bpo-45340: Don't create object dictionaries unless actually needed (GH-28802)

* Never change types' cached keys. It could invalidate inline attribute objects.

* Lazily create object dictionaries.

* Update specialization of LOAD/STORE_ATTR.

* Don't update shared keys version for deletion of value.

* Update gdb support to handle instance values.

* Rename SPLIT_KEYS opcodes to INSTANCE_VALUE.

18 files changed, 721 insertions, 400 deletions

diff --git a/Include/cpython/object.h b/Include/cpython/object.h
index 5ae6f36..849d5aa 100644
--- a/Include/cpython/object.h
+++ b/Include/cpython/object.h
@@ -270,6 +270,7 @@ struct _typeobject {
 
     destructor tp_finalize;
     vectorcallfunc tp_vectorcall;
+    Py_ssize_t tp_inline_values_offset;
 };
 
 /* The *real* layout of a type object when allocated on the heap */
diff --git a/Include/internal/pycore_dict.h b/Include/internal/pycore_dict.h
index d37ef71..13cb7cc 100644
--- a/Include/internal/pycore_dict.h
+++ b/Include/internal/pycore_dict.h
@@ -101,6 +101,8 @@ extern uint64_t _pydict_global_version;
 
 #define DICT_NEXT_VERSION() (++_pydict_global_version)
 
+PyObject *_PyObject_MakeDictFromInstanceAttributes(PyObject *obj, PyDictValues *values);
+
 #ifdef __cplusplus
 }
 #endif
diff --git a/Include/internal/pycore_object.h b/Include/internal/pycore_object.h
index 82dddf1..3c126aa 100644
--- a/Include/internal/pycore_object.h
+++ b/Include/internal/pycore_object.h
@@ -181,6 +181,16 @@ extern int _Py_CheckSlotResult(
 extern PyObject* _PyType_AllocNoTrack(PyTypeObject *type, Py_ssize_t nitems);
 
 extern int _PyObject_InitializeDict(PyObject *obj);
+extern int _PyObject_StoreInstanceAttribute(PyObject *obj, PyDictValues *values,
+                                          PyObject *name, PyObject *value);
+PyObject * _PyObject_GetInstanceAttribute(PyObject *obj, PyDictValues *values,
+                                        PyObject *name);
+PyDictValues ** _PyObject_ValuesPointer(PyObject *);
+PyObject ** _PyObject_DictPointer(PyObject *);
+int _PyObject_VisitInstanceAttributes(PyObject *self, visitproc visit, void *arg);
+void _PyObject_ClearInstanceAttributes(PyObject *self);
+void _PyObject_FreeInstanceAttributes(PyObject *self);
+int _PyObject_IsInstanceDictEmpty(PyObject *);
 
 #ifdef __cplusplus
 }
diff --git a/Include/object.h b/Include/object.h
index c3062cb..7f050b8 100644
--- a/Include/object.h
+++ b/Include/object.h
@@ -333,6 +333,7 @@ given type object has a specified feature.
 */
 
 #ifndef Py_LIMITED_API
+
 /* Set if instances of the type object are treated as sequences for pattern matching */
 #define Py_TPFLAGS_SEQUENCE (1 << 5)
 /* Set if instances of the type object are treated as mappings for pattern matching */
diff --git a/Include/opcode.h b/Include/opcode.h
index 8817a4d..15f7226 100644
--- a/Include/opcode.h
+++ b/Include/opcode.h
@@ -147,7 +147,7 @@ extern "C" {
 #define BINARY_SUBSCR_DICT       39
 #define JUMP_ABSOLUTE_QUICK      40
 #define LOAD_ATTR_ADAPTIVE       41
-#define LOAD_ATTR_SPLIT_KEYS     42
+#define LOAD_ATTR_INSTANCE_VALUE  42
 #define LOAD_ATTR_WITH_HINT      43
 #define LOAD_ATTR_SLOT           44
 #define LOAD_ATTR_MODULE         45
@@ -158,15 +158,16 @@ extern "C" {
 #define LOAD_METHOD_CACHED       80
 #define LOAD_METHOD_CLASS        81
 #define LOAD_METHOD_MODULE       87
-#define STORE_ATTR_ADAPTIVE      88
-#define STORE_ATTR_SPLIT_KEYS   120
-#define STORE_ATTR_SLOT         122
-#define STORE_ATTR_WITH_HINT    123
-#define LOAD_FAST__LOAD_FAST    127
-#define STORE_FAST__LOAD_FAST   128
-#define LOAD_FAST__LOAD_CONST   134
-#define LOAD_CONST__LOAD_FAST   140
-#define STORE_FAST__STORE_FAST  143
+#define LOAD_METHOD_NO_DICT      88
+#define STORE_ATTR_ADAPTIVE     120
+#define STORE_ATTR_INSTANCE_VALUE 122
+#define STORE_ATTR_SLOT         123
+#define STORE_ATTR_WITH_HINT    127
+#define LOAD_FAST__LOAD_FAST    128
+#define STORE_FAST__LOAD_FAST   134
+#define LOAD_FAST__LOAD_CONST   140
+#define LOAD_CONST__LOAD_FAST   143
+#define STORE_FAST__STORE_FAST  149
 #define DO_TRACING              255
 #ifdef NEED_OPCODE_JUMP_TABLES
 static uint32_t _PyOpcode_RelativeJump[8] = {
diff --git a/Lib/opcode.py b/Lib/opcode.py
index 5d35674..efd6aef 100644
--- a/Lib/opcode.py
+++ b/Lib/opcode.py
@@ -231,7 +231,7 @@ _specialized_instructions = [
     "BINARY_SUBSCR_DICT",
     "JUMP_ABSOLUTE_QUICK",
     "LOAD_ATTR_ADAPTIVE",
-    "LOAD_ATTR_SPLIT_KEYS",
+    "LOAD_ATTR_INSTANCE_VALUE",
     "LOAD_ATTR_WITH_HINT",
     "LOAD_ATTR_SLOT",
     "LOAD_ATTR_MODULE",
@@ -242,8 +242,9 @@ _specialized_instructions = [
     "LOAD_METHOD_CACHED",
     "LOAD_METHOD_CLASS",
     "LOAD_METHOD_MODULE",
+    "LOAD_METHOD_NO_DICT",
     "STORE_ATTR_ADAPTIVE",
-    "STORE_ATTR_SPLIT_KEYS",
+    "STORE_ATTR_INSTANCE_VALUE",
     "STORE_ATTR_SLOT",
     "STORE_ATTR_WITH_HINT",
     # Super instructions
diff --git a/Lib/test/test_descr.py b/Lib/test/test_descr.py
index af7848c..a5404b3 100644
--- a/Lib/test/test_descr.py
+++ b/Lib/test/test_descr.py
@@ -5500,17 +5500,19 @@ class SharedKeyTests(unittest.TestCase):
         class B(A):
             pass
 
+        #Shrink keys by repeatedly creating instances
+        [(A(), B()) for _ in range(20)]
+
         a, b = A(), B()
         self.assertEqual(sys.getsizeof(vars(a)), sys.getsizeof(vars(b)))
         self.assertLess(sys.getsizeof(vars(a)), sys.getsizeof({"a":1}))
-        # Initial hash table can contain at most 5 elements.
+        # Initial hash table can contain only one or two elements.
         # Set 6 attributes to cause internal resizing.
         a.x, a.y, a.z, a.w, a.v, a.u = range(6)
         self.assertNotEqual(sys.getsizeof(vars(a)), sys.getsizeof(vars(b)))
         a2 = A()
-        self.assertEqual(sys.getsizeof(vars(a)), sys.getsizeof(vars(a2)))
-        self.assertLess(sys.getsizeof(vars(a)), sys.getsizeof({"a":1}))
-        b.u, b.v, b.w, b.t, b.s, b.r = range(6)
+        self.assertGreater(sys.getsizeof(vars(a)), sys.getsizeof(vars(a2)))
+        self.assertLess(sys.getsizeof(vars(a2)), sys.getsizeof({"a":1}))
         self.assertLess(sys.getsizeof(vars(b)), sys.getsizeof({"a":1}))
 
 
diff --git a/Lib/test/test_dict.py b/Lib/test/test_dict.py
index 4014375..b43c83a 100644
--- a/Lib/test/test_dict.py
+++ b/Lib/test/test_dict.py
@@ -994,8 +994,8 @@ class DictTest(unittest.TestCase):
 
     @support.cpython_only
     def test_splittable_setdefault(self):
-        """split table must be combined when setdefault()
-        breaks insertion order"""
+        """split table must keep correct insertion
+        order when attributes are adding using setdefault()"""
         a, b = self.make_shared_key_dict(2)
 
         a['a'] = 1
@@ -1005,7 +1005,6 @@ class DictTest(unittest.TestCase):
         size_b = sys.getsizeof(b)
         b['a'] = 1
 
-        self.assertGreater(size_b, size_a)
         self.assertEqual(list(a), ['x', 'y', 'z', 'a', 'b'])
         self.assertEqual(list(b), ['x', 'y', 'z', 'b', 'a'])
 
diff --git a/Lib/test/test_gc.py b/Lib/test/test_gc.py
index 6c28b2b..52948f1 100644
--- a/Lib/test/test_gc.py
+++ b/Lib/test/test_gc.py
@@ -444,7 +444,7 @@ class GCTests(unittest.TestCase):
         # 0, thus mutating the trash graph as a side effect of merely asking
         # whether __del__ exists.  This used to (before 2.3b1) crash Python.
         # Now __getattr__ isn't called.
-        self.assertEqual(gc.collect(), 4)
+        self.assertEqual(gc.collect(), 2)
         self.assertEqual(len(gc.garbage), garbagelen)
 
     def test_boom2(self):
@@ -471,7 +471,7 @@ class GCTests(unittest.TestCase):
         # there isn't a second time, so this simply cleans up the trash cycle.
         # We expect a, b, a.__dict__ and b.__dict__ (4 objects) to get
         # reclaimed this way.
-        self.assertEqual(gc.collect(), 4)
+        self.assertEqual(gc.collect(), 2)
         self.assertEqual(len(gc.garbage), garbagelen)
 
     def test_boom_new(self):
@@ -491,7 +491,7 @@ class GCTests(unittest.TestCase):
         gc.collect()
         garbagelen = len(gc.garbage)
         del a, b
-        self.assertEqual(gc.collect(), 4)
+        self.assertEqual(gc.collect(), 2)
         self.assertEqual(len(gc.garbage), garbagelen)
 
     def test_boom2_new(self):
@@ -513,7 +513,7 @@ class GCTests(unittest.TestCase):
         gc.collect()
         garbagelen = len(gc.garbage)
         del a, b
-        self.assertEqual(gc.collect(), 4)
+        self.assertEqual(gc.collect(), 2)
         self.assertEqual(len(gc.garbage), garbagelen)
 
     def test_get_referents(self):
@@ -943,8 +943,8 @@ class GCTests(unittest.TestCase):
             A()
         t = gc.collect()
         c, nc = getstats()
-        self.assertEqual(t, 2*N) # instance object & its dict
-        self.assertEqual(c - oldc, 2*N)
+        self.assertEqual(t, N) # instance objects
+        self.assertEqual(c - oldc, N)
         self.assertEqual(nc - oldnc, 0)
 
         # But Z() is not actually collected.
@@ -964,8 +964,8 @@ class GCTests(unittest.TestCase):
         Z()
         t = gc.collect()
         c, nc = getstats()
-        self.assertEqual(t, 2*N)
-        self.assertEqual(c - oldc, 2*N)
+        self.assertEqual(t, N)
+        self.assertEqual(c - oldc, N)
         self.assertEqual(nc - oldnc, 0)
 
