lockdep.c

Kernel code of linux kernel

/*
 * kernel/lockdep.c
 *
 * Runtime locking correctness validator
 *
 * Started by Ingo Molnar:
 *
 *  Copyright (C) 2006,2007 Red Hat, Inc., Ingo Molnar <[e-mail]>
 *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <[e-mail]>
 *
 * this code maps all the lock dependencies as they occur in a live kernel
 * and will warn about the following classes of locking bugs:
 *
 * - lock inversion scenarios
 * - circular lock dependencies
 * - hardirq/softirq safe/unsafe locking bugs
 *
 * Bugs are reported even if the current locking scenario does not cause
 * any deadlock at this point.
 *
 * I.e. if anytime in the past two locks were taken in a different order,
 * even if it happened for another task, even if those were different
 * locks (but of the same class as this lock), this code will detect it.
 *
 * Thanks to Arjan van de Ven for coming up with the initial idea of
 * mapping lock dependencies runtime.
 */
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/delay.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/spinlock.h>
#include <linux/kallsyms.h>
#include <linux/interrupt.h>
#include <linux/stacktrace.h>
#include <linux/debug_locks.h>
#include <linux/irqflags.h>
#include <linux/utsname.h>
#include <linux/hash.h>
#include <linux/ftrace.h>

#include <asm/sections.h>

#include "lockdep_internals.h"

#ifdef CONFIG_PROVE_LOCKING
int prove_locking = 1;
module_param(prove_locking, int, 0644);
#else
#define prove_locking 0
#endif

#ifdef CONFIG_LOCK_STAT
int lock_stat = 1;
module_param(lock_stat, int, 0644);
#else
#define lock_stat 0
#endif

/*
 * lockdep_lock: protects the lockdep graph, the hashes and the
 *               class/list/hash allocators.
 *
 * This is one of the rare exceptions where it's justified
 * to use a raw spinlock - we really dont want the spinlock
 * code to recurse back into the lockdep code...
 */
static raw_spinlock_t lockdep_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;

static int graph_lock(void)
{
	__raw_spin_lock(&lockdep_lock);
	/*
	 * Make sure that if another CPU detected a bug while
	 * walking the graph we dont change it (while the other
	 * CPU is busy printing out stuff with the graph lock
	 * dropped already)
	 */
	if (!debug_locks) {
		__raw_spin_unlock(&lockdep_lock);
		return 0;
	}
	/* prevent any recursions within lockdep from causing deadlocks */
	current->lockdep_recursion++;
	return 1;
}

static inline int graph_unlock(void)
{
	if (debug_locks && !__raw_spin_is_locked(&lockdep_lock))
		return DEBUG_LOCKS_WARN_ON(1);

	current->lockdep_recursion--;
	__raw_spin_unlock(&lockdep_lock);
	return 0;
}

/*
 * Turn lock debugging off and return with 0 if it was off already,
 * and also release the graph lock:
 */
static inline int debug_locks_off_graph_unlock(void)
{
	int ret = debug_locks_off();

	__raw_spin_unlock(&lockdep_lock);

	return ret;
}

static int lockdep_initialized;

unsigned long nr_list_entries;
static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];

/*
 * All data structures here are protected by the global debug_lock.
 *
 * Mutex key structs only get allocated, once during bootup, and never
 * get freed - this significantly simplifies the debugging code.
 */
unsigned long nr_lock_classes;
static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];

static inline struct lock_class *hlock_class(struct held_lock *hlock)
{
	if (!hlock->class_idx) {
		DEBUG_LOCKS_WARN_ON(1);
		return NULL;
	}
	return lock_classes + hlock->class_idx - 1;
}

#ifdef CONFIG_LOCK_STAT
static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);

static int lock_contention_point(struct lock_class *class, unsigned long ip)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
		if (class->contention_point[i] == 0) {
			class->contention_point[i] = ip;
			break;
		}
		if (class->contention_point[i] == ip)
			break;
	}

	return i;
}

static void lock_time_inc(struct lock_time *lt, s64 time)
{
	if (time > lt->max)
		lt->max = time;

	if (time < lt->min || !lt->min)
		lt->min = time;

	lt->total += time;
	lt->nr++;
}

static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
{
	dst->min += src->min;
	dst->max += src->max;
	dst->total += src->total;
	dst->nr += src->nr;
}

struct lock_class_stats lock_stats(struct lock_class *class)
{
	struct lock_class_stats stats;
	int cpu, i;

	memset(&stats, 0, sizeof(struct lock_class_stats));
	for_each_possible_cpu(cpu) {
		struct lock_class_stats *pcs =
			&per_cpu(lock_stats, cpu)[class - lock_classes];

		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
			stats.contention_point[i] += pcs->contention_point[i];

