P0482R5 char8_t: Standard library support

gcc/cp:

2019-02-19  Tom Honermann  <tom@honermann.net>

	* name-lookup.c (get_std_name_hint): Added u8string as a name hint.

libstdc++:

2019-02-19  Tom Honermann  <tom@honermann.net>

	P0482R5 char8_t: Standard library support
	* config/abi/pre/gnu-versioned-namespace.ver (CXXABI_2.0): Add
	typeinfo symbols for char8_t.
	* config/abi/pre/gnu.ver: Add CXXABI_1.3.12.
	(GLIBCXX_3.4.26): Add symbols for specializations of
	numeric_limits and codecvt that involve char8_t.
	(CXXABI_1.3.12): Add typeinfo symbols for char8_t.
	* include/bits/atomic_base.h: Add atomic_char8_t.
	* include/bits/basic_string.h: Add std::hash<u8string> and
	operator""s(const char8_t*, size_t).
	* include/bits/c++config: Define _GLIBCXX_USE_CHAR8_T and
	__cpp_lib_char8_t.
	* include/bits/char_traits.h: Add char_traits<char8_t>.
	* include/bits/codecvt.h: Add
	codecvt<char16_t, char8_t, mbstate_t>,
	codecvt<char32_t, char8_t, mbstate_t>,
	codecvt_byname<char16_t, char8_t, mbstate_t>, and
	codecvt_byname<char32_t, char8_t, mbstate_t>.
	* include/bits/cpp_type_traits.h: Add __is_integer<char8_t> to
	recognize char8_t as an integral type.
	* include/bits/fs_path.h: (path::__is_encoded_char): Recognize
	char8_t.
	(path::u8string): Return std::u8string when char8_t support is
	enabled.
	(path::generic_u8string): Likewise.
	(path::_S_convert): Handle conversion from char8_t input.
	(path::_S_str_convert): Likewise.
	* include/bits/functional_hash.h: Add hash<char8_t>.
	* include/bits/locale_conv.h (__str_codecvt_out): Add overloads for
	char8_t.
	* include/bits/locale_facets.h (_GLIBCXX_NUM_UNICODE_FACETS): Bump
	for new char8_t specializations.
	* include/bits/localefwd.h: Add missing declarations of
	codecvt<char16_t, char, mbstate_t> and
	codecvt<char32_t, char, mbstate_t>.  Add char8_t declarations
	codecvt<char16_t, char8_t, mbstate_t> and
	codecvt<char32_t, char8_t, mbstate_t>.
	* include/bits/postypes.h: Add u8streampos
	* include/bits/stringfwd.h: Add declarations of
	char_traits<char8_t> and u8string.
	* include/c_global/cstddef: Add __byte_operand<char8_t>.
	* include/experimental/bits/fs_path.h (path::__is_encoded_char):
	Recognize char8_t.
	(path::u8string): Return std::u8string when char8_t support is
	enabled.
	(path::generic_u8string): Likewise.
	(path::_S_convert): Handle conversion from char8_t input.
	(path::_S_str_convert): Likewise.
	* include/experimental/string: Add u8string.
	* include/experimental/string_view: Add u8string_view,
	hash<experimental::u8string_view>, and
	operator""sv(const char8_t*, size_t).
	* include/std/atomic: Add atomic<char8_t> and atomic_char8_t.
	* include/std/charconv (__is_int_to_chars_type): Recognize char8_t
	as a character type.
	* include/std/limits: Add numeric_limits<char8_t>.
	* include/std/string_view: Add u8string_view,
	hash<experimental::u8string_view>, and
	operator""sv(const char8_t*, size_t).
	* include/std/type_traits: Add __is_integral_helper<char8_t>,
	__make_unsigned<char8_t>, and __make_signed<char8_t>.
	* libsupc++/atomic_lockfree_defines.h: Define
	ATOMIC_CHAR8_T_LOCK_FREE.
	* src/c++11/Makefile.am: Compile with -fchar8_t when compiling
	codecvt.cc and limits.cc so that char8_t specializations of
	numeric_limits and codecvt and emitted.
	* src/c++11/Makefile.in: Likewise.
	* src/c++11/codecvt.cc: Define members of
	codecvt<char16_t, char8_t, mbstate_t>,
	codecvt<char32_t, char8_t, mbstate_t>,
	codecvt_byname<char16_t, char8_t, mbstate_t>, and
	codecvt_byname<char32_t, char8_t, mbstate_t>.
	* src/c++11/limits.cc: Define members of
	numeric_limits<char8_t>.
	* src/c++98/Makefile.am: Compile with -fchar8_t when compiling
	locale_init.cc and localename.cc.
	* src/c++98/Makefile.in: Likewise.
	* src/c++98/locale_init.cc: Add initialization for the
	codecvt<char16_t, char8_t, mbstate_t> and
	codecvt<char32_t, char8_t, mbstate_t> facets.
	* src/c++98/localename.cc: Likewise.
	* testsuite/util/testsuite_abi.cc: Validate ABI bump.