         # The A() trash should have been reclaimed already but the
@@ -974,8 +974,8 @@ class GCTests(unittest.TestCase):
         zs.clear()
         t = gc.collect()
         c, nc = getstats()
-        self.assertEqual(t, 4)
-        self.assertEqual(c - oldc, 4)
+        self.assertEqual(t, 2)
+        self.assertEqual(c - oldc, 2)
         self.assertEqual(nc - oldnc, 0)
 
         gc.enable()
@@ -1128,8 +1128,7 @@ class GCCallbackTests(unittest.TestCase):
     @cpython_only
     def test_collect_garbage(self):
         self.preclean()
-        # Each of these cause four objects to be garbage: Two
-        # Uncollectables and their instance dicts.
+        # Each of these cause two objects to be garbage:
         Uncollectable()
         Uncollectable()
         C1055820(666)
@@ -1138,8 +1137,8 @@ class GCCallbackTests(unittest.TestCase):
             if v[1] != "stop":
                 continue
             info = v[2]
-            self.assertEqual(info["collected"], 2)
-            self.assertEqual(info["uncollectable"], 8)
+            self.assertEqual(info["collected"], 1)
+            self.assertEqual(info["uncollectable"], 4)
 
         # We should now have the Uncollectables in gc.garbage
         self.assertEqual(len(gc.garbage), 4)
@@ -1156,7 +1155,7 @@ class GCCallbackTests(unittest.TestCase):
                 continue
             info = v[2]
             self.assertEqual(info["collected"], 0)
-            self.assertEqual(info["uncollectable"], 4)
+            self.assertEqual(info["uncollectable"], 2)
 
         # Uncollectables should be gone
         self.assertEqual(len(gc.garbage), 0)
diff --git a/Lib/test/test_sys.py b/Lib/test/test_sys.py
index 93e39bc..2ce40fc 100644
--- a/Lib/test/test_sys.py
+++ b/Lib/test/test_sys.py
@@ -1409,7 +1409,7 @@ class SizeofTest(unittest.TestCase):
         check((1,2,3), vsize('') + 3*self.P)
         # type
         # static type: PyTypeObject
-        fmt = 'P2nPI13Pl4Pn9Pn11PIPP'
+        fmt = 'P2nPI13Pl4Pn9Pn12PIPP'
         s = vsize(fmt)
         check(int, s)
         # class
@@ -1422,15 +1422,15 @@ class SizeofTest(unittest.TestCase):
                   '5P')
         class newstyleclass(object): pass
         # Separate block for PyDictKeysObject with 8 keys and 5 entries
-        check(newstyleclass, s + calcsize(DICT_KEY_STRUCT_FORMAT) + 8 + 5*calcsize("n2P"))
+        check(newstyleclass, s + calcsize(DICT_KEY_STRUCT_FORMAT) + 32 + 21*calcsize("n2P"))
         # dict with shared keys
-        check(newstyleclass().__dict__, size('nQ2P') + 5*self.P)
+        check(newstyleclass().__dict__, size('nQ2P') + 15*self.P)
         o = newstyleclass()
         o.a = o.b = o.c = o.d = o.e = o.f = o.g = o.h = 1
         # Separate block for PyDictKeysObject with 16 keys and 10 entries
-        check(newstyleclass, s + calcsize(DICT_KEY_STRUCT_FORMAT) + 16 + 10*calcsize("n2P"))
+        check(newstyleclass, s + calcsize(DICT_KEY_STRUCT_FORMAT) + 32 + 21*calcsize("n2P"))
         # dict with shared keys
-        check(newstyleclass().__dict__, size('nQ2P') + 10*self.P)
+        check(newstyleclass().__dict__, size('nQ2P') + 13*self.P)
         # unicode
         # each tuple contains a string and its expected character size
         # don't put any static strings here, as they may contain
diff --git a/Misc/NEWS.d/next/Core and Builtins/2021-10-08-09-47-38.bpo-45340.ukHgDb.rst b/Misc/NEWS.d/next/Core and Builtins/2021-10-08-09-47-38.bpo-45340.ukHgDb.rst
new file mode 100644
index 0000000..7760773
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2021-10-08-09-47-38.bpo-45340.ukHgDb.rst
@@ -0,0 +1,3 @@
+Object attributes are held in an array instead of a dictionary. An object's
+dictionary are created lazily, only when needed. Reduces the memory
+consumption of a typical Python object by about 30%. Patch by Mark Shannon.
diff --git a/Objects/dictobject.c b/Objects/dictobject.c
index 60470bf..3d6e4c1 100644
--- a/Objects/dictobject.c
+++ b/Objects/dictobject.c
@@ -634,7 +634,7 @@ new_values(Py_ssize_t size)
 
 /* Consumes a reference to the keys object */
 static PyObject *
-new_dict(PyDictKeysObject *keys, PyDictValues *values)
+new_dict(PyDictKeysObject *keys, PyDictValues *values, Py_ssize_t used, int free_values_on_failure)
 {
     PyDictObject *mp;
     assert(keys != NULL);
@@ -653,7 +653,7 @@ new_dict(PyDictKeysObject *keys, PyDictValues *values)
         mp = PyObject_GC_New(PyDictObject, &PyDict_Type);
         if (mp == NULL) {
             dictkeys_decref(keys);
-            if (values != empty_values) {
+            if (free_values_on_failure) {
                 free_values(values);
             }
             return NULL;
@@ -661,12 +661,18 @@ new_dict(PyDictKeysObject *keys, PyDictValues *values)
     }
     mp->ma_keys = keys;
     mp->ma_values = values;
-    mp->ma_used = 0;
+    mp->ma_used = used;
     mp->ma_version_tag = DICT_NEXT_VERSION();
     ASSERT_CONSISTENT(mp);
     return (PyObject *)mp;
 }
 
+static inline Py_ssize_t
+shared_keys_usable_size(PyDictKeysObject *keys)
+{
+    return keys->dk_nentries + keys->dk_usable;
+}
+
 /* Consumes a reference to the keys object */
 static PyObject *
 new_dict_with_shared_keys(PyDictKeysObject *keys)
@@ -674,7 +680,7 @@ new_dict_with_shared_keys(PyDictKeysObject *keys)
     PyDictValues *values;
     Py_ssize_t i, size;
 
-    size = USABLE_FRACTION(DK_SIZE(keys));
+    size = shared_keys_usable_size(keys);
     values = new_values(size);
     if (values == NULL) {
         dictkeys_decref(keys);
@@ -684,7 +690,7 @@ new_dict_with_shared_keys(PyDictKeysObject *keys)
     for (i = 0; i < size; i++) {
         values->values[i] = NULL;
     }
-    return new_dict(keys, values);
+    return new_dict(keys, values, 0, 1);
 }
 
 
@@ -733,7 +739,7 @@ PyObject *
 PyDict_New(void)
 {
     dictkeys_incref(Py_EMPTY_KEYS);
-    return new_dict(Py_EMPTY_KEYS, empty_values);
+    return new_dict(Py_EMPTY_KEYS, empty_values, 0, 0);
 }
 
 /* Search index of hash table from offset of entry table */
@@ -998,6 +1004,40 @@ insertion_resize(PyDictObject *mp)
     return dictresize(mp, calculate_log2_keysize(GROWTH_RATE(mp)));
 }
 
+static int
+insert_into_dictkeys(PyDictKeysObject *keys, PyObject *name)
+{
+    assert(PyUnicode_CheckExact(name));
+    Py_hash_t hash = ((PyASCIIObject *)name)->hash;
+    if (hash == -1) {
+        hash = PyUnicode_Type.tp_hash(name);
+        if (hash == -1) {
+            PyErr_Clear();
+            return DKIX_EMPTY;
+        }
+    }
+    Py_ssize_t ix = dictkeys_stringlookup(keys, name, hash);
+    if (ix == DKIX_EMPTY) {
+        if (keys->dk_usable <= 0) {
+            return DKIX_EMPTY;
+        }
+        Py_INCREF(name);
+        /* Insert into new slot. */
+        keys->dk_version = 0;
+        Py_ssize_t hashpos = find_empty_slot(keys, hash);
+        ix = keys->dk_nentries;
+        PyDictKeyEntry *ep = &DK_ENTRIES(keys)[ix];
+        dictkeys_set_index(keys, hashpos, ix);
+        assert(ep->me_key == NULL);
+        ep->me_key = name;
+        ep->me_hash = hash;
+        keys->dk_usable--;
+        keys->dk_nentries++;
+    }
+    assert (ix < SHARED_KEYS_MAX_SIZE);
+    return (int)ix;
+}
+
 /*
 Internal routine to insert a new item into the table.
 Used both by the internal resize routine and by the public insert routine.
@@ -1043,7 +1083,7 @@ insertdict(PyDictObject *mp, PyObject *key, Py_hash_t hash, PyObject *value)
             Py_ssize_t index = mp->ma_keys->dk_nentries;
             assert(index < SHARED_KEYS_MAX_SIZE);
             assert((mp->ma_values->mv_order >> 60) == 0);
-            mp->ma_values->mv_order = (mp->ma_values->mv_order)<<4 | index;
+            mp->ma_values->mv_order = ((mp->ma_values->mv_order)<<4) | index;
             assert (mp->ma_values->values[index] == NULL);
             mp->ma_values->values[index] = value;
         }
@@ -1144,8 +1184,7 @@ actually be smaller than the old one.
 If a table is split (its keys and hashes are shared, its values are not),
 then the values are temporarily copied into the table, it is resized as
 a combined table, then the me_value slots in the old table are NULLed out.
-After resizing a table is always combined,
-but can be resplit by make_keys_shared().
+After resizing a table is always combined.
 */
 static int
 dictresize(PyDictObject *mp, uint8_t log2_newsize)
@@ -1186,19 +1225,16 @@ dictresize(PyDictObject *mp, uint8_t log2_newsize)
     if (oldvalues != NULL) {
         /* Convert split table into new combined table.
          * We must incref keys; we can transfer values.
-         * Note that values of split table is always dense.
          */
         for (Py_ssize_t i = 0; i < numentries; i++) {
-            int index = oldvalues->mv_order >> ((numentries-1-i)*4) & 15;
-            assert(oldvalues->values[index] != NULL);
+            int index = get_index_from_order(mp, i);
             PyDictKeyEntry *ep = &oldentries[index];
-            PyObject *key = ep->me_key;
-            Py_INCREF(key);
-            newentries[i].me_key = key;
+            assert(oldvalues->values[index] != NULL);
+            Py_INCREF(ep->me_key);
+            newentries[i].me_key = ep->me_key;
             newentries[i].me_hash = ep->me_hash;
             newentries[i].me_value = oldvalues->values[index];
         }
-
         dictkeys_decref(oldkeys);
         mp->ma_values = NULL;
         if (oldvalues != empty_values) {
@@ -1241,69 +1277,8 @@ dictresize(PyDictObject *mp, uint8_t log2_newsize)
     build_indices(mp->ma_keys, newentries, numentries);
     mp->ma_keys->dk_usable -= numentries;
     mp->ma_keys->dk_nentries = numentries;
-    return 0;
-}
-
-/* Returns NULL if unable to split table.
- * A NULL return does not necessarily indicate an error */
-static PyDictKeysObject *
-make_keys_shared(PyObject *op)
-{
-    Py_ssize_t i;
-    Py_ssize_t size;
-    PyDictObject *mp = (PyDictObject *)op;
-
-    if (!PyDict_CheckExact(op))
-        return NULL;
-    if (mp->ma_used > SHARED_KEYS_MAX_SIZE) {
-        return NULL;
-    }
-    if (!_PyDict_HasSplitTable(mp)) {
-        PyDictKeyEntry *ep0;
-        PyDictValues *values;
-        assert(mp->ma_keys->dk_refcnt == 1);
-        if (mp->ma_keys->dk_kind == DICT_KEYS_GENERAL) {
-            return NULL;
-        }
-        else if (mp->ma_used > mp->ma_keys->dk_nentries) {
-            /* Remove dummy keys */
-            if (dictresize(mp, DK_LOG_SIZE(mp->ma_keys)))
-                return NULL;
-        }
-        assert(mp->ma_used == mp->ma_keys->dk_nentries);
-        /* Copy values into a new array */
-        ep0 = DK_ENTRIES(mp->ma_keys);
-        size = USABLE_FRACTION(DK_SIZE(mp->ma_keys));
-        values = new_values(size);
-        if (values == NULL) {
-            PyErr_SetString(PyExc_MemoryError,
-                "Not enough memory to allocate new values array");
-            return NULL;
-        }
-        uint64_t order = 0;
-        for (i = 0; i < mp->ma_used; i++) {
-            order <<= 4;
-            order |= i;
-            assert(ep0[i].me_value != NULL);
-            values->values[i] = ep0[i].me_value;
-            ep0[i].me_value = NULL;
-        }
-        values->mv_order = order;
-        for (; i < size; i++) {
-            assert(ep0[i].me_value == NULL);
-            values->values[i] = NULL;
-            ep0[i].me_value = NULL;
-        }
-        if (mp->ma_keys->dk_nentries + mp->ma_keys->dk_usable > SHARED_KEYS_MAX_SIZE) {
-            assert(mp->ma_keys->dk_nentries <= SHARED_KEYS_MAX_SIZE);
-            mp->ma_keys->dk_usable = SHARED_KEYS_MAX_SIZE - mp->ma_keys->dk_nentries;
-        }
-        mp->ma_keys->dk_kind = DICT_KEYS_SPLIT;
-        mp->ma_values = values;
-    }
-    dictkeys_incref(mp->ma_keys);
     ASSERT_CONSISTENT(mp);
-    return mp->ma_keys;
+    return 0;
 }
 
