Lazily create singletons on instance_{exec,eval} (#5146)

* Lazily create singletons on instance_{exec,eval}

Previously when instance_exec or instance_eval was called on an object,
that object would be given a singleton class so that method
definitions inside the block would be added to the object rather than
its class.

This commit aims to improve performance by delaying the creation of the
singleton class unless/until one is needed for method definition. Most
of the time instance_eval is used without any method definition.

This was implemented by adding a flag to the cref indicating that it
represents a singleton of the object rather than a class itself. In this
case CREF_CLASS returns the object's existing class, but in cases that
we are defining a method (either via definemethod or
VM_SPECIAL_OBJECT_CBASE which is used for undef and alias).

This also happens to fix what I believe is a bug. Previously
instance_eval behaved differently with regards to constant access for
true/false/nil than for all other objects. I don't think this was
intentional.

    String::Foo = "foo"
    "".instance_eval("Foo")   # => "foo"
    Integer::Foo = "foo"
    123.instance_eval("Foo")  # => "foo"
    TrueClass::Foo = "foo"
    true.instance_eval("Foo") # NameError: uninitialized constant Foo

This also slightly changes the error message when trying to define a method
through instance_eval on an object which can't have a singleton class.

Before:

    $ ruby -e '123.instance_eval { def foo; end }'
    -e:1:in `block in <main>': no class/module to add method (TypeError)

After:

    $ ./ruby -e '123.instance_eval { def foo; end }'
    -e:1:in `block in <main>': can't define singleton (TypeError)

IMO this error is a small improvement on the original and better matches
the (both old and new) message when definging a method using `def self.`

    $ ruby -e '123.instance_eval{ def self.foo; end }'
    -e:1:in `block in <main>': can't define singleton (TypeError)

Co-authored-by: Matthew Draper <[email protected]>

* Remove "under" argument from yield_under

* Move CREF_SINGLETON_SET into vm_cref_new

* Simplify vm_get_const_base

* Fix leaf VM_SPECIAL_OBJECT_CONST_BASE

Co-authored-by: Matthew Draper <[email protected]>

1 files changed, 20 insertions, 37 deletions

diff --git a/vm_eval.c b/vm_eval.c
index 73739fc3a5..0abb4644f9 100644
--- a/vm_eval.c
+++ b/vm_eval.c
@@ -1860,7 +1860,7 @@ eval_string_wrap_protect(VALUE data)
 {
     const struct eval_string_wrap_arg *const arg = (struct eval_string_wrap_arg*)data;
     rb_cref_t *cref = rb_vm_cref_new_toplevel();
-    cref->klass = arg->klass;
+    cref->klass_or_self = arg->klass;
     return eval_string_with_cref(arg->top_self, rb_str_new_cstr(arg->str), cref, rb_str_new_cstr("eval"), 1);
 }
 
@@ -1922,7 +1922,7 @@ rb_eval_cmd_kw(VALUE cmd, VALUE arg, int kw_splat)
 /* block eval under the class/module context */
 
 static VALUE
-yield_under(VALUE under, VALUE self, int argc, const VALUE *argv, int kw_splat)
+yield_under(VALUE self, int singleton, int argc, const VALUE *argv, int kw_splat)
 {
     rb_execution_context_t *ec = GET_EC();
     rb_control_frame_t *cfp = ec->cfp;
@@ -1963,7 +1963,9 @@ yield_under(VALUE under, VALUE self, int argc, const VALUE *argv, int kw_splat)
 	VM_FORCE_WRITE_SPECIAL_CONST(&VM_CF_LEP(ec->cfp)[VM_ENV_DATA_INDEX_SPECVAL], new_block_handler);
     }
 
-    cref = vm_cref_push(ec, under, ep, TRUE);
+    VM_ASSERT(singleton || RB_TYPE_P(self, T_MODULE) || RB_TYPE_P(self, T_CLASS));
+    cref = vm_cref_push(ec, self, ep, TRUE, singleton);
+
     return vm_yield_with_cref(ec, argc, argv, kw_splat, cref, is_lambda);
 }
 
@@ -1981,7 +1983,7 @@ rb_yield_refine_block(VALUE refinement, VALUE refinements)
 	struct rb_captured_block new_captured = *captured;
 	VALUE new_block_handler = VM_BH_FROM_ISEQ_BLOCK(&new_captured);
 	const VALUE *ep = captured->ep;
-	rb_cref_t *cref = vm_cref_push(ec, refinement, ep, TRUE);
+	rb_cref_t *cref = vm_cref_push(ec, refinement, ep, TRUE, FALSE);
 	CREF_REFINEMENTS_SET(cref, refinements);
 	VM_FORCE_WRITE_SPECIAL_CONST(&VM_CF_LEP(ec->cfp)[VM_ENV_DATA_INDEX_SPECVAL], new_block_handler);
 	new_captured.self = refinement;
@@ -1991,19 +1993,20 @@ rb_yield_refine_block(VALUE refinement, VALUE refinements)
 
