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

gdb/ChangeLog:
2017-11-08  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.

1 files changed, 17 insertions, 14 deletions

diff --git a/gdb/mdebugread.c b/gdb/mdebugread.c
index 3f53e1a..debf46d 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;
 }