Per-language symbol name hashing algorithm

Currently, we have a mess of symbol name hashing/comparison routines.
There's msymbol_hash for mangled names, and dict_hash and
msymbol_hash_iw for demangled names.  Then there's strcmp_iw,
strcmp_iw_ordered and Ada's full_match/wild_match, which all have to
agree with the hashing routines.  That's why dict_hash is really about
Ada names.  From the inconsistency department, minimal symbol hashing
doesn't go via dict_hash, so Ada's wild matching can't ever work with
minimal symbols.

This patch starts fixing this, by doing two things:

#1 - adds a language vector method to let each language decide how to
     compute a symbol name hash.

#2 - makes dictionaries know the language of the symbols they hold,
     and then use the dictionaries language to decide which hashing
     method to use.

For now, this is just scaffolding, since all languages install the
default method.  The series will make C++ install its own hashing
method later on, and will add per-language symbol name comparison
routines too.

This patch is based on a patch that Keith wrote for the libcc1/C++ WIP
support.

gdb/ChangeLog:
yyyy-mm-dd  Keith Seitz  <keiths@redhat.com>
	    Pedro Alves  <palves@redhat.com>

	* ada-lang.c (ada_language_defn): Install
	default_search_name_hash.
	* buildsym.c (struct buildsym_compunit): <language>: New field.
	(finish_block_internal): Pass language when creating dictionaries.
	(start_buildsym_compunit, start_symtab): New language parameters.
	Use them.
	(restart_symtab): Pass down compilation unit's language.
	* buildsym.h (enum language): Forward declare.
	(start_symtab): New 'language' parameter.
	* c-lang.c (c_language_defn, cplus_language_defn)
	(asm_language_defn, minimal_language_defn): Install
	default_search_name_hash.
	* coffread.c (coff_start_symtab): Adjust.
	* d-lang.c (d_language_defn): Install default_search_name_hash.
	* dbxread.c (struct symloc): Add 'pst_language' field.
	(PST_LANGUAGE): Define.
	(start_psymtab, read_ofile_symtab): Use it.
	(process_one_symbol): New 'language' parameter.  Pass it down.
	* dictionary.c (struct dictionary) <language>: New field.
	(DICT_LANGUAGE): Define.
	(dict_create_hashed, dict_create_hashed_expandable)
	(dict_create_linear, dict_create_linear_expandable): New parameter
	'language'.  Set the dictionary's language.
	(iter_match_first_hashed): Adjust to rename.
	(insert_symbol_hashed): Assert we don't see mismatching
	languages.  Adjust to rename.
	(dict_hash): Rename to ...
	(default_search_name_hash): ... this and make extern.
	* dictionary.h (struct language_defn): Forward declare.
	(dict_create_hashed): New parameter 'language'.
	* dwarf2read.c (dwarf2_start_symtab): Pass down language.
	* f-lang.c (f_language_defn): Install default_search_name_hash.
	* go-lang.c (go_language_defn): Install default_search_name_hash.
	* jit.c (finalize_symtab): Pass compunit's language to dictionary
	creation.
	* language.c (unknown_language_defn, auto_language_defn):
	* language.h (language_defn::la_search_name_hash): New field.
	(default_search_name_hash): Declare.
	* m2-lang.c (m2_language_defn): Install default_search_name_hash.
	* mdebugread.c (new_block): New parameter 'language'.
	* mdebugread.c (parse_symbol): Pass symbol language to block
	allocation.
	(psymtab_to_symtab_1): Pass down language.
	(new_symtab): Pass compunit's language to block allocation.
	* objc-lang.c (objc_language_defn): Install
	default_search_name_hash.
	* opencl-lang.c (opencl_language_defn):
	* p-lang.c (pascal_language_defn): Install
	default_search_name_hash.
	* rust-lang.c (rust_language_defn): Install
	default_search_name_hash.
	* stabsread.h (enum language): Forward declare.
	(process_one_symbol): Add 'language' parameter.
	* symtab.c (search_name_hash): New function.
	* symtab.h (search_name_hash): Declare.
	* xcoffread.c (read_xcoff_symtab): Pass language to start_symtab.

25 files changed, 161 insertions, 87 deletions

diff --git a/gdb/ada-lang.c b/gdb/ada-lang.c
index 7409496ce7a..a3d1207fdd6 100644
--- a/gdb/ada-lang.c
+++ b/gdb/ada-lang.c
@@ -13956,6 +13956,7 @@ extern const struct language_defn ada_language_defn = {
   c_watch_location_expression,
   ada_get_symbol_name_cmp,	/* la_get_symbol_name_cmp */
   ada_iterate_over_symbols,
+  default_search_name_hash,
   &ada_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/buildsym.c b/gdb/buildsym.c
index c556ac1339a..e9469698778 100644
--- a/gdb/buildsym.c
+++ b/gdb/buildsym.c
@@ -129,6 +129,9 @@ struct buildsym_compunit
 
   /* The compunit we are building.  */
   struct compunit_symtab *compunit_symtab;
+
+  /* Language of this compunit_symtab.  */
+  enum language language;
 };
 
