s390/spinlock,rwlock: always to a load-and-test first

In case a lock is contended it is better to do a load-and-test first
before trying to get the lock with compare-and-swap. This helps to avoid
unnecessary cache invalidations of the cacheline for the lock if the
CPU has to wait for the lock. For an uncontended lock doing the
compare-and-swap directly is a bit better, if the CPU does not have the
cacheline in its cache yet the compare-and-swap will get it read-write
immediately while a load-and-test would get it read-only first.

Always to the load-and-test first to avoid the cacheline invalidations
for the contended case outweight the potential read-only to read-write
cacheline upgrade for the uncontended case.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/include/asm/spinlock.h

@@ -59,7 +59,9 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lp)
 
 static inline int arch_spin_trylock_once(arch_spinlock_t *lp)
 {
-	return _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL);
+	barrier();
+	return likely(arch_spin_value_unlocked(*lp) &&
+		      _raw_compare_and_swap(&lp->lock, 0, SPINLOCK_LOCKVAL));
 }
 
 static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp)
@@ -69,20 +71,20 @@ static inline int arch_spin_tryrelease_once(arch_spinlock_t *lp)
 
 static inline void arch_spin_lock(arch_spinlock_t *lp)
 {
-	if (unlikely(!arch_spin_trylock_once(lp)))
+	if (!arch_spin_trylock_once(lp))
 		arch_spin_lock_wait(lp);
 }
 
 static inline void arch_spin_lock_flags(arch_spinlock_t *lp,
 					unsigned long flags)
 {
-	if (unlikely(!arch_spin_trylock_once(lp)))
+	if (!arch_spin_trylock_once(lp))
 		arch_spin_lock_wait_flags(lp, flags);
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lp)
 {
-	if (unlikely(!arch_spin_trylock_once(lp)))
+	if (!arch_spin_trylock_once(lp))
 		return arch_spin_trylock_retry(lp);
 	return 1;
 }
@@ -128,19 +130,29 @@ extern void _raw_write_lock_wait(arch_rwlock_t *lp);
 extern void _raw_write_lock_wait_flags(arch_rwlock_t *lp, unsigned long flags);
 extern int _raw_write_trylock_retry(arch_rwlock_t *lp);
 
+static inline int arch_read_trylock_once(arch_rwlock_t *rw)
+{
+	unsigned int old = ACCESS_ONCE(rw->lock);
+	return likely((int) old >= 0 &&
+		      _raw_compare_and_swap(&rw->lock, old, old + 1));
+}
+
+static inline int arch_write_trylock_once(arch_rwlock_t *rw)
+{
+	unsigned int old = ACCESS_ONCE(rw->lock);
+	return likely(old == 0 &&
+		      _raw_compare_and_swap(&rw->lock, 0, 0x80000000));
+}
+
 static inline void arch_read_lock(arch_rwlock_t *rw)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (!_raw_compare_and_swap(&rw->lock, old, old + 1))
+	if (!arch_read_trylock_once(rw))
 		_raw_read_lock_wait(rw);
 }
 
 static inline void arch_read_lock_flags(arch_rwlock_t *rw, unsigned long flags)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (!_raw_compare_and_swap(&rw->lock, old, old + 1))
+	if (!arch_read_trylock_once(rw))
 		_raw_read_lock_wait_flags(rw, flags);
 }
 
@@ -155,13 +167,13 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 static inline void arch_write_lock(arch_rwlock_t *rw)
 {
-	if (unlikely(!_raw_compare_and_swap(&rw->lock, 0, 0x80000000)))
+	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait(rw);
 }
 
 static inline void arch_write_lock_flags(arch_rwlock_t *rw, unsigned long flags)
 {
-	if (unlikely(!_raw_compare_and_swap(&rw->lock, 0, 0x80000000)))
+	if (!arch_write_trylock_once(rw))
 		_raw_write_lock_wait_flags(rw, flags);
 }
 
