lockstat: core infrastructure

Introduce the core lock statistics code.

Lock statistics provides lock wait-time and hold-time (as well as the count
of corresponding contention and acquisitions events). Also, the first few
call-sites that encounter contention are tracked.

Lock wait-time is the time spent waiting on the lock. This provides insight
into the locking scheme, that is, a heavily contended lock is indicative of
a too coarse locking scheme.

Lock hold-time is the duration the lock was held, this provides a reference for
the wait-time numbers, so they can be put into perspective.

  1)
    lock
  2)
    ... do stuff ..
    unlock
  3)

The time between 1 and 2 is the wait-time. The time between 2 and 3 is the
hold-time.

The lockdep held-lock tracking code is reused, because it already collects locks
into meaningful groups (classes), and because it is an existing infrastructure
for lock instrumentation.

Currently lockdep tracks lock acquisition with two hooks:

  lock()
    lock_acquire()
    _lock()

 ... code protected by lock ...

  unlock()
    lock_release()
    _unlock()

We need to extend this with two more hooks, in order to measure contention.

  lock_contended() - used to measure contention events
  lock_acquired()  - completion of the contention

These are then placed the following way:

  lock()
    lock_acquire()
    if (!_try_lock())
      lock_contended()
      _lock()
      lock_acquired()

 ... do locked stuff ...

  unlock()
    lock_release()
    _unlock()

(Note: the try_lock() 'trick' is used to avoid instrumenting all platform
       dependent lock primitive implementations.)

It is also possible to toggle the two lockdep features at runtime using:

  /proc/sys/kernel/prove_locking
  /proc/sys/kernel/lock_stat

(esp. turning off the O(n^2) prove_locking functionaliy can help)

[akpm@linux-foundation.org: build fixes]
[akpm@linux-foundation.org: nuke unneeded ifdefs]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Jason Baron <jbaron@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 14c937d..8f946f6 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -9,6 +9,7 @@
 #define __LINUX_LOCKDEP_H
 
 struct task_struct;
+struct lockdep_map;
 
 #ifdef CONFIG_LOCKDEP
 
@@ -114,8 +115,32 @@
 
 	const char			*name;
 	int				name_version;
+
+#ifdef CONFIG_LOCK_STAT
+	unsigned long			contention_point[4];
+#endif
 };
 
+#ifdef CONFIG_LOCK_STAT
+struct lock_time {
+	s64				min;
+	s64				max;
+	s64				total;
+	unsigned long			nr;
+};
+
+struct lock_class_stats {
+	unsigned long			contention_point[4];
+	struct lock_time		read_waittime;
+	struct lock_time		write_waittime;
+	struct lock_time		read_holdtime;
+	struct lock_time		write_holdtime;
+};
+
+struct lock_class_stats lock_stats(struct lock_class *class);
+void clear_lock_stats(struct lock_class *class);
+#endif
+
 /*
  * Map the lock object (the lock instance) to the lock-class object.
  * This is embedded into specific lock instances:
@@ -165,6 +190,10 @@
 	unsigned long			acquire_ip;
 	struct lockdep_map		*instance;
 
+#ifdef CONFIG_LOCK_STAT
+	u64 				waittime_stamp;
+	u64				holdtime_stamp;
+#endif
 	/*
 	 * The lock-stack is unified in that the lock chains of interrupt
 	 * contexts nest ontop of process context chains, but we 'separate'
@@ -281,6 +310,30 @@
 
 #endif /* !LOCKDEP */
 
+#ifdef CONFIG_LOCK_STAT
+
+extern void lock_contended(struct lockdep_map *lock, unsigned long ip);
+extern void lock_acquired(struct lockdep_map *lock);
+
+#define LOCK_CONTENDED(_lock, try, lock)			\
+do {								\
+	if (!try(_lock)) {					\
+		lock_contended(&(_lock)->dep_map, _RET_IP_);	\
+		lock(_lock);					\
+		lock_acquired(&(_lock)->dep_map);		\
+	}							\
+} while (0)
+
+#else /* CONFIG_LOCK_STAT */
+
+#define lock_contended(lockdep_map, ip) do {} while (0)
+#define lock_acquired(lockdep_map) do {} while (0)
+
+#define LOCK_CONTENDED(_lock, try, lock) \
+	lock(_lock)
+
+#endif /* CONFIG_LOCK_STAT */
+
 #if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_GENERIC_HARDIRQS)
 extern void early_init_irq_lock_class(void);
 #else