c++, c: Introduce -Wkeyword-macro warning/pedwarn - part of C++26 P2843R3 [PR120778]

The following patch introduces a -Wkeyword-macro warning that clang has
since 2014 to implement part of C++26 P2843R3 Preprocessing is never undefined
paper.
The relevant change in the paper is moving [macro.names]/2 paragraph to
https://eel.is/c++draft/cpp.replace.general#9 :
"A translation unit shall not #define or #undef names lexically identical to
keywords, to the identifiers listed in Table 4, or to the attribute-tokens
described in [dcl.attr], except that the names likely and unlikely may be
defined as function-like macros."

Now, my understanding of the paper is that in [macro.names] and surrounding
sections the word shall bears different meaning from [cpp.replace.general],
where only the latter location implies ill-formed, diagnostic required.

The warning in clang when introduced diagnosed all #define/#undef directives
on keywords, but shortly after introduction has been changed not to
diagnose #undef at all (with "#undef a keyword is generally harmless but used
often in configuration scripts" message) and later on even the #define
part tweaked - not warn about say
  #define inline
(or const, extern, static), or
  #define keyword keyword
or
  #define keyword __keyword
or
  #define keyword __keyword__
Later on the warning has been moved to be only pedantic diagnostic unless
requested by users.  Clearly some code in the wild does e.g.
  #define private public
and similar games, or e.g. Linux kernel (sure, C) does
  #define inline __inline__ __attribute__((__always_inline__))
etc.
Now, I believe at least with the current C++26 wording such exceptions
aren't allowed (unless it is changed to IFNDR).  But given that this is just
pedantic stuff, the following patch makes the warning off by default for
C and C++ before C++26 and even for C++26 it enables it by default only
if -pedantic/-pedantic-errors (in that case it pedwarns, otherwise it
warns).  And it diagnoses both #define and #undef without exceptions.

From what I can see, all the current NODE_WARN cases are macros starting
with __ with one exception (_Pragma).  As the NODE_* flags seem to be a
limited resource, I chose to just use NODE_WARN as well and differentiate
on the node names (if they don't start with __ or _P, they are considered
to be -Wkeyword-macro registered ones, otherwise old NODE_WARN cases,
typically builtin macros or __STDC* macros).

2025-08-07  Jakub Jelinek  <jakub@redhat.com>

	PR preprocessor/120778
gcc/
	* doc/invoke.texi (Wkeyword-macro): Document.
gcc/c-family/
	* c.opt (Wkeyword-macro): New option.
	* c.opt.urls: Regenerate.
	* c-common.h (cxx_dialect): Comment formatting fix.
	* c-opts.cc (c_common_post_options): Default to
	-Wkeyword-macro for C++26 if pedantic.
gcc/c/
	* c-decl.cc (c_init_decl_processing): Mark cpp nodes corresponding
	to keywords as NODE_WARN if warn_keyword_macro.
gcc/cp/
	* lex.cc (cxx_init): Mark cpp nodes corresponding
	to keywords, identifiers with special meaning and standard
	attribute identifiers as NODE_WARN if warn_keyword_macro.
gcc/testsuite/
	* gcc.dg/Wkeyword-macro-1.c: New test.
	* gcc.dg/Wkeyword-macro-2.c: New test.
	* gcc.dg/Wkeyword-macro-3.c: New test.
	* gcc.dg/Wkeyword-macro-4.c: New test.
	* gcc.dg/Wkeyword-macro-5.c: New test.
	* gcc.dg/Wkeyword-macro-6.c: New test.
	* gcc.dg/Wkeyword-macro-7.c: New test.
	* gcc.dg/Wkeyword-macro-8.c: New test.
	* gcc.dg/Wkeyword-macro-9.c: New test.
	* g++.dg/warn/Wkeyword-macro-1.C: New test.
	* g++.dg/warn/Wkeyword-macro-2.C: New test.
	* g++.dg/warn/Wkeyword-macro-3.C: New test.
	* g++.dg/warn/Wkeyword-macro-4.C: New test.
	* g++.dg/warn/Wkeyword-macro-5.C: New test.
	* g++.dg/warn/Wkeyword-macro-6.C: New test.
	* g++.dg/warn/Wkeyword-macro-7.C: New test.
	* g++.dg/warn/Wkeyword-macro-8.C: New test.
	* g++.dg/warn/Wkeyword-macro-9.C: New test.
	* g++.dg/warn/Wkeyword-macro-10.C: New test.
	* g++.dg/opt/pr82577.C: Don't #define register to nothing for
	C++17 and later.  Instead define reg macro to nothing for C++17
	and later or to register and use it instead of register.
	* g++.dg/modules/atom-preamble-3.C: Add -Wno-keyword-macro to
	dg-additional-options.
	* g++.dg/template/sfinae17.C (static_assert): Rename macro to ...
	(my_static_assert): ... this.
	(main): Use my_static_assert instead of static_assert.
libcpp/
	* include/cpplib.h (struct cpp_options): Add cpp_warn_keyword_macro.
	(enum cpp_warning_reason): Add CPP_W_KEYWORD_MACRO enumerator.
	(cpp_keyword_p): New inline function.
	* directives.cc (do_undef): Support -Wkeyword-macro diagnostics.
	* macro.cc (warn_of_redefinition): Ignore NODE_WARN flag on nodes
	registered for -Wkeyword-macro.
	(_cpp_create_definition): Support -Wkeyword-macro diagnostics.
	Formatting fixes.