 /* The work-in-progress of the compunit we are building.
@@ -352,20 +355,23 @@ finish_block_internal (struct symbol *symbol,
 
   if (symbol)
     {
-      BLOCK_DICT (block) = dict_create_linear (&objfile->objfile_obstack,
-					       *listhead);
+      BLOCK_DICT (block)
+	= dict_create_linear (&objfile->objfile_obstack,
+			      buildsym_compunit->language, *listhead);
     }
   else
     {
       if (expandable)
 	{
-	  BLOCK_DICT (block) = dict_create_hashed_expandable ();
+	  BLOCK_DICT (block)
+	    = dict_create_hashed_expandable (buildsym_compunit->language);
 	  dict_add_pending (BLOCK_DICT (block), *listhead);
 	}
       else
 	{
 	  BLOCK_DICT (block) =
-	    dict_create_hashed (&objfile->objfile_obstack, *listhead);
+	    dict_create_hashed (&objfile->objfile_obstack,
+				buildsym_compunit->language, *listhead);
 	}
     }
 
@@ -769,7 +775,8 @@ start_subfile (const char *name)
    (or NULL if not known).  */
 
 static struct buildsym_compunit *
-start_buildsym_compunit (struct objfile *objfile, const char *comp_dir)
+start_buildsym_compunit (struct objfile *objfile, const char *comp_dir,
+			 enum language language)
 {
   struct buildsym_compunit *bscu;
 
@@ -778,6 +785,7 @@ start_buildsym_compunit (struct objfile *objfile, const char *comp_dir)
 
   bscu->objfile = objfile;
   bscu->comp_dir = (comp_dir == NULL) ? NULL : xstrdup (comp_dir);
+  bscu->language = language;
 
   /* Initialize the debug format string to NULL.  We may supply it
      later via a call to record_debugformat.  */
@@ -1042,17 +1050,20 @@ prepare_for_building (const char *name, CORE_ADDR start_addr)
    TAG_compile_unit DIE is seen.  It indicates the start of data for
    one original source file.
 
-   NAME is the name of the file (cannot be NULL).  COMP_DIR is the directory in
-   which the file was compiled (or NULL if not known).  START_ADDR is the
-   lowest address of objects in the file (or 0 if not known).  */
+   NAME is the name of the file (cannot be NULL).  COMP_DIR is the
+   directory in which the file was compiled (or NULL if not known).
+   START_ADDR is the lowest address of objects in the file (or 0 if
+   not known).  LANGUAGE is the language of the source file, or
+   language_unknown if not known, in which case it'll be deduced from
+   the filename.  */
 
 struct compunit_symtab *
 start_symtab (struct objfile *objfile, const char *name, const char *comp_dir,
-	      CORE_ADDR start_addr)
+	      CORE_ADDR start_addr, enum language language)
 {
   prepare_for_building (name, start_addr);
 
-  buildsym_compunit = start_buildsym_compunit (objfile, comp_dir);
+  buildsym_compunit = start_buildsym_compunit (objfile, comp_dir, language);
 
   /* Allocate the compunit symtab now.  The caller needs it to allocate
      non-primary symtabs.  It is also needed by get_macro_table.  */
@@ -1089,7 +1100,8 @@ restart_symtab (struct compunit_symtab *cust,
   prepare_for_building (name, start_addr);
 
   buildsym_compunit = start_buildsym_compunit (COMPUNIT_OBJFILE (cust),
-					       COMPUNIT_DIRNAME (cust));
+					       COMPUNIT_DIRNAME (cust),
+					       compunit_language (cust));
   buildsym_compunit->compunit_symtab = cust;
 }
 
diff --git a/gdb/buildsym.h b/gdb/buildsym.h
index 60109a0da2e..80ca7da2d37 100644
--- a/gdb/buildsym.h
+++ b/gdb/buildsym.h
@@ -23,6 +23,7 @@ struct objfile;
 struct symbol;
 struct addrmap;
 struct compunit_symtab;
+enum language;
 
 /* This module provides definitions used for creating and adding to
    the symbol table.  These routines are called from various symbol-
@@ -254,7 +255,8 @@ extern record_line_ftype record_line;
 extern struct compunit_symtab *start_symtab (struct objfile *objfile,
 					     const char *name,
 					     const char *comp_dir,
-					     CORE_ADDR start_addr);
+					     CORE_ADDR start_addr,
+					     enum language language);
 
 extern void restart_symtab (struct compunit_symtab *cust,
 			    const char *name, CORE_ADDR start_addr);
diff --git a/gdb/c-lang.c b/gdb/c-lang.c
index f86e26ed5f7..9749935dac5 100644
--- a/gdb/c-lang.c
+++ b/gdb/c-lang.c
@@ -871,6 +871,7 @@ extern const struct language_defn c_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &c_varobj_ops,
   c_get_compile_context,
   c_compute_program,
@@ -1015,6 +1016,7 @@ extern const struct language_defn cplus_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &cplus_varobj_ops,
   NULL,
   NULL,
@@ -1068,6 +1070,7 @@ extern const struct language_defn asm_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
@@ -1121,6 +1124,7 @@ extern const struct language_defn minimal_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/coffread.c b/gdb/coffread.c
index 4b5edf0919e..62b6d7945a8 100644
--- a/gdb/coffread.c
+++ b/gdb/coffread.c
@@ -392,7 +392,9 @@ coff_start_symtab (struct objfile *objfile, const char *name)
 		 NULL,
   /* The start address is irrelevant, since we set
      last_source_start_addr in coff_end_symtab.  */
-		 0);
+		 0,
+  /* Let buildsym.c deduce the language for this symtab.  */
+		 language_unknown);
   record_debugformat ("COFF");
 }
 
