Security fix for CVE-2023-24329

Resolves: rhbz#2174018
This commit is contained in:
Charalampos Stratakis 2023-05-29 18:54:49 +02:00
parent 64d44f1f88
commit e78e06dbee
2 changed files with 148 additions and 1 deletions

131
399-cve-2023-24329.patch Normal file
View File

@ -0,0 +1,131 @@
From 71b1e29f61ee1fa7d70a0b00bdbca5eddf107076 Mon Sep 17 00:00:00 2001
From: Lumir Balhar <lbalhar@redhat.com>
Date: Thu, 25 May 2023 10:03:57 +0200
Subject: [PATCH] 00399-cve-2023-24329.patch
00399 #
* gh-102153: Start stripping C0 control and space chars in `urlsplit` (GH-102508)
`urllib.parse.urlsplit` has already been respecting the WHATWG spec a bit GH-25595.
This adds more sanitizing to respect the "Remove any leading C0 control or space from input" [rule](https://url.spec.whatwg.org/GH-url-parsing:~:text=Remove%20any%20leading%20and%20trailing%20C0%20control%20or%20space%20from%20input.) in response to [CVE-2023-24329](https://nvd.nist.gov/vuln/detail/CVE-2023-24329).
Backported to Python 2 from Python 3.12.
Co-authored-by: Illia Volochii <illia.volochii@gmail.com>
Co-authored-by: Gregory P. Smith [Google] <greg@krypto.org>
Co-authored-by: Lumir Balhar <lbalhar@redhat.com>
---
lib-python/2.7/test/test_urlparse.py | 59 ++++++++++++++++++++++++++++
lib-python/2.7/urlparse.py | 10 +++++
2 files changed, 69 insertions(+)
diff --git a/lib-python/2.7/test/test_urlparse.py b/lib-python/2.7/test/test_urlparse.py
index 9912fe2..94fe940 100644
--- a/lib-python/2.7/test/test_urlparse.py
+++ b/lib-python/2.7/test/test_urlparse.py
@@ -572,6 +572,65 @@ class UrlParseTestCase(unittest.TestCase):
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), b"http://www.python.org/javascript:alert('msg')/#frag")
+ def test_urlsplit_strip_url(self):
+ noise = "".join([chr(i) for i in range(0, 0x20 + 1)])
+ base_url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
+
+ url = noise.decode("utf-8") + base_url
+ p = urlparse.urlsplit(url)
+ self.assertEqual(p.scheme, "http")
+ self.assertEqual(p.netloc, "User:Pass@www.python.org:080")
+ self.assertEqual(p.path, "/doc/")
+ self.assertEqual(p.query, "query=yes")
+ self.assertEqual(p.fragment, "frag")
+ self.assertEqual(p.username, "User")
+ self.assertEqual(p.password, "Pass")
+ self.assertEqual(p.hostname, "www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), base_url)
+
+ url = noise + base_url.encode("utf-8")
+ p = urlparse.urlsplit(url)
+ self.assertEqual(p.scheme, b"http")
+ self.assertEqual(p.netloc, b"User:Pass@www.python.org:080")
+ self.assertEqual(p.path, b"/doc/")
+ self.assertEqual(p.query, b"query=yes")
+ self.assertEqual(p.fragment, b"frag")
+ self.assertEqual(p.username, b"User")
+ self.assertEqual(p.password, b"Pass")
+ self.assertEqual(p.hostname, b"www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), base_url.encode("utf-8"))
+
+ # Test that trailing space is preserved as some applications rely on
+ # this within query strings.
+ query_spaces_url = "https://www.python.org:88/doc/?query= "
+ p = urlparse.urlsplit(noise.decode("utf-8") + query_spaces_url)
+ self.assertEqual(p.scheme, "https")
+ self.assertEqual(p.netloc, "www.python.org:88")
+ self.assertEqual(p.path, "/doc/")
+ self.assertEqual(p.query, "query= ")
+ self.assertEqual(p.port, 88)
+ self.assertEqual(p.geturl(), query_spaces_url)
+
+ p = urlparse.urlsplit("www.pypi.org ")
+ # That "hostname" gets considered a "path" due to the
+ # trailing space and our existing logic... YUCK...
+ # and re-assembles via geturl aka unurlsplit into the original.
+ # django.core.validators.URLValidator (at least through v3.2) relies on
+ # this, for better or worse, to catch it in a ValidationError via its
+ # regular expressions.
+ # Here we test the basic round trip concept of such a trailing space.
+ self.assertEqual(urlparse.urlunsplit(p), "www.pypi.org ")
+
+ # with scheme as cache-key
+ url = "//www.python.org/"
+ scheme = noise.decode("utf-8") + "https" + noise.decode("utf-8")
+ for _ in range(2):
+ p = urlparse.urlsplit(url, scheme=scheme)
+ self.assertEqual(p.scheme, "https")
+ self.assertEqual(p.geturl(), "https://www.python.org/")
+
def test_attributes_bad_port(self):
"""Check handling of non-integer ports."""
p = urlparse.urlsplit("http://www.example.net:foo")
diff --git a/lib-python/2.7/urlparse.py b/lib-python/2.7/urlparse.py
index 6f6c435..5adf78d 100644
--- a/lib-python/2.7/urlparse.py
+++ b/lib-python/2.7/urlparse.py
@@ -26,6 +26,10 @@ scenarios for parsing, and for backward compatibility purposes, some
parsing quirks from older RFCs are retained. The testcases in
test_urlparse.py provides a good indicator of parsing behavior.
+The WHATWG URL Parser spec should also be considered. We are not compliant with
+it either due to existing user code API behavior expectations (Hyrum's Law).
+It serves as a useful guide when making changes.
+
"""
import re
@@ -62,6 +66,10 @@ scheme_chars = ('abcdefghijklmnopqrstuvwxyz'
'0123456789'
'+-.')
+# Leading and trailing C0 control and space to be stripped per WHATWG spec.
+# == "".join([chr(i) for i in range(0, 0x20 + 1)])
+_WHATWG_C0_CONTROL_OR_SPACE = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\t\n\x0b\x0c\r\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f '
+
# Unsafe bytes to be removed per WHATWG spec
_UNSAFE_URL_BYTES_TO_REMOVE = ['\t', '\r', '\n']
@@ -193,6 +201,8 @@ def urlsplit(url, scheme='', allow_fragments=True):
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
+ url = url.lstrip(_WHATWG_C0_CONTROL_OR_SPACE)
+ scheme = scheme.strip(_WHATWG_C0_CONTROL_OR_SPACE)
allow_fragments = bool(allow_fragments)
key = url, scheme, allow_fragments, type(url), type(scheme)
cached = _parse_cache.get(key, None)
--
2.40.1

