lockstat: contend with points

We currently only provide points that have to wait on contention, also
lists the points we have to wait for.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 41 insertions, 15 deletions

diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index dbda475b13b..234a9dccb4b 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -136,16 +136,16 @@ static inline struct lock_class *hlock_class(struct held_lock *hlock)
 #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)
+static int lock_point(unsigned long points[], 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;
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		if (points[i] == 0) {
+			points[i] = ip;
 			break;
 		}
-		if (class->contention_point[i] == ip)
+		if (points[i] == ip)
 			break;
 	}
 
@@ -185,6 +185,9 @@ struct lock_class_stats lock_stats(struct lock_class *class)
 		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
 			stats.contention_point[i] += pcs->contention_point[i];
 
+		for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
+			stats.contending_point[i] += pcs->contending_point[i];
+
 		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
 		lock_time_add(&pcs->write_waittime, &stats.write_waittime);
 
@@ -209,6 +212,7 @@ void clear_lock_stats(struct lock_class *class)
 		memset(cpu_stats, 0, sizeof(struct lock_class_stats));
 	}
 	memset(class->contention_point, 0, sizeof(class->contention_point));
+	memset(class->contending_point, 0, sizeof(class->contending_point));
 }
 
 static struct lock_class_stats *get_lock_stats(struct lock_class *class)
@@ -3001,7 +3005,7 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 	struct held_lock *hlock, *prev_hlock;
 	struct lock_class_stats *stats;
 	unsigned int depth;
-	int i, point;
+	int i, contention_point, contending_point;
 
 	depth = curr->lockdep_depth;
 	if (DEBUG_LOCKS_WARN_ON(!depth))
@@ -3025,18 +3029,22 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip)
 found_it:
 	hlock->waittime_stamp = sched_clock();
 
-	point = lock_contention_point(hlock_class(hlock), ip);
+	contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
+	contending_point = lock_point(hlock_class(hlock)->contending_point,
+				      lock->ip);
 
 	stats = get_lock_stats(hlock_class(hlock));
-	if (point < ARRAY_SIZE(stats->contention_point))
-		stats->contention_point[point]++;
+	if (contention_point < LOCKSTAT_POINTS)
+		stats->contention_point[contention_point]++;
+	if (contending_point < LOCKSTAT_POINTS)
+		stats->contending_point[contending_point]++;
 	if (lock->cpu != smp_processor_id())
 		stats->bounces[bounce_contended + !!hlock->read]++;
 	put_lock_stats(stats);
 }
 
 static void
-__lock_acquired(struct lockdep_map *lock)
+__lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
 	struct held_lock *hlock, *prev_hlock;
@@ -3085,6 +3093,7 @@ found_it:
 	put_lock_stats(stats);
 
 	lock->cpu = cpu;
+	lock->ip = ip;
 }
 
 void lock_contended(struct lockdep_map *lock, unsigned long ip)
@@ -3106,7 +3115,7 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 }
 EXPORT_SYMBOL_GPL(lock_contended);
 
-void lock_acquired(struct lockdep_map *lock)
+void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
@@ -3119,7 +3128,7 @@ void lock_acquired(struct lockdep_map *lock)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion = 1;
-	__lock_acquired(lock);
+	__lock_acquired(lock, ip);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c
index 8d3a6eba8d5..13716b81389 100644
--- a/kernel/lockdep_proc.c
+++ b/kernel/lockdep_proc.c
@@ -557,7 +557,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 	if (stats->read_holdtime.nr)
 		namelen += 2;
 
-	for (i = 0; i < ARRAY_SIZE(class->contention_point); i++) {
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
 		char sym[KSYM_SYMBOL_LEN];
 		char ip[32];
 
@@ -574,6 +574,23 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 				stats->contention_point[i],
 				ip, sym);
 	}
+	for (i = 0; i < LOCKSTAT_POINTS; i++) {
+		char sym[KSYM_SYMBOL_LEN];
+		char ip[32];
+
+		if (class->contending_point[i] == 0)
+			break;
+
+		if (!i)
+			seq_line(m, '-', 40-namelen, namelen);
+
+		sprint_symbol(sym, class->contending_point[i]);
+		snprintf(ip, sizeof(ip), "[<%p>]",
+				(void *)class->contending_point[i]);
+		seq_printf(m, "%40s %14lu %29s %s\n", name,
+				stats->contending_point[i],
+				ip, sym);
+	}
 	if (i) {
 		seq_puts(m, "\n");
 		seq_line(m, '.', 0, 40 + 1 + 10 * (14 + 1));
@@ -583,7 +600,7 @@ static void seq_stats(struct seq_file *m, struct lock_stat_data *data)
 
 static void seq_header(struct seq_file *m)
 {
-	seq_printf(m, "lock_stat version 0.2\n");
+	seq_printf(m, "lock_stat version 0.3\n");
 	seq_line(m, '-', 0, 40 + 1 + 10 * (14 + 1));
 	seq_printf(m, "%40s %14s %14s %14s %14s %14s %14s %14s %14s "
 			"%14s %14s\n",
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 12c779dc65d..39a3816b68d 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -184,7 +184,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	}
 
 done:
-	lock_acquired(&lock->dep_map);
+	lock_acquired(&lock->dep_map, ip);
 	/* got the lock - rejoice! */
 	mutex_remove_waiter(lock, &waiter, task_thread_info(task));
 	debug_mutex_set_owner(lock, task_thread_info(task));