diff --git a/gdb/d-lang.c b/gdb/d-lang.c
index e3220d41f6e..2fa429b4bac 100644
--- a/gdb/d-lang.c
+++ b/gdb/d-lang.c
@@ -247,6 +247,7 @@ extern const struct language_defn d_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/dbxread.c b/gdb/dbxread.c
index ce009628094..e843b49e3b0 100644
--- a/gdb/dbxread.c
+++ b/gdb/dbxread.c
@@ -54,7 +54,6 @@
 #include "cp-support.h"
 #include "psympriv.h"
 #include "block.h"
-
 #include "aout/aout64.h"
 #include "aout/stab_gnu.h"	/* We always use GNU stabs, not
 				   native, now.  */
@@ -92,6 +91,7 @@ struct symloc
     int symbol_offset;
     int string_offset;
     int file_string_offset;
+    enum language pst_language;
   };
 
 #define LDSYMOFF(p) (((struct symloc *)((p)->read_symtab_private))->ldsymoff)
@@ -101,6 +101,7 @@ struct symloc
 #define SYMBOL_OFFSET(p) (SYMLOC(p)->symbol_offset)
 #define STRING_OFFSET(p) (SYMLOC(p)->string_offset)
 #define FILE_STRING_OFFSET(p) (SYMLOC(p)->file_string_offset)
+#define PST_LANGUAGE(p) (SYMLOC(p)->pst_language)
 
 
 /* The objfile we are currently reading.  */
@@ -2016,6 +2017,7 @@ start_psymtab (struct objfile *objfile, const char *filename, CORE_ADDR textlow,
 
   /* Deduce the source language from the filename for this psymtab.  */
   psymtab_language = deduce_language_from_filename (filename);
+  PST_LANGUAGE (result) = psymtab_language;
 
   return result;
 }
@@ -2402,7 +2404,8 @@ read_ofile_symtab (struct objfile *objfile, struct partial_symtab *pst)
 		 positive offsets.  */
 	    nlist.n_value = (nlist.n_value ^ 0x80000000) - 0x80000000;
 	  process_one_symbol (type, nlist.n_desc, nlist.n_value,
-			      namestring, section_offsets, objfile);
+			      namestring, section_offsets, objfile,
+			      PST_LANGUAGE (pst));
 	}
       /* We skip checking for a new .o or -l file; that should never
          happen in this routine.  */
@@ -2497,12 +2500,14 @@ cp_set_block_scope (const struct symbol *symbol,
    the pst->section_offsets.  All symbols that refer to memory
    locations need to be offset by these amounts.
    OBJFILE is the object file from which we are reading symbols.  It
-   is used in end_symtab.  */
+   is used in end_symtab.
+   LANGUAGE is the language of the symtab.
+*/
 
 void
 process_one_symbol (int type, int desc, CORE_ADDR valu, const char *name,
 		    const struct section_offsets *section_offsets,
-		    struct objfile *objfile)
+		    struct objfile *objfile, enum language language)
 {
   struct gdbarch *gdbarch = get_objfile_arch (objfile);
   struct context_stack *newobj;
@@ -2716,7 +2721,7 @@ process_one_symbol (int type, int desc, CORE_ADDR valu, const char *name,
       function_start_offset = 0;
 
       start_stabs ();
-      start_symtab (objfile, name, NULL, valu);
+      start_symtab (objfile, name, NULL, valu, language);
       record_debugformat ("stabs");
       break;
 
diff --git a/gdb/dictionary.c b/gdb/dictionary.c
index b2cfca28ab0..1ffa4f32180 100644
--- a/gdb/dictionary.c
+++ b/gdb/dictionary.c
@@ -165,6 +165,7 @@ struct dictionary_linear_expandable
 
 struct dictionary
 {
+  const struct language_defn *language;
   const struct dict_vector *vector;
   union
   {
@@ -179,6 +180,7 @@ struct dictionary
 /* Accessor macros.  */
 
 #define DICT_VECTOR(d)			(d)->vector
+#define DICT_LANGUAGE(d)                (d)->language
 
 /* These can be used for DICT_HASHED_EXPANDABLE, too.  */
 
@@ -245,8 +247,6 @@ static struct symbol *iter_match_next_hashed (const char *name,
 					      symbol_compare_ftype *compare,
 					      struct dict_iterator *iterator);
 
-static unsigned int dict_hash (const char *string);
-
 /* Functions only for DICT_HASHED.  */
 
 static int size_hashed (const struct dictionary *dict);
@@ -348,12 +348,11 @@ static void expand_hashtable (struct dictionary *dict);
 
