minor optimization to pthread_spin_trylock

use CAS instead of swap since it's lighter for most archs, and keep
EBUSY in the lock value so that the old value obtained by CAS can be
used directly as the return value for pthread_spin_trylock.

src/thread/pthread_spin_lock.c

@@ -1,7 +1,8 @@
 #include "pthread_impl.h"
+#include <errno.h>
 
 int pthread_spin_lock(pthread_spinlock_t *s)
 {
-	while (*(volatile int *)s || a_cas(s, 0, 1)) a_spin();
+	while (*(volatile int *)s || a_cas(s, 0, EBUSY)) a_spin();
 	return 0;
 }

src/thread/pthread_spin_trylock.c

@@ -1,6 +1,7 @@
 #include "pthread_impl.h"
+#include <errno.h>
 
 int pthread_spin_trylock(pthread_spinlock_t *s)
 {
-	return -a_swap(s, 1) & EBUSY;
+	return a_cas(s, 0, EBUSY);
 }