GH-126491: GC: Mark objects reachable from roots before doing cycle collection

Include/cpython/pystats.h

@@ -99,6 +99,8 @@ typedef struct _gc_stats {
     uint64_t collections;
     uint64_t object_visits;
     uint64_t objects_collected;
+    uint64_t objects_transitively_reachable;
+    uint64_t objects_not_transitively_reachable;
 } GCStats;
 
 typedef struct _uop_stats {

Include/internal/pycore_frame.h

@@ -71,6 +71,7 @@ typedef struct _PyInterpreterFrame {
     _PyStackRef *stackpointer;
     uint16_t return_offset;  /* Only relevant during a function call */
     char owner;
+    char visited;
     /* Locals and stack */
     _PyStackRef localsplus[1];
 } _PyInterpreterFrame;
@@ -165,6 +166,7 @@ _PyFrame_Initialize(
     frame->instr_ptr = _PyCode_CODE(code);
     frame->return_offset = 0;
     frame->owner = FRAME_OWNED_BY_THREAD;
+    frame->visited = 0;
 
     for (int i = null_locals_from; i < code->co_nlocalsplus; i++) {
         frame->localsplus[i] = PyStackRef_NULL;
@@ -341,6 +343,7 @@ _PyFrame_PushTrampolineUnchecked(PyThreadState *tstate, PyCodeObject *code, int
     frame->frame_obj = NULL;
     frame->instr_ptr = _PyCode_CODE(code);
     frame->owner = FRAME_OWNED_BY_THREAD;
+    frame->visited = 0;
     frame->return_offset = 0;
 
 #ifdef Py_GIL_DISABLED

Include/internal/pycore_gc.h

@@ -302,6 +302,11 @@ struct gc_generation_stats {
     Py_ssize_t uncollectable;
 };
 
+enum _GCPhase {
+    GC_PHASE_MARK = 0,
+    GC_PHASE_COLLECT = 1
+};
+
 struct _gc_runtime_state {
     /* List of objects that still need to be cleaned up, singly linked
      * via their gc headers' gc_prev pointers.  */
@@ -329,6 +334,7 @@ struct _gc_runtime_state {
     Py_ssize_t work_to_do;
     /* Which of the old spaces is the visited space */
     int visited_space;
+    int phase;
 
 #ifdef Py_GIL_DISABLED
     /* This is the number of objects that survived the last full

Include/internal/pycore_object.h

@@ -466,8 +466,8 @@ static inline void _PyObject_GC_TRACK(
     PyGC_Head *last = (PyGC_Head*)(generation0->_gc_prev);
     _PyGCHead_SET_NEXT(last, gc);
     _PyGCHead_SET_PREV(gc, last);
-    /* Young objects will be moved into the visited space during GC, so set the bit here */
-    gc->_gc_next = ((uintptr_t)generation0) | (uintptr_t)interp->gc.visited_space;
+    uintptr_t not_visited = 1 ^ interp->gc.visited_space;
+    gc->_gc_next = ((uintptr_t)generation0) | not_visited;
     generation0->_gc_prev = (uintptr_t)gc;
 #endif
 }

Include/internal/pycore_runtime_init.h

@@ -132,6 +132,7 @@ extern PyTypeObject _PyExc_MemoryError;
                 { .threshold = 0, }, \
             }, \
             .work_to_do = -5000, \
+            .phase = 0, \
         }, \
         .qsbr = { \
             .wr_seq = QSBR_INITIAL, \

Lib/test/test_dict.py

@@ -880,115 +880,6 @@ class C(object):
             gc.collect()
             self.assertIs(ref(), None, "Cycle was not collected")
 