 PyObject *
@@ -1331,7 +1306,7 @@ _PyDict_NewPresized(Py_ssize_t minused)
     new_keys = new_keys_object(log2_newsize);
     if (new_keys == NULL)
         return NULL;
-    return new_dict(new_keys, NULL);
+    return new_dict(new_keys, NULL, 0, 0);
 }
 
 /* Note that, for historical reasons, PyDict_GetItem() suppresses all errors
@@ -1503,6 +1478,9 @@ _PyDict_GetItemStringWithError(PyObject *v, const char *key)
 /* Fast version of global value lookup (LOAD_GLOBAL).
  * Lookup in globals, then builtins.
  *
+ *
+ *
+ *
  * Raise an exception and return NULL if an error occurred (ex: computing the
  * key hash failed, key comparison failed, ...). Return NULL if the key doesn't
  * exist. Return the value if the key exists.
@@ -1590,6 +1568,21 @@ _PyDict_SetItem_KnownHash(PyObject *op, PyObject *key, PyObject *value,
     return insertdict(mp, key, hash, value);
 }
 
+static uint64_t
+delete_index_from_order(uint64_t order, Py_ssize_t ix)
+{        /* Update order */
+    for (int i = 0;; i+= 4) {
+        assert (i < 64);
+        if (((order >> i) & 15) == (uint64_t)ix) {
+            /* Remove 4 bits at ith position */
+            uint64_t high = ((order>>i)>>4)<<i;
+            uint64_t low = order & ((((uint64_t)1)<<i)-1);
+            return high | low;
+        }
+    }
+    Py_UNREACHABLE();
+}
+
 static int
 delitem_common(PyDictObject *mp, Py_hash_t hash, Py_ssize_t ix,
                PyObject *old_value)
@@ -1601,7 +1594,6 @@ delitem_common(PyDictObject *mp, Py_hash_t hash, Py_ssize_t ix,
     assert(hashpos >= 0);
 
     mp->ma_used--;
-    mp->ma_keys->dk_version = 0;
     mp->ma_version_tag = DICT_NEXT_VERSION();
     ep = &DK_ENTRIES(mp->ma_keys)[ix];
     if (mp->ma_values) {
@@ -1609,19 +1601,12 @@ delitem_common(PyDictObject *mp, Py_hash_t hash, Py_ssize_t ix,
         mp->ma_values->values[ix] = NULL;
         assert(ix < SHARED_KEYS_MAX_SIZE);
         /* Update order */
-        for (int i = 0;; i+= 4) {
-            assert (i < 64);
-            if (((mp->ma_values->mv_order >> i) & 15) == (uint64_t)ix) {
-                /* Remove 4 bits at ith position */
-                uint64_t order = mp->ma_values->mv_order;
-                uint64_t high = ((order>>i)>>4)<<i;
-                uint64_t low = order & ((((uint64_t)1)<<i)-1);
-                mp->ma_values->mv_order = high | low;
-                break;
-            }
-        }
+        mp->ma_values->mv_order =
+            delete_index_from_order(mp->ma_values->mv_order, ix);
+        ASSERT_CONSISTENT(mp);
     }
     else {
+        mp->ma_keys->dk_version = 0;
         dictkeys_set_index(mp->ma_keys, hashpos, DKIX_DUMMY);
         old_key = ep->me_key;
         ep->me_key = NULL;
@@ -2692,7 +2677,7 @@ PyDict_Copy(PyObject *o)
 
     if (_PyDict_HasSplitTable(mp)) {
         PyDictObject *split_copy;
-        Py_ssize_t size = USABLE_FRACTION(DK_SIZE(mp->ma_keys));
+        Py_ssize_t size = shared_keys_usable_size(mp->ma_keys);
         PyDictValues *newvalues;
         newvalues = new_values(size);
         if (newvalues == NULL)
@@ -2740,7 +2725,7 @@ PyDict_Copy(PyObject *o)
         if (keys == NULL) {
             return NULL;
         }
-        PyDictObject *new = (PyDictObject *)new_dict(keys, NULL);
+        PyDictObject *new = (PyDictObject *)new_dict(keys, NULL, 0, 0);
         if (new == NULL) {
             /* In case of an error, `new_dict()` takes care of
                cleaning up `keys`. */
@@ -2979,15 +2964,6 @@ PyDict_SetDefault(PyObject *d, PyObject *key, PyObject *defaultobj)
     if (ix == DKIX_ERROR)
         return NULL;
 
-    if (_PyDict_HasSplitTable(mp) &&
-        ((ix >= 0 && value == NULL && mp->ma_used != ix) ||
-         (ix == DKIX_EMPTY && mp->ma_used != mp->ma_keys->dk_nentries))) {
-        if (insertion_resize(mp) < 0) {
-            return NULL;
-        }
-        ix = DKIX_EMPTY;
-    }
-
     if (ix == DKIX_EMPTY) {
         mp->ma_keys->dk_version = 0;
         PyDictKeyEntry *ep, *ep0;
@@ -3028,7 +3004,7 @@ PyDict_SetDefault(PyObject *d, PyObject *key, PyObject *defaultobj)
     else if (value == NULL) {
         value = defaultobj;
         assert(_PyDict_HasSplitTable(mp));
-        assert(ix == mp->ma_used);
+        assert(mp->ma_values->values[ix] == NULL);
         Py_INCREF(value);
         MAINTAIN_TRACKING(mp, key, value);
         mp->ma_values->values[ix] = value;
@@ -3204,20 +3180,22 @@ static PyObject *dictiter_new(PyDictObject *, PyTypeObject *);
 Py_ssize_t
 _PyDict_SizeOf(PyDictObject *mp)
 {
-    Py_ssize_t size, usable, res;
+    Py_ssize_t size, res;
 
     size = DK_SIZE(mp->ma_keys);
-    usable = USABLE_FRACTION(size);
 
     res = _PyObject_SIZE(Py_TYPE(mp));
-    if (mp->ma_values)
-        res += usable * sizeof(PyObject*);
+    if (mp->ma_values) {
+        res += shared_keys_usable_size(mp->ma_keys) * sizeof(PyObject*);
+    }
     /* If the dictionary is split, the keys portion is accounted-for
        in the type object. */
-    if (mp->ma_keys->dk_refcnt == 1)
+    if (mp->ma_keys->dk_refcnt == 1) {
+        Py_ssize_t usable = USABLE_FRACTION(size);
         res += (sizeof(PyDictKeysObject)
                 + DK_IXSIZE(mp->ma_keys) * size
                 + sizeof(PyDictKeyEntry) * usable);
+    }
     return res;
 }
 
@@ -4919,11 +4897,14 @@ dictvalues_reversed(_PyDictViewObject *dv, PyObject *Py_UNUSED(ignored))
 PyDictKeysObject *
 _PyDict_NewKeysForClass(void)
 {
-    PyDictKeysObject *keys = new_keys_object(PyDict_LOG_MINSIZE);
+    PyDictKeysObject *keys = new_keys_object(5); /* log2(32) */
     if (keys == NULL) {
         PyErr_Clear();
     }
     else {
+        assert(keys->dk_nentries == 0);
+        /* Set to max size+1 as it will shrink by one before each new object */
+        keys->dk_usable = SHARED_KEYS_MAX_SIZE;
         keys->dk_kind = DICT_KEYS_SPLIT;
     }
     return keys;
@@ -4931,15 +4912,42 @@ _PyDict_NewKeysForClass(void)
 
 #define CACHED_KEYS(tp) (((PyHeapTypeObject*)tp)->ht_cached_keys)
 
+static int
+init_inline_values(PyObject *obj, PyTypeObject *tp)
+{
+    assert(tp->tp_flags & Py_TPFLAGS_HEAPTYPE);
+    assert(tp->tp_dictoffset > 0);
+    assert(tp->tp_inline_values_offset > 0);
+    PyDictKeysObject *keys = CACHED_KEYS(tp);
+    assert(keys != NULL);
+    if (keys->dk_usable > 1) {
+        keys->dk_usable--;
+    }
+    Py_ssize_t size = shared_keys_usable_size(keys);
+    assert(size > 0);
+    PyDictValues *values = new_values(size);
+    if (values == NULL) {
+        PyErr_NoMemory();
+        return -1;
+    }
+    values->mv_order = 0;
+    for (int i = 0; i < size; i++) {
+        values->values[i] = NULL;
+    }
+    *((PyDictValues **)((char *)obj + tp->tp_inline_values_offset)) = values;
+    return 0;
+}
+
 int
 _PyObject_InitializeDict(PyObject *obj)
 {
-    PyObject **dictptr = _PyObject_GetDictPtr(obj);
-    if (dictptr == NULL) {
+    PyTypeObject *tp = Py_TYPE(obj);
+    if (tp->tp_dictoffset == 0) {
         return 0;
     }
-    assert(*dictptr == NULL);
-    PyTypeObject *tp = Py_TYPE(obj);
+    if (tp->tp_inline_values_offset) {
+        return init_inline_values(obj, tp);
+    }
     PyObject *dict;
     if (_PyType_HasFeature(tp, Py_TPFLAGS_HEAPTYPE) && CACHED_KEYS(tp)) {
         dictkeys_incref(CACHED_KEYS(tp));
@@ -4951,15 +4959,174 @@ _PyObject_InitializeDict(PyObject *obj)
     if (dict == NULL) {
         return -1;
     }
+    PyObject **dictptr = _PyObject_DictPointer(obj);
     *dictptr = dict;
     return 0;
 }
 