 /* The creation functions.  */
 
-/* Create a dictionary implemented via a fixed-size hashtable.  All
-   memory it uses is allocated on OBSTACK; the environment is
-   initialized from SYMBOL_LIST.  */
+/* See dictionary.h.  */
 
 struct dictionary *
 dict_create_hashed (struct obstack *obstack,
+		    enum language language,
 		    const struct pending *symbol_list)
 {
   struct dictionary *retval;
@@ -363,6 +362,7 @@ dict_create_hashed (struct obstack *obstack,
 
   retval = XOBNEW (obstack, struct dictionary);
   DICT_VECTOR (retval) = &dict_hashed_vector;
+  DICT_LANGUAGE (retval) = language_def (language);
 
   /* Calculate the number of symbols, and allocate space for them.  */
   for (list_counter = symbol_list;
@@ -391,17 +391,15 @@ dict_create_hashed (struct obstack *obstack,
   return retval;
 }
 
-/* Create a dictionary implemented via a hashtable that grows as
-   necessary.  The dictionary is initially empty; to add symbols to
-   it, call dict_add_symbol().  Call dict_free() when you're done with
-   it.  */
+/* See dictionary.h.  */
 
 extern struct dictionary *
-dict_create_hashed_expandable (void)
+dict_create_hashed_expandable (enum language language)
 {
   struct dictionary *retval = XNEW (struct dictionary);
 
   DICT_VECTOR (retval) = &dict_hashed_expandable_vector;
+  DICT_LANGUAGE (retval) = language_def (language);
   DICT_HASHED_NBUCKETS (retval) = DICT_EXPANDABLE_INITIAL_CAPACITY;
   DICT_HASHED_BUCKETS (retval) = XCNEWVEC (struct symbol *,
 					   DICT_EXPANDABLE_INITIAL_CAPACITY);
@@ -410,13 +408,11 @@ dict_create_hashed_expandable (void)
   return retval;
 }
 
-/* Create a dictionary implemented via a fixed-size array.  All memory
-   it uses is allocated on OBSTACK; the environment is initialized
-   from the SYMBOL_LIST.  The symbols are ordered in the same order
-   that they're found in SYMBOL_LIST.  */
+/* See dictionary.h.  */
 
 struct dictionary *
 dict_create_linear (struct obstack *obstack,
+		    enum language language,
 		    const struct pending *symbol_list)
 {
   struct dictionary *retval;
@@ -426,6 +422,7 @@ dict_create_linear (struct obstack *obstack,
 
   retval = XOBNEW (obstack, struct dictionary);
   DICT_VECTOR (retval) = &dict_linear_vector;
+  DICT_LANGUAGE (retval) = language_def (language);
 
   /* Calculate the number of symbols, and allocate space for them.  */
   for (list_counter = symbol_list;
@@ -455,17 +452,15 @@ dict_create_linear (struct obstack *obstack,
   return retval;
 }
 
-/* Create a dictionary implemented via an array that grows as
-   necessary.  The dictionary is initially empty; to add symbols to
-   it, call dict_add_symbol().  Call dict_free() when you're done with
-   it.  */
+/* See dictionary.h.  */
 
 struct dictionary *
-dict_create_linear_expandable (void)
+dict_create_linear_expandable (enum language language)
 {
   struct dictionary *retval = XNEW (struct dictionary);
 
   DICT_VECTOR (retval) = &dict_linear_expandable_vector;
+  DICT_LANGUAGE (retval) = language_def (language);
   DICT_LINEAR_NSYMS (retval) = 0;
   DICT_LINEAR_EXPANDABLE_CAPACITY (retval) = DICT_EXPANDABLE_INITIAL_CAPACITY;
   DICT_LINEAR_SYMS (retval)
@@ -638,7 +633,9 @@ iter_match_first_hashed (const struct dictionary *dict, const char *name,
 			 symbol_compare_ftype *compare,
 			 struct dict_iterator *iterator)
 {
-  unsigned int hash_index = dict_hash (name) % DICT_HASHED_NBUCKETS (dict);
+  unsigned int hash_index
+    = (search_name_hash (DICT_LANGUAGE (dict)->la_language, name)
+       % DICT_HASHED_NBUCKETS (dict));
   struct symbol *sym;
 
   DICT_ITERATOR_DICT (iterator) = dict;
@@ -689,10 +686,15 @@ insert_symbol_hashed (struct dictionary *dict,
 		      struct symbol *sym)
 {
   unsigned int hash_index;
+  unsigned int hash;
   struct symbol **buckets = DICT_HASHED_BUCKETS (dict);
 
