[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
diff --git a/libcxx/src/mutex.cpp b/libcxx/src/mutex.cpp
index e56271d..5f8ba0a 100644
--- a/libcxx/src/mutex.cpp
+++ b/libcxx/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;