Cache one datachunk per tstate to prevent alloc/dealloc thrashing

Summary:
Cache one datachunk per tstate to prevent alloc/dealloc thrashing when repeatedly hitting the same call depth at exactly the wrong boundary.

Upstream issue: python/cpython#142183
Upstream PR: python/cpython#145789

Reviewed By: itamaro

Differential Revision: D96052502

fbshipit-source-id: 883f6148568b6cca5a71dd7d754eb206fbb56f90

Author: Yhg1s

cinderx/UpstreamBorrow/borrowed-3.14.free-threading.gen_cached.c

@@ -7698,9 +7698,20 @@ push_chunk(PyThreadState *tstate, int size)
     while (allocate_size < (int)sizeof(PyObject*)*(size + MINIMUM_OVERHEAD)) {
         allocate_size *= 2;
     }
-    _PyStackChunk *new = allocate_chunk(allocate_size, tstate->datastack_chunk);
-    if (new == NULL) {
-        return NULL;
+    _PyStackChunk *new;
+    if (tstate->datastack_cached_chunk != NULL
+        && (size_t)allocate_size <= tstate->datastack_cached_chunk->size)
+    {
+        new = tstate->datastack_cached_chunk;
+        tstate->datastack_cached_chunk = NULL;
+        new->previous = tstate->datastack_chunk;
+        new->top = 0;
+    }
+    else {
+        new = allocate_chunk(allocate_size, tstate->datastack_chunk);
+        if (new == NULL) {
+            return NULL;
+        }
     }
     if (tstate->datastack_chunk) {
         tstate->datastack_chunk->top = tstate->datastack_top -