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, 12 insertions, 0 deletions

diff --git a/vm.c b/vm.c
index 814f8b6780..75ca12f2a5 100644
--- a/vm.c
+++ b/vm.c
@@ -2206,6 +2206,10 @@ ruby_vm_destruct(rb_vm_t *vm)
 	    st_free_table(vm->frozen_strings);
 	    vm->frozen_strings = 0;
 	}
+	if (vm->tainted_frozen_strings) {
+	    st_free_table(vm->tainted_frozen_strings);
+	    vm->tainted_frozen_strings = 0;
+	}
 	rb_vm_gvl_destroy(vm);
 	if (objspace) {
 	    rb_objspace_free(objspace);
@@ -3142,6 +3146,8 @@ Init_vm_objects(void)
     vm->mark_object_ary = rb_ary_tmp_new(128);
     vm->loading_table = st_init_strtable();
     vm->frozen_strings = st_init_table_with_size(&rb_fstring_hash_type, 1000);
+    vm->tainted_frozen_strings =
+		st_init_table_with_size(&rb_fstring_hash_type, 1000);
 }
 
 /* top self */
@@ -3203,6 +3209,12 @@ rb_vm_fstring_table(void)
     return GET_VM()->frozen_strings;
 }
 
+st_table *
+rb_vm_tfstring_table(void)
+{
+    return GET_VM()->tainted_frozen_strings;
+}
+
 #if VM_COLLECT_USAGE_DETAILS
 
 #define HASH_ASET(h, k, v) rb_hash_aset((h), (st_data_t)(k), (st_data_t)(v))