[patch 2/5] infrastructure to debug (dynamic) objects

[Thomas Gleixner]

We can see an ever repeating problem pattern with objects of any kind in
the kernel:

1) freeing of active objects
2) reinitialization of active objects

Both problems can be hard to debug because the crash happens at a
point where we have no chance to decode the root cause anymore. One
problem spot are kernel timers, where the detection of the problem
often happens in interrupt context and usually causes the machine to
panic.

While working on a timer related bug report I had to hack specialized
code into the timer subsystem to get a reasonable hint for the root
cause. This debug hack was fine for temporary use, but far from a
mergeable solution due to the intrusiveness into the timer code.

The code further lacked the ability to detect and report the root cause
instantly and keep the system operational. 

Keeping the system operational is important to get hold of the debug
information without special debugging aids like serial consoles and
special knowledge of the bug reporter.

The problems described above are not restricted to timers, but timers
tend to expose it usually in a full system crash. Other objects are
less explosive, but the symptoms caused by such mistakes can be even
harder to debug.

Instead of creating specialized debugging code for the timer subsystem
a generic infrastructure is created which allows developers to verify
their code and provides an easy to enable debug facility for users in
case of trouble.

The debugobjects core code keeps track of operations on static and
dynamic objects by inserting them into a hashed list and sanity
checking them on object operations and provides additional checks
whenever kernel memory is freed.

The tracked object operations are:
- initializing an object
- adding an object to a subsystem list
- deleting an object from a subsystem list

Each operation is sanity checked before the operation is executed and
the subsystem specific code can provide a fixup function which allows
to prevent the damage of the operation. When the sanity check triggers
a warning message and a stack trace is printed.

The list of operations can be extended if the need arises. For now it's
limited to the requirements of the first user (timers).

The core code enqueues the objects into hash buckets. The hash index
is generated from the address of the object to simplify the lookup for
the check on kfree/vfree. Each bucket has it's own spinlock to avoid
contention on a global lock.

The debug code can be compiled in without being active. The runtime
overhead is minimal and could be optimized by asm alternatives. A
kernel command line option enables the debugging code.

Thanks to Ingo Molnar for review, suggestions and cleanup patches.

Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
---
 Documentation/kernel-parameters.txt |    2 
 include/linux/debugobjects.h        |   90 +++
 init/main.c                         |    3 
 lib/Kconfig.debug                   |   23 
 lib/Makefile                        |    1 
 lib/debugobjects.c                  |  890 ++++++++++++++++++++++++++++++++++++
 mm/page_alloc.c                     |   10 
 mm/slab.c                           |   10 
 mm/slub.c                           |    3 
 mm/vmalloc.c                        |    2 
 10 files changed, 1030 insertions(+), 4 deletions(-)

Index: linux-2.6/Documentation/kernel-parameters.txt
===================================================================
--- linux-2.6.orig/Documentation/kernel-parameters.txt
+++ linux-2.6/Documentation/kernel-parameters.txt
@@ -551,6 +551,8 @@ and is between 256 and 4096 characters. 
 			1 will print _a lot_ more information - normally
 			only useful to kernel developers.
 
