lock contention tracking -v3

Index: linux-2.6-git/include/linux/spinlock_types_up.h
===================================================================
@@ -12,14 +12,10 @@
  * Released under the General Public License (GPL).
  */
 
-#if defined(CONFIG_DEBUG_SPINLOCK) || \
-	defined(CONFIG_DEBUG_LOCK_ALLOC)
+#ifdef CONFIG_DEBUG_SPINLOCK
 
 typedef struct {
 	volatile unsigned int slock;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
 } raw_spinlock_t;
 
 #define __RAW_SPIN_LOCK_UNLOCKED { 1 }

@@ -34,9 +30,6 @@ typedef struct { } raw_spinlock_t;
 
 typedef struct {
 	/* no debug version on UP */
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
 } raw_rwlock_t;
 
 #define __RAW_RW_LOCK_UNLOCKED { }

Index: linux-2.6-git/include/linux/spinlock_types.h
===================================================================
@@ -9,14 +9,14 @@
  * Released under the General Public License (GPL).
  */
 
-#include <linux/lockdep.h>
-
 #if defined(CONFIG_SMP)
 # include <asm/spinlock_types.h>
 #else
 # include <linux/spinlock_types_up.h>
 #endif
 
+#include <linux/lockdep.h>
+
 typedef struct {
 	raw_spinlock_t raw_lock;
 #if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP)

Index: linux-2.6-git/kernel/lockdep.c
===================================================================
@@ -95,6 +95,7 @@ static int lockdep_initialized;
 unsigned long nr_list_entries;
 static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES];
 
+#ifdef CONFIG_PROVE_LOCKING
 /*
  * Allocate a lockdep entry. (assumes the graph_lock held, returns
  * with NULL on failure)

@@ -111,6 +112,7 @@ static struct lock_list *alloc_list_entr
 	}
 	return list_entries + nr_list_entries++;
 }
+#endif
 
 /*
  * All data structures here are protected by the global debug_lock.

@@ -140,7 +142,9 @@ LIST_HEAD(all_lock_classes);
 static struct list_head classhash_table[CLASSHASH_SIZE];
 
 unsigned long nr_lock_chains;
+#ifdef CONFIG_PROVE_LOCKING
 static struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS];
+#endif
 
 /*
  * We put the lock dependency chains into a hash-table as well, to cache

@@ -486,6 +490,7 @@ static void print_lock_dependencies(stru
 	}
 }
 
+#ifdef CONFIG_PROVE_LOCKING
 /*
  * Add a new dependency to the head of the list:
  */

@@ -545,6 +550,7 @@ print_circular_bug_entry(struct lock_lis
 
 	return 0;
 }
+#endif
 
 static void print_kernel_version(void)
 {

@@ -553,6 +559,7 @@ static void print_kernel_version(void)
 		init_utsname()->version);
 }
 
+#ifdef CONFIG_PROVE_LOCKING
 /*
  * When a circular dependency is detected, print the
  * header first:

@@ -643,6 +650,7 @@ check_noncircular(struct lock_class *sou
 	}
 	return 1;
 }
+#endif
 
 static int very_verbose(struct lock_class *class)
 {

@@ -827,6 +835,7 @@ check_usage(struct task_struct *curr, st
 
 #endif
 
+#ifdef CONFIG_PROVE_LOCKING
 static int
 print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 		   struct held_lock *next)

@@ -1091,7 +1100,7 @@ out_bug:
 
 	return 0;
 }
-
+#endif
 
 /*
  * Is this the address of a static object:

@@ -1311,6 +1320,7 @@ out_unlock_set:
 	return class;
 }
 
+#ifdef CONFIG_PROVE_LOCKING
 /*
  * Look up a dependency chain. If the key is not present yet then
  * add it and return 1 - in this case the new dependency chain is

@@ -1385,6 +1395,7 @@ cache_hit:
 
 	return 1;
 }
+#endif
 
 /*
  * We are building curr_chain_key incrementally, so double-check

Index: linux-2.6-git/kernel/spinlock.c
===================================================================
@@ -88,7 +88,7 @@ unsigned long __lockfunc _spin_lock_irqs
 	 * _raw_spin_lock_flags() code, because lockdep assumes
 	 * that interrupts are not re-enabled during lock-acquire:
 	 */
-#ifdef CONFIG_PROVE_LOCKING
+#ifdef CONFIG_LOCKDEP
 	_raw_spin_lock(lock);
 #else
 	_raw_spin_lock_flags(lock, &flags);

