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

diff --git a/configure b/configure
index 644329a5e2887b5f88215e19c8443c837fea51b9..d5ed340e978be149a1f47ecfa91b20069bde41b6 100755 (executable)
--- a/configure
+++ b/configure
@@ -20333,6 +20333,67 @@ fi
 done
 
 
+{ echo "$as_me:$LINENO: checking for builtin locking functions" >&5
+echo $ECHO_N "checking for builtin locking functions... $ECHO_C" >&6; }
+if test "${pgac_cv_gcc_int_atomics+set}" = set; then
+  echo $ECHO_N "(cached) $ECHO_C" >&6
+else
+  cat >conftest.$ac_ext <<_ACEOF
+/* confdefs.h.  */
+_ACEOF
+cat confdefs.h >>conftest.$ac_ext
+cat >>conftest.$ac_ext <<_ACEOF
+/* end confdefs.h.  */
+
+int
+main ()
+{
+int lock = 0;
+   __sync_lock_test_and_set(&lock, 1);
+   __sync_lock_release(&lock);
+  ;
+  return 0;
+}
+_ACEOF
+rm -f conftest.$ac_objext conftest$ac_exeext
+if { (ac_try="$ac_link"
+case "(($ac_try" in
+  *\"* | *\`* | *\\*) ac_try_echo=\$ac_try;;
+  *) ac_try_echo=$ac_try;;
+esac
+eval "echo \"\$as_me:$LINENO: $ac_try_echo\"") >&5
+  (eval "$ac_link") 2>conftest.er1
+  ac_status=$?
+  grep -v '^ *+' conftest.er1 >conftest.err
+  rm -f conftest.er1
+  cat conftest.err >&5
+  echo "$as_me:$LINENO: \$? = $ac_status" >&5
+  (exit $ac_status); } && {
+        test -z "$ac_c_werror_flag" ||
+        test ! -s conftest.err
+       } && test -s conftest$ac_exeext &&
+       $as_test_x conftest$ac_exeext; then
+  pgac_cv_gcc_int_atomics="yes"
+else
+  echo "$as_me: failed program was:" >&5
+sed 's/^/| /' conftest.$ac_ext >&5
+
+       pgac_cv_gcc_int_atomics="no"
+fi
+
+rm -f core conftest.err conftest.$ac_objext conftest_ipa8_conftest.oo \
+      conftest$ac_exeext conftest.$ac_ext
+fi
+{ echo "$as_me:$LINENO: result: $pgac_cv_gcc_int_atomics" >&5
+echo "${ECHO_T}$pgac_cv_gcc_int_atomics" >&6; }
+if test x"$pgac_cv_gcc_int_atomics" = x"yes"; then
+
+cat >>confdefs.h <<\_ACEOF
+#define HAVE_GCC_INT_ATOMICS 1
+_ACEOF
+
+fi
+
 
 #
 # Pthreads

diff --git a/configure.in b/configure.in
index e9df8f4f0d689d9cec04fb22c52c473c5b4d1ed5..73d248b71a9887ae996bf3c005d89d79276a5c74 100644 (file)
--- a/configure.in
+++ b/configure.in
@@ -1384,6 +1384,17 @@ AC_CHECK_FUNCS(atexit, [],
                [AC_CHECK_FUNCS(on_exit, [],
                [AC_MSG_ERROR([neither atexit() nor on_exit() found])])])
 
+AC_CACHE_CHECK([for builtin locking functions], pgac_cv_gcc_int_atomics,
+[AC_TRY_LINK([],
+  [int lock = 0;
+   __sync_lock_test_and_set(&lock, 1);
+   __sync_lock_release(&lock);],
+  [pgac_cv_gcc_int_atomics="yes"],
+  [pgac_cv_gcc_int_atomics="no"])])
+if test x"$pgac_cv_gcc_int_atomics" = x"yes"; then
+  AC_DEFINE(HAVE_GCC_INT_ATOMICS, 1, [Define to 1 if you have __sync_lock_test_and_set(int *) and friends.])
+fi
+
 
 #
 # Pthreads

diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 4fd7b4818eda63276d4d838caecd04887929a381..042451e690901d19dfc026160ae1af762f566458 100644 (file)
--- 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 534543eed31447d2fcf2b4ab37aeac4ff7d2798e..97ccdbebf6e3d62b68361d479c3b118b8d57ab4c 100644 (file)
--- 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__ */