GH-116422: Modify a few uops so that they can be supported by tier 2 with hot/cold splitting (GH-116832)

Author: markshannon

Include/internal/pycore_ceval.h

@@ -138,12 +138,12 @@ extern void _PyEval_DeactivateOpCache(void);
 /* With USE_STACKCHECK macro defined, trigger stack checks in
    _Py_CheckRecursiveCall() on every 64th call to _Py_EnterRecursiveCall. */
 static inline int _Py_MakeRecCheck(PyThreadState *tstate)  {
-    return (tstate->c_recursion_remaining-- <= 0
+    return (tstate->c_recursion_remaining-- < 0
             || (tstate->c_recursion_remaining & 63) == 0);
 }
 #else
 static inline int _Py_MakeRecCheck(PyThreadState *tstate) {
-    return tstate->c_recursion_remaining-- <= 0;
+    return tstate->c_recursion_remaining-- < 0;
 }
 #endif
 
@@ -161,6 +161,11 @@ static inline int _Py_EnterRecursiveCallTstate(PyThreadState *tstate,
     return (_Py_MakeRecCheck(tstate) && _Py_CheckRecursiveCall(tstate, where));
 }
 
+static inline void _Py_EnterRecursiveCallTstateUnchecked(PyThreadState *tstate)  {
+    assert(tstate->c_recursion_remaining > 0);
+    tstate->c_recursion_remaining--;
+}
+
 static inline int _Py_EnterRecursiveCall(const char *where) {
     PyThreadState *tstate = _PyThreadState_GET();
     return _Py_EnterRecursiveCallTstate(tstate, where);

Python/bytecodes.c

@@ -3376,14 +3376,12 @@ dummy_func(
             DEOPT_IF(total_args != 1);
             DEOPT_IF(!PyCFunction_CheckExact(callable));
             DEOPT_IF(PyCFunction_GET_FLAGS(callable) != METH_O);
+            // CPython promises to check all non-vectorcall function calls.
+            DEOPT_IF(tstate->c_recursion_remaining <= 0);
             STAT_INC(CALL, hit);
             PyCFunction cfunc = PyCFunction_GET_FUNCTION(callable);
-            // This is slower but CPython promises to check all non-vectorcall
-            // function calls.
-            if (_Py_EnterRecursiveCallTstate(tstate, " while calling a Python object")) {
-                GOTO_ERROR(error);
-            }
             PyObject *arg = args[0];
+            _Py_EnterRecursiveCallTstateUnchecked(tstate);
             res = _PyCFunction_TrampolineCall(cfunc, PyCFunction_GET_SELF(callable), arg);
             _Py_LeaveRecursiveCallTstate(tstate);
             assert((res != NULL) ^ (_PyErr_Occurred(tstate) != NULL));
@@ -3480,10 +3478,11 @@ dummy_func(
             }
             res = PyLong_FromSsize_t(len_i);
             assert((res != NULL) ^ (_PyErr_Occurred(tstate) != NULL));
-
+            if (res == NULL) {
+                GOTO_ERROR(error);
+            }
             Py_DECREF(callable);
             Py_DECREF(arg);
-            ERROR_IF(res == NULL, error);
         }
 
         inst(CALL_ISINSTANCE, (unused/1, unused/2, callable, self_or_null, args[oparg] -- res)) {
@@ -3505,11 +3504,12 @@ dummy_func(
             }
             res = PyBool_FromLong(retval);
             assert((res != NULL) ^ (_PyErr_Occurred(tstate) != NULL));
-
+            if (res == NULL) {
+                GOTO_ERROR(error);
+            }
             Py_DECREF(inst);
             Py_DECREF(cls);
             Py_DECREF(callable);
-            ERROR_IF(res == NULL, error);
         }
 
         // This is secretly a super-instruction
@@ -3543,16 +3543,14 @@ dummy_func(
             DEOPT_IF(!Py_IS_TYPE(method, &PyMethodDescr_Type));
             PyMethodDef *meth = method->d_method;
             DEOPT_IF(meth->ml_flags != METH_O);
+            // CPython promises to check all non-vectorcall function calls.
+            DEOPT_IF(tstate->c_recursion_remaining <= 0);
             PyObject *arg = args[1];
             PyObject *self = args[0];
             DEOPT_IF(!Py_IS_TYPE(self, method->d_common.d_type));
             STAT_INC(CALL, hit);
             PyCFunction cfunc = meth->ml_meth;
-            // This is slower but CPython promises to check all non-vectorcall
-            // function calls.
-            if (_Py_EnterRecursiveCallTstate(tstate, " while calling a Python object")) {
-                GOTO_ERROR(error);
-            }
+            _Py_EnterRecursiveCallTstateUnchecked(tstate);
             res = _PyCFunction_TrampolineCall(cfunc, self, arg);
             _Py_LeaveRecursiveCallTstate(tstate);
             assert((res != NULL) ^ (_PyErr_Occurred(tstate) != NULL));
@@ -3616,13 +3614,11 @@ dummy_func(
             PyObject *self = args[0];
             DEOPT_IF(!Py_IS_TYPE(self, method->d_common.d_type));
             DEOPT_IF(meth->ml_flags != METH_NOARGS);
+            // CPython promises to check all non-vectorcall function calls.
+            DEOPT_IF(tstate->c_recursion_remaining <= 0);
             STAT_INC(CALL, hit);
             PyCFunction cfunc = meth->ml_meth;
-            // This is slower but CPython promises to check all non-vectorcall
-            // function calls.
-            if (_Py_EnterRecursiveCallTstate(tstate, " while calling a Python object")) {
-                GOTO_ERROR(error);
-            }
+            _Py_EnterRecursiveCallTstateUnchecked(tstate);
             res = _PyCFunction_TrampolineCall(cfunc, self, NULL);
             _Py_LeaveRecursiveCallTstate(tstate);
             assert((res != NULL) ^ (_PyErr_Occurred(tstate) != NULL));