[3.13] gh-119506: fix `_io.TextIOWrapper.write()` write during flush (GH-119507) (#119964)

gh-119506: fix `_io.TextIOWrapper.write()` write during flush (GH-119507)
(cherry picked from commit 52586f930f62bd80374f0f240a4ecce0c0238174)

Co-authored-by: Radislav Chugunov <52372310+chgnrdv@users.noreply.github.com>
Co-authored-by: Inada Naoki <songofacandy@gmail.com>

1 files changed, 22 insertions, 9 deletions

diff --git a/Modules/_io/textio.c b/Modules/_io/textio.c
index 9dff8ea..c162d81 100644
--- a/Modules/_io/textio.c
+++ b/Modules/_io/textio.c
@@ -1719,16 +1719,26 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text)
         bytes_len = PyBytes_GET_SIZE(b);
     }
 
-    if (self->pending_bytes == NULL) {
-        self->pending_bytes_count = 0;
-        self->pending_bytes = b;
-    }
-    else if (self->pending_bytes_count + bytes_len > self->chunk_size) {
-        // Prevent to concatenate more than chunk_size data.
-        if (_textiowrapper_writeflush(self) < 0) {
-            Py_DECREF(b);
-            return NULL;
+    // We should avoid concatinating huge data.
+    // Flush the buffer before adding b to the buffer if b is not small.
+    // https://github.com/python/cpython/issues/87426
+    if (bytes_len >= self->chunk_size) {
+        // _textiowrapper_writeflush() calls buffer.write().
+        // self->pending_bytes can be appended during buffer->write()
+        // or other thread.
+        // We need to loop until buffer becomes empty.
+        // https://github.com/python/cpython/issues/118138
+        // https://github.com/python/cpython/issues/119506
+        while (self->pending_bytes != NULL) {
+            if (_textiowrapper_writeflush(self) < 0) {
+                Py_DECREF(b);
+                return NULL;
+            }
         }
+    }
+
+    if (self->pending_bytes == NULL) {
+        assert(self->pending_bytes_count == 0);
         self->pending_bytes = b;
     }
     else if (!PyList_CheckExact(self->pending_bytes)) {
@@ -1737,6 +1747,9 @@ _io_TextIOWrapper_write_impl(textio *self, PyObject *text)
             Py_DECREF(b);
             return NULL;
         }
+        // Since Python 3.12, allocating GC object won't trigger GC and release
+        // GIL. See https://github.com/python/cpython/issues/97922
+        assert(!PyList_CheckExact(self->pending_bytes));
         PyList_SET_ITEM(list, 0, self->pending_bytes);
         PyList_SET_ITEM(list, 1, b);
         self->pending_bytes = list;