Merge from trunk revision 8dc2499aa62f768c6395c9754b8cabc1ce25c494

30 files changed, 1498 insertions, 252 deletions

diff --git a/libcpp/ChangeLog b/libcpp/ChangeLog
index 32c91eb..c3679fe 100644
--- a/libcpp/ChangeLog
+++ b/libcpp/ChangeLog
@@ -1,3 +1,328 @@
+2022-02-01  Jakub Jelinek  <jakub@redhat.com>
+
+	PR preprocessor/104147
+	* macro.cc (funlike_invocation_p): For padding prefer a token
+	with val.source non-NULL especially if it has PREV_WHITE set
+	on val.source->flags.  Add gcc_assert that CPP_PADDING tokens
+	don't have PREV_WHITE set in flags.
+
+2022-02-01  Jakub Jelinek  <jakub@redhat.com>
+
+	* directives.cc (destringize_and_run): Push &pfile->avoid_paste
+	instead of a copy of pfile->directive_result for the CPP_PADDING
+	case.
+
+2022-01-24  Marek Polacek  <polacek@redhat.com>
+
+	PR preprocessor/104030
+	* include/cpplib.h (enum cpp_bidirectional_level): Add
+	bidirectional_ucn.  Set values explicitly.
+	* internal.h (cpp_reader): Adjust warn_bidi_p.
+	* lex.cc (maybe_warn_bidi_on_close): Don't warn about UCNs
+	unless UCN checking is on.
+	(maybe_warn_bidi_on_char): Likewise.
+
+2022-01-18  Richard Biener  <rguenther@suse.de>
+
+	* include/line-map.h (class line_maps): Re-arrange fields
+	to minimize padding.
+	(class rich_location): Likewise.
+	* line-map.cc (rich_location::rich_location): Adjust.
+
+2022-01-17  Martin Liska  <mliska@suse.cz>
+
+	* Makefile.in: Rename .c names to .cc.
+
+2022-01-17  Martin Liska  <mliska@suse.cz>
+
+	* Makefile.in: Rename .c names to .cc.
+	* charset.cc (convert_escape): Likewise.
+	* directives.cc (directive_diagnostics): Likewise.
+	(_cpp_handle_directive): Likewise.
+	(lex_macro_node): Likewise.
+	* include/cpplib.h (struct _cpp_file): Likewise.
+	(PURE_ZERO): Likewise.
+	(cpp_defined): Likewise.
+	(cpp_error_at): Likewise.
+	(cpp_forall_identifiers): Likewise.
+	(cpp_compare_macros): Likewise.
+	(cpp_get_converted_source): Likewise.
+	(cpp_read_state): Likewise.
+	(cpp_directive_only_process): Likewise.
+	(struct cpp_decoded_char): Likewise.
+	* include/line-map.h (enum lc_reason): Likewise.
+	(enum location_aspect): Likewise.
+	* include/mkdeps.h: Likewise.
+	* init.cc (cpp_destroy): Likewise.
+	(cpp_finish): Likewise.
+	* internal.h (struct cpp_reader): Likewise.
+	(_cpp_defined_macro_p): Likewise.
+	(_cpp_backup_tokens_direct): Likewise.
+	(_cpp_destroy_hashtable): Likewise.
+	(_cpp_has_header): Likewise.
+	(_cpp_expand_op_stack): Likewise.
+	(_cpp_commit_buff): Likewise.
+	(_cpp_restore_special_builtin): Likewise.
+	(_cpp_bracket_include): Likewise.
+	(_cpp_replacement_text_len): Likewise.
+	(ufputs): Likewise.
+	* line-map.cc (linemap_macro_loc_to_exp_point): Likewise.
+	(linemap_check_files_exited): Likewise.
+	(line_map_new_raw): Likewise.
+	* traditional.cc (enum ls): Likewise.
+
+2022-01-17  Martin Liska  <mliska@suse.cz>
+
+	* charset.c: Moved to...
+	* charset.cc: ...here.
+	* directives.c: Moved to...
+	* directives.cc: ...here.
+	* errors.c: Moved to...
+	* errors.cc: ...here.
+	* expr.c: Moved to...
+	* expr.cc: ...here.
+	* files.c: Moved to...
+	* files.cc: ...here.
+	* identifiers.c: Moved to...
+	* identifiers.cc: ...here.
+	* init.c: Moved to...
+	* init.cc: ...here.
+	* lex.c: Moved to...
+	* lex.cc: ...here.
+	* line-map.c: Moved to...
+	* line-map.cc: ...here.
+	* macro.c: Moved to...
+	* macro.cc: ...here.
+	* makeucnid.c: Moved to...
+	* makeucnid.cc: ...here.
+	* mkdeps.c: Moved to...
+	* mkdeps.cc: ...here.
+	* pch.c: Moved to...
+	* pch.cc: ...here.
+	* symtab.c: Moved to...
+	* symtab.cc: ...here.
+	* traditional.c: Moved to...
+	* traditional.cc: ...here.
+
+2022-01-15  Martin Sebor  <msebor@redhat.com>
+
+	* files.c (_cpp_find_file): Substitute a valid pointer for
+	an invalid one to avoid -Wuse-after-free.
+
+2022-01-12  Clément Chigot  <clement.chigot@atos.net>
+
+	* configure.ac: Check sizeof ino_t and dev_t.
+	* config.in: Regenerate.
+	* configure: Regenerate.
+	* include/cpplib.h (INO_T_CPP): Change for AIX.
+	(DEV_T_CPP): New macro.
+	(struct cpp_dir): Use it.
+
+2021-12-30  Jakub Jelinek  <jakub@redhat.com>
+
+	PR preprocessor/89971
+	* macro.c (replace_args): For ##__VA_OPT__, if __VA_OPT__ expands
+	to no tokens at all, drop PASTE_LEFT flag from the previous token.
+
+2021-12-04  Jakub Jelinek  <jakub@redhat.com>
+
+	PR preprocessor/102432
+	* lex.c (_cpp_lex_direct): If buffer->need_line while
+	pfile->state.in_deferred_pragma, return CPP_PRAGMA_EOL token instead
+	of assertion failure.
+
+2021-12-03  Jakub Jelinek  <jakub@redhat.com>
+
+	PR pch/71934
+	* include/line-map.h (class line_maps): Add GTY((callback)) to
+	reallocator and round_alloc_size members.
+
+2021-12-01  Jakub Jelinek  <jakub@redhat.com>
+
+	PR c++/100977
+	* init.c (struct lang_flags): Remove cxx23_identifiers.
+	(lang_defaults): Remove cxx23_identifiers initializers.
+	(cpp_set_lang): Don't copy cxx23_identifiers.
+	* include/cpplib.h (struct cpp_options): Adjust comment about
+	c11_identifiers.  Remove cxx23_identifiers field.
+	* lex.c (warn_about_normalization): Use cplusplus instead of
+	cxx23_identifiers.
+	* charset.c (ucn_valid_in_identifier): Likewise.
+
+2021-12-01  Jakub Jelinek  <jakub@redhat.com>
+
+	PR preprocessor/103415
+	* macro.c (stringify_arg): Remove va_opt argument and va_opt handling.
+	(paste_tokens): On successful paste or in PREV_WHITE and
+	PREV_FALLTHROUGH flags from the *plhs token to the new token.
+	(replace_args): Adjust stringify_arg callers.  For #__VA_OPT__,
+	perform token pasting in a separate loop before stringify_arg call.
+
+2021-11-30  Richard Biener  <rguenther@suse.de>
+
+	* charset.c (convert_escape): Remove unreachable break.
+
+2021-11-30  Jakub Jelinek  <jakub@redhat.com>
+
+	PR c++/100977
+	* init.c (lang_defaults): Enable cxx23_identifiers for
+	-std={gnu,c}++{11,14,17,20} too.
+
+2021-11-29  Eric Gallager  <egallager@gcc.gnu.org>
+
+	PR other/103021
+	* Makefile.in: Use ETAGS variable in TAGS target.
+	* configure: Regenerate.
+	* configure.ac: Allow ETAGS variable to be overridden.
+
+2021-11-23  Christophe Lyon  <christophe.lyon@foss.st.com>
+
+	PR preprocessor/103355
+	* system.h (ATTR_LIKELY): Fix definition.
+
+2021-11-23  Marek Polacek  <polacek@redhat.com>
+	    Jonathan Wakely  <jwakely@redhat.com>
+
+	PR preprocessor/103355
+	* lex.c: Use ATTR_LIKELY instead of [[likely]].
+	* system.h (ATTR_LIKELY): Define.
+
+2021-11-22  Jakub Jelinek  <jakub@redhat.com>
+	    Tobias Burnus  <tobias@codesourcery.com>
+
+	PR preprocessor/103165
+	* internal.h (struct lexer_state): Add ignore__Pragma field.
+	* macro.c (builtin_macro): Don't interpret _Pragma if
+	pfile->state.ignore__Pragma.
+	(expand_arg): Temporarily set pfile->state.ignore__Pragma to 1.
+
+2021-11-17  David Malcolm  <dmalcolm@redhat.com>
+
+	PR preprocessor/103026
+	* lex.c (struct bidi::context): New.
+	(bidi::vec): Convert to a vec of context rather than unsigned
+	char.
+	(bidi::ctx_at): Rename to...
+	(bidi::pop_kind_at): ...this and reimplement for above change.
+	(bidi::current_ctx): Update for change to vec.
+	(bidi::current_ctx_ucn_p): Likewise.
+	(bidi::current_ctx_loc): New.
+	(bidi::on_char): Update for usage of context struct.  Add "loc"
+	param and pass it when pushing contexts.
+	(get_location_for_byte_range_in_cur_line): New.
+	(get_bidi_utf8): Rename to...
+	(get_bidi_utf8_1): ...this, reintroducing...
+	(get_bidi_utf8): ...as a wrapper, setting *OUT when the result is
+	not NONE.
+	(get_bidi_ucn): Rename to...
+	(get_bidi_ucn_1): ...this, reintroducing...
+	(get_bidi_ucn): ...as a wrapper, setting *OUT when the result is
+	not NONE.
+	(class unpaired_bidi_rich_location): New.
+	(maybe_warn_bidi_on_close): Use unpaired_bidi_rich_location when
+	reporting on unpaired bidi chars.  Split into singular vs plural
+	spellings.
+	(maybe_warn_bidi_on_char): Pass in a location_t rather than a
+	const uchar * and use it when emitting warnings, and when calling
+	bidi::on_char.
+	(_cpp_skip_block_comment): Capture location when kind is not NONE
+	and pass it to maybe_warn_bidi_on_char.
+	(skip_line_comment): Likewise.
+	(forms_identifier_p): Likewise.
+	(lex_raw_string): Likewise.
+	(lex_string): Likewise.
+
+2021-11-17  David Malcolm  <dmalcolm@redhat.com>
+
+	PR preprocessor/103026
+	* lex.c (maybe_warn_bidi_on_close): Use a rich_location
+	and call set_escape_on_output (true) on it.
+	(maybe_warn_bidi_on_char): Likewise.
+
+2021-11-17  Jakub Jelinek  <jakub@redhat.com>
+
+	PR preprocessor/103130
+	* lex.c (cpp_directive_only_process): Treat even \*/ as end of block
+	comment.
+
+2021-11-17  Marek Polacek  <polacek@redhat.com>
+
+	PR preprocessor/103026
+	* include/cpplib.h (enum cpp_bidirectional_level): New.
+	(struct cpp_options): Add cpp_warn_bidirectional.
+	(enum cpp_warning_reason): Add CPP_W_BIDIRECTIONAL.
+	* internal.h (struct cpp_reader): Add warn_bidi_p member
+	function.
+	* init.c (cpp_create_reader): Set cpp_warn_bidirectional.
+	* lex.c (bidi): New namespace.
+	(get_bidi_utf8): New function.
+	(get_bidi_ucn): Likewise.
+	(maybe_warn_bidi_on_close): Likewise.
+	(maybe_warn_bidi_on_char): Likewise.
+	(_cpp_skip_block_comment): Implement warning about bidirectional
+	control characters.
+	(skip_line_comment): Likewise.
+	(forms_identifier_p): Likewise.
+	(lex_identifier): Likewise.
+	(lex_string): Likewise.
+	(lex_raw_string): Likewise.
+
+2021-11-01  David Malcolm  <dmalcolm@redhat.com>
+
+	* charset.c (convert_escape): Use encoding_rich_location when
+	complaining about nonprintable unknown escape sequences.
+	(cpp_display_width_computation::::cpp_display_width_computation):
+	Pass in policy rather than tabstop.
+	(cpp_display_width_computation::process_next_codepoint): Add "out"
+	param and populate *out if non-NULL.
+	(cpp_display_width_computation::advance_display_cols): Pass NULL
+	to process_next_codepoint.
+	(cpp_byte_column_to_display_column): Pass in policy rather than
+	tabstop.  Pass NULL to process_next_codepoint.
+	(cpp_display_column_to_byte_column): Pass in policy rather than
+	tabstop.
+	* errors.c (cpp_diagnostic_get_current_location): New function,
+	splitting out the logic from...
+	(cpp_diagnostic): ...here.
+	(cpp_warning_at): New function.
+	(cpp_pedwarning_at): New function.
+	* include/cpplib.h (cpp_warning_at): New decl for rich_location.
+	(cpp_pedwarning_at): Likewise.
+	(struct cpp_decoded_char): New.
+	(struct cpp_char_column_policy): New.
+	(cpp_display_width_computation::cpp_display_width_computation):
+	Replace "tabstop" param with "policy".
+	(cpp_display_width_computation::process_next_codepoint): Add "out"
+	param.
+	(cpp_display_width_computation::m_tabstop): Replace with...
+	(cpp_display_width_computation::m_policy): ...this.
+	(cpp_byte_column_to_display_column): Replace "tabstop" param with
+	"policy".
+	(cpp_display_width): Likewise.
+	(cpp_display_column_to_byte_column): Likewise.
+	* include/line-map.h (rich_location::escape_on_output_p): New.
+	(rich_location::set_escape_on_output): New.
+	(rich_location::m_escape_on_output): New.
+	* internal.h (cpp_diagnostic_get_current_location): New decl.
+	(class encoding_rich_location): New.
+	* lex.c (skip_whitespace): Use encoding_rich_location when
+	complaining about null characters.
+	(warn_about_normalization): Generate a source range when
+	complaining about improperly normalized tokens, rather than just a
+	point, and use encoding_rich_location so that the source code
+	is escaped on printing.
+	* line-map.c (rich_location::rich_location): Initialize
+	m_escape_on_output.
+
+2021-10-29  Tobias Burnus  <tobias@codesourcery.com>
+
+	PR c++/102409
+	* directives.c (destringize_and_run): Add PRAGMA_OP to the
+	CPP_PRAGMA token's flags to mark is as coming from _Pragma.
+	* include/cpplib.h (PRAGMA_OP): #define, to be used with token flags.
+	* macro.c (collect_args): Only handle CPP_PRAGMA special if PRAGMA_OP
+	is set.
+
 2021-10-22  Eric Gallager  <egallager@gcc.gnu.org>
 
 	PR other/102663
@@ -6861,7 +7186,7 @@
 	* include/symtab.h: Moved from gcc/hashtable.h.  Change header
 	guard name.
 
-Copyright (C) 2004-2021 Free Software Foundation, Inc.
+Copyright (C) 2004-2022 Free Software Foundation, Inc.
 
 Copying and distribution of this file, with or without modification,
 are permitted in any medium without royalty provided the copyright
diff --git a/libcpp/Makefile.in b/libcpp/Makefile.in
index 34e4206..9e4c3fe 100644
--- a/libcpp/Makefile.in
+++ b/libcpp/Makefile.in
@@ -1,7 +1,7 @@
 # @configure_input@
 # Makefile for libcpp.  Run 'configure' to generate Makefile from Makefile.in
 
-# Copyright (C) 2004-2021 Free Software Foundation, Inc.
+# Copyright (C) 2004-2022 Free Software Foundation, Inc.
 
