diff --git a/config/c-compiler.m4 b/config/c-compiler.m4
index 802f5539d34..2cf74bbb2ae 100644
--- a/config/c-compiler.m4
+++ b/config/c-compiler.m4
@@ -300,3 +300,101 @@ if test x"$Ac_cachevar" = x"yes"; then
fi
undefine([Ac_cachevar])dnl
])# PGAC_PROG_CC_LDFLAGS_OPT
+
+# PGAC_HAVE_GCC__SYNC_CHAR_TAS
+# -------------------------
+# Check if the C compiler understands __sync_lock_test_and_set(char),
+# and define HAVE_GCC__SYNC_CHAR_TAS
+#
+# NB: There are platforms where test_and_set is available but compare_and_swap
+# is not, so test this separately.
+# NB: Some platforms only do 32bit tas, others only do 8bit tas. Test both.
+AC_DEFUN([PGAC_HAVE_GCC__SYNC_CHAR_TAS],
+[AC_CACHE_CHECK(for builtin __sync char locking functions, pgac_cv_gcc_sync_char_tas,
+[AC_TRY_LINK([],
+ [char lock = 0;
+ __sync_lock_test_and_set(&lock, 1);
+ __sync_lock_release(&lock);],
+ [pgac_cv_gcc_sync_char_tas="yes"],
+ [pgac_cv_gcc_sync_char_tas="no"])])
+if test x"$pgac_cv_gcc_sync_char_tas" = x"yes"; then
+ AC_DEFINE(HAVE_GCC__SYNC_CHAR_TAS, 1, [Define to 1 if you have __sync_lock_test_and_set(char *) and friends.])
+fi])# PGAC_HAVE_GCC__SYNC_CHAR_TAS
+
+# PGAC_HAVE_GCC__SYNC_INT32_TAS
+# -------------------------
+# Check if the C compiler understands __sync_lock_test_and_set(),
+# and define HAVE_GCC__SYNC_INT32_TAS
+AC_DEFUN([PGAC_HAVE_GCC__SYNC_INT32_TAS],
+[AC_CACHE_CHECK(for builtin __sync int32 locking functions, pgac_cv_gcc_sync_int32_tas,
+[AC_TRY_LINK([],
+ [int lock = 0;
+ __sync_lock_test_and_set(&lock, 1);
+ __sync_lock_release(&lock);],
+ [pgac_cv_gcc_sync_int32_tas="yes"],
+ [pgac_cv_gcc_sync_int32_tas="no"])])
+if test x"$pgac_cv_gcc_sync_int32_tas" = x"yes"; then
+ AC_DEFINE(HAVE_GCC__SYNC_INT32_TAS, 1, [Define to 1 if you have __sync_lock_test_and_set(int *) and friends.])
+fi])# PGAC_HAVE_GCC__SYNC_INT32_TAS
+
+# PGAC_HAVE_GCC__SYNC_INT32_CAS
+# -------------------------
+# Check if the C compiler understands __sync_compare_and_swap() for 32bit
+# types, and define HAVE_GCC__SYNC_INT32_CAS if so.
+AC_DEFUN([PGAC_HAVE_GCC__SYNC_INT32_CAS],
+[AC_CACHE_CHECK(for builtin __sync int32 atomic operations, pgac_cv_gcc_sync_int32_cas,
+[AC_TRY_LINK([],
+ [int val = 0;
+ __sync_val_compare_and_swap(&val, 0, 37);],
+ [pgac_cv_gcc_sync_int32_cas="yes"],
+ [pgac_cv_gcc_sync_int32_cas="no"])])
+if test x"$pgac_cv_gcc_sync_int32_cas" = x"yes"; then
+ AC_DEFINE(HAVE_GCC__SYNC_INT32_CAS, 1, [Define to 1 if you have __sync_compare_and_swap(int *, int, int).])
+fi])# PGAC_HAVE_GCC__SYNC_INT32_CAS
+
+# PGAC_HAVE_GCC__SYNC_INT64_CAS
+# -------------------------
+# Check if the C compiler understands __sync_compare_and_swap() for 64bit
+# types, and define HAVE_GCC__SYNC_INT64_CAS if so.
+AC_DEFUN([PGAC_HAVE_GCC__SYNC_INT64_CAS],
+[AC_CACHE_CHECK(for builtin __sync int64 atomic operations, pgac_cv_gcc_sync_int64_cas,
+[AC_TRY_LINK([],
+ [PG_INT64_TYPE lock = 0;
+ __sync_val_compare_and_swap(&lock, 0, (PG_INT64_TYPE) 37);],
+ [pgac_cv_gcc_sync_int64_cas="yes"],
+ [pgac_cv_gcc_sync_int64_cas="no"])])
+if test x"$pgac_cv_gcc_sync_int64_cas" = x"yes"; then
+ AC_DEFINE(HAVE_GCC__SYNC_INT64_CAS, 1, [Define to 1 if you have __sync_compare_and_swap(int64 *, int64, int64).])
+fi])# PGAC_HAVE_GCC__SYNC_INT64_CAS
+
+# PGAC_HAVE_GCC__ATOMIC_INT32_CAS
+# -------------------------
+# Check if the C compiler understands __atomic_compare_exchange_n() for 32bit
+# types, and define HAVE_GCC__ATOMIC_INT32_CAS if so.
+AC_DEFUN([PGAC_HAVE_GCC__ATOMIC_INT32_CAS],
+[AC_CACHE_CHECK(for builtin __atomic int32 atomic operations, pgac_cv_gcc_atomic_int32_cas,
+[AC_TRY_LINK([],
+ [int val = 0;
+ int expect = 0;
+ __atomic_compare_exchange_n(&val, &expect, 37, 0, __ATOMIC_SEQ_CST, __ATOMIC_RELAXED);],
+ [pgac_cv_gcc_atomic_int32_cas="yes"],
+ [pgac_cv_gcc_atomic_int32_cas="no"])])
+if test x"$pgac_cv_gcc_atomic_int32_cas" = x"yes"; then
+ AC_DEFINE(HAVE_GCC__ATOMIC_INT32_CAS, 1, [Define to 1 if you have __atomic_compare_exchange_n(int *, int *, int).])
+fi])# PGAC_HAVE_GCC__ATOMIC_INT32_CAS
+
+# PGAC_HAVE_GCC__ATOMIC_INT64_CAS
+# -------------------------
+# Check if the C compiler understands __atomic_compare_exchange_n() for 64bit
+# types, and define HAVE_GCC__ATOMIC_INT64_CAS if so.
+AC_DEFUN([PGAC_HAVE_GCC__ATOMIC_INT64_CAS],
+[AC_CACHE_CHECK(for builtin __atomic int64 atomic operations, pgac_cv_gcc_atomic_int64_cas,
+[AC_TRY_LINK([],
+ [PG_INT64_TYPE val = 0;
+ PG_INT64_TYPE expect = 0;
+ __atomic_compare_exchange_n(&val, &expect, 37, 0, __ATOMIC_SEQ_CST, __ATOMIC_RELAXED);],
+ [pgac_cv_gcc_atomic_int64_cas="yes"],
+ [pgac_cv_gcc_atomic_int64_cas="no"])])
+if test x"$pgac_cv_gcc_atomic_int64_cas" = x"yes"; then
+ AC_DEFINE(HAVE_GCC__ATOMIC_INT64_CAS, 1, [Define to 1 if you have __atomic_compare_exchange_n(int64 *, int *, int64).])
+fi])# PGAC_HAVE_GCC__ATOMIC_INT64_CAS
diff --git a/configure b/configure
index dac8e49084e..f0580ceb5e5 100755
--- a/configure
+++ b/configure
@@ -802,6 +802,7 @@ enable_nls
with_pgport
enable_rpath
enable_spinlocks
+enable_atomics
enable_debug
enable_profiling
enable_coverage
@@ -1470,6 +1471,7 @@ Optional Features:
--disable-rpath do not embed shared library search path in
executables
--disable-spinlocks do not use spinlocks
+ --disable-atomics do not use atomic operations
--enable-debug build with debugging symbols (-g)
--enable-profiling build with profiling enabled
--enable-coverage build with coverage testing instrumentation
@@ -3145,6 +3147,33 @@ fi
+#
+# Atomic operations
+#
+
+
+# Check whether --enable-atomics was given.
+if test "${enable_atomics+set}" = set; then :
+ enableval=$enable_atomics;
+ case $enableval in
+ yes)
+ :
+ ;;
+ no)
+ :
+ ;;
+ *)
+ as_fn_error $? "no argument expected for --enable-atomics option" "$LINENO" 5
+ ;;
+ esac
+
+else
+ enable_atomics=yes
+
+fi
+
+
+
#
# --enable-debug adds -g to compiler flags
#
@@ -8349,6 +8378,17 @@ $as_echo "$as_me: WARNING:
*** Not using spinlocks will cause poor performance." >&2;}
fi
+if test "$enable_atomics" = yes; then
+
+$as_echo "#define HAVE_ATOMICS 1" >>confdefs.h
+
+else
+ { $as_echo "$as_me:${as_lineno-$LINENO}: WARNING:
+*** Not using atomic operations will cause poor performance." >&5
+$as_echo "$as_me: WARNING:
+*** Not using atomic operations will cause poor performance." >&2;}
+fi
+
if test "$with_gssapi" = yes ; then
if test "$PORTNAME" != "win32"; then
{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for library containing gss_init_sec_context" >&5
@@ -9123,7 +9163,7 @@ fi
done
-for ac_header in crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h poll.h pwd.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h
+for ac_header in atomic.h crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h poll.h pwd.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h
do :
as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
ac_fn_c_check_header_mongrel "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default"
@@ -12154,40 +12194,6 @@ fi
done
-{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for builtin locking functions" >&5
-$as_echo_n "checking for builtin locking functions... " >&6; }
-if ${pgac_cv_gcc_int_atomics+:} false; then :
- $as_echo_n "(cached) " >&6
-else
- cat confdefs.h - <<_ACEOF >conftest.$ac_ext
-/* end confdefs.h. */
-
-int
-main ()
-{
-int lock = 0;
- __sync_lock_test_and_set(&lock, 1);
- __sync_lock_release(&lock);
- ;
- return 0;
-}
-_ACEOF
-if ac_fn_c_try_link "$LINENO"; then :
- pgac_cv_gcc_int_atomics="yes"
-else
- pgac_cv_gcc_int_atomics="no"
-fi
-rm -f core conftest.err conftest.$ac_objext \
- conftest$ac_exeext conftest.$ac_ext
-fi
-{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_gcc_int_atomics" >&5
-$as_echo "$pgac_cv_gcc_int_atomics" >&6; }
-if test x"$pgac_cv_gcc_int_atomics" = x"yes"; then
-
-$as_echo "#define HAVE_GCC_INT_ATOMICS 1" >>confdefs.h
-
-fi
-
# Lastly, restore full LIBS list and check for readline/libedit symbols
LIBS="$LIBS_including_readline"
@@ -13711,6 +13717,204 @@ _ACEOF
fi
+# Check for various atomic operations now that we have checked how to declare
+# 64bit integers.
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for builtin __sync char locking functions" >&5
+$as_echo_n "checking for builtin __sync char locking functions... " >&6; }
+if ${pgac_cv_gcc_sync_char_tas+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+
+int
+main ()
+{
+char lock = 0;
+ __sync_lock_test_and_set(&lock, 1);
+ __sync_lock_release(&lock);
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+ pgac_cv_gcc_sync_char_tas="yes"
+else
+ pgac_cv_gcc_sync_char_tas="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+ conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_gcc_sync_char_tas" >&5
+$as_echo "$pgac_cv_gcc_sync_char_tas" >&6; }
+if test x"$pgac_cv_gcc_sync_char_tas" = x"yes"; then
+
+$as_echo "#define HAVE_GCC__SYNC_CHAR_TAS 1" >>confdefs.h
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for builtin __sync int32 locking functions" >&5
+$as_echo_n "checking for builtin __sync int32 locking functions... " >&6; }
+if ${pgac_cv_gcc_sync_int32_tas+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+
+int
+main ()
+{
+int lock = 0;
+ __sync_lock_test_and_set(&lock, 1);
+ __sync_lock_release(&lock);
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+ pgac_cv_gcc_sync_int32_tas="yes"
+else
+ pgac_cv_gcc_sync_int32_tas="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+ conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_gcc_sync_int32_tas" >&5
+$as_echo "$pgac_cv_gcc_sync_int32_tas" >&6; }
+if test x"$pgac_cv_gcc_sync_int32_tas" = x"yes"; then
+
+$as_echo "#define HAVE_GCC__SYNC_INT32_TAS 1" >>confdefs.h
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for builtin __sync int32 atomic operations" >&5
+$as_echo_n "checking for builtin __sync int32 atomic operations... " >&6; }
+if ${pgac_cv_gcc_sync_int32_cas+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+
+int
+main ()
+{
+int val = 0;
+ __sync_val_compare_and_swap(&val, 0, 37);
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+ pgac_cv_gcc_sync_int32_cas="yes"
+else
+ pgac_cv_gcc_sync_int32_cas="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+ conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_gcc_sync_int32_cas" >&5
+$as_echo "$pgac_cv_gcc_sync_int32_cas" >&6; }
+if test x"$pgac_cv_gcc_sync_int32_cas" = x"yes"; then
+
+$as_echo "#define HAVE_GCC__SYNC_INT32_CAS 1" >>confdefs.h
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for builtin __sync int64 atomic operations" >&5
+$as_echo_n "checking for builtin __sync int64 atomic operations... " >&6; }
+if ${pgac_cv_gcc_sync_int64_cas+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+
+int
+main ()
+{
+PG_INT64_TYPE lock = 0;
+ __sync_val_compare_and_swap(&lock, 0, (PG_INT64_TYPE) 37);
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+ pgac_cv_gcc_sync_int64_cas="yes"
+else
+ pgac_cv_gcc_sync_int64_cas="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+ conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_gcc_sync_int64_cas" >&5
+$as_echo "$pgac_cv_gcc_sync_int64_cas" >&6; }
+if test x"$pgac_cv_gcc_sync_int64_cas" = x"yes"; then
+
+$as_echo "#define HAVE_GCC__SYNC_INT64_CAS 1" >>confdefs.h
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for builtin __atomic int32 atomic operations" >&5
+$as_echo_n "checking for builtin __atomic int32 atomic operations... " >&6; }
+if ${pgac_cv_gcc_atomic_int32_cas+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+
+int
+main ()
+{
+int val = 0;
+ int expect = 0;
+ __atomic_compare_exchange_n(&val, &expect, 37, 0, __ATOMIC_SEQ_CST, __ATOMIC_RELAXED);
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+ pgac_cv_gcc_atomic_int32_cas="yes"
+else
+ pgac_cv_gcc_atomic_int32_cas="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+ conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_gcc_atomic_int32_cas" >&5
+$as_echo "$pgac_cv_gcc_atomic_int32_cas" >&6; }
+if test x"$pgac_cv_gcc_atomic_int32_cas" = x"yes"; then
+
+$as_echo "#define HAVE_GCC__ATOMIC_INT32_CAS 1" >>confdefs.h
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for builtin __atomic int64 atomic operations" >&5
+$as_echo_n "checking for builtin __atomic int64 atomic operations... " >&6; }
+if ${pgac_cv_gcc_atomic_int64_cas+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h. */
+
+int
+main ()
+{
+PG_INT64_TYPE val = 0;
+ PG_INT64_TYPE expect = 0;
+ __atomic_compare_exchange_n(&val, &expect, 37, 0, __ATOMIC_SEQ_CST, __ATOMIC_RELAXED);
+ ;
+ return 0;
+}
+_ACEOF
+if ac_fn_c_try_link "$LINENO"; then :
+ pgac_cv_gcc_atomic_int64_cas="yes"
+else
+ pgac_cv_gcc_atomic_int64_cas="no"
+fi
+rm -f core conftest.err conftest.$ac_objext \
+ conftest$ac_exeext conftest.$ac_ext
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $pgac_cv_gcc_atomic_int64_cas" >&5
+$as_echo "$pgac_cv_gcc_atomic_int64_cas" >&6; }
+if test x"$pgac_cv_gcc_atomic_int64_cas" = x"yes"; then
+
+$as_echo "#define HAVE_GCC__ATOMIC_INT64_CAS 1" >>confdefs.h
+
+fi
if test "$PORTNAME" != "win32"
then
diff --git a/configure.in b/configure.in
index 13922775390..527b0762053 100644
--- a/configure.in
+++ b/configure.in
@@ -178,6 +178,12 @@ AC_SUBST(enable_rpath)
PGAC_ARG_BOOL(enable, spinlocks, yes,
[do not use spinlocks])
+#
+# Atomic operations
+#
+PGAC_ARG_BOOL(enable, atomics, yes,
+ [do not use atomic operations])
+
#
# --enable-debug adds -g to compiler flags
#
@@ -936,6 +942,13 @@ else
*** Not using spinlocks will cause poor performance.])
fi
+if test "$enable_atomics" = yes; then
+ AC_DEFINE(HAVE_ATOMICS, 1, [Define to 1 if you want to use atomics if available.])