-    def _not_tracked(self, t):
-        # Nested containers can take several collections to untrack
-        gc.collect()
-        gc.collect()
-        self.assertFalse(gc.is_tracked(t), t)
-
-    def _tracked(self, t):
-        self.assertTrue(gc.is_tracked(t), t)
-        gc.collect()
-        gc.collect()
-        self.assertTrue(gc.is_tracked(t), t)
-
-    def test_string_keys_can_track_values(self):
-        # Test that this doesn't leak.
-        for i in range(10):
-            d = {}
-            for j in range(10):
-                d[str(j)] = j
-            d["foo"] = d
-
-    @support.cpython_only
-    def test_track_literals(self):
-        # Test GC-optimization of dict literals
-        x, y, z, w = 1.5, "a", (1, None), []
-
-        self._not_tracked({})
-        self._not_tracked({x:(), y:x, z:1})
-        self._not_tracked({1: "a", "b": 2})
-        self._not_tracked({1: 2, (None, True, False, ()): int})
-        self._not_tracked({1: object()})
-
-        # Dicts with mutable elements are always tracked, even if those
-        # elements are not tracked right now.
-        self._tracked({1: []})
-        self._tracked({1: ([],)})
-        self._tracked({1: {}})
-        self._tracked({1: set()})
-
-    @support.cpython_only
-    def test_track_dynamic(self):
-        # Test GC-optimization of dynamically-created dicts
-        class MyObject(object):
-            pass
-        x, y, z, w, o = 1.5, "a", (1, object()), [], MyObject()
-
-        d = dict()
-        self._not_tracked(d)
-        d[1] = "a"
-        self._not_tracked(d)
-        d[y] = 2
-        self._not_tracked(d)
-        d[z] = 3
-        self._not_tracked(d)
-        self._not_tracked(d.copy())
-        d[4] = w
-        self._tracked(d)
-        self._tracked(d.copy())
-        d[4] = None
-        self._not_tracked(d)
-        self._not_tracked(d.copy())
-
-        # dd isn't tracked right now, but it may mutate and therefore d
-        # which contains it must be tracked.
-        d = dict()
-        dd = dict()
-        d[1] = dd
-        self._not_tracked(dd)
-        self._tracked(d)
-        dd[1] = d
-        self._tracked(dd)
-
-        d = dict.fromkeys([x, y, z])
-        self._not_tracked(d)
-        dd = dict()
-        dd.update(d)
-        self._not_tracked(dd)
-        d = dict.fromkeys([x, y, z, o])
-        self._tracked(d)
-        dd = dict()
-        dd.update(d)
-        self._tracked(dd)
-
-        d = dict(x=x, y=y, z=z)
-        self._not_tracked(d)
-        d = dict(x=x, y=y, z=z, w=w)
-        self._tracked(d)
-        d = dict()
-        d.update(x=x, y=y, z=z)
-        self._not_tracked(d)
-        d.update(w=w)
-        self._tracked(d)
-
-        d = dict([(x, y), (z, 1)])
-        self._not_tracked(d)
-        d = dict([(x, y), (z, w)])
-        self._tracked(d)
-        d = dict()
-        d.update([(x, y), (z, 1)])
-        self._not_tracked(d)
-        d.update([(x, y), (z, w)])
-        self._tracked(d)
-
-    @support.cpython_only
-    def test_track_subtypes(self):
-        # Dict subtypes are always tracked
-        class MyDict(dict):
-            pass
-        self._tracked(MyDict())
-
     def make_shared_key_dict(self, n):
         class C:
             pass

Lib/test/test_gc.py

@@ -1284,7 +1284,8 @@ def test_refcount_errors(self):
             from test.support import gc_collect, SuppressCrashReport
 
             a = [1, 2, 3]
-            b = [a]
+            b = [a, a]
+            a.append(b)
 
             # Avoid coredump when Py_FatalError() calls abort()
             SuppressCrashReport().__enter__()
@@ -1294,6 +1295,8 @@ def test_refcount_errors(self):
             # (to avoid deallocating it):
             import ctypes
             ctypes.pythonapi.Py_DecRef(ctypes.py_object(a))
+            del a
+            del b
 
