lockdep.c

	if (!subclass)
		class = lock->class_cache;
	/*
	 * Not cached yet or subclass?
	 */
	if (unlikely(!class)) {
		class = register_lock_class(lock, subclass, 0);
		if (!class)
			return 0;
	}
	debug_atomic_inc((atomic_t *)&class->ops);
	if (very_verbose(class)) {
		printk("\nacquire class [%p] %s", class->key, class->name);
		if (class->name_version > 1)
			printk("#%d", class->name_version);
		printk("\n");
		dump_stack();
	}

	/*
	 * Add the lock to the list of currently held locks.
	 * (we dont increase the depth just yet, up until the
	 * dependency checks are done)
	 */
	depth = curr->lockdep_depth;
	if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH))
		return 0;

	hlock = curr->held_locks + depth;

	hlock->class = class;
	hlock->acquire_ip = ip;
	hlock->instance = lock;
	hlock->trylock = trylock;
	hlock->read = read;
	hlock->check = check;
	hlock->hardirqs_off = hardirqs_off;

	if (check != 2)
		goto out_calc_hash;
#ifdef CONFIG_TRACE_IRQFLAGS
	/*
	 * If non-trylock use in a hardirq or softirq context, then
	 * mark the lock as used in these contexts:
	 */
	if (!trylock) {
		if (read) {
			if (curr->hardirq_context)
				if (!mark_lock(curr, hlock,
						LOCK_USED_IN_HARDIRQ_READ, ip))
					return 0;
			if (curr->softirq_context)
				if (!mark_lock(curr, hlock,
						LOCK_USED_IN_SOFTIRQ_READ, ip))
					return 0;
		} else {
			if (curr->hardirq_context)
				if (!mark_lock(curr, hlock, LOCK_USED_IN_HARDIRQ, ip))
					return 0;
			if (curr->softirq_context)
				if (!mark_lock(curr, hlock, LOCK_USED_IN_SOFTIRQ, ip))
					return 0;
		}
	}
	if (!hardirqs_off) {
		if (read) {
			if (!mark_lock(curr, hlock,
					LOCK_ENABLED_HARDIRQS_READ, ip))
				return 0;
			if (curr->softirqs_enabled)
				if (!mark_lock(curr, hlock,
						LOCK_ENABLED_SOFTIRQS_READ, ip))
					return 0;
		} else {
			if (!mark_lock(curr, hlock,
					LOCK_ENABLED_HARDIRQS, ip))
				return 0;
			if (curr->softirqs_enabled)
				if (!mark_lock(curr, hlock,
						LOCK_ENABLED_SOFTIRQS, ip))
					return 0;
		}
	}
#endif
	/* mark it as used: */
	if (!mark_lock(curr, hlock, LOCK_USED, ip))
		return 0;
out_calc_hash:
	/*
	 * Calculate the chain hash: it's the combined has of all the
	 * lock keys along the dependency chain. We save the hash value
	 * at every step so that we can get the current hash easily
	 * after unlock. The chain hash is then used to cache dependency
	 * results.
	 *
	 * The 'key ID' is what is the most compact key value to drive
	 * the hash, not class->key.
	 */
	id = class - lock_classes;
	if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS))
		return 0;

	chain_key = curr->curr_chain_key;
	if (!depth) {
		if (DEBUG_LOCKS_WARN_ON(chain_key != 0))
			return 0;
		chain_head = 1;
	}

	hlock->prev_chain_key = chain_key;

#ifdef CONFIG_TRACE_IRQFLAGS
	/*
	 * Keep track of points where we cross into an interrupt context:
	 */
	hlock->irq_context = 2*(curr->hardirq_context ? 1 : 0) +
				curr->softirq_context;
	if (depth) {
		struct held_lock *prev_hlock;

		prev_hlock = curr->held_locks + depth-1;
		/*
		 * If we cross into another context, reset the
		 * hash key (this also prevents the checking and the
		 * adding of the dependency to 'prev'):
		 */
		if (prev_hlock->irq_context != hlock->irq_context) {
			chain_key = 0;
			chain_head = 1;
		}
	}
#endif
	chain_key = iterate_chain_key(chain_key, id);
	curr->curr_chain_key = chain_key;

	/*
	 * Trylock needs to maintain the stack of held locks, but it
	 * does not add new dependencies, because trylock can be done
	 * in any order.
	 *
	 * We look up the chain_key and do the O(N^2) check and update of
	 * the dependencies only if this is a new dependency chain.
	 * (If lookup_chain_cache() returns with 1 it acquires
	 * hash_lock for us)
	 */
	if (!trylock && (check == 2) && lookup_chain_cache(chain_key, class)) {
		/*
		 * Check whether last held lock:
		 *
		 * - is irq-safe, if this lock is irq-unsafe
		 * - is softirq-safe, if this lock is hardirq-unsafe
		 *
		 * And check whether the new lock's dependency graph
		 * could lead back to the previous lock.
		 *
		 * any of these scenarios could lead to a deadlock. If
		 * All validations
		 */
		int ret = check_deadlock(curr, hlock, lock, read);

		if (!ret)
			return 0;
		/*
		 * Mark recursive read, as we jump over it when
		 * building dependencies (just like we jump over
		 * trylock entries):
		 */
		if (ret == 2)
			hlock->read = 2;
		/*
		 * Add dependency only if this lock is not the head
		 * of the chain, and if it's not a secondary read-lock:
		 */
		if (!chain_head && ret != 2)
			if (!check_prevs_add(curr, hlock))
				return 0;
		__raw_spin_unlock(&hash_lock);
	}
	curr->lockdep_depth++;
	check_chain_key(curr);
	if (unlikely(curr->lockdep_depth >= MAX_LOCK_DEPTH)) {
		debug_locks_off();
		printk("BUG: MAX_LOCK_DEPTH too low!\n");
		printk("turning off the locking correctness validator.\n");
		return 0;
	}
	if (unlikely(curr->lockdep_depth > max_lockdep_depth))
		max_lockdep_depth = curr->lockdep_depth;

	return 1;
}

static int
print_unlock_inbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
			   unsigned long ip)
{
	if (!debug_locks_off())
		return 0;
	if (debug_locks_silent)
		return 0;

	printk("\n=====================================\n");
	printk(  "[ BUG: bad unlock balance detected! ]\n");
	printk(  "-------------------------------------\n");
	printk("%s/%d is trying to release lock (",
		curr->comm, curr->pid);
	print_lockdep_cache(lock);
	printk(") at:\n");
	print_ip_sym(ip);
	printk("but there are no more locks to release!\n");
	printk("\nother info that might help us debug this:\n");
	lockdep_print_held_locks(curr);

	printk("\nstack backtrace:\n");
	dump_stack();

	return 0;
}

/*
 * Common debugging checks for both nested and non-nested unlock:
 */
static int check_unlock(struct task_struct *curr, struct lockdep_map *lock,
			unsigned long ip)
{
	if (unlikely(!debug_locks))
		return 0;
	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
		return 0;

	if (curr->lockdep_depth <= 0)
		return print_unlock_inbalance_bug(curr, lock, ip);

	return 1;
}

/*
 * Remove the lock to the list of currently held locks in a
 * potentially non-nested (out of order) manner. This is a
 * relatively rare operation, as all the unlock APIs default
 * to nested mode (which uses lock_release()):
 */
static int
lock_release_non_nested(struct task_struct *curr,
			struct lockdep_map *lock, unsigned long ip)
{
	struct held_lock *hlock, *prev_hlock;
	unsigned int depth;
	int i;

	/*
	 * Check whether the lock exists in the current stack
	 * of held locks:
	 */
	depth = curr->lockdep_depth;
	if (DEBUG_LOCKS_WARN_ON(!depth))
		return 0;

	prev_hlock = NULL;
	for (i = depth-1; i >= 0; i--) {
		hlock = curr->held_locks + i;
		/*
		 * We must not cross into another context:
		 */
		if (prev_hlock && prev_hlock->irq_context != hlock->irq_context)
			break;
		if (hlock->instance == lock)
			goto found_it;
		prev_hlock = hlock;
	}
	return print_unlock_inbalance_bug(curr, lock, ip);

found_it:
	/*
	 * We have the right lock to unlock, 'hlock' points to it.
	 * Now we remove it from the stack, and add back the other
	 * entries (if any), recalculating the hash along the way:
	 */
	curr->lockdep_depth = i;
	curr->curr_chain_key = hlock->prev_chain_key;

	for (i++; i < depth; i++) {
		hlock = curr->held_locks + i;
		if (!__lock_acquire(hlock->instance,
			hlock->class->subclass, hlock->trylock,
				hlock->read, hlock->check, hlock->hardirqs_off,
				hlock->acquire_ip))
			return 0;
	}

