[PATCH v4 3/3] Optimize CAS in __pthread_mutex_lock_full [BZ #28537]

["H.J. Lu" <hjl.tools@gmail.com>]

1. Do an atomic load and skip CAS if compare may fail to reduce cache
line bouncing on contended locks.
2. Replace atomic_compare_and_exchange_bool_acq with
atomic_compare_and_exchange_val_acq to avoid the extra load.
---
 nptl/pthread_mutex_lock.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/nptl/pthread_mutex_lock.c b/nptl/pthread_mutex_lock.c
index 1126ecba95..9a18073f29 100644
--- a/nptl/pthread_mutex_lock.c
+++ b/nptl/pthread_mutex_lock.c
@@ -309,12 +309,17 @@ __pthread_mutex_lock_full (pthread_mutex_t *mutex)
 	     meantime.  */
 	  if ((oldval & FUTEX_WAITERS) == 0)
 	    {
-	      if (atomic_compare_and_exchange_bool_acq (&mutex->__data.__lock,
-							oldval | FUTEX_WAITERS,
-							oldval)
-		  != 0)
+	      int currval = atomic_load_relaxed (&mutex->__data.__lock);
+	      if (currval != oldval)
+		{
+		  oldval = currval;
+		  continue;
+		}
+	      int newval = atomic_compare_and_exchange_val_acq
+		(&mutex->__data.__lock, oldval | FUTEX_WAITERS, oldval);
+	      if (newval != oldval)
 		{
-		  oldval = mutex->__data.__lock;
+		  oldval = newval;
 		  continue;
 		}
 	      oldval |= FUTEX_WAITERS;
-- 
2.33.1