 #This file is part of libcpp.
 
@@ -89,14 +89,14 @@ libcpp_a_OBJS = charset.o directives.o errors.o \
 	expr.o files.o identifiers.o init.o lex.o line-map.o macro.o \
 	mkdeps.o pch.o symtab.o traditional.o
 
-libcpp_a_SOURCES = charset.c directives.c errors.c \
-	expr.c files.c identifiers.c init.c lex.c line-map.c macro.c \
-	mkdeps.c pch.c symtab.c traditional.c
+libcpp_a_SOURCES = charset.cc directives.cc errors.cc \
+	expr.cc files.cc identifiers.cc init.cc lex.cc line-map.cc macro.cc \
+	mkdeps.cc pch.cc symtab.cc traditional.cc
 
 all: libcpp.a $(USED_CATALOGS)
 
 .SUFFIXES:
-.SUFFIXES: .c .gmo .o .obj .po .pox
+.SUFFIXES: .cc .gmo .o .obj .po .pox
 
 libcpp.a: $(libcpp_a_OBJS)
 	-rm -f libcpp.a
@@ -223,7 +223,7 @@ endif
 
 # Implicit rules and I18N
 
-.c.o:
+.cc.o:
 	$(COMPILE) $<
 	$(POSTCOMPILE)
 
@@ -264,11 +264,13 @@ po/$(PACKAGE).pot: $(libcpp_a_SOURCES)
 	sed 's:$(srcdir)/::g' <po/$(PACKAGE).pot.tmp >po/$(PACKAGE).pot
 	rm po/$(PACKAGE).pot.tmp
 
+ETAGS = @ETAGS@
+
 TAGS_SOURCES = $(libcpp_a_SOURCES) internal.h system.h ucnid.h \
     include/cpplib.h include/line-map.h include/mkdeps.h include/symtab.h
 
 TAGS: $(TAGS_SOURCES)
-	cd $(srcdir) && etags $(TAGS_SOURCES)
+	cd $(srcdir) && $(ETAGS) $(TAGS_SOURCES)
 
 # Tell versions [3.59,3.63) of GNU make to not export all variables.
 # Otherwise a system limit (for SysV at least) may be exceeded.
diff --git a/libcpp/charset.c b/libcpp/charset.cc
index e4e45f6..ca8b7cf 100644
--- a/libcpp/charset.c
+++ b/libcpp/charset.cc
@@ -1,7 +1,7 @@
 /* CPP Library - charsets
-   Copyright (C) 1998-2021 Free Software Foundation, Inc.
+   Copyright (C) 1998-2022 Free Software Foundation, Inc.
 
-   Broken out of c-lex.c Apr 2003, adding valid C99 UCN ranges.
+   Broken out of c-lex.cc Apr 2003, adding valid C99 UCN ranges.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
@@ -955,14 +955,12 @@ ucn_valid_in_identifier (cpp_reader *pfile, cppchar_t c,
   valid_flags = C99 | CXX | C11 | CXX23;
   if (CPP_PEDANTIC (pfile))
     {
-      if (CPP_OPTION (pfile, cxx23_identifiers))
+      if (CPP_OPTION (pfile, cplusplus))
 	valid_flags = CXX23;
       else if (CPP_OPTION (pfile, c11_identifiers))
 	valid_flags = C11;
       else if (CPP_OPTION (pfile, c99))
 	valid_flags = C99;
-      else if (CPP_OPTION (pfile, cplusplus))
-	valid_flags = CXX;
     }
   if (! (ucnranges[mn].flags & valid_flags))
       return 0;
@@ -1021,7 +1019,7 @@ ucn_valid_in_identifier (cpp_reader *pfile, cppchar_t c,
       return 2;
     }
 
-  if (CPP_OPTION (pfile, cxx23_identifiers))
+  if (CPP_OPTION (pfile, cplusplus))
     invalid_start_flags = NXX23;
   else if (CPP_OPTION (pfile, c11_identifiers))
     invalid_start_flags = N11;
@@ -1534,7 +1532,6 @@ convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
     case 'x':
       return convert_hex (pfile, from, limit, tbuf, cvt,
 			  char_range, loc_reader, ranges);
-      break;
 
     case '0':  case '1':  case '2':  case '3':
     case '4':  case '5':  case '6':  case '7':
@@ -1582,12 +1579,14 @@ convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
 		   "unknown escape sequence: '\\%c'", (int) c);
       else
 	{
-	  /* diagnostic.c does not support "%03o".  When it does, this
+	  encoding_rich_location rich_loc (pfile);
+
+	  /* diagnostic.cc does not support "%03o".  When it does, this
 	     code can use %03o directly in the diagnostic again.  */
 	  char buf[32];
 	  sprintf(buf, "%03o", (int) c);
-	  cpp_error (pfile, CPP_DL_PEDWARN,
-		     "unknown escape sequence: '\\%s'", buf);
+	  cpp_error_at (pfile, CPP_DL_PEDWARN, &rich_loc,
+			"unknown escape sequence: '\\%s'", buf);
 	}
     }
 
@@ -2345,14 +2344,16 @@ cpp_string_location_reader::get_next ()
 }
 
 cpp_display_width_computation::
-cpp_display_width_computation (const char *data, int data_length, int tabstop) :
+cpp_display_width_computation (const char *data, int data_length,
+			       const cpp_char_column_policy &policy) :
   m_begin (data),
   m_next (m_begin),
   m_bytes_left (data_length),
-  m_tabstop (tabstop),
+  m_policy (policy),
   m_display_cols (0)
 {
-  gcc_assert (m_tabstop > 0);
+  gcc_assert (policy.m_tabstop > 0);
+  gcc_assert (policy.m_width_cb);
 }
 
 
@@ -2364,19 +2365,28 @@ cpp_display_width_computation (const char *data, int data_length, int tabstop) :
    point to a valid UTF-8-encoded sequence, then it will be treated as a single
    byte with display width 1.  m_cur_display_col is the current display column,
    relative to which tab stops should be expanded.  Returns the display width of
-   the codepoint just processed.  */
+   the codepoint just processed.
+   If OUT is non-NULL, it is populated.  */
 
 int
-cpp_display_width_computation::process_next_codepoint ()
+cpp_display_width_computation::process_next_codepoint (cpp_decoded_char *out)
 {
   cppchar_t c;
   int next_width;
 
+  if (out)
+    out->m_start_byte = m_next;
+
   if (*m_next == '\t')
     {
       ++m_next;
       --m_bytes_left;
-      next_width = m_tabstop - (m_display_cols % m_tabstop);
+      next_width = m_policy.m_tabstop - (m_display_cols % m_policy.m_tabstop);
+      if (out)
+	{
+	  out->m_ch = '\t';
+	  out->m_valid_ch = true;
+	}
     }
   else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c)
 	   != 0)
@@ -2386,14 +2396,24 @@ cpp_display_width_computation::process_next_codepoint ()
 	 of one.  */
       ++m_next;
       --m_bytes_left;
-      next_width = 1;
+      next_width = m_policy.m_undecoded_byte_width;
+      if (out)
+	out->m_valid_ch = false;
     }
   else
     {
       /*  one_utf8_to_cppchar() has updated m_next and m_bytes_left for us.  */
-      next_width = cpp_wcwidth (c);
+      next_width = m_policy.m_width_cb (c);
+      if (out)
+	{
+	  out->m_ch = c;
+	  out->m_valid_ch = true;
+	}
     }
 
+  if (out)
+    out->m_next_byte = m_next;
+
   m_display_cols += next_width;
   return next_width;
 }
@@ -2409,7 +2429,7 @@ cpp_display_width_computation::advance_display_cols (int n)
   const int start = m_display_cols;
   const int target = start + n;
   while (m_display_cols < target && !done ())
-    process_next_codepoint ();
+    process_next_codepoint (NULL);
   return m_display_cols - start;
 }
 
@@ -2417,29 +2437,33 @@ cpp_display_width_computation::advance_display_cols (int n)
     how many display columns are occupied by the first COLUMN bytes.  COLUMN
     may exceed DATA_LENGTH, in which case the phantom bytes at the end are
     treated as if they have display width 1.  Tabs are expanded to the next tab
-    stop, relative to the start of DATA.  */
+    stop, relative to the start of DATA, and non-printable-ASCII characters
+    will be escaped as per POLICY.  */
 
 int
 cpp_byte_column_to_display_column (const char *data, int data_length,
-				   int column, int tabstop)
+				   int column,
+				   const cpp_char_column_policy &policy)
 {
   const int offset = MAX (0, column - data_length);
-  cpp_display_width_computation dw (data, column - offset, tabstop);
+  cpp_display_width_computation dw (data, column - offset, policy);
   while (!dw.done ())
-    dw.process_next_codepoint ();
+    dw.process_next_codepoint (NULL);
   return dw.display_cols_processed () + offset;
 }
 
 /*  For the string of length DATA_LENGTH bytes that begins at DATA, compute
     the least number of bytes that will result in at least DISPLAY_COL display
     columns.  The return value may exceed DATA_LENGTH if the entire string does
-    not occupy enough display columns.  */
+    not occupy enough display columns.  Non-printable-ASCII characters
+    will be escaped as per POLICY.  */
 
 int
 cpp_display_column_to_byte_column (const char *data, int data_length,
-				   int display_col, int tabstop)
+				   int display_col,
+				   const cpp_char_column_policy &policy)
 {
-  cpp_display_width_computation dw (data, data_length, tabstop);
+  cpp_display_width_computation dw (data, data_length, policy);
   const int avail_display = dw.advance_display_cols (display_col);
   return dw.bytes_processed () + MAX (0, display_col - avail_display);
 }
diff --git a/libcpp/config.in b/libcpp/config.in
index 89aa6a1..9983aee 100644
--- a/libcpp/config.in
+++ b/libcpp/config.in
@@ -258,6 +258,12 @@
 /* Define to the version of this package. */
 #undef PACKAGE_VERSION
 
+/* The size of `dev_t', as computed by sizeof. */
+#undef SIZEOF_DEV_T
+
+/* The size of `ino_t', as computed by sizeof. */
+#undef SIZEOF_INO_T
+
 /* The size of `int', as computed by sizeof. */
 #undef SIZEOF_INT
 
diff --git a/libcpp/configure b/libcpp/configure
index 9674cd9..7514539 100755
--- a/libcpp/configure
+++ b/libcpp/configure
@@ -652,6 +652,7 @@ noexception_flags
 WARN_PEDANTIC
 c_warn
 warn
+ETAGS
 AUTOHEADER
 AUTOCONF
 ACLOCAL
@@ -4896,6 +4897,11 @@ done
 test -n "$AUTOHEADER" || AUTOHEADER="$MISSING autoheader"
 
 
+if test -z "$ETAGS"; then
+  ETAGS=etags
+fi
+
+
 # Figure out what compiler warnings we can enable.
 # See config/warnings.m4 for details.
 
@@ -6638,6 +6644,73 @@ $as_echo "#define HAVE_UCHAR 1" >>confdefs.h
 
 fi
 
+# The cast to long int works around a bug in the HP C Compiler
+# version HP92453-01 B.11.11.23709.GP, which incorrectly rejects
+# declarations like `int a3[[(sizeof (unsigned char)) >= 0]];'.
+# This bug is HP SR number 8606223364.
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking size of ino_t" >&5
+$as_echo_n "checking size of ino_t... " >&6; }
+if ${ac_cv_sizeof_ino_t+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if ac_fn_c_compute_int "$LINENO" "(long int) (sizeof (ino_t))" "ac_cv_sizeof_ino_t"        "$ac_includes_default"; then :
+
+else
+  if test "$ac_cv_type_ino_t" = yes; then
+     { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5
+$as_echo "$as_me: error: in \`$ac_pwd':" >&2;}
+as_fn_error 77 "cannot compute sizeof (ino_t)
+See \`config.log' for more details" "$LINENO" 5; }
+   else
+     ac_cv_sizeof_ino_t=0
+   fi
+fi
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_sizeof_ino_t" >&5
+$as_echo "$ac_cv_sizeof_ino_t" >&6; }
+
+
+
+cat >>confdefs.h <<_ACEOF
+#define SIZEOF_INO_T $ac_cv_sizeof_ino_t
+_ACEOF
+
+
+# The cast to long int works around a bug in the HP C Compiler
+# version HP92453-01 B.11.11.23709.GP, which incorrectly rejects
+# declarations like `int a3[[(sizeof (unsigned char)) >= 0]];'.
+# This bug is HP SR number 8606223364.
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking size of dev_t" >&5
+$as_echo_n "checking size of dev_t... " >&6; }
+if ${ac_cv_sizeof_dev_t+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  if ac_fn_c_compute_int "$LINENO" "(long int) (sizeof (dev_t))" "ac_cv_sizeof_dev_t"        "$ac_includes_default"; then :
+
+else
+  if test "$ac_cv_type_dev_t" = yes; then
+     { { $as_echo "$as_me:${as_lineno-$LINENO}: error: in \`$ac_pwd':" >&5
+$as_echo "$as_me: error: in \`$ac_pwd':" >&2;}
+as_fn_error 77 "cannot compute sizeof (dev_t)
+See \`config.log' for more details" "$LINENO" 5; }
+   else
+     ac_cv_sizeof_dev_t=0
+   fi
+fi
+
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_sizeof_dev_t" >&5
+$as_echo "$ac_cv_sizeof_dev_t" >&6; }
+
+
+
+cat >>confdefs.h <<_ACEOF
+#define SIZEOF_DEV_T $ac_cv_sizeof_dev_t
+_ACEOF
+
+
+
 # g++ on Solaris 10+ defines _XOPEN_SOURCE=600, which exposes a different
 # iconv() prototype.
 ac_ext=cpp
diff --git a/libcpp/configure.ac b/libcpp/configure.ac
index 1efa96f..9b60425 100644
--- a/libcpp/configure.ac
+++ b/libcpp/configure.ac
@@ -22,6 +22,11 @@ AC_CHECK_PROGS([ACLOCAL], [aclocal], [$MISSING aclocal])
 AC_CHECK_PROGS([AUTOCONF], [autoconf], [$MISSING autoconf])
 AC_CHECK_PROGS([AUTOHEADER], [autoheader], [$MISSING autoheader])
 
+if test -z "$ETAGS"; then
+  ETAGS=etags
+fi
+AC_SUBST([ETAGS])
+
 # Figure out what compiler warnings we can enable.
 # See config/warnings.m4 for details.
 
@@ -98,6 +103,9 @@ if test $ac_cv_type_uchar = yes; then
   [Define if <sys/types.h> defines \`uchar'.])
 fi
 
+AC_CHECK_SIZEOF(ino_t)
+AC_CHECK_SIZEOF(dev_t)
+
 # g++ on Solaris 10+ defines _XOPEN_SOURCE=600, which exposes a different
 # iconv() prototype.
 AC_LANG_PUSH([C++])
diff --git a/libcpp/directives.c b/libcpp/directives.cc
index b4bc8b4..f804a44 100644
--- a/libcpp/directives.c
+++ b/libcpp/directives.cc
@@ -1,5 +1,5 @@
 /* CPP Library. (Directive handling.)
-   Copyright (C) 1986-2021 Free Software Foundation, Inc.
+   Copyright (C) 1986-2022 Free Software Foundation, Inc.
    Contributed by Per Bothner, 1994-95.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
@@ -416,7 +416,7 @@ directive_diagnostics (cpp_reader *pfile, const directive *dir, int indented)
 
 /* Check if we have a known directive.  INDENTED is true if the
    '#' of the directive was indented.  This function is in this file
-   to save unnecessarily exporting dtable etc. to lex.c.  Returns
+   to save unnecessarily exporting dtable etc. to lex.cc.  Returns
    nonzero if the line of tokens has been handled, zero if we should
    continue processing the line.  */
 int
@@ -480,7 +480,7 @@ _cpp_handle_directive (cpp_reader *pfile, bool indented)
 
 	 does not cause '#define foo bar' to get executed when
 	 compiled with -save-temps, we recognize directives in
-	 -fpreprocessed mode only if the # is in column 1.  macro.c
+	 -fpreprocessed mode only if the # is in column 1.  macro.cc
 	 puts a space in front of any '#' at the start of a macro.
 	 