	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - 1))
		return 0;
	return 1;
}

/*
 * Remove the lock to the list of currently held locks - this gets
 * called on mutex_unlock()/spin_unlock*() (or on a failed
 * mutex_lock_interruptible()). This is done for unlocks that nest
 * perfectly. (i.e. the current top of the lock-stack is unlocked)
 */
static int lock_release_nested(struct task_struct *curr,
			       struct lockdep_map *lock, unsigned long ip)
{
	struct held_lock *hlock;
	unsigned int depth;

	/*
	 * Pop off the top of the lock stack:
	 */
	depth = curr->lockdep_depth - 1;
	hlock = curr->held_locks + depth;

	/*
	 * Is the unlock non-nested:
	 */
	if (hlock->instance != lock)
		return lock_release_non_nested(curr, lock, ip);
	curr->lockdep_depth--;

	if (DEBUG_LOCKS_WARN_ON(!depth && (hlock->prev_chain_key != 0)))
		return 0;

	curr->curr_chain_key = hlock->prev_chain_key;

#ifdef CONFIG_DEBUG_LOCKDEP
	hlock->prev_chain_key = 0;
	hlock->class = NULL;
	hlock->acquire_ip = 0;
	hlock->irq_context = 0;
#endif
	return 1;
}

/*
 * Remove the lock to the list of currently held locks - this gets
 * called on mutex_unlock()/spin_unlock*() (or on a failed
 * mutex_lock_interruptible()). This is done for unlocks that nest
 * perfectly. (i.e. the current top of the lock-stack is unlocked)
 */
static void
__lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
{
	struct task_struct *curr = current;

	if (!check_unlock(curr, lock, ip))
		return;

	if (nested) {
		if (!lock_release_nested(curr, lock, ip))
			return;
	} else {
		if (!lock_release_non_nested(curr, lock, ip))
			return;
	}

	check_chain_key(curr);
}

/*
 * Check whether we follow the irq-flags state precisely:
 */
static void check_flags(unsigned long flags)
{
#if defined(CONFIG_DEBUG_LOCKDEP) && defined(CONFIG_TRACE_IRQFLAGS)
	if (!debug_locks)
		return;

	if (irqs_disabled_flags(flags))
		DEBUG_LOCKS_WARN_ON(current->hardirqs_enabled);
	else
		DEBUG_LOCKS_WARN_ON(!current->hardirqs_enabled);

	/*
	 * We dont accurately track softirq state in e.g.
	 * hardirq contexts (such as on 4KSTACKS), so only
	 * check if not in hardirq contexts:
	 */
	if (!hardirq_count()) {
		if (softirq_count())
			DEBUG_LOCKS_WARN_ON(current->softirqs_enabled);
		else
			DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
	}

	if (!debug_locks)
		print_irqtrace_events(current);
#endif
}

/*
 * We are not always called with irqs disabled - do that here,
 * and also avoid lockdep recursion:
 */
void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
		  int trylock, int read, int check, unsigned long ip)
{
	unsigned long flags;

	if (unlikely(current->lockdep_recursion))
		return;

	raw_local_irq_save(flags);
	check_flags(flags);

	current->lockdep_recursion = 1;
	__lock_acquire(lock, subclass, trylock, read, check,
		       irqs_disabled_flags(flags), ip);
	current->lockdep_recursion = 0;
	raw_local_irq_restore(flags);
}

EXPORT_SYMBOL_GPL(lock_acquire);

void lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
{
	unsigned long flags;

	if (unlikely(current->lockdep_recursion))
		return;

	raw_local_irq_save(flags);
	check_flags(flags);
	current->lockdep_recursion = 1;
	__lock_release(lock, nested, ip);
	current->lockdep_recursion = 0;
	raw_local_irq_restore(flags);
}

EXPORT_SYMBOL_GPL(lock_release);

/*
 * Used by the testsuite, sanitize the validator state
 * after a simulated failure:
 */

void lockdep_reset(void)
{
	unsigned long flags;

	raw_local_irq_save(flags);
	current->curr_chain_key = 0;
	current->lockdep_depth = 0;
	current->lockdep_recursion = 0;
	memset(current->held_locks, 0, MAX_LOCK_DEPTH*sizeof(struct held_lock));
	nr_hardirq_chains = 0;
	nr_softirq_chains = 0;
	nr_process_chains = 0;
	debug_locks = 1;
	raw_local_irq_restore(flags);
}

static void zap_class(struct lock_class *class)
{
	int i;

