diff --git a/Include/internal/pycore_call.h b/Include/internal/pycore_call.h
index 28a4194db74845..933d714f13377c 100644
--- a/Include/internal/pycore_call.h
+++ b/Include/internal/pycore_call.h
@@ -8,6 +8,8 @@ extern "C" {
 #  error "this header requires Py_BUILD_CORE define"
 #endif
 
+#include "pycore_pystate.h"       // _PyThreadState_GET()
+
 PyAPI_FUNC(PyObject *) _PyObject_Call_Prepend(
     PyThreadState *tstate,
     PyObject *callable,
@@ -36,7 +38,7 @@ _PyObject_CallNoArgsTstate(PyThreadState *tstate, PyObject *func) {
 // Private static inline function variant of public PyObject_CallNoArgs()
 static inline PyObject *
 _PyObject_CallNoArgs(PyObject *func) {
-    PyThreadState *tstate = PyThreadState_Get();
+    PyThreadState *tstate = _PyThreadState_GET();
     return _PyObject_VectorcallTstate(tstate, func, NULL, 0, NULL);
 }
 
diff --git a/Include/internal/pycore_ceval.h b/Include/internal/pycore_ceval.h
index f2acf10df8c233..53580b99d33ac6 100644
--- a/Include/internal/pycore_ceval.h
+++ b/Include/internal/pycore_ceval.h
@@ -12,7 +12,8 @@ extern "C" {
 struct pyruntimestate;
 struct _ceval_runtime_state;
 
-#include "pycore_interp.h"   /* PyInterpreterState.eval_frame */
+#include "pycore_interp.h"        // PyInterpreterState.eval_frame
+#include "pycore_pystate.h"       // _PyThreadState_GET()
 
 extern void _Py_FinishPendingCalls(PyThreadState *tstate);
 extern void _PyEval_InitRuntimeState(struct _ceval_runtime_state *);
@@ -93,7 +94,7 @@ static inline int _Py_EnterRecursiveCall(PyThreadState *tstate,
 }
 
 static inline int _Py_EnterRecursiveCall_inline(const char *where) {
-    PyThreadState *tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     return _Py_EnterRecursiveCall(tstate, where);
 }
 
@@ -104,7 +105,7 @@ static inline void _Py_LeaveRecursiveCall(PyThreadState *tstate)  {
 }
 
 static inline void _Py_LeaveRecursiveCall_inline(void)  {
-    PyThreadState *tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     _Py_LeaveRecursiveCall(tstate);
 }
 
diff --git a/Include/internal/pycore_pystate.h b/Include/internal/pycore_pystate.h
index aef318989aa6e5..1b74e5ffb0473e 100644
--- a/Include/internal/pycore_pystate.h
+++ b/Include/internal/pycore_pystate.h
@@ -82,7 +82,7 @@ _PyRuntimeState_GetThreadState(_PyRuntimeState *runtime)
 
    The caller must hold the GIL.
 
-   See also PyThreadState_Get() and PyThreadState_GET(). */
+   See also PyThreadState_Get() and _PyThreadState_UncheckedGet(). */
 static inline PyThreadState*
 _PyThreadState_GET(void)
 {
@@ -93,10 +93,6 @@ _PyThreadState_GET(void)
 #endif
 }
 
-/* Redefine PyThreadState_GET() as an alias to _PyThreadState_GET() */
-#undef PyThreadState_GET
-#define PyThreadState_GET() _PyThreadState_GET()
-
 PyAPI_FUNC(void) _Py_NO_RETURN _Py_FatalError_TstateNULL(const char *func);
 
 static inline void
diff --git a/Include/pystate.h b/Include/pystate.h
index bae440778b261a..d81f42a3efe321 100644
--- a/Include/pystate.h
+++ b/Include/pystate.h
@@ -66,18 +66,10 @@ PyAPI_FUNC(void) PyThreadState_Delete(PyThreadState *);
 
    The caller must hold the GIL.
 