+static PyObject *
+make_dict_from_instance_attributes(PyDictKeysObject *keys, PyDictValues *values)
+{
+    dictkeys_incref(keys);
+    Py_ssize_t used = 0;
+    Py_ssize_t track = 0;
+    for (Py_ssize_t i = 0; i < shared_keys_usable_size(keys); i++) {
+        PyObject *val = values->values[i];
+        if (val != NULL) {
+            used += 1;
+            track += _PyObject_GC_MAY_BE_TRACKED(val);
+        }
+    }
+    PyObject *res = new_dict(keys, values, used, 0);
+    if (track && res) {
+        _PyObject_GC_TRACK(res);
+    }
+    return res;
+}
+
+PyObject *
+_PyObject_MakeDictFromInstanceAttributes(PyObject *obj, PyDictValues *values)
+{
+    assert(Py_TYPE(obj)->tp_inline_values_offset != 0);
+    PyDictKeysObject *keys = CACHED_KEYS(Py_TYPE(obj));
+    return make_dict_from_instance_attributes(keys, values);
+}
+
+int
+_PyObject_StoreInstanceAttribute(PyObject *obj, PyDictValues *values,
+                              PyObject *name, PyObject *value)
+{
+    assert(PyUnicode_CheckExact(name));
+    PyTypeObject *tp = Py_TYPE(obj);
+    PyDictKeysObject *keys = CACHED_KEYS(Py_TYPE(obj));
+    assert(keys != NULL);
+    assert(values != NULL);
+    int ix = insert_into_dictkeys(keys, name);
+    if (ix == DKIX_EMPTY) {
+        if (value == NULL) {
+            PyErr_SetObject(PyExc_AttributeError, name);
+            return -1;
+        }
+        PyObject *dict = make_dict_from_instance_attributes(keys, values);
+        if (dict == NULL) {
+            return -1;
+        }
+        *((PyDictValues **)((char *)obj + tp->tp_inline_values_offset)) = NULL;
+        *((PyObject **) ((char *)obj + tp->tp_dictoffset)) = dict;
+        return PyDict_SetItem(dict, name, value);
+    }
+    PyObject *old_value = values->values[ix];
+    Py_XINCREF(value);
+    values->values[ix] = value;
+    if (old_value == NULL) {
+        if (value == NULL) {
+            PyErr_SetObject(PyExc_AttributeError, name);
+            return -1;
+        }
+        values->mv_order = (values->mv_order << 4) | ix;
+    }
+    else {
+        if (value == NULL) {
+            values->mv_order = delete_index_from_order(values->mv_order, ix);
+        }
+        Py_DECREF(old_value);
+    }
+    return 0;
+}
+
+PyObject *
+_PyObject_GetInstanceAttribute(PyObject *obj, PyDictValues *values,
+                              PyObject *name)
+{
+    assert(PyUnicode_CheckExact(name));
+    PyDictKeysObject *keys = CACHED_KEYS(Py_TYPE(obj));
+    assert(keys != NULL);
+    Py_ssize_t ix = _PyDictKeys_StringLookup(keys, name);
+    if (ix == DKIX_EMPTY) {
+        return NULL;
+    }
+    PyObject *value = values->values[ix];
+    Py_XINCREF(value);
+    return value;
+}
+
+int
+_PyObject_IsInstanceDictEmpty(PyObject *obj)
+{
+    PyTypeObject *tp = Py_TYPE(obj);
+    if (tp->tp_dictoffset == 0) {
+        return 1;
+    }
+    PyDictValues **values_ptr = _PyObject_ValuesPointer(obj);
+    if (values_ptr && *values_ptr) {
+        PyDictKeysObject *keys = CACHED_KEYS(tp);
+        for (Py_ssize_t i = 0; i < keys->dk_nentries; i++) {
+            if ((*values_ptr)->values[i] != NULL) {
+                return 0;
+            }
+        }
+        return 1;
+    }
+    PyObject **dictptr = _PyObject_DictPointer(obj);
+    PyObject *dict = *dictptr;
+    if (dict == NULL) {
+        return 1;
+    }
+    return ((PyDictObject *)dict)->ma_used == 0;
+}
+
+
+int
+_PyObject_VisitInstanceAttributes(PyObject *self, visitproc visit, void *arg)
+{
+    PyTypeObject *tp = Py_TYPE(self);
+    assert(tp->tp_inline_values_offset);
+    PyDictValues **values_ptr = _PyObject_ValuesPointer(self);
+    if (*values_ptr == NULL) {
+        return 0;
+    }
+    PyDictKeysObject *keys = CACHED_KEYS(tp);
+    for (Py_ssize_t i = 0; i < keys->dk_nentries; i++) {
+        Py_VISIT((*values_ptr)->values[i]);
+    }
+    return 0;
+}
+
+void
+_PyObject_ClearInstanceAttributes(PyObject *self)
+{
+    PyTypeObject *tp = Py_TYPE(self);
+    assert(tp->tp_inline_values_offset);
+    PyDictValues **values_ptr = _PyObject_ValuesPointer(self);
+    if (*values_ptr == NULL) {
+        return;
+    }
+    PyDictKeysObject *keys = CACHED_KEYS(tp);
+    for (Py_ssize_t i = 0; i < keys->dk_nentries; i++) {
+        Py_CLEAR((*values_ptr)->values[i]);
+    }
+}
+
+void
+_PyObject_FreeInstanceAttributes(PyObject *self)
+{
+    PyTypeObject *tp = Py_TYPE(self);
+    assert(tp->tp_inline_values_offset);
+    PyDictValues **values_ptr = _PyObject_ValuesPointer(self);
+    if (*values_ptr == NULL) {
+        return;
+    }
+    PyDictKeysObject *keys = CACHED_KEYS(tp);
+    for (Py_ssize_t i = 0; i < keys->dk_nentries; i++) {
+        Py_XDECREF((*values_ptr)->values[i]);
+    }
+    free_values(*values_ptr);
+}
 
 PyObject *
 PyObject_GenericGetDict(PyObject *obj, void *context)
 {
-    PyObject **dictptr = _PyObject_GetDictPtr(obj);
+    PyObject **dictptr = _PyObject_DictPointer(obj);
     if (dictptr == NULL) {
         PyErr_SetString(PyExc_AttributeError,
                         "This object has no __dict__");
@@ -4968,7 +5135,14 @@ PyObject_GenericGetDict(PyObject *obj, void *context)
     PyObject *dict = *dictptr;
     if (dict == NULL) {
         PyTypeObject *tp = Py_TYPE(obj);
-        if (_PyType_HasFeature(tp, Py_TPFLAGS_HEAPTYPE) && CACHED_KEYS(tp)) {
+        PyDictValues **values_ptr = _PyObject_ValuesPointer(obj);
+        if (values_ptr && *values_ptr) {
+            *dictptr = dict = make_dict_from_instance_attributes(CACHED_KEYS(tp), *values_ptr);
+            if (dict != NULL) {
+                *values_ptr = NULL;
+            }
+        }
+        else if (_PyType_HasFeature(tp, Py_TPFLAGS_HEAPTYPE) && CACHED_KEYS(tp)) {
             dictkeys_incref(CACHED_KEYS(tp));
             *dictptr = dict = new_dict_with_shared_keys(CACHED_KEYS(tp));
         }
@@ -5003,37 +5177,7 @@ _PyObjectDict_SetItem(PyTypeObject *tp, PyObject **dictptr,
             res = PyDict_DelItem(dict, key);
         }
         else {
-            int was_shared = (cached == ((PyDictObject *)dict)->ma_keys);
             res = PyDict_SetItem(dict, key, value);
-            if (was_shared &&
-                    (cached = CACHED_KEYS(tp)) != NULL &&
-                    cached != ((PyDictObject *)dict)->ma_keys &&
-                    cached->dk_nentries <= SHARED_KEYS_MAX_SIZE) {
-                /* PyDict_SetItem() may call dictresize and convert split table
-                 * into combined table.  In such case, convert it to split
-                 * table again and update type's shared key only when this is
-                 * the only dict sharing key with the type.
-                 *
-                 * This is to allow using shared key in class like this:
-                 *
-                 *     class C:
-                 *         def __init__(self):
-                 *             # one dict resize happens
-                 *             self.a, self.b, self.c = 1, 2, 3
-                 *             self.d, self.e, self.f = 4, 5, 6
-                 *     a = C()
-                 */
-                if (cached->dk_refcnt == 1) {
-                    PyDictKeysObject *new_cached = make_keys_shared(dict);
-                    if (new_cached != NULL) {
-                        CACHED_KEYS(tp) = new_cached;
-                        dictkeys_decref(cached);
-                    }
-                    else if (PyErr_Occurred()) {
-                        return -1;
-                    }
-                }
-            }
         }
     } else {
         dict = *dictptr;
diff --git a/Objects/object.c b/Objects/object.c
index 9d48346..14c85c2 100644
--- a/Objects/object.c
+++ b/Objects/object.c
@@ -5,6 +5,7 @@
 #include "pycore_call.h"          // _PyObject_CallNoArgs()
 #include "pycore_ceval.h"         // _Py_EnterRecursiveCall()
 #include "pycore_context.h"
+#include "pycore_dict.h"
 #include "pycore_initconfig.h"    // _PyStatus_EXCEPTION()
 #include "pycore_object.h"        // _PyType_CheckConsistency()
 #include "pycore_pyerrors.h"      // _PyErr_Occurred()
@@ -1065,10 +1066,8 @@ PyObject_SetAttr(PyObject *v, PyObject *name, PyObject *value)
     return -1;
 }
 
-/* Helper to get a pointer to an object's __dict__ slot, if any */
-
 PyObject **
-_PyObject_GetDictPtr(PyObject *obj)
+_PyObject_DictPointer(PyObject *obj)
 {
     Py_ssize_t dictoffset;
     PyTypeObject *tp = Py_TYPE(obj);
@@ -1090,6 +1089,35 @@ _PyObject_GetDictPtr(PyObject *obj)
     return (PyObject **) ((char *)obj + dictoffset);
 }
 
+/* Helper to get a pointer to an object's __dict__ slot, if any.
+ * Creates the dict from inline attributes if necessary.
+ * Does not set an exception. */
+PyObject **
+_PyObject_GetDictPtr(PyObject *obj)
+{
+    PyObject **dict_ptr = _PyObject_DictPointer(obj);
+    if (dict_ptr == NULL) {
+        return NULL;
+    }
+    if (*dict_ptr != NULL) {
+        return dict_ptr;
+    }
+    PyDictValues **values_ptr = _PyObject_ValuesPointer(obj);
+    if (values_ptr == NULL || *values_ptr == NULL) {
+        return dict_ptr;
+    }
+    PyObject *dict = _PyObject_MakeDictFromInstanceAttributes(obj, *values_ptr);
+    if (dict == NULL) {
+        PyErr_Clear();
+        return NULL;
+    }
+    assert(*dict_ptr == NULL);
+    assert(*values_ptr != NULL);
+    *values_ptr = NULL;
+    *dict_ptr = dict;
+    return dict_ptr;
+}
+
 PyObject *
 PyObject_SelfIter(PyObject *obj)
 {
@@ -1136,7 +1164,7 @@ _PyObject_GetMethod(PyObject *obj, PyObject *name, PyObject **method)
         }
     }
 
-    if (tp->tp_getattro != PyObject_GenericGetAttr || !PyUnicode_Check(name)) {
+    if (tp->tp_getattro != PyObject_GenericGetAttr || !PyUnicode_CheckExact(name)) {
         *method = PyObject_GetAttr(obj, name);
         return 0;
     }
@@ -1156,23 +1184,34 @@ _PyObject_GetMethod(PyObject *obj, PyObject *name, PyObject **method)
             }
         }
     }
-
-    PyObject **dictptr = _PyObject_GetDictPtr(obj);
-    PyObject *dict;
-    if (dictptr != NULL && (dict = *dictptr) != NULL) {
-        Py_INCREF(dict);
-        PyObject *attr = PyDict_GetItemWithError(dict, name);
+    PyDictValues **values_ptr = _PyObject_ValuesPointer(obj);
+    if (values_ptr && *values_ptr) {
+        assert(*_PyObject_DictPointer(obj) == NULL);
+        PyObject *attr = _PyObject_GetInstanceAttribute(obj, *values_ptr, name);
         if (attr != NULL) {
-            *method = Py_NewRef(attr);
-            Py_DECREF(dict);
+            *method = attr;
             Py_XDECREF(descr);
             return 0;
         }
-        Py_DECREF(dict);
+    }
+    else {
+        PyObject **dictptr = _PyObject_DictPointer(obj);
+        PyObject *dict;
+        if (dictptr != NULL && (dict = *dictptr) != NULL) {
+            Py_INCREF(dict);
+            PyObject *attr = PyDict_GetItemWithError(dict, name);
+            if (attr != NULL) {
+                *method = Py_NewRef(attr);
+                Py_DECREF(dict);
+                Py_XDECREF(descr);
+                return 0;
+            }
+            Py_DECREF(dict);
 