-  hash_index = 
-    dict_hash (SYMBOL_SEARCH_NAME (sym)) % DICT_HASHED_NBUCKETS (dict);
+  /* We don't want to insert a symbol into a dictionary of a different
+     language.  The two may not use the same hashing algorithm.  */
+  gdb_assert (SYMBOL_LANGUAGE (sym) == DICT_LANGUAGE (dict)->la_language);
+
+  hash = search_name_hash (SYMBOL_LANGUAGE (sym), SYMBOL_SEARCH_NAME (sym));
+  hash_index = hash % DICT_HASHED_NBUCKETS (dict);
   sym->hash_next = buckets[hash_index];
   buckets[hash_index] = sym;
 }
@@ -765,13 +767,10 @@ expand_hashtable (struct dictionary *dict)
   xfree (old_buckets);
 }
 
-/* Produce an unsigned hash value from STRING0 that is consistent
-   with strcmp_iw, strcmp, and, at least on Ada symbols, wild_match.
-   That is, two identifiers equivalent according to any of those three
-   comparison operators hash to the same value.  */
+/* See dictionary.h.  */
 
-static unsigned int
-dict_hash (const char *string0)
+unsigned int
+default_search_name_hash (const char *string0)
 {
   /* The Ada-encoded version of a name P1.P2...Pn has either the form
      P1__P2__...Pn<suffix> or _ada_P1__P2__...Pn<suffix> (where the Pi
diff --git a/gdb/dictionary.h b/gdb/dictionary.h
index 4f4f160b931..e4a9315be8c 100644
--- a/gdb/dictionary.h
+++ b/gdb/dictionary.h
@@ -35,42 +35,46 @@ struct dictionary;
 struct symbol;
 struct obstack;
 struct pending;
-
+struct language_defn;
 
 /* The creation functions for various implementations of
    dictionaries.  */
 
-/* Create a dictionary implemented via a fixed-size hashtable.  All
-   memory it uses is allocated on OBSTACK; the environment is
-   initialized from SYMBOL_LIST.  */
+/* Create a dictionary of symbols of language LANGUAGE implemented via
+   a fixed-size hashtable.  All memory it uses is allocated on
+   OBSTACK; the environment is initialized from SYMBOL_LIST.  */
 
 extern struct dictionary *dict_create_hashed (struct obstack *obstack,
+					      enum language language,
 					      const struct pending
 					      *symbol_list);
 
-/* Create a dictionary implemented via a hashtable that grows as
-   necessary.  The dictionary is initially empty; to add symbols to
-   it, call dict_add_symbol().  Call dict_free() when you're done with
-   it.  */
+/* Create a dictionary of symbols of language LANGUAGE, implemented
+   via a hashtable that grows as necessary.  The dictionary is
+   initially empty; to add symbols to it, call dict_add_symbol().
+   Call dict_free() when you're done with it.  */
 
-extern struct dictionary *dict_create_hashed_expandable (void);
+extern struct dictionary *
+  dict_create_hashed_expandable (enum language language);
 
-/* Create a dictionary implemented via a fixed-size array.  All memory
-   it uses is allocated on OBSTACK; the environment is initialized
-   from the SYMBOL_LIST.  The symbols are ordered in the same order
-   that they're found in SYMBOL_LIST.  */
+/* Create a dictionary of symbols of language LANGUAGE, implemented
+   via a fixed-size array.  All memory it uses is allocated on
+   OBSTACK; the environment is initialized from the SYMBOL_LIST.  The
+   symbols are ordered in the same order that they're found in
+   SYMBOL_LIST.  */
 
 extern struct dictionary *dict_create_linear (struct obstack *obstack,
+					      enum language language,
 					      const struct pending
 					      *symbol_list);
 
-/* Create a dictionary implemented via an array that grows as
-   necessary.  The dictionary is initially empty; to add symbols to
-   it, call dict_add_symbol().  Call dict_free() when you're done with
-   it.  */
-
-extern struct dictionary *dict_create_linear_expandable (void);
+/* Create a dictionary of symbols of language LANGUAGE, implemented
+   via an array that grows as necessary.  The dictionary is initially
+   empty; to add symbols to it, call dict_add_symbol().  Call
+   dict_free() when you're done with it.  */
 
+extern struct dictionary *
+  dict_create_linear_expandable (enum language language);
 
 /* The functions providing the interface to dictionaries.  Note that
    the most common parts of the interface, namely symbol lookup, are
diff --git a/gdb/dwarf2read.c b/gdb/dwarf2read.c
index f27d9b96afe..9da866709ad 100644
--- a/gdb/dwarf2read.c
+++ b/gdb/dwarf2read.c
@@ -18929,7 +18929,7 @@ dwarf2_start_symtab (struct dwarf2_cu *cu,
 		     const char *name, const char *comp_dir, CORE_ADDR low_pc)
 {
   struct compunit_symtab *cust
-    = start_symtab (cu->objfile, name, comp_dir, low_pc);
+    = start_symtab (cu->objfile, name, comp_dir, low_pc, cu->language);
 