@@ -305,7 +305,7 @@ unsigned long __lockfunc _spin_lock_irqs
 	 * _raw_spin_lock_flags() code, because lockdep assumes
 	 * that interrupts are not re-enabled during lock-acquire:
 	 */
-#ifdef CONFIG_PROVE_SPIN_LOCKING
+#ifdef CONFIG_LOCKDEP
 	_raw_spin_lock(lock);
 #else
 	_raw_spin_lock_flags(lock, &flags);

Index: linux-2.6-git/kernel/lockdep.c
===================================================================
@@ -42,6 +42,16 @@
 
 #include "lockdep_internals.h"
 
+#ifdef CONFIG_PROVE_LOCKING
+int prove_locking = 1;
+module_param(prove_locking, int, 0644);
+#endif
+
+#ifdef CONFIG_LOCK_STAT
+int lock_stat = 1;
+module_param(lock_stat, int, 0644);
+#endif
+
 /*
  * lockdep_lock: protects the lockdep graph, the hashes and the
  *               class/list/hash allocators.

@@ -123,6 +133,92 @@ static struct lock_list *alloc_list_entr
 unsigned long nr_lock_classes;
 static struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
 
+#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 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;
+}
+
+static void lock_time_inc(struct lock_time *lt, unsigned long long time)
+{
+	if (time > lt->max)
+		lt->max = time;
+
+	if (time < lt->min || !lt->min)
+		lt->min = time;
+
+	lt->total += time;
+	lt->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);
+	}
+
+	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);
+}
+#endif
+
 /*
  * We keep a global list of all lock classes. The list only grows,
  * never shrinks. The list is only accessed with the lockdep

@@ -2035,6 +2131,11 @@ static int __lock_acquire(struct lockdep
 	int chain_head = 0;
 	u64 chain_key;
 
+#ifdef CONFIG_PROVE_LOCKING
+	if (!prove_locking)
+		check = 1;
+#endif
+
 	if (unlikely(!debug_locks))
 		return 0;
 

@@ -2085,6 +2186,10 @@ static int __lock_acquire(struct lockdep
 	hlock->read = read;
 	hlock->check = check;
 	hlock->hardirqs_off = hardirqs_off;
+#ifdef CONFIG_LOCK_STAT
+	hlock->waittime_stamp = 0;
+	hlock->holdtime_stamp = sched_clock();
+#endif
 
 	if (check != 2)
 		goto out_calc_hash;

@@ -2132,10 +2237,11 @@ static int __lock_acquire(struct lockdep
 		}
 	}
 #endif
+out_calc_hash:
 	/* mark it as used: */
 	if (!mark_lock(curr, hlock, LOCK_USED))
 		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

@@ -2183,6 +2289,7 @@ out_calc_hash:
 	chain_key = iterate_chain_key(chain_key, id);
 	curr->curr_chain_key = chain_key;
 
+#ifdef CONFIG_PROVE_LOCKING
 	/*
 	 * Trylock needs to maintain the stack of held locks, but it
 	 * does not add new dependencies, because trylock can be done

@@ -2229,6 +2336,7 @@ out_calc_hash:
 		/* after lookup_chain_cache(): */
 		if (unlikely(!debug_locks))
 			return 0;
+#endif
 
 	curr->lockdep_depth++;
 	check_chain_key(curr);

@@ -2276,6 +2384,35 @@ print_unlock_inbalance_bug(struct task_s
 	return 0;
 }
 
+#ifdef CONFIG_LOCK_STAT
+static int
+print_lock_contention_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 contention detected! ]\n");
+	printk(  "---------------------------------\n");
+	printk("%s/%d is trying to contend lock (",
+		curr->comm, curr->pid);
+	print_lockdep_cache(lock);
+	printk(") at:\n");
+	print_ip_sym(ip);
+	printk("but there are no locks held!\n");
+	printk("\nother info that might help us debug this:\n");
+	lockdep_print_held_locks(curr);
+
+	printk("\nstack backtrace:\n");
+	dump_stack();
+
+	return 0;
+}
+#endif
+
 /*
  * Common debugging checks for both nested and non-nested unlock:
  */