-        if (PyErr_Occurred()) {
-            Py_XDECREF(descr);
-            return 0;
+            if (PyErr_Occurred()) {
+                Py_XDECREF(descr);
+                return 0;
+            }
         }
     }
 
@@ -1200,6 +1239,17 @@ _PyObject_GetMethod(PyObject *obj, PyObject *name, PyObject **method)
     return 0;
 }
 
+PyDictValues **
+_PyObject_ValuesPointer(PyObject *obj)
+{
+    PyTypeObject *tp = Py_TYPE(obj);
+    Py_ssize_t offset = tp->tp_inline_values_offset;
+    if (offset == 0) {
+        return NULL;
+    }
+    return (PyDictValues **) ((char *)obj + offset);
+}
+
 /* Generic GetAttr functions - put these in your tp_[gs]etattro slot. */
 
 PyObject *
@@ -1247,25 +1297,46 @@ _PyObject_GenericGetAttrWithDict(PyObject *obj, PyObject *name,
             goto done;
         }
     }
-
     if (dict == NULL) {
-        /* Inline _PyObject_GetDictPtr */
-        dictoffset = tp->tp_dictoffset;
-        if (dictoffset != 0) {
-            if (dictoffset < 0) {
-                Py_ssize_t tsize = Py_SIZE(obj);
-                if (tsize < 0) {
-                    tsize = -tsize;
+        PyDictValues **values_ptr = _PyObject_ValuesPointer(obj);
+        if (values_ptr && *values_ptr) {
+            if (PyUnicode_CheckExact(name)) {
+                assert(*_PyObject_DictPointer(obj) == NULL);
+                res = _PyObject_GetInstanceAttribute(obj, *values_ptr, name);
+                if (res != NULL) {
+                    goto done;
                 }
-                size_t size = _PyObject_VAR_SIZE(tp, tsize);
-                _PyObject_ASSERT(obj, size <= PY_SSIZE_T_MAX);
-
-                dictoffset += (Py_ssize_t)size;
-                _PyObject_ASSERT(obj, dictoffset > 0);
-                _PyObject_ASSERT(obj, dictoffset % SIZEOF_VOID_P == 0);
             }
-            dictptr = (PyObject **) ((char *)obj + dictoffset);
-            dict = *dictptr;
+            else {
+                dictptr = _PyObject_DictPointer(obj);
+                assert(dictptr != NULL && *dictptr == NULL);
+                *dictptr = dict = _PyObject_MakeDictFromInstanceAttributes(obj, *values_ptr);
+                if (dict == NULL) {
+                    res = NULL;
+                    goto done;
+                }
+                *values_ptr = NULL;
+            }
+        }
+        else {
+            /* Inline _PyObject_DictPointer */
+            dictoffset = tp->tp_dictoffset;
+            if (dictoffset != 0) {
+                if (dictoffset < 0) {
+                    Py_ssize_t tsize = Py_SIZE(obj);
+                    if (tsize < 0) {
+                        tsize = -tsize;
+                    }
+                    size_t size = _PyObject_VAR_SIZE(tp, tsize);
+                    _PyObject_ASSERT(obj, size <= PY_SSIZE_T_MAX);
+
+                    dictoffset += (Py_ssize_t)size;
+                    _PyObject_ASSERT(obj, dictoffset > 0);
+                    _PyObject_ASSERT(obj, dictoffset % SIZEOF_VOID_P == 0);
+                }
+                dictptr = (PyObject **) ((char *)obj + dictoffset);
+                dict = *dictptr;
+            }
         }
     }
     if (dict != NULL) {
@@ -1328,7 +1399,6 @@ _PyObject_GenericSetAttrWithDict(PyObject *obj, PyObject *name,
     PyTypeObject *tp = Py_TYPE(obj);
     PyObject *descr;
     descrsetfunc f;
-    PyObject **dictptr;
     int res = -1;
 
     if (!PyUnicode_Check(name)){
@@ -1354,30 +1424,30 @@ _PyObject_GenericSetAttrWithDict(PyObject *obj, PyObject *name,
         }
     }
 
-    /* XXX [Steve Dower] These are really noisy - worth it? */
-    /*if (PyType_Check(obj) || PyModule_Check(obj)) {
-        if (value && PySys_Audit("object.__setattr__", "OOO", obj, name, value) < 0)
-            return -1;
-        if (!value && PySys_Audit("object.__delattr__", "OO", obj, name) < 0)
-            return -1;
-    }*/
-
     if (dict == NULL) {
-        dictptr = _PyObject_GetDictPtr(obj);
-        if (dictptr == NULL) {
-            if (descr == NULL) {
-                PyErr_Format(PyExc_AttributeError,
-                             "'%.100s' object has no attribute '%U'",
-                             tp->tp_name, name);
+        PyDictValues **values_ptr = _PyObject_ValuesPointer(obj);
+        if (values_ptr && *values_ptr) {
+            res = _PyObject_StoreInstanceAttribute(obj, *values_ptr, name, value);
+        }
+        else {
+            PyObject **dictptr = _PyObject_DictPointer(obj);
+            if (dictptr == NULL) {
+                if (descr == NULL) {
+                    PyErr_Format(PyExc_AttributeError,
+                                "'%.100s' object has no attribute '%U'",
+                                tp->tp_name, name);
+                }
+                else {
+                    PyErr_Format(PyExc_AttributeError,
+                                "'%.50s' object attribute '%U' is read-only",
+                                tp->tp_name, name);
+                }
+                goto done;
             }
             else {
-                PyErr_Format(PyExc_AttributeError,
-                             "'%.50s' object attribute '%U' is read-only",
-                             tp->tp_name, name);
+                res = _PyObjectDict_SetItem(tp, dictptr, name, value);
             }
-            goto done;
         }
-        res = _PyObjectDict_SetItem(tp, dictptr, name, value);
     }
     else {
         Py_INCREF(dict);
@@ -1407,8 +1477,15 @@ PyObject_GenericSetDict(PyObject *obj, PyObject *value, void *context)
 {
     PyObject **dictptr = _PyObject_GetDictPtr(obj);
     if (dictptr == NULL) {
-        PyErr_SetString(PyExc_AttributeError,
-                        "This object has no __dict__");
+        PyDictValues** values_ptr = _PyObject_ValuesPointer(obj);
+        if (values_ptr != NULL && *values_ptr != NULL) {
+            /* Was unable to convert to dict */
+            PyErr_NoMemory();
+        }
+        else {
+            PyErr_SetString(PyExc_AttributeError,
+                            "This object has no __dict__");
+        }
         return -1;
     }
     if (value == NULL) {
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index 544e8a4..aa07333 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -1232,8 +1232,16 @@ subtype_traverse(PyObject *self, visitproc visit, void *arg)
         assert(base);
     }
 
+    if (type->tp_inline_values_offset) {
+        assert(type->tp_dictoffset);
+        int err = _PyObject_VisitInstanceAttributes(self, visit, arg);
+        if (err) {
+            return err;
+        }
+    }
+
     if (type->tp_dictoffset != base->tp_dictoffset) {
-        PyObject **dictptr = _PyObject_GetDictPtr(self);
+        PyObject **dictptr = _PyObject_DictPointer(self);
         if (dictptr && *dictptr)
             Py_VISIT(*dictptr);
     }
@@ -1293,8 +1301,11 @@ subtype_clear(PyObject *self)
 
     /* Clear the instance dict (if any), to break cycles involving only
        __dict__ slots (as in the case 'self.__dict__ is self'). */
+    if (type->tp_inline_values_offset) {
+        _PyObject_ClearInstanceAttributes(self);
+    }
     if (type->tp_dictoffset != base->tp_dictoffset) {
-        PyObject **dictptr = _PyObject_GetDictPtr(self);
+        PyObject **dictptr = _PyObject_DictPointer(self);
         if (dictptr && *dictptr)
             Py_CLEAR(*dictptr);
     }
@@ -1433,9 +1444,12 @@ subtype_dealloc(PyObject *self)
         assert(base);
     }
 
-    /* If we added a dict, DECREF it */
+    /* If we added a dict, DECREF it, or free inline values. */
+    if (type->tp_inline_values_offset) {
+        _PyObject_FreeInstanceAttributes(self);
+    }
     if (type->tp_dictoffset && !base->tp_dictoffset) {
-        PyObject **dictptr = _PyObject_GetDictPtr(self);
+        PyObject **dictptr = _PyObject_DictPointer(self);
         if (dictptr != NULL) {
             PyObject *dict = *dictptr;
             if (dict != NULL) {
@@ -2159,7 +2173,6 @@ mro_internal(PyTypeObject *type, PyObject **p_old_mro)
     return 1;
 }
 
-
 /* Calculate the best base amongst multiple base classes.
    This is the first one that's on the path to the "solid base". */
 
@@ -2230,6 +2243,10 @@ extra_ivars(PyTypeObject *type, PyTypeObject *base)
         return t_size != b_size ||
             type->tp_itemsize != base->tp_itemsize;
     }
+    if (type->tp_inline_values_offset && base->tp_inline_values_offset == 0 &&
+        type->tp_inline_values_offset + sizeof(PyDictValues *) == t_size &&
+        type->tp_flags & Py_TPFLAGS_HEAPTYPE)
+        t_size -= sizeof(PyDictValues *);
     if (type->tp_weaklistoffset && base->tp_weaklistoffset == 0 &&
         type->tp_weaklistoffset + sizeof(PyObject *) == t_size &&
         type->tp_flags & Py_TPFLAGS_HEAPTYPE)
@@ -2238,7 +2255,6 @@ extra_ivars(PyTypeObject *type, PyTypeObject *base)
         type->tp_dictoffset + sizeof(PyObject *) == t_size &&
         type->tp_flags & Py_TPFLAGS_HEAPTYPE)
         t_size -= sizeof(PyObject *);
-
     return t_size != b_size;
 }
 
@@ -2258,6 +2274,7 @@ solid_base(PyTypeObject *type)
 }
 
 static void object_dealloc(PyObject *);
+static PyObject *object_new(PyTypeObject *, PyObject *, PyObject *);
 static int object_init(PyObject *, PyObject *, PyObject *);
 static int update_slot(PyTypeObject *, PyObject *);
 static void fixup_slot_dispatchers(PyTypeObject *);
@@ -2979,6 +2996,13 @@ type_new_descriptors(const type_new_ctx *ctx, PyTypeObject *type)
         type->tp_weaklistoffset = slotoffset;
         slotoffset += sizeof(PyObject *);
     }
+    if (type->tp_dictoffset > 0) {
+        type->tp_inline_values_offset = slotoffset;
+        slotoffset += sizeof(PyDictValues *);
+    }
+    else {
+        type->tp_inline_values_offset = 0;
+    }
 
     type->tp_basicsize = slotoffset;
     type->tp_itemsize = ctx->base->tp_itemsize;
@@ -3181,7 +3205,8 @@ type_new_impl(type_new_ctx *ctx)
     // Put the proper slots in place
     fixup_slot_dispatchers(type);
 
