Use more of gcc's __sync_fetch_and_xxx builtin functions for atomic ops.

In addition to __sync_fetch_and_add, gcc offers __sync_fetch_and_sub,
__sync_fetch_and_and, and __sync_fetch_and_or, which correspond directly
to primitive atomic ops that we want.  Testing shows that in some cases
they generate better code than our generic implementations, so use them.

We've assumed that configure's test for __sync_val_compare_and_swap is
sufficient to allow assuming that __sync_fetch_and_add is available, so
make the same assumption for these functions.  Should that prove to be
wrong, we can add more configure tests.

Yura Sokolov, reviewed by Jesper Pedersen and myself

Discussion: https://postgr.es/m/7f65886daca545067f82bf2b463b218d@postgrespro.ru

1 files changed, 58 insertions, 0 deletions

diff --git a/src/include/port/atomics/generic-gcc.h b/src/include/port/atomics/generic-gcc.h
index 7efc0861e71..e6871646a7f 100644
--- a/src/include/port/atomics/generic-gcc.h
+++ b/src/include/port/atomics/generic-gcc.h
@@ -176,6 +176,8 @@ pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
 }
 #endif
 
+/* if we have 32-bit __sync_val_compare_and_swap, assume we have these too: */
+
 #if !defined(PG_HAVE_ATOMIC_FETCH_ADD_U32) && defined(HAVE_GCC__SYNC_INT32_CAS)
 #define PG_HAVE_ATOMIC_FETCH_ADD_U32
 static inline uint32
@@ -185,6 +187,33 @@ pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
 }
 #endif
 
+#if !defined(PG_HAVE_ATOMIC_FETCH_SUB_U32) && defined(HAVE_GCC__SYNC_INT32_CAS)
+#define PG_HAVE_ATOMIC_FETCH_SUB_U32
+static inline uint32
+pg_atomic_fetch_sub_u32_impl(volatile pg_atomic_uint32 *ptr, int32 sub_)
+{
+	return __sync_fetch_and_sub(&ptr->value, sub_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_AND_U32) && defined(HAVE_GCC__SYNC_INT32_CAS)
+#define PG_HAVE_ATOMIC_FETCH_AND_U32
+static inline uint32
+pg_atomic_fetch_and_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 and_)
+{
+	return __sync_fetch_and_and(&ptr->value, and_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_OR_U32) && defined(HAVE_GCC__SYNC_INT32_CAS)
+#define PG_HAVE_ATOMIC_FETCH_OR_U32
+static inline uint32
+pg_atomic_fetch_or_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 or_)
+{
+	return __sync_fetch_and_or(&ptr->value, or_);
+}
+#endif
+
 
 #if !defined(PG_DISABLE_64_BIT_ATOMICS)
 
@@ -214,6 +243,8 @@ pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
 }
 #endif
 
+/* if we have 64-bit __sync_val_compare_and_swap, assume we have these too: */
+
 #if !defined(PG_HAVE_ATOMIC_FETCH_ADD_U64) && defined(HAVE_GCC__SYNC_INT64_CAS)
 #define PG_HAVE_ATOMIC_FETCH_ADD_U64
 static inline uint64
@@ -223,6 +254,33 @@ pg_atomic_fetch_add_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
 }
 #endif
 
+#if !defined(PG_HAVE_ATOMIC_FETCH_SUB_U64) && defined(HAVE_GCC__SYNC_INT64_CAS)
+#define PG_HAVE_ATOMIC_FETCH_SUB_U64
+static inline uint64
+pg_atomic_fetch_sub_u64_impl(volatile pg_atomic_uint64 *ptr, int64 sub_)
+{
+	return __sync_fetch_and_sub(&ptr->value, sub_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_AND_U64) && defined(HAVE_GCC__SYNC_INT64_CAS)
+#define PG_HAVE_ATOMIC_FETCH_AND_U64
+static inline uint64
+pg_atomic_fetch_and_u64_impl(volatile pg_atomic_uint64 *ptr, uint64 and_)
+{
+	return __sync_fetch_and_and(&ptr->value, and_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_OR_U64) && defined(HAVE_GCC__SYNC_INT64_CAS)
+#define PG_HAVE_ATOMIC_FETCH_OR_U64
+static inline uint64
+pg_atomic_fetch_or_u64_impl(volatile pg_atomic_uint64 *ptr, uint64 or_)
+{
+	return __sync_fetch_and_or(&ptr->value, or_);
+}
+#endif
+
 #endif /* !defined(PG_DISABLE_64_BIT_ATOMICS) */
 
 #endif /* defined(HAVE_ATOMICS) */