 	 We exclude the -fdirectives-only case because macro expansion
@@ -632,7 +632,7 @@ lex_macro_node (cpp_reader *pfile, bool is_def_or_undef)
   return NULL;
 }
 
-/* Process a #define directive.  Most work is done in macro.c.  */
+/* Process a #define directive.  Most work is done in macro.cc.  */
 static void
 do_define (cpp_reader *pfile)
 {
@@ -1907,6 +1907,8 @@ destringize_and_run (cpp_reader *pfile, const cpp_string *in,
   save_directive = pfile->directive;
   pfile->directive = &dtable[T_PRAGMA];
   do_pragma (pfile);
+  if (pfile->directive_result.type == CPP_PRAGMA)
+    pfile->directive_result.flags |= PRAGMA_OP;
   end_directive (pfile, 1);
   pfile->directive = save_directive;
 
@@ -1952,8 +1954,7 @@ destringize_and_run (cpp_reader *pfile, const cpp_string *in,
   else
     {
       count = 1;
-      toks = XNEW (cpp_token);
-      toks[0] = pfile->directive_result;
+      toks = &pfile->avoid_paste;
 
       /* If we handled the entire pragma internally, make sure we get the
 	 line number correct for the next token.  */
diff --git a/libcpp/errors.c b/libcpp/errors.cc
index 5e1bf33..df5f8d6 100644
--- a/libcpp/errors.c
+++ b/libcpp/errors.cc
@@ -1,5 +1,5 @@
 /* Default error handlers for CPP Library.
-   Copyright (C) 1986-2021 Free Software Foundation, Inc.
+   Copyright (C) 1986-2022 Free Software Foundation, Inc.
    Written by Per Bothner, 1994.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
@@ -27,6 +27,31 @@ along with this program; see the file COPYING3.  If not see
 #include "cpplib.h"
 #include "internal.h"
 
+/* Get a location_t for the current location in PFILE,
+   generally that of the previously lexed token.  */
+
+location_t
+cpp_diagnostic_get_current_location (cpp_reader *pfile)
+{
+  if (CPP_OPTION (pfile, traditional))
+    {
+      if (pfile->state.in_directive)
+	return pfile->directive_line;
+      else
+	return pfile->line_table->highest_line;
+    }
+  /* We don't want to refer to a token before the beginning of the
+     current run -- that is invalid.  */
+  else if (pfile->cur_token == pfile->cur_run->base)
+    {
+      return 0;
+    }
+  else
+    {
+      return pfile->cur_token[-1].src_loc;
+    }
+}
+
 /* Print a diagnostic at the given location.  */
 
 ATTRIBUTE_FPTR_PRINTF(5,0)
@@ -52,25 +77,7 @@ cpp_diagnostic (cpp_reader * pfile, enum cpp_diagnostic_level level,
 		enum cpp_warning_reason reason,
 		const char *msgid, va_list *ap)
 {
-  location_t src_loc;
-
-  if (CPP_OPTION (pfile, traditional))
-    {
-      if (pfile->state.in_directive)
-	src_loc = pfile->directive_line;
-      else
-	src_loc = pfile->line_table->highest_line;
-    }
-  /* We don't want to refer to a token before the beginning of the
-     current run -- that is invalid.  */
-  else if (pfile->cur_token == pfile->cur_run->base)
-    {
-      src_loc = 0;
-    }
-  else
-    {
-      src_loc = pfile->cur_token[-1].src_loc;
-    }
+  location_t src_loc = cpp_diagnostic_get_current_location (pfile);
   rich_location richloc (pfile->line_table, src_loc);
   return cpp_diagnostic_at (pfile, level, reason, &richloc, msgid, ap);
 }
@@ -144,6 +151,43 @@ cpp_warning_syshdr (cpp_reader * pfile, enum cpp_warning_reason reason,
   return ret;
 }
 
+/* As cpp_warning above, but use RICHLOC as the location of the diagnostic.  */
+
+bool cpp_warning_at (cpp_reader *pfile, enum cpp_warning_reason reason,
+		     rich_location *richloc, const char *msgid, ...)
+{
+  va_list ap;
+  bool ret;
+
+  va_start (ap, msgid);
+
+  ret = cpp_diagnostic_at (pfile, CPP_DL_WARNING, reason, richloc,
+			   msgid, &ap);
+
+  va_end (ap);
+  return ret;
+
+}
+
+/* As cpp_pedwarning above, but use RICHLOC as the location of the
+   diagnostic.  */
+
+bool
+cpp_pedwarning_at (cpp_reader * pfile, enum cpp_warning_reason reason,
+		   rich_location *richloc, const char *msgid, ...)
+{
+  va_list ap;
+  bool ret;
+
+  va_start (ap, msgid);
+
+  ret = cpp_diagnostic_at (pfile, CPP_DL_PEDWARN, reason, richloc,
+			   msgid, &ap);
+
+  va_end (ap);
+  return ret;
+}
+
 /* Print a diagnostic at a specific location.  */
 
 ATTRIBUTE_FPTR_PRINTF(6,0)
diff --git a/libcpp/expr.c b/libcpp/expr.cc
index ab4a260..78c5c3e 100644
--- a/libcpp/expr.c
+++ b/libcpp/expr.cc
@@ -1,5 +1,5 @@
 /* Parse C expressions for cpplib.
-   Copyright (C) 1987-2021 Free Software Foundation, Inc.
+   Copyright (C) 1987-2022 Free Software Foundation, Inc.
    Contributed by Per Bothner, 1994.
 
 This program is free software; you can redistribute it and/or modify it
diff --git a/libcpp/files.c b/libcpp/files.cc
index c93a03c..24208f7 100644
--- a/libcpp/files.c
+++ b/libcpp/files.cc
@@ -1,5 +1,5 @@
 /* Part of CPP library.  File handling.
-   Copyright (C) 1986-2021 Free Software Foundation, Inc.
+   Copyright (C) 1986-2022 Free Software Foundation, Inc.
    Written by Per Bothner, 1994.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
@@ -553,12 +553,11 @@ _cpp_find_file (cpp_reader *pfile, const char *fname, cpp_dir *start_dir,
 		  {
 		    /* If *hash_slot is NULL, the above
 		       htab_find_slot_with_hash call just created the
-		       slot, but we aren't going to store there
-		       anything, so need to remove the newly created
-		       entry.  htab_clear_slot requires that it is
-		       non-NULL, so store there some non-NULL pointer,
-		       htab_clear_slot will overwrite it
-		       immediately.  */
+		       slot, but we aren't going to store there anything
+		       of use, so need to remove the newly created entry.
+		       htab_clear_slot requires that it is non-NULL, so
+		       store some non-NULL but valid pointer there,
+		       htab_clear_slot will immediately overwrite it.  */
 		    *hash_slot = file;
 		    htab_clear_slot (pfile->file_hash, hash_slot);
 		  }
@@ -582,7 +581,7 @@ _cpp_find_file (cpp_reader *pfile, const char *fname, cpp_dir *start_dir,
 		if (*hash_slot == NULL)
 		  {
 		    /* See comment on the above htab_clear_slot call.  */
-		    *hash_slot = file;
+		    *hash_slot = &hash_slot;
 		    htab_clear_slot (pfile->file_hash, hash_slot);
 		  }
 		return NULL;
diff --git a/libcpp/identifiers.c b/libcpp/identifiers.cc
index dc0df11..835a971 100644
--- a/libcpp/identifiers.c
+++ b/libcpp/identifiers.cc
@@ -1,5 +1,5 @@
 /* Hash tables for the CPP library.
-   Copyright (C) 1986-2021 Free Software Foundation, Inc.
+   Copyright (C) 1986-2022 Free Software Foundation, Inc.
    Written by Per Bothner, 1994.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index 6e2fcb6..3eba6f7 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -1,5 +1,5 @@
 /* Definitions for CPP library.
-   Copyright (C) 1995-2021 Free Software Foundation, Inc.
+   Copyright (C) 1995-2022 Free Software Foundation, Inc.
    Written by Per Bothner, 1994-95.
 
 This program is free software; you can redistribute it and/or modify it
@@ -46,7 +46,7 @@ struct _cpp_file;
    '='.  The lexer needs operators ending in '=', like ">>=", to be in
    the same order as their counterparts without the '=', like ">>".
 
-   See the cpp_operator table optab in expr.c if you change the order or
+   See the cpp_operator table optab in expr.cc if you change the order or
    add or remove anything in the first group.  */
 
 #define TTYPE_TABLE							\
@@ -192,12 +192,13 @@ struct GTY(()) cpp_string {
 				     comment.  */
 #define BOL		(1 << 6) /* Token at beginning of line.  */
 #define PURE_ZERO	(1 << 7) /* Single 0 digit, used by the C++ frontend,
-				    set in c-lex.c.  */
+				    set in c-lex.cc.  */
 #define SP_DIGRAPH	(1 << 8) /* # or ## token was a digraph.  */
 #define SP_PREV_WHITE	(1 << 9) /* If whitespace before a ##
 				    operator, or before this token
 				    after a # operator.  */
 #define NO_EXPAND	(1 << 10) /* Do not macro-expand this token.  */
+#define PRAGMA_OP	(1 << 11) /* _Pragma token.  */
 
 /* Specify which field, if any, of the cpp_token union is used.  */
 
@@ -318,6 +319,18 @@ enum cpp_main_search
   CMS_system,  /* Search the system INCLUDE path.  */
 };
 
+/* The possible bidirectional control characters checking levels.  */
+enum cpp_bidirectional_level {
+  /* No checking.  */
+  bidirectional_none = 0,
+  /* Only detect unpaired uses of bidirectional control characters.  */
+  bidirectional_unpaired = 1,
+  /* Detect any use of bidirectional control characters.  */
+  bidirectional_any = 2,
+  /* Also warn about UCNs.  */
+  bidirectional_ucn = 4
+};
+
 /* This structure is nested inside struct cpp_reader, and
    carries all the options visible to the command line.  */
 struct cpp_options
@@ -479,13 +492,9 @@ struct cpp_options
   unsigned char ext_numeric_literals;
 
   /* Nonzero means extended identifiers allow the characters specified
-     in C11 and C++11.  */
+     in C11.  */
   unsigned char c11_identifiers;
 
-  /* Nonzero means extended identifiers allow the characters specified
-     in C++23.  */
-  unsigned char cxx23_identifiers;
-
   /* Nonzero for C++ 2014 Standard binary constants.  */
   unsigned char binary_constants;
 
@@ -538,6 +547,10 @@ struct cpp_options
   /* True if warn about differences between C++98 and C++11.  */
   bool cpp_warn_cxx11_compat;
 
+  /* Nonzero if bidirectional control characters checking is on.  See enum
+     cpp_bidirectional_level.  */
+  unsigned char cpp_warn_bidirectional;
+
   /* Dependency generation.  */
   struct
   {
@@ -642,7 +655,8 @@ enum cpp_warning_reason {
   CPP_W_C90_C99_COMPAT,
   CPP_W_C11_C2X_COMPAT,
   CPP_W_CXX11_COMPAT,
-  CPP_W_EXPANSION_TO_DEFINED
+  CPP_W_EXPANSION_TO_DEFINED,
+  CPP_W_BIDIRECTIONAL
 };
 
 /* Callback for header lookup for HEADER, which is the name of a
@@ -739,10 +753,18 @@ struct cpp_callbacks
 
 #ifdef VMS
 #define INO_T_CPP ino_t ino[3]
+#elif defined (_AIX) && SIZEOF_INO_T == 4
+#define INO_T_CPP ino64_t ino
 #else
 #define INO_T_CPP ino_t ino
 #endif
 
+#if defined (_AIX) && SIZEOF_DEV_T == 4
+#define DEV_T_CPP dev64_t dev
+#else
+#define DEV_T_CPP dev_t dev
+#endif
+
 /* Chain of directories to look for include files in.  */
 struct cpp_dir
 {
@@ -777,7 +799,7 @@ struct cpp_dir
   /* The C front end uses these to recognize duplicated
      directories in the search path.  */
   INO_T_CPP;
-  dev_t dev;
+  DEV_T_CPP;
 };
 
 /* The kind of the cpp_macro.  */
@@ -1174,7 +1196,7 @@ extern int cpp_defined (cpp_reader *, const unsigned char *, int);
    the double integer are set to zero.  */
 
 /* This type has to be equal to unsigned HOST_WIDE_INT, see
-   gcc/c-family/c-lex.c.  */
+   gcc/c-family/c-lex.cc.  */
 typedef uint64_t cpp_num_part;
 typedef struct cpp_num cpp_num;
 struct cpp_num
@@ -1267,6 +1289,14 @@ extern bool cpp_warning_syshdr (cpp_reader *, enum cpp_warning_reason reason,
 				const char *msgid, ...)
   ATTRIBUTE_PRINTF_3;
 
+/* As their counterparts above, but use RICHLOC.  */
+extern bool cpp_warning_at (cpp_reader *, enum cpp_warning_reason,
+			    rich_location *richloc, const char *msgid, ...)
+  ATTRIBUTE_PRINTF_4;
+extern bool cpp_pedwarning_at (cpp_reader *, enum cpp_warning_reason,
+			       rich_location *richloc, const char *msgid, ...)
+  ATTRIBUTE_PRINTF_4;
+
 /* Output a diagnostic with "MSGID: " preceding the
    error string of errno.  No location is printed.  */
 extern bool cpp_errno (cpp_reader *, enum cpp_diagnostic_level,
@@ -1304,7 +1334,7 @@ extern bool cpp_error_at (cpp_reader * pfile, enum cpp_diagnostic_level,
 			  rich_location *richloc, const char *msgid, ...)
   ATTRIBUTE_PRINTF_4;
 
-/* In lex.c */
+/* In lex.cc */
 extern int cpp_ideq (const cpp_token *, const char *);
 extern void cpp_output_line (cpp_reader *, FILE *);
 extern unsigned char *cpp_output_line_to_string (cpp_reader *,
@@ -1361,7 +1391,7 @@ extern cpp_hashnode *cpp_lookup (cpp_reader *, const unsigned char *,
 typedef int (*cpp_cb) (cpp_reader *, cpp_hashnode *, void *);
 extern void cpp_forall_identifiers (cpp_reader *, cpp_cb, void *);
 
-/* In macro.c */
+/* In macro.cc */
 extern void cpp_scan_nooutput (cpp_reader *);
 extern int  cpp_sys_macro_p (cpp_reader *);
 extern unsigned char *cpp_quote_string (unsigned char *, const unsigned char *,
@@ -1369,7 +1399,7 @@ extern unsigned char *cpp_quote_string (unsigned char *, const unsigned char *,
 extern bool cpp_compare_macros (const cpp_macro *macro1,
 				const cpp_macro *macro2);
 
-/* In files.c */
+/* In files.cc */
 extern bool cpp_included (cpp_reader *, const char *);
 extern bool cpp_included_before (cpp_reader *, const char *, location_t);
 extern void cpp_make_system_header (cpp_reader *, int, int);
@@ -1397,7 +1427,7 @@ struct cpp_converted_source
 cpp_converted_source cpp_get_converted_source (const char *fname,
 					       const char *input_charset);
 
