pycore_pystate.h no longer redefines PyThreadState_GET() (GH-28921)

Redefining the PyThreadState_GET() macro in pycore_pystate.h is
useless since it doesn't affect files not including it. Either use
_PyThreadState_GET() directly, or don't use pycore_pystate.h internal
C API. For example, the _testcapi extension don't use the internal C
API, but use the public PyThreadState_Get() function instead.

Replace PyThreadState_Get() with _PyThreadState_GET(). The
_PyThreadState_GET() macro is more efficient than PyThreadState_Get()
and PyThreadState_GET() function calls which call fail with a fatal
Python error.

posixmodule.c and _ctypes extension now include <windows.h> before
pycore header files (like pycore_call.h).

_PyTraceback_Add() now uses _PyErr_Fetch()/_PyErr_Restore() instead
of PyErr_Fetch()/PyErr_Restore().

The _decimal and _xxsubinterpreters extensions are now built with the
Py_BUILD_CORE_MODULE macro defined to get access to the internal C
API.

11 files changed, 56 insertions, 44 deletions

diff --git a/Modules/_asynciomodule.c b/Modules/_asynciomodule.c
index 56079b0..adc5ff9 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 2567067..f8940fd 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 18b0104..c24f04c 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 6788aee..b7585bc 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 ea3c58b..43669d7 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 e2979a5..dd876f2 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 097d0eff..2e27afc 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 d5616fd..3ba9396 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 ff85838..39b116a 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 11b55f7..939114e 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 ada1a58..9c174ee 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__