+	debug_objects	[KNL] Enable object debugging
+
 	decnet.addr=	[HW,NET]
 			Format: <area>[,<node>]
 			See also Documentation/networking/decnet.txt.
Index: linux-2.6/include/linux/debugobjects.h
===================================================================
--- /dev/null
+++ linux-2.6/include/linux/debugobjects.h
@@ -0,0 +1,90 @@
+#ifndef _LINUX_DEBUGOBJECTS_H
+#define _LINUX_DEBUGOBJECTS_H
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+enum debug_obj_state {
+	ODEBUG_STATE_NONE,
+	ODEBUG_STATE_INIT,
+	ODEBUG_STATE_INACTIVE,
+	ODEBUG_STATE_ACTIVE,
+	ODEBUG_STATE_DESTROYED,
+	ODEBUG_STATE_NOTAVAILABLE,
+	ODEBUG_STATE_MAX,
+};
+
+struct debug_obj_descr;
+
+/**
+ * struct debug_obj - representaion of an tracked object
+ * @node:	hlist node to link the object into the tracker list
+ * @state:	tracked object state
+ * @object:	pointer to the real object
+ * @descr:	pointer to an object type specific debug description structure
+ */
+struct debug_obj {
+	struct hlist_node	node;
+	enum debug_obj_state	state;
+	void			*object;
+	struct debug_obj_descr	*descr;
+};
+
+/**
+ * struct debug_obj_descr - object type specific debug description structure
+ * @name:		name of the object typee
+ * @fixup_init:		fixup function, which is called when the init check
+ *			fails
+ * @fixup_activate:	fixup function, which is called when the activate check
+ *			fails
+ * @fixup_destroy:	fixup function, which is called when the destroy check
+ *			fails
+ * @fixup_free:		fixup function, which is called when the free check
+ *			fails
+ */
+struct debug_obj_descr {
+	const char		*name;
+
+	int (*fixup_init)	(void *addr, enum debug_obj_state state);
+	int (*fixup_activate)	(void *addr, enum debug_obj_state state);
+	int (*fixup_destroy)	(void *addr, enum debug_obj_state state);
+	int (*fixup_free)	(void *addr, enum debug_obj_state state);
+};
+
+#ifdef CONFIG_DEBUG_OBJECTS
+extern void debug_object_init      (void *addr, struct debug_obj_descr *descr);
+extern void
+debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr);
+extern void debug_object_activate  (void *addr, struct debug_obj_descr *descr);
+extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr);
+extern void debug_object_destroy   (void *addr, struct debug_obj_descr *descr);
+extern void debug_object_free      (void *addr, struct debug_obj_descr *descr);
+
+extern void debug_objects_early_init(void);
+extern void debug_objects_mem_init(void);
+#else
+static inline void
+debug_object_init      (void *addr, struct debug_obj_descr *descr) { }
+static inline void
+debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr) { }
+static inline void
+debug_object_activate  (void *addr, struct debug_obj_descr *descr) { }
+static inline void
+debug_object_deactivate(void *addr, struct debug_obj_descr *descr) { }
+static inline void
+debug_object_destroy   (void *addr, struct debug_obj_descr *descr) { }
+static inline void
+debug_object_free      (void *addr, struct debug_obj_descr *descr) { }
+
+static inline void debug_objects_early_init(void) { }
+static inline void debug_objects_mem_init(void) { }
+#endif
+
+#ifdef CONFIG_DEBUG_OBJECTS_FREE
+extern void debug_check_no_obj_freed(const void *address, unsigned long size);
+#else
+static inline void
+debug_check_no_obj_freed(const void *address, unsigned long size) { }
+#endif
+
+#endif
Index: linux-2.6/init/main.c
===================================================================
--- linux-2.6.orig/init/main.c
+++ linux-2.6/init/main.c
@@ -52,6 +52,7 @@
 #include <linux/unwind.h>
 #include <linux/buffer_head.h>
 #include <linux/debug_locks.h>
+#include <linux/debugobjects.h>
 #include <linux/lockdep.h>
 #include <linux/pid_namespace.h>
 #include <linux/device.h>
@@ -517,6 +518,7 @@ asmlinkage void __init start_kernel(void
 	 */
 	unwind_init();
 	lockdep_init();
+	debug_objects_early_init();
 	cgroup_init_early();
 
 	local_irq_disable();
@@ -610,6 +612,7 @@ asmlinkage void __init start_kernel(void
 	enable_debug_pagealloc();
 	cpu_hotplug_init();
 	kmem_cache_init();
+	debug_objects_mem_init();
 	setup_per_cpu_pageset();
 	numa_policy_init();
 	if (late_time_init)
Index: linux-2.6/lib/Kconfig.debug
===================================================================
--- linux-2.6.orig/lib/Kconfig.debug
+++ linux-2.6/lib/Kconfig.debug
@@ -183,6 +183,29 @@ config TIMER_STATS
 	  (it defaults to deactivated on bootup and will only be activated
 	  if some application like powertop activates it explicitly).
 
+config DEBUG_OBJECTS
+	bool "Debug object operations"
+	depends on DEBUG_KERNEL
+	help
+	  If you say Y here, additional code will be inserted into the
+	  kernel to track the life time of various objects and validate
+	  the operations on those objects.
+
+config DEBUG_OBJECTS_SELFTEST
+	bool "Debug objects selftest"
+	depends on DEBUG_OBJECTS
+	help
+	  This enables the selftest of the object debug code.
+
+config DEBUG_OBJECTS_FREE
+	bool "Debug objects in freed memory"
+	depends on DEBUG_OBJECTS
+	help
+	  This enables checks whether a k/v free operation frees an area
+	  which contains an object which has not been deactivated
+	  properly. This can make kmalloc/kfree-intensive workloads
+	  much slower.
+
 config DEBUG_SLAB
 	bool "Debug slab memory allocations"
 	depends on DEBUG_KERNEL && SLAB
Index: linux-2.6/lib/Makefile
===================================================================
--- linux-2.6.orig/lib/Makefile
+++ linux-2.6/lib/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_LOCK_KERNEL) += kernel_lock
 obj-$(CONFIG_PLIST) += plist.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
 obj-$(CONFIG_DEBUG_LIST) += list_debug.o
+obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
 
 ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
   lib-y += dec_and_lock.o
Index: linux-2.6/lib/debugobjects.c
===================================================================
--- /dev/null
+++ linux-2.6/lib/debugobjects.c
@@ -0,0 +1,890 @@
+/*
+ * Generic infrastructure for lifetime debugging of objects.
+ *
+ * Started by Thomas Gleixner
+ *
+ * Copyright (C) 2008, Thomas Gleixner <tglx@xxxxxxxxxxxxx>
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#include <linux/debugobjects.h>
+#include <linux/interrupt.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/hash.h>
+
+#define ODEBUG_HASH_BITS	14
+#define ODEBUG_HASH_SIZE	(1 << ODEBUG_HASH_BITS)
+
+#define ODEBUG_POOL_SIZE	512
+#define ODEBUG_POOL_MIN_LEVEL	256
+
+#define ODEBUG_CHUNK_SHIFT	PAGE_SHIFT
+#define ODEBUG_CHUNK_SIZE	(1 << ODEBUG_CHUNK_SHIFT)
+#define ODEBUG_CHUNK_MASK	(~(ODEBUG_CHUNK_SIZE - 1))
+
+struct debug_bucket {
+	struct hlist_head	list;
+	spinlock_t		lock;
+};
+
+static struct debug_bucket	obj_hash[ODEBUG_HASH_SIZE];
+
+static struct debug_obj		obj_static_pool[ODEBUG_POOL_SIZE];
+
+static DEFINE_SPINLOCK(pool_lock);
+
+static HLIST_HEAD(obj_pool);
+
+static int			obj_pool_min_free = ODEBUG_POOL_SIZE;
+static int			obj_pool_free = ODEBUG_POOL_SIZE;
+static int			obj_pool_used;
+static int			obj_pool_max_used;
+static struct kmem_cache	*obj_cache;
+
+static int			debug_objects_maxchain __read_mostly;
+static int			debug_objects_fixups __read_mostly;
+static int			debug_objects_warnings __read_mostly;
+static int			debug_objects_enabled __read_mostly;
+static struct debug_obj_descr	*descr_test  __read_mostly;
+
+static int __init enable_object_debug(char *str)
+{
+	debug_objects_enabled = 1;
+	return 0;
+}
+early_param("debug_objects", enable_object_debug);
+
+static const char *obj_states[ODEBUG_STATE_MAX] = {
+	[ODEBUG_STATE_NONE]		= "none",
+	[ODEBUG_STATE_INIT]		= "initialized",
+	[ODEBUG_STATE_INACTIVE]		= "inactive",
+	[ODEBUG_STATE_ACTIVE]		= "active",
+	[ODEBUG_STATE_DESTROYED]	= "destroyed",
+	[ODEBUG_STATE_NOTAVAILABLE]	= "not available",
+};
+
+static int fill_pool(void)
+{
+	gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
+	struct debug_obj *new;
+
+	if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL))
+		return obj_pool_free;
+
+	if (unlikely(!obj_cache))
+		return obj_pool_free;
+
+	while (obj_pool_free < ODEBUG_POOL_MIN_LEVEL) {
+
+		new = kmem_cache_zalloc(obj_cache, gfp);
+		if (!new)
+			return obj_pool_free;
+
+		spin_lock(&pool_lock);
+		hlist_add_head(&new->node, &obj_pool);
+		obj_pool_free++;
+		spin_unlock(&pool_lock);
+	}
+	return obj_pool_free;
+}
+
+/*
+ * Lookup an object in the hash bucket.
+ */
+static struct debug_obj *lookup_object(void *addr, struct debug_bucket *b)
+{
+	struct hlist_node *node;
+	struct debug_obj *obj;
+	int cnt = 0;
+
+	hlist_for_each_entry(obj, node, &b->list, node) {
+		cnt++;
+		if (obj->object == addr)
+			return obj;
+	}
+	if (cnt > debug_objects_maxchain)
+		debug_objects_maxchain = cnt;
+
+	return NULL;
+}
+
+/*
+ * Allocate a new object. If the pool is empty and no refill possible,
+ * switch off the debugger.
+ */
+static struct debug_obj *
+alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
+{
+	struct debug_obj *obj = NULL;
+	int retry = 0;
+
+repeat:
+	spin_lock(&pool_lock);
+	if (obj_pool.first) {
+		obj	    = hlist_entry(obj_pool.first, typeof(*obj), node);
+
+		obj->object = addr;
+		obj->descr  = descr;
+		obj->state  = ODEBUG_STATE_NONE;
+		hlist_del(&obj->node);
+
+		hlist_add_head(&obj->node, &b->list);
+
+		obj_pool_used++;
+		if (obj_pool_used > obj_pool_max_used)
+			obj_pool_max_used = obj_pool_used;
+
+		obj_pool_free--;
+		if (obj_pool_free < obj_pool_min_free)
+			obj_pool_min_free = obj_pool_free;
+	}
+	spin_unlock(&pool_lock);
+
+	if (fill_pool() && !obj && !retry++)
+		goto repeat;
+
+	return obj;
+}
+
+/*
+ * Put the object back into the pool or give it back to kmem_cache:
+ */
+static void free_object(struct debug_obj *obj)
+{
+	unsigned long idx = (unsigned long)(obj - obj_static_pool);
+
+	if (obj_pool_free < ODEBUG_POOL_SIZE || idx < ODEBUG_POOL_SIZE) {
+		spin_lock(&pool_lock);
+		hlist_add_head(&obj->node, &obj_pool);
+		obj_pool_free++;
+		obj_pool_used--;
+		spin_unlock(&pool_lock);
+	} else {
+		spin_lock(&pool_lock);
+		obj_pool_used--;
+		spin_unlock(&pool_lock);
+		kmem_cache_free(obj_cache, obj);
+	}
+}
+
+/*
+ * We run out of memory. That means we probably have tons of objects
+ * allocated.
+ */
+static void debug_objects_oom(void)
+{
+	struct debug_bucket *db = obj_hash;
+	struct hlist_node *node, *tmp;
+	struct debug_obj *obj;
+	unsigned long flags;
+	int i;
+
+	printk(KERN_WARNING "ODEBUG: Out of memory. ODEBUG disabled\n");
+
+	for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) {
+		spin_lock_irqsave(&db->lock, flags);
+		hlist_for_each_entry_safe(obj, node, tmp, &db->list, node) {
+			hlist_del(&obj->node);
+			free_object(obj);
+		}
+		spin_unlock_irqrestore(&db->lock, flags);
+	}
+}
+
+/*
+ * We use the pfn of the address for the hash. That way we can check
+ * for freed objects simply by checking the affected bucket.
+ */
+static struct debug_bucket *get_bucket(unsigned long addr)
+{
+	unsigned long hash;
+
+	hash = hash_long((addr >> ODEBUG_CHUNK_SHIFT), ODEBUG_HASH_BITS);
+	return &obj_hash[hash];
+}
+
+static void debug_print_object(struct debug_obj *obj, char *msg)
+{
+	static int limit;
+
+	if (limit < 5 && obj->descr != descr_test) {
+		limit++;
+		printk(KERN_ERR "ODEBUG: %s %s object type: %s\n", msg,
+		       obj_states[obj->state], obj->descr->name);
+		WARN_ON(1);
+	}
+	debug_objects_warnings++;
+}
+
+/*
+ * Try to repair the damage, so we have a better chance to get useful
+ * debug output.
+ */
+static void
+debug_object_fixup(int (*fixup)(void *addr, enum debug_obj_state state),
+		   void * addr, enum debug_obj_state state)
+{
+	if (fixup)
+		debug_objects_fixups += fixup(addr, state);
+}
+
+static void debug_object_is_on_stack(void *addr, int onstack)
+{
+	void *stack = current->stack;
+	int is_on_stack;
+	static int limit;
+
+	if (limit > 4)
+		return;
+
+	is_on_stack = (addr >= stack && addr < (stack + THREAD_SIZE));
+
+	if (is_on_stack == onstack)
+		return;
+
+	limit++;
+	if (is_on_stack)
+		printk(KERN_WARNING
+		       "ODEBUG: object is on stack, but not annotated\n");
+	else
+		printk(KERN_WARNING
+		       "ODEBUG: object is not on stack, but annotated\n");
+	WARN_ON(1);
+}
+
+static void
+__debug_object_init(void *addr, struct debug_obj_descr *descr, int onstack)
+{
+	enum debug_obj_state state;
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	db = get_bucket((unsigned long) addr);
+
+	spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (!obj) {
+		obj = alloc_object(addr, db, descr);
+		if (!obj) {
+			debug_objects_enabled = 0;
+			spin_unlock_irqrestore(&db->lock, flags);
+			debug_objects_oom();
+			return;
+		}
+		debug_object_is_on_stack(addr, onstack);
+	}
+
+	switch (obj->state) {
+	case ODEBUG_STATE_NONE:
+	case ODEBUG_STATE_INIT:
+	case ODEBUG_STATE_INACTIVE:
+		obj->state = ODEBUG_STATE_INIT;
+		break;
+
+	case ODEBUG_STATE_ACTIVE:
+		debug_print_object(obj, "init");
+		state = obj->state;
+		spin_unlock_irqrestore(&db->lock, flags);
+		debug_object_fixup(descr->fixup_init, addr, state);
+		return;
+
+	case ODEBUG_STATE_DESTROYED:
+		debug_print_object(obj, "init");
+		break;
+	default:
+		break;
+	}
+
+	spin_unlock_irqrestore(&db->lock, flags);
+}
+
+/**
+ * debug_object_init - debug checks when an object is initialized
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ */
+void debug_object_init(void *addr, struct debug_obj_descr *descr)
+{
+	if (!debug_objects_enabled)
+		return;
+
+	__debug_object_init(addr, descr, 0);
+}
+
+/**
+ * debug_object_init_on_stack - debug checks when an object on stack is
+ *				initialized
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ */
+void debug_object_init_on_stack(void *addr, struct debug_obj_descr *descr)
+{
+	if (!debug_objects_enabled)
+		return;
+
+	__debug_object_init(addr, descr, 1);
+}
+
+/**
+ * debug_object_activate - debug checks when an object is activated
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ */
+void debug_object_activate(void *addr, struct debug_obj_descr *descr)
+{
+	enum debug_obj_state state;
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	if (!debug_objects_enabled)
+		return;
+
+	db = get_bucket((unsigned long) addr);
+
+	spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (obj) {
+		switch (obj->state) {
+		case ODEBUG_STATE_INIT:
+		case ODEBUG_STATE_INACTIVE:
+			obj->state = ODEBUG_STATE_ACTIVE;
+			break;
+
+		case ODEBUG_STATE_ACTIVE:
+			debug_print_object(obj, "activate");
+			state = obj->state;
+			spin_unlock_irqrestore(&db->lock, flags);
+			debug_object_fixup(descr->fixup_activate, addr, state);
+			return;
+
+		case ODEBUG_STATE_DESTROYED:
+			debug_print_object(obj, "activate");
+			break;
+		default:
+			break;
+		}
+		spin_unlock_irqrestore(&db->lock, flags);
+		return;
+	}
+
+	spin_unlock_irqrestore(&db->lock, flags);
+	/*
+	 * This happens when a static object is activated. We
+	 * let the type specific code decide whether this is
+	 * true or not.
+	 */
+	debug_object_fixup(descr->fixup_activate, addr,
+			   ODEBUG_STATE_NOTAVAILABLE);
+}
+
+/**
+ * debug_object_deactivate - debug checks when an object is deactivated
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ */
+void debug_object_deactivate(void *addr, struct debug_obj_descr *descr)
+{
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	if (!debug_objects_enabled)
+		return;
+
+	db = get_bucket((unsigned long) addr);
+
+	spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (obj) {
+		switch (obj->state) {
+		case ODEBUG_STATE_INIT:
+		case ODEBUG_STATE_INACTIVE:
+		case ODEBUG_STATE_ACTIVE:
+			obj->state = ODEBUG_STATE_INACTIVE;
+			break;
+
+		case ODEBUG_STATE_DESTROYED:
+			debug_print_object(obj, "deactivate");
+			break;
+		default:
+			break;
+		}
+	} else {
+		struct debug_obj o = { .object = addr,
+				       .state = ODEBUG_STATE_NOTAVAILABLE,
+				       .descr = descr };
+
+		debug_print_object(&o, "deactivate");
+	}
+
+	spin_unlock_irqrestore(&db->lock, flags);
+}
+
+/**
+ * debug_object_destroy - debug checks when an object is destroyed
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ */
+void debug_object_destroy(void *addr, struct debug_obj_descr *descr)
+{
+	enum debug_obj_state state;
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	if (!debug_objects_enabled)
+		return;
+
+	db = get_bucket((unsigned long) addr);
+
+	spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (!obj)
+		goto out_unlock;
+
+	switch (obj->state) {
+	case ODEBUG_STATE_NONE:
+	case ODEBUG_STATE_INIT:
+	case ODEBUG_STATE_INACTIVE:
+		obj->state = ODEBUG_STATE_DESTROYED;
+		break;
+	case ODEBUG_STATE_ACTIVE:
+		debug_print_object(obj, "destroy");
+		state = obj->state;
+		spin_unlock_irqrestore(&db->lock, flags);
+		debug_object_fixup(descr->fixup_destroy, addr, state);
+		return;
+
+	case ODEBUG_STATE_DESTROYED:
+		debug_print_object(obj, "destroy");
+		break;
+	default:
+		break;
+	}
+out_unlock:
+	spin_unlock_irqrestore(&db->lock, flags);
+}
+
+/**
+ * debug_object_free - debug checks when an object is freed
+ * @addr:	address of the object
+ * @descr:	pointer to an object specific debug description structure
+ */
+void debug_object_free(void *addr, struct debug_obj_descr *descr)
+{
+	enum debug_obj_state state;
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+
+	if (!debug_objects_enabled)
+		return;
+
+	db = get_bucket((unsigned long) addr);
+
+	spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (!obj)
+		goto out_unlock;
+
+	switch (obj->state) {
+	case ODEBUG_STATE_ACTIVE:
+		debug_print_object(obj, "free");
+		state = obj->state;
+		spin_unlock_irqrestore(&db->lock, flags);
+		debug_object_fixup(descr->fixup_free, addr, state);
+		return;
+	default:
+		hlist_del(&obj->node);
+		free_object(obj);
+		break;
+	}
+out_unlock:
+	spin_unlock_irqrestore(&db->lock, flags);
+}
+
+#ifdef CONFIG_DEBUG_OBJECTS_FREE
+static void __debug_check_no_obj_freed(const void *address, unsigned long size)
+{
+	unsigned long flags, oaddr, saddr, eaddr, paddr, chunks;
+	struct hlist_node *node, *tmp;
+	struct debug_obj_descr *descr;
+	enum debug_obj_state state;
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	int cnt;
+
+	saddr = (unsigned long) address;
+	eaddr = saddr + size;
+	paddr = saddr & ODEBUG_CHUNK_MASK;
+	chunks = ((eaddr - paddr) + (ODEBUG_CHUNK_SIZE - 1));
+	chunks >>= ODEBUG_CHUNK_SHIFT;
+
+	for (;chunks > 0; chunks--, paddr += ODEBUG_CHUNK_SIZE) {
+		db = get_bucket(paddr);
+
+repeat:
+		cnt = 0;
+		spin_lock_irqsave(&db->lock, flags);
+		hlist_for_each_entry_safe(obj, node, tmp, &db->list, node) {
+			cnt++;
+			oaddr = (unsigned long) obj->object;
+			if (oaddr < saddr || oaddr >= eaddr)
+				continue;
+
+			switch (obj->state) {
+			case ODEBUG_STATE_ACTIVE:
+				debug_print_object(obj, "free");
+				descr = obj->descr;
+				state = obj->state;
+				spin_unlock_irqrestore(&db->lock, flags);
+				debug_object_fixup(descr->fixup_free,
+						   (void *) oaddr, state);
+				goto repeat;
+			default:
+				hlist_del(&obj->node);