+else
+ AC_MSG_WARN([
+*** Not using atomic operations will cause poor performance.])
+fi
+
if test "$with_gssapi" = yes ; then
if test "$PORTNAME" != "win32"; then
AC_SEARCH_LIBS(gss_init_sec_context, [gssapi_krb5 gss 'gssapi -lkrb5 -lcrypto'], [],
@@ -1003,7 +1016,7 @@ AC_SUBST(UUID_LIBS)
##
dnl sys/socket.h is required by AC_FUNC_ACCEPT_ARGTYPES
-AC_CHECK_HEADERS([crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h poll.h pwd.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h])
+AC_CHECK_HEADERS([atomic.h crypt.h dld.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h poll.h pwd.h sys/ioctl.h sys/ipc.h sys/poll.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/socket.h sys/sockio.h sys/tas.h sys/time.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h])
# On BSD, test for net/if.h will fail unless sys/socket.h
# is included first.
@@ -1467,17 +1480,6 @@ fi
AC_CHECK_FUNCS([strtoll strtoq], [break])
AC_CHECK_FUNCS([strtoull strtouq], [break])
-AC_CACHE_CHECK([for builtin locking functions], pgac_cv_gcc_int_atomics,
-[AC_TRY_LINK([],
- [int lock = 0;
- __sync_lock_test_and_set(&lock, 1);
- __sync_lock_release(&lock);],
- [pgac_cv_gcc_int_atomics="yes"],
- [pgac_cv_gcc_int_atomics="no"])])
-if test x"$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
-
# Lastly, restore full LIBS list and check for readline/libedit symbols
LIBS="$LIBS_including_readline"
@@ -1746,6 +1748,14 @@ AC_CHECK_TYPES([int8, uint8, int64, uint64], [], [],
# C, but is missing on some old platforms.
AC_CHECK_TYPES(sig_atomic_t, [], [], [#include <signal.h>])
+# Check for various atomic operations now that we have checked how to declare
+# 64bit integers.
+PGAC_HAVE_GCC__SYNC_CHAR_TAS
+PGAC_HAVE_GCC__SYNC_INT32_TAS
+PGAC_HAVE_GCC__SYNC_INT32_CAS
+PGAC_HAVE_GCC__SYNC_INT64_CAS
+PGAC_HAVE_GCC__ATOMIC_INT32_CAS
+PGAC_HAVE_GCC__ATOMIC_INT64_CAS
if test "$PORTNAME" != "win32"
then
diff --git a/src/backend/main/main.c b/src/backend/main/main.c
index 413c9823c34..c51b391199c 100644
--- a/src/backend/main/main.c
+++ b/src/backend/main/main.c
@@ -30,6 +30,7 @@
#include "common/username.h"
#include "postmaster/postmaster.h"
#include "storage/barrier.h"
+#include "storage/s_lock.h"
#include "storage/spin.h"
#include "tcop/tcopprot.h"
#include "utils/help_config.h"
diff --git a/src/backend/port/Makefile b/src/backend/port/Makefile
index 15ea873a497..c6b1d20c55e 100644
--- a/src/backend/port/Makefile
+++ b/src/backend/port/Makefile
@@ -21,7 +21,7 @@ subdir = src/backend/port
top_builddir = ../../..
include $(top_builddir)/src/Makefile.global
-OBJS = dynloader.o pg_sema.o pg_shmem.o pg_latch.o $(TAS)
+OBJS = atomics.o dynloader.o pg_sema.o pg_shmem.o pg_latch.o $(TAS)
ifeq ($(PORTNAME), darwin)
SUBDIRS += darwin
diff --git a/src/backend/port/atomics.c b/src/backend/port/atomics.c
new file mode 100644
index 00000000000..32255b00675
--- /dev/null
+++ b/src/backend/port/atomics.c
@@ -0,0 +1,127 @@
+/*-------------------------------------------------------------------------
+ *
+ * atomics.c
+ * Non-Inline parts of the atomics implementation
+ *
+ * Portions Copyright (c) 2013-2014, PostgreSQL Global Development Group
+ *
+ *
+ * IDENTIFICATION
+ * src/backend/port/atomics.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+/*
+ * We want the functions below to be inline; but if the compiler doesn't
+ * support that, fall back on providing them as regular functions. See
+ * STATIC_IF_INLINE in c.h.
+ */
+#define ATOMICS_INCLUDE_DEFINITIONS
+
+#include "port/atomics.h"
+#include "storage/spin.h"
+
+#ifdef PG_HAVE_MEMORY_BARRIER_EMULATION
+void
+pg_spinlock_barrier(void)
+{
+ S_LOCK(&dummy_spinlock);
+ S_UNLOCK(&dummy_spinlock);
+}
+#endif
+
+
+#ifdef PG_HAVE_ATOMIC_FLAG_SIMULATION
+
+void
+pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ StaticAssertStmt(sizeof(ptr->sema) >= sizeof(slock_t),
+ "size mismatch of atomic_flag vs slock_t");
+
+#ifndef HAVE_SPINLOCKS
+ /*
+ * NB: If we're using semaphore based TAS emulation, be careful to use a
+ * separate set of semaphores. Otherwise we'd get in trouble if a atomic
+ * var would be manipulated while spinlock is held.
+ */
+ s_init_lock_sema((slock_t *) &ptr->sema, true);
+#else
+ SpinLockInit((slock_t *) &ptr->sema);
+#endif
+}
+
+bool
+pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ return TAS((slock_t *) &ptr->sema);
+}
+
+void
+pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ S_UNLOCK((slock_t *) &ptr->sema);
+}
+
+#endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */
+
+#ifdef PG_HAVE_ATOMIC_U32_SIMULATION
+void
+pg_atomic_init_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 val_)
+{
+ StaticAssertStmt(sizeof(ptr->sema) >= sizeof(slock_t),
+ "size mismatch of atomic_flag vs slock_t");
+
+ /*
+ * If we're using semaphore based atomic flags, be careful about nested
+ * usage of atomics while a spinlock is held.
+ */
+#ifndef HAVE_SPINLOCKS
+ s_init_lock_sema((slock_t *) &ptr->sema, true);
+#else
+ SpinLockInit((slock_t *) &ptr->sema);
+#endif
+ ptr->value = val_;
+}
+
+bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ bool ret;
+ /*
+ * Do atomic op under a spinlock. It might look like we could just skip
+ * the cmpxchg if the lock isn't available, but that'd just emulate a
+ * 'weak' compare and swap. I.e. one that allows spurious failures. Since
+ * several algorithms rely on a strong variant and that is efficiently
+ * implementable on most major architectures let's emulate it here as
+ * well.
+ */
+ SpinLockAcquire((slock_t *) &ptr->sema);
+
+ /* perform compare/exchange logic*/
+ ret = ptr->value == *expected;
+ *expected = ptr->value;
+ if (ret)
+ ptr->value = newval;
+
+ /* and release lock */
+ SpinLockRelease((slock_t *) &ptr->sema);
+
+ return ret;
+}
+
+uint32
+pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ uint32 oldval;
+ SpinLockAcquire((slock_t *) &ptr->sema);
+ oldval = ptr->value;
+ ptr->value += add_;
+ SpinLockRelease((slock_t *) &ptr->sema);
+ return oldval;
+}
+
+#endif /* PG_HAVE_ATOMIC_U32_SIMULATION */
diff --git a/src/backend/storage/lmgr/spin.c b/src/backend/storage/lmgr/spin.c
index e5a9d353730..de3d9224e6e 100644
--- a/src/backend/storage/lmgr/spin.c
+++ b/src/backend/storage/lmgr/spin.c
@@ -67,7 +67,7 @@ SpinlockSemas(void)
int
SpinlockSemas(void)
{
- return NUM_SPINLOCK_SEMAPHORES;
+ return NUM_SPINLOCK_SEMAPHORES + NUM_ATOMICS_SEMAPHORES;
}
/*
@@ -77,8 +77,9 @@ extern void
SpinlockSemaInit(PGSemaphore spinsemas)
{
int i;
+ int nsemas = SpinlockSemas();
- for (i = 0; i < NUM_SPINLOCK_SEMAPHORES; ++i)
+ for (i = 0; i < nsemas; ++i)
PGSemaphoreCreate(&spinsemas[i]);
SpinlockSemaArray = spinsemas;
}
@@ -88,7 +89,7 @@ SpinlockSemaInit(PGSemaphore spinsemas)
*/
void
-s_init_lock_sema(volatile slock_t *lock)
+s_init_lock_sema(volatile slock_t *lock, bool nested)
{
static int counter = 0;
diff --git a/src/include/c.h b/src/include/c.h
index 2ceaaf6c1d7..ce38d78736f 100644
--- a/src/include/c.h
+++ b/src/include/c.h
@@ -582,6 +582,7 @@ typedef NameData *Name;
#define AssertMacro(condition) ((void)true)
#define AssertArg(condition)
#define AssertState(condition)
+#define AssertPointerAlignment(ptr, bndr) ((void)true)
#define Trap(condition, errorType)
#define TrapMacro(condition, errorType) (true)
@@ -592,6 +593,7 @@ typedef NameData *Name;
#define AssertMacro(p) ((void) assert(p))
#define AssertArg(condition) assert(condition)
#define AssertState(condition) assert(condition)
+#define AssertPointerAlignment(ptr, bndr) ((void)true)
#else /* USE_ASSERT_CHECKING && !FRONTEND */
/*
@@ -628,8 +630,15 @@ typedef NameData *Name;
#define AssertState(condition) \
Trap(!(condition), "BadState")
-#endif /* USE_ASSERT_CHECKING && !FRONTEND */
+/*
+ * Check that `ptr' is `bndr' aligned.
+ */
+#define AssertPointerAlignment(ptr, bndr) \
+ Trap(TYPEALIGN(bndr, (uintptr_t)(ptr)) != (uintptr_t)(ptr), \
+ "UnalignedPointer")
+
+#endif /* USE_ASSERT_CHECKING && !FRONTEND */
/*
* Macros to support compile-time assertion checks.
@@ -856,12 +865,22 @@ typedef NameData *Name;
* The header must also declare the functions' prototypes, protected by
* !PG_USE_INLINE.
*/
+
+/* declarations which are only visible when not inlining and in the .c file */
#ifdef PG_USE_INLINE
#define STATIC_IF_INLINE static inline
#else
#define STATIC_IF_INLINE
#endif /* PG_USE_INLINE */
+/* declarations which are marked inline when inlining, extern otherwise */
+#ifdef PG_USE_INLINE
+#define STATIC_IF_INLINE_DECLARE static inline
+#else
+#define STATIC_IF_INLINE_DECLARE extern
+#endif /* PG_USE_INLINE */
+
+
/* ----------------------------------------------------------------
* Section 8: random stuff
* ----------------------------------------------------------------
diff --git a/src/include/pg_config.h.in b/src/include/pg_config.h.in
index 1ce37c8765b..ddcf4b07173 100644
--- a/src/include/pg_config.h.in
+++ b/src/include/pg_config.h.in
@@ -87,6 +87,12 @@
/* Define to 1 if you have the `append_history' function. */
#undef HAVE_APPEND_HISTORY
+/* Define to 1 if you want to use atomics if available. */
+#undef HAVE_ATOMICS
+
+/* Define to 1 if you have the <atomic.h> header file. */
+#undef HAVE_ATOMIC_H
+
/* Define to 1 if you have the `cbrt' function. */
#undef HAVE_CBRT
@@ -173,8 +179,24 @@
/* Define to 1 if your compiler understands __FUNCTION__. */
#undef HAVE_FUNCNAME__FUNCTION
+/* Define to 1 if you have __atomic_compare_exchange_n(int *, int *, int). */
+#undef HAVE_GCC__ATOMIC_INT32_CAS
+
+/* Define to 1 if you have __atomic_compare_exchange_n(int64 *, int *, int64).
+ */
+#undef HAVE_GCC__ATOMIC_INT64_CAS
+
+/* Define to 1 if you have __sync_lock_test_and_set(char *) and friends. */
+#undef HAVE_GCC__SYNC_CHAR_TAS
+
+/* Define to 1 if you have __sync_compare_and_swap(int *, int, int). */
+#undef HAVE_GCC__SYNC_INT32_CAS
+
/* Define to 1 if you have __sync_lock_test_and_set(int *) and friends. */
-#undef HAVE_GCC_INT_ATOMICS
+#undef HAVE_GCC__SYNC_INT32_TAS
+
+/* Define to 1 if you have __sync_compare_and_swap(int64 *, int64, int64). */
+#undef HAVE_GCC__SYNC_INT64_CAS
/* Define to 1 if you have the `getaddrinfo' function. */
#undef HAVE_GETADDRINFO
diff --git a/src/include/pg_config.h.win32 b/src/include/pg_config.h.win32
index bce67a2b492..05941e65774 100644
--- a/src/include/pg_config.h.win32
+++ b/src/include/pg_config.h.win32
@@ -334,6 +334,9 @@
/* Define to 1 if you have spinlocks. */
#define HAVE_SPINLOCKS 1
+/* Define to 1 if you have atomics. */
+#define HAVE_ATOMICS 1
+
/* Define to 1 if you have the `srandom' function. */
/* #undef HAVE_SRANDOM */
diff --git a/src/include/pg_config_manual.h b/src/include/pg_config_manual.h
index d78f38e3bd5..195fb262811 100644
--- a/src/include/pg_config_manual.h
+++ b/src/include/pg_config_manual.h
@@ -64,6 +64,14 @@
*/
#define NUM_SPINLOCK_SEMAPHORES 1024
+/*
+ * When we have neither spinlocks nor atomic operations support we're
+ * implementing atomic operations on top of spinlock on top of semaphores. To
+ * be safe against atomic operations while holding a spinlock separate
+ * semaphores have to be used.