		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
		lock_time_add(&pcs->write_waittime, &stats.write_waittime);

		lock_time_add(&pcs->read_holdtime, &stats.read_holdtime);
		lock_time_add(&pcs->write_holdtime, &stats.write_holdtime);

		for (i = 0; i < ARRAY_SIZE(stats.bounces); i++)
			stats.bounces[i] += pcs->bounces[i];
	}

	return stats;
}

void clear_lock_stats(struct lock_class *class)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		struct lock_class_stats *cpu_stats =
			&per_cpu(lock_stats, cpu)[class - lock_classes];

		memset(cpu_stats, 0, sizeof(struct lock_class_stats));
	}
	memset(class->contention_point, 0, sizeof(class->contention_point));
}

static struct lock_class_stats *get_lock_stats(struct lock_class *class)
{
	return &get_cpu_var(lock_stats)[class - lock_classes];
}

static void put_lock_stats(struct lock_class_stats *stats)
{
	put_cpu_var(lock_stats);
}

static void lock_release_holdtime(struct held_lock *hlock)
{
	struct lock_class_stats *stats;
	s64 holdtime;

	if (!lock_stat)
		return;

	holdtime = sched_clock() - hlock->holdtime_stamp;

	stats = get_lock_stats(hlock_class(hlock));
	if (hlock->read)
		lock_time_inc(&stats->read_holdtime, holdtime);
	else
		lock_time_inc(&stats->write_holdtime, holdtime);
	put_lock_stats(stats);
}
#else
static inline void lock_release_holdtime(struct held_lock *hlock)
{
}
#endif

/*
 * We keep a global list of all lock classes. The list only grows,
 * never shrinks. The list is only accessed with the lockdep
 * spinlock lock held.
 */
LIST_HEAD(all_lock_classes);

/*
 * The lockdep classes are in a hash-table as well, for fast lookup:
 */
#define CLASSHASH_BITS		(MAX_LOCKDEP_KEYS_BITS - 1)
#define CLASSHASH_SIZE		(1UL << CLASSHASH_BITS)
#define __classhashfn(key)	hash_long((unsigned long)key, CLASSHASH_BITS)
#define classhashentry(key)	(classhash_table + __classhashfn((key)))

static struct list_head classhash_table[CLASSHASH_SIZE];

/*
 * We put the lock dependency chains into a hash-table as well, to cache
 * their existence:
 */
#define CHAINHASH_BITS		(MAX_LOCKDEP_CHAINS_BITS-1)
#define CHAINHASH_SIZE		(1UL << CHAINHASH_BITS)
#define __chainhashfn(chain)	hash_long(chain, CHAINHASH_BITS)
#define chainhashentry(chain)	(chainhash_table + __chainhashfn((chain)))

static struct list_head chainhash_table[CHAINHASH_SIZE];

/*
 * The hash key of the lock dependency chains is a hash itself too:
 * it's a hash of all locks taken up to that lock, including that lock.
 * It's a 64-bit hash, because it's important for the keys to be
 * unique.
 */
#define iterate_chain_key(key1, key2) \
	(((key1) << MAX_LOCKDEP_KEYS_BITS) ^ \
	((key1) >> (64-MAX_LOCKDEP_KEYS_BITS)) ^ \
	(key2))

void lockdep_off(void)
{
	current->lockdep_recursion++;
}

EXPORT_SYMBOL(lockdep_off);

void lockdep_on(void)
{
	current->lockdep_recursion--;
}

EXPORT_SYMBOL(lockdep_on);

/*
 * Debugging switches:
 */

#define VERBOSE			0
#define VERY_VERBOSE		0

#if VERBOSE
# define HARDIRQ_VERBOSE	1
# define SOFTIRQ_VERBOSE	1
#else
# define HARDIRQ_VERBOSE	0
# define SOFTIRQ_VERBOSE	0
#endif

#if VERBOSE || HARDIRQ_VERBOSE || SOFTIRQ_VERBOSE
/*
 * Quick filtering for interesting events:
 */
static int class_filter(struct lock_class *class)
{
#if 0
	/* Example */
	if (class->name_version == 1 &&
			!strcmp(class->name, "lockname"))
		return 1;
	if (class->name_version == 1 &&
			!strcmp(class->name, "&struct->lockfield"))
		return 1;
#endif
	/* Filter everything else. 1 would be to allow everything else */
	return 0;
}
#endif

static int verbose(struct lock_class *class)
{
#if VERBOSE
	return class_filter(class);
#endif
	return 0;
}

/*
 * Stack-trace: tightly packed array of stack backtrace
 * addresses. Protected by the graph_lock.
 */
unsigned long nr_stack_trace_entries;
static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];

static int save_trace(struct stack_trace *trace)
{
	trace->nr_entries = 0;
	trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
	trace->entries = stack_trace + nr_stack_trace_entries;

	trace->skip = 3;

	save_stack_trace(trace);

	trace->max_entries = trace->nr_entries;

	nr_stack_trace_entries += trace->nr_entries;

	if (nr_stack_trace_entries == MAX_STACK_TRACE_ENTRIES) {
		if (!debug_locks_off_graph_unlock())
			return 0;

		printk("BUG: MAX_STACK_TRACE_ENTRIES too low!\n");
		printk("turning off the locking correctness validator.\n");
		dump_stack();

		return 0;
	}

	return 1;
}

unsigned int nr_hardirq_chains;
unsigned int nr_softirq_chains;
unsigned int nr_process_chains;
unsigned int max_lockdep_depth;
unsigned int max_recursion_depth;

static unsigned int lockdep_dependency_gen_id;

static bool lockdep_dependency_visit(struct lock_class *source,
				     unsigned int depth)
{
	if (!depth)
		lockdep_dependency_gen_id++;
	if (source->dep_gen_id == lockdep_dependency_gen_id)
		return true;
	source->dep_gen_id = lockdep_dependency_gen_id;
	return false;
}

