[rtems commit] SMP: Optimize ticket lock implementation

[Sebastian Huber]

Module:    rtems
Branch:    master
Commit:    ba1ed5240b2f8c724a8efa8f652a8ba391fc92dd
Changeset: http://git.rtems.org/rtems/commit/?id=ba1ed5240b2f8c724a8efa8f652a8ba391fc92dd

Author:    Sebastian Huber <sebastian.huber at embedded-brains.de>
Date:      Fri Oct  2 07:59:24 2015 +0200

SMP: Optimize ticket lock implementation

This reverts the relevant part of commit
da06fe948c0878057e5f563ebd3dfe40c0f1b0d2.  The acquire/release order is
superfluous for the next ticket increment.  The mutual exclusion is
guaranteed by the acquire load from and release store to the next
serving atomic variable.

---

 cpukit/score/include/rtems/score/smplock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cpukit/score/include/rtems/score/smplock.h b/cpukit/score/include/rtems/score/smplock.h
index ccf6b59..f98f38a 100644
--- a/cpukit/score/include/rtems/score/smplock.h
+++ b/cpukit/score/include/rtems/score/smplock.h
@@ -277,7 +277,7 @@ static inline void _SMP_ticket_lock_Do_acquire(
 #endif
 
   my_ticket =
-    _Atomic_Fetch_add_uint( &lock->next_ticket, 1U, ATOMIC_ORDER_ACQ_REL );
+    _Atomic_Fetch_add_uint( &lock->next_ticket, 1U, ATOMIC_ORDER_RELAXED );
 
 #if defined( RTEMS_PROFILING )
   now_serving =