From-SVN: r269004

8 files changed, 270 insertions, 29 deletions

diff --git a/libstdc++-v3/src/c++11/Makefile.am b/libstdc++-v3/src/c++11/Makefile.am
index 46d31b9..9fc1866 100644
--- a/libstdc++-v3/src/c++11/Makefile.am
+++ b/libstdc++-v3/src/c++11/Makefile.am
@@ -126,6 +126,16 @@ hashtable_c++0x.lo: hashtable_c++0x.cc
 hashtable_c++0x.o: hashtable_c++0x.cc
 	$(CXXCOMPILE) -fimplicit-templates -c $<
 
+# Use special rules for source files that require -fchar8_t.
+codecvt.lo: codecvt.cc
+	$(LTCXXCOMPILE) -fchar8_t -c $<
+codecvt.o: codecvt.cc
+	$(CXXCOMPILE) -fchar8_t -c $<
+limits.lo: limits.cc
+	$(LTCXXCOMPILE) -fchar8_t -c $<
+limits.o: limits.cc
+	$(CXXCOMPILE) -fchar8_t -c $<
+
 if ENABLE_DUAL_ABI
 # Rewrite the type info for __ios_failure.
 rewrite_ios_failure_typeinfo = sed -e '/^_*_ZTISt13__ios_failure:/,/_ZTVN10__cxxabiv120__si_class_type_infoE/s/_ZTVN10__cxxabiv120__si_class_type_infoE/_ZTVSt19__iosfail_type_info/'
diff --git a/libstdc++-v3/src/c++11/Makefile.in b/libstdc++-v3/src/c++11/Makefile.in
index 92816c8..a972915 100644
--- a/libstdc++-v3/src/c++11/Makefile.in
+++ b/libstdc++-v3/src/c++11/Makefile.in
@@ -834,6 +834,16 @@ hashtable_c++0x.lo: hashtable_c++0x.cc
 hashtable_c++0x.o: hashtable_c++0x.cc
 	$(CXXCOMPILE) -fimplicit-templates -c $<
 
+# Use special rules for source files that require -fchar8_t.
+codecvt.lo: codecvt.cc
+	$(LTCXXCOMPILE) -fchar8_t -c $<
+codecvt.o: codecvt.cc
+	$(CXXCOMPILE) -fchar8_t -c $<
+limits.lo: limits.cc
+	$(LTCXXCOMPILE) -fchar8_t -c $<
+limits.o: limits.cc
+	$(CXXCOMPILE) -fchar8_t -c $<
+
 @ENABLE_DUAL_ABI_TRUE@cxx11-ios_failure-lt.s: cxx11-ios_failure.cc
 @ENABLE_DUAL_ABI_TRUE@	$(LTCXXCOMPILE) -S $< -o tmp-cxx11-ios_failure-lt.s
 @ENABLE_DUAL_ABI_TRUE@	-test -f tmp-cxx11-ios_failure-lt.o && mv -f tmp-cxx11-ios_failure-lt.o tmp-cxx11-ios_failure-lt.s
diff --git a/libstdc++-v3/src/c++11/codecvt.cc b/libstdc++-v3/src/c++11/codecvt.cc
index b2fa375..372aea2 100644
--- a/libstdc++-v3/src/c++11/codecvt.cc
+++ b/libstdc++-v3/src/c++11/codecvt.cc
@@ -193,8 +193,9 @@ namespace
     }
 
