drm/sched: Fix drm_sched_fence_free() so it can be passed an uninitialized fence

drm_sched_job_cleanup() will pass an uninitialized fence to
drm_sched_fence_free(), which will cause to_drm_sched_fence() to return
a NULL fence object, causing a NULL pointer deref when this NULL object
is passed to kmem_cache_free().

Let's create a new drm_sched_fence_free() function that takes a
drm_sched_fence pointer and suffix the old function with _rcu. While at
it, complain if drm_sched_fence_free() is passed an initialized fence
or if drm_sched_fence_free_rcu() is passed an uninitialized fence.

Fixes: dbe48d030b ("drm/sched: Split drm_sched_job_init")
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20210903120554.444101-1-boris.brezillon@collabora.com

drivers/gpu/drm/scheduler/sched_fence.c

@@ -69,19 +69,28 @@ static const char *drm_sched_fence_get_timeline_name(struct dma_fence *f)
 	return (const char *)fence->sched->name;
 }
 
-/**
- * drm_sched_fence_free - free up the fence memory
- *
- * @rcu: RCU callback head
- *
- * Free up the fence memory after the RCU grace period.
- */
-void drm_sched_fence_free(struct rcu_head *rcu)
+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);
 
-	kmem_cache_free(sched_fence_slab, fence);
+	if (!WARN_ON_ONCE(!fence))
+		kmem_cache_free(sched_fence_slab, fence);
+}
+
+/**
+ * drm_sched_fence_free - free up an uninitialized fence
+ *
+ * @fence: fence to free
+ *
+ * Free up the fence memory. Should only be used if drm_sched_fence_init()
+ * has not been called yet.
+ */
+void drm_sched_fence_free(struct drm_sched_fence *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);
 }
 
 /**
@@ -97,7 +106,7 @@ 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);
 }
 
 /**

drivers/gpu/drm/scheduler/sched_main.c

@@ -750,7 +750,7 @@ void drm_sched_job_cleanup(struct drm_sched_job *job)
 		dma_fence_put(&job->s_fence->finished);
 	} else {
 		/* aborted job before committing to run it */
-		drm_sched_fence_free(&job->s_fence->finished.rcu);
+		drm_sched_fence_free(job->s_fence);
 	}
 
 	job->s_fence = NULL;

include/drm/gpu_scheduler.h

@@ -509,7 +509,7 @@ struct drm_sched_fence *drm_sched_fence_alloc(
 	struct drm_sched_entity *s_entity, void *owner);
 void drm_sched_fence_init(struct drm_sched_fence *fence,
 			  struct drm_sched_entity *entity);
-void drm_sched_fence_free(struct rcu_head *rcu);
+void drm_sched_fence_free(struct drm_sched_fence *fence);
 
 void drm_sched_fence_scheduled(struct drm_sched_fence *fence);
 void drm_sched_fence_finished(struct drm_sched_fence *fence);