+ */
+#define NUM_ATOMICS_SEMAPHORES 64
+
/*
* Define this if you want to allow the lo_import and lo_export SQL
* functions to be executed by ordinary users. By default these
diff --git a/src/include/port/atomics.h b/src/include/port/atomics.h
new file mode 100644
index 00000000000..6a68aa21f4f
--- /dev/null
+++ b/src/include/port/atomics.h
@@ -0,0 +1,531 @@
+/*-------------------------------------------------------------------------
+ *
+ * atomics.h
+ * Atomic operations.
+ *
+ * Hardware and compiler dependent functions for manipulating memory
+ * atomically and dealing with cache coherency. Used to implement locking
+ * facilities and lockless algorithms/data structures.
+ *
+ * To bring up postgres on a platform/compiler at the very least
+ * implementations for the following operations should be provided:
+ * * pg_compiler_barrier(), pg_write_barrier(), pg_read_barrier()
+ * * pg_atomic_compare_exchange_u32(), pg_atomic_fetch_add_u32()
+ * * pg_atomic_test_set_flag(), pg_atomic_init_flag(), pg_atomic_clear_flag()
+ *
+ * There exist generic, hardware independent, implementations for several
+ * compilers which might be sufficient, although possibly not optimal, for a
+ * new platform. If no such generic implementation is available spinlocks (or
+ * even OS provided semaphores) will be used to implement the API.
+ *
+ * Implement the _u64 variantes if and only if your platform can use them
+ * efficiently (and obviously correctly).
+ *
+ * Use higher level functionality (lwlocks, spinlocks, heavyweight locks)
+ * whenever possible. Writing correct code using these facilities is hard.
+ *
+ * For an introduction to using memory barriers within the PostgreSQL backend,
+ * see src/backend/storage/lmgr/README.barrier
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/port/atomics.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef ATOMICS_H
+#define ATOMICS_H
+
+#define INSIDE_ATOMICS_H
+
+#include <limits.h>
+
+/*
+ * First a set of architecture specific files is included.
+ *
+ * These files can provide the full set of atomics or can do pretty much
+ * nothing if all the compilers commonly used on these platforms provide
+ * useable generics.
+ *
+ * Don't add an inline assembly of the actual atomic operations if all the
+ * common implementations of your platform provide intrinsics. Intrinsics are
+ * much easier to understand and potentially support more architectures.
+ *
+ * It will often make sense to define memory barrier semantics here, since
+ * e.g. generic compiler intrinsics for x86 memory barriers can't know that
+ * postgres doesn't need x86 read/write barriers do anything more than a
+ * compiler barrier.
+ *
+ */
+#if defined(__arm__) || defined(__arm) || \
+ defined(__aarch64__) || defined(__aarch64)
+# include "port/atomics/arch-arm.h"
+#elif defined(__i386__) || defined(__i386) || defined(__x86_64__)
+# include "port/atomics/arch-x86.h"
+#elif defined(__ia64__) || defined(__ia64)
+# include "port/atomics/arch-ia64.h"
+#elif defined(__ppc__) || defined(__powerpc__) || defined(__ppc64__) || defined(__powerpc64__)
+# include "port/atomics/arch-ppc.h"
+#elif defined(__hppa) || defined(__hppa__)
+# include "port/atomics/arch-hppa.h"
+#endif
+
+/*
+ * Compiler specific, but architecture independent implementations.
+ *
+ * Provide architecture independent implementations of the atomic
+ * facilities. At the very least compiler barriers should be provided, but a
+ * full implementation of
+ * * pg_compiler_barrier(), pg_write_barrier(), pg_read_barrier()
+ * * pg_atomic_compare_exchange_u32(), pg_atomic_fetch_add_u32()
+ * using compiler intrinsics are a good idea.
+ */
+/* gcc or compatible, including clang and icc */
+#if defined(__GNUC__) || defined(__INTEL_COMPILER)
+# include "port/atomics/generic-gcc.h"
+#elif defined(WIN32_ONLY_COMPILER)
+# include "port/atomics/generic-msvc.h"
+#elif defined(__hpux) && defined(__ia64) && !defined(__GNUC__)
+# include "port/atomics/generic-acc.h"
+#elif defined(__SUNPRO_C) && !defined(__GNUC__)
+# include "port/atomics/generic-sunpro.h"
+#elif (defined(__IBMC__) || defined(__IBMCPP__)) && !defined(__GNUC__)
+# include "port/atomics/generic-xlc.h"
+#else
+/*
+ * Unsupported compiler, we'll likely use slower fallbacks... At least
+ * compiler barriers should really be provided.
+ */
+#endif
+
+/*
+ * Provide a full fallback of the pg_*_barrier(), pg_atomic**_flag and
+ * pg_atomic_*_u32 APIs for platforms without sufficient spinlock and/or
+ * atomics support. In the case of spinlock backed atomics the emulation is
+ * expected to be efficient, although less so than native atomics support.
+ */
+#include "port/atomics/fallback.h"
+
+/*
+ * Provide additional operations using supported infrastructure. These are
+ * expected to be efficient if the underlying atomic operations are efficient.
+ */
+#include "port/atomics/generic.h"
+
+/*
+ * Provide declarations for all functions here - on most platforms static
+ * inlines are used and these aren't necessary, but when static inline is
+ * unsupported these will be external functions.
+ */
+STATIC_IF_INLINE_DECLARE void pg_atomic_init_flag(volatile pg_atomic_flag *ptr);
+STATIC_IF_INLINE_DECLARE bool pg_atomic_test_set_flag(volatile pg_atomic_flag *ptr);
+STATIC_IF_INLINE_DECLARE bool pg_atomic_unlocked_test_flag(volatile pg_atomic_flag *ptr);
+STATIC_IF_INLINE_DECLARE void pg_atomic_clear_flag(volatile pg_atomic_flag *ptr);
+
+STATIC_IF_INLINE_DECLARE void pg_atomic_init_u32(volatile pg_atomic_uint32 *ptr, uint32 val);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_read_u32(volatile pg_atomic_uint32 *ptr);
+STATIC_IF_INLINE_DECLARE void pg_atomic_write_u32(volatile pg_atomic_uint32 *ptr, uint32 val);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_exchange_u32(volatile pg_atomic_uint32 *ptr, uint32 newval);
+STATIC_IF_INLINE_DECLARE bool pg_atomic_compare_exchange_u32(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_fetch_add_u32(volatile pg_atomic_uint32 *ptr, int32 add_);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_fetch_sub_u32(volatile pg_atomic_uint32 *ptr, int32 sub_);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_fetch_and_u32(volatile pg_atomic_uint32 *ptr, uint32 and_);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_fetch_or_u32(volatile pg_atomic_uint32 *ptr, uint32 or_);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_add_fetch_u32(volatile pg_atomic_uint32 *ptr, int32 add_);
+STATIC_IF_INLINE_DECLARE uint32 pg_atomic_sub_fetch_u32(volatile pg_atomic_uint32 *ptr, int32 sub_);
+
+#ifdef PG_HAVE_ATOMIC_U64_SUPPORT
+
+STATIC_IF_INLINE_DECLARE void pg_atomic_init_u64(volatile pg_atomic_uint64 *ptr, uint64 val_);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_read_u64(volatile pg_atomic_uint64 *ptr);
+STATIC_IF_INLINE_DECLARE void pg_atomic_write_u64(volatile pg_atomic_uint64 *ptr, uint64 val);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_exchange_u64(volatile pg_atomic_uint64 *ptr, uint64 newval);
+STATIC_IF_INLINE_DECLARE bool pg_atomic_compare_exchange_u64(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_fetch_add_u64(volatile pg_atomic_uint64 *ptr, int64 add_);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_fetch_sub_u64(volatile pg_atomic_uint64 *ptr, int64 sub_);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_fetch_and_u64(volatile pg_atomic_uint64 *ptr, uint64 and_);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_fetch_or_u64(volatile pg_atomic_uint64 *ptr, uint64 or_);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_add_fetch_u64(volatile pg_atomic_uint64 *ptr, int64 add_);
+STATIC_IF_INLINE_DECLARE uint64 pg_atomic_sub_fetch_u64(volatile pg_atomic_uint64 *ptr, int64 sub_);
+
+#endif /* PG_HAVE_64_BIT_ATOMICS */
+
+
+/*
+ * pg_compiler_barrier - prevent the compiler from moving code across
+ *
+ * A compiler barrier need not (and preferably should not) emit any actual
+ * machine code, but must act as an optimization fence: the compiler must not
+ * reorder loads or stores to main memory around the barrier. However, the
+ * CPU may still reorder loads or stores at runtime, if the architecture's
+ * memory model permits this.
+ */
+#define pg_compiler_barrier() pg_compiler_barrier_impl()
+
+/*
+ * pg_memory_barrier - prevent the CPU from reordering memory access
+ *
+ * A memory barrier must act as a compiler barrier, and in addition must
+ * guarantee that all loads and stores issued prior to the barrier are
+ * completed before any loads or stores issued after the barrier. Unless
+ * loads and stores are totally ordered (which is not the case on most
+ * architectures) this requires issuing some sort of memory fencing
+ * instruction.
+ */
+#define pg_memory_barrier() pg_memory_barrier_impl()
+
+/*
+ * pg_(read|write)_barrier - prevent the CPU from reordering memory access
+ *
+ * A read barrier must act as a compiler barrier, and in addition must
+ * guarantee that any loads issued prior to the barrier are completed before
+ * any loads issued after the barrier. Similarly, a write barrier acts
+ * as a compiler barrier, and also orders stores. Read and write barriers
+ * are thus weaker than a full memory barrier, but stronger than a compiler
+ * barrier. In practice, on machines with strong memory ordering, read and
+ * write barriers may require nothing more than a compiler barrier.
+ */
+#define pg_read_barrier() pg_read_barrier_impl()
+#define pg_write_barrier() pg_write_barrier_impl()
+
+/*
+ * Spinloop delay - Allow CPU to relax in busy loops
+ */
+#define pg_spin_delay() pg_spin_delay_impl()
+
+/*
+ * The following functions are wrapper functions around the platform specific
+ * implementation of the atomic operations performing common checks.
+ */
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+/*
+ * pg_atomic_init_flag - initialize atomic flag.
+ *
+ * No barrier semantics.
+ */
+STATIC_IF_INLINE_DECLARE void
+pg_atomic_init_flag(volatile pg_atomic_flag *ptr)
+{
+ AssertPointerAlignment(ptr, sizeof(*ptr));
+
+ pg_atomic_init_flag_impl(ptr);
+}
+
+/*
+ * pg_atomic_test_and_set_flag - TAS()
+ *
+ * Returns true if the flag has successfully been set, false otherwise.
+ *
+ * Acquire (including read barrier) semantics.
+ */
+STATIC_IF_INLINE_DECLARE bool
+pg_atomic_test_set_flag(volatile pg_atomic_flag *ptr)
+{
+ AssertPointerAlignment(ptr, sizeof(*ptr));
+
+ return pg_atomic_test_set_flag_impl(ptr);
+}
+
+/*
+ * pg_atomic_unlocked_test_flag - Check if the lock is free
+ *
+ * Returns true if the flag currently is not set, false otherwise.
+ *
+ * No barrier semantics.
+ */
+STATIC_IF_INLINE_DECLARE bool
+pg_atomic_unlocked_test_flag(volatile pg_atomic_flag *ptr)
+{
+ AssertPointerAlignment(ptr, sizeof(*ptr));
+
+ return pg_atomic_unlocked_test_flag_impl(ptr);
+}
+
+/*
+ * pg_atomic_clear_flag - release lock set by TAS()
+ *
+ * Release (including write barrier) semantics.
+ */
+STATIC_IF_INLINE_DECLARE void
+pg_atomic_clear_flag(volatile pg_atomic_flag *ptr)
+{
+ AssertPointerAlignment(ptr, sizeof(*ptr));
+
+ pg_atomic_clear_flag_impl(ptr);
+}
+
+
+/*
+ * pg_atomic_init_u32 - initialize atomic variable
+ *
+ * Has to be done before any concurrent usage..
+ *
+ * No barrier semantics.
+ */
+STATIC_IF_INLINE_DECLARE void
+pg_atomic_init_u32(volatile pg_atomic_uint32 *ptr, uint32 val)
+{
+ AssertPointerAlignment(ptr, 4);
+
+ pg_atomic_init_u32_impl(ptr, val);
+}
+
+/*
+ * pg_atomic_write_u32 - unlocked write to atomic variable.
+ *
+ * The write is guaranteed to succeed as a whole, i.e. it's not possible to
+ * observe a partial write for any reader.
+ *
+ * No barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_read_u32(volatile pg_atomic_uint32 *ptr)
+{
+ AssertPointerAlignment(ptr, 4);
+ return pg_atomic_read_u32_impl(ptr);
+}
+
+/*
+ * pg_atomic_read_u32 - unlocked read from atomic variable.
+ *
+ * The read is guaranteed to return a value as it has been written by this or
+ * another process at some point in the past. There's however no cache
+ * coherency interaction guaranteeing the value hasn't since been written to
+ * again.
+ *
+ * No barrier semantics.
+ */
+STATIC_IF_INLINE_DECLARE void
+pg_atomic_write_u32(volatile pg_atomic_uint32 *ptr, uint32 val)
+{
+ AssertPointerAlignment(ptr, 4);
+
+ pg_atomic_write_u32_impl(ptr, val);
+}
+
+/*
+ * pg_atomic_exchange_u32 - exchange newval with current value
+ *
+ * Returns the old value of 'ptr' before the swap.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_exchange_u32(volatile pg_atomic_uint32 *ptr, uint32 newval)
+{
+ AssertPointerAlignment(ptr, 4);
+
+ return pg_atomic_exchange_u32_impl(ptr, newval);
+}
+
+/*
+ * pg_atomic_compare_exchange_u32 - CAS operation
+ *
+ * Atomically compare the current value of ptr with *expected and store newval
+ * iff ptr and *expected have the same value. The current value of *ptr will
+ * always be stored in *expected.