-/* In pch.c */
+/* In pch.cc */
 struct save_macro_data;
 extern int cpp_save_state (cpp_reader *, FILE *);
 extern int cpp_write_pch_deps (cpp_reader *, FILE *);
@@ -1407,7 +1437,7 @@ extern void cpp_prepare_state (cpp_reader *, struct save_macro_data **);
 extern int cpp_read_state (cpp_reader *, const char *, FILE *,
 			   struct save_macro_data *);
 
-/* In lex.c */
+/* In lex.cc */
 extern void cpp_force_token_locations (cpp_reader *, location_t);
 extern void cpp_stop_forcing_token_locations (cpp_reader *);
 enum CPP_DO_task
@@ -1423,7 +1453,7 @@ extern void cpp_directive_only_process (cpp_reader *pfile,
 						    CPP_DO_task,
 						    void *data, ...));
 
-/* In expr.c */
+/* In expr.cc */
 extern enum cpp_ttype cpp_userdef_string_remove_type
   (enum cpp_ttype type);
 extern enum cpp_ttype cpp_userdef_string_add_type
@@ -1439,45 +1469,97 @@ extern bool cpp_userdef_char_p
 extern const char * cpp_get_userdef_suffix
   (const cpp_token *);
 
-/* In charset.c */
+/* In charset.cc */
+
+/* The result of attempting to decode a run of UTF-8 bytes.  */
+
+struct cpp_decoded_char
+{
+  const char *m_start_byte;
+  const char *m_next_byte;
+
+  bool m_valid_ch;
+  cppchar_t m_ch;
+};
+
+/* Information for mapping between code points and display columns.
+
+   This is a tabstop value, along with a callback for getting the
+   widths of characters.  Normally this callback is cpp_wcwidth, but we
+   support other schemes for escaping non-ASCII unicode as a series of
+   ASCII chars when printing the user's source code in diagnostic-show-locus.cc
+
+   For example, consider:
+   - the Unicode character U+03C0 "GREEK SMALL LETTER PI" (UTF-8: 0xCF 0x80)
+   - the Unicode character U+1F642 "SLIGHTLY SMILING FACE"
+     (UTF-8: 0xF0 0x9F 0x99 0x82)
+   - the byte 0xBF (a stray trailing byte of a UTF-8 character)
+   Normally U+03C0 would occupy one display column, U+1F642
+   would occupy two display columns, and the stray byte would be
+   printed verbatim as one display column.
+
+   However when escaping them as unicode code points as "<U+03C0>"
+   and "<U+1F642>" they occupy 8 and 9 display columns respectively,
+   and when escaping them as bytes as "<CF><80>" and "<F0><9F><99><82>"
+   they occupy 8 and 16 display columns respectively.  In both cases
+   the stray byte is escaped to <BF> as 4 display columns.  */
+
+struct cpp_char_column_policy
+{
+  cpp_char_column_policy (int tabstop,
+			  int (*width_cb) (cppchar_t c))
+  : m_tabstop (tabstop),
+    m_undecoded_byte_width (1),
+    m_width_cb (width_cb)
+  {}
+
+  int m_tabstop;
+  /* Width in display columns of a stray byte that isn't decodable
+     as UTF-8.  */
+  int m_undecoded_byte_width;
+  int (*m_width_cb) (cppchar_t c);
+};
 
 /* A class to manage the state while converting a UTF-8 sequence to cppchar_t
    and computing the display width one character at a time.  */
 class cpp_display_width_computation {
  public:
   cpp_display_width_computation (const char *data, int data_length,
-				 int tabstop);
+				 const cpp_char_column_policy &policy);
   const char *next_byte () const { return m_next; }
   int bytes_processed () const { return m_next - m_begin; }
   int bytes_left () const { return m_bytes_left; }
   bool done () const { return !bytes_left (); }
   int display_cols_processed () const { return m_display_cols; }
 
-  int process_next_codepoint ();
+  int process_next_codepoint (cpp_decoded_char *out);
   int advance_display_cols (int n);
 
  private:
   const char *const m_begin;
   const char *m_next;
   size_t m_bytes_left;
-  const int m_tabstop;
+  const cpp_char_column_policy &m_policy;
   int m_display_cols;
 };
 
 /* Convenience functions that are simple use cases for class
    cpp_display_width_computation.  Tab characters will be expanded to spaces
-   as determined by TABSTOP.  */
+   as determined by POLICY.m_tabstop, and non-printable-ASCII characters
+   will be escaped as per POLICY.  */
 
 int cpp_byte_column_to_display_column (const char *data, int data_length,
-				       int column, int tabstop);
+				       int column,
+				       const cpp_char_column_policy &policy);
 inline int cpp_display_width (const char *data, int data_length,
-			      int tabstop)
+			      const cpp_char_column_policy &policy)
 {
   return cpp_byte_column_to_display_column (data, data_length, data_length,
-					    tabstop);
+					    policy);
 }
 int cpp_display_column_to_byte_column (const char *data, int data_length,
-				       int display_col, int tabstop);
+				       int display_col,
+				       const cpp_char_column_policy &policy);
 int cpp_wcwidth (cppchar_t c);
 
 bool cpp_input_conversion_is_trivial (const char *input_charset);
diff --git a/libcpp/include/line-map.h b/libcpp/include/line-map.h
index 464494b..8033572 100644
--- a/libcpp/include/line-map.h
+++ b/libcpp/include/line-map.h
@@ -1,5 +1,5 @@
 /* Map (unsigned int) keys to (source file, line, column) triples.
-   Copyright (C) 2001-2021 Free Software Foundation, Inc.
+   Copyright (C) 2001-2022 Free Software Foundation, Inc.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
@@ -83,7 +83,7 @@ enum lc_reason
 
    This key only has meaning in relation to a line_maps instance.  Within
    gcc there is a single line_maps instance: "line_table", declared in
-   gcc/input.h and defined in gcc/input.c.
+   gcc/input.h and defined in gcc/input.cc.
 
    The values of the keys are intended to be internal to libcpp,
    but for ease-of-understanding the implementation, they are currently
@@ -792,6 +792,9 @@ public:
   /* If true, prints an include trace a la -H.  */
   bool trace_includes;
 
+  /* True if we've seen a #line or # 44 "file" directive.  */
+  bool seen_line_directive;
+
   /* Highest location_t "given out".  */
   location_t highest_location;
 
@@ -803,11 +806,11 @@ public:
   unsigned int max_column_hint;
 
   /* The allocator to use when resizing 'maps', defaults to xrealloc.  */
-  line_map_realloc reallocator;
+  line_map_realloc GTY((callback)) reallocator;
 
   /* The allocators' function used to know the actual size it
      allocated, for a certain allocation size requested.  */
-  line_map_round_alloc_size_func round_alloc_size;
+  line_map_round_alloc_size_func GTY((callback)) round_alloc_size;
 
   struct location_adhoc_data_map location_adhoc_data_map;
 
@@ -815,9 +818,6 @@ public:
      built-in tokens.  */
   location_t builtin_location;
 
-  /* True if we've seen a #line or # 44 "file" directive.  */
-  bool seen_line_directive;
-
   /* The default value of range_bits in ordinary line maps.  */
   unsigned int default_range_bits;
 
@@ -1787,6 +1787,18 @@ class rich_location
   const diagnostic_path *get_path () const { return m_path; }
   void set_path (const diagnostic_path *path) { m_path = path; }
 
+  /* A flag for hinting that the diagnostic involves character encoding
+     issues, and thus that it will be helpful to the user if we show some
+     representation of how the characters in the pertinent source lines
+     are encoded.
+     The default is false (i.e. do not escape).
+     When set to true, non-ASCII bytes in the pertinent source lines will
+     be escaped in a manner controlled by the user-supplied option
+     -fdiagnostics-escape-format=, so that the user can better understand
+     what's going on with the encoding in their source file.  */
+  bool escape_on_output_p () const { return m_escape_on_output; }
+  void set_escape_on_output (bool flag) { m_escape_on_output = flag; }
+
 private:
   bool reject_impossible_fixit (location_t where);
   void stop_supporting_fixits ();
@@ -1804,14 +1816,15 @@ protected:
   int m_column_override;
 
   bool m_have_expanded_location;
+  bool m_seen_impossible_fixit;
+  bool m_fixits_cannot_be_auto_applied;
+  bool m_escape_on_output;
+
   expanded_location m_expanded_location;
 
   static const int MAX_STATIC_FIXIT_HINTS = 2;
   semi_embedded_vec <fixit_hint *, MAX_STATIC_FIXIT_HINTS> m_fixit_hints;
 
-  bool m_seen_impossible_fixit;
-  bool m_fixits_cannot_be_auto_applied;
-
   const diagnostic_path *m_path;
 };
 
@@ -2093,8 +2106,8 @@ enum location_aspect
 
 /* The rich_location class requires a way to expand location_t instances.
    We would directly use expand_location_to_spelling_point, which is
-   implemented in gcc/input.c, but we also need to use it for rich_location
-   within genmatch.c.
+   implemented in gcc/input.cc, but we also need to use it for rich_location
+   within genmatch.cc.
    Hence we require client code of libcpp to implement the following
    symbol.  */
 extern expanded_location
diff --git a/libcpp/include/mkdeps.h b/libcpp/include/mkdeps.h
index 007f74e..96d6464 100644
--- a/libcpp/include/mkdeps.h
+++ b/libcpp/include/mkdeps.h
@@ -1,5 +1,5 @@
 /* Dependency generator for Makefile fragments.
-   Copyright (C) 2000-2021 Free Software Foundation, Inc.
+   Copyright (C) 2000-2022 Free Software Foundation, Inc.
    Contributed by Zack Weinberg, Mar 2000
 
 This program is free software; you can redistribute it and/or modify it
@@ -25,7 +25,7 @@ along with this program; see the file COPYING3.  If not see
 
 #include "cpplib.h"
 
-/* This is the data structure used by all the functions in mkdeps.c.
+/* This is the data structure used by all the functions in mkdeps.cc.
    It's quite straightforward, but should be treated as opaque.  */
 
 class mkdeps;
diff --git a/libcpp/include/symtab.h b/libcpp/include/symtab.h
index 6905753..53efe6c 100644
--- a/libcpp/include/symtab.h
+++ b/libcpp/include/symtab.h
@@ -1,5 +1,5 @@
 /* Hash tables.
-   Copyright (C) 2000-2021 Free Software Foundation, Inc.
+   Copyright (C) 2000-2022 Free Software Foundation, Inc.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
diff --git a/libcpp/init.c b/libcpp/init.cc
index 5a424e2..f4ab83d 100644
--- a/libcpp/init.c
+++ b/libcpp/init.cc
@@ -1,5 +1,5 @@
 /* CPP Library.
-   Copyright (C) 1986-2021 Free Software Foundation, Inc.
+   Copyright (C) 1986-2022 Free Software Foundation, Inc.
    Contributed by Per Bothner, 1994-95.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
@@ -82,7 +82,6 @@ struct lang_flags
   char extended_numbers;
   char extended_identifiers;
   char c11_identifiers;
-  char cxx23_identifiers;
   char std;
   char digraphs;
   char uliterals;
@@ -100,31 +99,31 @@ struct lang_flags
 };
 
 static const struct lang_flags lang_defaults[] =
-{ /*              c99 c++ xnum xid c11 c++23 std digr ulit rlit udlit bincst digsep trig u8chlit vaopt scope dfp szlit elifdef */
-  /* GNUC89   */  { 0,  0,  1,  0,  0,  0,    0,  1,   0,   0,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
-  /* GNUC99   */  { 1,  0,  1,  1,  0,  0,    0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
-  /* GNUC11   */  { 1,  0,  1,  1,  1,  0,    0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
-  /* GNUC17   */  { 1,  0,  1,  1,  1,  0,    0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
-  /* GNUC2X   */  { 1,  0,  1,  1,  1,  0,    0,  1,   1,   1,   0,    1,     1,     0,   1,      1,   1,     1,   0,   1 },
-  /* STDC89   */  { 0,  0,  0,  0,  0,  0,    1,  0,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
-  /* STDC94   */  { 0,  0,  0,  0,  0,  0,    1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
-  /* STDC99   */  { 1,  0,  1,  1,  0,  0,    1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
-  /* STDC11   */  { 1,  0,  1,  1,  1,  0,    1,  1,   1,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
-  /* STDC17   */  { 1,  0,  1,  1,  1,  0,    1,  1,   1,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
-  /* STDC2X   */  { 1,  0,  1,  1,  1,  0,    1,  1,   1,   0,   0,    1,     1,     1,   1,      0,   1,     1,   0,   1 },
-  /* GNUCXX   */  { 0,  1,  1,  1,  0,  0,    0,  1,   0,   0,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
-  /* CXX98    */  { 0,  1,  0,  1,  0,  0,    1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   1,     0,   0,   0 },
-  /* GNUCXX11 */  { 1,  1,  1,  1,  1,  0,    0,  1,   1,   1,   1,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
-  /* CXX11    */  { 1,  1,  0,  1,  1,  0,    1,  1,   1,   1,   1,    0,     0,     1,   0,      0,   1,     0,   0,   0 },
-  /* GNUCXX14 */  { 1,  1,  1,  1,  1,  0,    0,  1,   1,   1,   1,    1,     1,     0,   0,      1,   1,     0,   0,   0 },
-  /* CXX14    */  { 1,  1,  0,  1,  1,  0,    1,  1,   1,   1,   1,    1,     1,     1,   0,      0,   1,     0,   0,   0 },
-  /* GNUCXX17 */  { 1,  1,  1,  1,  1,  0,    0,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   0,   0 },
-  /* CXX17    */  { 1,  1,  1,  1,  1,  0,    1,  1,   1,   1,   1,    1,     1,     0,   1,      0,   1,     0,   0,   0 },
-  /* GNUCXX20 */  { 1,  1,  1,  1,  1,  0,    0,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   0,   0 },
-  /* CXX20    */  { 1,  1,  1,  1,  1,  0,    1,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   0,   0 },
-  /* GNUCXX23 */  { 1,  1,  1,  1,  1,  1,    0,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   1,   1 },
-  /* CXX23    */  { 1,  1,  1,  1,  1,  1,    1,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   1,   1 },
-  /* ASM      */  { 0,  0,  1,  0,  0,  0,    0,  0,   0,   0,   0,    0,     0,     0,   0,      0,   0,     0,   0,   0 }
+{ /*              c99 c++ xnum xid c11 std digr ulit rlit udlit bincst digsep trig u8chlit vaopt scope dfp szlit elifdef */
+  /* GNUC89   */  { 0,  0,  1,  0,  0,  0,  1,   0,   0,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
+  /* GNUC99   */  { 1,  0,  1,  1,  0,  0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
+  /* GNUC11   */  { 1,  0,  1,  1,  1,  0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
+  /* GNUC17   */  { 1,  0,  1,  1,  1,  0,  1,   1,   1,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
+  /* GNUC2X   */  { 1,  0,  1,  1,  1,  0,  1,   1,   1,   0,    1,     1,     0,   1,      1,   1,     1,   0,   1 },
+  /* STDC89   */  { 0,  0,  0,  0,  0,  1,  0,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
+  /* STDC94   */  { 0,  0,  0,  0,  0,  1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
+  /* STDC99   */  { 1,  0,  1,  1,  0,  1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
+  /* STDC11   */  { 1,  0,  1,  1,  1,  1,  1,   1,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
+  /* STDC17   */  { 1,  0,  1,  1,  1,  1,  1,   1,   0,   0,    0,     0,     1,   0,      0,   0,     0,   0,   0 },
+  /* STDC2X   */  { 1,  0,  1,  1,  1,  1,  1,   1,   0,   0,    1,     1,     1,   1,      0,   1,     1,   0,   1 },
+  /* GNUCXX   */  { 0,  1,  1,  1,  0,  0,  1,   0,   0,   0,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
+  /* CXX98    */  { 0,  1,  0,  1,  0,  1,  1,   0,   0,   0,    0,     0,     1,   0,      0,   1,     0,   0,   0 },
+  /* GNUCXX11 */  { 1,  1,  1,  1,  1,  0,  1,   1,   1,   1,    0,     0,     0,   0,      1,   1,     0,   0,   0 },
+  /* CXX11    */  { 1,  1,  0,  1,  1,  1,  1,   1,   1,   1,    0,     0,     1,   0,      0,   1,     0,   0,   0 },
+  /* GNUCXX14 */  { 1,  1,  1,  1,  1,  0,  1,   1,   1,   1,    1,     1,     0,   0,      1,   1,     0,   0,   0 },
+  /* CXX14    */  { 1,  1,  0,  1,  1,  1,  1,   1,   1,   1,    1,     1,     1,   0,      0,   1,     0,   0,   0 },
+  /* GNUCXX17 */  { 1,  1,  1,  1,  1,  0,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   0,   0 },
+  /* CXX17    */  { 1,  1,  1,  1,  1,  1,  1,   1,   1,   1,    1,     1,     0,   1,      0,   1,     0,   0,   0 },
+  /* GNUCXX20 */  { 1,  1,  1,  1,  1,  0,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   0,   0 },
+  /* CXX20    */  { 1,  1,  1,  1,  1,  1,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   0,   0 },
+  /* GNUCXX23 */  { 1,  1,  1,  1,  1,  0,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   1,   1 },
+  /* CXX23    */  { 1,  1,  1,  1,  1,  1,  1,   1,   1,   1,    1,     1,     0,   1,      1,   1,     0,   1,   1 },
+  /* ASM      */  { 0,  0,  1,  0,  0,  0,  0,   0,   0,   0,    0,     0,     0,   0,      0,   0,     0,   0,   0 }
 };
 
