[libcxx] Introduce an externally-threaded libc++ variant.

This patch further decouples libc++ from pthread, allowing libc++ to be built
against other threading systems. There are two main use cases:

- Building libc++ against a thread library other than pthreads.

- Building libc++ with an "external" thread API, allowing a separate library to
  provide the implementation of that API.

The two use cases are quite similar, the second one being sligtly more
de-coupled than the first. The cmake option LIBCXX_HAS_EXTERNAL_THREAD_API
enables both kinds of builds. One needs to place an <__external_threading>
header file containing an implementation of the "libc++ thread API" declared
in the <__threading_support> header.

For the second use case, the implementation of the libc++ thread API can
delegate to a custom "external" thread API where the implementation of this
external API is provided in a seperate library. This mechanism allows toolchain
vendors to distribute a build of libc++ with a custom thread-porting-layer API
(which is the "external" API above), platform vendors (recipients of the
toolchain/libc++) are then required to provide their implementation of this API
to be linked with (end-user) C++ programs.

Note that the second use case still requires establishing the basic types that
get passed between the external thread library and the libc++ library
(e.g. __libcpp_mutex_t). These cannot be opaque pointer types (libc++ sources
won't compile otherwise). It should also be noted that the second use case can
have a slight performance penalty; as all the thread constructs need to cross a
library boundary through an additional function call.

When the header <__external_threading> is omitted, libc++ is built with the
"libc++ thread API" (declared in <__threading_support>) as the "external" thread
API (basic types are pthread based). An implementation (pthread based) of this
API is provided in test/support/external_threads.cpp, which is built into a
separate DSO and linked in when running the libc++ test suite. A test run
therefore demonstrates the second use case (less the intermediate custom API).

Differential revision: https://reviews.llvm.org/D21968

Reviewers: bcraig, compnerd, EricWF, mclow.lists

git-svn-id: https://llvm.org/svn/llvm-project/libcxx/trunk@281179 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/include/__config b/include/__config
index b462191..c4e1101 100644
--- a/include/__config
+++ b/include/__config
@@ -831,7 +831,9 @@
 #endif
 
 // Thread API
-#if !defined(_LIBCPP_HAS_NO_THREADS) && !defined(_LIBCPP_HAS_THREAD_API_PTHREAD)
+#if !defined(_LIBCPP_HAS_NO_THREADS) && \
+    !defined(_LIBCPP_HAS_THREAD_API_PTHREAD) && \
+    !defined(_LIBCPP_HAS_THREAD_API_EXTERNAL)
 # if defined(__FreeBSD__) || \
     defined(__NetBSD__) || \
     defined(__linux__) || \
@@ -849,6 +851,11 @@
          _LIBCPP_HAS_NO_THREADS is not defined.
 #endif
 
+#if defined(_LIBCPP_HAS_NO_THREADS) && defined(_LIBCPP_HAS_THREAD_API_EXTERNAL)
+#  error _LIBCPP_HAS_EXTERNAL_THREAD_API may not be defined when \
+         _LIBCPP_HAS_NO_THREADS is defined.
+#endif
+
 #if defined(_LIBCPP_HAS_NO_MONOTONIC_CLOCK) && !defined(_LIBCPP_HAS_NO_THREADS)
 #  error _LIBCPP_HAS_NO_MONOTONIC_CLOCK may only be defined when \
          _LIBCPP_HAS_NO_THREADS is defined.
diff --git a/include/__config_site.in b/include/__config_site.in
index 6c2b7bb..dce30bc 100644
--- a/include/__config_site.in
+++ b/include/__config_site.in
@@ -20,5 +20,6 @@
 #cmakedefine _LIBCPP_HAS_NO_THREAD_UNSAFE_C_FUNCTIONS
 #cmakedefine _LIBCPP_HAS_MUSL_LIBC
 #cmakedefine _LIBCPP_HAS_THREAD_API_PTHREAD
+#cmakedefine _LIBCPP_HAS_THREAD_API_EXTERNAL
 
 #endif // _LIBCPP_CONFIG_SITE
diff --git a/include/__threading_support b/include/__threading_support
index c9a4ea9..b36a52e 100644
--- a/include/__threading_support
+++ b/include/__threading_support
@@ -19,20 +19,83 @@
 
 #ifndef _LIBCPP_HAS_NO_THREADS
 
-#if defined(_LIBCPP_HAS_THREAD_API_PTHREAD)
+#if defined(_LIBCPP_HAS_THREAD_API_EXTERNAL) && (!defined(__has_include) || __has_include(<__external_threading>))
+#include <__external_threading>
+#else
 #include <pthread.h>
 #include <sched.h>
 #endif
 