+ *
+ * Return true if values have been exchanged, false otherwise.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE bool
+pg_atomic_compare_exchange_u32(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ AssertPointerAlignment(ptr, 4);
+ AssertPointerAlignment(expected, 4);
+
+ return pg_atomic_compare_exchange_u32_impl(ptr, expected, newval);
+}
+
+/*
+ * pg_atomic_fetch_add_u32 - atomically add to variable
+ *
+ * Returns the the value of ptr before the arithmetic operation.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_fetch_add_u32(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ AssertPointerAlignment(ptr, 4);
+ return pg_atomic_fetch_add_u32_impl(ptr, add_);
+}
+
+/*
+ * pg_atomic_fetch_sub_u32 - atomically subtract from variable
+ *
+ * Returns the the value of ptr before the arithmetic operation. Note that
+ * sub_ may not be INT_MIN due to platform limitations.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_fetch_sub_u32(volatile pg_atomic_uint32 *ptr, int32 sub_)
+{
+ AssertPointerAlignment(ptr, 4);
+ Assert(sub_ != INT_MIN);
+ return pg_atomic_fetch_sub_u32_impl(ptr, sub_);
+}
+
+/*
+ * pg_atomic_fetch_and_u32 - atomically bit-and and_ with variable
+ *
+ * Returns the the value of ptr before the arithmetic operation.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_fetch_and_u32(volatile pg_atomic_uint32 *ptr, uint32 and_)
+{
+ AssertPointerAlignment(ptr, 4);
+ return pg_atomic_fetch_and_u32_impl(ptr, and_);
+}
+
+/*
+ * pg_atomic_fetch_or_u32 - atomically bit-or or_ with variable
+ *
+ * Returns the the value of ptr before the arithmetic operation.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_fetch_or_u32(volatile pg_atomic_uint32 *ptr, uint32 or_)
+{
+ AssertPointerAlignment(ptr, 4);
+ return pg_atomic_fetch_or_u32_impl(ptr, or_);
+}
+
+/*
+ * pg_atomic_add_fetch_u32 - atomically add to variable
+ *
+ * Returns the the value of ptr after the arithmetic operation.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_add_fetch_u32(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ AssertPointerAlignment(ptr, 4);
+ return pg_atomic_add_fetch_u32_impl(ptr, add_);
+}
+
+/*
+ * pg_atomic_sub_fetch_u32 - atomically subtract from variable
+ *
+ * Returns the the value of ptr after the arithmetic operation. Note that sub_
+ * may not be INT_MIN due to platform limitations.
+ *
+ * Full barrier semantics.
+ */
+STATIC_IF_INLINE uint32
+pg_atomic_sub_fetch_u32(volatile pg_atomic_uint32 *ptr, int32 sub_)
+{
+ AssertPointerAlignment(ptr, 4);
+ Assert(sub_ != INT_MIN);
+ return pg_atomic_sub_fetch_u32_impl(ptr, sub_);
+}
+
+/* ----
+ * The 64 bit operations have the same semantics as their 32bit counterparts
+ * if they are available. Check the corresponding 32bit function for
+ * documentation.
+ * ----
+ */
+#ifdef PG_HAVE_ATOMIC_U64_SUPPORT
+
+STATIC_IF_INLINE_DECLARE void
+pg_atomic_init_u64(volatile pg_atomic_uint64 *ptr, uint64 val)
+{
+ AssertPointerAlignment(ptr, 8);
+
+ pg_atomic_init_u64_impl(ptr, val);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_read_u64(volatile pg_atomic_uint64 *ptr)
+{
+ AssertPointerAlignment(ptr, 8);
+ return pg_atomic_read_u64_impl(ptr);
+}
+
+STATIC_IF_INLINE void
+pg_atomic_write_u64(volatile pg_atomic_uint64 *ptr, uint64 val)
+{
+ AssertPointerAlignment(ptr, 8);
+ pg_atomic_write_u64_impl(ptr, val);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_exchange_u64(volatile pg_atomic_uint64 *ptr, uint64 newval)
+{
+ AssertPointerAlignment(ptr, 8);
+
+ return pg_atomic_exchange_u64_impl(ptr, newval);
+}
+
+STATIC_IF_INLINE bool
+pg_atomic_compare_exchange_u64(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ AssertPointerAlignment(ptr, 8);
+ AssertPointerAlignment(expected, 8);
+ return pg_atomic_compare_exchange_u64_impl(ptr, expected, newval);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_fetch_add_u64(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ AssertPointerAlignment(ptr, 8);
+ return pg_atomic_fetch_add_u64_impl(ptr, add_);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_fetch_sub_u64(volatile pg_atomic_uint64 *ptr, int64 sub_)
+{
+ AssertPointerAlignment(ptr, 8);
+ Assert(sub_ != -INT64CONST(0x7FFFFFFFFFFFFFFF) - 1);
+ return pg_atomic_fetch_sub_u64_impl(ptr, sub_);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_fetch_and_u64(volatile pg_atomic_uint64 *ptr, uint64 and_)
+{
+ AssertPointerAlignment(ptr, 8);
+ return pg_atomic_fetch_and_u64_impl(ptr, and_);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_fetch_or_u64(volatile pg_atomic_uint64 *ptr, uint64 or_)
+{
+ AssertPointerAlignment(ptr, 8);
+ return pg_atomic_fetch_or_u64_impl(ptr, or_);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_add_fetch_u64(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ AssertPointerAlignment(ptr, 8);
+ return pg_atomic_add_fetch_u64_impl(ptr, add_);
+}
+
+STATIC_IF_INLINE uint64
+pg_atomic_sub_fetch_u64(volatile pg_atomic_uint64 *ptr, int64 sub_)
+{
+ AssertPointerAlignment(ptr, 8);
+ Assert(sub_ != -INT64CONST(0x7FFFFFFFFFFFFFFF) - 1);
+ return pg_atomic_sub_fetch_u64_impl(ptr, sub_);
+}
+
+#endif /* PG_HAVE_64_BIT_ATOMICS */
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
+
+#undef INSIDE_ATOMICS_H
+
+#endif /* ATOMICS_H */
diff --git a/src/include/port/atomics/arch-arm.h b/src/include/port/atomics/arch-arm.h
new file mode 100644
index 00000000000..ec7665f09fa
--- /dev/null
+++ b/src/include/port/atomics/arch-arm.h
@@ -0,0 +1,25 @@
+/*-------------------------------------------------------------------------
+ *
+ * arch-arm.h
+ * Atomic operations considerations specific to ARM
+ *
+ * Portions Copyright (c) 2013-2014, PostgreSQL Global Development Group
+ *
+ * NOTES:
+ *
+ * src/include/port/atomics/arch-arm.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/* intentionally no include guards, should only be included by atomics.h */
+#ifndef INSIDE_ATOMICS_H
+#error "should be included via atomics.h"
+#endif
+
+/*
+ * 64 bit atomics on arm are implemented using kernel fallbacks and might be
+ * slow, so disable entirely for now.
+ * XXX: We might want to change that at some point for AARCH64
+ */
+#define PG_DISABLE_64_BIT_ATOMICS
diff --git a/src/include/port/atomics/arch-hppa.h b/src/include/port/atomics/arch-hppa.h
new file mode 100644
index 00000000000..0c6d31a1f34
--- /dev/null
+++ b/src/include/port/atomics/arch-hppa.h
@@ -0,0 +1,17 @@
+/*-------------------------------------------------------------------------
+ *
+ * arch-hppa.h
+ * Atomic operations considerations specific to HPPA
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES:
+ *
+ * src/include/port/atomics/arch-hppa.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/* HPPA doesn't do either read or write reordering */
+#define pg_memory_barrier_impl() pg_compiler_barrier_impl()
diff --git a/src/include/port/atomics/arch-ia64.h b/src/include/port/atomics/arch-ia64.h
new file mode 100644
index 00000000000..92a088e4cf5
--- /dev/null
+++ b/src/include/port/atomics/arch-ia64.h
@@ -0,0 +1,26 @@
+/*-------------------------------------------------------------------------
+ *
+ * arch-ia64.h
+ * Atomic operations considerations specific to intel itanium
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES:
+ *
+ * src/include/port/atomics/arch-ia64.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/*
+ * Itanium is weakly ordered, so read and write barriers require a full
+ * fence.
+ */
+#if defined(__INTEL_COMPILER)
+# define pg_memory_barrier_impl() __mf()
+#elif defined(__GNUC__)
+# define pg_memory_barrier_impl() __asm__ __volatile__ ("mf" : : : "memory")
+#elif defined(__hpux)
+# define pg_memory_barrier_impl() _Asm_mf()
+#endif
diff --git a/src/include/port/atomics/arch-ppc.h b/src/include/port/atomics/arch-ppc.h
new file mode 100644
index 00000000000..250b6c44330
--- /dev/null
+++ b/src/include/port/atomics/arch-ppc.h
@@ -0,0 +1,26 @@
+/*-------------------------------------------------------------------------
+ *
+ * arch-ppc.h
+ * Atomic operations considerations specific to PowerPC
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES:
+ *
+ * src/include/port/atomics/arch-ppc.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+#if defined(__GNUC__)
+
+/*
+ * lwsync orders loads with respect to each other, and similarly with stores.
+ * But a load can be performed before a subsequent store, so sync must be used
+ * for a full memory barrier.
+ */
+#define pg_memory_barrier_impl() __asm__ __volatile__ ("sync" : : : "memory")
+#define pg_read_barrier_impl() __asm__ __volatile__ ("lwsync" : : : "memory")
+#define pg_write_barrier_impl() __asm__ __volatile__ ("lwsync" : : : "memory")
+#endif
diff --git a/src/include/port/atomics/arch-x86.h b/src/include/port/atomics/arch-x86.h
new file mode 100644
index 00000000000..b2127add36c
--- /dev/null
+++ b/src/include/port/atomics/arch-x86.h
@@ -0,0 +1,241 @@
+/*-------------------------------------------------------------------------
+ *
+ * arch-x86.h
+ * Atomic operations considerations specific to intel x86
+ *
+ * Note that we actually require a 486 upwards because the 386 doesn't have
+ * support for xadd and cmpxchg. Given that the 386 isn't supported anywhere
+ * anymore that's not much of restriction luckily.
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES:
+ *
+ * src/include/port/atomics/arch-x86.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/*
+ * Both 32 and 64 bit x86 do not allow loads to be reordered with other loads,
+ * or stores to be reordered with other stores, but a load can be performed
+ * before a subsequent store.
+ *
+ * Technically, some x86-ish chips support uncached memory access and/or
+ * special instructions that are weakly ordered. In those cases we'd need
+ * the read and write barriers to be lfence and sfence. But since we don't
+ * do those things, a compiler barrier should be enough.
+ *
+ * "lock; addl" has worked for longer than "mfence". It's also rumored to be
+ * faster in many scenarios
+ */
+
+#if defined(__INTEL_COMPILER)
+#define pg_memory_barrier_impl() _mm_mfence()
+#elif defined(__GNUC__) && (defined(__i386__) || defined(__i386))
+#define pg_memory_barrier_impl() \
+ __asm__ __volatile__ ("lock; addl $0,0(%%esp)" : : : "memory", "cc")
+#elif defined(__GNUC__) && defined(__x86_64__)
+#define pg_memory_barrier_impl() \
+ __asm__ __volatile__ ("lock; addl $0,0(%%rsp)" : : : "memory", "cc")
+#endif
+
+#define pg_read_barrier_impl() pg_compiler_barrier_impl()
+#define pg_write_barrier_impl() pg_compiler_barrier_impl()
+
+/*
+ * Provide implementation for atomics using inline assembly on x86 gcc. It's
+ * nice to support older gcc's and the compare/exchange implementation here is
+ * actually more efficient than the * __sync variant.
+ */
+#if defined(HAVE_ATOMICS)
+
+#if defined(__GNUC__) && !defined(__INTEL_COMPILER)
+
+#define PG_HAVE_ATOMIC_FLAG_SUPPORT
+typedef struct pg_atomic_flag
+{
+ volatile char value;
+} pg_atomic_flag;
+
+#define PG_HAVE_ATOMIC_U32_SUPPORT
+typedef struct pg_atomic_uint32
+{
+ volatile uint32 value;
+} pg_atomic_uint32;
+
+/*
+ * It's too complicated to write inline asm for 64bit types on 32bit and the
+ * 468 can't do it.
+ */
+#ifdef __x86_64__
+#define PG_HAVE_ATOMIC_U64_SUPPORT
+typedef struct pg_atomic_uint64
+{
+ volatile uint64 value;
+} pg_atomic_uint64;
+#endif
+
+#endif /* defined(HAVE_ATOMICS) */
+#endif /* defined(__GNUC__) && !defined(__INTEL_COMPILER) */
+
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#if !defined(PG_HAVE_SPIN_DELAY)
+/*
+ * This sequence is equivalent to the PAUSE instruction ("rep" is
+ * ignored by old IA32 processors if the following instruction is
+ * not a string operation); the IA-32 Architecture Software
+ * Developer's Manual, Vol. 3, Section 7.7.2 describes why using
+ * PAUSE in the inner loop of a spin lock is necessary for good
+ * performance:
+ *
+ * The PAUSE instruction improves the performance of IA-32
+ * processors supporting Hyper-Threading Technology when
+ * executing spin-wait loops and other routines where one
+ * thread is accessing a shared lock or semaphore in a tight
+ * polling loop. When executing a spin-wait loop, the
+ * processor can suffer a severe performance penalty when
+ * exiting the loop because it detects a possible memory order
+ * violation and flushes the core processor's pipeline. The
+ * PAUSE instruction provides a hint to the processor that the
+ * code sequence is a spin-wait loop. The processor uses this
+ * hint to avoid the memory order violation and prevent the
+ * pipeline flush. In addition, the PAUSE instruction
+ * de-pipelines the spin-wait loop to prevent it from
+ * consuming execution resources excessively.
+ */
+#if defined(__INTEL_COMPILER)
+#define PG_HAVE_SPIN_DELAY
+static inline
+pg_spin_delay_impl(void)
+{
+ _mm_pause();
+}
+#elif defined(__GNUC__)
+#define PG_HAVE_SPIN_DELAY
+static __inline__ void
+pg_spin_delay_impl(void)
+{
+ __asm__ __volatile__(
+ " rep; nop \n");
+}
+#elif defined(WIN32_ONLY_COMPILER) && defined(__x86_64__)
+#define PG_HAVE_SPIN_DELAY
+static __forceinline void
+pg_spin_delay_impl(void)
+{
+ _mm_pause();
+}
+#elif defined(WIN32_ONLY_COMPILER)
+#define PG_HAVE_SPIN_DELAY
+static __forceinline void
+pg_spin_delay_impl(void)
+{
+ /* See comment for gcc code. Same code, MASM syntax */
+ __asm rep nop;
+}
+#endif
+#endif /* !defined(PG_HAVE_SPIN_DELAY) */
+
+
+#if defined(HAVE_ATOMICS)
+
+/* inline assembly implementation for gcc */
+#if defined(__GNUC__) && !defined(__INTEL_COMPILER)
+
+#define PG_HAVE_ATOMIC_TEST_SET_FLAG
+static inline bool
+pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ register char _res = 1;
+
+ __asm__ __volatile__(
+ " lock \n"
+ " xchgb %0,%1 \n"
+: "+q"(_res), "+m"(ptr->value)
+:
+: "memory");
+ return _res == 0;
+}
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+static inline bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ char ret;
+
+ /*
+ * Perform cmpxchg and use the zero flag which it implicitly sets when
+ * equal to measure the success.