 /* Sets internal flags correctly for a given language.  */
@@ -140,7 +139,6 @@ cpp_set_lang (cpp_reader *pfile, enum c_lang lang)
   CPP_OPTION (pfile, extended_numbers)		 = l->extended_numbers;
   CPP_OPTION (pfile, extended_identifiers)	 = l->extended_identifiers;
   CPP_OPTION (pfile, c11_identifiers)		 = l->c11_identifiers;
-  CPP_OPTION (pfile, cxx23_identifiers)		 = l->cxx23_identifiers;
   CPP_OPTION (pfile, std)			 = l->std;
   CPP_OPTION (pfile, digraphs)			 = l->digraphs;
   CPP_OPTION (pfile, uliterals)			 = l->uliterals;
@@ -223,6 +221,7 @@ cpp_create_reader (enum c_lang lang, cpp_hash_table *table,
       = ENABLE_CANONICAL_SYSTEM_HEADERS;
   CPP_OPTION (pfile, ext_numeric_literals) = 1;
   CPP_OPTION (pfile, warn_date_time) = 0;
+  CPP_OPTION (pfile, cpp_warn_bidirectional) = bidirectional_unpaired;
 
   /* Default CPP arithmetic to something sensible for the host for the
      benefit of dumb users like fix-header.  */
@@ -383,7 +382,7 @@ cpp_destroy (cpp_reader *pfile)
 
    There are two tables of these.  builtin_array holds all the
    "builtin" macros: these are handled by builtin_macro() in
-   macro.c.  Builtin is somewhat of a misnomer -- the property of
+   macro.cc.  Builtin is somewhat of a misnomer -- the property of
    interest is that these macros require special code to compute their
    expansions.  The value is a "cpp_builtin_type" enumerator.
 
@@ -413,7 +412,7 @@ static const struct builtin_macro builtin_array[] =
   B("__INCLUDE_LEVEL__", BT_INCLUDE_LEVEL, true),
   B("__COUNTER__",	 BT_COUNTER,       true),
   /* Make sure to update the list of built-in
-     function-like macros in traditional.c:
+     function-like macros in traditional.cc:
      fun_like_macro() when adding more following */
   B("__has_attribute",	 BT_HAS_ATTRIBUTE, true),
   B("__has_c_attribute", BT_HAS_STD_ATTRIBUTE, true),
@@ -849,7 +848,7 @@ cpp_finish (cpp_reader *pfile, FILE *deps_stream)
   if (CPP_OPTION (pfile, warn_unused_macros))
     cpp_forall_identifiers (pfile, _cpp_warn_if_unused_macro, NULL);
 
-  /* lex.c leaves the final buffer on the stack.  This it so that
+  /* lex.cc leaves the final buffer on the stack.  This it so that
      it returns an unending stream of CPP_EOFs to the client.  If we
      popped the buffer, we'd dereference a NULL buffer pointer and
      segfault.  It's nice to allow the client to do worry-free excess
diff --git a/libcpp/internal.h b/libcpp/internal.h
index fd44de6..badfd1b 100644
--- a/libcpp/internal.h
+++ b/libcpp/internal.h
@@ -1,5 +1,5 @@
 /* Part of CPP library.
-   Copyright (C) 1997-2021 Free Software Foundation, Inc.
+   Copyright (C) 1997-2022 Free Software Foundation, Inc.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
@@ -287,6 +287,9 @@ struct lexer_state
 
   /* Nonzero if the deferred pragma being handled allows macro expansion.  */
   unsigned char pragma_allow_expansion;
+
+  /* Nonzero if _Pragma should not be interpreted.  */
+  unsigned char ignore__Pragma;
 };
 
 /* Special nodes - identifiers with predefined significance.  */
@@ -531,15 +534,15 @@ struct cpp_reader
   cpp_token avoid_paste;
   cpp_token endarg;
 
-  /* Opaque handle to the dependencies of mkdeps.c.  */
+  /* Opaque handle to the dependencies of mkdeps.cc.  */
   class mkdeps *deps;
 
   /* Obstack holding all macro hash nodes.  This never shrinks.
-     See identifiers.c */
+     See identifiers.cc */
   struct obstack hash_ob;
 
   /* Obstack holding buffer and conditional structures.  This is a
-     real stack.  See directives.c.  */
+     real stack.  See directives.cc.  */
   struct obstack buffer_ob;
 
   /* Pragma table - dynamic, because a library user can add to the
@@ -574,7 +577,7 @@ struct cpp_reader
     location_t first_line;
   } out;
 
-  /* Used for buffer overlays by traditional.c.  */
+  /* Used for buffer overlays by traditional.cc.  */
   const unsigned char *saved_cur, *saved_rlimit, *saved_line_base;
 
   /* A saved list of the defined macros, for dependency checking
@@ -597,6 +600,14 @@ struct cpp_reader
   /* Location identifying the main source file -- intended to be line
      zero of said file.  */
   location_t main_loc;
+
+  /* Returns true iff we should warn about UTF-8 bidirectional control
+     characters.  */
+  bool warn_bidi_p () const
+  {
+    return (CPP_OPTION (this, cpp_warn_bidirectional)
+	    & (bidirectional_unpaired|bidirectional_any));
+  }
 };
 
 /* Character classes.  Based on the more primitive macros in safe-ctype.h.
@@ -604,7 +615,7 @@ struct cpp_reader
    definition of a pp-number in the C standard [section 6.4.8 of C99].
 
    In the unlikely event that characters other than \r and \n enter
-   the set is_vspace, the macro handle_newline() in lex.c must be
+   the set is_vspace, the macro handle_newline() in lex.cc must be
    updated.  */
 #define _dollar_ok(x)	((x) == '$' && CPP_OPTION (pfile, dollars_in_ident))
 
@@ -663,7 +674,7 @@ inline bool _cpp_defined_macro_p (cpp_hashnode *node)
   return cpp_macro_p (node) && !(node->flags & NODE_CONDITIONAL);
 }
 
-/* In macro.c */
+/* In macro.cc */
 extern bool _cpp_notify_macro_use (cpp_reader *pfile, cpp_hashnode *node,
 				   location_t);
 inline bool _cpp_maybe_notify_macro_use (cpp_reader *pfile, cpp_hashnode *node,
@@ -692,11 +703,11 @@ extern void _cpp_push_token_context (cpp_reader *, cpp_hashnode *,
 				     const cpp_token *, unsigned int);
 extern void _cpp_backup_tokens_direct (cpp_reader *, unsigned int);
 
-/* In identifiers.c */
+/* In identifiers.cc */
 extern void _cpp_init_hashtable (cpp_reader *, cpp_hash_table *);
 extern void _cpp_destroy_hashtable (cpp_reader *);
 
-/* In files.c */
+/* In files.cc */
 enum _cpp_find_file_kind
   { _cpp_FFK_NORMAL, _cpp_FFK_FAKE, _cpp_FFK_PRE_INCLUDE, _cpp_FFK_HAS_INCLUDE };
 extern _cpp_file *_cpp_find_file (cpp_reader *, const char *, cpp_dir *,
@@ -722,11 +733,11 @@ extern struct stat *_cpp_get_file_stat (_cpp_file *);
 extern bool _cpp_has_header (cpp_reader *, const char *, int,
 			     enum include_type);
 
-/* In expr.c */
+/* In expr.cc */
 extern bool _cpp_parse_expr (cpp_reader *, bool);
 extern struct op *_cpp_expand_op_stack (cpp_reader *);
 
-/* In lex.c */
+/* In lex.cc */
 extern void _cpp_process_line_notes (cpp_reader *, int);
 extern void _cpp_clean_line (cpp_reader *);
 extern bool _cpp_get_fresh_line (cpp_reader *);
@@ -749,13 +760,13 @@ static inline void *_cpp_reserve_room (cpp_reader *pfile, size_t have,
 }
 extern void *_cpp_commit_buff (cpp_reader *pfile, size_t size);
 
-/* In init.c.  */
+/* In init.cc.  */
 extern void _cpp_maybe_push_include_file (cpp_reader *);
 extern const char *cpp_named_operator2name (enum cpp_ttype type);
 extern void _cpp_restore_special_builtin (cpp_reader *pfile,
 					  struct def_pragma_macro *);
 
-/* In directives.c */
+/* In directives.cc */
 extern int _cpp_test_assertion (cpp_reader *, unsigned int *);
 extern int _cpp_handle_directive (cpp_reader *, bool);
 extern void _cpp_define_builtin (cpp_reader *, const char *);
@@ -769,7 +780,10 @@ extern void _cpp_do_file_change (cpp_reader *, enum lc_reason, const char *,
 extern void _cpp_pop_buffer (cpp_reader *);
 extern char *_cpp_bracket_include (cpp_reader *);
 
-/* In traditional.c.  */
+/* In errors.cc  */
+extern location_t cpp_diagnostic_get_current_location (cpp_reader *);
+
+/* In traditional.cc.  */
 extern bool _cpp_scan_out_logical_line (cpp_reader *, cpp_macro *, bool);
 extern bool _cpp_read_logical_line_trad (cpp_reader *);
 extern void _cpp_overlay_buffer (cpp_reader *pfile, const unsigned char *,
@@ -782,7 +796,7 @@ extern unsigned char *_cpp_copy_replacement_text (const cpp_macro *,
 						  unsigned char *);
 extern size_t _cpp_replacement_text_len (const cpp_macro *);
 
-/* In charset.c.  */
+/* In charset.cc.  */
 
 /* The normalization state at this point in the sequence.
    It starts initialized to all zeros, and at the end
@@ -887,7 +901,7 @@ ufputs (const unsigned char *s, FILE *f)
   return fputs ((const char *)s, f);
 }
 
-/* In line-map.c.  */
+/* In line-map.cc.  */
 
 /* Create and return a virtual location for a token that is part of a
    macro expansion-list at a macro expansion point.  See the comment
@@ -935,6 +949,26 @@ int linemap_get_expansion_line (class line_maps *,
 const char* linemap_get_expansion_filename (class line_maps *,
 					    location_t);
 
+/* A subclass of rich_location for emitting a diagnostic
+   at the current location of the reader, but flagging
+   it with set_escape_on_output (true).  */
+class encoding_rich_location : public rich_location
+{
+ public:
+  encoding_rich_location (cpp_reader *pfile)
+  : rich_location (pfile->line_table,
+		   cpp_diagnostic_get_current_location (pfile))
+  {
+    set_escape_on_output (true);
+  }
+
+  encoding_rich_location (cpp_reader *pfile, location_t loc)
+  : rich_location (pfile->line_table, loc)
+  {
+    set_escape_on_output (true);
+  }
+};
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/libcpp/lex.c b/libcpp/lex.cc
index 8e3ef09..fb1dfab 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.cc
@@ -1,5 +1,5 @@
 /* CPP Library - lexical analysis.
-   Copyright (C) 2000-2021 Free Software Foundation, Inc.
+   Copyright (C) 2000-2022 Free Software Foundation, Inc.
    Contributed by Per Bothner, 1994-95.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
@@ -1164,6 +1164,479 @@ _cpp_process_line_notes (cpp_reader *pfile, int in_comment)
     }
 }
 