	/*
	 * Remove all dependencies this lock is
	 * involved in:
	 */
	for (i = 0; i < nr_list_entries; i++) {
		if (list_entries[i].class == class)
			list_del_rcu(&list_entries[i].entry);
	}
	/*
	 * Unhash the class and remove it from the all_lock_classes list:
	 */
	list_del_rcu(&class->hash_entry);
	list_del_rcu(&class->lock_entry);

}

static inline int within(void *addr, void *start, unsigned long size)
{
	return addr >= start && addr < start + size;
}

void lockdep_free_key_range(void *start, unsigned long size)
{
	struct lock_class *class, *next;
	struct list_head *head;
	unsigned long flags;
	int i;

	raw_local_irq_save(flags);
	__raw_spin_lock(&hash_lock);

	/*
	 * Unhash all classes that were created by this module:
	 */
	for (i = 0; i < CLASSHASH_SIZE; i++) {
		head = classhash_table + i;
		if (list_empty(head))
			continue;
		list_for_each_entry_safe(class, next, head, hash_entry)
			if (within(class->key, start, size))
				zap_class(class);
	}

	__raw_spin_unlock(&hash_lock);
	raw_local_irq_restore(flags);
}

void lockdep_reset_lock(struct lockdep_map *lock)
{
	struct lock_class *class, *next;
	struct list_head *head;
	unsigned long flags;
	int i, j;

	raw_local_irq_save(flags);

	/*
	 * Remove all classes this lock might have:
	 */
	for (j = 0; j < MAX_LOCKDEP_SUBCLASSES; j++) {
		/*
		 * If the class exists we look it up and zap it:
		 */
		class = look_up_lock_class(lock, j);
		if (class)
			zap_class(class);
	}
	/*
	 * Debug check: in the end all mapped classes should
	 * be gone.
	 */
	__raw_spin_lock(&hash_lock);
	for (i = 0; i < CLASSHASH_SIZE; i++) {
		head = classhash_table + i;
		if (list_empty(head))
			continue;
		list_for_each_entry_safe(class, next, head, hash_entry) {
			if (unlikely(class == lock->class_cache)) {
				__raw_spin_unlock(&hash_lock);
				DEBUG_LOCKS_WARN_ON(1);
				goto out_restore;
			}
		}
	}
	__raw_spin_unlock(&hash_lock);

out_restore:
	raw_local_irq_restore(flags);
}

void __init lockdep_init(void)
{
	int i;

	/*
	 * Some architectures have their own start_kernel()
	 * code which calls lockdep_init(), while we also
	 * call lockdep_init() from the start_kernel() itself,
	 * and we want to initialize the hashes only once:
	 */
	if (lockdep_initialized)
		return;

	for (i = 0; i < CLASSHASH_SIZE; i++)
		INIT_LIST_HEAD(classhash_table + i);

	for (i = 0; i < CHAINHASH_SIZE; i++)
		INIT_LIST_HEAD(chainhash_table + i);

	lockdep_initialized = 1;
}

void __init lockdep_info(void)
{
	printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n");

	printk("... MAX_LOCKDEP_SUBCLASSES:    %lu\n", MAX_LOCKDEP_SUBCLASSES);
	printk("... MAX_LOCK_DEPTH:          %lu\n", MAX_LOCK_DEPTH);
	printk("... MAX_LOCKDEP_KEYS:        %lu\n", MAX_LOCKDEP_KEYS);
	printk("... CLASSHASH_SIZE:           %lu\n", CLASSHASH_SIZE);
	printk("... MAX_LOCKDEP_ENTRIES:     %lu\n", MAX_LOCKDEP_ENTRIES);
	printk("... MAX_LOCKDEP_CHAINS:      %lu\n", MAX_LOCKDEP_CHAINS);
	printk("... CHAINHASH_SIZE:          %lu\n", CHAINHASH_SIZE);

	printk(" memory used by lock dependency info: %lu kB\n",
		(sizeof(struct lock_class) * MAX_LOCKDEP_KEYS +
		sizeof(struct list_head) * CLASSHASH_SIZE +
		sizeof(struct lock_list) * MAX_LOCKDEP_ENTRIES +
		sizeof(struct lock_chain) * MAX_LOCKDEP_CHAINS +
		sizeof(struct list_head) * CHAINHASH_SIZE) / 1024);

	printk(" per task-struct memory footprint: %lu bytes\n",
		sizeof(struct held_lock) * MAX_LOCK_DEPTH);

