GH-116596: Better determination of escaping uops. (GH-116597)

Author: markshannon

Include/internal/pycore_opcode_metadata.h

@@ -1033,6 +1033,7 @@ uop_optimize(
             break;
         }
         assert(_PyOpcode_uop_name[buffer[pc].opcode]);
+        assert(strncmp(_PyOpcode_uop_name[buffer[pc].opcode], _PyOpcode_uop_name[opcode], strlen(_PyOpcode_uop_name[opcode])) == 0);
     }
     _PyExecutorObject *executor = make_executor_from_uops(buffer, &dependencies);
     if (executor == NULL) {

Include/internal/pycore_uop_metadata.h

@@ -430,15 +430,15 @@ remove_unneeded_uops(_PyUOpInstruction *buffer, int buffer_size)
         int opcode = buffer[pc].opcode;
         switch (opcode) {
             case _SET_IP:
-                buffer[pc].opcode = NOP;
+                buffer[pc].opcode = _NOP;
                 last_set_ip = pc;
                 break;
             case _CHECK_VALIDITY:
                 if (may_have_escaped) {
                     may_have_escaped = false;
                 }
                 else {
-                    buffer[pc].opcode = NOP;
+                    buffer[pc].opcode = _NOP;
                 }
                 break;
             case _CHECK_VALIDITY_AND_SET_IP:
@@ -447,7 +447,7 @@ remove_unneeded_uops(_PyUOpInstruction *buffer, int buffer_size)
                     buffer[pc].opcode = _CHECK_VALIDITY;
                 }
                 else {
-                    buffer[pc].opcode = NOP;
+                    buffer[pc].opcode = _NOP;
                 }
                 last_set_ip = pc;
                 break;
@@ -463,7 +463,7 @@ remove_unneeded_uops(_PyUOpInstruction *buffer, int buffer_size)
                     last->opcode == _COPY
                 ) {
                     last->opcode = _NOP;
-                    buffer[pc].opcode = NOP;
+                    buffer[pc].opcode = _NOP;
                 }
                 if (last->opcode == _REPLACE_WITH_TRUE) {
                     last->opcode = _NOP;

Python/optimizer.c

@@ -335,6 +335,7 @@ def is_infallible(op: parser.InstDef) -> bool:
     "_PyDictOrValues_IsValues",
     "_PyObject_DictOrValuesPointer",
     "_PyDictOrValues_GetValues",
+    "_PyDictValues_AddToInsertionOrder",
     "_PyObject_MakeInstanceAttributesFromDict",
     "Py_DECREF",
     "_Py_DECREF_SPECIALIZED",
@@ -355,8 +356,10 @@ def is_infallible(op: parser.InstDef) -> bool:
     "_PyLong_IsCompact",
     "_PyLong_IsNonNegativeCompact",
     "_PyLong_CompactValue",
+    "_PyLong_DigitCount",
     "_Py_NewRef",
     "_Py_IsImmortal",
+    "PyLong_FromLong",
     "_Py_STR",
     "_PyLong_Add",
     "_PyLong_Multiply",
@@ -368,6 +371,17 @@ def is_infallible(op: parser.InstDef) -> bool:
     "_Py_atomic_load_uintptr_relaxed",
     "_PyFrame_GetCode",
     "_PyThreadState_HasStackSpace",
+    "_PyUnicode_Equal",
+    "_PyFrame_SetStackPointer",
+    "_PyType_HasFeature",
+    "PyUnicode_Concat",
+    "_PyList_FromArraySteal",
+    "_PyTuple_FromArraySteal",
+    "PySlice_New",
+    "_Py_LeaveRecursiveCallPy",
+    "CALL_STAT_INC",
+    "maybe_lltrace_resume_frame",
+    "_PyUnicode_JoinArray",
 )
 
 ESCAPING_FUNCTIONS = (
@@ -379,6 +393,8 @@ def is_infallible(op: parser.InstDef) -> bool:
 def makes_escaping_api_call(instr: parser.InstDef) -> bool:
     if "CALL_INTRINSIC" in instr.name:
         return True
+    if instr.name == "_BINARY_OP":
+        return True
     tkns = iter(instr.tokens)
     for tkn in tkns:
         if tkn.kind != lexer.IDENTIFIER: