Implement CALL_FUNCTION_EX_PY specialization

Author: Fidget-Spinner

Include/internal/pycore_code.h

@@ -160,6 +160,12 @@ typedef struct {
 
 #define INLINE_CACHE_ENTRIES_CONTAINS_OP CACHE_ENTRIES(_PyContainsOpCache)
 
+typedef struct {
+    _Py_BackoffCounter counter;
+} _PyCallFunctionExCache;
+
+#define INLINE_CACHE_ENTRIES_CALL_FUNCTION_EX CACHE_ENTRIES(_PyCallFunctionExCache)
+
 /* "Locals plus" for a code object is the set of locals + cell vars +
  * free vars.  This relates to variable names as well as offsets into
  * the "fast locals" storage array of execution frames.  The compiler
@@ -326,6 +332,7 @@ PyAPI_FUNC(void) _Py_Specialize_Send(_PyStackRef receiver, _Py_CODEUNIT *instr);
 PyAPI_FUNC(void) _Py_Specialize_ToBool(_PyStackRef value, _Py_CODEUNIT *instr);
 PyAPI_FUNC(void) _Py_Specialize_ContainsOp(_PyStackRef value, _Py_CODEUNIT *instr);
 PyAPI_FUNC(void) _Py_GatherStats_GetIter(_PyStackRef iterable);
+PyAPI_FUNC(void) _Py_Specialize_CallFunctionEx(_PyStackRef func_st, _Py_CODEUNIT *instr);
 
 // Utility functions for reading/writing 32/64-bit values in the inline caches.
 // Great care should be taken to ensure that these functions remain correct and

Include/internal/pycore_magic_number.h

@@ -287,6 +287,7 @@ Known values:
     Python 3.15a1 3654 (Fix missing exception handlers in logical expression)
     Python 3.15a1 3655 (Fix miscompilation of some module-level annotations)
     Python 3.15a1 3656 (Add TRACE_RECORD instruction, for platforms with switch based interpreter)
+    Python 3.15a1 3657 (Add CALL_FUNCTION_EX specialization)
 
 
     Python 3.16 will start with 3700
@@ -300,7 +301,7 @@ PC/launcher.c must also be updated.
 
 */
 
-#define PYC_MAGIC_NUMBER 3656
+#define PYC_MAGIC_NUMBER 3657
 /* This is equivalent to converting PYC_MAGIC_NUMBER to 2 bytes
    (little-endian) and then appending b'\r\n'. */
 #define PYC_MAGIC_NUMBER_TOKEN \