[3.12] gh-145986: Avoid unbound C recursion in `conv_content_model` in `pyexpat.c...

Fix C stack overflow (CVE-2026-4224) when an Expat parser
with a registered `ElementDeclHandler` parses inline DTD
containing deeply nested content model.

---------
(cherry picked from commit eb0e8be3a7e11b87d198a2c3af1ed0eccf532768)

Co-authored-by: Stan Ulbrych <89152624+StanFromIreland@users.noreply.github.com>
Co-authored-by: Bénédikt Tran <10796600+picnixz@users.noreply.github.com>

diff --git a/Lib/test/test_pyexpat.py b/Lib/test/test_pyexpat.py
index 38f951573f0ad5aa356410a92cae1f795e03fb9c..37d9086f40a827dd0b9073911357f9373a6118e0 100644 (file)
--- a/Lib/test/test_pyexpat.py
+++ b/Lib/test/test_pyexpat.py
@@ -675,6 +675,24 @@ class ChardataBufferTest(unittest.TestCase):
         parser.Parse(xml2, True)
         self.assertEqual(self.n, 4)
 
+class ElementDeclHandlerTest(unittest.TestCase):
+    def test_deeply_nested_content_model(self):
+        # This should raise a RecursionError and not crash.
+        # See https://github.com/python/cpython/issues/145986.
+        N = 500_000
+        data = (
+            b'<!DOCTYPE root [\n<!ELEMENT root '
+            + b'(a, ' * N + b'a' + b')' * N
+            + b'>\n]>\n<root/>\n'
+        )
+
+        parser = expat.ParserCreate()
+        parser.ElementDeclHandler = lambda _1, _2: None
+        with support.infinite_recursion():
+            with self.assertRaises(RecursionError):
+                parser.Parse(data)
+
+
 class MalformedInputTest(unittest.TestCase):
     def test1(self):
         xml = b"\0\r\n"

diff --git a/Misc/NEWS.d/next/Security/2026-03-14-17-31-39.gh-issue-145986.ifSSr8.rst b/Misc/NEWS.d/next/Security/2026-03-14-17-31-39.gh-issue-145986.ifSSr8.rst
new file mode 100644 (file)
index 0000000..79536d1
--- /dev/null
+++ b/Misc/NEWS.d/next/Security/2026-03-14-17-31-39.gh-issue-145986.ifSSr8.rst
@@ -0,0 +1,4 @@
+:mod:`xml.parsers.expat`: Fixed a crash caused by unbounded C recursion when
+converting deeply nested XML content models with
+:meth:`~xml.parsers.expat.xmlparser.ElementDeclHandler`.
+This addresses :cve:`2026-4224`.

diff --git a/Modules/pyexpat.c b/Modules/pyexpat.c
index 79492ca5c4f79d3018ef34ac7fa6de9360a77147..8673540f358142f031c2c6ec6a381c06db6ce7dd 100644 (file)
--- a/Modules/pyexpat.c
+++ b/Modules/pyexpat.c
@@ -3,6 +3,7 @@
 #endif
 
 #include "Python.h"
+#include "pycore_ceval.h"           // _Py_EnterRecursiveCall()
 #include "pycore_runtime.h"         // _Py_ID()
 #include <ctype.h>
 
@@ -578,6 +579,10 @@ static PyObject *
 conv_content_model(XML_Content * const model,
                    PyObject *(*conv_string)(const XML_Char *))
 {
+    if (_Py_EnterRecursiveCall(" in conv_content_model")) {
+        return NULL;
+    }
+
     PyObject *result = NULL;
     PyObject *children = PyTuple_New(model->numchildren);
     int i;
@@ -589,7 +594,7 @@ conv_content_model(XML_Content * const model,
                                                  conv_string);
             if (child == NULL) {
                 Py_XDECREF(children);
-                return NULL;
+                goto done;
             }
             PyTuple_SET_ITEM(children, i, child);
         }
@@ -597,6 +602,8 @@ conv_content_model(XML_Content * const model,
                                model->type, model->quant,
                                conv_string,model->name, children);
     }
+done:
+    _Py_LeaveRecursiveCall();
     return result;
 }