gh-117045: Add code object to function version cache (#117028)

Changes to the function version cache:

- In addition to the function object, also store the code object,
  and allow the latter to be retrieved even if the function has been evicted.
- Stop assigning new function versions after a critical attribute (e.g. `__code__`)
  has been modified; the version is permanently reset to zero in this case.
- Changes to `__annotations__` are no longer considered critical. (This fixes gh-109998.)

Changes to the Tier 2 optimization machinery:

- If we cannot map a function version to a function, but it is still mapped to a code object,
  we continue projecting the trace.
  The operand of the `_PUSH_FRAME` and `_POP_FRAME` opcodes can be either NULL,
  a function object, or a code object with the lowest bit set.

This allows us to trace through code that calls an ephemeral function,
i.e., a function that may not be alive when we are constructing the executor,
e.g. a generator expression or certain nested functions.
We will lose globals removal inside such functions,
but we can still do other peephole operations
(and even possibly [call inlining](https://github.com/python/cpython/pull/116290),
if we decide to do it), which only need the code object.
As before, if we cannot retrieve the code object from the cache, we stop projecting.

2 files changed, 12 insertions, 5 deletions

diff --git a/Include/internal/pycore_frame.h b/Include/internal/pycore_frame.h
index 0f9e733..74d9e4c 100644
--- a/Include/internal/pycore_frame.h
+++ b/Include/internal/pycore_frame.h
@@ -55,7 +55,7 @@ enum _frameowner {
 };
 
 typedef struct _PyInterpreterFrame {
-    PyObject *f_executable; /* Strong reference */
+    PyObject *f_executable; /* Strong reference (code object or None) */
     struct _PyInterpreterFrame *previous;
     PyObject *f_funcobj; /* Strong reference. Only valid if not on C stack */
     PyObject *f_globals; /* Borrowed reference. Only valid if not on C stack */
diff --git a/Include/internal/pycore_function.h b/Include/internal/pycore_function.h
index dad6a89..24fbb3d 100644
--- a/Include/internal/pycore_function.h
+++ b/Include/internal/pycore_function.h
@@ -17,20 +17,27 @@ extern PyObject* _PyFunction_Vectorcall(
 #define FUNC_MAX_WATCHERS 8
 
 #define FUNC_VERSION_CACHE_SIZE (1<<12)  /* Must be a power of 2 */
+
+struct _func_version_cache_item {
+    PyFunctionObject *func;
+    PyObject *code;
+};
+
 struct _py_func_state {
     uint32_t next_version;
-    // Borrowed references to function objects whose
+    // Borrowed references to function and code objects whose
     // func_version % FUNC_VERSION_CACHE_SIZE
     // once was equal to the index in the table.
-    // They are cleared when the function is deallocated.
-    PyFunctionObject *func_version_cache[FUNC_VERSION_CACHE_SIZE];
+    // They are cleared when the function or code object is deallocated.
+    struct _func_version_cache_item func_version_cache[FUNC_VERSION_CACHE_SIZE];
 };
 
 extern PyFunctionObject* _PyFunction_FromConstructor(PyFrameConstructor *constr);
 
 extern uint32_t _PyFunction_GetVersionForCurrentState(PyFunctionObject *func);
 PyAPI_FUNC(void) _PyFunction_SetVersion(PyFunctionObject *func, uint32_t version);
-PyFunctionObject *_PyFunction_LookupByVersion(uint32_t version);
+void _PyFunction_ClearCodeByVersion(uint32_t version);
+PyFunctionObject *_PyFunction_LookupByVersion(uint32_t version, PyObject **p_code);
 
 extern PyObject *_Py_set_function_type_params(
     PyThreadState* unused, PyObject *func, PyObject *type_params);