[libc++] Allow building libc++ using llvm-libc without locale support (#187603)

This PR allows libc++ to be configured to use LLVM-libc without
requiring locale-variants of libc functions.

This PR updates libc++ to use `<llvm-libc-types/mbstate_t.h>`
when building against LLVM-libc to avoid pulling in all of `wchar.h`.

There is some code duplication in this PR. The code in `formatting.h` is
similar to the implementation in `fuchsia.h`, except that the new code
does not use thread-local locales via `__locale_guard`:

673002f325/libcxx/include/__locale_dir/support/fuchsia.h (L133)

If reviewers would like, I'm happy to refactor to create more shared
headers, similar to how `no_locale` is set up. I've avoided doing so in
this PR, but lmk. It looks like there's three general ways these
passthrough functions are defined for unix systems:
- No locale (e.g. Fuchsia's `strtod` ignores locales entirely).
- Thread-local locale (e.g. other Fuchsia functions use `__locale_guard`
set up locales via `uselocale`).
- Native locale-specific function variant (i.e. the proxy just uses the
*_l variant, like `toupper_l`).

libcxx/include/CMakeLists.txt

@@ -543,9 +543,12 @@ set(files
   __locale_dir/support/freebsd.h
   __locale_dir/support/fuchsia.h
   __locale_dir/support/linux.h
+  __locale_dir/support/llvm_libc.h
   __locale_dir/support/netbsd.h
   __locale_dir/support/newlib.h
   __locale_dir/support/no_locale/characters.h
+  __locale_dir/support/no_locale/conversions.h
+  __locale_dir/support/no_locale/formatting.h
   __locale_dir/support/no_locale/strtonum.h
   __locale_dir/support/windows.h
   __locale_dir/time.h

libcxx/include/__locale_dir/locale_base_api.h

@@ -119,6 +119,8 @@
 #    include <__locale_dir/support/windows.h>
 #  elif defined(__Fuchsia__)
 #    include <__locale_dir/support/fuchsia.h>
+#  elif _LIBCPP_LIBC_LLVM_LIBC
+#    include <__locale_dir/support/llvm_libc.h>
 #  elif defined(__linux__)
 #    include <__locale_dir/support/linux.h>
 #  elif _LIBCPP_LIBC_NEWLIB

libcxx/include/__locale_dir/support/llvm_libc.h

@@ -0,0 +1,60 @@
+//===-----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _LIBCPP___LOCALE_DIR_SUPPORT_LLVM_LIBC_H
+#define _LIBCPP___LOCALE_DIR_SUPPORT_LLVM_LIBC_H
+
+#include <__config>
+#include <clocale>
+#include <cstdio>
+#include <cstdlib>
+#include <ctype.h>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#  pragma GCC system_header
+#endif
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+namespace __locale {
+
+using __locale_t _LIBCPP_NODEBUG = ::locale_t;
+
+#define _LIBCPP_COLLATE_MASK LC_COLLATE_MASK
+#define _LIBCPP_CTYPE_MASK LC_CTYPE_MASK
+#define _LIBCPP_MONETARY_MASK LC_MONETARY_MASK
+#define _LIBCPP_NUMERIC_MASK LC_NUMERIC_MASK
+#define _LIBCPP_TIME_MASK LC_TIME_MASK
+#define _LIBCPP_MESSAGES_MASK LC_MESSAGES_MASK
+#define _LIBCPP_ALL_MASK LC_ALL_MASK
+#define _LIBCPP_LC_ALL LC_ALL
+
+#if defined(_LIBCPP_BUILDING_LIBRARY)
+using __lconv_t _LIBCPP_NODEBUG = std::lconv;
+
+inline _LIBCPP_HIDE_FROM_ABI __locale_t __newlocale(int __category_mask, const char* __locale, __locale_t __base) {
+  return ::newlocale(__category_mask, __locale, __base);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI void __freelocale(__locale_t __loc) { ::freelocale(__loc); }
+
+inline _LIBCPP_HIDE_FROM_ABI char* __setlocale(int __category, char const* __locale) {
+  return ::setlocale(__category, __locale);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI __lconv_t* __localeconv(__locale_t&) { return std::localeconv(); }
+#endif // _LIBCPP_BUILDING_LIBRARY
+
+} // namespace __locale
+_LIBCPP_END_NAMESPACE_STD
+
+#include <__locale_dir/support/no_locale/characters.h>
+#include <__locale_dir/support/no_locale/conversions.h>
+#include <__locale_dir/support/no_locale/formatting.h>
+#include <__locale_dir/support/no_locale/strtonum.h>
+
+#endif // _LIBCPP___LOCALE_DIR_SUPPORT_LLVM_LIBC_H