#ifdef CONFIG_DEBUG_LOCKDEP
	if (lockdep_init_error)
		printk("WARNING: lockdep init error! Arch code didnt call lockdep_init() early enough?\n");
#endif
}

static inline int in_range(const void *start, const void *addr, const void *end)
{
	return addr >= start && addr <= end;
}

static void
print_freed_lock_bug(struct task_struct *curr, const void *mem_from,
		     const void *mem_to, struct held_lock *hlock)
{
	if (!debug_locks_off())
		return;
	if (debug_locks_silent)
		return;

	printk("\n=========================\n");
	printk(  "[ BUG: held lock freed! ]\n");
	printk(  "-------------------------\n");
	printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n",
		curr->comm, curr->pid, mem_from, mem_to-1);
	print_lock(hlock);
	lockdep_print_held_locks(curr);

	printk("\nstack backtrace:\n");
	dump_stack();
}

/*
 * Called when kernel memory is freed (or unmapped), or if a lock
 * is destroyed or reinitialized - this code checks whether there is
 * any held lock in the memory range of <from> to <to>:
 */
void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
{
	const void *mem_to = mem_from + mem_len, *lock_from, *lock_to;
	struct task_struct *curr = current;
	struct held_lock *hlock;
	unsigned long flags;
	int i;

	if (unlikely(!debug_locks))
		return;

	local_irq_save(flags);
	for (i = 0; i < curr->lockdep_depth; i++) {
		hlock = curr->held_locks + i;

		lock_from = (void *)hlock->instance;
		lock_to = (void *)(hlock->instance + 1);

		if (!in_range(mem_from, lock_from, mem_to) &&
					!in_range(mem_from, lock_to, mem_to))
			continue;

		print_freed_lock_bug(curr, mem_from, mem_to, hlock);
		break;
	}
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);

static void print_held_locks_bug(struct task_struct *curr)
{
	if (!debug_locks_off())
		return;
	if (debug_locks_silent)
		return;

	printk("\n=====================================\n");
	printk(  "[ BUG: lock held at task exit time! ]\n");
	printk(  "-------------------------------------\n");
	printk("%s/%d is exiting with locks still held!\n",
		curr->comm, curr->pid);
	lockdep_print_held_locks(curr);

	printk("\nstack backtrace:\n");
	dump_stack();
}

void debug_check_no_locks_held(struct task_struct *task)
{
	if (unlikely(task->lockdep_depth > 0))
		print_held_locks_bug(task);
}

void debug_show_all_locks(void)
{
	struct task_struct *g, *p;
	int count = 10;
	int unlock = 1;

	printk("\nShowing all locks held in the system:\n");

	/*
	 * Here we try to get the tasklist_lock as hard as possible,
	 * if not successful after 2 seconds we ignore it (but keep
	 * trying). This is to enable a debug printout even if a
	 * tasklist_lock-holding task deadlocks or crashes.
	 */
retry:
	if (!read_trylock(&tasklist_lock)) {
		if (count == 10)
			printk("hm, tasklist_lock locked, retrying... ");
		if (count) {
			count--;
			printk(" #%d", 10-count);
			mdelay(200);
			goto retry;
		}
		printk(" ignoring it.\n");
		unlock = 0;
	}
	if (count != 10)
		printk(" locked it.\n");

	do_each_thread(g, p) {
		if (p->lockdep_depth)
			lockdep_print_held_locks(p);
		if (!unlock)
			if (read_trylock(&tasklist_lock))
				unlock = 1;
	} while_each_thread(g, p);

	printk("\n");
	printk("=============================================\n\n");

	if (unlock)
		read_unlock(&tasklist_lock);
}

EXPORT_SYMBOL_GPL(debug_show_all_locks);

void debug_show_held_locks(struct task_struct *task)
{
	lockdep_print_held_locks(task);
}

EXPORT_SYMBOL_GPL(debug_show_held_locks);