   record_debugformat ("DWARF 2");
   record_producer (cu->producer);
diff --git a/gdb/f-lang.c b/gdb/f-lang.c
index 073d5291f74..0d78e5a5792 100644
--- a/gdb/f-lang.c
+++ b/gdb/f-lang.c
@@ -291,6 +291,7 @@ extern const struct language_defn f_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/go-lang.c b/gdb/go-lang.c
index f66535ee61e..87ad0631bf2 100644
--- a/gdb/go-lang.c
+++ b/gdb/go-lang.c
@@ -608,6 +608,7 @@ extern const struct language_defn go_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/jit.c b/gdb/jit.c
index 556bcb67499..65d8096dfbd 100644
--- a/gdb/jit.c
+++ b/gdb/jit.c
@@ -651,12 +651,14 @@ finalize_symtab (struct gdb_symtab *stab, struct objfile *objfile)
   size_t blockvector_size;
   CORE_ADDR begin, end;
   struct blockvector *bv;
+  enum language language;
 
   actual_nblocks = FIRST_LOCAL_BLOCK + stab->nblocks;
 
   cust = allocate_compunit_symtab (objfile, stab->file_name);
   allocate_symtab (cust, stab->file_name);
   add_compunit_symtab_to_objfile (cust);
+  language = compunit_language (cust);
 
   /* JIT compilers compile in memory.  */
   COMPUNIT_DIRNAME (cust) = NULL;
@@ -701,7 +703,7 @@ finalize_symtab (struct gdb_symtab *stab, struct objfile *objfile)
 					   "void");
 
       BLOCK_DICT (new_block) = dict_create_linear (&objfile->objfile_obstack,
-                                                   NULL);
+						   language, NULL);
       /* The address range.  */
       BLOCK_START (new_block) = (CORE_ADDR) gdb_block_iter->begin;
       BLOCK_END (new_block) = (CORE_ADDR) gdb_block_iter->end;
@@ -739,7 +741,7 @@ finalize_symtab (struct gdb_symtab *stab, struct objfile *objfile)
 		   ? allocate_global_block (&objfile->objfile_obstack)
 		   : allocate_block (&objfile->objfile_obstack));
       BLOCK_DICT (new_block) = dict_create_linear (&objfile->objfile_obstack,
-                                                   NULL);
+						   language, NULL);
       BLOCK_SUPERBLOCK (new_block) = block_iter;
       block_iter = new_block;
 
diff --git a/gdb/language.c b/gdb/language.c
index ecdf431743f..9c927042a7a 100644
--- a/gdb/language.c
+++ b/gdb/language.c
@@ -837,6 +837,7 @@ const struct language_defn unknown_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
@@ -887,6 +888,7 @@ const struct language_defn auto_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/language.h b/gdb/language.h
index d4ca900834d..64ccfccdab6 100644
--- a/gdb/language.h
+++ b/gdb/language.h
@@ -392,6 +392,11 @@ struct language_defn
       (const struct block *block, const char *name, domain_enum domain,
        gdb::function_view<symbol_found_callback_ftype> callback);
 
+    /* Hash the given symbol search name.  Use
+       default_search_name_hash if no special treatment is
+       required.  */
+    unsigned int (*la_search_name_hash) (const char *name);
+
     /* Various operations on varobj.  */
     const struct lang_varobj_ops *la_varobj_ops;
 
@@ -611,6 +616,14 @@ void default_print_typedef (struct type *type, struct symbol *new_symbol,
 void default_get_string (struct value *value, gdb_byte **buffer, int *length,
 			 struct type **char_type, const char **charset);
 
+/* Default name hashing function.  */
+
+/* Produce an unsigned hash value from SEARCH_NAME that is consistent
+   with strcmp_iw, strcmp, and, at least on Ada symbols, wild_match.
+   That is, two identifiers equivalent according to any of those three
+   comparison operators hash to the same value.  */
+extern unsigned int default_search_name_hash (const char *search_name);
+
 void c_get_string (struct value *value, gdb_byte **buffer, int *length,
 		   struct type **char_type, const char **charset);
 
diff --git a/gdb/m2-lang.c b/gdb/m2-lang.c
index ddd50af54cb..4170ae92c26 100644
--- a/gdb/m2-lang.c
+++ b/gdb/m2-lang.c
@@ -395,6 +395,7 @@ extern const struct language_defn m2_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/mdebugread.c b/gdb/mdebugread.c
index 3f53e1a6853..debf46dc616 100644
--- a/gdb/mdebugread.c
+++ b/gdb/mdebugread.c
@@ -234,7 +234,7 @@ static struct type *new_type (char *);
 
 enum block_type { FUNCTION_BLOCK, NON_FUNCTION_BLOCK };
 
-static struct block *new_block (enum block_type);
+static struct block *new_block (enum block_type, enum language);
 
 static struct compunit_symtab *new_symtab (const char *, int, struct objfile *);
 
@@ -809,7 +809,7 @@ parse_symbol (SYMR *sh, union aux_ext *ax, char *ext_sh, int bigend,
 	TYPE_PROTOTYPED (SYMBOL_TYPE (s)) = 1;
 