             # The garbage collector should now have a fatal error
             # when it reaches the broken object
@@ -1322,7 +1325,7 @@ def test_refcount_errors(self):
         self.assertRegex(stderr,
             br'object type name: list')
         self.assertRegex(stderr,
-            br'object repr     : \[1, 2, 3\]')
+            br'object repr     : \[1, 2, 3, \[\[...\], \[...\]\]\]')
 
 
 class GCTogglingTests(unittest.TestCase):

Objects/dictobject.c

@@ -883,6 +883,7 @@ new_dict(PyInterpreterState *interp,
     mp->ma_used = used;
     mp->_ma_watcher_tag = 0;
     ASSERT_CONSISTENT(mp);
+    _PyObject_GC_TRACK(mp);
     return (PyObject *)mp;
 }
 
@@ -1578,64 +1579,6 @@ _PyDict_HasOnlyStringKeys(PyObject *dict)
     return 1;
 }
 
-#define MAINTAIN_TRACKING(mp, key, value) \
-    do { \
-        if (!_PyObject_GC_IS_TRACKED(mp)) { \
-            if (_PyObject_GC_MAY_BE_TRACKED(key) || \
-                _PyObject_GC_MAY_BE_TRACKED(value)) { \
-                _PyObject_GC_TRACK(mp); \
-            } \
-        } \
-    } while(0)
-
-void
-_PyDict_MaybeUntrack(PyObject *op)
-{
-    PyDictObject *mp;
-    PyObject *value;
-    Py_ssize_t i, numentries;
-
-    ASSERT_WORLD_STOPPED_OR_DICT_LOCKED(op);
-
-    if (!PyDict_CheckExact(op) || !_PyObject_GC_IS_TRACKED(op))
-        return;
-
-    mp = (PyDictObject *) op;
-    ASSERT_CONSISTENT(mp);
-    numentries = mp->ma_keys->dk_nentries;
-    if (_PyDict_HasSplitTable(mp)) {
-        for (i = 0; i < numentries; i++) {
-            if ((value = mp->ma_values->values[i]) == NULL)
-                continue;
-            if (_PyObject_GC_MAY_BE_TRACKED(value)) {
-                return;
-            }
-        }
-    }
-    else {
-        if (DK_IS_UNICODE(mp->ma_keys)) {
-            PyDictUnicodeEntry *ep0 = DK_UNICODE_ENTRIES(mp->ma_keys);
-            for (i = 0; i < numentries; i++) {
-                if ((value = ep0[i].me_value) == NULL)
-                    continue;
-                if (_PyObject_GC_MAY_BE_TRACKED(value))
-                    return;
-            }
-        }
-        else {
-            PyDictKeyEntry *ep0 = DK_ENTRIES(mp->ma_keys);
-            for (i = 0; i < numentries; i++) {
-                if ((value = ep0[i].me_value) == NULL)
-                    continue;
-                if (_PyObject_GC_MAY_BE_TRACKED(value) ||
-                    _PyObject_GC_MAY_BE_TRACKED(ep0[i].me_key))
-                    return;
-            }
-        }
-    }
-    _PyObject_GC_UNTRACK(op);
-}
-
 void
 _PyDict_EnablePerThreadRefcounting(PyObject *op)
 {
@@ -1761,7 +1704,6 @@ insert_split_value(PyInterpreterState *interp, PyDictObject *mp, PyObject *key,
 {
     assert(PyUnicode_CheckExact(key));
     ASSERT_DICT_LOCKED(mp);
-    MAINTAIN_TRACKING(mp, key, value);
     PyObject *old_value = mp->ma_values->values[ix];
     if (old_value == NULL) {
         _PyDict_NotifyEvent(interp, PyDict_EVENT_ADDED, mp, key, value);
@@ -1818,8 +1760,6 @@ insertdict(PyInterpreterState *interp, PyDictObject *mp,
     if (ix == DKIX_ERROR)
         goto Fail;
 