+ */
+ __asm__ __volatile__(
+ " lock \n"
+ " cmpxchgl %4,%5 \n"
+ " setz %2 \n"
+: "=a" (*expected), "=m"(ptr->value), "=r" (ret)
+: "a" (*expected), "r" (newval), "m"(ptr->value)
+: "memory", "cc");
+ return (bool) ret;
+}
+
+#define PG_HAVE_ATOMIC_FETCH_ADD_U32
+static inline uint32
+pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ uint32 res;
+ __asm__ __volatile__(
+ " lock \n"
+ " xaddl %0,%1 \n"
+: "=q"(res), "=m"(ptr->value)
+: "0" (add_), "m"(ptr->value)
+: "memory", "cc");
+ return res;
+}
+
+#ifdef __x86_64__
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
+static inline bool
+pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ char ret;
+
+ /*
+ * Perform cmpxchg and use the zero flag which it implicitly sets when
+ * equal to measure the success.
+ */
+ __asm__ __volatile__(
+ " lock \n"
+ " cmpxchgq %4,%5 \n"
+ " setz %2 \n"
+: "=a" (*expected), "=m"(ptr->value), "=r" (ret)
+: "a" (*expected), "r" (newval), "m"(ptr->value)
+: "memory", "cc");
+ return (bool) ret;
+}
+
+#define PG_HAVE_ATOMIC_FETCH_ADD_U64
+static inline uint64
+pg_atomic_fetch_add_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ uint64 res;
+ __asm__ __volatile__(
+ " lock \n"
+ " xaddq %0,%1 \n"
+: "=q"(res), "=m"(ptr->value)
+: "0" (add_), "m"(ptr->value)
+: "memory", "cc");
+ return res;
+}
+
+#endif /* __x86_64__ */
+
+#endif /* defined(__GNUC__) && !defined(__INTEL_COMPILER) */
+
+#endif /* HAVE_ATOMICS */
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
diff --git a/src/include/port/atomics/fallback.h b/src/include/port/atomics/fallback.h
new file mode 100644
index 00000000000..fb97814d387
--- /dev/null
+++ b/src/include/port/atomics/fallback.h
@@ -0,0 +1,132 @@
+/*-------------------------------------------------------------------------
+ *
+ * fallback.h
+ * Fallback for platforms without spinlock and/or atomics support. Slower
+ * than native atomics support, but not unusably slow.
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/port/atomics/fallback.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/* intentionally no include guards, should only be included by atomics.h */
+#ifndef INSIDE_ATOMICS_H
+# error "should be included via atomics.h"
+#endif
+
+#ifndef pg_memory_barrier_impl
+/*
+ * If we have no memory barrier implementation for this architecture, we
+ * fall back to acquiring and releasing a spinlock. This might, in turn,
+ * fall back to the semaphore-based spinlock implementation, which will be
+ * amazingly slow.
+ *
+ * It's not self-evident that every possible legal implementation of a
+ * spinlock acquire-and-release would be equivalent to a full memory barrier.
+ * For example, I'm not sure that Itanium's acq and rel add up to a full
+ * fence. But all of our actual implementations seem OK in this regard.
+ */
+#define PG_HAVE_MEMORY_BARRIER_EMULATION
+
+extern void pg_spinlock_barrier(void);
+#define pg_memory_barrier_impl pg_spinlock_barrier
+#endif
+
+/*
+ * If we have atomics implementation for this platform fall back to providing
+ * the atomics API using a spinlock to protect the internal state. Possibly
+ * the spinlock implementation uses semaphores internally...
+ *
+ * We have to be a bit careful here, as it's not guaranteed that atomic
+ * variables are mapped to the same address in every process (e.g. dynamic
+ * shared memory segments). We can't just hash the address and use that to map
+ * to a spinlock. Instead assign a spinlock on initialization of the atomic
+ * variable.
+ */
+#if !defined(PG_HAVE_ATOMIC_FLAG_SUPPORT) && !defined(PG_HAVE_ATOMIC_U32_SUPPORT)
+
+#define PG_HAVE_ATOMIC_FLAG_SIMULATION
+#define PG_HAVE_ATOMIC_FLAG_SUPPORT
+
+typedef struct pg_atomic_flag
+{
+ /*
+ * To avoid circular includes we can't use s_lock as a type here. Instead
+ * just reserve enough space for all spinlock types. Some platforms would
+ * be content with just one byte instead of 4, but that's not too much
+ * waste.
+ */
+#if defined(__hppa) || defined(__hppa__) /* HP PA-RISC, GCC and HP compilers */
+ int sema[4];
+#else
+ int sema;
+#endif
+} pg_atomic_flag;
+
+#endif /* PG_HAVE_ATOMIC_FLAG_SUPPORT */
+
+#if !defined(PG_HAVE_ATOMIC_U32_SUPPORT)
+
+#define PG_HAVE_ATOMIC_U32_SIMULATION
+
+#define PG_HAVE_ATOMIC_U32_SUPPORT
+typedef struct pg_atomic_uint32
+{
+ /* Check pg_atomic_flag's definition above for an explanation */
+#if defined(__hppa) || defined(__hppa__) /* HP PA-RISC, GCC and HP compilers */
+ int sema[4];
+#else
+ int sema;
+#endif
+ volatile uint32 value;
+} pg_atomic_uint32;
+
+#endif /* PG_HAVE_ATOMIC_U32_SUPPORT */
+
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#ifdef PG_HAVE_ATOMIC_FLAG_SIMULATION
+
+#define PG_HAVE_ATOMIC_INIT_FLAG
+extern void pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr);
+
+#define PG_HAVE_ATOMIC_TEST_SET_FLAG
+extern bool pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr);
+
+#define PG_HAVE_ATOMIC_CLEAR_FLAG
+extern void pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr);
+
+#define PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG
+static inline bool
+pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ /*
+ * Can't do this efficiently in the semaphore based implementation - we'd
+ * have to try to acquire the semaphore - so always return true. That's
+ * correct, because this is only an unlocked test anyway.Do this in the
+ * header so compilers can optimize the test away.
+ */
+ return true;
+}
+
+#endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */
+
+#ifdef PG_HAVE_ATOMIC_U32_SIMULATION
+
+#define PG_HAVE_ATOMIC_INIT_U32
+extern void pg_atomic_init_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 val_);
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+extern bool pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval);
+
+#define PG_HAVE_ATOMIC_FETCH_ADD_U32
+extern uint32 pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_);
+
+#endif /* PG_HAVE_ATOMIC_U32_SIMULATION */
+
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
diff --git a/src/include/port/atomics/generic-acc.h b/src/include/port/atomics/generic-acc.h
new file mode 100644
index 00000000000..627e2dfcb5e
--- /dev/null
+++ b/src/include/port/atomics/generic-acc.h
@@ -0,0 +1,99 @@
+/*-------------------------------------------------------------------------
+ *
+ * generic-acc.h
+ * Atomic operations support when using HPs acc on HPUX
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES:
+ *
+ * Documentation:
+ * * inline assembly for Itanium-based HP-UX:
+ * http://h21007.www2.hp.com/portal/download/files/unprot/Itanium/inline_assem_ERS.pdf
+ * * Implementing Spinlocks on the Intel (R) Itanium (R) Architecture and PA-RISC
+ * http://h21007.www2.hp.com/portal/download/files/unprot/itanium/spinlocks.pdf
+ *
+ * Itanium only supports a small set of numbers (6, -8, -4, -1, 1, 4, 8, 16)
+ * for atomic add/sub, so we just implement everything but compare_exchange
+ * via the compare_exchange fallbacks in atomics/generic.h.
+ *
+ * src/include/port/atomics/generic-acc.h
+ *
+ * -------------------------------------------------------------------------
+ */
+
+#include <machine/sys/inline.h>
+
+/* IA64 always has 32/64 bit atomics */
+
+#define PG_HAVE_ATOMIC_U32_SUPPORT
+typedef struct pg_atomic_uint32
+{
+ volatile uint32 value;
+} pg_atomic_uint32;
+
+#define PG_HAVE_ATOMIC_U64_SUPPORT
+typedef struct pg_atomic_uint64
+{
+ volatile uint64 value;
+} pg_atomic_uint64;
+
+#define pg_compiler_barrier_impl() _Asm_sched_fence()
+
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#define MINOR_FENCE (_Asm_fence) (_UP_CALL_FENCE | _UP_SYS_FENCE | \
+ _DOWN_CALL_FENCE | _DOWN_SYS_FENCE )
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+STATIC_IF_INLINE bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ bool ret;
+ uint32 current;
+
+ _Asm_mov_to_ar(_AREG_CCV, *expected, MINOR_FENCE);
+ /*
+ * We want a barrier, not just release/acquire semantics.
+ */
+ _Asm_mf();
+ /*
+ * Notes:
+ * DOWN_MEM_FENCE | _UP_MEM_FENCE prevents reordering by the compiler
+ */
+ current = _Asm_cmpxchg(_SZ_W, /* word */
+ _SEM_REL,
+ &ptr->value,
+ newval, _LDHINT_NONE,
+ _DOWN_MEM_FENCE | _UP_MEM_FENCE);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
+STATIC_IF_INLINE bool
+pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ bool ret;
+ uint64 current;
+
+ _Asm_mov_to_ar(_AREG_CCV, *expected, MINOR_FENCE);
+ _Asm_mf();
+ current = _Asm_cmpxchg(_SZ_D, /* doubleword */
+ _SEM_REL,
+ &ptr->value,
+ newval, _LDHINT_NONE,
+ _DOWN_MEM_FENCE | _UP_MEM_FENCE);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+#undef MINOR_FENCE
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
diff --git a/src/include/port/atomics/generic-gcc.h b/src/include/port/atomics/generic-gcc.h
new file mode 100644
index 00000000000..23fa2a6ebb8
--- /dev/null
+++ b/src/include/port/atomics/generic-gcc.h
@@ -0,0 +1,236 @@
+/*-------------------------------------------------------------------------
+ *
+ * generic-gcc.h
+ * Atomic operations, implemented using gcc (or compatible) intrinsics.
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES:
+ *
+ * Documentation:
+ * * Legacy __sync Built-in Functions for Atomic Memory Access
+ * http://gcc.gnu.org/onlinedocs/gcc-4.8.2/gcc/_005f_005fsync-Builtins.html
+ * * Built-in functions for memory model aware atomic operations
+ * http://gcc.gnu.org/onlinedocs/gcc-4.8.2/gcc/_005f_005fatomic-Builtins.html
+ *
+ * src/include/port/atomics/generic-gcc.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/* intentionally no include guards, should only be included by atomics.h */
+#ifndef INSIDE_ATOMICS_H
+#error "should be included via atomics.h"
+#endif
+
+/*
+ * icc provides all the same intrinsics but doesn't understand gcc's inline asm
+ */
+#if defined(__INTEL_COMPILER)
+/* NB: Yes, __memory_barrier() is actually just a compiler barrier */
+#define pg_compiler_barrier_impl() __memory_barrier()
+#else
+#define pg_compiler_barrier_impl() __asm__ __volatile__("" ::: "memory")
+#endif
+
+/*
+ * If we're on GCC 4.1.0 or higher, we should be able to get a memory barrier
+ * out of this compiler built-in. But we prefer to rely on platform specific
+ * definitions where possible, and use this only as a fallback.
+ */
+#if !defined(pg_memory_barrier_impl)
+# if defined(HAVE_GCC__ATOMIC_INT64_CAS)
+# define pg_memory_barrier_impl() __atomic_thread_fence(__ATOMIC_SEQ_CST)
+# elif (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1))
+# define pg_memory_barrier_impl() __sync_synchronize()
+# endif
+#endif /* !defined(pg_memory_barrier_impl) */
+
+#if !defined(pg_read_barrier_impl) && defined(HAVE_GCC__ATOMIC_INT64_CAS)
+/* acquire semantics include read barrier semantics */
+# define pg_read_barrier_impl() __atomic_thread_fence(__ATOMIC_ACQUIRE)
+#endif
+
+#if !defined(pg_write_barrier_impl) && defined(HAVE_GCC__ATOMIC_INT64_CAS)
+/* release semantics include write barrier semantics */
+# define pg_write_barrier_impl() __atomic_thread_fence(__ATOMIC_RELEASE)
+#endif
+
+#ifdef HAVE_ATOMICS
+
+/* generic gcc based atomic flag implementation */
+#if !defined(PG_HAVE_ATOMIC_FLAG_SUPPORT) \
+ && (defined(HAVE_GCC__SYNC_INT32_TAS) || defined(HAVE_GCC__SYNC_CHAR_TAS))
+
+#define PG_HAVE_ATOMIC_FLAG_SUPPORT
+typedef struct pg_atomic_flag
+{
+ /* some platforms only have a 8 bit wide TAS */
+#ifdef HAVE_GCC__SYNC_CHAR_TAS
+ volatile char value;
+#else
+ /* but an int works on more platforms */
+ volatile int value;
+#endif
+} pg_atomic_flag;
+
+#endif /* !ATOMIC_FLAG_SUPPORT && SYNC_INT32_TAS */
+
+/* generic gcc based atomic uint32 implementation */
+#if !defined(PG_HAVE_ATOMIC_U32_SUPPORT) \
+ && (defined(HAVE_GCC__ATOMIC_INT32_CAS) || defined(HAVE_GCC__SYNC_INT32_CAS))
+
+#define PG_HAVE_ATOMIC_U32_SUPPORT
+typedef struct pg_atomic_uint32
+{
+ volatile uint32 value;
+} pg_atomic_uint32;
+
+#endif /* defined(HAVE_GCC__ATOMIC_INT32_CAS) || defined(HAVE_GCC__SYNC_INT32_CAS) */
+
+/* generic gcc based atomic uint64 implementation */
+#if !defined(PG_HAVE_ATOMIC_U64_SUPPORT) \
+ && !defined(PG_DISABLE_64_BIT_ATOMICS) \
+ && (defined(HAVE_GCC__ATOMIC_INT64_CAS) || defined(HAVE_GCC__SYNC_INT64_CAS))
+
+#define PG_HAVE_ATOMIC_U64_SUPPORT
+
+typedef struct pg_atomic_uint64
+{
+ volatile uint64 value;
+} pg_atomic_uint64;
+
+#endif /* defined(HAVE_GCC__ATOMIC_INT64_CAS) || defined(HAVE_GCC__SYNC_INT64_CAS) */
+
+/*
+ * Implementation follows. Inlined or directly included from atomics.c
+ */
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#if !defined(PG_HAVE_ATOMIC_TEST_SET_FLAG) && \
+ (defined(HAVE_GCC__SYNC_CHAR_TAS) || defined(HAVE_GCC__SYNC_INT32_TAS))
+#define PG_HAVE_ATOMIC_TEST_SET_FLAG
+static inline bool
+pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ /* NB: only a acquire barrier, not a full one */
+ /* some platform only support a 1 here */
+ return __sync_lock_test_and_set(&ptr->value, 1) == 0;
+}
+#endif /* !defined(PG_HAVE_ATOMIC_TEST_SET_FLAG) && defined(HAVE_GCC__SYNC_*_TAS) */
+
+#ifndef PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG
+#define PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG
+static inline bool
+pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ return ptr->value == 0;
+}
+#endif
+
+#ifndef PG_HAVE_ATOMIC_CLEAR_FLAG
+#define PG_HAVE_ATOMIC_CLEAR_FLAG
+static inline void
+pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ /*
+ * XXX: It would be nicer to use __sync_lock_release here, but gcc insists
+ * on making that an atomic op which is far to expensive and a stronger
+ * guarantee than what we actually need.
