kobject: delayed kobject release: help find buggy drivers

Implement debugging for kobject release functions. kobjects are
reference counted, so the drop of the last reference to them is not
predictable. However, the common case is for the last reference to be
the kobject's removal from a subsystem, which results in the release
function being immediately called.

This can hide subtle bugs, which can occur when another thread holds a
reference to the kobject at the same time that a kobject is removed.
This results in the release method being delayed.

In order to make these kinds of problems more visible, the following
patch implements a delayed release; this has the effect that the
release function will be out of order with respect to the removal of
the kobject in the same manner that it would be if a reference was
being held.

This provides us with an easy way to allow driver writers to debug
their drivers and fix otherwise hidden problems.

Signed-off-by: Russell King <[e-mail]>
Signed-off-by: Greg Kroah-Hartman <[e-mail]>

include/linux/kobject.h

···
 #include <linux/kernel.h>
 #include <linux/wait.h>
 #include <linux/atomic.h>
+#include <linux/workqueue.h>
 
 #define UEVENT_HELPER_PATH_LEN		256
 #define UEVENT_NUM_ENVP			32	/* number of env pointers */
···
 	struct kobj_type	*ktype;
 	struct sysfs_dirent	*sd;
 	struct kref		kref;
+#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
+	struct delayed_work	release;
+#endif
 	unsigned int state_initialized:1;
 	unsigned int state_in_sysfs:1;
 	unsigned int state_add_uevent_sent:1;

lib/Kconfig.debug

···
 	  If you say Y here, some extra kobject debugging messages will be sent
 	  to the syslog. 
 
+config DEBUG_KOBJECT_RELEASE
+	bool "kobject release debugging"
+	depends on DEBUG_KERNEL
+	help
+	  kobjects are reference counted objects.  This means that their
+	  last reference count put is not predictable, and the kobject can
+	  live on past the point at which a driver decides to drop it's
+	  initial reference to the kobject gained on allocation.  An
+	  example of this would be a struct device which has just been
+	  unregistered.
+
+	  However, some buggy drivers assume that after such an operation,
+	  the memory backing the kobject can be immediately freed.  This
+	  goes completely against the principles of a refcounted object.
+
+	  If you say Y here, the kernel will delay the release of kobjects
+	  on the last reference count to improve the visibility of this
+	  kind of kobject release bug.
+
 config HAVE_DEBUG_BUGVERBOSE
 	bool
 

lib/kobject.c

···
 	struct kobj_type *t = get_ktype(kobj);
 	const char *name = kobj->name;
 
-	pr_debug("kobject: '%s' (%p): %s\n",
-		 kobject_name(kobj), kobj, __func__);
+	pr_debug("kobject: '%s' (%p): %s, parent %p\n",
+		 kobject_name(kobj), kobj, __func__, kobj->parent);
 
 	if (t && !t->release)
 		pr_debug("kobject: '%s' (%p): does not have a release() "
···
 	}
 }
 
+#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
+static void kobject_delayed_cleanup(struct work_struct *work)
+{
+	kobject_cleanup(container_of(to_delayed_work(work),
+				     struct kobject, release));
+}
+#endif
+
 static void kobject_release(struct kref *kref)
 {
-	kobject_cleanup(container_of(kref, struct kobject, kref));
+	struct kobject *kobj = container_of(kref, struct kobject, kref);
+#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
+	pr_debug("kobject: '%s' (%p): %s, parent %p (delayed)\n",
+		 kobject_name(kobj), kobj, __func__, kobj->parent);
+	INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup);
+	schedule_delayed_work(&kobj->release, HZ);
+#else
+	kobject_cleanup(kobj);
+#endif
 }
 
 /**