       /* Create and enter a new lexical context.  */
-      b = new_block (FUNCTION_BLOCK);
+      b = new_block (FUNCTION_BLOCK, SYMBOL_LANGUAGE (s));
       SYMBOL_BLOCK_VALUE (s) = b;
       BLOCK_FUNCTION (b) = s;
       BLOCK_START (b) = BLOCK_END (b) = sh->value;
@@ -1142,7 +1142,7 @@ parse_symbol (SYMR *sh, union aux_ext *ax, char *ext_sh, int bigend,
 	}
 
       top_stack->blocktype = stBlock;
-      b = new_block (NON_FUNCTION_BLOCK);
+      b = new_block (NON_FUNCTION_BLOCK, psymtab_language);
       BLOCK_START (b) = sh->value + top_stack->procadr;
       BLOCK_SUPERBLOCK (b) = top_stack->cur_block;
       top_stack->cur_block = b;
@@ -4023,6 +4023,7 @@ psymtab_to_symtab_1 (struct objfile *objfile,
 	  if (ECOFF_IS_STAB (&sh) || (name[0] == '#'))
 	    {
 	      int type_code = ECOFF_UNMARK_STAB (sh.index);
+	      enum language language = PST_PRIVATE (pst)->pst_language;
 
 	      /* We should never get non N_STAB symbols here, but they
 	         should be harmless, so keep process_one_symbol from
@@ -4050,14 +4051,14 @@ psymtab_to_symtab_1 (struct objfile *objfile,
 		    {
 		      last_symtab_ended = 0;
 		      process_one_symbol (type_code, 0, valu, name,
-					  section_offsets, objfile);
+					  section_offsets, objfile, language);
 		    }
 		}
 	      /* Similarly a hack.  */
 	      else if (name[0] == '#')
 		{
 		  process_one_symbol (N_SLINE, 0, valu, name,
-				      section_offsets, objfile);
+				      section_offsets, objfile, language);
 		}
 	      if (type_code == N_FUN)
 		{
@@ -4718,16 +4719,18 @@ new_symtab (const char *name, int maxlines, struct objfile *objfile)
   struct compunit_symtab *cust = allocate_compunit_symtab (objfile, name);
   struct symtab *symtab;
   struct blockvector *bv;
+  enum language lang;
 
   add_compunit_symtab_to_objfile (cust);
   symtab = allocate_symtab (cust, name);
 
   SYMTAB_LINETABLE (symtab) = new_linetable (maxlines);
+  lang = compunit_language (cust);
 
   /* All symtabs must have at least two blocks.  */
   bv = new_bvect (2);
-  BLOCKVECTOR_BLOCK (bv, GLOBAL_BLOCK) = new_block (NON_FUNCTION_BLOCK);
-  BLOCKVECTOR_BLOCK (bv, STATIC_BLOCK) = new_block (NON_FUNCTION_BLOCK);
+  BLOCKVECTOR_BLOCK (bv, GLOBAL_BLOCK) = new_block (NON_FUNCTION_BLOCK, lang);
+  BLOCKVECTOR_BLOCK (bv, STATIC_BLOCK) = new_block (NON_FUNCTION_BLOCK, lang);
   BLOCK_SUPERBLOCK (BLOCKVECTOR_BLOCK (bv, STATIC_BLOCK)) =
     BLOCKVECTOR_BLOCK (bv, GLOBAL_BLOCK);
   COMPUNIT_BLOCKVECTOR (cust) = bv;
@@ -4809,13 +4812,13 @@ new_bvect (int nblocks)
   return bv;
 }
 
-/* Allocate and zero a new block, and set its BLOCK_DICT.  If function
-   is non-zero, assume the block is associated to a function, and make
-   sure that the symbols are stored linearly; otherwise, store them
-   hashed.  */
+/* Allocate and zero a new block of language LANGUAGE, and set its
+   BLOCK_DICT.  If function is non-zero, assume the block is
+   associated to a function, and make sure that the symbols are stored
+   linearly; otherwise, store them hashed.  */
 
 static struct block *
-new_block (enum block_type type)
+new_block (enum block_type type, enum language language)
 {
   /* FIXME: carlton/2003-09-11: This should use allocate_block to
      allocate the block.  Which, in turn, suggests that the block
@@ -4823,9 +4826,9 @@ new_block (enum block_type type)
   struct block *retval = XCNEW (struct block);
 
   if (type == FUNCTION_BLOCK)
-    BLOCK_DICT (retval) = dict_create_linear_expandable ();
+    BLOCK_DICT (retval) = dict_create_linear_expandable (language);
   else
-    BLOCK_DICT (retval) = dict_create_hashed_expandable ();
+    BLOCK_DICT (retval) = dict_create_hashed_expandable (language);
 