+namespace bidi {
+  enum class kind {
+    NONE, LRE, RLE, LRO, RLO, LRI, RLI, FSI, PDF, PDI, LTR, RTL
+  };
+
+  /* All the UTF-8 encodings of bidi characters start with E2.  */
+  constexpr uchar utf8_start = 0xe2;
+
+  struct context
+  {
+    context () {}
+    context (location_t loc, kind k, bool pdf, bool ucn)
+    : m_loc (loc), m_kind (k), m_pdf (pdf), m_ucn (ucn)
+    {
+    }
+
+    kind get_pop_kind () const
+    {
+      return m_pdf ? kind::PDF : kind::PDI;
+    }
+    bool ucn_p () const
+    {
+      return m_ucn;
+    }
+
+    location_t m_loc;
+    kind m_kind;
+    unsigned m_pdf : 1;
+    unsigned m_ucn : 1;
+  };
+
+  /* A vector holding currently open bidi contexts.  We use a char for
+     each context, its LSB is 1 if it represents a PDF context, 0 if it
+     represents a PDI context.  The next bit is 1 if this context was open
+     by a bidi character written as a UCN, and 0 when it was UTF-8.  */
+  semi_embedded_vec <context, 16> vec;
+
+  /* Close the whole comment/identifier/string literal/character constant
+     context.  */
+  void on_close ()
+  {
+    vec.truncate (0);
+  }
+
+  /* Pop the last element in the vector.  */
+  void pop ()
+  {
+    unsigned int len = vec.count ();
+    gcc_checking_assert (len > 0);
+    vec.truncate (len - 1);
+  }
+
+  /* Return the pop kind of the context of the Ith element.  */
+  kind pop_kind_at (unsigned int i)
+  {
+    return vec[i].get_pop_kind ();
+  }
+
+  /* Return the pop kind of the context that is currently opened.  */
+  kind current_ctx ()
+  {
+    unsigned int len = vec.count ();
+    if (len == 0)
+      return kind::NONE;
+    return vec[len - 1].get_pop_kind ();
+  }
+
+  /* Return true if the current context comes from a UCN origin, that is,
+     the bidi char which started this bidi context was written as a UCN.  */
+  bool current_ctx_ucn_p ()
+  {
+    unsigned int len = vec.count ();
+    gcc_checking_assert (len > 0);
+    return vec[len - 1].m_ucn;
+  }
+
+  location_t current_ctx_loc ()
+  {
+    unsigned int len = vec.count ();
+    gcc_checking_assert (len > 0);
+    return vec[len - 1].m_loc;
+  }
+
+  /* We've read a bidi char, update the current vector as necessary.
+     LOC is only valid when K is not kind::NONE.  */
+  void on_char (kind k, bool ucn_p, location_t loc)
+  {
+    switch (k)
+      {
+      case kind::LRE:
+      case kind::RLE:
+      case kind::LRO:
+      case kind::RLO:
+	vec.push (context (loc, k, true, ucn_p));
+	break;
+      case kind::LRI:
+      case kind::RLI:
+      case kind::FSI:
+	vec.push (context (loc, k, false, ucn_p));
+	break;
+      /* PDF terminates the scope of the last LRE, RLE, LRO, or RLO
+	 whose scope has not yet been terminated.  */
+      case kind::PDF:
+	if (current_ctx () == kind::PDF)
+	  pop ();
+	break;
+      /* PDI terminates the scope of the last LRI, RLI, or FSI whose
+	 scope has not yet been terminated, as well as the scopes of
+	 any subsequent LREs, RLEs, LROs, or RLOs whose scopes have not
+	 yet been terminated.  */
+      case kind::PDI:
+	for (int i = vec.count () - 1; i >= 0; --i)
+	  if (pop_kind_at (i) == kind::PDI)
+	    {
+	      vec.truncate (i);
+	      break;
+	    }
+	break;
+      case kind::LTR:
+      case kind::RTL:
+	/* These aren't popped by a PDF/PDI.  */
+	break;
+      ATTR_LIKELY case kind::NONE:
+	break;
+      default:
+	abort ();
+      }
+  }
+
+  /* Return a descriptive string for K.  */
+  const char *to_str (kind k)
+  {
+    switch (k)
+      {
+      case kind::LRE:
+	return "U+202A (LEFT-TO-RIGHT EMBEDDING)";
+      case kind::RLE:
+	return "U+202B (RIGHT-TO-LEFT EMBEDDING)";
+      case kind::LRO:
+	return "U+202D (LEFT-TO-RIGHT OVERRIDE)";
+      case kind::RLO:
+	return "U+202E (RIGHT-TO-LEFT OVERRIDE)";
+      case kind::LRI:
+	return "U+2066 (LEFT-TO-RIGHT ISOLATE)";
+      case kind::RLI:
+	return "U+2067 (RIGHT-TO-LEFT ISOLATE)";
+      case kind::FSI:
+	return "U+2068 (FIRST STRONG ISOLATE)";
+      case kind::PDF:
+	return "U+202C (POP DIRECTIONAL FORMATTING)";
+      case kind::PDI:
+	return "U+2069 (POP DIRECTIONAL ISOLATE)";
+      case kind::LTR:
+	return "U+200E (LEFT-TO-RIGHT MARK)";
+      case kind::RTL:
+	return "U+200F (RIGHT-TO-LEFT MARK)";
+      default:
+	abort ();
+      }
+  }
+}
+
+/* Get location_t for the range of bytes [START, START + NUM_BYTES)
+   within the current line in FILE, with the caret at START.  */
+
+static location_t
+get_location_for_byte_range_in_cur_line (cpp_reader *pfile,
+					 const unsigned char *const start,
+					 size_t num_bytes)
+{
+  gcc_checking_assert (num_bytes > 0);
+
+  /* CPP_BUF_COLUMN and linemap_position_for_column both refer
+     to offsets in bytes, but CPP_BUF_COLUMN is 0-based,
+     whereas linemap_position_for_column is 1-based.  */
+
+  /* Get 0-based offsets within the line.  */
+  size_t start_offset = CPP_BUF_COLUMN (pfile->buffer, start);
+  size_t end_offset = start_offset + num_bytes - 1;
+
+  /* Now convert to location_t, where "columns" are 1-based byte offsets.  */
+  location_t start_loc = linemap_position_for_column (pfile->line_table,
+						      start_offset + 1);
+  location_t end_loc = linemap_position_for_column (pfile->line_table,
+						     end_offset + 1);
+
+  if (start_loc == end_loc)
+    return start_loc;
+
+  source_range src_range;
+  src_range.m_start = start_loc;
+  src_range.m_finish = end_loc;
+  location_t combined_loc = COMBINE_LOCATION_DATA (pfile->line_table,
+						   start_loc,
+						   src_range,
+						   NULL);
+  return combined_loc;
+}
+
+/* Parse a sequence of 3 bytes starting with P and return its bidi code.  */
+
+static bidi::kind
+get_bidi_utf8_1 (const unsigned char *const p)
+{
+  gcc_checking_assert (p[0] == bidi::utf8_start);
+
+  if (p[1] == 0x80)
+    switch (p[2])
+      {
+      case 0xaa:
+	return bidi::kind::LRE;
+      case 0xab:
+	return bidi::kind::RLE;
+      case 0xac:
+	return bidi::kind::PDF;
+      case 0xad:
+	return bidi::kind::LRO;
+      case 0xae:
+	return bidi::kind::RLO;
+      case 0x8e:
+	return bidi::kind::LTR;
+      case 0x8f:
+	return bidi::kind::RTL;
+      default:
+	break;
+      }
+  else if (p[1] == 0x81)
+    switch (p[2])
+      {
+      case 0xa6:
+	return bidi::kind::LRI;
+      case 0xa7:
+	return bidi::kind::RLI;
+      case 0xa8:
+	return bidi::kind::FSI;
+      case 0xa9:
+	return bidi::kind::PDI;
+      default:
+	break;
+      }
+
+  return bidi::kind::NONE;
+}
+
+/* Parse a sequence of 3 bytes starting with P and return its bidi code.
+   If the kind is not NONE, write the location to *OUT.*/
+
+static bidi::kind
+get_bidi_utf8 (cpp_reader *pfile, const unsigned char *const p, location_t *out)
+{
+  bidi::kind result = get_bidi_utf8_1 (p);
+  if (result != bidi::kind::NONE)
+    {
+      /* We have a sequence of 3 bytes starting at P.  */
+      *out = get_location_for_byte_range_in_cur_line (pfile, p, 3);
+    }
+  return result;
+}
+
+/* Parse a UCN where P points just past \u or \U and return its bidi code.  */
+
+static bidi::kind
+get_bidi_ucn_1 (const unsigned char *p, bool is_U)
+{
+  /* 6.4.3 Universal Character Names
+      \u hex-quad
+      \U hex-quad hex-quad
+     where \unnnn means \U0000nnnn.  */
+
+  if (is_U)
+    {
+      if (p[0] != '0' || p[1] != '0' || p[2] != '0' || p[3] != '0')
+	return bidi::kind::NONE;
+      /* Skip 4B so we can treat \u and \U the same below.  */
+      p += 4;
+    }
+
+  /* All code points we are looking for start with 20xx.  */
+  if (p[0] != '2' || p[1] != '0')
+    return bidi::kind::NONE;
+  else if (p[2] == '2')
+    switch (p[3])
+      {
+      case 'a':
+      case 'A':
+	return bidi::kind::LRE;
+      case 'b':
+      case 'B':
+	return bidi::kind::RLE;
+      case 'c':
+      case 'C':
+	return bidi::kind::PDF;
+      case 'd':
+      case 'D':
+	return bidi::kind::LRO;
+      case 'e':
+      case 'E':
+	return bidi::kind::RLO;
+      default:
+	break;
+      }
+  else if (p[2] == '6')
+    switch (p[3])
+      {
+      case '6':
+	return bidi::kind::LRI;
+      case '7':
+	return bidi::kind::RLI;
+      case '8':
+	return bidi::kind::FSI;
+      case '9':
+	return bidi::kind::PDI;
+      default:
+	break;
+      }
+  else if (p[2] == '0')
+    switch (p[3])
+      {
+      case 'e':
+      case 'E':
+	return bidi::kind::LTR;
+      case 'f':
+      case 'F':
+	return bidi::kind::RTL;
+      default:
+	break;
+      }
+
+  return bidi::kind::NONE;
+}
+
+/* Parse a UCN where P points just past \u or \U and return its bidi code.
+   If the kind is not NONE, write the location to *OUT.*/
+
+static bidi::kind
+get_bidi_ucn (cpp_reader *pfile,  const unsigned char *p, bool is_U,
+	      location_t *out)
+{
+  bidi::kind result = get_bidi_ucn_1 (p, is_U);
+  if (result != bidi::kind::NONE)
+    {
+      const unsigned char *start = p - 2;
+      size_t num_bytes = 2 + (is_U ? 8 : 4);
+      *out = get_location_for_byte_range_in_cur_line (pfile, start, num_bytes);
+    }
+  return result;
+}
+
+/* Subclass of rich_location for reporting on unpaired UTF-8
+   bidirectional control character(s).
+   Escape the source lines on output, and show all unclosed
+   bidi context, labelling everything.  */
+
+class unpaired_bidi_rich_location : public rich_location
+{
+ public:
+  class custom_range_label : public range_label
+  {
+   public:
+     label_text get_text (unsigned range_idx) const FINAL OVERRIDE
+     {
+       /* range 0 is the primary location; each subsequent range i + 1
+	  is for bidi::vec[i].  */
+       if (range_idx > 0)
+	 {
+	   const bidi::context &ctxt (bidi::vec[range_idx - 1]);
+	   return label_text::borrow (bidi::to_str (ctxt.m_kind));
+	 }
+       else
+	 return label_text::borrow (_("end of bidirectional context"));
+     }
+  };
+
+  unpaired_bidi_rich_location (cpp_reader *pfile, location_t loc)
+  : rich_location (pfile->line_table, loc, &m_custom_label)
+  {
+    set_escape_on_output (true);
+    for (unsigned i = 0; i < bidi::vec.count (); i++)
+      add_range (bidi::vec[i].m_loc,
+		 SHOW_RANGE_WITHOUT_CARET,
+		 &m_custom_label);
+  }
+
+ private:
+   custom_range_label m_custom_label;
+};
+
+/* We're closing a bidi context, that is, we've encountered a newline,
+   are closing a C-style comment, or are at the end of a string literal,
+   character constant, or identifier.  Warn if this context was not
+   properly terminated by a PDI or PDF.  P points to the last character
+   in this context.  */
+
+static void
+maybe_warn_bidi_on_close (cpp_reader *pfile, const uchar *p)
+{
+  const auto warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
+  if (bidi::vec.count () > 0
+      && (warn_bidi & bidirectional_unpaired
+	  && (!bidi::current_ctx_ucn_p ()
+	      || (warn_bidi & bidirectional_ucn))))
+    {
+      const location_t loc
+	= linemap_position_for_column (pfile->line_table,
+				       CPP_BUF_COLUMN (pfile->buffer, p));
+      unpaired_bidi_rich_location rich_loc (pfile, loc);
+      /* cpp_callbacks doesn't yet have a way to handle singular vs plural
+	 forms of a diagnostic, so fake it for now.  */
+      if (bidi::vec.count () > 1)
+	cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
+			"unpaired UTF-8 bidirectional control characters "
+			"detected");
+      else
+	cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
+			"unpaired UTF-8 bidirectional control character "
+			"detected");
+    }
+  /* We're done with this context.  */
+  bidi::on_close ();
+}
+
+/* We're at the beginning or in the middle of an identifier/comment/string
+   literal/character constant.  Warn if we've encountered a bidi character.
+   KIND says which bidi control character it was; UCN_P is true iff this bidi
+   control character was written as a UCN.  LOC is the location of the
+   character, but is only valid if KIND != bidi::kind::NONE.  */
+
+static void
+maybe_warn_bidi_on_char (cpp_reader *pfile, bidi::kind kind,
+			 bool ucn_p, location_t loc)
+{
+  if (__builtin_expect (kind == bidi::kind::NONE, 1))
+    return;
+
+  const auto warn_bidi = CPP_OPTION (pfile, cpp_warn_bidirectional);
+
+  if (warn_bidi & (bidirectional_unpaired|bidirectional_any))
+    {
+      rich_location rich_loc (pfile->line_table, loc);
+      rich_loc.set_escape_on_output (true);
+
+      /* It seems excessive to warn about a PDI/PDF that is closing
+	 an opened context because we've already warned about the
+	 opening character.  Except warn when we have a UCN x UTF-8
+	 mismatch, if UCN checking is enabled.  */
+      if (kind == bidi::current_ctx ())
+	{
+	  if (warn_bidi == (bidirectional_unpaired|bidirectional_ucn)
+	      && bidi::current_ctx_ucn_p () != ucn_p)
+	    {
+	      rich_loc.add_range (bidi::current_ctx_loc ());
+	      cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
+			      "UTF-8 vs UCN mismatch when closing "
+			      "a context by \"%s\"", bidi::to_str (kind));
+	    }
+	}
+      else if (warn_bidi & bidirectional_any
+	       && (!ucn_p || (warn_bidi & bidirectional_ucn)))
+	{
+	  if (kind == bidi::kind::PDF || kind == bidi::kind::PDI)
+	    cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
+			    "\"%s\" is closing an unopened context",
+			    bidi::to_str (kind));
+	  else
+	    cpp_warning_at (pfile, CPP_W_BIDIRECTIONAL, &rich_loc,
+			    "found problematic Unicode character \"%s\"",
+			    bidi::to_str (kind));
+	}
+    }
+  /* We're done with this context.  */
+  bidi::on_char (kind, ucn_p, loc);
+}
+
 /* Skip a C-style block comment.  We find the end of the comment by
    seeing if an asterisk is before every '/' we encounter.  Returns
    nonzero if comment terminated by EOF, zero otherwise.
@@ -1175,6 +1648,7 @@ _cpp_skip_block_comment (cpp_reader *pfile)
   cpp_buffer *buffer = pfile->buffer;
   const uchar *cur = buffer->cur;
   uchar c;
+  const bool warn_bidi_p = pfile->warn_bidi_p ();
 
   cur++;
   if (*cur == '/')
@@ -1189,7 +1663,11 @@ _cpp_skip_block_comment (cpp_reader *pfile)
       if (c == '/')
 	{
 	  if (cur[-2] == '*')
-	    break;
+	    {
+	      if (warn_bidi_p)
+		maybe_warn_bidi_on_close (pfile, cur);
+	      break;
+	    }
 
 	  /* Warn about potential nested comments, but not if the '/'
 	     comes immediately before the true comment delimiter.
@@ -1208,6 +1686,8 @@ _cpp_skip_block_comment (cpp_reader *pfile)
 	{
 	  unsigned int cols;
 	  buffer->cur = cur - 1;
+	  if (warn_bidi_p)
+	    maybe_warn_bidi_on_close (pfile, cur);
 	  _cpp_process_line_notes (pfile, true);
 	  if (buffer->next_line >= buffer->rlimit)
 	    return true;
@@ -1218,6 +1698,14 @@ _cpp_skip_block_comment (cpp_reader *pfile)
 
 	  cur = buffer->cur;
 	}
+      /* If this is a beginning of a UTF-8 encoding, it might be
+	 a bidirectional control character.  */
+      else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
+	{
+	  location_t loc;
+	  bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc);
+	  maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+	}
     }
 
   buffer->cur = cur;
@@ -1233,9 +1721,31 @@ skip_line_comment (cpp_reader *pfile)
 {
   cpp_buffer *buffer = pfile->buffer;
   location_t orig_line = pfile->line_table->highest_line;
+  const bool warn_bidi_p = pfile->warn_bidi_p ();
 
-  while (*buffer->cur != '\n')
-    buffer->cur++;
+  if (!warn_bidi_p)
+    while (*buffer->cur != '\n')
+      buffer->cur++;
+  else
+    {
+      while (*buffer->cur != '\n'
+	     && *buffer->cur != bidi::utf8_start)
+	buffer->cur++;
+      if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
+	{
+	  while (*buffer->cur != '\n')
+	    {
+	      if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0))
+		{
+		  location_t loc;
+		  bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
+		  maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+		}
+	      buffer->cur++;
+	    }
+	  maybe_warn_bidi_on_close (pfile, buffer->cur);
+	}
+    }
 
