[gdb/symtab] Don't expand non-Ada CUs for info exceptions

I noticed when running test-case gdb.ada/info_exc.exp with glibc debug info
installed, that the "info exceptions" command that lists all Ada exceptions
also expands non-Ada CUs, which includes CUs in
/lib64/ld-linux-x86-64.so.2 and /lib64/libc.so.6.

Fix this by:
- adding a new lang_matcher parameter to the expand_symtabs_matching
  function, and
- using that new parameter in the expand_symtabs_matching call in
  ada_add_global_exceptions.

The new parameter is a hint, meaning implementations are free to ignore it and
expand CUs with any language.  This is the case for partial symtabs, I'm not
sure whether it makes sense to implement support for this there.

Conversely, when processing a CU with language C and name "<artificial>"
(as produced by GCC LTO), the CU may not really have a single language and we
should ignore the lang_matcher.  See also commit d2f6771173
("Fix 'catch exception' with -flto").

Now that we have lang_matcher available, also use it to limit name splitting
styles and symbol matchers to those applicable to the matched languages.

Without this patch we have (with a gdb build with -O0):
...
$ time gdb -q -batch -x outputs/gdb.ada/info_exc/gdb.in.1 > /dev/null
real	0m1.866s
user	0m2.089s
sys	0m0.120s
...
and with this patch we have:
...
$ time gdb -q -batch -x outputs/gdb.ada/info_exc/gdb.in.1 > /dev/null
real	0m0.469s
user	0m0.777s
sys	0m0.051s
...

Or, to put it in terms of number of CUs, we have 1853 CUs:
...
$ gdb -q -batch -readnow outputs/gdb.ada/info_exc/foo \
    -ex start \
    -ex "maint info symtabs" \
    | grep -c " name "
1853
...

Without this patch, we have:
...
$ gdb -q -batch outputs/gdb.ada/info_exc/foo \
    -ex start \
    -ex "info exceptions" \
    -ex "maint info symtabs" \
    | grep -c " name "
1393
...
so ~75% of the CUs is expanded, and with this patch we have:
...
$ gdb <same-as-above>
20
...
so ~1% of the CUs is expanded.

Tested on x86_64-linux.

Approved-By: Tom Tromey <tom@tromey.com>

PR symtab/32182
Bug: https://sourceware.org/bugzilla/show_bug.cgi?id=32182

gdb/ada-lang.c

@@ -13048,7 +13048,12 @@ ada_add_global_exceptions (compiled_regex *preg,
 			   },
 			   NULL,
 			   SEARCH_GLOBAL_BLOCK | SEARCH_STATIC_BLOCK,
-			   SEARCH_VAR_DOMAIN);
+			   SEARCH_VAR_DOMAIN,
+			   [&] (enum language lang)
+			     {
+			       /* Try to skip non-Ada CUs.  */
+			       return lang == language_ada;
+			     });
 
   /* Iterate over all objfiles irrespective of scope or linker namespaces
      so we get all exceptions anywhere in the progspace.  */

gdb/dwarf2/cooked-index.h

@@ -778,7 +778,9 @@ struct cooked_index_functions : public dwarf2_base_index_functions
      gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
      gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
      block_search_flags search_flags,
-     domain_search_flags domain) override;
+     domain_search_flags domain,
+     gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
+       override;
 
   struct compunit_symtab *find_pc_sect_compunit_symtab
     (struct objfile *objfile, bound_minimal_symbol msymbol,

gdb/dwarf2/read-gdb-index.c

@@ -158,7 +158,9 @@ struct dwarf2_gdb_index : public dwarf2_base_index_functions
      gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
      gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
      block_search_flags search_flags,
-     domain_search_flags domain) override;
+     domain_search_flags domain,
+     gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
+       override;
 };
 
 /* This dumps minimal information about the index.
@@ -187,7 +189,8 @@ dw2_expand_marked_cus
    gdb::function_view<expand_symtabs_file_matcher_ftype> file_matcher,
    gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
    block_search_flags search_flags,
-   domain_search_flags kind)
+   domain_search_flags kind,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
 {
   offset_type vec_len, vec_idx;
   bool global_seen = false;
@@ -268,7 +271,7 @@ dw2_expand_marked_cus
 
       dwarf2_per_cu_data *per_cu = per_objfile->per_bfd->get_cu (cu_index);
       if (!dw2_expand_symtabs_matching_one (per_cu, per_objfile, file_matcher,
-					    expansion_notify))
+					    expansion_notify, lang_matcher))
 	return false;
     }
 
