hash: keep fstrings of tainted strings for string keys

The same hash keys may be loaded from tainted data sources
frequently (e.g. parsing headers from socket or loading
YAML data from a file).  If a non-tainted fstring already
exists (because the application expects the hash key),
cache and deduplicate the tainted version in the new
tainted_frozen_strings table.

For non-embedded strings, this also allows sharing with the
underlying malloc-ed data.

* vm_core.h (rb_vm_struct): add tainted_frozen_strings
* vm.c (ruby_vm_destruct): free tainted_frozen_strings
  (Init_vm_objects): initialize tainted_frozen_strings
  (rb_vm_tfstring_table): accessor for tainted_frozen_strings
* internal.h: declare rb_fstring_existing, rb_vm_tfstring_table
* hash.c (fstring_existing_str): remove (moved to string.c)
  (hash_aset_str): use rb_fstring_existing
* string.c (rb_fstring_existing): new, based on fstring_existing_str
  (tainted_fstr_update): new
  (rb_fstring_existing0): new, based on fstring_existing_str
  (rb_tainted_fstring_existing): new, special case for tainted strings
  (rb_str_free): delete from tainted_frozen_strings table
* test/ruby/test_optimization.rb (test_hash_reuse_fstring): new test
  [ruby-core:82012] [Bug #13737]

git-svn-id: svn+ssh://ci.ruby-lang.org/ruby/trunk@59354 b2dd03c8-39d4-4d8f-98ff-823fe69b080e

1 files changed, 1 insertions, 22 deletions

diff --git a/hash.c b/hash.c
index c47f21ee9f..6ae13ba1b4 100644
--- a/hash.c
+++ b/hash.c
@@ -18,7 +18,6 @@
 #include "probes.h"
 #include "id.h"
 #include "symbol.h"
-#include "gc.h"
 
 #ifdef __APPLE__
 # ifdef HAVE_CRT_EXTERNS_H
@@ -1516,33 +1515,13 @@ hash_aset(st_data_t *key, st_data_t *val, struct update_arg *arg, int existing)
     return ST_CONTINUE;
 }
 
-static VALUE
-fstring_existing_str(VALUE str)
-{
-    st_data_t fstr;
-    st_table *tbl = rb_vm_fstring_table();
-
-    if (st_lookup(tbl, str, &fstr)) {
-	if (rb_objspace_garbage_object_p(fstr)) {
-	    return rb_fstring(str);
-	}
-	else {
-	    return (VALUE)fstr;
-	}
-    }
-    else {
-	return Qnil;
-    }
-}
-
 static int
 hash_aset_str(st_data_t *key, st_data_t *val, struct update_arg *arg, int existing)
 {
     if (!existing && !RB_OBJ_FROZEN(*key)) {
 	VALUE k;
 
-	if (!RB_OBJ_TAINTED(*key) &&
-	    (k = fstring_existing_str(*key)) != Qnil) {
+	if ((k = rb_fstring_existing(*key)) != Qnil) {
 	    *key = k;
 	}
 	else {