[PATCH 3.10 178/319] driver core: fix race between creating/querying glue dir and its cleanup

[Willy Tarreau]

From: Ming Lei <ming.lei@xxxxxxxxxxxxx>

commit cebf8fd16900fdfd58c0028617944f808f97fe50 upstream.

The global mutex of 'gdp_mutex' is used to serialize creating/querying
glue dir and its cleanup. Turns out it isn't a perfect way because
part(kobj_kset_leave()) of the actual cleanup action() is done inside
the release handler of the glue dir kobject. That means gdp_mutex has
to be held before releasing the last reference count of the glue dir
kobject.

This patch moves glue dir's cleanup after kobject_del() in device_del()
for avoiding the race.

Cc: Yijing Wang <wangyijing@xxxxxxxxxx>
Reported-by: Chandra Sekhar Lingutla <clingutla@xxxxxxxxxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
---
 drivers/base/core.c | 39 +++++++++++++++++++++++++++++----------
 1 file changed, 29 insertions(+), 10 deletions(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index d92ecf3..986fc4e 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -827,11 +827,29 @@ static struct kobject *get_device_parent(struct device *dev,
 	return NULL;
 }
 
+static inline bool live_in_glue_dir(struct kobject *kobj,
+				    struct device *dev)
+{
+	if (!kobj || !dev->class ||
+	    kobj->kset != &dev->class->p->glue_dirs)
+		return false;
+	return true;
+}
+
+static inline struct kobject *get_glue_dir(struct device *dev)
+{
+	return dev->kobj.parent;
+}
+
+/*
+ * make sure cleaning up dir as the last step, we need to make
+ * sure .release handler of kobject is run with holding the
+ * global lock
+ */
 static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 {
 	/* see if we live in a "glue" directory */
-	if (!glue_dir || !dev->class ||
-	    glue_dir->kset != &dev->class->p->glue_dirs)
+	if (!live_in_glue_dir(glue_dir, dev))
 		return;
 
 	mutex_lock(&gdp_mutex);
@@ -839,11 +857,6 @@ static void cleanup_glue_dir(struct device *dev, struct kobject *glue_dir)
 	mutex_unlock(&gdp_mutex);
 }
 
-static void cleanup_device_parent(struct device *dev)
-{
-	cleanup_glue_dir(dev, dev->kobj.parent);
-}
-
 static int device_add_class_symlinks(struct device *dev)
 {
 	int error;
@@ -1007,6 +1020,7 @@ int device_add(struct device *dev)
 	struct kobject *kobj;
 	struct class_interface *class_intf;
 	int error = -EINVAL;
+	struct kobject *glue_dir = NULL;
 
 	dev = get_device(dev);
 	if (!dev)
@@ -1051,8 +1065,10 @@ int device_add(struct device *dev)
 	/* first, register with generic layer. */
 	/* we require the name to be set before, and pass NULL */
 	error = kobject_add(&dev->kobj, dev->kobj.parent, NULL);
-	if (error)
+	if (error) {
+		glue_dir = get_glue_dir(dev);
 		goto Error;
+	}
 
 	/* notify platform of device entry */
 	if (platform_notify)
@@ -1135,9 +1151,10 @@ done:
 	device_remove_file(dev, &uevent_attr);
  attrError:
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
+	glue_dir = get_glue_dir(dev);
 	kobject_del(&dev->kobj);
  Error:
-	cleanup_device_parent(dev);
+	cleanup_glue_dir(dev, glue_dir);
 	put_device(parent);
 name_error:
 	kfree(dev->p);
@@ -1209,6 +1226,7 @@ void put_device(struct device *dev)
 void device_del(struct device *dev)
 {
 	struct device *parent = dev->parent;
+	struct kobject *glue_dir = NULL;
 	struct class_interface *class_intf;
 
 	/* Notify clients of device removal.  This call must come
@@ -1250,8 +1268,9 @@ void device_del(struct device *dev)
 	if (platform_notify_remove)
 		platform_notify_remove(dev);
 	kobject_uevent(&dev->kobj, KOBJ_REMOVE);
-	cleanup_device_parent(dev);
+	glue_dir = get_glue_dir(dev);
 	kobject_del(&dev->kobj);
+	cleanup_glue_dir(dev, glue_dir);
 	put_device(parent);
 }
 
-- 
2.8.0.rc2.1.gbe9624a