@@ -172,18 +184,16 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
-	unsigned int old;
-	old = rw->lock & 0x7fffffffU;
-	if (likely(_raw_compare_and_swap(&rw->lock, old, old + 1)))
-		return 1;
-	return _raw_read_trylock_retry(rw);
+	if (!arch_read_trylock_once(rw))
+		return _raw_read_trylock_retry(rw);
+	return 1;
 }
 
 static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
-	if (likely(_raw_compare_and_swap(&rw->lock, 0, 0x80000000)))
-		return 1;
-	return _raw_write_trylock_retry(rw);
+	if (!arch_write_trylock_once(rw))
+		return _raw_write_trylock_retry(rw);
+	return 1;
 }
 
 #define arch_read_relax(lock)	cpu_relax()

arch/s390/lib/spinlock.c

@@ -100,12 +100,9 @@ int arch_spin_trylock_retry(arch_spinlock_t *lp)
 {
 	int count;
 
-	for (count = spin_retry; count > 0; count--) {
-		if (arch_spin_is_locked(lp))
-			continue;
+	for (count = spin_retry; count > 0; count--)
 		if (arch_spin_trylock_once(lp))
 			return 1;
-	}
 	return 0;
 }
 EXPORT_SYMBOL(arch_spin_trylock_retry);
@@ -120,9 +117,9 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 			smp_yield();
 			count = spin_retry;
 		}
-		if (!arch_read_can_lock(rw))
+		old = ACCESS_ONCE(rw->lock);
+		if ((int) old < 0)
 			continue;
-		old = rw->lock & 0x7fffffffU;
 		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
 			return;
 	}
@@ -140,9 +137,9 @@ void _raw_read_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
 			smp_yield();
 			count = spin_retry;
 		}
-		if (!arch_read_can_lock(rw))
+		old = ACCESS_ONCE(rw->lock);
+		if ((int) old < 0)
 			continue;
-		old = rw->lock & 0x7fffffffU;
 		local_irq_disable();
 		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
 			return;
@@ -156,9 +153,9 @@ int _raw_read_trylock_retry(arch_rwlock_t *rw)
 	int count = spin_retry;
 
 	while (count-- > 0) {
-		if (!arch_read_can_lock(rw))
+		old = ACCESS_ONCE(rw->lock);
+		if ((int) old < 0)
 			continue;
-		old = rw->lock & 0x7fffffffU;
 		if (_raw_compare_and_swap(&rw->lock, old, old + 1))
 			return 1;
 	}
@@ -168,6 +165,7 @@ EXPORT_SYMBOL(_raw_read_trylock_retry);
 
 void _raw_write_lock_wait(arch_rwlock_t *rw)
 {
+	unsigned int old;
 	int count = spin_retry;
 
 	while (1) {
@@ -175,7 +173,8 @@ void _raw_write_lock_wait(arch_rwlock_t *rw)
 			smp_yield();
 			count = spin_retry;
 		}
-		if (!arch_write_can_lock(rw))
+		old = ACCESS_ONCE(rw->lock);
+		if (old)
 			continue;
 		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
 			return;
@@ -185,6 +184,7 @@ EXPORT_SYMBOL(_raw_write_lock_wait);
 
 void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
 {
+	unsigned int old;
 	int count = spin_retry;
 
 	local_irq_restore(flags);
@@ -193,7 +193,8 @@ void _raw_write_lock_wait_flags(arch_rwlock_t *rw, unsigned long flags)
 			smp_yield();
 			count = spin_retry;
 		}
-		if (!arch_write_can_lock(rw))
+		old = ACCESS_ONCE(rw->lock);
+		if (old)
 			continue;
 		local_irq_disable();
 		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
@@ -204,10 +205,12 @@ EXPORT_SYMBOL(_raw_write_lock_wait_flags);
 
 int _raw_write_trylock_retry(arch_rwlock_t *rw)
 {
+	unsigned int old;
 	int count = spin_retry;
 
 	while (count-- > 0) {
-		if (!arch_write_can_lock(rw))
+		old = ACCESS_ONCE(rw->lock);
+		if (old)
 			continue;
 		if (_raw_compare_and_swap(&rw->lock, 0, 0x80000000))
 			return 1;