   // If generate_header is set in mode write out UTF-8 BOM.
+  template<typename C>
   bool
-  write_utf8_bom(range<char>& to, codecvt_mode mode)
+  write_utf8_bom(range<C>& to, codecvt_mode mode)
   {
     if (mode & generate_header)
       return write_bom(to, utf8_bom);
@@ -218,8 +219,9 @@ namespace
   }
 
   // If consume_header is set in mode update from.next to after any BOM.
+  template<typename C>
   void
-  read_utf8_bom(range<const char>& from, codecvt_mode mode)
+  read_utf8_bom(range<const C>& from, codecvt_mode mode)
   {
     if (mode & consume_header)
       read_bom(from, utf8_bom);
@@ -245,8 +247,9 @@ namespace
   // Read a codepoint from a UTF-8 multibyte sequence.
   // Updates from.next if the codepoint is not greater than maxcode.
   // Returns invalid_mb_sequence, incomplete_mb_character or the code point.
+  template<typename C>
   char32_t
-  read_utf8_code_point(range<const char>& from, unsigned long maxcode)
+  read_utf8_code_point(range<const C>& from, unsigned long maxcode)
   {
     const size_t avail = from.size();
     if (avail == 0)
@@ -315,8 +318,9 @@ namespace
       return invalid_mb_sequence;
   }
 
+  template<typename C>
   bool
-  write_utf8_code_point(range<char>& to, char32_t code_point)
+  write_utf8_code_point(range<C>& to, char32_t code_point)
   {
     if (code_point < 0x80)
       {
@@ -445,8 +449,9 @@ namespace
   }
 
   // utf8 -> ucs4
+  template<typename C>
   codecvt_base::result
-  ucs4_in(range<const char>& from, range<char32_t>& to,
+  ucs4_in(range<const C>& from, range<char32_t>& to,
           unsigned long maxcode = max_code_point, codecvt_mode mode = {})
   {
     read_utf8_bom(from, mode);
@@ -463,8 +468,9 @@ namespace
   }
 
   // ucs4 -> utf8
+  template<typename C>
   codecvt_base::result
-  ucs4_out(range<const char32_t>& from, range<char>& to,
+  ucs4_out(range<const char32_t>& from, range<C>& to,
            unsigned long maxcode = max_code_point, codecvt_mode mode = {})
   {
     if (!write_utf8_bom(to, mode))
@@ -522,9 +528,9 @@ namespace
   enum class surrogates { allowed, disallowed };
 
   // utf8 -> utf16 (or utf8 -> ucs2 if s == surrogates::disallowed)
-  template<typename C>
+  template<typename C8, typename C16>
   codecvt_base::result
-  utf16_in(range<const char>& from, range<C>& to,
+  utf16_in(range<const C8>& from, range<C16>& to,
 	   unsigned long maxcode = max_code_point, codecvt_mode mode = {},
 	   surrogates s = surrogates::allowed)
   {
@@ -552,9 +558,9 @@ namespace
   }
 
   // utf16 -> utf8 (or ucs2 -> utf8 if s == surrogates::disallowed)
-  template<typename C>
+  template<typename C16, typename C8>
   codecvt_base::result
-  utf16_out(range<const C>& from, range<char>& to,
+  utf16_out(range<const C16>& from, range<C8>& to,
 	    unsigned long maxcode = max_code_point, codecvt_mode mode = {},
 	    surrogates s = surrogates::allowed)
   {
@@ -593,11 +599,12 @@ namespace
   }
 