-   See also PyThreadState_GET() and _PyThreadState_GET(). */
+   See also _PyThreadState_UncheckedGet() and _PyThreadState_GET(). */
 PyAPI_FUNC(PyThreadState *) PyThreadState_Get(void);
 
-/* Get the current Python thread state.
-
-   Macro using PyThreadState_Get() or _PyThreadState_GET() depending if
-   pycore_pystate.h is included or not (this header redefines the macro).
-
-   If PyThreadState_Get() is used, issue a fatal error if the current thread
-   state is NULL.
-
-   See also PyThreadState_Get() and _PyThreadState_GET(). */
+// Alias to PyThreadState_Get()
 #define PyThreadState_GET() PyThreadState_Get()
 
 PyAPI_FUNC(PyThreadState *) PyThreadState_Swap(PyThreadState *);
diff --git a/Modules/_asynciomodule.c b/Modules/_asynciomodule.c
index 56079b0277d1a6..adc5ff9f796cca 100644
--- a/Modules/_asynciomodule.c
+++ b/Modules/_asynciomodule.c
@@ -1,5 +1,6 @@
 #include "Python.h"
 #include "pycore_pyerrors.h"      // _PyErr_ClearExcState()
+#include "pycore_pystate.h"       // _PyThreadState_GET()
 #include <stddef.h>               // offsetof()
 
 
@@ -225,7 +226,7 @@ get_running_loop(PyObject **loop)
 {
     PyObject *rl;
 
-    PyThreadState *ts = PyThreadState_Get();
+    PyThreadState *ts = _PyThreadState_GET();
     uint64_t ts_id = PyThreadState_GetID(ts);
     if (ts_id == cached_running_holder_tsid && cached_running_holder != NULL) {
         // Fast path, check the cache.
@@ -287,7 +288,7 @@ set_running_loop(PyObject *loop)
 {
     PyObject *ts_dict = NULL;
 
-    PyThreadState *tstate = PyThreadState_Get();
+    PyThreadState *tstate = _PyThreadState_GET();
     if (tstate != NULL) {
         ts_dict = _PyThreadState_GetDict(tstate);  // borrowed
     }
diff --git a/Modules/_ctypes/_ctypes.c b/Modules/_ctypes/_ctypes.c
index 2567067f0b39fa..f8940fdbed2424 100644
--- a/Modules/_ctypes/_ctypes.c
+++ b/Modules/_ctypes/_ctypes.c
@@ -102,12 +102,16 @@ bytes(cdata)
 #define PY_SSIZE_T_CLEAN
 
 #include "Python.h"
+// windows.h must be included before pycore internal headers
+#ifdef MS_WIN32
+#  include <windows.h>
+#endif
+
 #include "pycore_call.h"          // _PyObject_CallNoArgs()
 #include "structmember.h"         // PyMemberDef
 
 #include <ffi.h>
 #ifdef MS_WIN32
-#include <windows.h>
 #include <malloc.h>
 #ifndef IS_INTRESOURCE
 #define IS_INTRESOURCE(x) (((size_t)(x) >> 16) == 0)
diff --git a/Modules/_ctypes/callbacks.c b/Modules/_ctypes/callbacks.c
index 18b010493628c9..c24f04ce3a0f8e 100644
--- a/Modules/_ctypes/callbacks.c
+++ b/Modules/_ctypes/callbacks.c
@@ -1,13 +1,15 @@
 #include "Python.h"
+// windows.h must be included before pycore internal headers
+#ifdef MS_WIN32
+#  include <windows.h>
+#endif
+
 #include "pycore_call.h"          // _PyObject_CallNoArgs()
 #include "frameobject.h"
 
 #include <stdbool.h>
 
 #include <ffi.h>
-#ifdef MS_WIN32
-#include <windows.h>
-#endif
 #include "ctypes.h"
 
 /**************************************************************/
diff --git a/Modules/_ctypes/cfield.c b/Modules/_ctypes/cfield.c
index 6788aee78a2d30..b7585bc8a9fffb 100644
--- a/Modules/_ctypes/cfield.c
+++ b/Modules/_ctypes/cfield.c
@@ -1,11 +1,13 @@
 #include "Python.h"
+// windows.h must be included before pycore internal headers
+#ifdef MS_WIN32
+#  include <windows.h>
+#endif
+
 #include "pycore_bitutils.h"      // _Py_bswap32()
 #include "pycore_call.h"          // _PyObject_CallNoArgs()
 
