACE(&fence->finished,
-				"signaled from irq context\n");
-	else
-		DMA_FENCE_TRACE(&fence->finished,
-				"was already signaled\n");
+	if (result)
+		dma_fence_set_error(&fence->finished, result);
+	dma_fence_signal(&fence->finished);
 }
 
 static const char *drm_sched_fence_get_driver_name(struct dma_fence *fence)
@@ -83,19 +95,28 @@ static const char *drm_sched_fence_get_timeline_name(struct dma_fence *f)
 	return (const char *)fence->sched->name;
 }
 
+static void drm_sched_fence_free_rcu(struct rcu_head *rcu)
+{
+	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
+	struct drm_sched_fence *fence = to_drm_sched_fence(f);
+
+	if (!WARN_ON_ONCE(!fence))
+		kmem_cache_free(sched_fence_slab, fence);
+}
+
 /**
- * drm_sched_fence_free - free up the fence memory
+ * drm_sched_fence_free - free up an uninitialized fence
  *
- * @rcu: RCU callback head
+ * @fence: fence to free
  *
- * Free up the fence memory after the RCU grace period.
+ * Free up the fence memory. Should only be used if drm_sched_fence_init()
+ * has not been called yet.
  */
-static void drm_sched_fence_free(struct rcu_head *rcu)
+void drm_sched_fence_free(struct drm_sched_fence *fence)
 {
-	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
-	struct drm_sched_fence *fence = to_drm_sched_fence(f);
-
-	kmem_cache_free(sched_fence_slab, fence);
+	/* This function should not be called if the fence has been initialized. */
+	if (!WARN_ON_ONCE(fence->sched))
+		kmem_cache_free(sched_fence_slab, fence);
 }
 
 /**
@@ -111,7 +132,7 @@ static void drm_sched_fence_release_scheduled(struct dma_fence *f)
 	struct drm_sched_fence *fence = to_drm_sched_fence(f);
 
 	dma_fence_put(fence->parent);
-	call_rcu(&fence->finished.rcu, drm_sched_fence_free);
+	call_rcu(&fence->finished.rcu, drm_sched_fence_free_rcu);
 }
 
 /**
@@ -128,6 +149,37 @@ static void drm_sched_fence_release_finished(struct dma_fence *f)
 	dma_fence_put(&fence->scheduled);
 }
 
+static void drm_sched_fence_set_deadline_finished(struct dma_fence *f,
+						  ktime_t deadline)
+{
+	struct drm_sched_fence *fence = to_drm_sched_fence(f);
+	struct dma_fence *parent;
+	unsigned long flags;
+
+	spin_lock_irqsave(&fence->lock, flags);
+
+	/* If we already have an earlier deadline, keep it: */
+	if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags) &&
+	    ktime_before(fence->deadline, deadline)) {
+		spin_unlock_irqrestore(&fence->lock, flags);
+		return;
+	}
+
+	fence->deadline = deadline;
+	set_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, &f->flags);
+
+	spin_unlock_irqrestore(&fence->lock, flags);
+
+	/*
+	 * smp_load_aquire() to ensure that if we are racing another
+	 * thread calling drm_sched_fence_set_parent(), that we see
+	 * the parent set before it calls test_bit(HAS_DEADLINE_BIT)
+	 */
+	parent = smp_load_acquire(&fence->parent);
+	if (parent)
+		dma_fence_set_deadline(parent, deadline);
+}
+
 static const struct dma_fence_ops drm_sched_fence_ops_scheduled = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
@@ -138,6 +190,7 @@ static const struct dma_fence_ops drm_sched_fence_ops_finished = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
 	.release = drm_sched_fence_release_finished,
+	.set_deadline = drm_sched_fence_set_deadline_finished,
 };
 
 struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
@@ -152,27 +205,34 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f)
 }
 EXPORT_SYMBOL(to_drm_sched_fence);
 
-struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity,
-					       void *owner)
+struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity,
+					      void *owner,
+					      u64 drm_client_id)
 {
 	struct drm_sched_fence *fence = NULL;
-	unsigned seq;
 
 	fence = kmem_cache_zalloc(sched_fence_slab, GFP_KERNEL);
 	if (fence == NULL)
 		return NULL;
 
 	fence->owner = owner;
-	fence->sched = entity->rq->sched;
+	fence->drm_client_id = drm_client_id;
 	spin_lock_init(&fence->lock);
 
+	return fence;
+}
+
+void drm_sched_fence_init(struct drm_sched_fence *fence,
+			  struct drm_sched_entity *entity)
+{
+	unsigned seq;
+
+	fence->sched = entity->rq->sched;
 	seq = atomic_inc_return(&entity->fence_seq);
 	dma_fence_init(&fence->scheduled, &drm_sched_fence_ops_scheduled,
 		       &fence->lock, entity->fence_context, seq);
 	dma_fence_init(&fence->finished, &drm_sched_fence_ops_finished,
 		       &fence->lock, entity->fence_context + 1, seq);
-
-	return fence;
 }
 
 module_init(drm_sched_fence_slab_init);