   // return pos such that [begin,pos) is valid UTF-16 string no longer than max
-  const char*
-  utf16_span(const char* begin, const char* end, size_t max,
+  template<typename C>
+  const C*
+  utf16_span(const C* begin, const C* end, size_t max,
 	     char32_t maxcode = max_code_point, codecvt_mode mode = {})
   {
-    range<const char> from{ begin, end };
+    range<const C> from{ begin, end };
     read_utf8_bom(from, mode);
     size_t count = 0;
     while (count+1 < max)
@@ -615,8 +622,9 @@ namespace
   }
 
   // utf8 -> ucs2
+  template<typename C>
   codecvt_base::result
-  ucs2_in(range<const char>& from, range<char16_t>& to,
+  ucs2_in(range<const C>& from, range<char16_t>& to,
 	  char32_t maxcode = max_code_point, codecvt_mode mode = {})
   {
     // UCS-2 only supports characters in the BMP, i.e. one UTF-16 code unit:
@@ -625,8 +633,9 @@ namespace
   }
 
   // ucs2 -> utf8
+  template<typename C>
   codecvt_base::result
-  ucs2_out(range<const char16_t>& from, range<char>& to,
+  ucs2_out(range<const char16_t>& from, range<C>& to,
 	   char32_t maxcode = max_code_point, codecvt_mode mode = {})
   {
     // UCS-2 only supports characters in the BMP, i.e. one UTF-16 code unit:
@@ -687,11 +696,12 @@ namespace
     return reinterpret_cast<const char16_t*>(from.next);
   }
 
-  const char*
-  ucs2_span(const char* begin, const char* end, size_t max,
+  template<typename C>
+  const C*
+  ucs2_span(const C* begin, const C* end, size_t max,
             char32_t maxcode, codecvt_mode mode)
   {
-    range<const char> from{ begin, end };
+    range<const C> from{ begin, end };
     read_utf8_bom(from, mode);
     // UCS-2 only supports characters in the BMP, i.e. one UTF-16 code unit:
     maxcode = std::min(max_single_utf16_unit, maxcode);
@@ -702,11 +712,12 @@ namespace
   }
 
   // return pos such that [begin,pos) is valid UCS-4 string no longer than max
-  const char*
-  ucs4_span(const char* begin, const char* end, size_t max,
+  template<typename C>
+  const C*
+  ucs4_span(const C* begin, const C* end, size_t max,
             char32_t maxcode = max_code_point, codecvt_mode mode = {})
   {
-    range<const char> from{ begin, end };
+    range<const C> from{ begin, end };
     read_utf8_bom(from, mode);
     char32_t c = 0;
     while (max-- && c <= maxcode)
@@ -875,6 +886,156 @@ codecvt<char32_t, char, mbstate_t>::do_max_length() const throw()
   return 4;
 }
 
