[libcxx] Add atomic_support.h header to src that handles needed atomic operations.

Summary:
In some places in libc++ we need to use the `__atomic_*` builtins. This patch adds a header that provides access to those builtins in a uniform way from within the dylib source.

If the compiler building the dylib does not support these builtins then a warning is issued.

Only relaxed loads are needed within the headers. A singe function to do these relaxed loads has been added to `<memory>`.

This patch applies the new atomic builtins to `__shared_count` and `call_once`.

Reviewers: mclow.lists

Subscribers: majnemer, jroelofs, cfe-commits

Differential Revision: http://reviews.llvm.org/D10406

llvm-svn: 241532
Cr-Mirrored-From: sso://chromium.googlesource.com/_direct/external/github.com/llvm/llvm-project
Cr-Mirrored-Commit: 1faf289e27bcb54e54b2e3e0f492d6f54d59cd9e
diff --git a/src/memory.cpp b/src/memory.cpp
index 8a4eb34..66fb143 100644
--- a/src/memory.cpp
+++ b/src/memory.cpp
@@ -13,24 +13,28 @@
 #include "mutex"
 #include "thread"
 #endif
+#include "support/atomic_support.h"
 
 _LIBCPP_BEGIN_NAMESPACE_STD
 
 namespace
 {
 
+// NOTE: Relaxed and acq/rel atomics (for increment and decrement respectively)
+// should be sufficient for thread safety.
+// See https://llvm.org/bugs/show_bug.cgi?id=22803
 template <class T>
 inline T
 increment(T& t) _NOEXCEPT
 {
-    return __sync_add_and_fetch(&t, 1);
+    return __libcpp_atomic_add(&t, 1, _AO_Relaxed);
 }
 
 template <class T>
 inline T
 decrement(T& t) _NOEXCEPT
 {
-    return __sync_add_and_fetch(&t, -1);
+    return __libcpp_atomic_add(&t, -1, _AO_Acq_Rel);
 }
 
 }  // namespace
@@ -99,14 +103,13 @@
 __shared_weak_count*
 __shared_weak_count::lock() _NOEXCEPT
 {
-    long object_owners = __shared_owners_;
+    long object_owners = __libcpp_atomic_load(&__shared_owners_);
     while (object_owners != -1)
     {
-        if (__sync_bool_compare_and_swap(&__shared_owners_,
-                                         object_owners,
-                                         object_owners+1))
+        if (__libcpp_atomic_compare_exchange(&__shared_owners_,
+                                             &object_owners,
+                                             object_owners+1))
             return this;
-        object_owners = __shared_owners_;
     }
     return 0;
 }
diff --git a/src/mutex.cpp b/src/mutex.cpp
index e56271d..5f8ba0a 100644
--- a/src/mutex.cpp
+++ b/src/mutex.cpp
@@ -12,6 +12,7 @@
 #include "limits"
 #include "system_error"
 #include "cassert"
+#include "support/atomic_support.h"
 
 _LIBCPP_BEGIN_NAMESPACE_STD
 #ifndef _LIBCPP_HAS_NO_THREADS
@@ -220,6 +221,9 @@
 static pthread_cond_t  cv  = PTHREAD_COND_INITIALIZER;
 #endif
 