+#if defined(_LIBCPP_HAS_THREAD_API_EXTERNAL)
+#define _LIBCPP_THREAD_ABI_VISIBILITY _LIBCPP_FUNC_VIS
+#else
+#define _LIBCPP_THREAD_ABI_VISIBILITY inline _LIBCPP_INLINE_VISIBILITY
+#endif
+
 _LIBCPP_BEGIN_NAMESPACE_STD
 
-#if defined(_LIBCPP_HAS_THREAD_API_PTHREAD)
-
 // Mutex
-#define _LIBCPP_MUTEX_INITIALIZER PTHREAD_MUTEX_INITIALIZER
 typedef pthread_mutex_t __libcpp_mutex_t;
+#define _LIBCPP_MUTEX_INITIALIZER PTHREAD_MUTEX_INITIALIZER
 
-inline _LIBCPP_ALWAYS_INLINE
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_recursive_mutex_init(__libcpp_mutex_t* __m);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_mutex_lock(__libcpp_mutex_t* __m);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_mutex_trylock(__libcpp_mutex_t* __m);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_mutex_unlock(__libcpp_mutex_t* __m);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_mutex_destroy(__libcpp_mutex_t* __m);
+
+// Condition variable
+typedef pthread_cond_t __libcpp_condvar_t;
+#define _LIBCPP_CONDVAR_INITIALIZER PTHREAD_COND_INITIALIZER
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_condvar_signal(__libcpp_condvar_t* __cv);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_condvar_broadcast(__libcpp_condvar_t* __cv);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_condvar_wait(__libcpp_condvar_t* __cv, __libcpp_mutex_t* __m);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_condvar_timedwait(__libcpp_condvar_t* __cv, __libcpp_mutex_t* __m, timespec* __ts);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_condvar_destroy(__libcpp_condvar_t* __cv);
+
+// Thread id
+typedef pthread_t __libcpp_thread_id;
+_LIBCPP_THREAD_ABI_VISIBILITY
+bool __libcpp_thread_id_equal(__libcpp_thread_id t1, __libcpp_thread_id t2);
+_LIBCPP_THREAD_ABI_VISIBILITY
+bool __libcpp_thread_id_less(__libcpp_thread_id t1, __libcpp_thread_id t2);
+
+// Thread
+typedef pthread_t __libcpp_thread_t;
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_thread_create(__libcpp_thread_t* __t, void* (*__func)(void*), void* __arg);
+_LIBCPP_THREAD_ABI_VISIBILITY
+__libcpp_thread_id __libcpp_thread_get_current_id();
+_LIBCPP_THREAD_ABI_VISIBILITY
+__libcpp_thread_id __libcpp_thread_get_id(const __libcpp_thread_t* __t);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_thread_join(__libcpp_thread_t* __t);
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_thread_detach(__libcpp_thread_t* __t);
+_LIBCPP_THREAD_ABI_VISIBILITY
+void __libcpp_thread_yield();
+
+// Thread local storage
+typedef pthread_key_t __libcpp_tls_key;
+_LIBCPP_THREAD_ABI_VISIBILITY
+int __libcpp_tls_create(__libcpp_tls_key* __key, void (*__at_exit)(void*));
+_LIBCPP_THREAD_ABI_VISIBILITY
+void* __libcpp_tls_get(__libcpp_tls_key __key);
+_LIBCPP_THREAD_ABI_VISIBILITY
+void __libcpp_tls_set(__libcpp_tls_key __key, void* __p);
+
+#if defined(_LIBCPP_HAS_THREAD_API_PTHREAD) || defined(_LIBCPP_BUILDING_EXTERNAL_THREADS)
+
 int __libcpp_recursive_mutex_init(__libcpp_mutex_t* __m)
 {
     pthread_mutexattr_t attr;
@@ -59,144 +122,112 @@
     return 0;
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_mutex_lock(__libcpp_mutex_t* __m)
 {
     return pthread_mutex_lock(__m);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_mutex_trylock(__libcpp_mutex_t* __m)
 {
     return pthread_mutex_trylock(__m);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_mutex_unlock(__libcpp_mutex_t* __m)
 {
     return pthread_mutex_unlock(__m);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_mutex_destroy(__libcpp_mutex_t* __m)
 {
     return pthread_mutex_destroy(__m);
 }
 
