drm: Apply kref_put_mutex() optimisations to drm_gem_object_unreference_unlocked()

We can apply the same optimisation tricks as kref_put_mutex() in our
local equivalent function. However, we have a different locking semantic
(we unlock ourselves, in kref_put_mutex() the callee unlocks) so that we
can use the same callbacks for both locked and unlocked kref_put()s and
so can not simply convert to using kref_put_mutex() directly.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Dave Airlie <airlied@redhat.com>
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index a029dea..3b7fda5 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1629,10 +1629,12 @@
 static inline void
 drm_gem_object_unreference_unlocked(struct drm_gem_object *obj)
 {
-	if (obj != NULL) {
+	if (obj && !atomic_add_unless(&obj->refcount.refcount, -1, 1)) {
 		struct drm_device *dev = obj->dev;
+
 		mutex_lock(&dev->struct_mutex);
-		kref_put(&obj->refcount, drm_gem_object_free);
+		if (likely(atomic_dec_and_test(&obj->refcount.refcount)))
+			drm_gem_object_free(&obj->refcount);
 		mutex_unlock(&dev->struct_mutex);
 	}
 }