   _cpp_process_line_notes (pfile, true);
   return orig_line != pfile->line_table->highest_line;
@@ -1268,7 +1778,11 @@ skip_whitespace (cpp_reader *pfile, cppchar_t c)
   while (is_nvspace (c));
 
   if (saw_NUL)
-    cpp_error (pfile, CPP_DL_WARNING, "null character(s) ignored");
+    {
+      encoding_rich_location rich_loc (pfile);
+      cpp_error_at (pfile, CPP_DL_WARNING, &rich_loc,
+		    "null character(s) ignored");
+    }
 
   buffer->cur--;
 }
@@ -1297,6 +1811,28 @@ warn_about_normalization (cpp_reader *pfile,
   if (CPP_OPTION (pfile, warn_normalize) < NORMALIZE_STATE_RESULT (s)
       && !pfile->state.skipping)
     {
+      location_t loc = token->src_loc;
+
+      /* If possible, create a location range for the token.  */
+      if (loc >= RESERVED_LOCATION_COUNT
+	  && token->type != CPP_EOF
+	  /* There must be no line notes to process.  */
+	  && (!(pfile->buffer->cur
+		>= pfile->buffer->notes[pfile->buffer->cur_note].pos
+		&& !pfile->overlaid_buffer)))
+	{
+	  source_range tok_range;
+	  tok_range.m_start = loc;
+	  tok_range.m_finish
+	    = linemap_position_for_column (pfile->line_table,
+					   CPP_BUF_COLUMN (pfile->buffer,
+							   pfile->buffer->cur));
+	  loc = COMBINE_LOCATION_DATA (pfile->line_table,
+				       loc, tok_range, NULL);
+	}
+
+      encoding_rich_location rich_loc (pfile, loc);
+
       /* Make sure that the token is printed using UCNs, even
 	 if we'd otherwise happily print UTF-8.  */
       unsigned char *buf = XNEWVEC (unsigned char, cpp_token_len (token));
@@ -1304,14 +1840,14 @@ warn_about_normalization (cpp_reader *pfile,
 
       sz = cpp_spell_token (pfile, token, buf, false) - buf;
       if (NORMALIZE_STATE_RESULT (s) == normalized_C)
-	cpp_warning_with_line (pfile, CPP_W_NORMALIZE, token->src_loc, 0,
-			       "`%.*s' is not in NFKC", (int) sz, buf);
-      else if (CPP_OPTION (pfile, cxx23_identifiers))
-	cpp_pedwarning_with_line (pfile, CPP_W_NORMALIZE, token->src_loc, 0,
+	cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
+			"`%.*s' is not in NFKC", (int) sz, buf);
+      else if (CPP_OPTION (pfile, cplusplus))
+	cpp_pedwarning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
 				  "`%.*s' is not in NFC", (int) sz, buf);
       else
-	cpp_warning_with_line (pfile, CPP_W_NORMALIZE, token->src_loc, 0,
-			       "`%.*s' is not in NFC", (int) sz, buf);
+	cpp_warning_at (pfile, CPP_W_NORMALIZE, &rich_loc,
+			"`%.*s' is not in NFC", (int) sz, buf);
       free (buf);
     }
 }
@@ -1320,11 +1856,13 @@ static const cppchar_t utf8_signifier = 0xC0;
 
 /* Returns TRUE if the sequence starting at buffer->cur is valid in
    an identifier.  FIRST is TRUE if this starts an identifier.  */
+
 static bool
 forms_identifier_p (cpp_reader *pfile, int first,
 		    struct normalize_state *state)
 {
   cpp_buffer *buffer = pfile->buffer;
+  const bool warn_bidi_p = pfile->warn_bidi_p ();
 
   if (*buffer->cur == '$')
     {
@@ -1347,6 +1885,13 @@ forms_identifier_p (cpp_reader *pfile, int first,
       cppchar_t s;
       if (*buffer->cur >= utf8_signifier)
 	{
+	  if (__builtin_expect (*buffer->cur == bidi::utf8_start, 0)
+	      && warn_bidi_p)
+	    {
+	      location_t loc;
+	      bidi::kind kind = get_bidi_utf8 (pfile, buffer->cur, &loc);
+	      maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+	    }
 	  if (_cpp_valid_utf8 (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
 			       state, &s))
 	    return true;
@@ -1355,6 +1900,15 @@ forms_identifier_p (cpp_reader *pfile, int first,
 	       && (buffer->cur[1] == 'u' || buffer->cur[1] == 'U'))
 	{
 	  buffer->cur += 2;
+	  if (warn_bidi_p)
+	    {
+	      location_t loc;
+	      bidi::kind kind = get_bidi_ucn (pfile,
+					      buffer->cur,
+					      buffer->cur[-1] == 'U',
+					      &loc);
+	      maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
+	    }
 	  if (_cpp_valid_ucn (pfile, &buffer->cur, buffer->rlimit, 1 + !first,
 			      state, &s, NULL, NULL))
 	    return true;
@@ -1463,6 +2017,7 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
   const uchar *cur;
   unsigned int len;
   unsigned int hash = HT_HASHSTEP (0, *base);
+  const bool warn_bidi_p = pfile->warn_bidi_p ();
 
   cur = pfile->buffer->cur;
   if (! starts_ucn)
@@ -1486,6 +2041,8 @@ lex_identifier (cpp_reader *pfile, const uchar *base, bool starts_ucn,
 	    pfile->buffer->cur++;
 	  }
       } while (forms_identifier_p (pfile, false, nst));
+      if (warn_bidi_p)
+	maybe_warn_bidi_on_close (pfile, pfile->buffer->cur);
       result = _cpp_interpret_identifier (pfile, base,
 					  pfile->buffer->cur - base);
       *spelling = cpp_lookup (pfile, base, pfile->buffer->cur - base);
@@ -1732,6 +2289,7 @@ static void
 lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
 {
   const uchar *pos = base;
+  const bool warn_bidi_p = pfile->warn_bidi_p ();
 
   /* 'tis a pity this information isn't passed down from the lexer's
      initial categorization of the token.  */
@@ -1968,8 +2526,18 @@ lex_raw_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
 	  pos = base = pfile->buffer->cur;
 	  note = &pfile->buffer->notes[pfile->buffer->cur_note];
 	}
+      else if (__builtin_expect ((unsigned char) c == bidi::utf8_start, 0)
+	       && warn_bidi_p)
+	{
+	  location_t loc;
+	  bidi::kind kind = get_bidi_utf8 (pfile, pos - 1, &loc);
+	  maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+	}
     }
 
+  if (warn_bidi_p)
+    maybe_warn_bidi_on_close (pfile, pos);
+
   if (CPP_OPTION (pfile, user_literals))
     {
       /* If a string format macro, say from inttypes.h, is placed touching
@@ -2064,15 +2632,29 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
   else
     terminator = '>', type = CPP_HEADER_NAME;
 
+  const bool warn_bidi_p = pfile->warn_bidi_p ();
   for (;;)
     {
       cppchar_t c = *cur++;
 
       /* In #include-style directives, terminators are not escapable.  */
       if (c == '\\' && !pfile->state.angled_headers && *cur != '\n')
-	cur++;
+	{
+	  if ((cur[0] == 'u' || cur[0] == 'U') && warn_bidi_p)
+	    {
+	      location_t loc;
+	      bidi::kind kind = get_bidi_ucn (pfile, cur + 1, cur[0] == 'U',
+					      &loc);
+	      maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/true, loc);
+	    }
+	  cur++;
+	}
       else if (c == terminator)
-	break;
+	{
+	  if (warn_bidi_p)
+	    maybe_warn_bidi_on_close (pfile, cur - 1);
+	  break;
+	}
       else if (c == '\n')
 	{
 	  cur--;
@@ -2089,6 +2671,12 @@ lex_string (cpp_reader *pfile, cpp_token *token, const uchar *base)
 	}
       else if (c == '\0')
 	saw_NUL = true;
+      else if (__builtin_expect (c == bidi::utf8_start, 0) && warn_bidi_p)
+	{
+	  location_t loc;
+	  bidi::kind kind = get_bidi_utf8 (pfile, cur - 1, &loc);
+	  maybe_warn_bidi_on_char (pfile, kind, /*ucn_p=*/false, loc);
+	}
     }
 
   if (saw_NUL && !pfile->state.skipping)
@@ -2946,7 +3534,21 @@ _cpp_lex_direct (cpp_reader *pfile)
   buffer = pfile->buffer;
   if (buffer->need_line)
     {
-      gcc_assert (!pfile->state.in_deferred_pragma);
+      if (pfile->state.in_deferred_pragma)
+	{
+	  /* This can happen in cases like:
+	     #define loop(x) whatever
+	     #pragma omp loop
+	     where when trying to expand loop we need to peek
+	     next token after loop, but aren't still in_deferred_pragma
+	     mode but are in in_directive mode, so buffer->need_line
+	     is set, a CPP_EOF is peeked.  */
+	  result->type = CPP_PRAGMA_EOL;
+	  pfile->state.in_deferred_pragma = false;
+	  if (!pfile->state.pragma_allow_expansion)
+	    pfile->state.prevent_expansion--;
+	  return result;
+	}
       if (!_cpp_get_fresh_line (pfile))
 	{
 	  result->type = CPP_EOF;
@@ -4467,7 +5069,7 @@ cpp_directive_only_process (cpp_reader *pfile,
 			break;
 
 		      case '*':
-			if (pos > peek && !esc)
+			if (pos > peek)
 			  star = is_block;
 			esc = false;
 			break;
diff --git a/libcpp/line-map.c b/libcpp/line-map.cc
index 1a6902a..62077c3 100644
--- a/libcpp/line-map.c
+++ b/libcpp/line-map.cc
@@ -1,5 +1,5 @@
 /* Map (unsigned int) keys to (source file, line, column) triples.
-   Copyright (C) 2001-2021 Free Software Foundation, Inc.
+   Copyright (C) 2001-2022 Free Software Foundation, Inc.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
@@ -44,7 +44,7 @@ static location_t linemap_macro_loc_to_exp_point (line_maps *,
 						  location_t,
 						  const line_map_ordinary **);
 
-/* Counters defined in macro.c.  */
+/* Counters defined in macro.cc.  */
 extern unsigned num_expanded_macros_counter;
 extern unsigned num_macro_tokens_counter;
 
@@ -374,7 +374,7 @@ linemap_check_files_exited (line_maps *set)
   for (const line_map_ordinary *map = LINEMAPS_LAST_ORDINARY_MAP (set);
        ! MAIN_FILE_P (map);
        map = linemap_included_from_linemap (set, map))
-    fprintf (stderr, "line-map.c: file \"%s\" entered but not left\n",
+    fprintf (stderr, "line-map.cc: file \"%s\" entered but not left\n",
 	     ORDINARY_MAP_FILE_NAME (map));
 }
 
@@ -410,7 +410,7 @@ line_map_new_raw (line_maps *set, bool macro_p, unsigned num)
 
       /* We are going to execute some dance to try to reduce the
 	 overhead of the memory allocator, in case we are using the
-	 ggc-page.c one.
+	 ggc-page.cc one.
 	 
 	 The actual size of memory we are going to get back from the
 	 allocator may well be larger than what we ask for.  Use this
@@ -2083,9 +2083,10 @@ rich_location::rich_location (line_maps *set, location_t loc,
   m_ranges (),
   m_column_override (0),
   m_have_expanded_location (false),
-  m_fixit_hints (),
   m_seen_impossible_fixit (false),
   m_fixits_cannot_be_auto_applied (false),
+  m_escape_on_output (false),
+  m_fixit_hints (),
   m_path (NULL)
 {
   add_range (loc, SHOW_RANGE_WITH_CARET, label);
diff --git a/libcpp/macro.c b/libcpp/macro.cc
index f214548..8ebf360 100644
--- a/libcpp/macro.c
+++ b/libcpp/macro.cc
@@ -1,5 +1,5 @@
 /* Part of CPP library.  (Macro and #define handling.)
-   Copyright (C) 1986-2021 Free Software Foundation, Inc.
+   Copyright (C) 1986-2022 Free Software Foundation, Inc.
    Written by Per Bothner, 1994.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
@@ -295,7 +295,7 @@ static cpp_context *next_context (cpp_reader *);
 static const cpp_token *padding_token (cpp_reader *, const cpp_token *);
 static const cpp_token *new_string_token (cpp_reader *, uchar *, unsigned int);
 static const cpp_token *stringify_arg (cpp_reader *, const cpp_token **,
-				       unsigned int, bool);
+				       unsigned int);
 static void paste_all_tokens (cpp_reader *, const cpp_token *);
 static bool paste_tokens (cpp_reader *, location_t,
 			  const cpp_token **, const cpp_token *);
@@ -750,8 +750,10 @@ builtin_macro (cpp_reader *pfile, cpp_hashnode *node,
   if (node->value.builtin == BT_PRAGMA)
     {
       /* Don't interpret _Pragma within directives.  The standard is
-         not clear on this, but to me this makes most sense.  */
-      if (pfile->state.in_directive)
+         not clear on this, but to me this makes most sense.
+         Similarly, don't interpret _Pragma inside expand_args, we might
+         need to stringize it later on.  */
+      if (pfile->state.in_directive || pfile->state.ignore__Pragma)
 	return 0;
 
       return _cpp_do__Pragma (pfile, loc);
@@ -832,8 +834,7 @@ cpp_quote_string (uchar *dest, const uchar *src, unsigned int len)
 /* Convert a token sequence FIRST to FIRST+COUNT-1 to a single string token
    according to the rules of the ISO C #-operator.  */
 static const cpp_token *
-stringify_arg (cpp_reader *pfile, const cpp_token **first, unsigned int count,
-	       bool va_opt)
+stringify_arg (cpp_reader *pfile, const cpp_token **first, unsigned int count)
 {
   unsigned char *dest;
   unsigned int i, escape_it, backslash_count = 0;
@@ -850,24 +851,6 @@ stringify_arg (cpp_reader *pfile, const cpp_token **first, unsigned int count,
     {
       const cpp_token *token = first[i];
 
-      if (va_opt && (token->flags & PASTE_LEFT))
-	{
-	  location_t virt_loc = pfile->invocation_location;
-	  const cpp_token *rhs;
-	  do
-	    {
-	      if (i == count)
-		abort ();
-	      rhs = first[++i];
-	      if (!paste_tokens (pfile, virt_loc, &token, rhs))
-		{
-		  --i;
-		  break;
-		}
-	    }
-	  while (rhs->flags & PASTE_LEFT);
-	}
-
       if (token->type == CPP_PADDING)
 	{
 	  if (source == NULL
@@ -1001,6 +984,7 @@ paste_tokens (cpp_reader *pfile, location_t location,
       return false;
     }
 
+  lhs->flags |= (*plhs)->flags & (PREV_WHITE | PREV_FALLTHROUGH);
   *plhs = lhs;
   _cpp_pop_buffer (pfile);
   return true;
@@ -1259,7 +1243,7 @@ collect_args (cpp_reader *pfile, const cpp_hashnode *node,
 	  else if (token->type == CPP_EOF
 		   || (token->type == CPP_HASH && token->flags & BOL))
 	    break;
-	  else if (token->type == CPP_PRAGMA)
+	  else if (token->type == CPP_PRAGMA && !(token->flags & PRAGMA_OP))
 	    {
 	      cpp_token *newtok = _cpp_temp_token (pfile);
 
@@ -1389,8 +1373,11 @@ funlike_invocation_p (cpp_reader *pfile, cpp_hashnode *node,
       token = cpp_get_token (pfile);
       if (token->type != CPP_PADDING)
 	break;
+      gcc_assert ((token->flags & PREV_WHITE) == 0);
       if (padding == NULL
-	  || (!(padding->flags & PREV_WHITE) && token->val.source == NULL))
+	  || padding->val.source == NULL
+	  || (!(padding->val.source->flags & PREV_WHITE)
+	      && token->val.source == NULL))
 	padding = token;
     }
 
