make __Pyx_PyFunction_FastCallNoKw compatible with Stackless Python

Compute the offset of the PyFrameObject member "f_localsplus" at runtime,
because the layout of PyFrameObject differs between regular C-python and
Stackless Python.

Cython/Compiler/ModuleNode.py

@@ -2357,6 +2357,7 @@ class ModuleNode(Nodes.Node, Nodes.BlockNode):
         env.use_utility_code(UtilityCode.load("CheckBinaryVersion", "ModuleSetupCode.c"))
         code.put_error_if_neg(self.pos, "__Pyx_check_binary_version()")
 
+        code.putln("__Pxy_PyFrame_Initialize_Offsets();")
         code.putln("%s = PyTuple_New(0); %s" % (
             Naming.empty_tuple, code.error_goto_if_null(Naming.empty_tuple, self.pos)))
         code.putln("%s = PyBytes_FromStringAndSize(\"\", 0); %s" % (

Cython/Utility/ModuleSetupCode.c

@@ -412,6 +412,45 @@ class __Pyx_FakeReference {
 #define __Pyx_PyFastCFunction_Check(func) 0
 #endif
 
+/* back port from Python 3 */
+#ifndef Py_BUILD_ASSERT_EXPR
+/* Assert a build-time dependency, as an expression.
+
+   Your compile will fail if the condition isn't true, or can't be evaluated
+   by the compiler. This can be used in an expression: its value is 0.
+
+   Example:
+
+   #define foo_to_char(foo)  \
+       ((char *)(foo)        \
+        + Py_BUILD_ASSERT_EXPR(offsetof(struct foo, string) == 0))
+
+   Written by Rusty Russell, public domain, http://ccodearchive.net/ */
+#define Py_BUILD_ASSERT_EXPR(cond) \
+    (sizeof(char [1 - 2*!(cond)]) - 1)
+#endif
+#ifndef Py_MEMBER_SIZE
+/* Get the size of a structure member in bytes */
+#define Py_MEMBER_SIZE(type, member) sizeof(((type *)0)->member)
+#endif
+
+#ifdef CYTHON_FAST_PYCALL
+  #include "frameobject.h"
+  // offsetof(PyFrameObject, f_localsplus) differs between regular C-Python and Stackless Python.
+  // Therefore the offset is computed at run time from PyFrame_type.tp_basicsize. That is feasible,
+  // because f_localsplus is the last field of PyFrameObject (checked by Py_BUILD_ASSERT_EXPR).
+  static size_t __pyx_pyframe_localsplus_offset = 0;
+  #define __Pxy_PyFrame_Initialize_Offsets()  \
+    ((void)Py_BUILD_ASSERT_EXPR(sizeof(PyFrameObject) == offsetof(PyFrameObject, f_localsplus) + Py_MEMBER_SIZE(PyFrameObject, f_localsplus)), \
+     (void)(__pyx_pyframe_localsplus_offset = PyFrame_Type.tp_basicsize - Py_MEMBER_SIZE(PyFrameObject, f_localsplus)))
+  #define __Pyx_PyFrame_GetLocalsplus(frame)  \
+    (assert(__pyx_pyframe_localsplus_offset), (PyObject **)(((char *)(frame)) + __pyx_pyframe_localsplus_offset))
+#else
+  #define __Pxy_PyFrame_Initialize_Offsets()  /* empty */
+  // not used
+  // #define __Pyx_PyFrame_GetLocalsplus(frame)  ((frame)->f_localsplus)
+#endif
+
 #if CYTHON_USE_DICT_VERSIONS
 #define __PYX_GET_DICT_VERSION(dict)  (((PyDictObject*)(dict))->ma_version_tag)
 #define __PYX_UPDATE_DICT_CACHE(dict, value, cache_var, version_var) \

Cython/Utility/ObjectHandling.c

@@ -1942,7 +1942,6 @@ static PyObject *__Pyx_PyFunction_FastCallDict(PyObject *func, PyObject **args,
 // copied from CPython 3.6 ceval.c
 
 #if CYTHON_FAST_PYCALL
-#include "frameobject.h"
 
 static PyObject* __Pyx_PyFunction_FastCallNoKw(PyCodeObject *co, PyObject **args, Py_ssize_t na,
                                                PyObject *globals) {
@@ -1963,7 +1962,7 @@ static PyObject* __Pyx_PyFunction_FastCallNoKw(PyCodeObject *co, PyObject **args
         return NULL;
     }
 
-    fastlocals = f->f_localsplus;
+    fastlocals = __Pyx_PyFrame_GetLocalsplus(f);
 
     for (i = 0; i < na; i++) {
         Py_INCREF(*args);