-    MAINTAIN_TRACKING(mp, key, value);
-
     if (ix == DKIX_EMPTY) {
         assert(!_PyDict_HasSplitTable(mp));
         /* Insert into new slot. */
@@ -1878,8 +1818,6 @@ insert_to_emptydict(PyInterpreterState *interp, PyDictObject *mp,
     /* We don't decref Py_EMPTY_KEYS here because it is immortal. */
     assert(mp->ma_values == NULL);
 
-    MAINTAIN_TRACKING(mp, key, value);
-
     size_t hashpos = (size_t)hash & (PyDict_MINSIZE-1);
     dictkeys_set_index(newkeys, hashpos, 0);
     if (unicode) {
@@ -3770,11 +3708,6 @@ dict_dict_merge(PyInterpreterState *interp, PyDictObject *mp, PyDictObject *othe
             STORE_USED(mp, other->ma_used);
             ASSERT_CONSISTENT(mp);
 
-            if (_PyObject_GC_IS_TRACKED(other) && !_PyObject_GC_IS_TRACKED(mp)) {
-                /* Maintain tracking. */
-                _PyObject_GC_TRACK(mp);
-            }
-
             return 0;
         }
     }
@@ -4024,8 +3957,7 @@ copy_lock_held(PyObject *o)
         split_copy->ma_used = mp->ma_used;
         split_copy->_ma_watcher_tag = 0;
         dictkeys_incref(mp->ma_keys);
-        if (_PyObject_GC_IS_TRACKED(mp))
-            _PyObject_GC_TRACK(split_copy);
+        _PyObject_GC_TRACK(split_copy);
         return (PyObject *)split_copy;
     }
 
@@ -4060,10 +3992,6 @@ copy_lock_held(PyObject *o)
 
         new->ma_used = mp->ma_used;
         ASSERT_CONSISTENT(new);
-        if (_PyObject_GC_IS_TRACKED(mp)) {
-            /* Maintain tracking. */
-            _PyObject_GC_TRACK(new);
-        }
 
         return (PyObject *)new;
     }
@@ -4350,8 +4278,6 @@ dict_setdefault_ref_lock_held(PyObject *d, PyObject *key, PyObject *default_valu
                 *result = NULL;
             }
         }
-
-        MAINTAIN_TRACKING(mp, key, value);
         STORE_USED(mp, mp->ma_used + 1);
         assert(mp->ma_keys->dk_usable >= 0);
         ASSERT_CONSISTENT(mp);
@@ -4801,15 +4727,8 @@ dict_new(PyTypeObject *type, PyObject *args, PyObject *kwds)
     d->ma_values = NULL;
     ASSERT_CONSISTENT(d);
 
-    if (type != &PyDict_Type) {
-        // Don't track if a subclass tp_alloc is PyType_GenericAlloc()
-        if (!_PyObject_GC_IS_TRACKED(d)) {
-            _PyObject_GC_TRACK(d);
-        }
-    }
-    else {
-        // _PyType_AllocNoTrack() does not track the created object
-        assert(!_PyObject_GC_IS_TRACKED(d));
+    if (!_PyObject_GC_IS_TRACKED(d)) {
+        _PyObject_GC_TRACK(d);
     }
     return self;
 }
@@ -6755,9 +6674,6 @@ make_dict_from_instance_attributes(PyInterpreterState *interp,
         }
     }
     PyDictObject *res = (PyDictObject *)new_dict(interp, keys, values, used, 0);
-    if (track && res) {
-        _PyObject_GC_TRACK(res);
-    }
     return res;
 }
 

Objects/moduleobject.c

@@ -107,8 +107,6 @@ static void
 track_module(PyModuleObject *m)
 {
     _PyDict_EnablePerThreadRefcounting(m->md_dict);
-    PyObject_GC_Track(m->md_dict);
-
     _PyObject_SetDeferredRefcount((PyObject *)m);
     PyObject_GC_Track(m);
 }