-    if (type->tp_dictoffset) {
+    if (type->tp_inline_values_offset) {
+        assert(type->tp_dictoffset > 0);
         PyHeapTypeObject *et = (PyHeapTypeObject*)type;
         et->ht_cached_keys = _PyDict_NewKeysForClass();
     }
@@ -3195,6 +3220,7 @@ type_new_impl(type_new_ctx *ctx)
     }
 
     assert(_PyType_CheckConsistency(type));
+
     return (PyObject *)type;
 
 error:
@@ -3550,7 +3576,8 @@ PyType_FromModuleAndSpec(PyObject *module, PyType_Spec *spec, PyObject *bases)
     if (PyType_Ready(type) < 0)
         goto fail;
 
-    if (type->tp_dictoffset) {
+    if (type->tp_inline_values_offset) {
+        assert(type->tp_dictoffset > 0);
         res->ht_cached_keys = _PyDict_NewKeysForClass();
     }
 
@@ -4257,7 +4284,6 @@ type_traverse(PyTypeObject *type, visitproc visit, void *arg)
 static int
 type_clear(PyTypeObject *type)
 {
-    PyDictKeysObject *cached_keys;
     /* Because of type_is_gc(), the collector only calls this
        for heaptypes. */
     _PyObject_ASSERT((PyObject *)type, type->tp_flags & Py_TPFLAGS_HEAPTYPE);
@@ -4292,11 +4318,6 @@ type_clear(PyTypeObject *type)
     */
 
     PyType_Modified(type);
-    cached_keys = ((PyHeapTypeObject *)type)->ht_cached_keys;
-    if (cached_keys != NULL) {
-        ((PyHeapTypeObject *)type)->ht_cached_keys = NULL;
-        _PyDictKeys_DecRef(cached_keys);
-    }
     if (type->tp_dict) {
         PyDict_Clear(type->tp_dict);
     }
@@ -4618,6 +4639,7 @@ compatible_with_tp_base(PyTypeObject *child)
             child->tp_itemsize == parent->tp_itemsize &&
             child->tp_dictoffset == parent->tp_dictoffset &&
             child->tp_weaklistoffset == parent->tp_weaklistoffset &&
+            child->tp_inline_values_offset == parent->tp_inline_values_offset &&
             ((child->tp_flags & Py_TPFLAGS_HAVE_GC) ==
              (parent->tp_flags & Py_TPFLAGS_HAVE_GC)) &&
             (child->tp_dealloc == subtype_dealloc ||
@@ -4637,6 +4659,8 @@ same_slots_added(PyTypeObject *a, PyTypeObject *b)
         size += sizeof(PyObject *);
     if (a->tp_weaklistoffset == size && b->tp_weaklistoffset == size)
         size += sizeof(PyObject *);
+    if (a->tp_inline_values_offset == size && b->tp_inline_values_offset == size)
+        size += sizeof(PyObject *);
 
     /* Check slots compliance */
     if (!(a->tp_flags & Py_TPFLAGS_HEAPTYPE) ||
@@ -4781,6 +4805,17 @@ object_set_class(PyObject *self, PyObject *value, void *closure)
     }
 
     if (compatible_for_assignment(oldto, newto, "__class__")) {
+        /* Changing the class will change the implicit dict keys,
+         * so we must materialize the dictionary first. */
+        assert(oldto->tp_inline_values_offset == newto->tp_inline_values_offset);
+        _PyObject_GetDictPtr(self);
+        PyDictValues** values_ptr = _PyObject_ValuesPointer(self);
+        if (values_ptr != NULL && *values_ptr != NULL) {
+            /* Was unable to convert to dict */
+            PyErr_NoMemory();
+            return -1;
+        }
+        assert(_PyObject_ValuesPointer(self) == NULL || *_PyObject_ValuesPointer(self) == NULL);
         if (newto->tp_flags & Py_TPFLAGS_HEAPTYPE) {
             Py_INCREF(newto);
         }
@@ -4906,23 +4941,16 @@ _PyObject_GetState(PyObject *obj, int required)
                          Py_TYPE(obj)->tp_name);
             return NULL;
         }
-
-        {
-            PyObject **dict;
-            dict = _PyObject_GetDictPtr(obj);
-            /* It is possible that the object's dict is not initialized
-               yet. In this case, we will return None for the state.
-               We also return None if the dict is empty to make the behavior
-               consistent regardless whether the dict was initialized or not.
-               This make unit testing easier. */
-            if (dict != NULL && *dict != NULL && PyDict_GET_SIZE(*dict)) {
-                state = *dict;
-            }
-            else {
-                state = Py_None;
-            }
+        if (_PyObject_IsInstanceDictEmpty(obj)) {
+            state = Py_None;
             Py_INCREF(state);
         }
+        else {
+            state = PyObject_GenericGetDict(obj, NULL);
+            if (state == NULL) {
+                return NULL;
+            }
+        }
 
         slotnames = _PyType_GetSlotNames(Py_TYPE(obj));
         if (slotnames == NULL) {
@@ -4933,12 +4961,18 @@ _PyObject_GetState(PyObject *obj, int required)
         assert(slotnames == Py_None || PyList_Check(slotnames));
         if (required) {
             Py_ssize_t basicsize = PyBaseObject_Type.tp_basicsize;
-            if (Py_TYPE(obj)->tp_dictoffset)
+            if (Py_TYPE(obj)->tp_dictoffset) {
                 basicsize += sizeof(PyObject *);
-            if (Py_TYPE(obj)->tp_weaklistoffset)
+            }
+            if (Py_TYPE(obj)->tp_weaklistoffset) {
                 basicsize += sizeof(PyObject *);
-            if (slotnames != Py_None)
+            }
+            if (Py_TYPE(obj)->tp_inline_values_offset) {
+                basicsize += sizeof(PyDictValues *);
+            }
+            if (slotnames != Py_None) {
                 basicsize += sizeof(PyObject *) * PyList_GET_SIZE(slotnames);
+            }
             if (Py_TYPE(obj)->tp_basicsize > basicsize) {
                 Py_DECREF(slotnames);
                 Py_DECREF(state);
@@ -5708,6 +5742,7 @@ inherit_special(PyTypeObject *type, PyTypeObject *base)
     COPYVAL(tp_itemsize);
     COPYVAL(tp_weaklistoffset);
     COPYVAL(tp_dictoffset);
+    COPYVAL(tp_inline_values_offset);
 #undef COPYVAL
 
     /* Setup fast subclass flags */
diff --git a/Python/ceval.c b/Python/ceval.c
index f4cacd8..5cf2ab3 100644
--- a/Python/ceval.c
+++ b/Python/ceval.c
@@ -3618,7 +3618,7 @@ check_eval_breaker:
             }
         }
 
-        TARGET(LOAD_ATTR_SPLIT_KEYS) {
+        TARGET(LOAD_ATTR_INSTANCE_VALUE) {
             assert(cframe.use_tracing == 0);
             PyObject *owner = TOP();
             PyObject *res;
@@ -3629,11 +3629,10 @@ check_eval_breaker:
             assert(cache1->tp_version != 0);
             DEOPT_IF(tp->tp_version_tag != cache1->tp_version, LOAD_ATTR);
             assert(tp->tp_dictoffset > 0);
-            PyDictObject *dict = *(PyDictObject **)(((char *)owner) + tp->tp_dictoffset);
-            DEOPT_IF(dict == NULL, LOAD_ATTR);
-            assert(PyDict_CheckExact((PyObject *)dict));
-            DEOPT_IF(dict->ma_keys->dk_version != cache1->dk_version_or_hint, LOAD_ATTR);
-            res = dict->ma_values->values[cache0->index];
+            assert(tp->tp_inline_values_offset > 0);
+            PyDictValues *values = *(PyDictValues **)(((char *)owner) + tp->tp_inline_values_offset);
+            DEOPT_IF(values == NULL, LOAD_ATTR);
+            res = values->values[cache0->index];
             DEOPT_IF(res == NULL, LOAD_ATTR);
             STAT_INC(LOAD_ATTR, hit);
             record_cache_hit(cache0);
@@ -3725,7 +3724,7 @@ check_eval_breaker:
             }
         }
 
-        TARGET(STORE_ATTR_SPLIT_KEYS) {
+        TARGET(STORE_ATTR_INSTANCE_VALUE) {
             assert(cframe.use_tracing == 0);
             PyObject *owner = TOP();
             PyTypeObject *tp = Py_TYPE(owner);
@@ -3735,31 +3734,23 @@ check_eval_breaker:
             assert(cache1->tp_version != 0);
             DEOPT_IF(tp->tp_version_tag != cache1->tp_version, STORE_ATTR);
             assert(tp->tp_dictoffset > 0);
-            PyDictObject *dict = *(PyDictObject **)(((char *)owner) + tp->tp_dictoffset);
-            DEOPT_IF(dict == NULL, STORE_ATTR);
-            assert(PyDict_CheckExact((PyObject *)dict));
-            DEOPT_IF(dict->ma_keys->dk_version != cache1->dk_version_or_hint, STORE_ATTR);
+            assert(tp->tp_inline_values_offset > 0);
+            PyDictValues *values = *(PyDictValues **)(((char *)owner) + tp->tp_inline_values_offset);
+            DEOPT_IF(values == NULL, STORE_ATTR);
             STAT_INC(STORE_ATTR, hit);
             record_cache_hit(cache0);
             int index = cache0->index;
             STACK_SHRINK(1);
             PyObject *value = POP();
-            PyObject *old_value = dict->ma_values->values[index];
-            dict->ma_values->values[index] = value;
+            PyObject *old_value = values->values[index];
+            values->values[index] = value;
             if (old_value == NULL) {
                 assert(index < 16);
-                dict->ma_values->mv_order = (dict->ma_values->mv_order << 4) | index;
-                dict->ma_used++;
+                values->mv_order = (values->mv_order << 4) | index;
             }
             else {
                 Py_DECREF(old_value);
             }
-            /* Ensure dict is GC tracked if it needs to be */
-            if (!_PyObject_GC_IS_TRACKED(dict) && _PyObject_GC_MAY_BE_TRACKED(value)) {
-                _PyObject_GC_TRACK(dict);
-            }
-            /* PEP 509 */
-            dict->ma_version_tag = DICT_NEXT_VERSION();
             Py_DECREF(owner);
             DISPATCH();
         }
@@ -4474,21 +4465,31 @@ check_eval_breaker:
             _PyObjectCache *cache2 = &caches[-2].obj;
 
             DEOPT_IF(self_cls->tp_version_tag != cache1->tp_version, LOAD_METHOD);
-            assert(cache1->dk_version_or_hint != 0);
-            assert(cache1->tp_version != 0);
-            assert(self_cls->tp_dictoffset >= 0);
-            assert(Py_TYPE(self_cls)->tp_dictoffset > 0);
-
-            // inline version of _PyObject_GetDictPtr for offset >= 0
-            PyObject *dict = self_cls->tp_dictoffset != 0 ?
-                *(PyObject **) ((char *)self + self_cls->tp_dictoffset) : NULL;
-
-            // Ensure self.__dict__ didn't modify keys.
-            // Don't care if self has no dict, it could be builtin or __slots__.
-            DEOPT_IF(dict != NULL &&
-                ((PyDictObject *)dict)->ma_keys->dk_version !=
-                cache1->dk_version_or_hint, LOAD_METHOD);
+            assert(self_cls->tp_dictoffset > 0);
+            assert(self_cls->tp_inline_values_offset > 0);
+            PyDictObject *dict = *(PyDictObject **)(((char *)self) + self_cls->tp_dictoffset);
+            DEOPT_IF(dict != NULL, LOAD_METHOD);
+            DEOPT_IF(((PyHeapTypeObject *)self_cls)->ht_cached_keys->dk_version != cache1->dk_version_or_hint, LOAD_METHOD);
+            STAT_INC(LOAD_METHOD, hit);
+            record_cache_hit(cache0);
+            PyObject *res = cache2->obj;
+            assert(res != NULL);
+            assert(_PyType_HasFeature(Py_TYPE(res), Py_TPFLAGS_METHOD_DESCRIPTOR));
+            Py_INCREF(res);
+            SET_TOP(res);
+            PUSH(self);
+            DISPATCH();
+        }
 
