mutex: implement adaptive spinning

Change mutex contention behaviour such that it will sometimes busy wait on
acquisition - moving its behaviour closer to that of spinlocks.

This concept got ported to mainline from the -rt tree, where it was originally
implemented for rtmutexes by Steven Rostedt, based on work by Gregory Haskins.

Testing with Ingo's test-mutex application (http://lkml.org/lkml/2006/1/8/50)
gave a 345% boost for VFS scalability on my testbox:

 # ./test-mutex-shm V 16 10 | grep "^avg ops"
 avg ops/sec:               296604

 # ./test-mutex-shm V 16 10 | grep "^avg ops"
 avg ops/sec:               85870

The key criteria for the busy wait is that the lock owner has to be running on
a (different) cpu. The idea is that as long as the owner is running, there is a
fair chance it'll release the lock soon, and thus we'll be better off spinning
instead of blocking/scheduling.

Since regular mutexes (as opposed to rtmutexes) do not atomically track the
owner, we add the owner in a non-atomic fashion and deal with the races in
the slowpath.

Furthermore, to ease the testing of the performance impact of this new code,
there is means to disable this behaviour runtime (without having to reboot
the system), when scheduler debugging is enabled (CONFIG_SCHED_DEBUG=y),
by issuing the following command:

 # echo NO_OWNER_SPIN > /debug/sched_features

This command re-enables spinning again (this is also the default):

 # echo OWNER_SPIN > /debug/sched_features

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

2 files changed, 4 insertions, 2 deletions

diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 7a0e5c4f8072..3069ec7e0ab8 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -50,8 +50,10 @@ struct mutex {
         atomic_t                count;
         spinlock_t              wait_lock;
         struct list_head        wait_list;
-#ifdef CONFIG_DEBUG_MUTEXES
+#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
         struct thread_info      *owner;
+#endif
+#ifdef CONFIG_DEBUG_MUTEXES
         const char              *name;
         void                    *magic;
 #endif
@@ -68,7 +70,6 @@ struct mutex_waiter {
         struct list_head        list;
         struct task_struct      *task;
 #ifdef CONFIG_DEBUG_MUTEXES
-        struct mutex            *lock;
         void                    *magic;
 #endif
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9f0b372cfa6f..c34b137cd1e5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -330,6 +330,7 @@ extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void __schedule(void);
 asmlinkage void schedule(void);
+extern int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner);
 
 struct nsproxy;
 struct user_namespace;