[libc++] cuchar redeclares ::mbstate_t when it's in its own clang module

When cuchar is compiled independently on platforms that don't have <uchar.h>, it doesn't get a declaration of mbstate_t, and so makes an empty declaration for ::mbstate_t. That conflicts with the declarations in __mbstate_t.h and cwchar since both of those headers do get mbstate_t before making ::mbstate_t.

Change `__mbstate_t.h` to just get the underlying declaration for mbstate_t and not make a declaration for ::mbstate_t. Include __mbstate_t.h in uchar.h and wchar.h when their next headers aren't available so that at least mbstate_t gets defined.

Add __std_mbstate_t.h to declare ::mbstate_t for headers that need that when cuchar or cwchar aren't available (because either _LIBCPP_HAS_NO_WIDE_CHARACTERS or _LIBCPP_CXX03_LANG).

Reviewed By: ldionne, Mordante, #libc, philnik

Differential Revision: https://reviews.llvm.org/D148542

Author: ian-twilightcoder

libcxx/include/CMakeLists.txt

@@ -614,6 +614,7 @@ set(files
   __ranges/views.h
   __ranges/zip_view.h
   __split_buffer
+  __std_mbstate_t.h
   __string/char_traits.h
   __string/constexpr_c_functions.h
   __string/extern_template_lists.h

libcxx/include/__locale

@@ -25,6 +25,8 @@
 
 #ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
 #  include <cwchar>
+#else
+#  include <__std_mbstate_t.h>
 #endif
 
 #if defined(_LIBCPP_MSVCRT_LIKE)

libcxx/include/__mbstate_t.h

@@ -16,29 +16,27 @@
 #  pragma GCC system_header
 #endif
 
-// TODO(ldionne):
-// The goal of this header is to provide mbstate_t without having to pull in
-// <wchar.h> or <uchar.h>. This is necessary because we need that type even
-// when we don't have (or try to provide) support for wchar_t, because several
-// types like std::fpos are defined in terms of mbstate_t.
+// The goal of this header is to provide mbstate_t without requiring all of
+// <uchar.h> or <wchar.h>. It's also used by the libc++ versions of <uchar.h>
+// and <wchar.h> to get mbstate_t when the C library doesn't provide <uchar.h>
+// or <wchar.h>, hence the #include_next of those headers instead of #include.
+// (e.g. if <wchar.h> isn't present in the C library, the libc++ <wchar.h>
+// will include this header. This header needs to not turn around and cyclically
+// include <wchar.h>, but fall through to <uchar.h>.)
 //
-// This is a gruesome hack, but I don't know how to make it cleaner for
-// the time being.
+// This does not define std::mbstate_t -- this only brings in the declaration
+// in the global namespace.
 
-#ifndef _LIBCPP_HAS_NO_WIDE_CHARACTERS
-#   include <wchar.h> // for mbstate_t
-#elif __has_include(<bits/types/mbstate_t.h>)
+#if __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>)
 #   include <sys/_types/_mbstate_t.h> // works on Darwin
+#elif !defined(_LIBCPP_HAS_NO_WIDE_CHARACTERS) && __has_include_next(<wchar.h>)
+#   include_next <wchar.h> // fall back to the C standard provider of mbstate_t
+#elif __has_include_next(<uchar.h>)
+#   include_next <uchar.h> // <uchar.h> is also required to make mbstate_t visible
 #else
-#   error "The library was configured without support for wide-characters, but we don't know how to get the definition of mbstate_t without <wchar.h> on your platform."
+#   error "We don't know how to get the definition of mbstate_t without <wchar.h> on your platform."
 #endif
 
-_LIBCPP_BEGIN_NAMESPACE_STD
-
-using ::mbstate_t _LIBCPP_USING_IF_EXISTS;
-
-_LIBCPP_END_NAMESPACE_STD
-
 #endif // _LIBCPP___MBSTATE_T_H

