libcpp: Improve the diagnostic for poisoned identifiers [PR36887]

The PR requests an enhancement to the diagnostic issued for the use of a
poisoned identifier. Currently, we show the location of the usage, but not
the location which requested the poisoning, which would be helpful for the
user if the decision to poison an identifier was made externally, such as
in a library header.

In order to output this information, we need to remember a location_t for
each identifier that has been poisoned, and that data needs to be preserved
as well in a PCH. One option would be to add a field to struct cpp_hashnode,
but there is no convenient place to add it without increasing the size of
the struct for all identifiers. Given this facility will be needed rarely,
it seemed better to add a second hash map, which is handled PCH-wise the
same as the current one in gcc/stringpool.cc. This hash map associates a new
struct cpp_hashnode_extra with each identifier that needs one. Currently
that struct only contains the new location_t, but it could be extended in
the future if there is other ancillary data that may be convenient to put
there for other purposes.

libcpp/ChangeLog:

	PR preprocessor/36887
	* directives.cc (do_pragma_poison): Store in the extra hash map the
	location from which an identifier has been poisoned.
	* lex.cc (identifier_diagnostics_on_lex): When issuing a diagnostic
	for the use of a poisoned identifier, also add a note indicating the
	location from which it was poisoned.
	* identifiers.cc (alloc_node): Convert to template function.
	(_cpp_init_hashtable): Handle the new extra hash map.
	(_cpp_destroy_hashtable): Likewise.
	* include/cpplib.h (struct cpp_hashnode_extra): New struct.
	(cpp_create_reader): Update prototype to...
	* init.cc (cpp_create_reader): ...accept an argument for the extra
	hash table and pass it to _cpp_init_hashtable.
	* include/symtab.h (ht_lookup): New overload for convenience.
	* internal.h (struct cpp_reader): Add EXTRA_HASH_TABLE member.
	(_cpp_init_hashtable): Adjust prototype.

gcc/c-family/ChangeLog:

	PR preprocessor/36887
	* c-opts.cc (c_common_init_options): Pass new extra hash map
	argument to cpp_create_reader().

gcc/ChangeLog:

	PR preprocessor/36887
	* toplev.h (ident_hash_extra): Declare...
	* stringpool.cc (ident_hash_extra): ...this new global variable.
	(init_stringpool): Handle ident_hash_extra as well as ident_hash.
	(ggc_mark_stringpool): Likewise.
	(ggc_purge_stringpool): Likewise.
	(struct string_pool_data_extra): New struct.
	(spd2): New GC root variable.
	(gt_pch_save_stringpool): Use spd2 to handle ident_hash_extra,
	analogous to how spd is used to handle ident_hash.
	(gt_pch_restore_stringpool): Likewise.

gcc/testsuite/ChangeLog:

	PR preprocessor/36887
	* c-c++-common/cpp/diagnostic-poison.c: New test.
	* g++.dg/pch/pr36887.C: New test.
	* g++.dg/pch/pr36887.Hs: New test.

7 files changed, 69 insertions, 25 deletions

diff --git a/libcpp/directives.cc b/libcpp/directives.cc
index ee5419d..c5c938f 100644
--- a/libcpp/directives.cc
+++ b/libcpp/directives.cc
@@ -1737,6 +1737,9 @@ do_pragma_poison (cpp_reader *pfile)
 		   NODE_NAME (hp));
       _cpp_free_definition (hp);
       hp->flags |= NODE_POISONED | NODE_DIAGNOSTIC;
+      const auto data = (cpp_hashnode_extra *)
+	ht_lookup (pfile->extra_hash_table, hp->ident, HT_ALLOC);
+      data->poisoned_loc = tok->src_loc;
     }
   pfile->state.poisoned_ok = 0;
 }
diff --git a/libcpp/identifiers.cc b/libcpp/identifiers.cc
index 7eccaa9..10cbbdf 100644
--- a/libcpp/identifiers.cc
+++ b/libcpp/identifiers.cc
@@ -27,24 +27,22 @@ along with this program; see the file COPYING3.  If not see
 #include "cpplib.h"
 #include "internal.h"
 
-static hashnode alloc_node (cpp_hash_table *);
-
 /* Return an identifier node for hashtable.c.  Used by cpplib except
    when integrated with the C front ends.  */
+template<typename Node>
 static hashnode
 alloc_node (cpp_hash_table *table)
 {
-  cpp_hashnode *node;
-
-  node = XOBNEW (&table->pfile->hash_ob, cpp_hashnode);
-  memset (node, 0, sizeof (cpp_hashnode));
+  const auto node = XOBNEW (&table->pfile->hash_ob, Node);
+  memset (node, 0, sizeof (Node));
   return HT_NODE (node);
 }
 