@@ -283,7 +286,8 @@ dwarf2_gdb_index::expand_symtabs_matching
      gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
      gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
      block_search_flags search_flags,
-     domain_search_flags domain)
+     domain_search_flags domain,
+     gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
 {
   dwarf2_per_objfile *per_objfile = get_dwarf2_per_objfile (objfile);
 
@@ -300,7 +304,8 @@ dwarf2_gdb_index::expand_symtabs_matching
 
 	  if (!dw2_expand_symtabs_matching_one (per_cu, per_objfile,
 						file_matcher,
-						expansion_notify))
+						expansion_notify,
+						lang_matcher))
 	    return false;
 	}
       return true;
@@ -316,10 +321,11 @@ dwarf2_gdb_index::expand_symtabs_matching
 					  [&] (offset_type idx)
     {
       if (!dw2_expand_marked_cus (per_objfile, idx, file_matcher,
-				  expansion_notify, search_flags, domain))
+				  expansion_notify, search_flags, domain,
+				  lang_matcher))
 	return false;
       return true;
-    }, per_objfile);
+    }, per_objfile, lang_matcher);
 
   return result;
 }

gdb/dwarf2/read.c

@@ -1644,7 +1644,9 @@ struct readnow_functions : public dwarf2_base_index_functions
      gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
      gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
      block_search_flags search_flags,
-     domain_search_flags domain) override
+     domain_search_flags domain,
+     gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
+       override
   {
     return true;
   }
@@ -2296,7 +2298,8 @@ dw2_expand_symtabs_matching_symbol
    const lookup_name_info &lookup_name_in,
    gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
    gdb::function_view<bool (offset_type)> match_callback,
-   dwarf2_per_objfile *per_objfile)
+   dwarf2_per_objfile *per_objfile,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
 {
   lookup_name_info lookup_name_without_params
     = lookup_name_in.make_ignore_params ();
@@ -2332,6 +2335,8 @@ dw2_expand_symtabs_matching_symbol
   for (int i = 0; i < nr_languages; i++)
     {
       enum language lang_e = (enum language) i;
+      if (lang_matcher != nullptr && !lang_matcher (lang_e))
+	continue;
 
       const language_defn *lang = language_def (lang_e);
       symbol_name_matcher_ftype *name_matcher
@@ -2489,7 +2494,7 @@ check_match (const char *file, int line,
     if (expected_str == NULL || strcmp (expected_str, matched_name) != 0)
       mismatch (expected_str, matched_name);
     return true;
-  }, per_objfile);
+  }, per_objfile, nullptr);
 
   const char *expected_str
   = expected_it == expected_end ? NULL : *expected_it++;
@@ -2850,19 +2855,29 @@ dw2_expand_symtabs_matching_one
   (dwarf2_per_cu_data *per_cu,
    dwarf2_per_objfile *per_objfile,
    gdb::function_view<expand_symtabs_file_matcher_ftype> file_matcher,
-   gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify)
+   gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
 {
-  if (file_matcher == NULL || per_cu->mark)
+  if (file_matcher != nullptr && !per_cu->mark)
+    return true;
+
+  if (lang_matcher != nullptr)
     {
-      bool symtab_was_null = !per_objfile->symtab_set_p (per_cu);
-
-      compunit_symtab *symtab
-	= dw2_instantiate_symtab (per_cu, per_objfile, false);
-      gdb_assert (symtab != nullptr);
-
-      if (expansion_notify != NULL && symtab_was_null)
-	return expansion_notify (symtab);
+      /* Try to skip CUs with non-matching language.  */
+      per_cu->ensure_lang (per_objfile);
+      if (!per_cu->maybe_multi_language ()
+	  && !lang_matcher (per_cu->lang ()))
+	return true;
     }
+
+  bool symtab_was_null = !per_objfile->symtab_set_p (per_cu);
+  compunit_symtab *symtab
+    = dw2_instantiate_symtab (per_cu, per_objfile, false);
+  gdb_assert (symtab != nullptr);
+
+  if (expansion_notify != NULL && symtab_was_null)
+    return expansion_notify (symtab);
+
   return true;
 }
 
