locking/qspinlock: Use _acquire/_release() versions of cmpxchg() & xchg()

This patch replaces the cmpxchg() and xchg() calls in the native
qspinlock code with the more relaxed _acquire or _release versions of
those calls to enable other architectures to adopt queued spinlocks
with less memory barrier performance overhead.

Signed-off-by: Waiman Long <Waiman.Long@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Douglas Hatch <doug.hatch@hpe.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Scott J Norton <scott.norton@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1447114167-47185-2-git-send-email-Waiman.Long@hpe.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/asm-generic/qspinlock.h

@@ -12,8 +12,9 @@
  * GNU General Public License for more details.
  *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <waiman.long@hp.com>
+ * Authors: Waiman Long <waiman.long@hpe.com>
  */
 #ifndef __ASM_GENERIC_QSPINLOCK_H
 #define __ASM_GENERIC_QSPINLOCK_H
@@ -62,7 +63,7 @@ static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
 	if (!atomic_read(&lock->val) &&
-	   (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+	   (atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0))
 		return 1;
 	return 0;
 }
@@ -77,7 +78,7 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock)
 {
 	u32 val;
 
-	val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+	val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL);
 	if (likely(val == 0))
 		return;
 	queued_spin_lock_slowpath(lock, val);
@@ -93,7 +94,7 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 	/*
 	 * smp_mb__before_atomic() in order to guarantee release semantics
 	 */
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_sub(_Q_LOCKED_VAL, &lock->val);
 }
 #endif

kernel/locking/qspinlock.c

@@ -14,8 +14,9 @@
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
  * (C) Copyright 2013-2014 Red Hat, Inc.
  * (C) Copyright 2015 Intel Corp.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <waiman.long@hp.com>
+ * Authors: Waiman Long <waiman.long@hpe.com>
  *          Peter Zijlstra <peterz@infradead.org>
  */
 
@@ -176,7 +177,12 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 {
 	struct __qspinlock *l = (void *)lock;
 
-	return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+	/*
+	 * Use release semantics to make sure that the MCS node is properly
+	 * initialized before changing the tail code.
+	 */
+	return (u32)xchg_release(&l->tail,
+				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
 }
 
 #else /* _Q_PENDING_BITS == 8 */
@@ -208,7 +214,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 
 	for (;;) {
 		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
-		old = atomic_cmpxchg(&lock->val, val, new);
+		/*
+		 * Use release semantics to make sure that the MCS node is
+		 * properly initialized before changing the tail code.
+		 */
+		old = atomic_cmpxchg_release(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -319,7 +329,11 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 		if (val == new)
 			new |= _Q_PENDING_VAL;
 
-		old = atomic_cmpxchg(&lock->val, val, new);
+		/*
+		 * Acquire semantic is required here as the function may
+		 * return immediately if the lock was free.
+		 */
+		old = atomic_cmpxchg_acquire(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -426,7 +440,12 @@ queue:
 			set_locked(lock);
 			break;
 		}
-		old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
+		/*
+		 * The smp_load_acquire() call above has provided the necessary
+		 * acquire semantics required for locking. At most two
+		 * iterations of this loop may be ran.
+		 */
+		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
 		if (old == val)
 			goto release;	/* No contention */