This commit implements the Object Shapes technique in CRuby.

Object Shapes is used for accessing instance variables and representing the
"frozenness" of objects.  Object instances have a "shape" and the shape
represents some attributes of the object (currently which instance variables are
set and the "frozenness").  Shapes form a tree data structure, and when a new
instance variable is set on an object, that object "transitions" to a new shape
in the shape tree.  Each shape has an ID that is used for caching. The shape
structure is independent of class, so objects of different types can have the
same shape.

For example:

```ruby
class Foo
  def initialize
    # Starts with shape id 0
    @a = 1 # transitions to shape id 1
    @b = 1 # transitions to shape id 2
  end
end

class Bar
  def initialize
    # Starts with shape id 0
    @a = 1 # transitions to shape id 1
    @b = 1 # transitions to shape id 2
  end
end

foo = Foo.new # `foo` has shape id 2
bar = Bar.new # `bar` has shape id 2
```

Both `foo` and `bar` instances have the same shape because they both set
instance variables of the same name in the same order.

This technique can help to improve inline cache hits as well as generate more
efficient machine code in JIT compilers.

This commit also adds some methods for debugging shapes on objects.  See
`RubyVM::Shape` for more details.

For more context on Object Shapes, see [Feature: #18776]

Co-Authored-By: Aaron Patterson <[email protected]>
Co-Authored-By: Eileen M. Uchitelle <[email protected]>
Co-Authored-By: John Hawthorn <[email protected]>

1 files changed, 6 insertions, 5 deletions

diff --git a/internal/class.h b/internal/class.h
index ae680564a6..36635d6eaa 100644
--- a/internal/class.h
+++ b/internal/class.h
@@ -14,6 +14,7 @@
 #include "ruby/internal/stdbool.h"     /* for bool */
 #include "ruby/intern.h"        /* for rb_alloc_func_t */
 #include "ruby/ruby.h"          /* for struct RBasic */
+#include "shape.h"
 
 #ifdef RCLASS_SUPER
 # undef RCLASS_SUPER
@@ -26,9 +27,9 @@ struct rb_subclass_entry {
 };
 
 struct rb_iv_index_tbl_entry {
-    uint32_t index;
-    rb_serial_t class_serial;
-    VALUE class_value;
+    uint32_t idx;
+    shape_id_t source_shape_id;
+    shape_id_t dest_shape_id;
 };
 
 struct rb_cvar_class_tbl_entry {
@@ -38,7 +39,6 @@ struct rb_cvar_class_tbl_entry {
 };
 
 struct rb_classext_struct {
-    struct st_table *iv_index_tbl; // ID -> struct rb_iv_index_tbl_entry
     struct st_table *iv_tbl;
 #if SIZEOF_SERIAL_T == SIZEOF_VALUE /* otherwise m_tbl is in struct RClass */
     struct rb_id_table *m_tbl;
@@ -64,6 +64,8 @@ struct rb_classext_struct {
     const VALUE refined_class;
     rb_alloc_func_t allocator;
     const VALUE includer;
+    uint32_t max_iv_count;
+    uint16_t shape_id;
 };
 
 struct RClass {
@@ -102,7 +104,6 @@ typedef struct rb_classext_struct rb_classext_t;
 #define RCLASS_CALLABLE_M_TBL(c) (RCLASS_EXT(c)->callable_m_tbl)
 #define RCLASS_CC_TBL(c) (RCLASS_EXT(c)->cc_tbl)
 #define RCLASS_CVC_TBL(c) (RCLASS_EXT(c)->cvc_tbl)
-#define RCLASS_IV_INDEX_TBL(c) (RCLASS_EXT(c)->iv_index_tbl)
 #define RCLASS_ORIGIN(c) (RCLASS_EXT(c)->origin_)
 #define RCLASS_REFINED_CLASS(c) (RCLASS_EXT(c)->refined_class)
 #if SIZEOF_SERIAL_T == SIZEOF_VALUE