+#if defined(_GLIBCXX_USE_CHAR8_T)
+// Define members of codecvt<char16_t, char8_t, mbstate_t> specialization.
+// Converts from UTF-8 to UTF-16.
+
+locale::id codecvt<char16_t, char8_t, mbstate_t>::id;
+
+codecvt<char16_t, char8_t, mbstate_t>::~codecvt() { }
+
+codecvt_base::result
+codecvt<char16_t, char8_t, mbstate_t>::
+do_out(state_type&,
+       const intern_type* __from,
+       const intern_type* __from_end, const intern_type*& __from_next,
+       extern_type* __to, extern_type* __to_end,
+       extern_type*& __to_next) const
+{
+  range<const char16_t> from{ __from, __from_end };
+  range<char8_t> to{ __to, __to_end };
+  auto res = utf16_out(from, to);
+  __from_next = from.next;
+  __to_next = to.next;
+  return res;
+}
+
+codecvt_base::result
+codecvt<char16_t, char8_t, mbstate_t>::
+do_unshift(state_type&, extern_type* __to, extern_type*,
+	   extern_type*& __to_next) const
+{
+  __to_next = __to;
+  return noconv; // we don't use mbstate_t for the unicode facets
+}
+
+codecvt_base::result
+codecvt<char16_t, char8_t, mbstate_t>::
+do_in(state_type&, const extern_type* __from, const extern_type* __from_end,
+      const extern_type*& __from_next,
+      intern_type* __to, intern_type* __to_end,
+      intern_type*& __to_next) const
+{
+  range<const char8_t> from{ __from, __from_end };
+  range<char16_t> to{ __to, __to_end };
+#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+  codecvt_mode mode = {};
+#else
+  codecvt_mode mode = little_endian;
+#endif
+  auto res = utf16_in(from, to, max_code_point, mode);
+  __from_next = from.next;
+  __to_next = to.next;
+  return res;
+}
+
+int
+codecvt<char16_t, char8_t, mbstate_t>::do_encoding() const throw()
+{ return 0; } // UTF-8 is not a fixed-width encoding
+
+bool
+codecvt<char16_t, char8_t, mbstate_t>::do_always_noconv() const throw()
+{ return false; }
+
+int
+codecvt<char16_t, char8_t, mbstate_t>::
+do_length(state_type&, const extern_type* __from,
+	  const extern_type* __end, size_t __max) const
+{
+  __end = utf16_span(__from, __end, __max);
+  return __end - __from;
+}
+
+int
+codecvt<char16_t, char8_t, mbstate_t>::do_max_length() const throw()
+{
+  // A single character (one or two UTF-16 code units) requires
+  // up to four UTF-8 code units.
+  return 4;
+}
+
+// Define members of codecvt<char32_t, char8_t, mbstate_t> specialization.
+// Converts from UTF-8 to UTF-32 (aka UCS-4).
+
+locale::id codecvt<char32_t, char8_t, mbstate_t>::id;
+
+codecvt<char32_t, char8_t, mbstate_t>::~codecvt() { }
+
+codecvt_base::result
+codecvt<char32_t, char8_t, mbstate_t>::
+do_out(state_type&, const intern_type* __from, const intern_type* __from_end,
+       const intern_type*& __from_next,
+       extern_type* __to, extern_type* __to_end,
+       extern_type*& __to_next) const
+{
+  range<const char32_t> from{ __from, __from_end };
+  range<char8_t> to{ __to, __to_end };
+  auto res = ucs4_out(from, to);
+  __from_next = from.next;
+  __to_next = to.next;
+  return res;
+}
+
+codecvt_base::result
+codecvt<char32_t, char8_t, mbstate_t>::
+do_unshift(state_type&, extern_type* __to, extern_type*,
+	   extern_type*& __to_next) const
+{
+  __to_next = __to;
+  return noconv;
+}
+
+codecvt_base::result
+codecvt<char32_t, char8_t, mbstate_t>::
+do_in(state_type&, const extern_type* __from, const extern_type* __from_end,
+      const extern_type*& __from_next,
+      intern_type* __to, intern_type* __to_end,
+      intern_type*& __to_next) const
+{
+  range<const char8_t> from{ __from, __from_end };
+  range<char32_t> to{ __to, __to_end };
+  auto res = ucs4_in(from, to);
+  __from_next = from.next;
+  __to_next = to.next;
+  return res;
+}
+
+int
+codecvt<char32_t, char8_t, mbstate_t>::do_encoding() const throw()
+{ return 0; } // UTF-8 is not a fixed-width encoding
+
+bool
+codecvt<char32_t, char8_t, mbstate_t>::do_always_noconv() const throw()
+{ return false; }
+
+int
+codecvt<char32_t, char8_t, mbstate_t>::
+do_length(state_type&, const extern_type* __from,
+	  const extern_type* __end, size_t __max) const
+{
+  __end = ucs4_span(__from, __end, __max);
+  return __end - __from;
+}
+
+int
+codecvt<char32_t, char8_t, mbstate_t>::do_max_length() const throw()
+{
+  // A single character (one UTF-32 code unit) requires
+  // up to 4 UTF-8 code units.
+  return 4;
+}
+#endif // _GLIBCXX_USE_CHAR8_T
+
 // Define members of codecvt_utf8<char16_t> base class implementation.
 // Converts from UTF-8 to UCS-2.
 
