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

Include/cpython/pystate.h

@@ -208,6 +208,7 @@ struct _ts {
     */
     PyObject *threading_local_sentinel;
     _PyRemoteDebuggerSupport remote_debugger_support;
+    _PyStackChunk *datastack_cached_chunk;
 };
 
 /* other API */

Python/pystate.c

@@ -1596,6 +1596,7 @@ init_threadstate(_PyThreadStateImpl *_tstate,
     tstate->datastack_chunk = NULL;
     tstate->datastack_top = NULL;
     tstate->datastack_limit = NULL;
+    tstate->datastack_cached_chunk = NULL;
     tstate->what_event = -1;
     tstate->current_executor = NULL;
     tstate->dict_global_version = 0;
@@ -1735,6 +1736,11 @@ clear_datastack(PyThreadState *tstate)
         _PyObject_VirtualFree(chunk, chunk->size);
         chunk = prev;
     }
+    if (tstate->datastack_cached_chunk != NULL) {
+        _PyObject_VirtualFree(tstate->datastack_cached_chunk,
+                              tstate->datastack_cached_chunk->size);
+        tstate->datastack_cached_chunk = NULL;
+    }
 }
 
 void
@@ -3050,9 +3056,20 @@ 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 -
@@ -3088,12 +3105,17 @@ _PyThreadState_PopFrame(PyThreadState *tstate, _PyInterpreterFrame * frame)
     if (base == &tstate->datastack_chunk->data[0]) {
         _PyStackChunk *chunk = tstate->datastack_chunk;
         _PyStackChunk *previous = chunk->previous;
+        _PyStackChunk *cached = tstate->datastack_cached_chunk;
         // push_chunk ensures that the root chunk is never popped:
         assert(previous);
         tstate->datastack_top = &previous->data[previous->top];
         tstate->datastack_chunk = previous;
-        _PyObject_VirtualFree(chunk, chunk->size);
         tstate->datastack_limit = (PyObject **)(((char *)previous) + previous->size);
+        chunk->previous = NULL;
+        if (cached != NULL) {
+            _PyObject_VirtualFree(cached, cached->size);
+        }
+        tstate->datastack_cached_chunk = chunk;
     }
     else {
         assert(tstate->datastack_top);