libcxx/include/__locale_dir/support/no_locale/characters.h

@@ -16,6 +16,7 @@
 #include <cstring>
 #include <ctime>
 #if _LIBCPP_HAS_WIDE_CHARACTERS
+#  include <cwchar>
 #  include <cwctype>
 #endif
 

libcxx/include/__locale_dir/support/no_locale/conversions.h

@@ -0,0 +1,72 @@
+//===-----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _LIBCPP___LOCALE_DIR_SUPPORT_NO_LOCALE_CONVERSIONS_H
+#define _LIBCPP___LOCALE_DIR_SUPPORT_NO_LOCALE_CONVERSIONS_H
+
+#include <__config>
+#include <__cstddef/size_t.h>
+#include <__std_mbstate_t.h>
+#include <cstdlib>
+#if _LIBCPP_HAS_WIDE_CHARACTERS
+#  include <cwchar>
+#endif
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#  pragma GCC system_header
+#endif
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+namespace __locale {
+
+#if defined(_LIBCPP_BUILDING_LIBRARY)
+inline _LIBCPP_HIDE_FROM_ABI decltype(MB_CUR_MAX) __mb_len_max(__locale_t) { return MB_CUR_MAX; }
+
+#  if _LIBCPP_HAS_WIDE_CHARACTERS
+inline _LIBCPP_HIDE_FROM_ABI wint_t __btowc(int __c, __locale_t) { return std::btowc(__c); }
+
+inline _LIBCPP_HIDE_FROM_ABI int __wctob(wint_t __c, __locale_t) { return std::wctob(__c); }
+
+inline _LIBCPP_HIDE_FROM_ABI size_t
+__wcsnrtombs(char* __dest, const wchar_t** __src, size_t __nwc, size_t __len, mbstate_t* __ps, __locale_t) {
+  return ::wcsnrtombs(__dest, __src, __nwc, __len, __ps); // Non-standard
+}
+
+inline _LIBCPP_HIDE_FROM_ABI size_t __wcrtomb(char* __s, wchar_t __wc, mbstate_t* __ps, __locale_t) {
+  return std::wcrtomb(__s, __wc, __ps);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI size_t
+__mbsnrtowcs(wchar_t* __dest, const char** __src, size_t __nms, size_t __len, mbstate_t* __ps, __locale_t) {
+  return ::mbsnrtowcs(__dest, __src, __nms, __len, __ps); // Non-standard
+}
+
+inline _LIBCPP_HIDE_FROM_ABI size_t
+__mbrtowc(wchar_t* __pwc, const char* __s, size_t __n, mbstate_t* __ps, __locale_t) {
+  return std::mbrtowc(__pwc, __s, __n, __ps);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI int __mbtowc(wchar_t* __pwc, const char* __pmb, size_t __max, __locale_t) {
+  return std::mbtowc(__pwc, __pmb, __max);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI size_t __mbrlen(const char* __s, size_t __n, mbstate_t* __ps, __locale_t) {
+  return std::mbrlen(__s, __n, __ps);
+}
+
+inline _LIBCPP_HIDE_FROM_ABI size_t
+__mbsrtowcs(wchar_t* __dest, const char** __src, size_t __len, mbstate_t* __ps, __locale_t) {
+  return std::mbsrtowcs(__dest, __src, __len, __ps);
+}
+#  endif // _LIBCPP_HAS_WIDE_CHARACTERS
+#endif   // _LIBCPP_BUILDING_LIBRARY
+
+} // namespace __locale
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // _LIBCPP___LOCALE_DIR_SUPPORT_NO_LOCALE_CONVERSIONS_H