@@ -1636,5 +1797,12 @@ inline template class __codecvt_abstract_base<char32_t, char, mbstate_t>;
 template class codecvt_byname<char16_t, char, mbstate_t>;
 template class codecvt_byname<char32_t, char, mbstate_t>;
 
+#if defined(_GLIBCXX_USE_CHAR8_T)
+inline template class __codecvt_abstract_base<char16_t, char8_t, mbstate_t>;
+inline template class __codecvt_abstract_base<char32_t, char8_t, mbstate_t>;
+template class codecvt_byname<char16_t, char8_t, mbstate_t>;
+template class codecvt_byname<char32_t, char8_t, mbstate_t>;
+#endif
+
 _GLIBCXX_END_NAMESPACE_VERSION
 }
diff --git a/libstdc++-v3/src/c++11/limits.cc b/libstdc++-v3/src/c++11/limits.cc
index ed7e631..77b652d 100644
--- a/libstdc++-v3/src/c++11/limits.cc
+++ b/libstdc++-v3/src/c++11/limits.cc
@@ -525,6 +525,33 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
   const bool numeric_limits<long double>::tinyness_before;
   const float_round_style numeric_limits<long double>::round_style;
 
+#ifdef _GLIBCXX_USE_CHAR8_T
+  // char8_t
+  const bool numeric_limits<char8_t>::is_specialized;
+  const int  numeric_limits<char8_t>::digits;
+  const int  numeric_limits<char8_t>::digits10;
+  const int  numeric_limits<char8_t>::max_digits10;
+  const bool numeric_limits<char8_t>::is_signed;
+  const bool numeric_limits<char8_t>::is_integer;
+  const bool numeric_limits<char8_t>::is_exact;
+  const int  numeric_limits<char8_t>::radix;
+  const int  numeric_limits<char8_t>::min_exponent;
+  const int  numeric_limits<char8_t>::min_exponent10;
+  const int  numeric_limits<char8_t>::max_exponent;
+  const int  numeric_limits<char8_t>::max_exponent10;
+  const bool numeric_limits<char8_t>::has_infinity;
+  const bool numeric_limits<char8_t>::has_quiet_NaN;
+  const bool numeric_limits<char8_t>::has_signaling_NaN;
+  const float_denorm_style numeric_limits<char8_t>::has_denorm;
+  const bool numeric_limits<char8_t>::has_denorm_loss;
+  const bool numeric_limits<char8_t>::is_iec559;
+  const bool numeric_limits<char8_t>::is_bounded;
+  const bool numeric_limits<char8_t>::is_modulo;
+  const bool numeric_limits<char8_t>::traps;
+  const bool numeric_limits<char8_t>::tinyness_before;
+  const float_round_style numeric_limits<char8_t>::round_style;
+#endif // _GLIBCXX_USE_CHAR8_T
+
   // char16_t
   const bool numeric_limits<char16_t>::is_specialized;
   const int  numeric_limits<char16_t>::digits;
diff --git a/libstdc++-v3/src/c++98/Makefile.am b/libstdc++-v3/src/c++98/Makefile.am
index b9f59ec..ba88f00 100644
--- a/libstdc++-v3/src/c++98/Makefile.am
+++ b/libstdc++-v3/src/c++98/Makefile.am
@@ -184,13 +184,13 @@ endif
 
 # XXX TODO move locale_init.cc and localename.cc to src/c++11
 locale_init.lo: locale_init.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 locale_init.o: locale_init.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 localename.lo: localename.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 localename.o: localename.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 
 # Use special rules for the deprecated source files so that they find
 # deprecated include files.
diff --git a/libstdc++-v3/src/c++98/Makefile.in b/libstdc++-v3/src/c++98/Makefile.in
index 009cb11..8e89c73 100644
--- a/libstdc++-v3/src/c++98/Makefile.in
+++ b/libstdc++-v3/src/c++98/Makefile.in
@@ -888,13 +888,13 @@ c++locale.o: c++locale.cc
 
