drm/gem: Make the GEM LRU lock part of drm_device

Recently, a few races have been discovered in the GEM LRU logic, all
of them caused by the fact the LRU lock is accessed through
gem->lru->lock, and that very same lock also protects changes to
gem->lru, leading to situations where gem->lru needs to first be
accessed without the lock held, to then get the lru to access the lock
through and finally take the lock and do the expected operation.

Currently, the only driver making use of this API (MSM) declares a
device-wide lock, and the user we're about to add (panthor) will
do the same. There's no evidence that we will ever have a driver
that wants different pools of LRUs protected by different locks under
the same drm_device. So we're better off moving this lock to drm_device
and always locking it through obj->dev->gem_lru_mutex, or directly
through dev->gem_lru_mutex.

If anyone ever needs more fine-grained locking, this can be revisited
to pass some drm_gem_lru_pool object representing the pool of LRUs
under a specific lock, but for now, the per-device lock seems to be
enough.

Fixes: e7c2af13f811 ("drm/gem: Add LRU/shrinker helper")
Reported-by: Chia-I Wu <olvaffe@gmail.com>
Closes: https://gitlab.freedesktop.org/panfrost/linux/-/work_items/86
Reviewed-by: Rob Clark <rob.clark@oss.qualcomm.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Steven Price <steven.price@arm.com>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Link: https://patch.msgid.link/20260518-panthor-shrinker-fixes-v4-1-1920234470d5@collabora.com
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>

2 files changed, 16 insertions, 11 deletions

diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
index bc78fb77cc27..768a8dae83c5 100644
--- a/include/drm/drm_device.h
+++ b/include/drm/drm_device.h
@@ -375,6 +375,13 @@ struct drm_device {
 	 * Root directory for debugfs files.
 	 */
 	struct dentry *debugfs_root;
+
+	/**
+	 * @gem_lru_mutex:
+	 *
+	 * Lock protecting movement of GEM objects between LRUs.
+	 */
+	struct mutex gem_lru_mutex;
 };
 
 void drm_dev_set_dma_dev(struct drm_device *dev, struct device *dma_dev);
diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h
index 86f5846154f7..8a704f6a65c1 100644
--- a/include/drm/drm_gem.h
+++ b/include/drm/drm_gem.h
@@ -245,18 +245,12 @@ struct drm_gem_object_funcs {
  * for lockless &shrinker.count_objects, and provides
  * &drm_gem_lru_scan for driver's &shrinker.scan_objects
  * implementation.
+ *
+ * Any access to this kind of object must be done with
+ * drm_device::gem_lru_mutex held.
  */
 struct drm_gem_lru {
 	/**
-	 * @lock:
-	 *
-	 * Lock protecting movement of GEM objects between LRUs.  All
-	 * LRUs that the object can move between should be protected
-	 * by the same lock.
-	 */
-	struct mutex *lock;
-
-	/**
 	 * @count:
 	 *
 	 * The total number of backing pages of the GEM objects in
@@ -453,6 +447,9 @@ struct drm_gem_object {
 	 * @lru:
 	 *
 	 * The current LRU list that the GEM object is on.
+	 *
+	 * Access to this field must be done with drm_device::gem_lru_mutex
+	 * held.
 	 */
 	struct drm_gem_lru *lru;
 };
@@ -610,12 +607,13 @@ void drm_gem_unlock_reservations(struct drm_gem_object **objs, int count,
 int drm_gem_dumb_map_offset(struct drm_file *file, struct drm_device *dev,
 			    u32 handle, u64 *offset);
 
-void drm_gem_lru_init(struct drm_gem_lru *lru, struct mutex *lock);
+void drm_gem_lru_init(struct drm_gem_lru *lru);
 void drm_gem_lru_remove(struct drm_gem_object *obj);
 void drm_gem_lru_move_tail_locked(struct drm_gem_lru *lru, struct drm_gem_object *obj);
 void drm_gem_lru_move_tail(struct drm_gem_lru *lru, struct drm_gem_object *obj);
 unsigned long
-drm_gem_lru_scan(struct drm_gem_lru *lru,
+drm_gem_lru_scan(struct drm_device *dev,
+		 struct drm_gem_lru *lru,
 		 unsigned int nr_to_scan,
 		 unsigned long *remaining,
 		 bool (*shrink)(struct drm_gem_object *obj, struct ww_acquire_ctx *ticket),