 #include <ffi.h>
-#ifdef MS_WIN32
-#include <windows.h>
-#endif
 #include "ctypes.h"
 
 
diff --git a/Modules/_ctypes/stgdict.c b/Modules/_ctypes/stgdict.c
index ea3c58b88e704a..43669d7152a7e9 100644
--- a/Modules/_ctypes/stgdict.c
+++ b/Modules/_ctypes/stgdict.c
@@ -1,9 +1,13 @@
 #include "Python.h"
+// windows.h must be included before pycore internal headers
+#ifdef MS_WIN32
+#  include <windows.h>
+#endif
+
 #include "pycore_call.h"          // _PyObject_CallNoArgs()
 #include <ffi.h>
 #ifdef MS_WIN32
-#include <windows.h>
-#include <malloc.h>
+#  include <malloc.h>
 #endif
 #include "ctypes.h"
 
diff --git a/Modules/_decimal/_decimal.c b/Modules/_decimal/_decimal.c
index e2979a577c96c7..dd876f200365d5 100644
--- a/Modules/_decimal/_decimal.c
+++ b/Modules/_decimal/_decimal.c
@@ -27,6 +27,7 @@
 
 
 #include <Python.h>
+#include "pycore_pystate.h"       // _PyThreadState_GET()
 #include "longintrepr.h"
 #include "complexobject.h"
 #include "mpdecimal.h"
@@ -1511,18 +1512,20 @@ static PyGetSetDef context_getsets [] =
 static PyObject *
 current_context_from_dict(void)
 {
-    PyObject *dict;
-    PyObject *tl_context;
-    PyThreadState *tstate;
+    PyThreadState *tstate = _PyThreadState_GET();
+#ifdef Py_DEBUG
+    // The caller must hold the GIL
+    _Py_EnsureTstateNotNULL(tstate);
+#endif
 
-    dict = PyThreadState_GetDict();
+    PyObject *dict = _PyThreadState_GetDict(tstate);
     if (dict == NULL) {
         PyErr_SetString(PyExc_RuntimeError,
             "cannot get thread state");
         return NULL;
     }
 
-    tl_context = PyDict_GetItemWithError(dict, tls_context_key);
+    PyObject *tl_context = PyDict_GetItemWithError(dict, tls_context_key);
     if (tl_context != NULL) {
         /* We already have a thread local context. */
         CONTEXT_CHECK(tl_context);
@@ -1548,11 +1551,8 @@ current_context_from_dict(void)
 
     /* Cache the context of the current thread, assuming that it
      * will be accessed several times before a thread switch. */
-    tstate = PyThreadState_GET();
-    if (tstate) {
-        cached_context = (PyDecContextObject *)tl_context;
-        cached_context->tstate = tstate;
-    }
+    cached_context = (PyDecContextObject *)tl_context;
+    cached_context->tstate = tstate;
 
     /* Borrowed reference with refcount==1 */
     return tl_context;
@@ -1562,9 +1562,7 @@ current_context_from_dict(void)
 static PyObject *
 current_context(void)
 {
-    PyThreadState *tstate;
-
-    tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     if (cached_context && cached_context->tstate == tstate) {
         return (PyObject *)cached_context;
     }
diff --git a/Modules/_lsprof.c b/Modules/_lsprof.c
index 097d0eff2602d1..2e27afcea1b799 100644
--- a/Modules/_lsprof.c
+++ b/Modules/_lsprof.c
@@ -1,5 +1,6 @@
 #include "Python.h"
 #include "pycore_call.h"          // _PyObject_CallNoArgs()
+#include "pycore_pystate.h"       // _PyThreadState_GET()
 #include "rotatingtree.h"
 
 /************************************************************/
@@ -672,7 +673,7 @@ profiler_enable(ProfilerObject *self, PyObject *args, PyObject *kwds)
         return NULL;
     }
 
-    PyThreadState *tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     if (_PyEval_SetProfile(tstate, profiler_callback, (PyObject*)self) < 0) {
         return NULL;
     }
@@ -706,7 +707,7 @@ Stop collecting profiling information.\n\
 static PyObject*
 profiler_disable(ProfilerObject *self, PyObject* noarg)
 {
-    PyThreadState *tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     if (_PyEval_SetProfile(tstate, NULL, NULL) < 0) {
         return NULL;
     }
@@ -743,7 +744,7 @@ static void
 profiler_dealloc(ProfilerObject *op)
 {
     if (op->flags & POF_ENABLED) {
-        PyThreadState *tstate = PyThreadState_GET();
+        PyThreadState *tstate = _PyThreadState_GET();
         if (_PyEval_SetProfile(tstate, NULL, NULL) < 0) {
             PyErr_WriteUnraisable((PyObject *)op);
         }
diff --git a/Modules/_testinternalcapi.c b/Modules/_testinternalcapi.c
index d5616fd59c6e50..3ba939651a4173 100644
--- a/Modules/_testinternalcapi.c
+++ b/Modules/_testinternalcapi.c
@@ -18,7 +18,8 @@
 #include "pycore_hashtable.h"    // _Py_hashtable_new()
 #include "pycore_initconfig.h"   // _Py_GetConfigsAsDict()
 #include "pycore_interp.h"       // _PyInterpreterState_GetConfigCopy()
-#include "pycore_pyerrors.h"      // _Py_UTF8_Edit_Cost()
+#include "pycore_pyerrors.h"     // _Py_UTF8_Edit_Cost()
+#include "pycore_pystate.h"      // _PyThreadState_GET()
 
