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 <tenderlove@ruby-lang.org>
Co-Authored-By: Eileen M. Uchitelle <eileencodes@gmail.com>
Co-Authored-By: John Hawthorn <john@hawthorn.email>

1 files changed, 44 insertions, 2 deletions

diff --git a/object.c b/object.c
index 2328b20757..213f9760be 100644
--- a/object.c
+++ b/object.c
@@ -39,6 +39,7 @@
 #include "ruby/util.h"
 #include "ruby/assert.h"
 #include "builtin.h"
+#include "shape.h"
 
 /*!
  * \addtogroup object
@@ -271,9 +272,33 @@ rb_obj_copy_ivar(VALUE dest, VALUE obj)
     VALUE *src_buf = ROBJECT_IVPTR(obj);
     uint32_t dest_len = ROBJECT_NUMIV(dest);
     uint32_t src_len = ROBJECT_NUMIV(obj);
-    uint32_t len = dest_len < src_len ? dest_len : src_len;
+    uint32_t max_len = dest_len < src_len ? src_len : dest_len;
 
-    MEMCPY(dest_buf, src_buf, VALUE, len);
+    rb_ensure_iv_list_size(dest, dest_len, max_len);
+
+    dest_len = ROBJECT_NUMIV(dest);
+    uint32_t min_len = dest_len > src_len ? src_len : dest_len;
+
+    if (RBASIC(obj)->flags & ROBJECT_EMBED) {
+        src_buf = ROBJECT(obj)->as.ary;
+
+        // embedded -> embedded
+        if (RBASIC(dest)->flags & ROBJECT_EMBED) {
+            dest_buf = ROBJECT(dest)->as.ary;
+        }
+        // embedded -> extended
+        else {
+            dest_buf = ROBJECT(dest)->as.heap.ivptr;
+        }
+    }
+    // extended -> extended
+    else {
+        RUBY_ASSERT(!(RBASIC(dest)->flags & ROBJECT_EMBED));
+        dest_buf = ROBJECT(dest)->as.heap.ivptr;
+        src_buf = ROBJECT(obj)->as.heap.ivptr;
+    }
+
+    MEMCPY(dest_buf, src_buf, VALUE, min_len);
 }
 
 static void
@@ -283,10 +308,23 @@ init_copy(VALUE dest, VALUE obj)
         rb_raise(rb_eTypeError, "[bug] frozen object (%s) allocated", rb_obj_classname(dest));
     }
     RBASIC(dest)->flags &= ~(T_MASK|FL_EXIVAR);
+    // Copies the shape id from obj to dest
     RBASIC(dest)->flags |= RBASIC(obj)->flags & (T_MASK|FL_EXIVAR);
     rb_copy_wb_protected_attribute(dest, obj);
     rb_copy_generic_ivar(dest, obj);
     rb_gc_copy_finalizer(dest, obj);
+
+    rb_shape_t *shape_to_set = rb_shape_get_shape(obj);
+
+    // If the object is frozen, the "dup"'d object will *not* be frozen,
+    // so we need to copy the frozen shape's parent to the new object.
+    if (rb_shape_frozen_shape_p(shape_to_set)) {
+        shape_to_set = shape_to_set->parent;
+    }
+
+    // shape ids are different
+    rb_shape_set_shape(dest, shape_to_set);
+
     if (RB_TYPE_P(obj, T_OBJECT)) {
         rb_obj_copy_ivar(dest, obj);
     }
@@ -392,6 +430,9 @@ mutable_obj_clone(VALUE obj, VALUE kwfreeze)
       case Qnil:
         rb_funcall(clone, id_init_clone, 1, obj);
         RBASIC(clone)->flags |= RBASIC(obj)->flags & FL_FREEZE;
+        if (RB_OBJ_FROZEN(obj)) {
+            rb_shape_transition_shape_frozen(clone);
+        }
         break;
       case Qtrue:
         {
@@ -407,6 +448,7 @@ mutable_obj_clone(VALUE obj, VALUE kwfreeze)
         argv[1] = freeze_true_hash;
         rb_funcallv_kw(clone, id_init_clone, 2, argv, RB_PASS_KEYWORDS);
         RBASIC(clone)->flags |= FL_FREEZE;
+        rb_shape_transition_shape_frozen(clone);
         break;
         }
       case Qfalse: