[3.14] gh-139103: fix free-threading dataclass.__init__ perf issue (gh-141596) (gh-141750)

The dataclasses `__init__` function is generated dynamically by a call to `exec()` and so doesn't have deferred reference counting enabled. Enable deferred reference counting on functions when assigned as an attribute to type objects to avoid reference count contention when creating dataclass instances.
(cherry picked from commit ce79154176)

Co-authored-by: Edward Xu <xuxiangad@gmail.com>

Misc/NEWS.d/next/Core_and_Builtins/2025-11-15-23-58-23.gh-issue-139103.9cVYJ0.rst

@@ -0,0 +1 @@
+Improve multithreaded scaling of dataclasses on the free-threaded build.

Objects/typeobject.c

@@ -6181,6 +6181,18 @@ type_setattro(PyObject *self, PyObject *name, PyObject *value)
     assert(!_PyType_HasFeature(metatype, Py_TPFLAGS_INLINE_VALUES));
     assert(!_PyType_HasFeature(metatype, Py_TPFLAGS_MANAGED_DICT));
 
+#ifdef Py_GIL_DISABLED
+    // gh-139103: Enable deferred refcounting for functions assigned
+    // to type objects.  This is important for `dataclass.__init__`,
+    // which is generated dynamically.
+    if (value != NULL &&
+        PyFunction_Check(value) &&
+        !_PyObject_HasDeferredRefcount(value))
+    {
+        PyUnstable_Object_EnableDeferredRefcount(value);
+    }
+#endif
+
     PyObject *old_value = NULL;
     PyObject *descr = _PyType_LookupRef(metatype, name);
     if (descr != NULL) {

Tools/ftscalingbench/ftscalingbench.py

@@ -27,6 +27,7 @@
 import sys
 import threading
 import time
+from dataclasses import dataclass
 
 # The iterations in individual benchmarks are scaled by this factor.
 WORK_SCALE = 100
@@ -189,6 +190,17 @@ def thread_local_read():
         _ = tmp.x
 
 
+@dataclass
+class MyDataClass:
+    x: int
+    y: int
+    z: int
+
+@register_benchmark
+def instantiate_dataclass():
+    for _ in range(1000 * WORK_SCALE):
+        obj = MyDataClass(x=1, y=2, z=3)
+
 def bench_one_thread(func):
     t0 = time.perf_counter_ns()
     func()