bpo-45753: Interpreter internal tweaks (GH-29575)

* Split exit paths into exceptional and non-exceptional.

* Move exit tracing code to individual bytecodes.

* Wrap all trace entry and exit events in macros to make them clearer and easier to enhance.

* Move return sequence into RETURN_VALUE, YIELD_VALUE and YIELD_FROM. Distinguish between normal trace events and dtrace events.

Include/internal/pycore_code.h

@@ -137,24 +137,25 @@ _GetSpecializedCacheEntryForInstruction(const _Py_CODEUNIT *first_instr, int nex
 #define QUICKENING_INITIAL_WARMUP_VALUE (-QUICKENING_WARMUP_DELAY)
 #define QUICKENING_WARMUP_COLDEST 1
 
-static inline void
-PyCodeObject_IncrementWarmup(PyCodeObject * co)
-{
-    co->co_warmup++;
-}
+int _Py_Quicken(PyCodeObject *code);
 
-/* Used by the interpreter to determine when a code object should be quickened */
+/* Returns 1 if quickening occurs.
+ * -1 if an error occurs
+ * 0 otherwise */
 static inline int
-PyCodeObject_IsWarmedUp(PyCodeObject * co)
+_Py_IncrementCountAndMaybeQuicken(PyCodeObject *code)
 {
-    return (co->co_warmup == 0);
+    if (code->co_warmup != 0) {
+        code->co_warmup++;
+        if (code->co_warmup == 0) {
+            return _Py_Quicken(code) ? -1 : 1;
+        }
+    }
+    return 0;
 }
 
-int _Py_Quicken(PyCodeObject *code);
-
 extern Py_ssize_t _Py_QuickenedCount;
 
-
 /* "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

Include/internal/pycore_frame.h

@@ -19,6 +19,11 @@ enum _framestate {
 
 typedef signed char PyFrameState;
 
+/*
+    frame->f_lasti refers to the index of the last instruction,
+    unless it's -1 in which case next_instr should be first_instr.
+*/
+
 typedef struct _interpreter_frame {
     PyFunctionObject *f_func; /* Strong reference */
     PyObject *f_globals; /* Borrowed reference */