 /* Set up the identifier hash table.  Use TABLE if non-null, otherwise
    create our own.  */
 void
-_cpp_init_hashtable (cpp_reader *pfile, cpp_hash_table *table)
+_cpp_init_hashtable (cpp_reader *pfile, cpp_hash_table *table,
+		     cpp_hash_table *extra_table)
 {
   struct spec_nodes *s;
 
@@ -52,13 +50,23 @@ _cpp_init_hashtable (cpp_reader *pfile, cpp_hash_table *table)
     {
       pfile->our_hashtable = 1;
       table = ht_create (13);	/* 8K (=2^13) entries.  */
-      table->alloc_node = alloc_node;
+      table->alloc_node = alloc_node<cpp_hashnode>;
+    }
 
-      obstack_specify_allocation (&pfile->hash_ob, 0, 0, xmalloc, free);
+  if (extra_table == NULL)
+    {
+      pfile->our_extra_hashtable = true;
+      extra_table = ht_create (6); /* 64 entries.  */
+      extra_table->alloc_node = alloc_node<cpp_hashnode_extra>;
     }
 
+  if (pfile->our_hashtable || pfile->our_extra_hashtable)
+    obstack_specify_allocation (&pfile->hash_ob, 0, 0, xmalloc, free);
+
   table->pfile = pfile;
+  extra_table->pfile = pfile;
   pfile->hash_table = table;
+  pfile->extra_hash_table = extra_table;
 
   /* Now we can initialize things that use the hash table.  */
   _cpp_init_directives (pfile);
@@ -80,10 +88,11 @@ void
 _cpp_destroy_hashtable (cpp_reader *pfile)
 {
   if (pfile->our_hashtable)
-    {
-      ht_destroy (pfile->hash_table);
-      obstack_free (&pfile->hash_ob, 0);
-    }
+    ht_destroy (pfile->hash_table);
+  if (pfile->our_extra_hashtable)
+    ht_destroy (pfile->extra_hash_table);
+  if (pfile->our_hashtable || pfile->our_extra_hashtable)
+    obstack_free (&pfile->hash_ob, 0);
 }
 
 /* Returns the hash entry for the STR of length LEN, creating one
@@ -110,7 +119,12 @@ cpp_defined (cpp_reader *pfile, const unsigned char *str, int len)
 /* We don't need a proxy since the hash table's identifier comes first
    in cpp_hashnode.  However, in case this is ever changed, we have a
    static assertion for it.  */
-extern char proxy_assertion_broken[offsetof (struct cpp_hashnode, ident) == 0 ? 1 : -1];
+static_assert (offsetof (cpp_hashnode, ident) == 0,
+	       "struct cpp_hashnode must have a struct ht_identifier as"
+	       " its first member");
+static_assert (offsetof (cpp_hashnode_extra, ident) == 0,
+	       "struct cpp_hashnode_extra must have a struct ht_identifier as"
+	       " its first member");
 
 /* For all nodes in the hashtable, callback CB with parameters PFILE,
    the node, and V.  */
diff --git a/libcpp/include/cpplib.h b/libcpp/include/cpplib.h
index c0af82c..fe73a27 100644
--- a/libcpp/include/cpplib.h
+++ b/libcpp/include/cpplib.h
@@ -1009,6 +1009,14 @@ struct GTY(()) cpp_hashnode {
   union _cpp_hashnode_value GTY ((desc ("%1.type"))) value;
 };
 
+/* Extra information we may need to store per identifier, which is needed rarely
+   enough that it's not worth adding directly into the main identifier hash.  */
+struct GTY(()) cpp_hashnode_extra
+{
+  struct ht_identifier ident;
+  location_t poisoned_loc;
+};
+
 /* A class for iterating through the source locations within a
    string token (before escapes are interpreted, and before
    concatenation).  */
@@ -1055,12 +1063,15 @@ class cpp_substring_ranges
 
 /* Call this first to get a handle to pass to other functions.
 