 
 static PyObject *
@@ -31,7 +32,7 @@ get_configs(PyObject *self, PyObject *Py_UNUSED(args))
 static PyObject*
 get_recursion_depth(PyObject *self, PyObject *Py_UNUSED(args))
 {
-    PyThreadState *tstate = PyThreadState_Get();
+    PyThreadState *tstate = _PyThreadState_GET();
 
     /* subtract one to ignore the frame of the get_recursion_depth() call */
     return PyLong_FromLong(tstate->recursion_depth - 1);
diff --git a/Modules/_threadmodule.c b/Modules/_threadmodule.c
index ff858386b426ff..39b116afcaa3e1 100644
--- a/Modules/_threadmodule.c
+++ b/Modules/_threadmodule.c
@@ -1319,7 +1319,7 @@ static PyObject *
 thread__set_sentinel(PyObject *module, PyObject *Py_UNUSED(ignored))
 {
     PyObject *wr;
-    PyThreadState *tstate = PyThreadState_Get();
+    PyThreadState *tstate = _PyThreadState_GET();
     lockobject *lock;
 
     if (tstate->on_delete_data != NULL) {
diff --git a/Modules/_xxsubinterpretersmodule.c b/Modules/_xxsubinterpretersmodule.c
index 11b55f7f0c7d1b..939114e60cae97 100644
--- a/Modules/_xxsubinterpretersmodule.c
+++ b/Modules/_xxsubinterpretersmodule.c
@@ -5,6 +5,7 @@
 #include "Python.h"
 #include "frameobject.h"
 #include "pycore_frame.h"
+#include "pycore_pystate.h"       // _PyThreadState_GET()
 #include "interpreteridobject.h"
 
 
@@ -2017,7 +2018,7 @@ interp_create(PyObject *self, PyObject *args, PyObject *kwds)
     }
 
     // Create and initialize the new interpreter.
-    PyThreadState *save_tstate = PyThreadState_Get();
+    PyThreadState *save_tstate = _PyThreadState_GET();
     // XXX Possible GILState issues?
     PyThreadState *tstate = _Py_NewInterpreter(isolated);
     PyThreadState_Swap(save_tstate);
diff --git a/Modules/posixmodule.c b/Modules/posixmodule.c
index ada1a5865aae7c..9c174ee6b18df3 100644
--- a/Modules/posixmodule.c
+++ b/Modules/posixmodule.c
@@ -10,31 +10,25 @@
 #define PY_SSIZE_T_CLEAN
 
 #include "Python.h"
-#include "pycore_call.h"          // _PyObject_CallNoArgs()
-#include "pycore_fileutils.h"     // _Py_closerange()
-#include "pycore_moduleobject.h"  // _PyModule_GetState()
+// Include <windows.h> before pycore internal headers. FSCTL_GET_REPARSE_POINT
+// is not exported by <windows.h> if the WIN32_LEAN_AND_MEAN macro is defined,
+// whereas pycore_condvar.h defines the WIN32_LEAN_AND_MEAN macro.
 #ifdef MS_WINDOWS
-   /* include <windows.h> early to avoid conflict with pycore_condvar.h:
-
-        #define WIN32_LEAN_AND_MEAN
-        #include <windows.h>
-
-      FSCTL_GET_REPARSE_POINT is not exported with WIN32_LEAN_AND_MEAN. */
 #  include <windows.h>
 #  include <pathcch.h>
 #endif
 