+        TARGET(LOAD_METHOD_NO_DICT) {
+            PyObject *self = TOP();
+            PyTypeObject *self_cls = Py_TYPE(self);
+            SpecializedCacheEntry *caches = GET_CACHE();
+            _PyAdaptiveEntry *cache0 = &caches[0].adaptive;
+            _PyAttrCache *cache1 = &caches[-1].attr;
+            _PyObjectCache *cache2 = &caches[-2].obj;
+            DEOPT_IF(self_cls->tp_version_tag != cache1->tp_version, LOAD_METHOD);
+            assert(self_cls->tp_dictoffset == 0);
             STAT_INC(LOAD_METHOD, hit);
             record_cache_hit(cache0);
             PyObject *res = cache2->obj;
@@ -4530,7 +4531,6 @@ check_eval_breaker:
             record_cache_hit(cache0);
             PyObject *res = cache2->obj;
             assert(res != NULL);
-            assert(_PyType_HasFeature(Py_TYPE(res), Py_TPFLAGS_METHOD_DESCRIPTOR));
             Py_INCREF(res);
             SET_TOP(NULL);
             Py_DECREF(cls);
diff --git a/Python/opcode_targets.h b/Python/opcode_targets.h
index 30df683..773f925 100644
--- a/Python/opcode_targets.h
+++ b/Python/opcode_targets.h
@@ -41,7 +41,7 @@ static void *opcode_targets[256] = {
     &&TARGET_BINARY_SUBSCR_DICT,
     &&TARGET_JUMP_ABSOLUTE_QUICK,
     &&TARGET_LOAD_ATTR_ADAPTIVE,
-    &&TARGET_LOAD_ATTR_SPLIT_KEYS,
+    &&TARGET_LOAD_ATTR_INSTANCE_VALUE,
     &&TARGET_LOAD_ATTR_WITH_HINT,
     &&TARGET_LOAD_ATTR_SLOT,
     &&TARGET_LOAD_ATTR_MODULE,
@@ -87,7 +87,7 @@ static void *opcode_targets[256] = {
     &&TARGET_SETUP_ANNOTATIONS,
     &&TARGET_YIELD_VALUE,
     &&TARGET_LOAD_METHOD_MODULE,
-    &&TARGET_STORE_ATTR_ADAPTIVE,
+    &&TARGET_LOAD_METHOD_NO_DICT,
     &&TARGET_POP_EXCEPT,
     &&TARGET_STORE_NAME,
     &&TARGET_DELETE_NAME,
@@ -119,36 +119,36 @@ static void *opcode_targets[256] = {
     &&TARGET_IS_OP,
     &&TARGET_CONTAINS_OP,
     &&TARGET_RERAISE,
-    &&TARGET_STORE_ATTR_SPLIT_KEYS,
+    &&TARGET_STORE_ATTR_ADAPTIVE,
     &&TARGET_JUMP_IF_NOT_EXC_MATCH,
+    &&TARGET_STORE_ATTR_INSTANCE_VALUE,
     &&TARGET_STORE_ATTR_SLOT,
-    &&TARGET_STORE_ATTR_WITH_HINT,
     &&TARGET_LOAD_FAST,
     &&TARGET_STORE_FAST,
     &&TARGET_DELETE_FAST,
+    &&TARGET_STORE_ATTR_WITH_HINT,
     &&TARGET_LOAD_FAST__LOAD_FAST,
-    &&TARGET_STORE_FAST__LOAD_FAST,
     &&TARGET_GEN_START,
     &&TARGET_RAISE_VARARGS,
     &&TARGET_CALL_FUNCTION,
     &&TARGET_MAKE_FUNCTION,
     &&TARGET_BUILD_SLICE,
-    &&TARGET_LOAD_FAST__LOAD_CONST,
+    &&TARGET_STORE_FAST__LOAD_FAST,
     &&TARGET_MAKE_CELL,
     &&TARGET_LOAD_CLOSURE,
     &&TARGET_LOAD_DEREF,
     &&TARGET_STORE_DEREF,
     &&TARGET_DELETE_DEREF,
-    &&TARGET_LOAD_CONST__LOAD_FAST,
+    &&TARGET_LOAD_FAST__LOAD_CONST,
     &&TARGET_CALL_FUNCTION_KW,
     &&TARGET_CALL_FUNCTION_EX,
-    &&TARGET_STORE_FAST__STORE_FAST,
+    &&TARGET_LOAD_CONST__LOAD_FAST,
     &&TARGET_EXTENDED_ARG,
     &&TARGET_LIST_APPEND,
     &&TARGET_SET_ADD,
     &&TARGET_MAP_ADD,
     &&TARGET_LOAD_CLASSDEREF,
-    &&_unknown_opcode,
+    &&TARGET_STORE_FAST__STORE_FAST,
     &&_unknown_opcode,
     &&_unknown_opcode,
     &&TARGET_MATCH_CLASS,
diff --git a/Python/specialize.c b/Python/specialize.c
index 4e025384..6efee76 100644
--- a/Python/specialize.c
+++ b/Python/specialize.c
@@ -4,6 +4,7 @@
 #include "pycore_dict.h"
 #include "pycore_long.h"
 #include "pycore_moduleobject.h"
+#include "pycore_object.h"
 #include "opcode.h"
 #include "structmember.h"         // struct PyMemberDef, T_OFFSET_EX
 
@@ -462,6 +463,7 @@ specialize_module_load_attr(
     PyObject *value = NULL;
     PyObject *getattr;
     _Py_IDENTIFIER(__getattr__);
+    assert(owner->ob_type->tp_inline_values_offset == 0);
     PyDictObject *dict = (PyDictObject *)m->md_dict;
     if (dict == NULL) {
         SPECIALIZATION_FAIL(opcode, SPEC_FAIL_NO_DICT);
@@ -584,7 +586,7 @@ specialize_dict_access(
     PyObject *owner, _Py_CODEUNIT *instr, PyTypeObject *type,
     DesciptorClassification kind, PyObject *name,
     _PyAdaptiveEntry *cache0, _PyAttrCache *cache1,
-    int base_op, int split_op, int hint_op)
+    int base_op, int values_op, int hint_op)
 {
     assert(kind == NON_OVERRIDING || kind == NON_DESCRIPTOR || kind == ABSENT ||
         kind == BUILTIN_CLASSMETHOD || kind == PYTHON_CLASSMETHOD);
@@ -595,17 +597,11 @@ specialize_dict_access(
     }
     if (type->tp_dictoffset > 0) {
         PyObject **dictptr = (PyObject **) ((char *)owner + type->tp_dictoffset);
-        if (*dictptr == NULL || !PyDict_CheckExact(*dictptr)) {
-            SPECIALIZATION_FAIL(base_op, SPEC_FAIL_NO_DICT);
-            return 0;
-        }
-        // We found an instance with a __dict__.
         PyDictObject *dict = (PyDictObject *)*dictptr;
-        PyDictKeysObject *keys = dict->ma_keys;
-        if ((type->tp_flags & Py_TPFLAGS_HEAPTYPE)
-            && keys == ((PyHeapTypeObject*)type)->ht_cached_keys
-        ) {
-            // Keys are shared
+        if (type->tp_inline_values_offset && dict == NULL) {
+            // Virtual dictionary
+            PyDictKeysObject *keys = ((PyHeapTypeObject *)type)->ht_cached_keys;
+            assert(type->tp_inline_values_offset > 0);
             assert(PyUnicode_CheckExact(name));
             Py_ssize_t index = _PyDictKeys_StringLookup(keys, name);
             assert (index != DKIX_ERROR);
@@ -613,18 +609,17 @@ specialize_dict_access(
                 SPECIALIZATION_FAIL(base_op, SPEC_FAIL_OUT_OF_RANGE);
                 return 0;
             }
-            uint32_t keys_version = _PyDictKeys_GetVersionForCurrentState(keys);
-            if (keys_version == 0) {
-                SPECIALIZATION_FAIL(base_op, SPEC_FAIL_OUT_OF_VERSIONS);
-                return 0;
-            }
-            cache1->dk_version_or_hint = keys_version;
             cache1->tp_version = type->tp_version_tag;
             cache0->index = (uint16_t)index;
-            *instr = _Py_MAKECODEUNIT(split_op, _Py_OPARG(*instr));
+            *instr = _Py_MAKECODEUNIT(values_op, _Py_OPARG(*instr));
             return 0;
         }
         else {
+            if (dict == NULL || !PyDict_CheckExact(dict)) {
+                SPECIALIZATION_FAIL(base_op, SPEC_FAIL_NO_DICT);
+                return 0;
+            }
+            // We found an instance with a __dict__.
             PyObject *value = NULL;
             Py_ssize_t hint =
                 _PyDict_GetItemHint(dict, name, -1, &value);
@@ -736,7 +731,7 @@ _Py_Specialize_LoadAttr(PyObject *owner, _Py_CODEUNIT *instr, PyObject *name, Sp
     }
     int err = specialize_dict_access(
         owner, instr, type, kind, name, cache0, cache1,
-        LOAD_ATTR, LOAD_ATTR_SPLIT_KEYS, LOAD_ATTR_WITH_HINT
+        LOAD_ATTR, LOAD_ATTR_INSTANCE_VALUE, LOAD_ATTR_WITH_HINT
     );
     if (err < 0) {
         return -1;
@@ -818,7 +813,7 @@ _Py_Specialize_StoreAttr(PyObject *owner, _Py_CODEUNIT *instr, PyObject *name, S
 
     int err = specialize_dict_access(
         owner, instr, type, kind, name, cache0, cache1,
-        STORE_ATTR, STORE_ATTR_SPLIT_KEYS, STORE_ATTR_WITH_HINT
+        STORE_ATTR, STORE_ATTR_INSTANCE_VALUE, STORE_ATTR_WITH_HINT
     );
     if (err < 0) {
         return -1;
@@ -875,6 +870,27 @@ load_method_fail_kind(DesciptorClassification kind)
 }
 #endif
 
+static int
+specialize_class_load_method(PyObject *owner, _Py_CODEUNIT *instr, PyObject *name,
+                           _PyAttrCache *cache1, _PyObjectCache *cache2)
+{
+
+    PyObject *descr = NULL;
+    DesciptorClassification kind = 0;
+    kind = analyze_descriptor((PyTypeObject *)owner, name, &descr, 0);
+    switch (kind) {
+        case METHOD:
+        case NON_DESCRIPTOR:
+            cache1->tp_version = ((PyTypeObject *)owner)->tp_version_tag;
+            cache2->obj = descr;
+            *instr = _Py_MAKECODEUNIT(LOAD_METHOD_CLASS, _Py_OPARG(*instr));
+            return 0;
+        default:
+            SPECIALIZATION_FAIL(LOAD_METHOD, load_method_fail_kind(kind));
+            return -1;
+    }
+}
+
 // Please collect stats carefully before and after modifying. A subtle change
 // can cause a significant drop in cache hits. A possible test is
 // python.exe -m test_typing test_re test_dis test_zlib.
@@ -886,7 +902,6 @@ _Py_Specialize_LoadMethod(PyObject *owner, _Py_CODEUNIT *instr, PyObject *name,
     _PyObjectCache *cache2 = &cache[-2].obj;
 