-   If you want cpplib to manage its own hashtable, pass in a NULL
-   pointer.  Otherwise you should pass in an initialized hash table
-   that cpplib will share; this technique is used by the C front
-   ends.  */
+   The first hash table argument is for associating a struct cpp_hashnode
+   with each identifier.  The second hash table argument is for associating
+   a struct cpp_hashnode_extra with each identifier that needs one.  For
+   either, pass in a NULL pointer if you want cpplib to create and manage
+   the hash table itself, or else pass a suitably initialized hash table to
+   be managed external to libcpp, as is done by the C-family frontends.  */
 extern cpp_reader *cpp_create_reader (enum c_lang, struct ht *,
-				      class line_maps *);
+				      class line_maps *,
+				      struct ht * = nullptr);
 
 /* Reset the cpp_reader's line_map.  This is only used after reading a
    PCH file.  */
diff --git a/libcpp/include/symtab.h b/libcpp/include/symtab.h
index 0c713f2..4a2370e 100644
--- a/libcpp/include/symtab.h
+++ b/libcpp/include/symtab.h
@@ -81,6 +81,12 @@ extern hashnode ht_lookup (cpp_hash_table *, const unsigned char *,
 extern hashnode ht_lookup_with_hash (cpp_hash_table *, const unsigned char *,
                                      size_t, unsigned int,
                                      enum ht_lookup_option);
+inline hashnode ht_lookup (cpp_hash_table *ht, const ht_identifier &id,
+			   ht_lookup_option opt)
+{
+  return ht_lookup_with_hash (ht, id.str, id.len, id.hash_value, opt);
+}
+
 #define HT_HASHSTEP(r, c) ((r) * 67 + ((c) - 113));
 #define HT_HASHFINISH(r, len) ((r) + (len))
 
diff --git a/libcpp/init.cc b/libcpp/init.cc
index b97d7a7..18a7f04 100644
--- a/libcpp/init.cc
+++ b/libcpp/init.cc
@@ -191,7 +191,7 @@ init_library (void)
 /* Initialize a cpp_reader structure.  */
 cpp_reader *
 cpp_create_reader (enum c_lang lang, cpp_hash_table *table,
-		   class line_maps *line_table)
+		   class line_maps *line_table, cpp_hash_table *extra_table)
 {
   cpp_reader *pfile;
 
@@ -307,7 +307,7 @@ cpp_create_reader (enum c_lang lang, cpp_hash_table *table,
 
   _cpp_init_files (pfile);
 
-  _cpp_init_hashtable (pfile, table);
+  _cpp_init_hashtable (pfile, table, extra_table);
 
   return pfile;
 }
diff --git a/libcpp/internal.h b/libcpp/internal.h
index 33ed0a2..6a10e9d 100644
--- a/libcpp/internal.h
+++ b/libcpp/internal.h
@@ -555,6 +555,9 @@ struct cpp_reader
   /* Identifier hash table.  */
   struct ht *hash_table;
 
+  /* Identifier ancillary data hash table.  */
+  struct ht *extra_hash_table;
+
   /* Expression parser stack.  */
   struct op *op_stack, *op_limit;
 
@@ -566,7 +569,7 @@ struct cpp_reader
   struct spec_nodes spec_nodes;
 
   /* Whether cpplib owns the hashtable.  */
-  bool our_hashtable;
+  bool our_hashtable, our_extra_hashtable;
 
   /* Traditional preprocessing output buffer (a logical line).  */
   struct
@@ -704,7 +707,8 @@ extern void _cpp_push_token_context (cpp_reader *, cpp_hashnode *,
 extern void _cpp_backup_tokens_direct (cpp_reader *, unsigned int);
 
 /* In identifiers.cc */
-extern void _cpp_init_hashtable (cpp_reader *, cpp_hash_table *);
+extern void
+_cpp_init_hashtable (cpp_reader *, cpp_hash_table *, cpp_hash_table *);
 extern void _cpp_destroy_hashtable (cpp_reader *);
 
 /* In files.cc */
diff --git a/libcpp/lex.cc b/libcpp/lex.cc
index ce8ff61..5ca438a 100644
--- a/libcpp/lex.cc
+++ b/libcpp/lex.cc
@@ -2168,8 +2168,14 @@ identifier_diagnostics_on_lex (cpp_reader *pfile, cpp_hashnode *node)
 
   /* It is allowed to poison the same identifier twice.  */
   if ((node->flags & NODE_POISONED) && !pfile->state.poisoned_ok)
-    cpp_error (pfile, CPP_DL_ERROR, "attempt to use poisoned \"%s\"",
-	       NODE_NAME (node));
+    {
+      cpp_error (pfile, CPP_DL_ERROR, "attempt to use poisoned \"%s\"",
+		 NODE_NAME (node));
+      const auto data = (cpp_hashnode_extra *)
+	ht_lookup (pfile->extra_hash_table, node->ident, HT_NO_INSERT);
+      if (data && data->poisoned_loc)
+	cpp_error_at (pfile, CPP_DL_NOTE, data->poisoned_loc, "poisoned here");
+    }
 
   /* Constraint 6.10.3.5: __VA_ARGS__ should only appear in the
      replacement list of a variadic macro.  */