 # XXX TODO move locale_init.cc and localename.cc to src/c++11
 locale_init.lo: locale_init.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 locale_init.o: locale_init.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 localename.lo: localename.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 localename.o: localename.cc
-	$(LTCXXCOMPILE) -std=gnu++11 -c $<
+	$(LTCXXCOMPILE) -std=gnu++11 -fchar8_t -c $<
 strstream.lo: strstream.cc
 	$(LTCXXCOMPILE) -I$(GLIBCXX_INCLUDE_DIR)/backward -Wno-deprecated -c $<
 strstream.o: strstream.cc
diff --git a/libstdc++-v3/src/c++98/locale_init.cc b/libstdc++-v3/src/c++98/locale_init.cc
index 0b778de..e5e9d74 100644
--- a/libstdc++-v3/src/c++98/locale_init.cc
+++ b/libstdc++-v3/src/c++98/locale_init.cc
@@ -209,6 +209,16 @@ namespace
   __attribute__ ((aligned(__alignof__(codecvt<char32_t, char, mbstate_t>))));
   fake_codecvt_c32 codecvt_c32;
 
+#ifdef _GLIBCXX_USE_CHAR8_T
+  typedef char fake_codecvt_c16_c8[sizeof(codecvt<char16_t, char8_t, mbstate_t>)]
+  __attribute__ ((aligned(__alignof__(codecvt<char16_t, char8_t, mbstate_t>))));
+  fake_codecvt_c16_c8 codecvt_c16_c8;
+
+  typedef char fake_codecvt_c32_c8[sizeof(codecvt<char32_t, char8_t, mbstate_t>)]
+  __attribute__ ((aligned(__alignof__(codecvt<char32_t, char8_t, mbstate_t>))));
+  fake_codecvt_c32_c8 codecvt_c32_c8;
+#endif
+
   // Storage for "C" locale caches.
   typedef char fake_num_cache_c[sizeof(std::__numpunct_cache<char>)]
   __attribute__ ((aligned(__alignof__(std::__numpunct_cache<char>))));
@@ -329,6 +339,10 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
 #if _GLIBCXX_NUM_UNICODE_FACETS != 0
     &codecvt<char16_t, char, mbstate_t>::id,
     &codecvt<char32_t, char, mbstate_t>::id,
+#ifdef _GLIBCXX_USE_CHAR8_T
+    &codecvt<char16_t, char8_t, mbstate_t>::id,
+    &codecvt<char32_t, char8_t, mbstate_t>::id,
+#endif
 #endif
     0
   };
@@ -536,6 +550,12 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
 #if _GLIBCXX_NUM_UNICODE_FACETS != 0
     _M_init_facet(new (&codecvt_c16) codecvt<char16_t, char, mbstate_t>(1));
     _M_init_facet(new (&codecvt_c32) codecvt<char32_t, char, mbstate_t>(1));
+
+#ifdef _GLIBCXX_USE_CHAR8_T
+    _M_init_facet(new (&codecvt_c16_c8) codecvt<char16_t, char8_t, mbstate_t>(1));
+    _M_init_facet(new (&codecvt_c32_c8) codecvt<char32_t, char8_t, mbstate_t>(1));
+#endif
+
 #endif
 
 #if _GLIBCXX_USE_DUAL_ABI
diff --git a/libstdc++-v3/src/c++98/localename.cc b/libstdc++-v3/src/c++98/localename.cc
index 38290f0..4e9c5e6 100644
--- a/libstdc++-v3/src/c++98/localename.cc
+++ b/libstdc++-v3/src/c++98/localename.cc
@@ -272,6 +272,12 @@ const int num_facets = _GLIBCXX_NUM_FACETS + _GLIBCXX_NUM_UNICODE_FACETS
 #if _GLIBCXX_NUM_UNICODE_FACETS != 0
         _M_init_facet(new codecvt<char16_t, char, mbstate_t>);
         _M_init_facet(new codecvt<char32_t, char, mbstate_t>);
+
+#ifdef _GLIBCXX_USE_CHAR8_T
+        _M_init_facet(new codecvt<char16_t, char8_t, mbstate_t>);
+        _M_init_facet(new codecvt<char32_t, char8_t, mbstate_t>);
+#endif
+
 #endif
 
 #if _GLIBCXX_USE_DUAL_ABI