@@ -16619,7 +16634,8 @@ cooked_index_functions::expand_symtabs_matching
       gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
       gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
       block_search_flags search_flags,
-      domain_search_flags domain)
+      domain_search_flags domain,
+      gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
 {
   dwarf2_per_objfile *per_objfile = get_dwarf2_per_objfile (objfile);
 
@@ -16638,7 +16654,8 @@ cooked_index_functions::expand_symtabs_matching
 
 	  if (!dw2_expand_symtabs_matching_one (per_cu, per_objfile,
 						file_matcher,
-						expansion_notify))
+						expansion_notify,
+						lang_matcher))
 	    return false;
 	}
       return true;
@@ -16663,8 +16680,42 @@ cooked_index_functions::expand_symtabs_matching
   symbol_name_match_type match_type
     = lookup_name_without_params.match_type ();
 
+  std::bitset<nr_languages> unique_styles_used;
+  if (lang_matcher != nullptr)
+    for (unsigned iter = 0; iter < nr_languages; ++iter)
+      {
+	enum language lang = (enum language) iter;
+	if (!lang_matcher (lang))
+	  continue;
+
+	switch (lang)
+	  {
+	  case language_cplus:
+	  case language_rust:
+	    unique_styles_used[language_cplus] = true;
+	    break;
+	  case language_d:
+	  case language_go:
+	    unique_styles_used[language_d] = true;
+	    break;
+	  case language_ada:
+	    unique_styles_used[language_ada] = true;
+	    break;
+	  default:
+	    unique_styles_used[language_c] = true;
+	  }
+
+	if (unique_styles_used.count ()
+	    == sizeof (unique_styles) / sizeof (unique_styles[0]))
+	  break;
+      }
+
   for (enum language lang : unique_styles)
     {
+      if (lang_matcher != nullptr
+	  && !unique_styles_used.test (lang))
+	continue;
+
       std::vector<std::string_view> name_vec
 	= lookup_name_without_params.split_name (lang);
       std::vector<std::string> name_str_vec (name_vec.begin (), name_vec.end ());
@@ -16695,6 +16746,15 @@ cooked_index_functions::expand_symtabs_matching
 	      || !entry->matches (domain))
 	    continue;
 
+	  if (lang_matcher != nullptr)
+	    {
+	      /* Try to skip CUs with non-matching language.  */
+	      entry->per_cu->ensure_lang (per_objfile);
+	      if (!entry->per_cu->maybe_multi_language ()
+		  && !lang_matcher (entry->per_cu->lang ()))
+		continue;
+	    }
+
 	  /* We've found the base name of the symbol; now walk its
 	     parentage chain, ensuring that each component
 	     matches.  */
@@ -16763,7 +16823,7 @@ cooked_index_functions::expand_symtabs_matching
 
 	  if (!dw2_expand_symtabs_matching_one (entry->per_cu, per_objfile,
 						file_matcher,
-						expansion_notify))
+						expansion_notify, nullptr))
 	    return false;
 	}
     }
@@ -21463,6 +21523,24 @@ dwarf2_per_cu_data::set_lang (enum language lang,
   gdb_assert (old_dw == 0 || old_dw == dw_lang);
 }
 
+/* See read.h.  */
+
+void
+dwarf2_per_cu_data::ensure_lang (dwarf2_per_objfile *per_objfile)
+{
+  if (lang (false) != language_unknown)
+    return;
+
+  cutu_reader reader (this, per_objfile);
+  if (reader.dummy_p)
+    {
+      set_lang (language_minimal, (dwarf_source_language)0);
+      return;
+    }
+
+  prepare_one_comp_unit (reader.cu, reader.comp_unit_die, language_minimal);
+}
+
 /* A helper function for dwarf2_find_containing_comp_unit that returns
    the index of the result, and that searches a vector.  It will
    return a result even if the offset in question does not actually
@@ -21626,6 +21704,14 @@ prepare_one_comp_unit (struct dwarf2_cu *cu, struct die_info *comp_unit_die,
 
   cu->language_defn = language_def (lang);
 