3 files changed, 63 insertions, 8 deletions

diff --git a/libcpp/directives.cc b/libcpp/directives.cc
index 4d06caa9b56..47fb8fbdd13 100644
--- a/libcpp/directives.cc
+++ b/libcpp/directives.cc
@@ -734,13 +734,30 @@ do_undef (cpp_reader *pfile)
       if (pfile->cb.undef)
 	pfile->cb.undef (pfile, pfile->directive_line, node);
 
+      /* Handle -Wkeyword-macro registered identifiers.  */
+      bool diagnosed = false;
+      if (CPP_OPTION (pfile, cpp_warn_keyword_macro) && cpp_keyword_p (node))
+	{
+	  if (CPP_OPTION (pfile, cpp_pedantic)
+	      && CPP_OPTION (pfile, cplusplus)
+	      && CPP_OPTION (pfile, lang) >= CLK_GNUCXX26)
+	    cpp_pedwarning (pfile, CPP_W_KEYWORD_MACRO,
+			    "undefining keyword %qs", NODE_NAME (node));
+	  else
+	    cpp_warning (pfile, CPP_W_KEYWORD_MACRO,
+			 "undefining keyword %qs", NODE_NAME (node));
+	  diagnosed = true;
+	}
       /* 6.10.3.5 paragraph 2: [#undef] is ignored if the specified
 	 identifier is not currently defined as a macro name.  */
       if (cpp_macro_p (node))
 	{
 	  if (node->flags & NODE_WARN)
-	    cpp_error (pfile, CPP_DL_WARNING,
-		       "undefining %qs", NODE_NAME (node));
+	    {
+	      if (!diagnosed)
+		cpp_error (pfile, CPP_DL_WARNING,
+			   "undefining %qs", NODE_NAME (node));
+	    }
 	  else if (cpp_builtin_macro_p (node)
 		   && CPP_OPTION (pfile, warn_builtin_macro_redefined))
 	    cpp_warning (pfile, CPP_W_BUILTIN_MACRO_REDEFINED,
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index 75efdcd55d5..bbd88e56f58 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -620,6 +620,9 @@ struct cpp_options
   /* True if -finput-charset= option has been used explicitly.  */
   bool cpp_input_charset_explicit;
 
+  /* True if -Wkeyword-macro.  */
+  bool cpp_warn_keyword_macro;
+
   /* -Wleading-whitespace= value.  */
   unsigned char cpp_warn_leading_whitespace;
 
@@ -757,7 +760,8 @@ enum cpp_warning_reason {
   CPP_W_HEADER_GUARD,
   CPP_W_PRAGMA_ONCE_OUTSIDE_HEADER,
   CPP_W_LEADING_WHITESPACE,
-  CPP_W_TRAILING_WHITESPACE
+  CPP_W_TRAILING_WHITESPACE,
+  CPP_W_KEYWORD_MACRO
 };
 
