[PATCH] sleep profiling

Implement prof=sleep profiling.  TASK_UNINTERRUPTIBLE sleeps will be taken
as a profile hit, and every millisecond spent sleeping causes a profile-hit
for the call site that initiated the sleep.

Sample readprofile output on i386:

   306 ps2_sendbyte                               1.3973
   432 call_usermodehelper_keys                   1.9548
   484 ps2_command                                0.6453
   790 __driver_attach                            4.7879
  1593 msleep                                    44.2500
  3976 sync_buffer                               64.1290
  4076 do_lookup                                 12.4648
  8587 sync_page                                122.6714
 20820 total                                      0.0067

(NOTE: architectures need to check whether get_wchan() can be called from
deep within the wakeup path.)

akpm: we need to mark more functions __sched.  lock_sock(), msleep(), others..

akpm: the contention in do_lookup() is a surprise.  Presumably doing disk
reads for directory contents while holding i_mutex.

[akpm@osdl.org: various fixes]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 23 insertions, 1 deletions

diff --git a/include/linux/profile.h b/include/linux/profile.h
index acce53fd38..5670b340c4 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -6,10 +6,15 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/cpumask.h>
+#include <linux/cache.h>
+
 #include <asm/errno.h>
 
+extern int prof_on __read_mostly;
+
 #define CPU_PROFILING   1
 #define SCHED_PROFILING 2
+#define SLEEP_PROFILING 3
 
 struct proc_dir_entry;
 struct pt_regs;
@@ -18,7 +23,24 @@ struct notifier_block;
 /* init basic kernel profiler */
 void __init profile_init(void);
 void profile_tick(int);
-void profile_hit(int, void *);
+
+/*
+ * Add multiple profiler hits to a given address:
+ */
+void profile_hits(int, void *ip, unsigned int nr_hits);
+
+/*
+ * Single profiler hit:
+ */
+static inline void profile_hit(int type, void *ip)
+{
+        /*
+         * Speedup for the common (no profiling enabled) case:
+         */
+        if (unlikely(prof_on == type))
+                profile_hits(type, ip, 1);
+}
+
 #ifdef CONFIG_PROC_FS
 void create_prof_cpu_mask(struct proc_dir_entry *);
 #else