+  /* Initialize the lto_artificial field.  */
+  attr = dwarf2_attr (comp_unit_die, DW_AT_name, cu);
+  if (attr != nullptr
+      && cu->producer != nullptr
+      && strcmp (attr->as_string (), "<artificial>") == 0
+      && producer_is_gcc (cu->producer, nullptr, nullptr))
+    cu->per_cu->lto_artificial = true;
+
   switch (comp_unit_die->tag)
     {
     case DW_TAG_compile_unit:

gdb/dwarf2/read.h

@@ -102,6 +102,7 @@ struct dwarf2_per_cu_data
       is_dwz (false),
       reading_dwo_directly (false),
       tu_read (false),
+      lto_artificial (false),
       queued (false),
       m_header_read_in (false),
       mark (false),
@@ -148,6 +149,11 @@ public:
      This flag is only valid if is_debug_types is true.  */
   unsigned int tu_read : 1;
 
+  /* Non-zero if the CU is produced by GCC and has name "<artificial>".  GCC
+     uses this to indicate that the CU does not correspond to a single source
+     file.  GCC produces this type of CU during LTO.  */
+  unsigned int lto_artificial : 1;
+
   /* Wrap the following in struct packed instead of bitfields to avoid
      data races when the bitfields end up on the same memory location
      (per C++ memory model).  */
@@ -324,6 +330,9 @@ public:
     return l;
   }
 
+  /* Make sure that m_lang != language_unknown.  */
+  void ensure_lang (dwarf2_per_objfile *per_objfile);
+
   /* Return the language of this CU, as a DWARF DW_LANG_* value.  This
      may be 0 in some situations.  */
   dwarf_source_language dw_lang () const
@@ -335,6 +344,22 @@ public:
      situation LANG would be set by the importing CU.  */
   void set_lang (enum language lang, dwarf_source_language dw_lang);
 
+  /* Return true if the CU may be a multi-language CU.  */
+
+  bool maybe_multi_language () const
+  {
+    enum language lang = this->lang ();
+
+    if (!lto_artificial)
+      /* Assume multi-language CUs are generated only by GCC LTO.  */
+      return false;
+
+    /* If GCC mixes different languages in an artificial LTO CU, it labels it C.
+       The exception to this is when it mixes C and C++, which it labels it C++.
+       For now, we don't consider the latter a multi-language CU.  */
+    return lang == language_c;
+  }
+
   /* Free any cached file names.  */
   void free_cached_file_names ();
 };
@@ -867,7 +892,8 @@ extern bool dw2_expand_symtabs_matching_one
   (dwarf2_per_cu_data *per_cu,
    dwarf2_per_objfile *per_objfile,
    gdb::function_view<expand_symtabs_file_matcher_ftype> file_matcher,
-   gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify);
+   gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher);
 
 /* Helper for dw2_expand_symtabs_matching that works with a
    mapped_index_base instead of the containing objfile.  This is split
@@ -881,7 +907,8 @@ extern bool dw2_expand_symtabs_matching_symbol
    const lookup_name_info &lookup_name_in,
    gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
    gdb::function_view<bool (offset_type)> match_callback,
-   dwarf2_per_objfile *per_objfile);
+   dwarf2_per_objfile *per_objfile,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher);
 
 /* If FILE_MATCHER is non-NULL, set all the
    dwarf2_per_cu_quick_data::MARK of the current DWARF2_PER_OBJFILE

gdb/objfiles.h

@@ -597,7 +597,9 @@ public:
      gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
      gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
      block_search_flags search_flags,
-     domain_search_flags domain);
+     domain_search_flags domain,
+     gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher
+       = nullptr);
 