libcxx/include/__std_mbstate_t.h

@@ -0,0 +1,29 @@
+// -*- C++ -*-
+//===----------------------------------------------------------------------===//
+//
+// 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___STD_MBSTATE_T_H
+#define _LIBCPP___STD_MBSTATE_T_H
+
+#include <__config>
+#include <__mbstate_t.h>
+
+#if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)
+#  pragma GCC system_header
+#endif
+
+// The goal of this header is to provide std::mbstate_t without requiring all
+// of <cuchar> or <cwchar>.
+
+_LIBCPP_BEGIN_NAMESPACE_STD
+
+using ::mbstate_t _LIBCPP_USING_IF_EXISTS;
+
+_LIBCPP_END_NAMESPACE_STD
+
+#endif // _LIBCPP___STD_MBSTATE_T_H

libcxx/include/iosfwd

@@ -103,7 +103,7 @@ using u32streampos = fpos<char_traits<char32_t>::state_type>;
 #include <__fwd/sstream.h>
 #include <__fwd/streambuf.h>
 #include <__fwd/string.h>
-#include <__mbstate_t.h>
+#include <__std_mbstate_t.h>
 #include <version>
 
 #if !defined(_LIBCPP_HAS_NO_PRAGMA_SYSTEM_HEADER)

libcxx/include/module.modulemap.in

@@ -1735,6 +1735,7 @@ module std [system] {
   module __mbstate_t         { private header "__mbstate_t.h"       export * }
   module __node_handle       { private header "__node_handle"       export * }
   module __split_buffer      { private header "__split_buffer"      export * }
+  module __std_mbstate_t     { private header "__std_mbstate_t.h"   export * }
   module __threading_support {         header "__threading_support" export * }
   module __tree              {         header "__tree"              export * }
   module __undef_macros      {         header "__undef_macros"      export * }

libcxx/include/uchar.h

@@ -42,10 +42,12 @@ size_t c32rtomb(char* s, char32_t c32, mbstate_t* ps);
 
 // Some platforms don't implement <uchar.h> and we don't want to give a hard
 // error on those platforms. When the platform doesn't provide <uchar.h>, at
-// least include <stddef.h> so we get the declaration for size_t.
+// least include <stddef.h> so we get the declaration for size_t, and try to
+// get the declaration of mbstate_t too.
 #if __has_include_next(<uchar.h>)
 # include_next <uchar.h>
 #else
+# include <__mbstate_t.h>
 # include <stddef.h>
 #endif
 

libcxx/include/wchar.h

@@ -122,6 +122,8 @@ size_t wcsrtombs(char* restrict dst, const wchar_t** restrict src, size_t len,
 
 #  if __has_include_next(<wchar.h>)
 #    include_next <wchar.h>
+#  else
+#    include <__mbstate_t.h> // make sure we have mbstate_t regardless of the existence of <wchar.h>
 #  endif
 
 // Determine whether we have const-correct overloads for wcschr and friends.

libcxx/test/libcxx/private_headers.verify.cpp

@@ -614,6 +614,7 @@ END-SCRIPT
 #include <__ranges/views.h> // expected-error@*:* {{use of private header from outside its module: '__ranges/views.h'}}
 #include <__ranges/zip_view.h> // expected-error@*:* {{use of private header from outside its module: '__ranges/zip_view.h'}}
 #include <__split_buffer> // expected-error@*:* {{use of private header from outside its module: '__split_buffer'}}
+#include <__std_mbstate_t.h> // expected-error@*:* {{use of private header from outside its module: '__std_mbstate_t.h'}}
 #include <__string/char_traits.h> // expected-error@*:* {{use of private header from outside its module: '__string/char_traits.h'}}
 #include <__string/constexpr_c_functions.h> // expected-error@*:* {{use of private header from outside its module: '__string/constexpr_c_functions.h'}}
 #include <__string/extern_template_lists.h> // expected-error@*:* {{use of private header from outside its module: '__string/extern_template_lists.h'}}

libcxx/utils/generate_iwyu_mapping.py

@@ -56,11 +56,12 @@ def generate_map(include):
         elif i == '__pstl_memory': continue
         elif i == '__pstl_numeric': continue
         elif i == '__split_buffer': public = ['deque', 'vector']
+        elif i == '__std_mbstate_t.h': continue
         elif i == '__threading_support': public = ['atomic', 'mutex', 'semaphore', 'thread']
         elif i == '__tree': public = ['map', 'set']
         elif i == '__undef_macros': continue
         elif i == '__verbose_abort': continue
-        else: panic()
+        else: panic(i)
 
         for p in public:
             result.append(f'{generate(f"<{i}>", p)},')