#ifdef CONFIG_DEBUG_LOCKDEP
/*
 * We cannot printk in early bootup code. Not even early_printk()
 * might work. So we mark any initialization errors and printk
 * about it later on, in lockdep_info().
 */
static int lockdep_init_error;
static unsigned long lockdep_init_trace_data[20];
static struct stack_trace lockdep_init_trace = {
	.max_entries = ARRAY_SIZE(lockdep_init_trace_data),
	.entries = lockdep_init_trace_data,
};

/*
 * Various lockdep statistics:
 */
atomic_t chain_lookup_hits;
atomic_t chain_lookup_misses;
atomic_t hardirqs_on_events;
atomic_t hardirqs_off_events;
atomic_t redundant_hardirqs_on;
atomic_t redundant_hardirqs_off;
atomic_t softirqs_on_events;
atomic_t softirqs_off_events;
atomic_t redundant_softirqs_on;
atomic_t redundant_softirqs_off;
atomic_t nr_unused_locks;
atomic_t nr_cyclic_checks;
atomic_t nr_cyclic_check_recursions;
atomic_t nr_find_usage_forwards_checks;
atomic_t nr_find_usage_forwards_recursions;
atomic_t nr_find_usage_backwards_checks;
atomic_t nr_find_usage_backwards_recursions;
# define debug_atomic_inc(ptr)		atomic_inc(ptr)
# define debug_atomic_dec(ptr)		atomic_dec(ptr)
# define debug_atomic_read(ptr)		atomic_read(ptr)
#else
# define debug_atomic_inc(ptr)		do { } while (0)
# define debug_atomic_dec(ptr)		do { } while (0)
# define debug_atomic_read(ptr)		0
#endif

/*
 * Locking printouts:
 */

static const char *usage_str[] =
{
	[LOCK_USED] =			"initial-use ",
	[LOCK_USED_IN_HARDIRQ] =	"in-hardirq-W",
	[LOCK_USED_IN_SOFTIRQ] =	"in-softirq-W",
	[LOCK_ENABLED_SOFTIRQS] =	"softirq-on-W",
	[LOCK_ENABLED_HARDIRQS] =	"hardirq-on-W",
	[LOCK_USED_IN_HARDIRQ_READ] =	"in-hardirq-R",
	[LOCK_USED_IN_SOFTIRQ_READ] =	"in-softirq-R",
	[LOCK_ENABLED_SOFTIRQS_READ] =	"softirq-on-R",
	[LOCK_ENABLED_HARDIRQS_READ] =	"hardirq-on-R",
};

const char * __get_key_name(struct lockdep_subclass_key *key, char *str)
{
	return kallsyms_lookup((unsigned long)key, NULL, NULL, NULL, str);
}

void
get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4)
{
	*c1 = '.', *c2 = '.', *c3 = '.', *c4 = '.';

	if (class->usage_mask & LOCKF_USED_IN_HARDIRQ)
		*c1 = '+';
	else
		if (class->usage_mask & LOCKF_ENABLED_HARDIRQS)
			*c1 = '-';

	if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ)
		*c2 = '+';
	else
		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS)
			*c2 = '-';

	if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ)
		*c3 = '-';
	if (class->usage_mask & LOCKF_USED_IN_HARDIRQ_READ) {
		*c3 = '+';
		if (class->usage_mask & LOCKF_ENABLED_HARDIRQS_READ)
			*c3 = '?';
	}

	if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ)
		*c4 = '-';
	if (class->usage_mask & LOCKF_USED_IN_SOFTIRQ_READ) {
		*c4 = '+';
		if (class->usage_mask & LOCKF_ENABLED_SOFTIRQS_READ)
			*c4 = '?';
	}
}

static void print_lock_name(struct lock_class *class)
{
	char str[KSYM_NAME_LEN], c1, c2, c3, c4;
	const char *name;

	get_usage_chars(class, &c1, &c2, &c3, &c4);

	name = class->name;
	if (!name) {
		name = __get_key_name(class->key, str);
		printk(" (%s", name);
	} else {
		printk(" (%s", name);
		if (class->name_version > 1)
			printk("#%d", class->name_version);
		if (class->subclass)
			printk("/%d", class->subclass);
	}
	printk("){%c%c%c%c}", c1, c2, c3, c4);
}

static void print_lockdep_cache(struct lockdep_map *lock)
{
	const char *name;