// Remove ourself from the biased reference counting table of threads.
_Py_brc_remove_thread(tstate);
+
+ // Flush the thread's local GC allocation count to the global count
+ // before the thread state is cleared, otherwise the count is lost.
+ _PyThreadStateImpl *tstate_impl = (_PyThreadStateImpl *)tstate;
+ _Py_atomic_add_int(&tstate->interp->gc.generations[0].count,
+ (int)tstate_impl->gc.alloc_count);
+ tstate_impl->gc.alloc_count = 0;
+
#endif
// Merge our queue of pointers to be freed into the interpreter queue.