-#if !defined(EX_OK) && defined(EXIT_SUCCESS)
-#define EX_OK EXIT_SUCCESS
-#endif
-
 #ifdef __VXWORKS__
 #  include "pycore_bitutils.h"    // _Py_popcount32()
 #endif
+#include "pycore_call.h"          // _PyObject_CallNoArgs()
+#include "pycore_fileutils.h"     // _Py_closerange()
+#include "pycore_moduleobject.h"  // _PyModule_GetState()
 #include "pycore_ceval.h"         // _PyEval_ReInitThreads()
 #include "pycore_import.h"        // _PyImport_ReInitLock()
 #include "pycore_initconfig.h"    // _PyStatus_EXCEPTION()
 #include "pycore_pystate.h"       // _PyInterpreterState_GET()
+
 #include "structmember.h"         // PyMemberDef
 #ifndef MS_WINDOWS
 #  include "posixmodule.h"
@@ -42,6 +36,10 @@
 #  include "winreparse.h"
 #endif
 
+#if !defined(EX_OK) && defined(EXIT_SUCCESS)
+#  define EX_OK EXIT_SUCCESS
+#endif
+
 /* On android API level 21, 'AT_EACCESS' is not declared although
  * HAVE_FACCESSAT is defined. */
 #ifdef __ANDROID__
diff --git a/Objects/typeobject.c b/Objects/typeobject.c
index 0f56e59bc51853..544e8a4aa22112 100644
--- a/Objects/typeobject.c
+++ b/Objects/typeobject.c
@@ -3332,7 +3332,7 @@ type_vectorcall(PyObject *metatype, PyObject *const *args,
     }
     /* In other (much less common) cases, fall back to
        more flexible calling conventions. */
-    PyThreadState *tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     return _PyObject_MakeTpCall(tstate, metatype, args, nargs, kwnames);
 }
 
diff --git a/Python/bltinmodule.c b/Python/bltinmodule.c
index d07ba38b698c6b..9e3b25c59a5505 100644
--- a/Python/bltinmodule.c
+++ b/Python/bltinmodule.c
@@ -213,7 +213,7 @@ builtin___build_class__(PyObject *self, PyObject *const *args, Py_ssize_t nargs,
         goto error;
     }
     PyFrameConstructor *f =  PyFunction_AS_FRAME_CONSTRUCTOR(func);
-    PyThreadState *tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     cell = _PyEval_Vector(tstate, f, ns, NULL, 0, NULL);
     if (cell != NULL) {
         if (bases != orig_bases) {
diff --git a/Python/ceval.c b/Python/ceval.c
index 2d617a63648804..f4cacd84b66cb8 100644
--- a/Python/ceval.c
+++ b/Python/ceval.c
@@ -1064,7 +1064,7 @@ static int unpack_iterable(PyThreadState *, PyObject *, int, int, PyObject **);
 PyObject *
 PyEval_EvalCode(PyObject *co, PyObject *globals, PyObject *locals)
 {
-    PyThreadState *tstate = PyThreadState_GET();
+    PyThreadState *tstate = _PyThreadState_GET();
     if (locals == NULL) {
         locals = globals;
     }
diff --git a/Python/context.c b/Python/context.c
index 9560fb3f6676e0..ad47992d9e3cd6 100644
--- a/Python/context.c
+++ b/Python/context.c
@@ -728,7 +728,7 @@ static int
 contextvar_set(PyContextVar *var, PyObject *val)
 {
     var->var_cached = NULL;
-    PyThreadState *ts = PyThreadState_Get();
+    PyThreadState *ts = _PyThreadState_GET();
 
     PyContext *ctx = context_get();
     if (ctx == NULL) {
diff --git a/Python/pylifecycle.c b/Python/pylifecycle.c
index bfddc1922d25a9..c67a9b7fbfa2d8 100644
--- a/Python/pylifecycle.c
+++ b/Python/pylifecycle.c
@@ -472,7 +472,7 @@ interpreter_update_config(PyThreadState *tstate, int only_update_path_config)
 int
 _PyInterpreterState_SetConfig(const PyConfig *src_config)
 {
-    PyThreadState *tstate = PyThreadState_Get();
+    PyThreadState *tstate = _PyThreadState_GET();
     int res = -1;
 
     PyConfig config;
diff --git a/Python/pystate.c b/Python/pystate.c
index f02de926c6f026..ee9507c7dd80bf 100644
--- a/Python/pystate.c
+++ b/Python/pystate.c
@@ -1671,8 +1671,11 @@ _check_xidata(PyThreadState *tstate, _PyCrossInterpreterData *data)
 int
 _PyObject_GetCrossInterpreterData(PyObject *obj, _PyCrossInterpreterData *data)
 {
-    // PyThreadState_Get() aborts if tstate is NULL.
-    PyThreadState *tstate = PyThreadState_Get();
+    PyThreadState *tstate = _PyThreadState_GET();
+#ifdef Py_DEBUG
+    // The caller must hold the GIL
+    _Py_EnsureTstateNotNULL(tstate);
+#endif
     PyInterpreterState *interp = tstate->interp;
 
     // Reset data before re-populating.
diff --git a/Python/traceback.c b/Python/traceback.c
index 06b40bbbdc9f8e..3ea1db578b43a7 100644
--- a/Python/traceback.c
+++ b/Python/traceback.c
@@ -6,11 +6,13 @@
 #include "code.h"                 // PyCode_Addr2Line etc
 #include "pycore_interp.h"        // PyInterpreterState.gc
 #include "frameobject.h"          // PyFrame_GetBack()
-#include "pycore_frame.h"         // _PyFrame_GetCode()
-#include "pycore_pyarena.h"       // _PyArena_Free()
 #include "pycore_ast.h"           // asdl_seq_*
 #include "pycore_compile.h"       // _PyAST_Optimize
+#include "pycore_frame.h"         // _PyFrame_GetCode()
 #include "pycore_parser.h"        // _PyParser_ASTFromString
+#include "pycore_pyarena.h"       // _PyArena_Free()
+#include "pycore_pyerrors.h"      // _PyErr_Fetch()
+#include "pycore_pystate.h"       // _PyThreadState_GET()
 #include "../Parser/pegen.h"      // _PyPegen_byte_offset_to_character_offset()
 #include "structmember.h"         // PyMemberDef
 #include "osdefs.h"               // SEP
@@ -267,11 +269,12 @@ void _PyTraceback_Add(const char *funcname, const char *filename, int lineno)
     PyCodeObject *code;
     PyFrameObject *frame;
     PyObject *exc, *val, *tb;
+    PyThreadState *tstate = _PyThreadState_GET();
 
     /* Save and clear the current exception. Python functions must not be
        called with an exception set. Calling Python functions happens when
        the codec of the filesystem encoding is implemented in pure Python. */
-    PyErr_Fetch(&exc, &val, &tb);
+    _PyErr_Fetch(tstate, &exc, &val, &tb);
 
     globals = PyDict_New();
     if (!globals)
@@ -281,14 +284,14 @@ void _PyTraceback_Add(const char *funcname, const char *filename, int lineno)
         Py_DECREF(globals);
         goto error;
     }
-    frame = PyFrame_New(PyThreadState_Get(), code, globals, NULL);
+    frame = PyFrame_New(tstate, code, globals, NULL);
     Py_DECREF(globals);
     Py_DECREF(code);
     if (!frame)
         goto error;
     frame->f_lineno = lineno;
 
-    PyErr_Restore(exc, val, tb);
+    _PyErr_Restore(tstate, exc, val, tb);
     PyTraceBack_Here(frame);
     Py_DECREF(frame);
     return;
diff --git a/setup.py b/setup.py
index c6290eebed30f6..039c96b0e4d7b6 100644
--- a/setup.py
+++ b/setup.py
@@ -1000,7 +1000,8 @@ def detect_simple_extensions(self):
         self.add(Extension('syslog', ['syslogmodule.c']))
 
         # Python interface to subinterpreter C-API.
-        self.add(Extension('_xxsubinterpreters', ['_xxsubinterpretersmodule.c']))
+        self.add(Extension('_xxsubinterpreters', ['_xxsubinterpretersmodule.c'],
+                           extra_compile_args=['-DPy_BUILD_CORE_MODULE']))
 
         #
         # Here ends the simple stuff.  From here on, modules need certain
@@ -2310,7 +2311,7 @@ def detect_ctypes(self):
 
     def detect_decimal(self):
         # Stefan Krah's _decimal module
-        extra_compile_args = []
+        extra_compile_args = ['-DPy_BUILD_CORE_MODULE']
         undef_macros = []
         if '--with-system-libmpdec' in sysconfig.get_config_var("CONFIG_ARGS"):
             include_dirs = []