optimize spin lock not to dirty cache line while spinning
diff --git a/src/thread/pthread_spin_lock.c b/src/thread/pthread_spin_lock.c
index df575f0..0462e0f 100644
--- a/src/thread/pthread_spin_lock.c
+++ b/src/thread/pthread_spin_lock.c
@@ -2,6 +2,6 @@
 
 int pthread_spin_lock(pthread_spinlock_t *s)
 {
-	while (a_swap(s, 1)) a_spin();
+	while (*(volatile int *)s || a_cas(s, 0, 1)) a_spin();
 	return 0;
 }