     PyTypeObject *owner_cls = Py_TYPE(owner);
-    PyDictObject *owner_dict = NULL;
     if (PyModule_CheckExact(owner)) {
         int err = specialize_module_load_attr(owner, instr, name, cache0, cache1,
             LOAD_METHOD, LOAD_METHOD_MODULE);
@@ -900,9 +915,12 @@ _Py_Specialize_LoadMethod(PyObject *owner, _Py_CODEUNIT *instr, PyObject *name,
             return -1;
         }
     }
-    if (Py_TYPE(owner_cls)->tp_dictoffset < 0) {
-        SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_OUT_OF_RANGE);
-        goto fail;
+    if (PyType_Check(owner)) {
+        int err = specialize_class_load_method(owner, instr, name, cache1, cache2);
+        if (err) {
+            goto fail;
+        }
+        goto success;
     }
     // Technically this is fine for bound method calls, but it's uncommon and
     // slightly slower at runtime to get dict.
@@ -910,66 +928,45 @@ _Py_Specialize_LoadMethod(PyObject *owner, _Py_CODEUNIT *instr, PyObject *name,
         SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_OUT_OF_RANGE);
         goto fail;
     }
-    PyObject **owner_dictptr = _PyObject_GetDictPtr(owner);
-    int owner_has_dict = (owner_dictptr != NULL && *owner_dictptr != NULL);
-    owner_dict = owner_has_dict ? (PyDictObject *)*owner_dictptr : NULL;
-    // Make sure dict doesn't get GC-ed halfway.
-    Py_XINCREF(owner_dict);
-    // Check for classmethods.
-    int owner_is_class = PyType_Check(owner);
-    owner_cls = owner_is_class ? (PyTypeObject *)owner : owner_cls;
-
-    if ((owner_cls->tp_flags & Py_TPFLAGS_VALID_VERSION_TAG) == 0 ||
-        owner_cls->tp_version_tag == 0) {
-        SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_OUT_OF_VERSIONS);
-        goto fail;
-    }
 
     PyObject *descr = NULL;
     DesciptorClassification kind = 0;
     kind = analyze_descriptor(owner_cls, name, &descr, 0);
-    // Store the version right away, in case it's modified halfway through.
-    cache1->tp_version = owner_cls->tp_version_tag;
-
     assert(descr != NULL || kind == ABSENT || kind == GETSET_OVERRIDDEN);
     if (kind != METHOD) {
         SPECIALIZATION_FAIL(LOAD_METHOD, load_method_fail_kind(kind));
         goto fail;
     }
-    // If o.__dict__ changes, the method might be found in o.__dict__
-    // instead of old type lookup. So record o.__dict__'s keys.
-    uint32_t keys_version = UINT32_MAX;
-    if (owner_has_dict) {
-        // _PyDictKeys_GetVersionForCurrentState isn't accurate for
-        // custom dict subclasses at the moment.
-        if (!PyDict_CheckExact(owner_dict)) {
-            SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_DICT_SUBCLASS);
+    if (owner_cls->tp_inline_values_offset) {
+        PyObject **owner_dictptr = _PyObject_DictPointer(owner);
+        assert(owner_dictptr);
+        if (*owner_dictptr) {
+            SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_IS_ATTR);
             goto fail;
         }
-        assert(PyUnicode_CheckExact(name));
-        Py_hash_t hash = PyObject_Hash(name);
-        if (hash == -1) {
-            return -1;
-        }
-        PyObject *value = NULL;
-        if (!owner_is_class) {
-            // Instance methods shouldn't be in o.__dict__. That makes
-            // it an attribute.
-            Py_ssize_t ix = _Py_dict_lookup(owner_dict, name, hash, &value);
-            assert(ix != DKIX_ERROR);
-            if (ix != DKIX_EMPTY) {
-                SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_IS_ATTR);
-                goto fail;
-            }
+        PyDictKeysObject *keys = ((PyHeapTypeObject *)owner_cls)->ht_cached_keys;
+        Py_ssize_t index = _PyDictKeys_StringLookup(keys, name);
+        if (index != DKIX_EMPTY) {
+            SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_IS_ATTR);
+            goto fail;
         }
-        keys_version = _PyDictKeys_GetVersionForCurrentState(owner_dict->ma_keys);
+        uint32_t keys_version = _PyDictKeys_GetVersionForCurrentState(keys);
         if (keys_version == 0) {
-            SPECIALIZATION_FAIL(LOAD_ATTR, SPEC_FAIL_OUT_OF_VERSIONS);
+            SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_OUT_OF_VERSIONS);
             goto fail;
         }
-        // Fall through.
-    } // Else owner is maybe a builtin with no dict, or __slots__. Doesn't matter.
-
+        cache1->dk_version_or_hint = keys_version;
+        *instr = _Py_MAKECODEUNIT(LOAD_METHOD_CACHED, _Py_OPARG(*instr));
+    }
+    else {
+        if (owner_cls->tp_dictoffset == 0) {
+            *instr = _Py_MAKECODEUNIT(LOAD_METHOD_NO_DICT, _Py_OPARG(*instr));
+        }
+        else {
+            SPECIALIZATION_FAIL(LOAD_METHOD, SPEC_FAIL_IS_ATTR);
+            goto fail;
+        }
+    }
     /* `descr` is borrowed. This is safe for methods (even inherited ones from
     *  super classes!) as long as tp_version_tag is validated for two main reasons:
     *
@@ -984,19 +981,15 @@ _Py_Specialize_LoadMethod(PyObject *owner, _Py_CODEUNIT *instr, PyObject *name,
     *  PyType_Modified usages in typeobject.c). The MCACHE has been
     *  working since Python 2.6 and it's battle-tested.
     */
+    cache1->tp_version = owner_cls->tp_version_tag;
     cache2->obj = descr;
-    cache1->dk_version_or_hint = keys_version;
-    *instr = _Py_MAKECODEUNIT(owner_is_class ? LOAD_METHOD_CLASS :
-        LOAD_METHOD_CACHED, _Py_OPARG(*instr));
     // Fall through.
 success:
-    Py_XDECREF(owner_dict);
     STAT_INC(LOAD_METHOD, specialization_success);
     assert(!PyErr_Occurred());
     cache0->counter = saturating_start();
     return 0;
 fail:
-    Py_XDECREF(owner_dict);
     STAT_INC(LOAD_METHOD, specialization_failure);
     assert(!PyErr_Occurred());
     cache_backoff(cache0);
diff --git a/Tools/gdb/libpython.py b/Tools/gdb/libpython.py
index a118d32..54f7232 100755
--- a/Tools/gdb/libpython.py
+++ b/Tools/gdb/libpython.py
@@ -445,10 +445,11 @@ def _write_instance_repr(out, visited, name, pyop_attrdict, address):
     out.write(name)
 
     # Write dictionary of instance attributes:
-    if isinstance(pyop_attrdict, PyDictObjectPtr):
+    if isinstance(pyop_attrdict, (PyKeysValuesPair, PyDictObjectPtr)):
         out.write('(')
         first = True
-        for pyop_arg, pyop_val in pyop_attrdict.iteritems():
+        items = pyop_attrdict.iteritems()
+        for pyop_arg, pyop_val in items:
             if not first:
                 out.write(', ')
             first = False
@@ -520,6 +521,25 @@ class HeapTypeObjectPtr(PyObjectPtr):
         # Not found, or some kind of error:
         return None
 
+    def get_keys_values(self):
+        typeobj = self.type()
+        values_offset = int_from_int(typeobj.field('tp_inline_values_offset'))
+        if values_offset == 0:
+            return None
+        charptr = self._gdbval.cast(_type_char_ptr()) + values_offset
+        PyDictValuesPtrPtr = gdb.lookup_type("PyDictValues").pointer().pointer()
+        valuesptr = charptr.cast(PyDictValuesPtrPtr)
+        values = valuesptr.dereference()
+        if long(values) == 0:
+            return None
+        values = values['values']
+        return PyKeysValuesPair(self.get_cached_keys(), values)
+
+    def get_cached_keys(self):
+        typeobj = self.type()
+        HeapTypePtr = gdb.lookup_type("PyHeapTypeObject").pointer()
+        return typeobj._gdbval.cast(HeapTypePtr)['ht_cached_keys']
+
     def proxyval(self, visited):
         '''
         Support for classes.
@@ -533,7 +553,10 @@ class HeapTypeObjectPtr(PyObjectPtr):
         visited.add(self.as_address())
 
         pyop_attr_dict = self.get_attr_dict()
-        if pyop_attr_dict:
+        keys_values = self.get_keys_values()
+        if keys_values:
+            attr_dict = keys_values.proxyval(visited)
+        elif pyop_attr_dict:
             attr_dict = pyop_attr_dict.proxyval(visited)
         else:
             attr_dict = {}
@@ -549,9 +572,11 @@ class HeapTypeObjectPtr(PyObjectPtr):
             return
         visited.add(self.as_address())
 
-        pyop_attrdict = self.get_attr_dict()
+        pyop_attrs = self.get_keys_values()
+        if not pyop_attrs:
+            pyop_attrs = self.get_attr_dict()
         _write_instance_repr(out, visited,
-                             self.safe_tp_name(), pyop_attrdict, self.as_address())
+                             self.safe_tp_name(), pyop_attrs, self.as_address())
 
 class ProxyException(Exception):
     def __init__(self, tp_name, args):
@@ -673,6 +698,32 @@ class PyCodeObjectPtr(PyObjectPtr):
         assert False, "Unreachable"
 
 
+def items_from_keys_and_values(keys, values):
+    entries, nentries = PyDictObjectPtr._get_entries(keys)
+    for i in safe_range(nentries):
+        ep = entries[i]
+        pyop_value = PyObjectPtr.from_pyobject_ptr(values[i])
+        if not pyop_value.is_null():
+            pyop_key = PyObjectPtr.from_pyobject_ptr(ep['me_key'])
+            yield (pyop_key, pyop_value)
+
+class PyKeysValuesPair:
+
+    def __init__(self, keys, values):
+        self.keys = keys
+        self.values = values
+
+    def iteritems(self):
+        return items_from_keys_and_values(self.keys, self.values)
+
+    def proxyval(self, visited):
+        result = {}
+        for pyop_key, pyop_value in self.iteritems():
+            proxy_key = pyop_key.proxyval(visited)
+            proxy_value = pyop_value.proxyval(visited)
+            result[proxy_key] = proxy_value
+        return result
+
 class PyDictObjectPtr(PyObjectPtr):
     """
     Class wrapping a gdb.Value that's a PyDictObject* i.e. a dict instance
@@ -690,13 +741,14 @@ class PyDictObjectPtr(PyObjectPtr):
         has_values = long(values)
         if has_values:
             values = values['values']
+        if has_values:
+            for item in items_from_keys_and_values(keys, values):
+                yield item
+            return
         entries, nentries = self._get_entries(keys)
         for i in safe_range(nentries):
             ep = entries[i]
-            if has_values:
-                pyop_value = PyObjectPtr.from_pyobject_ptr(values[i])
-            else:
-                pyop_value = PyObjectPtr.from_pyobject_ptr(ep['me_value'])
+            pyop_value = PyObjectPtr.from_pyobject_ptr(ep['me_value'])
             if not pyop_value.is_null():
                 pyop_key = PyObjectPtr.from_pyobject_ptr(ep['me_key'])
                 yield (pyop_key, pyop_value)
@@ -732,7 +784,8 @@ class PyDictObjectPtr(PyObjectPtr):
             pyop_value.write_repr(out, visited)
         out.write('}')
 
-    def _get_entries(self, keys):
+    @staticmethod
+    def _get_entries(keys):
         dk_nentries = int(keys['dk_nentries'])
         dk_size = 1<<int(keys['dk_log2_size'])
         try:
@@ -1958,7 +2011,7 @@ def move_in_stack(move_up):
         print('Unable to find an older python frame')
     else:
         print('Unable to find a newer python frame')
-    
+
 
 class PyUp(gdb.Command):
     'Select and print all python stack frame in the same eval loop starting from the one that called this one (if any)'