@@ -2293,6 +2430,32 @@ static int check_unlock(struct task_stru
 	return 1;
 }
 
+#ifdef CONFIG_LOCK_STAT
+static void lock_release_holdtime(struct held_lock *hlock)
+{
+	struct lock_class_stats *stats;
+	unsigned long long holdtime;
+
+	if (!lock_stat)
+		return;
+
+	holdtime = sched_clock() - hlock->holdtime_stamp;
+
+	stats = get_lock_stats(hlock->class);
+
+	if (hlock->read)
+		lock_time_inc(&stats->read_holdtime, holdtime);
+	else
+		lock_time_inc(&stats->write_holdtime, holdtime);
+
+	put_lock_stats(stats);
+}
+#else
+static void lock_release_holdtime(struct held_lock *hlock)
+{
+}
+#endif
+
 /*
  * Remove the lock to the list of currently held locks in a
  * potentially non-nested (out of order) manner. This is a

@@ -2330,6 +2493,8 @@ lock_release_non_nested(struct task_stru
 	return print_unlock_inbalance_bug(curr, lock, ip);
 
 found_it:
+	lock_release_holdtime(hlock);
+
 	/*
 	 * We have the right lock to unlock, 'hlock' points to it.
 	 * Now we remove it from the stack, and add back the other

@@ -2382,6 +2547,8 @@ static int lock_release_nested(struct ta
 
 	curr->curr_chain_key = hlock->prev_chain_key;
 
+	lock_release_holdtime(hlock);
+
 #ifdef CONFIG_DEBUG_LOCKDEP
 	hlock->prev_chain_key = 0;
 	hlock->class = NULL;

@@ -2416,6 +2583,95 @@ __lock_release(struct lockdep_map *lock,
 	check_chain_key(curr);
 }
 
+#ifdef CONFIG_LOCK_STAT
+static void
+__lock_contended(struct lockdep_map *lock, unsigned long ip)
+{
+	struct task_struct *curr = current;
+	struct held_lock *hlock, *prev_hlock;
+	struct lock_class_stats *stats;
+	unsigned int depth;
+	int i, point;
+
+	depth = curr->lockdep_depth;
+	if (DEBUG_LOCKS_WARN_ON(!depth))
+		return;
+
+	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;
+	}
+	print_lock_contention_bug(curr, lock, ip);
+	return;
+
+found_it:
+	hlock->waittime_stamp = sched_clock();
+
+	point = lock_contention_point(hlock->class, ip);
+
+	stats = get_lock_stats(hlock->class);
+	if (point < ARRAY_SIZE(stats->contention_point))
+		stats->contention_point[i]++;
+	put_lock_stats(stats);
+}
+
+static void
+__lock_acquired(struct lockdep_map *lock)
+{
+	struct task_struct *curr = current;
+	struct held_lock *hlock, *prev_hlock;
+	struct lock_class_stats *stats;
+	unsigned int depth;
+	unsigned long long now, waittime;
+	int i;
+
+	depth = curr->lockdep_depth;
+	if (DEBUG_LOCKS_WARN_ON(!depth))
+		return;
+
+	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;
+	}
+	print_lock_contention_bug(curr, lock, _RET_IP_);
+	return;
+
+found_it:
+	if (!hlock->waittime_stamp)
+		return;
+
+	now = sched_clock();
+	waittime = now - hlock->waittime_stamp;
+
+	hlock->holdtime_stamp = now;
+
+	stats = get_lock_stats(hlock->class);
+
+	if (hlock->read)
+		lock_time_inc(&stats->read_waittime, waittime);
+	else
+		lock_time_inc(&stats->write_waittime, waittime);
+
+	put_lock_stats(stats);
+}
+#endif
+
 /*
  * Check whether we follow the irq-flags state precisely:
  */

@@ -2456,6 +2712,14 @@ void lock_acquire(struct lockdep_map *lo
 {
 	unsigned long flags;
 
+#ifdef CONFIG_LOCK_STAT
+	if (unlikely(!lock_stat))
+#endif
+#ifdef CONFIG_PROVE_LOCKING
+		if (unlikely(!prove_locking))
+#endif
+			return;
+
 	if (unlikely(current->lockdep_recursion))
 		return;
 