+ */
+ pg_write_barrier_impl();
+ ptr->value = 0;
+}
+#endif
+
+#ifndef PG_HAVE_ATOMIC_INIT_FLAG
+#define PG_HAVE_ATOMIC_INIT_FLAG
+static inline void
+pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ pg_atomic_clear_flag_impl(ptr);
+}
+#endif
+
+/* prefer __atomic, it has a better API */
+#if !defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32) && defined(HAVE_GCC__ATOMIC_INT32_CAS)
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+static inline bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ /* FIXME: we can probably use a lower consistency model */
+ return __atomic_compare_exchange_n(&ptr->value, expected, newval, false,
+ __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32) && defined(HAVE_GCC__SYNC_INT32_CAS)
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+static inline bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ bool ret;
+ uint32 current;
+ current = __sync_val_compare_and_swap(&ptr->value, *expected, newval);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_ADD_U32) && defined(HAVE_GCC__SYNC_INT32_CAS)
+#define PG_HAVE_ATOMIC_FETCH_ADD_U32
+static inline uint32
+pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ return __sync_fetch_and_add(&ptr->value, add_);
+}
+#endif
+
+
+#if !defined(PG_DISABLE_64_BIT_ATOMICS)
+
+#if !defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64) && defined(HAVE_GCC__ATOMIC_INT64_CAS)
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
+static inline bool
+pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ return __atomic_compare_exchange_n(&ptr->value, expected, newval, false,
+ __ATOMIC_SEQ_CST, __ATOMIC_SEQ_CST);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64) && defined(HAVE_GCC__SYNC_INT64_CAS)
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
+static inline bool
+pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ bool ret;
+ uint64 current;
+ current = __sync_val_compare_and_swap(&ptr->value, *expected, newval);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_ADD_U64) && defined(HAVE_GCC__SYNC_INT64_CAS)
+#define PG_HAVE_ATOMIC_FETCH_ADD_U64
+static inline uint64
+pg_atomic_fetch_add_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ return __sync_fetch_and_add(&ptr->value, add_);
+}
+#endif
+
+#endif /* !defined(PG_DISABLE_64_BIT_ATOMICS) */
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
+
+#endif /* defined(HAVE_ATOMICS) */
+
diff --git a/src/include/port/atomics/generic-msvc.h b/src/include/port/atomics/generic-msvc.h
new file mode 100644
index 00000000000..747daa0a760
--- /dev/null
+++ b/src/include/port/atomics/generic-msvc.h
@@ -0,0 +1,103 @@
+/*-------------------------------------------------------------------------
+ *
+ * generic-msvc.h
+ * Atomic operations support when using MSVC
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * NOTES:
+ *
+ * Documentation:
+ * * Interlocked Variable Access
+ * http://msdn.microsoft.com/en-us/library/ms684122%28VS.85%29.aspx
+ *
+ * src/include/port/atomics/generic-msvc.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#include <intrin.h>
+#include <windows.h>
+
+/* intentionally no include guards, should only be included by atomics.h */
+#ifndef INSIDE_ATOMICS_H
+#error "should be included via atomics.h"
+#endif
+
+/* Should work on both MSVC and Borland. */
+#pragma intrinsic(_ReadWriteBarrier)
+#define pg_compiler_barrier_impl() _ReadWriteBarrier()
+
+#ifndef pg_memory_barrier_impl
+#define pg_memory_barrier_impl() MemoryBarrier()
+#endif
+
+#define PG_HAVE_ATOMIC_U32_SUPPORT
+typedef struct pg_atomic_uint32
+{
+ volatile uint32 value;
+} pg_atomic_uint32;
+
+#define PG_HAVE_ATOMIC_U64_SUPPORT
+typedef struct pg_atomic_uint64
+{
+ volatile uint64 value;
+} pg_atomic_uint64;
+
+
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+static inline bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ bool ret;
+ uint32 current;
+ current = InterlockedCompareExchange(&ptr->value, newval, *expected);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+#define PG_HAVE_ATOMIC_FETCH_ADD_U32
+static inline uint32
+pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ return InterlockedExchangeAdd(&ptr->value, add_);
+}
+
+/*
+ * The non-intrinsics versions are only available in vista upwards, so use the
+ * intrinsic version. Only supported on >486, but we require XP as a minimum
+ * baseline, which doesn't support the 486, so we don't need to add checks for
+ * that case.
+ */
+#pragma intrinsic(_InterlockedCompareExchange64)
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
+static inline bool
+pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ bool ret;
+ uint64 current;
+ current = _InterlockedCompareExchange64(&ptr->value, newval, *expected);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+/* Only implemented on itanium and 64bit builds */
+#ifdef _WIN64
+#pragma intrinsic(_InterlockedExchangeAdd64)
+
+#define PG_HAVE_ATOMIC_FETCH_ADD_U64
+static inline uint64
+pg_atomic_fetch_add_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ return _InterlockedExchangeAdd64(&ptr->value, add_);
+}
+#endif /* _WIN64 */
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
diff --git a/src/include/port/atomics/generic-sunpro.h b/src/include/port/atomics/generic-sunpro.h
new file mode 100644
index 00000000000..b71b5230d3c
--- /dev/null
+++ b/src/include/port/atomics/generic-sunpro.h
@@ -0,0 +1,74 @@
+/*-------------------------------------------------------------------------
+ *
+ * generic-sunpro.h
+ * Atomic operations for solaris' CC
+ *
+ * Portions Copyright (c) 2013-2014, PostgreSQL Global Development Group
+ *
+ * NOTES:
+ *
+ * Documentation:
+ * * manpage for atomic_cas(3C)
+ * http://www.unix.com/man-page/opensolaris/3c/atomic_cas/
+ * http://docs.oracle.com/cd/E23824_01/html/821-1465/atomic-cas-3c.html
+ *
+ * src/include/port/atomics/generic-sunpro.h
+ *
+ * -------------------------------------------------------------------------
+ */
+
+/* Older versions of the compiler don't have atomic.h... */
+#ifdef HAVE_ATOMIC_H
+
+#include <atomic.h>
+
+#define PG_HAVE_ATOMIC_U32_SUPPORT
+typedef struct pg_atomic_uint32
+{
+ volatile uint32 value;
+} pg_atomic_uint32;
+
+#define PG_HAVE_ATOMIC_U64_SUPPORT
+typedef struct pg_atomic_uint64
+{
+ volatile uint64 value;
+} pg_atomic_uint64;
+
+#endif /* HAVE_ATOMIC_H */
+
+
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#ifdef HAVE_ATOMIC_H
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+static inline bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ bool ret;
+ uint32 current;
+
+ current = atomic_cas_32(&ptr->value, *expected, newval);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
+static inline bool
+pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ bool ret;
+ uint64 current;
+
+ current = atomic_cas_64(&ptr->value, *expected, newval);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+#endif /* HAVE_ATOMIC_H */
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
diff --git a/src/include/port/atomics/generic-xlc.h b/src/include/port/atomics/generic-xlc.h
new file mode 100644
index 00000000000..579554d8a67
--- /dev/null
+++ b/src/include/port/atomics/generic-xlc.h
@@ -0,0 +1,103 @@
+/*-------------------------------------------------------------------------
+ *
+ * generic-xlc.h
+ * Atomic operations for IBM's CC
+ *
+ * Portions Copyright (c) 2013-2014, PostgreSQL Global Development Group
+ *
+ * NOTES:
+ *
+ * Documentation:
+ * * Synchronization and atomic built-in functions
+ * http://publib.boulder.ibm.com/infocenter/lnxpcomp/v8v101/topic/com.ibm.xlcpp8l.doc/compiler/ref/bif_sync.htm
+ *
+ * src/include/port/atomics/generic-xlc.h
+ *
+ * -------------------------------------------------------------------------
+ */
+
+#include <atomic.h>
+
+#define PG_HAVE_ATOMIC_U32_SUPPORT
+typedef struct pg_atomic_uint32
+{
+ volatile uint32 value;
+} pg_atomic_uint32;
+
+
+/* 64bit atomics are only supported in 64bit mode */
+#ifdef __64BIT__
+#define PG_HAVE_ATOMIC_U64_SUPPORT
+typedef struct pg_atomic_uint64
+{
+ volatile uint64 value;
+} pg_atomic_uint64;
+
+#endif /* __64BIT__ */
+
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32
+static inline bool
+pg_atomic_compare_exchange_u32_impl(volatile pg_atomic_uint32 *ptr,
+ uint32 *expected, uint32 newval)
+{
+ bool ret;
+ uint64 current;
+
+ /*
+ * xlc's documentation tells us:
+ * "If __compare_and_swap is used as a locking primitive, insert a call to
+ * the __isync built-in function at the start of any critical sections."
+ */
+ __isync();
+
+ /*
+ * XXX: __compare_and_swap is defined to take signed parameters, but that
+ * shouldn't matter since we don't perform any arithmetic operations.
+ */
+ current = (uint32)__compare_and_swap((volatile int*)ptr->value,
+ (int)*expected, (int)newval);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+#define PG_HAVE_ATOMIC_FETCH_ADD_U32
+static inline uint32
+pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ return __fetch_and_add(&ptr->value, add_);
+}
+#endif
+
+#ifdef PG_HAVE_ATOMIC_U64_SUPPORT
+
+#define PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64
+static inline bool
+pg_atomic_compare_exchange_u64_impl(volatile pg_atomic_uint64 *ptr,
+ uint64 *expected, uint64 newval)
+{
+ bool ret;
+ uint64 current;
+
+ __isync();
+
+ current = (uint64)__compare_and_swaplp((volatile long*)ptr->value,
+ (long)*expected, (long)newval);
+ ret = current == *expected;
+ *expected = current;
+ return ret;
+}
+
+#define PG_HAVE_ATOMIC_FETCH_ADD_U64
+static inline uint64
+pg_atomic_fetch_add_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ return __fetch_and_addlp(&ptr->value, add_);
+}
+#endif
+
+#endif /* PG_HAVE_ATOMIC_U64_SUPPORT */
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
diff --git a/src/include/port/atomics/generic.h b/src/include/port/atomics/generic.h
new file mode 100644
index 00000000000..fa751237a59
--- /dev/null
+++ b/src/include/port/atomics/generic.h
@@ -0,0 +1,387 @@
+/*-------------------------------------------------------------------------
+ *
+ * generic.h
+ * Implement higher level operations based on some lower level tomic
+ * operations.
+ *
+ * Portions Copyright (c) 1996-2014, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * src/include/port/atomics/generic.h
+ *
+ *-------------------------------------------------------------------------
+ */
+
+/* intentionally no include guards, should only be included by atomics.h */
+#ifndef INSIDE_ATOMICS_H
+# error "should be included via atomics.h"
+#endif
+
+/*
+ * If read or write barriers are undefined, we upgrade them to full memory
+ * barriers.
+ */
+#if !defined(pg_read_barrier_impl)
+# define pg_read_barrier_impl pg_memory_barrier_impl
+#endif
+#if !defined(pg_write_barrier_impl)
+# define pg_write_barrier_impl pg_memory_barrier_impl
+#endif
+
+#ifndef PG_HAVE_SPIN_DELAY
+#define PG_HAVE_SPIN_DELAY
+#define pg_spin_delay_impl() ((void)0)
+#endif
+
+
+/* provide fallback */
+#if !defined(PG_HAVE_ATOMIC_FLAG_SUPPORT) && defined(PG_HAVE_ATOMIC_U32_SUPPORT)
+#define PG_HAVE_ATOMIC_FLAG_SUPPORT
+typedef pg_atomic_uint32 pg_atomic_flag;
+#endif
+
+#if defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS)
+
+#ifndef PG_HAVE_ATOMIC_READ_U32
+#define PG_HAVE_ATOMIC_READ_U32
+static inline uint32
+pg_atomic_read_u32_impl(volatile pg_atomic_uint32 *ptr)
+{
+ return *(&ptr->value);
+}
+#endif
+
+#ifndef PG_HAVE_ATOMIC_WRITE_U32
+#define PG_HAVE_ATOMIC_WRITE_U32
+static inline void
+pg_atomic_write_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 val)
+{
+ ptr->value = val;
+}
+#endif
+
+/*
+ * provide fallback for test_and_set using atomic_exchange if available
+ */
+#if !defined(PG_HAVE_ATOMIC_TEST_SET_FLAG) && defined(PG_HAVE_ATOMIC_EXCHANGE_U32)
+
+#define PG_HAVE_ATOMIC_INIT_FLAG
+static inline void
+pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ pg_atomic_write_u32_impl(ptr, 0);
+}
+
+#define PG_HAVE_ATOMIC_TEST_SET_FLAG
+static inline bool
+pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ return pg_atomic_exchange_u32_impl(ptr, &value, 1) == 0;
+}
+
+#define PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG
+static inline bool
+pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ return pg_atomic_read_u32_impl(ptr) == 0;
+}
+
+
+#define PG_HAVE_ATOMIC_CLEAR_FLAG
+static inline void
+pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ /* XXX: release semantics suffice? */
+ pg_memory_barrier_impl();
+ pg_atomic_write_u32_impl(ptr, 0);
+}
+
+/*
+ * provide fallback for test_and_set using atomic_compare_exchange if
+ * available.
+ */
+#elif !defined(PG_HAVE_ATOMIC_TEST_SET_FLAG) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32)
+
+#define PG_HAVE_ATOMIC_INIT_FLAG
+static inline void
+pg_atomic_init_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ pg_atomic_write_u32_impl(ptr, 0);
+}
+
+#define PG_HAVE_ATOMIC_TEST_SET_FLAG
+static inline bool
+pg_atomic_test_set_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ uint32 value = 0;
+ return pg_atomic_compare_exchange_u32_impl(ptr, &value, 1);
+}
+
+#define PG_HAVE_ATOMIC_UNLOCKED_TEST_FLAG
+static inline bool
+pg_atomic_unlocked_test_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ return pg_atomic_read_u32_impl(ptr) == 0;
+}
+
+#define PG_HAVE_ATOMIC_CLEAR_FLAG
+static inline void
+pg_atomic_clear_flag_impl(volatile pg_atomic_flag *ptr)
+{
+ /*
+ * Use a memory barrier + plain write if we have a native memory
+ * barrier. But don't do so if memory barriers use spinlocks - that'd lead
+ * to circularity if flags are used to implement spinlocks.
