GH-108362: Incremental Cycle GC (GH-116206)

3 files changed, 38 insertions, 29 deletions

diff --git a/Include/internal/pycore_gc.h b/Include/internal/pycore_gc.h
index 4a7191a..9d66e62 100644
--- a/Include/internal/pycore_gc.h
+++ b/Include/internal/pycore_gc.h
@@ -109,11 +109,14 @@ static inline void _PyObject_GC_SET_SHARED_INLINE(PyObject *op) {
 
 /* Bit flags for _gc_prev */
 /* Bit 0 is set when tp_finalize is called */
-#define _PyGC_PREV_MASK_FINALIZED  (1)
+#define _PyGC_PREV_MASK_FINALIZED  1
 /* Bit 1 is set when the object is in generation which is GCed currently. */
-#define _PyGC_PREV_MASK_COLLECTING (2)
-/* The (N-2) most significant bits contain the real address. */
-#define _PyGC_PREV_SHIFT           (2)
+#define _PyGC_PREV_MASK_COLLECTING 2
+
+/* Bit 0 is set if the object belongs to old space 1 */
+#define _PyGC_NEXT_MASK_OLD_SPACE_1    1
+
+#define _PyGC_PREV_SHIFT           2
 #define _PyGC_PREV_MASK            (((uintptr_t) -1) << _PyGC_PREV_SHIFT)
 
 /* set for debugging information */
@@ -139,11 +142,13 @@ typedef enum {
 // Lowest bit of _gc_next is used for flags only in GC.
 // But it is always 0 for normal code.
 static inline PyGC_Head* _PyGCHead_NEXT(PyGC_Head *gc) {
-    uintptr_t next = gc->_gc_next;
+    uintptr_t next = gc->_gc_next & _PyGC_PREV_MASK;
     return (PyGC_Head*)next;
 }
 static inline void _PyGCHead_SET_NEXT(PyGC_Head *gc, PyGC_Head *next) {
-    gc->_gc_next = (uintptr_t)next;
+    uintptr_t unext = (uintptr_t)next;
+    assert((unext & ~_PyGC_PREV_MASK) == 0);
+    gc->_gc_next = (gc->_gc_next & ~_PyGC_PREV_MASK) | unext;
 }
 
 // Lowest two bits of _gc_prev is used for _PyGC_PREV_MASK_* flags.
@@ -151,6 +156,7 @@ static inline PyGC_Head* _PyGCHead_PREV(PyGC_Head *gc) {
     uintptr_t prev = (gc->_gc_prev & _PyGC_PREV_MASK);
     return (PyGC_Head*)prev;
 }
+
 static inline void _PyGCHead_SET_PREV(PyGC_Head *gc, PyGC_Head *prev) {
     uintptr_t uprev = (uintptr_t)prev;
     assert((uprev & ~_PyGC_PREV_MASK) == 0);
@@ -236,6 +242,13 @@ struct gc_generation {
                   generations */
 };
 
+struct gc_collection_stats {
+    /* number of collected objects */
+    Py_ssize_t collected;
+    /* total number of uncollectable objects (put into gc.garbage) */
+    Py_ssize_t uncollectable;
+};
+
 /* Running stats per generation */
 struct gc_generation_stats {
     /* total number of collections */
@@ -257,8 +270,8 @@ struct _gc_runtime_state {
     int enabled;
     int debug;
     /* linked lists of container objects */
-    struct gc_generation generations[NUM_GENERATIONS];
-    PyGC_Head *generation0;
+    struct gc_generation young;
+    struct gc_generation old[2];
     /* a permanent generation which won't be collected */
     struct gc_generation permanent_generation;
     struct gc_generation_stats generation_stats[NUM_GENERATIONS];
@@ -268,6 +281,12 @@ struct _gc_runtime_state {
     PyObject *garbage;
     /* a list of callbacks to be invoked when collection is performed */
     PyObject *callbacks;
+
+    Py_ssize_t work_to_do;
+    /* Which of the old spaces is the visited space */
+    int visited_space;
+
+#ifdef Py_GIL_DISABLED
     /* This is the number of objects that survived the last full
        collection. It approximates the number of long lived objects
        tracked by the GC.
@@ -279,6 +298,7 @@ struct _gc_runtime_state {
        collections, and are awaiting to undergo a full collection for
        the first time. */
     Py_ssize_t long_lived_pending;
+#endif
 };
 