@@ -2475,6 +2739,14 @@ void lock_release(struct lockdep_map *lo
 {
 	unsigned long flags;
 
+#ifdef CONFIG_LOCK_STAT
+	if (unlikely(!lock_stat))
+#endif
+#ifdef CONFIG_PROVE_LOCKING
+		if (unlikely(!prove_locking))
+#endif
+			return;
+
 	if (unlikely(current->lockdep_recursion))
 		return;
 

@@ -2488,6 +2760,46 @@ void lock_release(struct lockdep_map *lo
 
 EXPORT_SYMBOL_GPL(lock_release);
 
+#ifdef CONFIG_LOCK_STAT
+void lock_contended(struct lockdep_map *lock, unsigned long ip)
+{
+	unsigned long flags;
+
+	if (unlikely(!lock_stat))
+		return;
+
+	if (unlikely(current->lockdep_recursion))
+		return;
+
+	raw_local_irq_save(flags);
+	check_flags(flags);
+	current->lockdep_recursion = 1;
+	__lock_contended(lock, ip);
+	current->lockdep_recursion = 0;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(lock_contended);
+
+void lock_acquired(struct lockdep_map *lock)
+{
+	unsigned long flags;
+
+	if (unlikely(!lock_stat))
+		return;
+
+	if (unlikely(current->lockdep_recursion))
+		return;
+
+	raw_local_irq_save(flags);
+	check_flags(flags);
+	current->lockdep_recursion = 1;
+	__lock_acquired(lock);
+	current->lockdep_recursion = 0;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(lock_acquired);
+#endif
+
 /*
  * Used by the testsuite, sanitize the validator state
  * after a simulated failure:

70 lines not on this page · raw message

Index: linux-2.6-git/kernel/sysctl.c
===================================================================
@@ -164,6 +164,14 @@ int sysctl_legacy_va_layout;
 #endif
 
 
+#ifdef CONFIG_PROVE_LOCKING
+extern int prove_locking;
+#endif
+
+#ifdef CONFIG_LOCK_STAT
+extern int lock_stat;
+#endif
+
 /* The default sysctl tables: */
 
 static ctl_table root_table[] = {

@@ -683,6 +691,26 @@ static ctl_table kern_table[] = {
 		.proc_handler	= &proc_dostring,
 		.strategy	= &sysctl_string,
 	},
+#ifdef CONFIG_PROVE_LOCKING
+	{
+		.ctl_name	= KERN_PROVE_LOCKING,
+		.procname	= "prove_locking",
+		.data		= &prove_locking,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+#ifdef CONFIG_LOCK_STAT
+	{
+		.ctl_name	= KERN_LOCK_STAT,
+		.procname	= "lock_stat",
+		.data		= &lock_stat,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
 
 	{ .ctl_name = 0 }
 };

Index: linux-2.6-git/include/linux/sysctl.h
===================================================================
@@ -166,6 +166,8 @@ enum
 	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
 	KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */
 	KERN_POWEROFF_CMD=77,	/* string: poweroff command line */
+	KERN_PROVE_LOCKING=78, /* int: enable lock dependancy checking */
+	KERN_LOCK_STAT=79, /* int: enable lock statistics */
 };
 
 

Index: linux-2.6-git/kernel/lockdep_proc.c
===================================================================
@@ -15,6 +15,10 @@
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/debug_locks.h>
+#include <linux/vmalloc.h>
+#include <linux/sort.h>
+#include <asm/uaccess.h>
+#include <asm/div64.h>
 
 #include "lockdep_internals.h"
 

@@ -342,6 +346,262 @@ static const struct file_operations proc
 	.release	= seq_release,
 };
 