+				free_object(obj);
+				break;
+			}
+		}
+		spin_unlock_irqrestore(&db->lock, flags);
+		if (cnt > debug_objects_maxchain)
+			debug_objects_maxchain = cnt;
+	}
+}
+
+void debug_check_no_obj_freed(const void *address, unsigned long size)
+{
+	if (debug_objects_enabled)
+		__debug_check_no_obj_freed(address, size);
+}
+#endif
+
+#ifdef CONFIG_DEBUG_FS
+
+static int debug_stats_show(struct seq_file *m, void *v)
+{
+	seq_printf(m, "max_chain     :%d\n", debug_objects_maxchain);
+	seq_printf(m, "warnings      :%d\n", debug_objects_warnings);
+	seq_printf(m, "fixups        :%d\n", debug_objects_fixups);
+	seq_printf(m, "pool_free     :%d\n", obj_pool_free);
+	seq_printf(m, "pool_min_free :%d\n", obj_pool_min_free);
+	seq_printf(m, "pool_used     :%d\n", obj_pool_used);
+	seq_printf(m, "pool_max_used :%d\n", obj_pool_max_used);
+	return 0;
+}
+
+static int debug_stats_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, debug_stats_show, NULL);
+}
+
+static const struct file_operations debug_stats_fops = {
+	.open		= debug_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init debug_objects_init_debugfs(void)
+{
+	struct dentry *dbgdir, *dbgstats;
+
+	if (!debug_objects_enabled)
+		return 0;
+
+	dbgdir = debugfs_create_dir("debug_objects", NULL);
+	if (!dbgdir)
+		return -ENOMEM;
+
+	dbgstats = debugfs_create_file("stats", 0444, dbgdir, NULL,
+				       &debug_stats_fops);
+	if (!dbgstats)
+		goto err;
+
+	return 0;
+
+err:
+	debugfs_remove(dbgdir);
+
+	return -ENOMEM;
+}
+__initcall(debug_objects_init_debugfs);
+
+#else
+static inline void debug_objects_init_debugfs(void) { }
+#endif
+
+#ifdef CONFIG_DEBUG_OBJECTS_SELFTEST
+
+/* Random data structure for the self test */
+struct self_test {
+	unsigned long	dummy1[6];
+	int		static_init;
+	unsigned long	dummy2[3];
+};
+
+static __initdata struct debug_obj_descr descr_type_test;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int __init fixup_init(void *addr, enum debug_obj_state state)
+{
+	struct self_test *obj = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		debug_object_deactivate(obj, &descr_type_test);
+		debug_object_init(obj, &descr_type_test);
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int __init fixup_activate(void *addr, enum debug_obj_state state)
+{
+	struct self_test *obj = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_NOTAVAILABLE:
+		if (obj->static_init == 1) {
+			debug_object_init(obj, &descr_type_test);
+			debug_object_activate(obj, &descr_type_test);
+			/*
+			 * Real code should return 0 here ! This is
+			 * not a fixup of some bad behaviour. We
+			 * merily call the debug_init function to keep
+			 * track of the object.
+			 */
+			return 1;
+		} else {
+			/* Real code needs to emit a warning here */
+		}
+		return 0;
+
+	case ODEBUG_STATE_ACTIVE:
+		debug_object_deactivate(obj, &descr_type_test);
+		debug_object_activate(obj, &descr_type_test);
+		return 1;
+
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_destroy is called when:
+ * - an active object is destroyed
+ */
+static int __init fixup_destroy(void *addr, enum debug_obj_state state)
+{
+	struct self_test *obj = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		debug_object_deactivate(obj, &descr_type_test);
+		debug_object_destroy(obj, &descr_type_test);
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int __init fixup_free(void *addr, enum debug_obj_state state)
+{
+	struct self_test *obj = addr;
+
+	switch (state) {
+	case ODEBUG_STATE_ACTIVE:
+		debug_object_deactivate(obj, &descr_type_test);
+		debug_object_free(obj, &descr_type_test);
+		return 1;
+	default:
+		return 0;
+	}
+}
+
+static int
+check_results(void *addr, enum debug_obj_state state, int fixups, int warnings)
+{
+	struct debug_bucket *db;
+	struct debug_obj *obj;
+	unsigned long flags;
+	int res = -EINVAL;
+
+	db = get_bucket((unsigned long) addr);
+
+	spin_lock_irqsave(&db->lock, flags);
+
+	obj = lookup_object(addr, db);
+	if (!obj && state != ODEBUG_STATE_NONE) {
+		printk(KERN_ERR "ODEBUG: selftest object not found\n");
+		WARN_ON(1);
+		goto out;
+	}
+	if (obj && obj->state != state) {
+		printk(KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n",
+		       obj->state, state);
+		WARN_ON(1);
+		goto out;
+	}
+	if (fixups != debug_objects_fixups) {
+		printk(KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n",
+		       fixups, debug_objects_fixups);
+		WARN_ON(1);
