drm/bridge: add list of removed refcounted bridges

Between drm_bridge_add() and drm_bridge_remove() bridges are registered to
the DRM core via the global bridge_list and visible in
/sys/kernel/debug/dri/bridges. However between drm_bridge_remove() and the
last drm_bridge_put() memory is still allocated even though the bridge is
not registered, i.e. not in bridges_list, and also not visible in
debugfs. This prevents debugging refcounted bridges lifetime, especially
leaks due to a missing drm_bridge_put().

In order to allow debugfs to also show the removed bridges, move such
bridges into a new ad-hoc list until they are eventually freed.

Note this requires adding INIT_LIST_HEAD(&bridge->list) in the bridge
initialization code. The lack of such init was not exposing any bug so far,
but it would with the new code, for example when a bridge is allocated and
then freed without calling drm_bridge_add(), which is common on probe
errors.

drm_bridge_add() needs special care for bridges being added after having
been previously added and then removed.  This happens for example for many
non-DCS DSI host bridge drivers like samsung-dsim which
drm_bridge_add/remove() themselves every time the DSI device does a DSI
attaches/detach. When the DSI device is hot-pluggable this happens multiple
times in the lifetime of the DSI host bridge.  On every attach after the
first one, drm_bridge_add() finds bridge->list in the removed list, not at
the initialized state as drm_bridge_add() currently expects. Add a
list_del_init() to remove the bridge from the lingering list and bring
bridge->list back to the initialized state.

Reviewed-by: Maxime Ripard <mripard@kernel.org>
Link: https://lore.kernel.org/r/20250915-drm-bridge-debugfs-removed-v9-1-6e5c0aff5de9@bootlin.com
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>

diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
index 5f265e8b4d49a38233c14d8e13c915318e9ac3ee..034dbe7203bfc21ebf157ae1d9d4167086220a5c 100644 (file)
--- a/drivers/gpu/drm/drm_bridge.c
+++ b/drivers/gpu/drm/drm_bridge.c
@@ -197,15 +197,22 @@
  * driver.
  */
 
+/* Protect bridge_list and bridge_lingering_list */
 static DEFINE_MUTEX(bridge_lock);
 static LIST_HEAD(bridge_list);
+static LIST_HEAD(bridge_lingering_list);
 
 static void __drm_bridge_free(struct kref *kref)
 {
        struct drm_bridge *bridge = container_of(kref, struct drm_bridge, refcount);
 
+       mutex_lock(&bridge_lock);
+       list_del(&bridge->list);
+       mutex_unlock(&bridge_lock);
+
        if (bridge->funcs->destroy)
                bridge->funcs->destroy(bridge);
+
        kfree(bridge->container);
 }
 
@@ -273,6 +280,7 @@ void *__devm_drm_bridge_alloc(struct device *dev, size_t size, size_t offset,
                return ERR_PTR(-ENOMEM);
 
        bridge = container + offset;
+       INIT_LIST_HEAD(&bridge->list);
        bridge->container = container;
        bridge->funcs = funcs;
        kref_init(&bridge->refcount);
@@ -300,6 +308,14 @@ void drm_bridge_add(struct drm_bridge *bridge)
 
        drm_bridge_get(bridge);
 
+       /*
+        * If the bridge was previously added and then removed, it is now
+        * in bridge_lingering_list. Remove it or bridge_lingering_list will be
+        * corrupted when adding this bridge to bridge_list below.
+        */
+       if (!list_empty(&bridge->list))
+               list_del_init(&bridge->list);
+
        mutex_init(&bridge->hpd_mutex);
 
        if (bridge->ops & DRM_BRIDGE_OP_HDMI)
@@ -343,7 +359,7 @@ EXPORT_SYMBOL(devm_drm_bridge_add);
 void drm_bridge_remove(struct drm_bridge *bridge)
 {
        mutex_lock(&bridge_lock);
-       list_del_init(&bridge->list);
+       list_move_tail(&bridge->list, &bridge_lingering_list);
        mutex_unlock(&bridge_lock);
 
        mutex_destroy(&bridge->hpd_mutex);