+#ifdef CONFIG_LOCK_STAT
+
+struct lock_stat_data {
+	struct lock_class *class;
+	struct lock_class_stats stats;
+};
+
+struct lock_stat_seq {
+	struct lock_stat_data *iter;
+	struct lock_stat_data *iter_end;
+	struct lock_stat_data stats[MAX_LOCKDEP_KEYS];
+};
+
+/*
+ * sort on absolute number of contentions
+ */
+int lock_stat_cmp(const void *l, const void *r)
+{
+	const struct lock_stat_data *dl = l, *dr = r;
+	unsigned long nl, nr;
+
+	nl = dl->stats.read_waittime.nr + dl->stats.write_waittime.nr;
+	nr = dr->stats.read_waittime.nr + dr->stats.write_waittime.nr;
+
+	return nr - nl;
+}
+
+static void seq_line(struct seq_file *m, char c, int offset, int length)
+{
+	int i;
+
+	for (i = 0; i < offset; i++)
+		seq_puts(m, " ");
+	for (i = 0; i < length; i++)
+		seq_printf(m, "%c", c);
+	seq_puts(m, "\n");
+}
+
+static void snprint_time(char *buf, size_t bufsiz, unsigned long long nr)
+{
+	unsigned long rem;
+
+	rem = do_div(nr, 1000);
+	snprintf(buf, bufsiz, "%llu.%02d", nr, ((int)rem+5)/10);
+}
+
+static void seq_time(struct seq_file *m, unsigned long long time)
+{
+	char num[15];
+
+	snprint_time(num, sizeof(num), time);
+	seq_printf(m, " %14s", num);
+}
+
+static void seq_lock_time(struct seq_file *m, struct lock_time *lt)
+{
+	seq_printf(m, "%14lu", lt->nr);
+	seq_time(m, lt->min);
+	seq_time(m, lt->max);
+	seq_time(m, lt->total);
+}
+
+static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
+{
+	char name[39];
+	struct lock_class *class;
+	struct lock_class_stats *stats;
+	int i, namelen;
+
+	class = data->class;
+	stats = &data->stats;
+
+	snprintf(name, 38, "%s", class->name);
+	namelen = strlen(name);
+
+	if (stats->write_holdtime.nr) {
+		if (stats->read_holdtime.nr)
+			seq_printf(m, "%38s-W:", name);
+		else
+			seq_printf(m, "%40s:", name);
+
+		seq_lock_time(m, &stats->write_waittime);
+		seq_puts(m, " ");
+		seq_lock_time(m, &stats->write_holdtime);
+		seq_puts(m, "\n");
+	}
+
+	if (stats->read_holdtime.nr) {
+		seq_printf(m, "%38s-R:", name);
+		seq_lock_time(m, &stats->read_waittime);
+		seq_puts(m, " ");
+		seq_lock_time(m, &stats->read_holdtime);
+		seq_puts(m, "\n");
+	}
+
+	if (stats->read_waittime.nr + stats->write_waittime.nr == 0)
+		return;
+
+	if (stats->read_holdtime.nr)
+		namelen += 2;
+
+	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
+		char sym[KSYM_SYMBOL_LEN];
+		char ip[32];
+
+		if (class->contention_point[i] == 0)
+			break;
+
+		if (!i)
+			seq_line(m, '-', 40-namelen, namelen);
+
+		sprint_symbol(sym, class->contention_point[i]);
+		snprintf(ip, sizeof(ip), "[<%p>]",
+				(void *)class->contention_point[i]);
+		seq_printf(m, "%40s %14lu %29s %s\n", name,
+				stats->contention_point[i],
+				ip, sym);
+	}
+	if (i) {
+		seq_puts(m, "\n");
+		seq_line(m, '.', 0, 40 + 1 + 8 * (14 + 1));
+		seq_puts(m, "\n");
+	}
+}
+
+static void seq_header(struct seq_file *m)
+{
+	seq_printf(m, "lock_stat version 0.1\n");
+	seq_line(m, '-', 0, 40 + 1 + 8 * (14 + 1));
+	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s\n",
+			"class name",
+			"contentions",
+			"waittime-min",
+			"waittime-max",
+			"waittime-total",
+			"acquisitions",
+			"holdtime-min",
+			"holdtime-max",
+			"holdtime-total");
+	seq_line(m, '-', 0, 40 + 1 + 8 * (14 + 1));
+	seq_printf(m, "\n");
+}
+
+static void *ls_start(struct seq_file *m, loff_t *pos)
+{
+	struct lock_stat_seq *data = m->private;
+
+	if (data->iter == data->stats)
+		seq_header(m);
+
+	return data->iter;
+}
+
+static void *ls_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct lock_stat_seq *data = m->private;
+
+	(*pos)++;
+
+	data->iter = v;
+	data->iter++;
+	if (data->iter == data->iter_end)
+		data->iter = NULL;
+
+	return data->iter;
+}
+
+static void ls_stop(struct seq_file *m, void *v)
+{
+}
+
+static int ls_show(struct seq_file *m, void *v)
+{
+	struct lock_stat_seq *data = m->private;
+
+	seq_stats(m, data->iter);
+	return 0;
+}
+
+static struct seq_operations lockstat_ops = {
+	.start	= ls_start,
+	.next	= ls_next,
+	.stop	= ls_stop,
+	.show	= ls_show,
+};
+
+static int lock_stat_open(struct inode *inode, struct file *file)
+{
+	int res;
+	struct lock_class *class;
+	struct lock_stat_seq *data = vmalloc(sizeof(struct lock_stat_seq));
+
+	if (!data)
+		return -ENOMEM;
+
+	res = seq_open(file, &lockstat_ops);
+	if (!res) {
+		struct lock_stat_data *iter = data->stats;
+		struct seq_file *m = file->private_data;
+
+		data->iter = iter;
+		list_for_each_entry(class, &all_lock_classes, lock_entry) {
+			iter->class = class;
+			iter->stats = lock_stats(class);
+			iter++;
+		}
+		data->iter_end = iter;
+
+		sort(data->stats, data->iter_end - data->iter,
+				sizeof(struct lock_stat_data),
+				lock_stat_cmp, NULL);
+
+		m->private = data;
+	} else
+		vfree(data);
+
+	return res;
+}
+
+ssize_t lock_stat_write(struct file *file, const char __user *buf,
+		size_t count, loff_t *ppos)
+{
+	struct lock_class *class;
+	char c;
+
+	if (count) {
+		if (get_user(c, buf))
+			return -EFAULT;
+
+		if (c != '0')
+			return count;
+
+		list_for_each_entry(class, &all_lock_classes, lock_entry)
+			clear_lock_stats(class);
+	}
+	return count;
+}
+
+static int lock_stat_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+
+	vfree(seq->private);
+	seq->private = NULL;
+	return seq_release(inode, file);
+}
+
+static const struct file_operations proc_lock_stat_operations = {
+	.open		= lock_stat_open,
+	.write		= lock_stat_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= lock_stat_release,
+};
+#endif /* CONFIG_LOCK_STAT */
+
 static int __init lockdep_proc_init(void)
 {
 	struct proc_dir_entry *entry;