 // Condition variable
-#define _LIBCPP_CONDVAR_INITIALIZER PTHREAD_COND_INITIALIZER
-typedef pthread_cond_t __libcpp_condvar_t;
-
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_condvar_signal(__libcpp_condvar_t* __cv)
 {
     return pthread_cond_signal(__cv);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_condvar_broadcast(__libcpp_condvar_t* __cv)
 {
     return pthread_cond_broadcast(__cv);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_condvar_wait(__libcpp_condvar_t* __cv, __libcpp_mutex_t* __m)
 {
     return pthread_cond_wait(__cv, __m);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_condvar_timedwait(__libcpp_condvar_t* __cv, __libcpp_mutex_t* __m, timespec* __ts)
 {
     return pthread_cond_timedwait(__cv, __m, __ts);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_condvar_destroy(__libcpp_condvar_t* __cv)
 {
     return pthread_cond_destroy(__cv);
 }
 
-// Thread id
-typedef pthread_t __libcpp_thread_id;
-
 // Returns non-zero if the thread ids are equal, otherwise 0
-inline _LIBCPP_ALWAYS_INLINE
 bool __libcpp_thread_id_equal(__libcpp_thread_id t1, __libcpp_thread_id t2)
 {
     return pthread_equal(t1, t2) != 0;
 }
 
 // Returns non-zero if t1 < t2, otherwise 0
-inline _LIBCPP_ALWAYS_INLINE
 bool __libcpp_thread_id_less(__libcpp_thread_id t1, __libcpp_thread_id t2)
 {
     return t1 < t2;
 }
 
 // Thread
-typedef pthread_t __libcpp_thread_t;
-
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_thread_create(__libcpp_thread_t* __t, void* (*__func)(void*), void* __arg)
 {
     return pthread_create(__t, 0, __func, __arg);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 __libcpp_thread_id __libcpp_thread_get_current_id()
 {
     return pthread_self();
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 __libcpp_thread_id __libcpp_thread_get_id(const __libcpp_thread_t* __t)
 {
     return *__t;
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_thread_join(__libcpp_thread_t* __t)
 {
     return pthread_join(*__t, 0);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 int __libcpp_thread_detach(__libcpp_thread_t* __t)
 {
     return pthread_detach(*__t);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
 void __libcpp_thread_yield()
 {
     sched_yield();
 }
 
 // Thread local storage
-typedef pthread_key_t __libcpp_tl_key;
-
-inline _LIBCPP_ALWAYS_INLINE
-int __libcpp_tl_create(__libcpp_tl_key* __key, void (*__at_exit)(void*))
+int __libcpp_tls_create(__libcpp_tls_key* __key, void (*__at_exit)(void*))
 {
     return pthread_key_create(__key, __at_exit);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
-void* __libcpp_tl_get(__libcpp_tl_key __key)
+void* __libcpp_tls_get(__libcpp_tls_key __key)
 {
     return pthread_getspecific(__key);
 }
 
-inline _LIBCPP_ALWAYS_INLINE
-void __libcpp_tl_set(__libcpp_tl_key __key, void* __p)
+void __libcpp_tls_set(__libcpp_tls_key __key, void* __p)
 {
     pthread_setspecific(__key, __p);
 }
 
-#else // !_LIBCPP_HAS_THREAD_API_PTHREAD
-  #error "No thread API selected."
-#endif
+#endif // _LIBCPP_HAS_THREAD_API_PTHREAD || _LIBCPP_BUILDING_EXTERNAL_THREADS
 
 _LIBCPP_END_NAMESPACE_STD
 
diff --git a/include/thread b/include/thread
index 21cc761..7fe4c77 100644
--- a/include/thread
+++ b/include/thread
@@ -137,7 +137,7 @@
 template <class _Tp>
 class __thread_specific_ptr
 {
-    __libcpp_tl_key __key_;
+    __libcpp_tls_key __key_;
 
      // Only __thread_local_data() may construct a __thread_specific_ptr
      // and only with _Tp == __thread_struct.
@@ -155,7 +155,7 @@
     ~__thread_specific_ptr();
 
     _LIBCPP_INLINE_VISIBILITY
-    pointer get() const {return static_cast<_Tp*>(__libcpp_tl_get(__key_));}
+    pointer get() const {return static_cast<_Tp*>(__libcpp_tls_get(__key_));}
     _LIBCPP_INLINE_VISIBILITY
     pointer operator*() const {return *get();}
     _LIBCPP_INLINE_VISIBILITY
@@ -173,7 +173,7 @@
 template <class _Tp>
 __thread_specific_ptr<_Tp>::__thread_specific_ptr()
 {
-    int __ec = __libcpp_tl_create(
+    int __ec = __libcpp_tls_create(
         &__key_,
         &__thread_specific_ptr::__at_thread_exit);
     if (__ec)
@@ -196,7 +196,7 @@
 {
     _LIBCPP_ASSERT(get() == nullptr,
                    "Attempting to overwrite thread local data");
-    __libcpp_tl_set(__key_, __p);
+    __libcpp_tls_set(__key_, __p);
 }
 
 class _LIBCPP_TYPE_VIS thread;