From 5a56cdcbaec2153cd67596c6c2c8056e1ea5ed56 Mon Sep 17 00:00:00 2001 From: David Lord Date: Tue, 2 May 2023 11:31:10 +0000 Subject: [PATCH] Merge pull request from GHSA-xg9f-g7g7-2323 limit the maximum number of multipart form parts CVE: CVE-2023-25577 Upstream-Status: Backport [https://github.com/pallets/werkzeug/commit/517cac5a804e8c4dc4ed038bb20dacd038e7a9f1] Signed-off-by: Narpat Mali --- CHANGES.rst | 5 +++++ docs/request_data.rst | 37 +++++++++++++++++--------------- src/werkzeug/formparser.py | 12 ++++++++++- src/werkzeug/sansio/multipart.py | 8 +++++++ src/werkzeug/wrappers/request.py | 8 +++++++ tests/test_formparser.py | 9 ++++++++ 6 files changed, 61 insertions(+), 18 deletions(-) diff --git a/CHANGES.rst b/CHANGES.rst index a351d7c..6e809ba 100644 --- a/CHANGES.rst +++ b/CHANGES.rst @@ -1,5 +1,10 @@ .. currentmodule:: werkzeug +- Specify a maximum number of multipart parts, default 1000, after which a + ``RequestEntityTooLarge`` exception is raised on parsing. This mitigates a DoS + attack where a larger number of form/file parts would result in disproportionate + resource use. + Version 2.1.1 ------------- diff --git a/docs/request_data.rst b/docs/request_data.rst index 83c6278..e55841e 100644 --- a/docs/request_data.rst +++ b/docs/request_data.rst @@ -73,23 +73,26 @@ read the stream *or* call :meth:`~Request.get_data`. Limiting Request Data --------------------- -To avoid being the victim of a DDOS attack you can set the maximum -accepted content length and request field sizes. The :class:`Request` -class has two attributes for that: :attr:`~Request.max_content_length` -and :attr:`~Request.max_form_memory_size`. - -The first one can be used to limit the total content length. For example -by setting it to ``1024 * 1024 * 16`` the request won't accept more than -16MB of transmitted data. - -Because certain data can't be moved to the hard disk (regular post data) -whereas temporary files can, there is a second limit you can set. The -:attr:`~Request.max_form_memory_size` limits the size of `POST` -transmitted form data. By setting it to ``1024 * 1024 * 2`` you can make -sure that all in memory-stored fields are not more than 2MB in size. - -This however does *not* affect in-memory stored files if the -`stream_factory` used returns a in-memory file. +The :class:`Request` class provides a few attributes to control how much data is +processed from the request body. This can help mitigate DoS attacks that craft the +request in such a way that the server uses too many resources to handle it. Each of +these limits will raise a :exc:`~werkzeug.exceptions.RequestEntityTooLarge` if they are +exceeded. + +- :attr:`~Request.max_content_length` Stop reading request data after this number + of bytes. It's better to configure this in the WSGI server or HTTP server, rather + than the WSGI application. +- :attr:`~Request.max_form_memory_size` Stop reading request data if any form part is + larger than this number of bytes. While file parts can be moved to disk, regular + form field data is stored in memory only. +- :attr:`~Request.max_form_parts` Stop reading request data if more than this number + of parts are sent in multipart form data. This is useful to stop a very large number + of very small parts, especially file parts. The default is 1000. + +Using Werkzeug to set these limits is only one layer of protection. WSGI servers +and HTTPS servers should set their own limits on size and timeouts. The operating system +or container manager should set limits on memory and processing time for server +processes. How to extend Parsing? diff --git a/src/werkzeug/formparser.py b/src/werkzeug/formparser.py index 10d58ca..bebb2fc 100644 --- a/src/werkzeug/formparser.py +++ b/src/werkzeug/formparser.py @@ -179,6 +179,8 @@ class FormDataParser: :param cls: an optional dict class to use. If this is not specified or `None` the default :class:`MultiDict` is used. :param silent: If set to False parsing errors will not be caught. + :param max_form_parts: The maximum number of parts to be parsed. If this is + exceeded, a :exc:`~exceptions.RequestEntityTooLarge` exception is raised. """ def __init__( @@ -190,6 +192,8 @@ class FormDataParser: max_content_length: t.Optional[int] = None, cls: t.Optional[t.Type[MultiDict]] = None, silent: bool = True, + *, + max_form_parts: t.Optional[int] = None, ) -> None: if stream_factory is None: stream_factory = default_stream_factory @@ -199,6 +203,7 @@ class FormDataParser: self.errors = errors self.max_form_memory_size = max_form_memory_size self.max_content_length = max_content_length + self.max_form_parts = max_form_parts if cls is None: cls = MultiDict @@ -281,6 +286,7 @@ class FormDataParser: self.errors, max_form_memory_size=self.max_form_memory_size, cls=self.cls, + max_form_parts=self.max_form_parts, ) boundary = options.get("boundary", "").encode("ascii") @@ -346,10 +352,12 @@ class MultiPartParser: max_form_memory_size: t.Optional[int] = None, cls: t.Optional[t.Type[MultiDict]] = None, buffer_size: int = 64 * 1024, + max_form_parts: t.Optional[int] = None, ) -> None: self.charset = charset self.errors = errors self.max_form_memory_size = max_form_memory_size + self.max_form_parts = max_form_parts if stream_factory is None: stream_factory = default_stream_factory @@ -409,7 +417,9 @@ class MultiPartParser: [None], ) - parser = MultipartDecoder(boundary, self.max_form_memory_size) + parser = MultipartDecoder( + boundary, self.max_form_memory_size, max_parts=self.max_form_parts + ) fields = [] files = [] diff --git a/src/werkzeug/sansio/multipart.py b/src/werkzeug/sansio/multipart.py index 2d54422..e7d742b 100644 --- a/src/werkzeug/sansio/multipart.py +++ b/src/werkzeug/sansio/multipart.py @@ -83,10 +83,13 @@ class MultipartDecoder: self, boundary: bytes, max_form_memory_size: Optional[int] = None, + *, + max_parts: Optional[int] = None, ) -> None: self.buffer = bytearray() self.complete = False self.max_form_memory_size = max_form_memory_size + self.max_parts = max_parts self.state = State.PREAMBLE self.boundary = boundary @@ -113,6 +116,7 @@ class MultipartDecoder: % (LINE_BREAK, re.escape(boundary), LINE_BREAK, LINE_BREAK), re.MULTILINE, ) + self._parts_decoded = 0 def last_newline(self) -> int: try: @@ -177,6 +181,10 @@ class MultipartDecoder: name=name, ) self.state = State.DATA + self._parts_decoded += 1 + + if self.max_parts is not None and self._parts_decoded > self.max_parts: + raise RequestEntityTooLarge() elif self.state == State.DATA: if self.buffer.find(b"--" + self.boundary) == -1: diff --git a/src/werkzeug/wrappers/request.py b/src/werkzeug/wrappers/request.py index 57b739c..a6d5429 100644 --- a/src/werkzeug/wrappers/request.py +++ b/src/werkzeug/wrappers/request.py @@ -83,6 +83,13 @@ class Request(_SansIORequest): #: .. versionadded:: 0.5 max_form_memory_size: t.Optional[int] = None + #: The maximum number of multipart parts to parse, passed to + #: :attr:`form_data_parser_class`. Parsing form data with more than this + #: many parts will raise :exc:`~.RequestEntityTooLarge`. + #: + #: .. versionadded:: 2.2.3 + max_form_parts = 1000 + #: The form data parser that should be used. Can be replaced to customize #: the form date parsing. form_data_parser_class: t.Type[FormDataParser] = FormDataParser @@ -246,6 +253,7 @@ class Request(_SansIORequest): self.max_form_memory_size, self.max_content_length, self.parameter_storage_class, + max_form_parts=self.max_form_parts, ) def _load_form_data(self) -> None: diff --git a/tests/test_formparser.py b/tests/test_formparser.py index 5fc803e..834324f 100644 --- a/tests/test_formparser.py +++ b/tests/test_formparser.py @@ -127,6 +127,15 @@ class TestFormParser: req.max_form_memory_size = 400 assert req.form["foo"] == "Hello World" + req = Request.from_values( + input_stream=io.BytesIO(data), + content_length=len(data), + content_type="multipart/form-data; boundary=foo", + method="POST", + ) + req.max_form_parts = 1 + pytest.raises(RequestEntityTooLarge, lambda: req.form["foo"]) + def test_missing_multipart_boundary(self): data = ( b"--foo\r\nContent-Disposition: form-field; name=foo\r\n\r\n" -- 2.40.0