@@ -1943,8 +1930,7 @@ replace_args (cpp_reader *pfile, cpp_hashnode *node, cpp_macro *macro,
 	if (src->flags & STRINGIFY_ARG)
 	  {
 	    if (!arg->stringified)
-	      arg->stringified = stringify_arg (pfile, arg->first, arg->count,
-						false);
+	      arg->stringified = stringify_arg (pfile, arg->first, arg->count);
 	  }
 	else if ((src->flags & PASTE_LEFT)
 		 || (src != macro->exp.tokens && (src[-1].flags & PASTE_LEFT)))
@@ -2064,11 +2050,46 @@ replace_args (cpp_reader *pfile, cpp_hashnode *node, cpp_macro *macro,
 		{
 		  unsigned int count
 		    = start ? paste_flag - start : tokens_buff_count (buff);
-		  const cpp_token *t
-		    = stringify_arg (pfile,
-				     start ? start + 1
-				     : (const cpp_token **) (buff->base),
-				     count, true);
+		  const cpp_token **first
+		    = start ? start + 1
+			    : (const cpp_token **) (buff->base);
+		  unsigned int i, j;
+
+		  /* Paste any tokens that need to be pasted before calling
+		     stringify_arg, because stringify_arg uses pfile->u_buff
+		     which paste_tokens can use as well.  */
+		  for (i = 0, j = 0; i < count; i++, j++)
+		    {
+		      const cpp_token *token = first[i];
+
+		      if (token->flags & PASTE_LEFT)
+			{
+			  location_t virt_loc = pfile->invocation_location;
+			  const cpp_token *rhs;
+			  do
+			    {
+			      if (i == count)
+				abort ();
+			      rhs = first[++i];
+			      if (!paste_tokens (pfile, virt_loc, &token, rhs))
+				{
+				  --i;
+				  break;
+				}
+			    }
+			  while (rhs->flags & PASTE_LEFT);
+			}
+
+		      first[j] = token;
+		    }
+		  if (j != i)
+		    {
+		      while (i-- != j)
+			tokens_buff_remove_last_token (buff);
+		      count = j;
+		    }
+
+		  const cpp_token *t = stringify_arg (pfile, first, count);
 		  while (count--)
 		    tokens_buff_remove_last_token (buff);
 		  if (src->flags & PASTE_LEFT)
@@ -2076,8 +2097,14 @@ replace_args (cpp_reader *pfile, cpp_hashnode *node, cpp_macro *macro,
 		  tokens_buff_add_token (buff, virt_locs,
 					 t, t->src_loc, t->src_loc,
 					 NULL, 0);
+		  continue;
 		}
-	      else if (src->flags & PASTE_LEFT)
+	      if (start && paste_flag == start && (*start)->flags & PASTE_LEFT)
+		/* If __VA_OPT__ expands to nothing (either because __VA_ARGS__
+		   is empty or because it is __VA_OPT__() ), drop PASTE_LEFT
+		   flag from previous token.  */
+		copy_paste_flag (pfile, start, &pfile->avoid_paste);
+	      if (src->flags & PASTE_LEFT)
 		{
 		  /* Don't avoid paste after all.  */
 		  while (paste_flag && paste_flag != start
@@ -2648,6 +2675,7 @@ expand_arg (cpp_reader *pfile, macro_arg *arg)
   size_t capacity;
   bool saved_warn_trad;
   bool track_macro_exp_p = CPP_OPTION (pfile, track_macro_expansion);
+  bool saved_ignore__Pragma;
 
   if (arg->count == 0
       || arg->expanded != NULL)
@@ -2670,6 +2698,9 @@ expand_arg (cpp_reader *pfile, macro_arg *arg)
     push_ptoken_context (pfile, NULL, NULL,
 			 arg->first, arg->count + 1);
 
+  saved_ignore__Pragma = pfile->state.ignore__Pragma;
+  pfile->state.ignore__Pragma = 1;
+
   for (;;)
     {
       const cpp_token *token;
@@ -2692,6 +2723,7 @@ expand_arg (cpp_reader *pfile, macro_arg *arg)
   _cpp_pop_context (pfile);
 
   CPP_WTRADITIONAL (pfile) = saved_warn_trad;
+  pfile->state.ignore__Pragma = saved_ignore__Pragma;
 }
 
 /* Returns the macro associated to the current context if we are in
diff --git a/libcpp/makeucnid.c b/libcpp/makeucnid.cc
index b3a0aab..57c3beb 100644
--- a/libcpp/makeucnid.c
+++ b/libcpp/makeucnid.cc
@@ -1,5 +1,5 @@
 /* Make ucnid.h from various sources.
-   Copyright (C) 2005-2021 Free Software Foundation, Inc.
+   Copyright (C) 2005-2022 Free Software Foundation, Inc.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
@@ -450,7 +450,7 @@ write_copyright (void)
 {
   static const char copyright[] = "\
 /* Unicode characters and various properties.\n\
-   Copyright (C) 2003-2021 Free Software Foundation, Inc.\n\
+   Copyright (C) 2003-2022 Free Software Foundation, Inc.\n\
 \n\
    This program is free software; you can redistribute it and/or modify it\n\
    under the terms of the GNU General Public License as published by the\n\
diff --git a/libcpp/mkdeps.c b/libcpp/mkdeps.cc
index 1867e00..30e87d8 100644
--- a/libcpp/mkdeps.c
+++ b/libcpp/mkdeps.cc
@@ -1,5 +1,5 @@
 /* Dependency generator for Makefile fragments.
-   Copyright (C) 2000-2021 Free Software Foundation, Inc.
+   Copyright (C) 2000-2022 Free Software Foundation, Inc.
    Contributed by Zack Weinberg, Mar 2000
 
 This program is free software; you can redistribute it and/or modify it
diff --git a/libcpp/pch.c b/libcpp/pch.cc
index bb80964..9aa589a 100644
--- a/libcpp/pch.c
+++ b/libcpp/pch.cc
@@ -1,5 +1,5 @@
 /* Part of CPP library.  (Precompiled header reading/writing.)
-   Copyright (C) 2000-2021 Free Software Foundation, Inc.
+   Copyright (C) 2000-2022 Free Software Foundation, Inc.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
diff --git a/libcpp/po/ChangeLog b/libcpp/po/ChangeLog
index 843a84b..54ca87f 100644
--- a/libcpp/po/ChangeLog
+++ b/libcpp/po/ChangeLog
@@ -1,3 +1,7 @@
+2021-12-20  Joseph Myers  <joseph@codesourcery.com>
+
+	* es.po: Update.
+
 2021-08-16  Joseph Myers  <joseph@codesourcery.com>
 
 	* de.po: Update.
diff --git a/libcpp/po/es.po b/libcpp/po/es.po
index fde067a..bd50130 100644
--- a/libcpp/po/es.po
+++ b/libcpp/po/es.po
@@ -6,10 +6,10 @@
 # Antonio Ceballos Roa <aceballos@gmail.com>, 2021.
 msgid ""
 msgstr ""
-"Project-Id-Version: cpplib 10.1-b20200209\n"
+"Project-Id-Version: cpplib 11.1-b20210207\n"
 "Report-Msgid-Bugs-To: https://gcc.gnu.org/bugs/\n"
 "POT-Creation-Date: 2021-02-05 21:38+0000\n"
-"PO-Revision-Date: 2021-01-07 11:33+0100\n"
+"PO-Revision-Date: 2021-12-18 09:17+0100\n"
 "Last-Translator: Antonio Ceballos Roa <aceballos@gmail.com>\n"
 "Language-Team: Spanish <es@tp.org.es>\n"
 "Language: es\n"
@@ -491,36 +491,28 @@ msgid "use of C99 long long integer constant"
 msgstr "uso de una constante entera long long C99"
 
 #: expr.c:822
-#, fuzzy
-#| msgid "use of C++11 long long integer constant"
 msgid "use of C++23 %<size_t%> integer constant"
-msgstr "uso de una constante entera long long C++11"
+msgstr "uso de constante entera %<size_t%> de C++23"
 
 #: expr.c:823
-#, fuzzy
-#| msgid "use of C++11 long long integer constant"
 msgid "use of C++23 %<make_signed_t<size_t>%> integer constant"
-msgstr "uso de una constante entera long long C++11"
+msgstr "uso de constante entera %<make_signed_t<size_t>%> de C++23"
 
 #: expr.c:834
 msgid "imaginary constants are a GCC extension"
-msgstr "las constantes imaginarias son una extensión GCC"
+msgstr "las constantes imaginarias son una extensión de GCC"
 
 #: expr.c:841
 msgid "binary constants are a C++14 feature or GCC extension"
-msgstr "las constantes binarias son una característica C++14 o extensión GCC"
+msgstr "las constantes binarias son una característica C++14 o una extensión de GCC"
 
 #: expr.c:843
-#, fuzzy
-#| msgid "binary constants are a C++14 feature or GCC extension"
 msgid "binary constants are a C2X feature or GCC extension"
-msgstr "las constantes binarias son una característica C++14 o extensión GCC"
+msgstr "las constantes binarias son una característica de C2X o una extensión de GCC"
 
 #: expr.c:848
-#, fuzzy
-#| msgid "decimal float constants are a C2X feature"
 msgid "binary constants are a C2X feature"
-msgstr "las constantes de coma flotante decimal son una característica de C2X"
+msgstr "las constantes binarias son una característica de C2X"
 
 #: expr.c:944
 msgid "integer constant is too large for its type"
@@ -713,16 +705,12 @@ msgid "`%.*s' is not in NFC"
 msgstr "`%.*s' no está en NFC"
 
 #: lex.c:1375
-#, fuzzy
-#| msgid "__VA_OPT__ is not available until C++2a"
 msgid "__VA_OPT__ is not available until C++20"
-msgstr "__VA_OPT__ no está disponible bajo C++2a"
+msgstr "__VA_OPT__ no está disponible hasta C++20"
 
 #: lex.c:1382
-#, fuzzy
-#| msgid "__VA_OPT__ can only appear in the expansion of a C++2a variadic macro"
 msgid "__VA_OPT__ can only appear in the expansion of a C++20 variadic macro"
-msgstr "__VA_OPT__ solamente puede aparecer en la expansión de una macro variadic C++2a"
+msgstr "__VA_OPT__ solamente puede aparecer en la expansión de una macro variadic de C++20"
 
 #: lex.c:1413 lex.c:1506
 #, c-format
@@ -778,12 +766,12 @@ msgstr "C++11 requiere un espacio entre cadena literal y macro"
 
 #: lex.c:2711
 msgid "module control-line cannot be in included file"
-msgstr ""
+msgstr "la línea de control del módulo no puede estar en un fichero incluido"
 
 #: lex.c:2725
 #, c-format
 msgid "module control-line \"%s\" cannot be an object-like macro"
-msgstr ""
+msgstr "la línea de control del módulo «%s» no puede ser una macro de tipo objeto"
 
 #: lex.c:3099 lex.c:4472 traditional.c:174
 msgid "unterminated comment"
@@ -811,16 +799,13 @@ msgid "unspellable token %s"
 msgstr "elemento %s impronunciable"
 
 #: lex.c:4627
-#, fuzzy, c-format
-#| msgid "raw string delimiter longer than 16 characters"
+#, c-format
 msgid "raw string delimiter longer than %d characters"
-msgstr "el delimitador de cadena cruda es más largo que 16 caracteres"
+msgstr "el delimitador de cadena cruda es mayor de %d caracteres"
 
 #: lex.c:4697
-#, fuzzy
-#| msgid "unterminated #%s"
 msgid "unterminated literal"
-msgstr "#%s sin terminar"
+msgstr "literal sin terminar"
 
 #: macro.c:94
 msgid "'##' cannot appear at either end of __VA_OPT__"
diff --git a/libcpp/symtab.c b/libcpp/symtab.cc
index 9a2fae0..a059214 100644
--- a/libcpp/symtab.c
+++ b/libcpp/symtab.cc
@@ -1,5 +1,5 @@
 /* Hash tables.
-   Copyright (C) 2000-2021 Free Software Foundation, Inc.
+   Copyright (C) 2000-2022 Free Software Foundation, Inc.
 
 This program is free software; you can redistribute it and/or modify it
 under the terms of the GNU General Public License as published by the
diff --git a/libcpp/system.h b/libcpp/system.h
index ee5fbe2..e80cf02 100644
--- a/libcpp/system.h
+++ b/libcpp/system.h
@@ -1,6 +1,6 @@
 /* Get common system includes and various definitions and declarations based
    on autoconf macros.
-   Copyright (C) 1998-2021 Free Software Foundation, Inc.
+   Copyright (C) 1998-2022 Free Software Foundation, Inc.
 
 This file is part of GCC.
 
@@ -422,6 +422,18 @@ extern void fancy_abort (const char *, int, const char *) ATTRIBUTE_NORETURN;
 #define gcc_checking_assert(EXPR) ((void)(0 && (EXPR)))
 #endif
 
+#ifdef __has_cpp_attribute
+# if __has_cpp_attribute(likely)
+#  define ATTR_LIKELY [[likely]]
+# elif __has_cpp_attribute(__likely__)
+#  define ATTR_LIKELY [[__likely__]]
+# else
+#  define ATTR_LIKELY
+# endif
+#else
+# define ATTR_LIKELY
+#endif
+
 /* Poison identifiers we do not want to use.  */
 #if (GCC_VERSION >= 3000)
 #undef calloc
diff --git a/libcpp/traditional.c b/libcpp/traditional.cc
index 92d0dd1..d02ea48 100644
--- a/libcpp/traditional.c
+++ b/libcpp/traditional.cc
@@ -1,5 +1,5 @@
 /* CPP Library - traditional lexical analysis and macro expansion.
-   Copyright (C) 2002-2021 Free Software Foundation, Inc.
+   Copyright (C) 2002-2022 Free Software Foundation, Inc.
    Contributed by Neil Booth, May 2002
 
 This program is free software; you can redistribute it and/or modify it
@@ -80,7 +80,7 @@ enum ls {ls_none = 0,		/* Normal state.  */
 	 ls_answer		/* In answer to predicate.  */
 };
 
-/* Lexing TODO: Maybe handle space in escaped newlines.  Stop lex.c
+/* Lexing TODO: Maybe handle space in escaped newlines.  Stop lex.cc
    from recognizing comments and directives during its lexing pass.  */
 
 static const uchar *skip_whitespace (cpp_reader *, const uchar *, int);
diff --git a/libcpp/ucnid.h b/libcpp/ucnid.h
index e7b0ac2..b15c123 100644
--- a/libcpp/ucnid.h
+++ b/libcpp/ucnid.h
@@ -1,5 +1,5 @@
 /* Unicode characters and various properties.
-   Copyright (C) 2003-2021 Free Software Foundation, Inc.
+   Copyright (C) 2003-2022 Free Software Foundation, Inc.
 
    This program is free software; you can redistribute it and/or modify it
    under the terms of the GNU General Public License as published by the
diff --git a/libcpp/ucnid.tab b/libcpp/ucnid.tab
index 6542d11..0940f9e 100644
--- a/libcpp/ucnid.tab
+++ b/libcpp/ucnid.tab
@@ -1,5 +1,5 @@
 ; Table of UCNs which are valid in identifiers.
-; Copyright (C) 2003-2021 Free Software Foundation, Inc.
+; Copyright (C) 2003-2022 Free Software Foundation, Inc.
 ; 
 ; This program is free software; you can redistribute it and/or modify it
 ; under the terms of the GNU General Public License as published by the