+		goto out;
+	}
+	if (warnings != debug_objects_warnings) {
+		printk(KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n",
+		       warnings, debug_objects_warnings);
+		WARN_ON(1);
+		goto out;
+	}
+	res = 0;
+out:
+	spin_unlock_irqrestore(&db->lock, flags);
+	if (res)
+		debug_objects_enabled = 0;
+	return res;
+}
+
+static __initdata struct debug_obj_descr descr_type_test = {
+	.name			= "selftest",
+	.fixup_init		= fixup_init,
+	.fixup_activate		= fixup_activate,
+	.fixup_destroy		= fixup_destroy,
+	.fixup_free		= fixup_free,
+};
+
+static __initdata struct self_test obj = { .static_init = 0 };
+
+static void __init debug_objects_selftest(void)
+{
+	int fixups, oldfixups, warnings, oldwarnings;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	fixups = oldfixups = debug_objects_fixups;
+	warnings = oldwarnings = debug_objects_warnings;
+	descr_test = &descr_type_test;
+
+	debug_object_init(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_INIT, fixups, warnings))
+		goto out;
+	debug_object_activate(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_ACTIVE, fixups, warnings))
+		goto out;
+	debug_object_activate(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_ACTIVE, ++fixups, ++warnings))
+		goto out;
+	debug_object_deactivate(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_INACTIVE, fixups, warnings))
+		goto out;
+	debug_object_destroy(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, warnings))
+		goto out;
+	debug_object_init(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, ++warnings))
+		goto out;
+	debug_object_activate(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, ++warnings))
+		goto out;
+	debug_object_deactivate(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_DESTROYED, fixups, ++warnings))
+		goto out;
+	debug_object_free(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_NONE, fixups, warnings))
+		goto out;
+
+	obj.static_init = 1;
+	debug_object_activate(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_ACTIVE, ++fixups, warnings))
+		goto out;
+	debug_object_init(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_INIT, ++fixups, ++warnings))
+		goto out;
+	debug_object_free(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_NONE, fixups, warnings))
+		goto out;
+
+#ifdef CONFIG_DEBUG_OBJECTS_FREE
+	debug_object_init(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_INIT, fixups, warnings))
+		goto out;
+	debug_object_activate(&obj, &descr_type_test);
+	if (check_results(&obj, ODEBUG_STATE_ACTIVE, fixups, warnings))
+		goto out;
+	__debug_check_no_obj_freed(&obj, sizeof(obj));
+	if (check_results(&obj, ODEBUG_STATE_NONE, ++fixups, ++warnings))
+		goto out;
+#endif
+	printk(KERN_INFO "ODEBUG: selftest passed\n");
+
+out:
+	debug_objects_fixups = oldfixups;
+	debug_objects_warnings = oldwarnings;
+	descr_test = NULL;
+
+	local_irq_restore(flags);
+}
+#else
+static inline void debug_objects_selftest(void) { }
+#endif
+
+/*
+ * Called during early boot to initialize the hash buckets and link
+ * the static object pool objects into the poll list. After this call
+ * the object tracker is fully operational.
+ */
+void __init debug_objects_early_init(void)
+{
+	int i;
+
+	for (i = 0; i < ODEBUG_HASH_SIZE; i++)
+		spin_lock_init(&obj_hash[i].lock);
+
+	for (i = 0; i < ODEBUG_POOL_SIZE; i++)
+		hlist_add_head(&obj_static_pool[i].node, &obj_pool);
+}
+
+/*
+ * Called after the kmem_caches are functional to setup a dedicated
+ * cache pool, which has the SLAB_DEBUG_OBJECTS flag set. This flag
+ * prevents that the debug code is called on kmem_cache_free() for the
+ * debug tracker objects to avoid recursive calls.
+ */
+void __init debug_objects_mem_init(void)
+{
+	if (!debug_objects_enabled)
+		return;
+
+	obj_cache = kmem_cache_create("debug_objects_cache",
+				      sizeof (struct debug_obj), 0,
+				      SLAB_DEBUG_OBJECTS, NULL);
+
+	if (!obj_cache)
+		debug_objects_enabled = 0;
+	else
+		debug_objects_selftest();
+}
Index: linux-2.6/mm/page_alloc.c
===================================================================
--- linux-2.6.orig/mm/page_alloc.c
+++ linux-2.6/mm/page_alloc.c
@@ -45,6 +45,7 @@
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
 #include <linux/memcontrol.h>
+#include <linux/debugobjects.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -532,8 +533,11 @@ static void __free_pages_ok(struct page 
 	if (reserved)
 		return;
 