+ */
+#ifndef PG_HAVE_MEMORY_BARRIER_EMULATION
+ /* XXX: release semantics suffice? */
+ pg_memory_barrier_impl();
+ pg_atomic_write_u32_impl(ptr, 0);
+#else
+ uint32 value = 1;
+ pg_atomic_compare_exchange_u32_impl(ptr, &value, 0);
+#endif
+}
+
+#elif !defined(PG_HAVE_ATOMIC_TEST_SET_FLAG)
+# error "No pg_atomic_test_and_set provided"
+#endif /* !defined(PG_HAVE_ATOMIC_TEST_SET_FLAG) */
+
+
+#ifndef PG_HAVE_ATOMIC_INIT_U32
+#define PG_HAVE_ATOMIC_INIT_U32
+static inline void
+pg_atomic_init_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 val_)
+{
+ pg_atomic_write_u32_impl(ptr, val_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_EXCHANGE_U32) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32)
+#define PG_HAVE_ATOMIC_EXCHANGE_U32
+static inline uint32
+pg_atomic_exchange_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 xchg_)
+{
+ uint32 old;
+ while (true)
+ {
+ old = pg_atomic_read_u32_impl(ptr);
+ if (pg_atomic_compare_exchange_u32_impl(ptr, &old, xchg_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_ADD_U32) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32)
+#define PG_HAVE_ATOMIC_FETCH_ADD_U32
+static inline uint32
+pg_atomic_fetch_add_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ uint32 old;
+ while (true)
+ {
+ old = pg_atomic_read_u32_impl(ptr);
+ if (pg_atomic_compare_exchange_u32_impl(ptr, &old, old + add_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_SUB_U32) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32)
+#define PG_HAVE_ATOMIC_FETCH_SUB_U32
+static inline uint32
+pg_atomic_fetch_sub_u32_impl(volatile pg_atomic_uint32 *ptr, int32 sub_)
+{
+ return pg_atomic_fetch_add_u32_impl(ptr, -sub_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_AND_U32) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32)
+#define PG_HAVE_ATOMIC_FETCH_AND_U32
+static inline uint32
+pg_atomic_fetch_and_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 and_)
+{
+ uint32 old;
+ while (true)
+ {
+ old = pg_atomic_read_u32_impl(ptr);
+ if (pg_atomic_compare_exchange_u32_impl(ptr, &old, old & and_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_OR_U32) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U32)
+#define PG_HAVE_ATOMIC_FETCH_OR_U32
+static inline uint32
+pg_atomic_fetch_or_u32_impl(volatile pg_atomic_uint32 *ptr, uint32 or_)
+{
+ uint32 old;
+ while (true)
+ {
+ old = pg_atomic_read_u32_impl(ptr);
+ if (pg_atomic_compare_exchange_u32_impl(ptr, &old, old | or_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_ADD_FETCH_U32) && defined(PG_HAVE_ATOMIC_FETCH_ADD_U32)
+#define PG_HAVE_ATOMIC_ADD_FETCH_U32
+static inline uint32
+pg_atomic_add_fetch_u32_impl(volatile pg_atomic_uint32 *ptr, int32 add_)
+{
+ return pg_atomic_fetch_add_u32_impl(ptr, add_) + add_;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_SUB_FETCH_U32) && defined(PG_HAVE_ATOMIC_FETCH_SUB_U32)
+#define PG_HAVE_ATOMIC_SUB_FETCH_U32
+static inline uint32
+pg_atomic_sub_fetch_u32_impl(volatile pg_atomic_uint32 *ptr, int32 sub_)
+{
+ return pg_atomic_fetch_sub_u32_impl(ptr, sub_) - sub_;
+}
+#endif
+
+#ifdef PG_HAVE_ATOMIC_U64_SUPPORT
+
+#if !defined(PG_HAVE_ATOMIC_EXCHANGE_U64) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64)
+#define PG_HAVE_ATOMIC_EXCHANGE_U64
+static inline uint64
+pg_atomic_exchange_u64_impl(volatile pg_atomic_uint64 *ptr, uint64 xchg_)
+{
+ uint64 old;
+ while (true)
+ {
+ old = ptr->value;
+ if (pg_atomic_compare_exchange_u64_impl(ptr, &old, xchg_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#ifndef PG_HAVE_ATOMIC_WRITE_U64
+#define PG_HAVE_ATOMIC_WRITE_U64
+static inline void
+pg_atomic_write_u64_impl(volatile pg_atomic_uint64 *ptr, uint64 val)
+{
+ /*
+ * 64 bit writes aren't safe on all platforms. In the generic
+ * implementation implement them as an atomic exchange.
+ */
+ pg_atomic_exchange_u64_impl(ptr, val);
+}
+#endif
+
+#ifndef PG_HAVE_ATOMIC_READ_U64
+#define PG_HAVE_ATOMIC_READ_U64
+static inline uint64
+pg_atomic_read_u64_impl(volatile pg_atomic_uint64 *ptr)
+{
+ uint64 old = 0;
+
+ /*
+ * 64 bit reads aren't safe on all platforms. In the generic
+ * implementation implement them as a compare/exchange with 0. That'll
+ * fail or succeed, but always return the old value. Possible might store
+ * a 0, but only if the prev. value also was a 0 - i.e. harmless.
+ */
+ pg_atomic_compare_exchange_u64_impl(ptr, &old, 0);
+
+ return old;
+}
+#endif
+
+#ifndef PG_HAVE_ATOMIC_INIT_U64
+#define PG_HAVE_ATOMIC_INIT_U64
+static inline void
+pg_atomic_init_u64_impl(volatile pg_atomic_uint64 *ptr, uint64 val_)
+{
+ pg_atomic_write_u64_impl(ptr, val_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_ADD_U64) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64)
+#define PG_HAVE_ATOMIC_FETCH_ADD_U64
+static inline uint64
+pg_atomic_fetch_add_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ uint64 old;
+ while (true)
+ {
+ old = pg_atomic_read_u64_impl(ptr);
+ if (pg_atomic_compare_exchange_u64_impl(ptr, &old, old + add_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_SUB_U64) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64)
+#define PG_HAVE_ATOMIC_FETCH_SUB_U64
+static inline uint64
+pg_atomic_fetch_sub_u64_impl(volatile pg_atomic_uint64 *ptr, int64 sub_)
+{
+ return pg_atomic_fetch_add_u64_impl(ptr, -sub_);
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_AND_U64) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64)
+#define PG_HAVE_ATOMIC_FETCH_AND_U64
+static inline uint64
+pg_atomic_fetch_and_u64_impl(volatile pg_atomic_uint64 *ptr, uint64 and_)
+{
+ uint64 old;
+ while (true)
+ {
+ old = pg_atomic_read_u64_impl(ptr);
+ if (pg_atomic_compare_exchange_u64_impl(ptr, &old, old & and_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_FETCH_OR_U64) && defined(PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64)
+#define PG_HAVE_ATOMIC_FETCH_OR_U64
+static inline uint64
+pg_atomic_fetch_or_u64_impl(volatile pg_atomic_uint64 *ptr, uint64 or_)
+{
+ uint64 old;
+ while (true)
+ {
+ old = pg_atomic_read_u64_impl(ptr);
+ if (pg_atomic_compare_exchange_u64_impl(ptr, &old, old | or_))
+ break;
+ }
+ return old;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_ADD_FETCH_U64) && defined(PG_HAVE_ATOMIC_FETCH_ADD_U64)
+#define PG_HAVE_ATOMIC_ADD_FETCH_U64
+static inline uint64
+pg_atomic_add_fetch_u64_impl(volatile pg_atomic_uint64 *ptr, int64 add_)
+{
+ return pg_atomic_fetch_add_u64_impl(ptr, add_) + add_;
+}
+#endif
+
+#if !defined(PG_HAVE_ATOMIC_SUB_FETCH_U64) && defined(PG_HAVE_ATOMIC_FETCH_SUB_U64)
+#define PG_HAVE_ATOMIC_SUB_FETCH_U64
+static inline uint64
+pg_atomic_sub_fetch_u64_impl(volatile pg_atomic_uint64 *ptr, int64 sub_)
+{
+ return pg_atomic_fetch_sub_u64_impl(ptr, sub_) - sub_;
+}
+#endif
+
+#endif /* PG_HAVE_ATOMIC_COMPARE_EXCHANGE_U64 */
+
+#endif /* defined(PG_USE_INLINE) || defined(ATOMICS_INCLUDE_DEFINITIONS) */
diff --git a/src/include/storage/barrier.h b/src/include/storage/barrier.h
index abb82c26d4c..b36705b8624 100644
--- a/src/include/storage/barrier.h
+++ b/src/include/storage/barrier.h
@@ -13,158 +13,11 @@
#ifndef BARRIER_H
#define BARRIER_H
-#include "storage/s_lock.h"
-
-extern slock_t dummy_spinlock;
-
/*
- * A compiler barrier need not (and preferably should not) emit any actual
- * machine code, but must act as an optimization fence: the compiler must not
- * reorder loads or stores to main memory around the barrier. However, the
- * CPU may still reorder loads or stores at runtime, if the architecture's
- * memory model permits this.
- *
- * A memory barrier must act as a compiler barrier, and in addition must
- * guarantee that all loads and stores issued prior to the barrier are
- * completed before any loads or stores issued after the barrier. Unless
- * loads and stores are totally ordered (which is not the case on most
- * architectures) this requires issuing some sort of memory fencing
- * instruction.
- *
- * A read barrier must act as a compiler barrier, and in addition must
- * guarantee that any loads issued prior to the barrier are completed before
- * any loads issued after the barrier. Similarly, a write barrier acts
- * as a compiler barrier, and also orders stores. Read and write barriers
- * are thus weaker than a full memory barrier, but stronger than a compiler
- * barrier. In practice, on machines with strong memory ordering, read and
- * write barriers may require nothing more than a compiler barrier.
- *
- * For an introduction to using memory barriers within the PostgreSQL backend,
- * see src/backend/storage/lmgr/README.barrier
+ * This used to be a separate file, full of compiler/architecture
+ * dependent defines, but it's not included in the atomics.h
+ * infrastructure and just kept for backward compatibility.
*/
-
-#if defined(DISABLE_BARRIERS)
-
-/*
- * Fall through to the spinlock-based implementation.
- */
-#elif defined(__INTEL_COMPILER)
-
-/*
- * icc defines __GNUC__, but doesn't support gcc's inline asm syntax
- */
-#if defined(__ia64__) || defined(__ia64)
-#define pg_memory_barrier() __mf()
-#elif defined(__i386__) || defined(__x86_64__)
-#define pg_memory_barrier() _mm_mfence()
-#endif
-
-#define pg_compiler_barrier() __memory_barrier()
-#elif defined(__GNUC__)
-
-/* This works on any architecture, since it's only talking to GCC itself. */
-#define pg_compiler_barrier() __asm__ __volatile__("" : : : "memory")
-
-#if defined(__i386__)
-
-/*
- * i386 does not allow loads to be reordered with other loads, or stores to be
- * reordered with other stores, but a load can be performed before a subsequent
- * store.
- *
- * "lock; addl" has worked for longer than "mfence".
- */
-#define pg_memory_barrier() \
- __asm__ __volatile__ ("lock; addl $0,0(%%esp)" : : : "memory", "cc")
-#define pg_read_barrier() pg_compiler_barrier()
-#define pg_write_barrier() pg_compiler_barrier()
-#elif defined(__x86_64__) /* 64 bit x86 */
-
-/*
- * x86_64 has similar ordering characteristics to i386.
- *
- * Technically, some x86-ish chips support uncached memory access and/or
- * special instructions that are weakly ordered. In those cases we'd need
- * the read and write barriers to be lfence and sfence. But since we don't
- * do those things, a compiler barrier should be enough.
- */
-#define pg_memory_barrier() \
- __asm__ __volatile__ ("lock; addl $0,0(%%rsp)" : : : "memory", "cc")
-#define pg_read_barrier() pg_compiler_barrier()
-#define pg_write_barrier() pg_compiler_barrier()
-#elif defined(__ia64__) || defined(__ia64)
-
-/*
- * Itanium is weakly ordered, so read and write barriers require a full
- * fence.
- */
-#define pg_memory_barrier() __asm__ __volatile__ ("mf" : : : "memory")
-#elif defined(__ppc__) || defined(__powerpc__) || defined(__ppc64__) || defined(__powerpc64__)
-
-/*
- * lwsync orders loads with respect to each other, and similarly with stores.
- * But a load can be performed before a subsequent store, so sync must be used
- * for a full memory barrier.
- */
-#define pg_memory_barrier() __asm__ __volatile__ ("sync" : : : "memory")
-#define pg_read_barrier() __asm__ __volatile__ ("lwsync" : : : "memory")
-#define pg_write_barrier() __asm__ __volatile__ ("lwsync" : : : "memory")
-
-#elif defined(__hppa) || defined(__hppa__) /* HP PA-RISC */
-
-/* HPPA doesn't do either read or write reordering */
-#define pg_memory_barrier() pg_compiler_barrier()
-#elif __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 1)
-
-/*
- * If we're on GCC 4.1.0 or higher, we should be able to get a memory
- * barrier out of this compiler built-in. But we prefer to rely on our
- * own definitions where possible, and use this only as a fallback.
- */
-#define pg_memory_barrier() __sync_synchronize()
-#endif
-#elif defined(__ia64__) || defined(__ia64)
-
-#define pg_compiler_barrier() _Asm_sched_fence()
-#define pg_memory_barrier() _Asm_mf()
-#elif defined(WIN32_ONLY_COMPILER)
-
-/* Should work on both MSVC and Borland. */
-#include <intrin.h>
-#pragma intrinsic(_ReadWriteBarrier)
-#define pg_compiler_barrier() _ReadWriteBarrier()
-#define pg_memory_barrier() MemoryBarrier()
-#endif
-
-/*
- * If we have no memory barrier implementation for this architecture, we
- * fall back to acquiring and releasing a spinlock. This might, in turn,
- * fall back to the semaphore-based spinlock implementation, which will be
- * amazingly slow.
- *
- * It's not self-evident that every possible legal implementation of a
- * spinlock acquire-and-release would be equivalent to a full memory barrier.
- * For example, I'm not sure that Itanium's acq and rel add up to a full
- * fence. But all of our actual implementations seem OK in this regard.
- */
-#if !defined(pg_memory_barrier)
-#define pg_memory_barrier() \
- do { S_LOCK(&dummy_spinlock); S_UNLOCK(&dummy_spinlock); } while (0)
-#endif
-
-/*
- * If read or write barriers are undefined, we upgrade them to full memory
- * barriers.
- *
- * If a compiler barrier is unavailable, you probably don't want a full
- * memory barrier instead, so if you have a use case for a compiler barrier,
- * you'd better use #ifdef.
- */
-#if !defined(pg_read_barrier)
-#define pg_read_barrier() pg_memory_barrier()
-#endif
-#if !defined(pg_write_barrier)
-#define pg_write_barrier() pg_memory_barrier()
-#endif
+#include "port/atomics.h"
#endif /* BARRIER_H */
diff --git a/src/include/storage/s_lock.h b/src/include/storage/s_lock.h
index 5f0ad7aa63a..79bc125c8a1 100644
--- a/src/include/storage/s_lock.h
+++ b/src/include/storage/s_lock.h
@@ -309,7 +309,7 @@ tas(volatile slock_t *lock)
* than other widths.
