gh-117657: Fix race involving GC and heap initialization (#119923)

The `_PyThreadState_Bind()` function is called before the first
`PyEval_AcquireThread()` so it's not synchronized with the stop the
world GC. We had a race where `gc_visit_heaps()` might visit a thread's
heap while it's being initialized.

Use a simple atomic int to avoid visiting heaps for threads that are not
yet fully initialized (i.e., before `tstate_mimalloc_bind()` is called).

The race was reproducible by running:
`python Lib/test/test_importlib/partial/pool_in_threads.py`.

2 files changed, 6 insertions, 0 deletions

diff --git a/Python/gc_free_threading.c b/Python/gc_free_threading.c
index d005b79..f19362c 100644
--- a/Python/gc_free_threading.c
+++ b/Python/gc_free_threading.c
@@ -252,6 +252,10 @@ gc_visit_heaps_lock_held(PyInterpreterState *interp, mi_block_visit_fun *visitor
     // visit each thread's heaps for GC objects
     for (PyThreadState *p = interp->threads.head; p != NULL; p = p->next) {
         struct _mimalloc_thread_state *m = &((_PyThreadStateImpl *)p)->mimalloc;
+        if (!_Py_atomic_load_int(&m->initialized)) {
+            // The thread may not have called tstate_mimalloc_bind() yet.
+            continue;
+        }
 
         arg->offset = offset_base;
         if (!mi_heap_visit_blocks(&m->heaps[_Py_MIMALLOC_HEAP_GC], true,
diff --git a/Python/pystate.c b/Python/pystate.c
index d029391..e1a9590 100644
--- a/Python/pystate.c
+++ b/Python/pystate.c
@@ -3074,6 +3074,8 @@ tstate_mimalloc_bind(PyThreadState *tstate)
     // _PyObject_GC_New() and similar functions temporarily override this to
     // use one of the GC heaps.
     mts->current_object_heap = &mts->heaps[_Py_MIMALLOC_HEAP_OBJECT];
+
+    _Py_atomic_store_int(&mts->initialized, 1);
 #endif
 }