 #ifdef Py_GIL_DISABLED
@@ -291,9 +311,8 @@ struct _gc_thread_state {
 
 extern void _PyGC_InitState(struct _gc_runtime_state *);
 
-extern Py_ssize_t _PyGC_Collect(PyThreadState *tstate, int generation,
-                                _PyGC_Reason reason);
-extern Py_ssize_t _PyGC_CollectNoFail(PyThreadState *tstate);
+extern Py_ssize_t _PyGC_Collect(PyThreadState *tstate, int generation, _PyGC_Reason reason);
+extern void _PyGC_CollectNoFail(PyThreadState *tstate);
 
 /* Freeze objects tracked by the GC and ignore them in future collections. */
 extern void _PyGC_Freeze(PyInterpreterState *interp);
diff --git a/Include/internal/pycore_object.h b/Include/internal/pycore_object.h
index 9809f5f..759ec4d1 100644
--- a/Include/internal/pycore_object.h
+++ b/Include/internal/pycore_object.h
@@ -125,19 +125,8 @@ static inline void _Py_RefcntAdd(PyObject* op, Py_ssize_t n)
 }
 #define _Py_RefcntAdd(op, n) _Py_RefcntAdd(_PyObject_CAST(op), n)
 
-static inline void _Py_SetImmortal(PyObject *op)
-{
-    if (op) {
-#ifdef Py_GIL_DISABLED
-        op->ob_tid = _Py_UNOWNED_TID;
-        op->ob_ref_local = _Py_IMMORTAL_REFCNT_LOCAL;
-        op->ob_ref_shared = 0;
-#else
-        op->ob_refcnt = _Py_IMMORTAL_REFCNT;
-#endif
-    }
-}
-#define _Py_SetImmortal(op) _Py_SetImmortal(_PyObject_CAST(op))
+extern void _Py_SetImmortal(PyObject *op);
+extern void _Py_SetImmortalUntracked(PyObject *op);
 
 // Makes an immortal object mortal again with the specified refcnt. Should only
 // be used during runtime finalization.
@@ -325,11 +314,12 @@ static inline void _PyObject_GC_TRACK(
                           filename, lineno, __func__);
 
     PyInterpreterState *interp = _PyInterpreterState_GET();
-    PyGC_Head *generation0 = interp->gc.generation0;
+    PyGC_Head *generation0 = &interp->gc.young.head;
     PyGC_Head *last = (PyGC_Head*)(generation0->_gc_prev);
     _PyGCHead_SET_NEXT(last, gc);
     _PyGCHead_SET_PREV(gc, last);
     _PyGCHead_SET_NEXT(gc, generation0);
+    assert((gc->_gc_next & _PyGC_NEXT_MASK_OLD_SPACE_1) == 0);
     generation0->_gc_prev = (uintptr_t)gc;
 #endif
 }
diff --git a/Include/internal/pycore_runtime_init.h b/Include/internal/pycore_runtime_init.h
index cc47b9a..88d8889 100644
--- a/Include/internal/pycore_runtime_init.h
+++ b/Include/internal/pycore_runtime_init.h
@@ -168,12 +168,12 @@ extern PyTypeObject _PyExc_MemoryError;
         }, \
         .gc = { \
             .enabled = 1, \
-            .generations = { \
-                /* .head is set in _PyGC_InitState(). */ \
-                { .threshold = 700, }, \
-                { .threshold = 10, }, \
+            .young = { .threshold = 2000, }, \
+            .old = { \
                 { .threshold = 10, }, \
+                { .threshold = 0, }, \
             }, \
+            .work_to_do = -5000, \
         }, \
         .qsbr = { \
             .wr_seq = QSBR_INITIAL, \