*/
#if defined(__arm__) || defined(__arm) || defined(__aarch64__) || defined(__aarch64)
-#ifdef HAVE_GCC_INT_ATOMICS
+#ifdef HAVE_GCC__SYNC_INT32_TAS
#define HAS_TEST_AND_SET
#define TAS(lock) tas(lock)
@@ -324,7 +324,7 @@ tas(volatile slock_t *lock)
#define S_UNLOCK(lock) __sync_lock_release(lock)
-#endif /* HAVE_GCC_INT_ATOMICS */
+#endif /* HAVE_GCC__SYNC_INT32_TAS */
#endif /* __arm__ || __arm || __aarch64__ || __aarch64 */
@@ -889,12 +889,12 @@ typedef int slock_t;
extern bool s_lock_free_sema(volatile slock_t *lock);
extern void s_unlock_sema(volatile slock_t *lock);
-extern void s_init_lock_sema(volatile slock_t *lock);
+extern void s_init_lock_sema(volatile slock_t *lock, bool nested);
extern int tas_sema(volatile slock_t *lock);
#define S_LOCK_FREE(lock) s_lock_free_sema(lock)
#define S_UNLOCK(lock) s_unlock_sema(lock)
-#define S_INIT_LOCK(lock) s_init_lock_sema(lock)
+#define S_INIT_LOCK(lock) s_init_lock_sema(lock, false)
#define TAS(lock) tas_sema(lock)
@@ -955,6 +955,7 @@ extern int tas(volatile slock_t *lock); /* in port/.../tas.s, or
#define TAS_SPIN(lock) TAS(lock)
#endif /* TAS_SPIN */
+extern slock_t dummy_spinlock;
/*
* Platform-independent out-of-line support routines
diff --git a/src/test/regress/expected/lock.out b/src/test/regress/expected/lock.out
index 0d7c3ba4f3a..fd273445030 100644
--- a/src/test/regress/expected/lock.out
+++ b/src/test/regress/expected/lock.out
@@ -60,3 +60,11 @@ DROP TABLE lock_tbl2;
DROP TABLE lock_tbl1;
DROP SCHEMA lock_schema1 CASCADE;
DROP ROLE regress_rol_lock1;
+-- atomic ops tests
+RESET search_path;
+SELECT test_atomic_ops();
+ test_atomic_ops
+-----------------
+ t
+(1 row)
+
diff --git a/src/test/regress/input/create_function_1.source b/src/test/regress/input/create_function_1.source
index aef15182874..1fded846a05 100644
--- a/src/test/regress/input/create_function_1.source
+++ b/src/test/regress/input/create_function_1.source
@@ -57,6 +57,11 @@ CREATE FUNCTION make_tuple_indirect (record)
AS '@libdir@/regress@DLSUFFIX@'
LANGUAGE C STRICT;
+CREATE FUNCTION test_atomic_ops()
+ RETURNS bool
+ AS '@libdir@/regress@DLSUFFIX@'
+ LANGUAGE C;
+
-- Things that shouldn't work:
CREATE FUNCTION test1 (int) RETURNS int LANGUAGE SQL
diff --git a/src/test/regress/output/create_function_1.source b/src/test/regress/output/create_function_1.source
index 9761d127e1f..9926c9073e7 100644
--- a/src/test/regress/output/create_function_1.source
+++ b/src/test/regress/output/create_function_1.source
@@ -51,6 +51,10 @@ CREATE FUNCTION make_tuple_indirect (record)
RETURNS record
AS '@libdir@/regress@DLSUFFIX@'
LANGUAGE C STRICT;
+CREATE FUNCTION test_atomic_ops()
+ RETURNS bool
+ AS '@libdir@/regress@DLSUFFIX@'
+ LANGUAGE C;
-- Things that shouldn't work:
CREATE FUNCTION test1 (int) RETURNS int LANGUAGE SQL
AS 'SELECT ''not an integer'';';
diff --git a/src/test/regress/regress.c b/src/test/regress/regress.c
index 09e027c1e5b..14871716c96 100644
--- a/src/test/regress/regress.c
+++ b/src/test/regress/regress.c
@@ -18,6 +18,7 @@
#include "executor/executor.h"
#include "executor/spi.h"
#include "miscadmin.h"
+#include "port/atomics.h"
#include "utils/builtins.h"
#include "utils/geo_decls.h"
#include "utils/rel.h"
@@ -865,3 +866,241 @@ wait_pid(PG_FUNCTION_ARGS)
PG_RETURN_VOID();
}
+
+#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION
+static void
+test_atomic_flag(void)
+{
+ pg_atomic_flag flag;
+
+ pg_atomic_init_flag(&flag);
+
+ if (!pg_atomic_unlocked_test_flag(&flag))
+ elog(ERROR, "flag: unexpectedly set");
+
+ if (!pg_atomic_test_set_flag(&flag))
+ elog(ERROR, "flag: couldn't set");
+
+ if (pg_atomic_unlocked_test_flag(&flag))
+ elog(ERROR, "flag: unexpectedly unset");
+
+ if (pg_atomic_test_set_flag(&flag))
+ elog(ERROR, "flag: set spuriously #2");
+
+ pg_atomic_clear_flag(&flag);
+
+ if (!pg_atomic_unlocked_test_flag(&flag))
+ elog(ERROR, "flag: unexpectedly set #2");
+
+ if (!pg_atomic_test_set_flag(&flag))
+ elog(ERROR, "flag: couldn't set");
+
+ pg_atomic_clear_flag(&flag);
+}
+#endif /* PG_HAVE_ATOMIC_FLAG_SIMULATION */
+
+static void
+test_atomic_uint32(void)
+{
+ pg_atomic_uint32 var;
+ uint32 expected;
+ int i;
+
+ pg_atomic_init_u32(&var, 0);
+
+ if (pg_atomic_read_u32(&var) != 0)
+ elog(ERROR, "atomic_read_u32() #1 wrong");
+
+ pg_atomic_write_u32(&var, 3);
+
+ if (pg_atomic_read_u32(&var) != 3)
+ elog(ERROR, "atomic_read_u32() #2 wrong");
+
+ if (pg_atomic_fetch_add_u32(&var, 1) != 3)
+ elog(ERROR, "atomic_fetch_add_u32() #1 wrong");
+
+ if (pg_atomic_fetch_sub_u32(&var, 1) != 4)
+ elog(ERROR, "atomic_fetch_sub_u32() #1 wrong");
+
+ if (pg_atomic_sub_fetch_u32(&var, 3) != 0)
+ elog(ERROR, "atomic_sub_fetch_u32() #1 wrong");
+
+ if (pg_atomic_add_fetch_u32(&var, 10) != 10)
+ elog(ERROR, "atomic_add_fetch_u32() #1 wrong");
+
+ if (pg_atomic_exchange_u32(&var, 5) != 10)
+ elog(ERROR, "pg_atomic_exchange_u32() #1 wrong");
+
+ if (pg_atomic_exchange_u32(&var, 0) != 5)
+ elog(ERROR, "pg_atomic_exchange_u32() #0 wrong");
+
+ /* test around numerical limits */
+ if (pg_atomic_fetch_add_u32(&var, INT_MAX) != 0)
+ elog(ERROR, "pg_atomic_fetch_add_u32() #2 wrong");
+
+ if (pg_atomic_fetch_add_u32(&var, INT_MAX) != INT_MAX)
+ elog(ERROR, "pg_atomic_add_fetch_u32() #3 wrong");
+
+ pg_atomic_fetch_add_u32(&var, 1); /* top up to UINT_MAX */
+
+ if (pg_atomic_read_u32(&var) != UINT_MAX)
+ elog(ERROR, "atomic_read_u32() #2 wrong");
+
+ if (pg_atomic_fetch_sub_u32(&var, INT_MAX) != UINT_MAX)
+ elog(ERROR, "pg_atomic_fetch_sub_u32() #2 wrong");
+
+ if (pg_atomic_read_u32(&var) != (uint32)INT_MAX + 1)
+ elog(ERROR, "atomic_read_u32() #3 wrong: %u", pg_atomic_read_u32(&var));
+
+ expected = pg_atomic_sub_fetch_u32(&var, INT_MAX);
+ if (expected != 1)
+ elog(ERROR, "pg_atomic_sub_fetch_u32() #3 wrong: %u", expected);
+
+ pg_atomic_sub_fetch_u32(&var, 1);
+
+ /* fail exchange because of old expected */
+ expected = 10;
+ if (pg_atomic_compare_exchange_u32(&var, &expected, 1))
+ elog(ERROR, "atomic_compare_exchange_u32() changed value spuriously");
+
+ /* CAS is allowed to fail due to interrupts, try a couple of times */
+ for (i = 0; i < 1000; i++)
+ {
+ expected = 0;
+ if (!pg_atomic_compare_exchange_u32(&var, &expected, 1))
+ break;
+ }
+ if (i == 1000)
+ elog(ERROR, "atomic_compare_exchange_u32() never succeeded");
+ if (pg_atomic_read_u32(&var) != 1)
+ elog(ERROR, "atomic_compare_exchange_u32() didn't set value properly");
+
+ pg_atomic_write_u32(&var, 0);
+
+ /* try setting flagbits */
+ if (pg_atomic_fetch_or_u32(&var, 1) & 1)
+ elog(ERROR, "pg_atomic_fetch_or_u32() #1 wrong");
+
+ if (!(pg_atomic_fetch_or_u32(&var, 2) & 1))
+ elog(ERROR, "pg_atomic_fetch_or_u32() #2 wrong");
+
+ if (pg_atomic_read_u32(&var) != 3)
+ elog(ERROR, "invalid result after pg_atomic_fetch_or_u32()");
+
+ /* try clearing flagbits */
+ if ((pg_atomic_fetch_and_u32(&var, ~2) & 3) != 3)
+ elog(ERROR, "pg_atomic_fetch_and_u32() #1 wrong");
+
+ if (pg_atomic_fetch_and_u32(&var, ~1) != 1)
+ elog(ERROR, "pg_atomic_fetch_and_u32() #2 wrong: is %u",
+ pg_atomic_read_u32(&var));
+ /* no bits set anymore */
+ if (pg_atomic_fetch_and_u32(&var, ~0) != 0)
+ elog(ERROR, "pg_atomic_fetch_and_u32() #3 wrong");
+}
+
+#ifdef PG_HAVE_ATOMIC_U64_SUPPORT
+static void
+test_atomic_uint64(void)
+{
+ pg_atomic_uint64 var;
+ uint64 expected;
+ int i;
+
+ pg_atomic_init_u64(&var, 0);
+
+ if (pg_atomic_read_u64(&var) != 0)
+ elog(ERROR, "atomic_read_u64() #1 wrong");
+
+ pg_atomic_write_u64(&var, 3);
+
+ if (pg_atomic_read_u64(&var) != 3)
+ elog(ERROR, "atomic_read_u64() #2 wrong");
+
+ if (pg_atomic_fetch_add_u64(&var, 1) != 3)
+ elog(ERROR, "atomic_fetch_add_u64() #1 wrong");
+
+ if (pg_atomic_fetch_sub_u64(&var, 1) != 4)
+ elog(ERROR, "atomic_fetch_sub_u64() #1 wrong");
+
+ if (pg_atomic_sub_fetch_u64(&var, 3) != 0)
+ elog(ERROR, "atomic_sub_fetch_u64() #1 wrong");
+
+ if (pg_atomic_add_fetch_u64(&var, 10) != 10)
+ elog(ERROR, "atomic_add_fetch_u64() #1 wrong");
+
+ if (pg_atomic_exchange_u64(&var, 5) != 10)
+ elog(ERROR, "pg_atomic_exchange_u64() #1 wrong");
+
+ if (pg_atomic_exchange_u64(&var, 0) != 5)
+ elog(ERROR, "pg_atomic_exchange_u64() #0 wrong");
+
+ /* fail exchange because of old expected */
+ expected = 10;
+ if (pg_atomic_compare_exchange_u64(&var, &expected, 1))
+ elog(ERROR, "atomic_compare_exchange_u64() changed value spuriously");
+
+ /* CAS is allowed to fail due to interrupts, try a couple of times */
+ for (i = 0; i < 100; i++)
+ {
+ expected = 0;
+ if (!pg_atomic_compare_exchange_u64(&var, &expected, 1))
+ break;
+ }
+ if (i == 100)
+ elog(ERROR, "atomic_compare_exchange_u64() never succeeded");
+ if (pg_atomic_read_u64(&var) != 1)
+ elog(ERROR, "atomic_compare_exchange_u64() didn't set value properly");
+
+ pg_atomic_write_u64(&var, 0);
+
+ /* try setting flagbits */
+ if (pg_atomic_fetch_or_u64(&var, 1) & 1)
+ elog(ERROR, "pg_atomic_fetch_or_u64() #1 wrong");
+
+ if (!(pg_atomic_fetch_or_u64(&var, 2) & 1))
+ elog(ERROR, "pg_atomic_fetch_or_u64() #2 wrong");
+
+ if (pg_atomic_read_u64(&var) != 3)
+ elog(ERROR, "invalid result after pg_atomic_fetch_or_u64()");
+
+ /* try clearing flagbits */
+ if ((pg_atomic_fetch_and_u64(&var, ~2) & 3) != 3)
+ elog(ERROR, "pg_atomic_fetch_and_u64() #1 wrong");
+
+ if (pg_atomic_fetch_and_u64(&var, ~1) != 1)
+ elog(ERROR, "pg_atomic_fetch_and_u64() #2 wrong: is "UINT64_FORMAT,
+ pg_atomic_read_u64(&var));
+ /* no bits set anymore */
+ if (pg_atomic_fetch_and_u64(&var, ~0) != 0)
+ elog(ERROR, "pg_atomic_fetch_and_u64() #3 wrong");
+}
+#endif /* PG_HAVE_ATOMIC_U64_SUPPORT */
+
+
+PG_FUNCTION_INFO_V1(test_atomic_ops);
+Datum
+test_atomic_ops(PG_FUNCTION_ARGS)
+{
+ /* ---
+ * Can't run the test under the semaphore emulation, it doesn't handle
+ * checking two edge cases well:
+ * - pg_atomic_unlocked_test_flag() always returns true
+ * - locking a already locked flag blocks
+ * it seems better to not test the semaphore fallback here, than weaken
+ * the checks for the other cases. The semaphore code will be the same
+ * everywhere, whereas the efficient implementations wont.
+ * ---
+ */
+#ifndef PG_HAVE_ATOMIC_FLAG_SIMULATION
+ test_atomic_flag();
+#endif
+
+ test_atomic_uint32();
+
+#ifdef PG_HAVE_ATOMIC_U64_SUPPORT
+ test_atomic_uint64();
+#endif
+
+ PG_RETURN_BOOL(true);
+}
diff --git a/src/test/regress/sql/lock.sql b/src/test/regress/sql/lock.sql
index dda212f78c6..567e8bccf1b 100644
--- a/src/test/regress/sql/lock.sql
+++ b/src/test/regress/sql/lock.sql
@@ -64,3 +64,8 @@ DROP TABLE lock_tbl2;
DROP TABLE lock_tbl1;
DROP SCHEMA lock_schema1 CASCADE;
DROP ROLE regress_rol_lock1;
+
+
+-- atomic ops tests
+RESET search_path;
+SELECT test_atomic_ops();