   return retval;
 }
diff --git a/gdb/objc-lang.c b/gdb/objc-lang.c
index 0423832d5f2..804a486c6cc 100644
--- a/gdb/objc-lang.c
+++ b/gdb/objc-lang.c
@@ -407,6 +407,7 @@ extern const struct language_defn objc_language_defn = {
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/opencl-lang.c b/gdb/opencl-lang.c
index 6a7232733ad..ffd4c926de1 100644
--- a/gdb/opencl-lang.c
+++ b/gdb/opencl-lang.c
@@ -1083,6 +1083,7 @@ extern const struct language_defn opencl_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/p-lang.c b/gdb/p-lang.c
index 439a3772cbf..2dca923a377 100644
--- a/gdb/p-lang.c
+++ b/gdb/p-lang.c
@@ -456,6 +456,7 @@ extern const struct language_defn pascal_language_defn =
   c_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/rust-lang.c b/gdb/rust-lang.c
index 261ddb1a109..466eb20ab14 100644
--- a/gdb/rust-lang.c
+++ b/gdb/rust-lang.c
@@ -2252,6 +2252,7 @@ extern const struct language_defn rust_language_defn =
   rust_watch_location_expression,
   NULL,				/* la_get_symbol_name_cmp */
   iterate_over_symbols,
+  default_search_name_hash,
   &default_varobj_ops,
   NULL,
   NULL,
diff --git a/gdb/stabsread.h b/gdb/stabsread.h
index b37be1a0421..b803cf9ac7c 100644
--- a/gdb/stabsread.h
+++ b/gdb/stabsread.h
@@ -17,6 +17,7 @@
    along with this program.  If not, see <http://www.gnu.org/licenses/>.  */
 
 struct objfile;
+enum language;
 
 /* Definitions, prototypes, etc for stabs debugging format support
    functions.
@@ -169,7 +170,7 @@ extern struct partial_symtab *dbx_end_psymtab
 
 extern void process_one_symbol (int, int, CORE_ADDR, const char *,
 				const struct section_offsets *,
-				struct objfile *);
+				struct objfile *, enum language);
 
 extern void elfstab_build_psymtabs (struct objfile *objfile,
 				    asection *stabsect,
diff --git a/gdb/symtab.c b/gdb/symtab.c
index 16a6b2eb6f3..035a95833a2 100644
--- a/gdb/symtab.c
+++ b/gdb/symtab.c
@@ -1795,6 +1795,14 @@ demangle_for_lookup (const char *name, enum language lang,
   return name;
 }
 
+/* See symtab.h.  */
+
+unsigned int
+search_name_hash (enum language language, const char *search_name)
+{
+  return language_def (language)->la_search_name_hash (search_name);
+}
+
 /* See symtab.h.
 
    This function (or rather its subordinates) have a bunch of loops and
diff --git a/gdb/symtab.h b/gdb/symtab.h
index cd6dbaea480..d5c929d1b50 100644
--- a/gdb/symtab.h
+++ b/gdb/symtab.h
@@ -277,6 +277,11 @@ extern const char *symbol_search_name (const struct general_symbol_info *);
 #define SYMBOL_MATCHES_SEARCH_NAME(symbol, name)			\
   (strcmp_iw (SYMBOL_SEARCH_NAME (symbol), (name)) == 0)
 
+/* Compute the hash of the given symbol search name of a symbol of
+   language LANGUAGE.  */
+extern unsigned int search_name_hash (enum language language,
+				      const char *search_name);
+
 /* Classification types for a minimal symbol.  These should be taken as
    "advisory only", since if gdb can't easily figure out a
    classification it simply selects mst_unknown.  It may also have to
diff --git a/gdb/xcoffread.c b/gdb/xcoffread.c
index ea11b3f966c..73c2f37664b 100644
--- a/gdb/xcoffread.c
+++ b/gdb/xcoffread.c
@@ -1044,7 +1044,8 @@ read_xcoff_symtab (struct objfile *objfile, struct partial_symtab *pst)
   last_csect_name = 0;
 
   start_stabs ();
-  start_symtab (objfile, filestring, (char *) NULL, file_start_addr);
+  start_symtab (objfile, filestring, (char *) NULL, file_start_addr,
+		language_unknown);
   record_debugformat (debugfmt);
   symnum = ((struct symloc *) pst->read_symtab_private)->first_symnum;
   max_symnum =
@@ -1137,7 +1138,8 @@ read_xcoff_symtab (struct objfile *objfile, struct partial_symtab *pst)
 	    }
 
 	  start_stabs ();
-	  start_symtab (objfile, "_globals_", (char *) NULL, (CORE_ADDR) 0);
+	  start_symtab (objfile, "_globals_", (char *) NULL, (CORE_ADDR) 0,
+			language_unknown);
 	  record_debugformat (debugfmt);
 	  cur_src_end_addr = first_object_file_end;
 	  /* Done with all files, everything from here on is globals.  */
@@ -1227,7 +1229,7 @@ read_xcoff_symtab (struct objfile *objfile, struct partial_symtab *pst)
 			  /* Give all csects for this source file the same
 			     name.  */
 			  start_symtab (objfile, filestring, NULL,
-					(CORE_ADDR) 0);
+					(CORE_ADDR) 0, language_unknown);
 			  record_debugformat (debugfmt);
 			}
 
@@ -1347,7 +1349,8 @@ read_xcoff_symtab (struct objfile *objfile, struct partial_symtab *pst)
 	    filestring = cs->c_name;
 
 	  start_stabs ();
-	  start_symtab (objfile, filestring, (char *) NULL, (CORE_ADDR) 0);
+	  start_symtab (objfile, filestring, (char *) NULL, (CORE_ADDR) 0,
+			language_unknown);
 	  record_debugformat (debugfmt);
 	  last_csect_name = 0;