Use __sync_lock_test_and_set() for spinlocks on ARM, if available.

Historically we've used the SWPB instruction for TAS() on ARM, but this
is deprecated and not available on ARMv6 and later.  Instead, make use
of a GCC builtin if available.  We'll still fall back to SWPB if not,
so as not to break existing ports using older GCC versions.

Eventually we might want to try using __sync_lock_test_and_set() on some
other architectures too, but for now that seems to present only risk and
not reward.

Back-patch to all supported versions, since people might want to use any
of them on more recent ARM chips.

Martin Pitt

2 files changed, 26 insertions, 2 deletions

diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 4fd7b4818ed..042451e6909 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -164,6 +164,9 @@
 /* Define to 1 if your compiler understands __FUNCTION__. */
 #undef HAVE_FUNCNAME__FUNCTION
 
+/* Define to 1 if you have __sync_lock_test_and_set(int *) and friends. */
+#undef HAVE_GCC_INT_ATOMICS
+
 /* Define to 1 if you have the `getaddrinfo' function. */
 #undef HAVE_GETADDRINFO
 
diff --git a/src/include/storage/s_lock.h b/src/include/storage/s_lock.h
index 534543eed31..97ccdbebf6e 100644
--- a/src/include/storage/s_lock.h
+++ b/src/include/storage/s_lock.h
@@ -252,13 +252,33 @@ tas(volatile slock_t *lock)
 #endif	 /* __ia64__ || __ia64 */
 
 
+/*
+ * On ARM, we use __sync_lock_test_and_set(int *, int) if available, and if
+ * not fall back on the SWPB instruction.  SWPB does not work on ARMv6 or
+ * later, so the compiler builtin is preferred if available.  Note also that
+ * the int-width variant of the builtin works on more chips than other widths.
+ */
 #if defined(__arm__) || defined(__arm)
 #define HAS_TEST_AND_SET
 
-typedef unsigned char slock_t;
-
 #define TAS(lock) tas(lock)
 
+#ifdef HAVE_GCC_INT_ATOMICS
+
+typedef int slock_t;
+
+static __inline__ int
+tas(volatile slock_t *lock)
+{
+	return __sync_lock_test_and_set(lock, 1);
+}
+
+#define S_UNLOCK(lock) __sync_lock_release(lock)
+
+#else /* !HAVE_GCC_INT_ATOMICS */
+
+typedef unsigned char slock_t;
+
 static __inline__ int
 tas(volatile slock_t *lock)
 {
@@ -272,6 +292,7 @@ tas(volatile slock_t *lock)
 	return (int) _res;
 }
 
+#endif	 /* HAVE_GCC_INT_ATOMICS */
 #endif	 /* __arm__ */