@@ -354,6 +614,12 @@ static int __init lockdep_proc_init(void
 	if (entry)
 		entry->proc_fops = &proc_lockdep_stats_operations;
 
+#ifdef CONFIG_LOCK_STAT
+	entry = create_proc_entry("lock_stat", S_IRUSR, NULL);
+	if (entry)
+		entry->proc_fops = &proc_lock_stat_operations;
+#endif
+
 	return 0;
 }
 

Index: linux-2.6-git/kernel/mutex.c
===================================================================
@@ -139,6 +139,12 @@ __mutex_lock_common(struct mutex *lock, 
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
+	old_val = atomic_xchg(&lock->count, -1);
+	if (old_val == 1)
+		goto done;
+
+	lock_contended(&lock->dep_map, _RET_IP_);
+
 	for (;;) {
 		/*
 		 * Lets try to take the lock again - this is needed even if

@@ -174,6 +180,8 @@ __mutex_lock_common(struct mutex *lock, 
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 
+	lock_acquired(&lock->dep_map);
+done:
 	/* got the lock - rejoice! */
 	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
 	debug_mutex_set_owner(lock, task_thread_info(task));

Index: linux-2.6-git/kernel/rwsem.c
===================================================================
@@ -20,7 +20,7 @@ void down_read(struct rw_semaphore *sem)
 	might_sleep();
 	rwsem_acquire_read(&sem->dep_map, 0, 0, _RET_IP_);
 
-	__down_read(sem);
+	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
 }
 
 EXPORT_SYMBOL(down_read);

@@ -47,7 +47,7 @@ void down_write(struct rw_semaphore *sem
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
 
-	__down_write(sem);
+	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
 }
 
 EXPORT_SYMBOL(down_write);