 /* Callback for header lookup for HEADER, which is the name of a
@@ -1250,6 +1254,17 @@ inline bool cpp_fun_like_macro_p (cpp_hashnode *node)
   return cpp_user_macro_p (node) && node->value.macro->fun_like;
 }
 
+/* Return true for nodes marked for -Wkeyword-macro diagnostics.  */
+inline bool cpp_keyword_p (cpp_hashnode *node)
+{
+  /* As keywords are marked identifiers which don't start with underscore
+     or start with underscore followed by capital letter (except for
+     _Pragma).  */
+  return ((node->flags & NODE_WARN)
+	  && (NODE_NAME (node)[0] != '_'
+	      || (NODE_NAME (node)[1] != '_' && NODE_NAME (node)[1] != 'P')));
+}
+
 extern const unsigned char *cpp_macro_definition (cpp_reader *, cpp_hashnode *);
 extern const unsigned char *cpp_macro_definition (cpp_reader *, cpp_hashnode *,
 						  const cpp_macro *);
diff --git a/libcpp/macro.cc b/libcpp/macro.cc
index 158c8215e52..a47e1feb820 100644
--- a/libcpp/macro.cc
+++ b/libcpp/macro.cc
@@ -3411,7 +3411,11 @@ warn_of_redefinition (cpp_reader *pfile, cpp_hashnode *node,
 {
   /* Some redefinitions need to be warned about regardless.  */
   if (node->flags & NODE_WARN)
-    return true;
+    {
+      /* Ignore NODE_WARN on -Wkeyword-macro registered identifiers though.  */
+      if (!CPP_OPTION (pfile, cpp_warn_keyword_macro) || !cpp_keyword_p (node))
+	return true;
+    }
 
   /* Suppress warnings for builtins that lack the NODE_WARN flag,
      unless Wbuiltin-macro-redefined.  */
@@ -3949,6 +3953,25 @@ _cpp_create_definition (cpp_reader *pfile, cpp_hashnode *node,
   if (name_loc)
     macro->line = name_loc;
 
+  /* Handle -Wkeyword-macro registered identifiers.  */
+  if (CPP_OPTION (pfile, cpp_warn_keyword_macro) && cpp_keyword_p (node))
+    {
+      if (macro->fun_like
+	  && CPP_OPTION (pfile, cplusplus)
+	  && (strcmp ((const char *) NODE_NAME (node), "likely") == 0
+	      || strcmp ((const char *) NODE_NAME (node), "unlikely") == 0))
+	/* likely and unlikely can be defined as function-like macros.  */;
+      else if (CPP_OPTION (pfile, cpp_pedantic)
+	       && CPP_OPTION (pfile, cplusplus)
+	       && CPP_OPTION (pfile, lang) >= CLK_GNUCXX26)
+	cpp_pedwarning_with_line (pfile, CPP_W_KEYWORD_MACRO, macro->line, 0,
+				  "keyword %qs defined as macro",
+				  NODE_NAME (node));
+      else
+	cpp_warning_with_line (pfile, CPP_W_KEYWORD_MACRO, macro->line, 0,
+			       "keyword %qs defined as macro",
+			       NODE_NAME (node));
+    }
   if (cpp_macro_p (node))
     {
       if (CPP_OPTION (pfile, warn_unused_macros))
@@ -3957,12 +3980,12 @@ _cpp_create_definition (cpp_reader *pfile, cpp_hashnode *node,
       if (warn_of_redefinition (pfile, node, macro))
 	{
           const enum cpp_warning_reason reason
-	    = (cpp_builtin_macro_p (node) && !(node->flags & NODE_WARN))
-	    ? CPP_W_BUILTIN_MACRO_REDEFINED : CPP_W_NONE;
+	    = (cpp_builtin_macro_p (node) && !(node->flags & NODE_WARN)
+	       ? CPP_W_BUILTIN_MACRO_REDEFINED : CPP_W_NONE);
 
 	  bool warned
-	    =  cpp_pedwarning_with_line (pfile, reason, macro->line, 0,
-					 "%qs redefined", NODE_NAME (node));
+	    = cpp_pedwarning_with_line (pfile, reason, macro->line, 0,
+					"%qs redefined", NODE_NAME (node));
 
 	  if (warned && cpp_user_macro_p (node))
 	    cpp_error_with_line (pfile, CPP_DL_NOTE, node->value.macro->line,