@@ -14,6 +14,7 @@
 #include <stdlib.h>               // malloc()
 #include <stdbool.h>
 #include <stdio.h>                // fopen(), fgets(), sscanf()
+#include <errno.h>                // errno
 #ifdef WITH_MIMALLOC
 // Forward declarations of functions used in our mimalloc modifications
 static void _PyMem_mi_page_clear_qsbr(mi_page_t *page);
@@ -648,7 +649,11 @@ _PyMem_ArenaFree(void *Py_UNUSED(ctx), void *ptr,
     if (ptr == NULL) {
         return;
     }
-    munmap(ptr, size);
+    if (munmap(ptr, size) < 0) {
+        _Py_FatalErrorFormat(__func__,
+                             "munmap(%p, %zu) failed with errno %d",
+                             ptr, size, errno);
+    }
 #else
     free(ptr);
 #endif
 
@@ -1433,16 +1433,30 @@ tstate_is_alive(PyThreadState *tstate)
 // lifecycle
 //----------
 
+/* When huge pages are enabled, _PyObject_VirtualAlloc may back small requests
+ * with a full 2MB huge page.  We must pass the *mapped* size (not the
+ * requested size) to _PyObject_VirtualFree, otherwise munmap receives a
+ * sub-hugepage length and fails with EINVAL, leaking the huge page. */
+#if defined(PYMALLOC_USE_HUGEPAGES) && defined(__linux__)
+#  define HUGEPAGE_SIZE (2U << 20)   /* 2 MB */
+#  define ROUND_UP_HUGEPAGE(n) \
+       (((n) + HUGEPAGE_SIZE - 1) & ~(HUGEPAGE_SIZE - 1))
+#else
+#  define ROUND_UP_HUGEPAGE(n) (n)
+#endif
+
+
 static _PyStackChunk*
 allocate_chunk(int size_in_bytes, _PyStackChunk* previous)
 {
     assert(size_in_bytes % sizeof(PyObject **) == 0);
-    _PyStackChunk *res = _PyObject_VirtualAlloc(size_in_bytes);
+    size_t mapped_size = ROUND_UP_HUGEPAGE(size_in_bytes);
+    _PyStackChunk *res = _PyObject_VirtualAlloc(mapped_size);
     if (res == NULL) {
         return NULL;
     }
     res->previous = previous;
-    res->size = size_in_bytes;
+    res->size = mapped_size;
     res->top = 0;
     return res;
 }
@@ -3082,7 +3096,7 @@ push_chunk(PyThreadState *tstate, int size)
                                        &tstate->datastack_chunk->data[0];
     }
     tstate->datastack_chunk = new;
-    tstate->datastack_limit = (PyObject **)(((char *)new) + allocate_size);
+    tstate->datastack_limit = (PyObject **)(((char *)new) + new->size);
     // When new is the "root" chunk (i.e. new->previous == NULL), we can keep
     // _PyThreadState_PopFrame from freeing it later by "skipping" over the
     // first element: