bpo-38876: Raise pickle.UnpicklingError when loading an item from memo for invalid input

PCManticore · PCManticore · commit f8e15c1f6931 · 2019-11-23T09:36:29.000+01:00
The previous code was raising a `KeyError` for both the Python and C implementation.
This was caused by the specified index of an invalid input which did not exist
in the memo structure, where the pickle stores what objects it has seen.
The malformed input would have caused either a `BINGET` or `LONG_BINGET` load
from the memo, leading to a `KeyError` as the determined index was bogus.
diff --git a/Lib/pickle.py b/Lib/pickle.py
@@ -1604,17 +1604,29 @@ def load_dup(self):
 
     def load_get(self):
         i = int(self.readline()[:-1])
-        self.append(self.memo[i])
+        try:
+            self.append(self.memo[i])
+        except KeyError:
+            msg = f'Memo value not found at index {i}'
+            raise UnpicklingError(msg) from None
     dispatch[GET[0]] = load_get
 
     def load_binget(self):
         i = self.read(1)[0]
-        self.append(self.memo[i])
+        try:
+            self.append(self.memo[i])
+        except KeyError as exc:
+            msg = f'Memo value not found at index {i}'
+            raise UnpicklingError(msg) from None
     dispatch[BINGET[0]] = load_binget
 
     def load_long_binget(self):
         i, = unpack('<I', self.read(4))
-        self.append(self.memo[i])
+        try:
+            self.append(self.memo[i])
+        except KeyError as exc:
+            msg = f'Memo value not found at index {i}'
+            raise UnpicklingError(msg) from None
     dispatch[LONG_BINGET[0]] = load_long_binget
 
     def load_put(self):
diff --git a/Lib/test/pickletester.py b/Lib/test/pickletester.py
@@ -1019,7 +1019,9 @@ def test_short_binunicode(self):
         self.assertEqual(self.loads(dumped), '\u20ac\x00')
 
     def test_misc_get(self):
-        self.check_unpickling_error(KeyError, b'g0\np0')
+        self.check_unpickling_error(pickle.UnpicklingError, b'g0\np0')
+        self.check_unpickling_error(pickle.UnpicklingError, b'jens:')
+        self.check_unpickling_error(pickle.UnpicklingError, b'hens:')
         self.assert_is_copy([(100,), (100,)],
                             self.loads(b'((Kdtp0\nh\x00l.))'))
 
diff --git a/Misc/NEWS.d/next/Library/2019-11-22-10-58-58.bpo-38876.qqy1Vp.rst b/Misc/NEWS.d/next/Library/2019-11-22-10-58-58.bpo-38876.qqy1Vp.rst
@@ -0,0 +1,9 @@
+Raise pickle.UnpicklingError when loading an item from memo for invalid
+input
+
+The previous code was raising a `KeyError` for both the Python and C
+implementation. This was caused by the specified index of an invalid input
+which did not exist in the memo structure, where the pickle stores what
+objects it has seen. The malformed input would have caused either a `BINGET`
+or `LONG_BINGET` load from the memo, leading to a `KeyError` as the
+determined index was bogus. Patch by Claudiu Popa
diff --git a/Modules/_pickle.c b/Modules/_pickle.c
@@ -6174,8 +6174,10 @@ load_get(UnpicklerObject *self)
 
     value = _Unpickler_MemoGet(self, idx);
     if (value == NULL) {
-        if (!PyErr_Occurred())
-            PyErr_SetObject(PyExc_KeyError, key);
+        if (!PyErr_Occurred()) {
+           PickleState *st = _Pickle_GetGlobalState();
+           PyErr_Format(st->UnpicklingError, "Memo value not found at index %ld", idx);
+        }
         Py_DECREF(key);
         return -1;
     }
@@ -6201,7 +6203,8 @@ load_binget(UnpicklerObject *self)
     if (value == NULL) {
         PyObject *key = PyLong_FromSsize_t(idx);
         if (key != NULL) {
-            PyErr_SetObject(PyExc_KeyError, key);
+            PickleState *st = _Pickle_GetGlobalState();
+            PyErr_Format(st->UnpicklingError, "Memo value not found at index %ld", idx);
             Py_DECREF(key);
         }
         return -1;
@@ -6227,7 +6230,8 @@ load_long_binget(UnpicklerObject *self)
     if (value == NULL) {
         PyObject *key = PyLong_FromSsize_t(idx);
         if (key != NULL) {
-            PyErr_SetObject(PyExc_KeyError, key);
+            PickleState *st = _Pickle_GetGlobalState();
+            PyErr_Format(st->UnpicklingError, "Memo value not found at index %ld", idx);
             Py_DECREF(key);
         }
         return -1;