+/// NOTE: Changes to flag are done via relaxed atomic stores
+///       even though the accesses are protected by a mutex because threads
+///       just entering 'call_once` concurrently read from flag.
 void
 __call_once(volatile unsigned long& flag, void* arg, void(*func)(void*))
 {
@@ -252,11 +256,11 @@
         try
         {
 #endif  // _LIBCPP_NO_EXCEPTIONS
-            flag = 1;
+            __libcpp_relaxed_store(&flag, 1ul);
             pthread_mutex_unlock(&mut);
             func(arg);
             pthread_mutex_lock(&mut);
-            flag = ~0ul;
+            __libcpp_relaxed_store(&flag, ~0ul);
             pthread_mutex_unlock(&mut);
             pthread_cond_broadcast(&cv);
 #ifndef _LIBCPP_NO_EXCEPTIONS
@@ -264,7 +268,7 @@
         catch (...)
         {
             pthread_mutex_lock(&mut);
-            flag = 0ul;
+            __libcpp_relaxed_store(&flag, 0ul);
             pthread_mutex_unlock(&mut);
             pthread_cond_broadcast(&cv);
             throw;
diff --git a/src/support/atomic_support.h b/src/support/atomic_support.h
new file mode 100644
index 0000000..e738a51
--- /dev/null
+++ b/src/support/atomic_support.h
@@ -0,0 +1,142 @@
+#ifndef ATOMIC_SUPPORT_H
+#define ATOMIC_SUPPORT_H
+
+#include "__config"
+#include "memory" // for __libcpp_relaxed_load
+
+#if defined(__clang__) && __has_builtin(__atomic_load_n)             \
+                       && __has_builtin(__atomic_store_n)            \
+                       && __has_builtin(__atomic_add_fetch)          \
+                       && __has_builtin(__atomic_compare_exchange_n) \
+                       && defined(__ATOMIC_RELAXED)                  \
+                       && defined(__ATOMIC_CONSUME)                  \
+                       && defined(__ATOMIC_ACQUIRE)                  \
+                       && defined(__ATOMIC_RELEASE)                  \
+                       && defined(__ATOMIC_ACQ_REL)                  \
+                       && defined(__ATOMIC_SEQ_CST)
+#   define _LIBCPP_HAS_ATOMIC_BUILTINS
+#elif !defined(__clang__) && defined(_GNUC_VER) && _GNUC_VER >= 407
+#   define _LIBCPP_HAS_ATOMIC_BUILTINS
+#endif
+
+#if !defined(_LIBCPP_HAS_ATOMIC_BUILTINS) && !defined(_LIBCPP_HAS_NO_THREADS)
+# if defined(_MSC_VER) && !defined(__clang__)
+    _LIBCPP_WARNING("Building libc++ without __atomic builtins is unsupported")
+# else
+#   warning Building libc++ without __atomic builtins is unsupported
+# endif
+#endif
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+
+namespace {
+
+#if defined(_LIBCPP_HAS_ATOMIC_BUILTINS) && !defined(_LIBCPP_HAS_NO_THREADS)
+
+enum __libcpp_atomic_order {
+    _AO_Relaxed = __ATOMIC_RELAXED,
+    _AO_Consume = __ATOMIC_CONSUME,
+    _AO_Aquire  = __ATOMIC_ACQUIRE,
+    _AO_Release = __ATOMIC_RELEASE,
+    _AO_Acq_Rel = __ATOMIC_ACQ_REL,
+    _AO_Seq     = __ATOMIC_SEQ_CST
+};
+
+template <class _ValueType, class _FromType>
+inline _LIBCPP_INLINE_VISIBILITY
+void __libcpp_atomic_store(_ValueType* __dest, _FromType __val,
+                           int __order = _AO_Seq)
+{
+    __atomic_store_n(__dest, __val, __order);
+}
+
+template <class _ValueType, class _FromType>
+inline _LIBCPP_INLINE_VISIBILITY
+void __libcpp_relaxed_store(_ValueType* __dest, _FromType __val)
+{
+    __atomic_store_n(__dest, __val, _AO_Relaxed);
+}
+
+template <class _ValueType>
+inline _LIBCPP_INLINE_VISIBILITY
+_ValueType __libcpp_atomic_load(_ValueType const* __val,
+                                int __order = _AO_Seq)
+{
+    return __atomic_load_n(__val, __order);
+}
+
+template <class _ValueType, class _AddType>
+inline _LIBCPP_INLINE_VISIBILITY
+_ValueType __libcpp_atomic_add(_ValueType* __val, _AddType __a,
+                               int __order = _AO_Seq)
+{
+    return __atomic_add_fetch(__val, __a, __order);
+}
+
+template <class _ValueType>
+inline _LIBCPP_INLINE_VISIBILITY
+bool __libcpp_atomic_compare_exchange(_ValueType* __val,
+    _ValueType* __expected, _ValueType __after,
+    int __success_order = _AO_Seq,
+    int __fail_order = _AO_Seq)
+{
+    return __atomic_compare_exchange_n(__val, __expected, __after, true,
+                                       __success_order, __fail_order);
+}
+
+#else // _LIBCPP_HAS_NO_THREADS
+
+enum __libcpp_atomic_order {
+    _AO_Relaxed,
+    _AO_Consume,
+    _AO_Acquire,
+    _AO_Release,
+    _AO_Acq_Rel,
+    _AO_Seq
+};
+
+template <class _ValueType, class _FromType>
+inline _LIBCPP_INLINE_VISIBILITY
+void __libcpp_atomic_store(_ValueType* __dest, _FromType __val,
+                           int = 0)
+{
+    *__dest = __val;
+}
+
+template <class _ValueType>
+inline _LIBCPP_INLINE_VISIBILITY
+_ValueType __libcpp_atomic_load(_ValueType const* __val,
+                                int = 0)
+{
+    return *__val;
+}
+
+template <class _ValueType, class _AddType>
+inline _LIBCPP_INLINE_VISIBILITY
+_ValueType __libcpp_atomic_add(_ValueType* __val, _AddType __a,
+                               int = 0)
+{
+    return *__val += __a;
+}
+
+template <class _ValueType>
+inline _LIBCPP_INLINE_VISIBILITY
+bool __libcpp_atomic_compare_exchange(_ValueType* __val,
+    _ValueType* __expected, _ValueType __after,
+    int = 0, int = 0)
+{
+    if (*__val == *__expected) {
+        *__val = __after;
+        return true;
+    }
+    *__expected = *__val;
+    return false;
+}
+
+#endif // _LIBCPP_HAS_NO_THREADS
+
+} // end namespace
+
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // ATOMIC_SUPPORT_H