 /* string eval under the class/module context */
 static VALUE
-eval_under(VALUE under, VALUE self, VALUE src, VALUE file, int line)
+eval_under(VALUE self, int singleton, VALUE src, VALUE file, int line)
 {
-    rb_cref_t *cref = vm_cref_push(GET_EC(), under, NULL, SPECIAL_CONST_P(self) && !NIL_P(under));
+    rb_cref_t *cref = vm_cref_push(GET_EC(), self, NULL, FALSE, singleton);
     SafeStringValue(src);
+
     return eval_string_with_cref(self, src, cref, file, line);
 }
 
 static VALUE
-specific_eval(int argc, const VALUE *argv, VALUE klass, VALUE self, int kw_splat)
+specific_eval(int argc, const VALUE *argv, VALUE self, int singleton, int kw_splat)
 {
     if (rb_block_given_p()) {
 	rb_check_arity(argc, 0, 0);
-        return yield_under(klass, self, 1, &self, kw_splat);
+        return yield_under(self, singleton, 1, &self, kw_splat);
     }
     else {
 	VALUE file = Qundef;
@@ -2019,23 +2022,7 @@ specific_eval(int argc, const VALUE *argv, VALUE klass, VALUE self, int kw_splat
 	    file = argv[1];
 	    if (!NIL_P(file)) StringValue(file);
 	}
-	return eval_under(klass, self, code, file, line);
-    }
-}
-
-static VALUE
-singleton_class_for_eval(VALUE self)
-{
-    if (SPECIAL_CONST_P(self)) {
-	return rb_special_singleton_class(self);
-    }
-    switch (BUILTIN_TYPE(self)) {
-      case T_FLOAT: case T_BIGNUM: case T_SYMBOL:
-	return Qnil;
-      case T_STRING:
-	if (FL_TEST_RAW(self, RSTRING_FSTR)) return Qnil;
-      default:
-	return rb_singleton_class(self);
+	return eval_under(self, singleton, code, file, line);
     }
 }
 
@@ -2075,15 +2062,13 @@ singleton_class_for_eval(VALUE self)
 static VALUE
 rb_obj_instance_eval_internal(int argc, const VALUE *argv, VALUE self)
 {
-    VALUE klass = singleton_class_for_eval(self);
-    return specific_eval(argc, argv, klass, self, RB_PASS_CALLED_KEYWORDS);
+    return specific_eval(argc, argv, self, TRUE, RB_PASS_CALLED_KEYWORDS);
 }
 
 VALUE
 rb_obj_instance_eval(int argc, const VALUE *argv, VALUE self)
 {
-    VALUE klass = singleton_class_for_eval(self);
-    return specific_eval(argc, argv, klass, self, RB_NO_KEYWORDS);
+    return specific_eval(argc, argv, self, TRUE, RB_NO_KEYWORDS);
 }
 
 /*
@@ -2107,15 +2092,13 @@ rb_obj_instance_eval(int argc, const VALUE *argv, VALUE self)
 static VALUE
 rb_obj_instance_exec_internal(int argc, const VALUE *argv, VALUE self)
 {
-    VALUE klass = singleton_class_for_eval(self);
-    return yield_under(klass, self, argc, argv, RB_PASS_CALLED_KEYWORDS);
+    return yield_under(self, TRUE, argc, argv, RB_PASS_CALLED_KEYWORDS);
 }
 
 VALUE
 rb_obj_instance_exec(int argc, const VALUE *argv, VALUE self)
 {
-    VALUE klass = singleton_class_for_eval(self);
-    return yield_under(klass, self, argc, argv, RB_NO_KEYWORDS);
+    return yield_under(self, TRUE, argc, argv, RB_NO_KEYWORDS);
 }
 
 /*
@@ -2148,13 +2131,13 @@ rb_obj_instance_exec(int argc, const VALUE *argv, VALUE self)
 static VALUE
 rb_mod_module_eval_internal(int argc, const VALUE *argv, VALUE mod)
 {
-    return specific_eval(argc, argv, mod, mod, RB_PASS_CALLED_KEYWORDS);
+    return specific_eval(argc, argv, mod, FALSE, RB_PASS_CALLED_KEYWORDS);
 }
 
 VALUE
 rb_mod_module_eval(int argc, const VALUE *argv, VALUE mod)
 {
-    return specific_eval(argc, argv, mod, mod, RB_NO_KEYWORDS);
+    return specific_eval(argc, argv, mod, FALSE, RB_NO_KEYWORDS);
 }
 
 /*
@@ -2182,13 +2165,13 @@ rb_mod_module_eval(int argc, const VALUE *argv, VALUE mod)
 static VALUE
 rb_mod_module_exec_internal(int argc, const VALUE *argv, VALUE mod)
 {
-    return yield_under(mod, mod, argc, argv, RB_PASS_CALLED_KEYWORDS);
+    return yield_under(mod, FALSE, argc, argv, RB_PASS_CALLED_KEYWORDS);
 }
 
 VALUE
 rb_mod_module_exec(int argc, const VALUE *argv, VALUE mod)
 {
-    return yield_under(mod, mod, argc, argv, RB_NO_KEYWORDS);
+    return yield_under(mod, FALSE, argc, argv, RB_NO_KEYWORDS);
 }
 
 /*