@@ -111,7 +111,7 @@ void down_read_nested(struct rw_semaphor
 	might_sleep();
 	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
 
-	__down_read(sem);
+	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
 }
 
 EXPORT_SYMBOL(down_read_nested);

@@ -130,7 +130,7 @@ void down_write_nested(struct rw_semapho
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
 
-	__down_write_nested(sem, subclass);
+	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
 }
 
 EXPORT_SYMBOL(down_write_nested);

Index: linux-2.6-git/kernel/spinlock.c
===================================================================
@@ -72,7 +72,7 @@ void __lockfunc _read_lock(rwlock_t *loc
 {
 	preempt_disable();
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_read_lock(lock);
+	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
 }
 EXPORT_SYMBOL(_read_lock);
 

@@ -89,7 +89,7 @@ unsigned long __lockfunc _spin_lock_irqs
 	 * that interrupts are not re-enabled during lock-acquire:
 	 */
 #ifdef CONFIG_LOCKDEP
-	_raw_spin_lock(lock);
+	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 #else
 	_raw_spin_lock_flags(lock, &flags);
 #endif

@@ -102,7 +102,7 @@ void __lockfunc _spin_lock_irq(spinlock_
 	local_irq_disable();
 	preempt_disable();
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_spin_lock(lock);
+	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 }
 EXPORT_SYMBOL(_spin_lock_irq);
 

@@ -111,7 +111,7 @@ void __lockfunc _spin_lock_bh(spinlock_t
 	local_bh_disable();
 	preempt_disable();
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_spin_lock(lock);
+	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 }
 EXPORT_SYMBOL(_spin_lock_bh);
 

@@ -122,7 +122,7 @@ unsigned long __lockfunc _read_lock_irqs
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_read_lock(lock);
+	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
 	return flags;
 }
 EXPORT_SYMBOL(_read_lock_irqsave);

@@ -132,7 +132,7 @@ void __lockfunc _read_lock_irq(rwlock_t 
 	local_irq_disable();
 	preempt_disable();
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_read_lock(lock);
+	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
 }
 EXPORT_SYMBOL(_read_lock_irq);
 

@@ -141,7 +141,7 @@ void __lockfunc _read_lock_bh(rwlock_t *
 	local_bh_disable();
 	preempt_disable();
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_read_lock(lock);
+	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
 }
 EXPORT_SYMBOL(_read_lock_bh);
 

@@ -152,7 +152,7 @@ unsigned long __lockfunc _write_lock_irq
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_write_lock(lock);
+	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
 	return flags;
 }
 EXPORT_SYMBOL(_write_lock_irqsave);

@@ -162,7 +162,7 @@ void __lockfunc _write_lock_irq(rwlock_t
 	local_irq_disable();
 	preempt_disable();
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_write_lock(lock);
+	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
 }
 EXPORT_SYMBOL(_write_lock_irq);
 

@@ -171,7 +171,7 @@ void __lockfunc _write_lock_bh(rwlock_t 
 	local_bh_disable();
 	preempt_disable();
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_write_lock(lock);
+	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
 }
 EXPORT_SYMBOL(_write_lock_bh);
 

@@ -179,7 +179,7 @@ void __lockfunc _spin_lock(spinlock_t *l
 {
 	preempt_disable();
 	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_spin_lock(lock);
+	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 }
 
 EXPORT_SYMBOL(_spin_lock);

@@ -188,7 +188,7 @@ void __lockfunc _write_lock(rwlock_t *lo
 {
 	preempt_disable();
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	_raw_write_lock(lock);
+	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
 }
 
 EXPORT_SYMBOL(_write_lock);

@@ -289,7 +289,7 @@ void __lockfunc _spin_lock_nested(spinlo
 {
 	preempt_disable();
 	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-	_raw_spin_lock(lock);
+	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 }
 
 EXPORT_SYMBOL(_spin_lock_nested);

@@ -306,7 +306,7 @@ unsigned long __lockfunc _spin_lock_irqs
 	 * that interrupts are not re-enabled during lock-acquire:
 	 */
 #ifdef CONFIG_LOCKDEP
-	_raw_spin_lock(lock);
+	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
 #else
 	_raw_spin_lock_flags(lock, &flags);
 #endif