   /* See quick_symbol_functions.  */
   struct compunit_symtab *

gdb/psymtab.c

@@ -893,7 +893,9 @@ psymbol_functions::expand_symtabs_matching
    gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
    gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
    block_search_flags search_flags,
-   domain_search_flags domain)
+   domain_search_flags domain,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype>
+     lang_matcher ATTRIBUTE_UNUSED)
 {
   /* Clear the search flags.  */
   for (partial_symtab *ps : partial_symbols (objfile))

gdb/psymtab.h

@@ -633,7 +633,9 @@ struct psymbol_functions : public quick_symbol_functions
      gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
      gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
      block_search_flags search_flags,
-     domain_search_flags kind) override;
+     domain_search_flags kind,
+     gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
+       override;
 
   struct compunit_symtab *find_pc_sect_compunit_symtab
     (struct objfile *objfile, bound_minimal_symbol msymbol, CORE_ADDR pc,

gdb/quick-symbol.h

@@ -46,6 +46,11 @@ typedef bool (expand_symtabs_file_matcher_ftype) (const char *filename,
 
 typedef bool (expand_symtabs_symbol_matcher_ftype) (const char *name);
 
+/* Callback for quick_symbol_functions->expand_symtabs_matching
+   to match a language.  */
+
+typedef bool (expand_symtabs_lang_matcher_ftype) (enum language lang);
+
 /* Callback for quick_symbol_functions->expand_symtabs_matching
    to be called after a symtab has been expanded.  If this returns
    true, more symtabs are checked; if it returns false, iteration
@@ -122,6 +127,10 @@ struct quick_symbol_functions
 
   /* Expand all symbol tables in OBJFILE matching some criteria.
 
+     If LANG_MATCHER returns false, expansion of the symbol table may be
+     skipped.  It may also not be skipped, which the caller needs to take into
+     account.
+
      FILE_MATCHER is called for each file in OBJFILE.  The file name
      is passed to it.  If the matcher returns false, the file is
      skipped.  If FILE_MATCHER is NULL the file is not skipped.  If
@@ -154,7 +163,9 @@ struct quick_symbol_functions
      gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
      gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
      block_search_flags search_flags,
-     domain_search_flags domain) = 0;
+     domain_search_flags domain,
+     gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher
+       = nullptr) = 0;
 
   /* Return the comp unit from OBJFILE that contains PC and
      SECTION.  Return NULL if there is no such compunit.  This

gdb/symfile-debug.c

@@ -376,7 +376,8 @@ objfile::expand_symtabs_matching
    gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
    gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
    block_search_flags search_flags,
-   domain_search_flags domain)
+   domain_search_flags domain,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
 {
   /* This invariant is documented in quick-functions.h.  */
   gdb_assert (lookup_name != nullptr || symbol_matcher == nullptr);
@@ -393,7 +394,8 @@ objfile::expand_symtabs_matching
   for (const auto &iter : qf)
     if (!iter->expand_symtabs_matching (this, file_matcher, lookup_name,
 					symbol_matcher, expansion_notify,
-					search_flags, domain))
+					search_flags, domain,
+					lang_matcher))
       return false;
   return true;
 }

gdb/symfile.c

@@ -3759,7 +3759,8 @@ expand_symtabs_matching
    gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
    gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
    block_search_flags search_flags,
-   domain_search_flags domain)
+   domain_search_flags domain,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher)
 {
   for (objfile *objfile : current_program_space->objfiles ())
     if (!objfile->expand_symtabs_matching (file_matcher,
@@ -3767,7 +3768,8 @@ expand_symtabs_matching
 					   symbol_matcher,
 					   expansion_notify,
 					   search_flags,
-					   domain))
+					   domain,
+					   lang_matcher))
       return false;
   return true;
 }

gdb/symfile.h

@@ -352,7 +352,9 @@ bool expand_symtabs_matching
    gdb::function_view<expand_symtabs_symbol_matcher_ftype> symbol_matcher,
    gdb::function_view<expand_symtabs_exp_notify_ftype> expansion_notify,
    block_search_flags search_flags,
-   domain_search_flags kind);
+   domain_search_flags kind,
+   gdb::function_view<expand_symtabs_lang_matcher_ftype> lang_matcher
+     = nullptr);
 
 void map_symbol_filenames (gdb::function_view<symbol_filename_ftype> fun,
 			   bool need_fullname);