libcxx/include/__locale_dir/support/no_locale/formatting.h

@@ -0,0 +1,50 @@
+//===-----------------------------------------------------------------------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _LIBCPP___LOCALE_DIR_SUPPORT_NO_LOCALE_FORMATTING_H
+#define _LIBCPP___LOCALE_DIR_SUPPORT_NO_LOCALE_FORMATTING_H
+
+#include <__config>
+#include <__utility/forward.h>
+#include <cstdio>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#  pragma GCC system_header
+#endif
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+namespace __locale {
+
+_LIBCPP_DIAGNOSTIC_PUSH
+_LIBCPP_CLANG_DIAGNOSTIC_IGNORED("-Wgcc-compat")
+_LIBCPP_GCC_DIAGNOSTIC_IGNORED("-Wformat-nonliteral") // GCC doesn't support [[gnu::format]] on variadic templates
+#ifdef _LIBCPP_COMPILER_CLANG_BASED
+#  define _LIBCPP_VARIADIC_ATTRIBUTE_FORMAT(...) _LIBCPP_ATTRIBUTE_FORMAT(__VA_ARGS__)
+#else
+#  define _LIBCPP_VARIADIC_ATTRIBUTE_FORMAT(...) /* nothing */
+#endif
+
+template <class... _Args>
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_VARIADIC_ATTRIBUTE_FORMAT(__printf__, 4, 5) int __snprintf(
+    char* __s, size_t __n, __locale_t, const char* __format, _Args&&... __args) {
+  return std::snprintf(__s, __n, __format, std::forward<_Args>(__args)...);
+}
+
+template <class... _Args>
+_LIBCPP_HIDE_FROM_ABI _LIBCPP_VARIADIC_ATTRIBUTE_FORMAT(__printf__, 3, 4) int __asprintf(
+    char** __s, __locale_t, const char* __format, _Args&&... __args) {
+  return ::asprintf(__s, __format, std::forward<_Args>(__args)...); // non-standard
+}
+
+_LIBCPP_DIAGNOSTIC_POP
+#undef _LIBCPP_VARIADIC_ATTRIBUTE_FORMAT
+
+} // namespace __locale
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // _LIBCPP___LOCALE_DIR_SUPPORT_NO_LOCALE_FORMATTING_H

libcxx/include/__mbstate_t.h

@@ -39,6 +39,8 @@
 #  define __NEED_mbstate_t
 #  include <bits/alltypes.h>
 #  undef __NEED_mbstate_t
+#elif _LIBCPP_LIBC_LLVM_LIBC
+#  include <llvm-libc-types/mbstate_t.h>
 #elif __has_include(<bits/types/mbstate_t.h>)
 #  include <bits/types/mbstate_t.h> // works on most Unixes
 #elif __has_include(<sys/_types/_mbstate_t.h>)

libcxx/include/module.modulemap.in

@@ -1606,7 +1606,10 @@ module std [system] {
       textual header "__locale_dir/support/freebsd.h"
       textual header "__locale_dir/support/fuchsia.h"
       textual header "__locale_dir/support/linux.h"
+      textual header "__locale_dir/support/llvm_libc.h"
       textual header "__locale_dir/support/netbsd.h"
+      textual header "__locale_dir/support/no_locale/conversions.h"
+      textual header "__locale_dir/support/no_locale/formatting.h"
       textual header "__locale_dir/support/newlib.h"
       textual header "__locale_dir/support/no_locale/characters.h"
       textual header "__locale_dir/support/no_locale/strtonum.h"