-	if (!PageHighMem(page))
+	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order);
+		debug_check_no_obj_freed(page_address(page),
+					   PAGE_SIZE << order);
+	}
 	arch_free_page(page, order);
 	kernel_map_pages(page, 1 << order, 0);
 
@@ -995,8 +999,10 @@ static void free_hot_cold_page(struct pa
 	if (free_pages_check(page))
 		return;
 
-	if (!PageHighMem(page))
+	if (!PageHighMem(page)) {
 		debug_check_no_locks_freed(page_address(page), PAGE_SIZE);
+		debug_check_no_obj_freed(page_address(page), PAGE_SIZE);
+	}
 	arch_free_page(page, 0);
 	kernel_map_pages(page, 1, 0);
 
Index: linux-2.6/mm/slab.c
===================================================================
--- linux-2.6.orig/mm/slab.c
+++ linux-2.6/mm/slab.c
@@ -110,6 +110,7 @@
 #include	<linux/fault-inject.h>
 #include	<linux/rtmutex.h>
 #include	<linux/reciprocal_div.h>
+#include	<linux/debugobjects.h>
 
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
@@ -178,12 +179,14 @@
 			 SLAB_CACHE_DMA | \
 			 SLAB_STORE_USER | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
-			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
+			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
+			 SLAB_DEBUG_OBJECTS)
 #else
 # define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
 			 SLAB_CACHE_DMA | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
-			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
+			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD | \
+			 SLAB_DEBUG_OBJECTS)
 #endif
 
 /*
@@ -3764,6 +3767,8 @@ void kmem_cache_free(struct kmem_cache *
 
 	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, obj_size(cachep));
+	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
+		debug_check_no_obj_freed(objp, obj_size(cachep));
 	__cache_free(cachep, objp);
 	local_irq_restore(flags);
 }
@@ -3789,6 +3794,7 @@ void kfree(const void *objp)
 	kfree_debugcheck(objp);
 	c = virt_to_cache(objp);
 	debug_check_no_locks_freed(objp, obj_size(c));
+	debug_check_no_obj_freed(objp, obj_size(c));
 	__cache_free(c, (void *)objp);
 	local_irq_restore(flags);
 }
Index: linux-2.6/mm/slub.c
===================================================================
--- linux-2.6.orig/mm/slub.c
+++ linux-2.6/mm/slub.c
@@ -21,6 +21,7 @@
 #include <linux/ctype.h>
 #include <linux/kallsyms.h>
 #include <linux/memory.h>
+#include <linux/debugobjects.h>
 
 /*
  * Lock order:
@@ -1694,6 +1695,8 @@ static __always_inline void slab_free(st
 	local_irq_save(flags);
 	c = get_cpu_slab(s, smp_processor_id());
 	debug_check_no_locks_freed(object, c->objsize);
+	if (!(s->flags & SLAB_DEBUG_OBJECTS))
+		debug_check_no_obj_freed(object, s->objsize);
 	if (likely(page == c->page && c->node >= 0)) {
 		object[c->offset] = c->freelist;
 		c->freelist = object;
Index: linux-2.6/mm/vmalloc.c
===================================================================
--- linux-2.6.orig/mm/vmalloc.c
+++ linux-2.6/mm/vmalloc.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
+#include <linux/debugobjects.h>
 
 #include <linux/vmalloc.h>
 
@@ -383,6 +384,7 @@ static void __vunmap(const void *addr, i
 	}
 
 	debug_check_no_locks_freed(addr, area->size);
+	debug_check_no_obj_freed(addr, area->size);
 
 	if (deallocate_pages) {
 		int i;

-- 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/