View File

@ -6,7 +6,7 @@
Name: pypy
Version: %{basever}.11
%global pyversion 2.7
Release: 2%{?dist}
Release: 3%{?dist}
Summary: Python implementation with a Just-In-Time compiler
# PyPy is MIT
@ -188,6 +188,18 @@ Source189: 189-use-rpm-wheels.patch
# Backported from python3.
Patch382: 382-cve-2015-20107.patch
# 00399 #
# CVE-2023-24329
#
# gh-102153: Start stripping C0 control and space chars in `urlsplit` (GH-102508)
#
# `urllib.parse.urlsplit` has already been respecting the WHATWG spec a bit GH-25595.
#
# This adds more sanitizing to respect the "Remove any leading C0 control or space from input" [rule](https://url.spec.whatwg.org/GH-url-parsing:~:text=Remove%%20any%%20leading%%20and%%20trailing%%20C0%%20control%%20or%%20space%%20from%%20input.) in response to [CVE-2023-24329](https://nvd.nist.gov/vuln/detail/CVE-2023-24329).
#
# Backported from Python 3.12
Patch399: 399-cve-2023-24329.patch
# Build-time requirements:
# pypy's can be rebuilt using itself, rather than with CPython; doing so
@ -867,6 +879,10 @@ CheckPyPy %{name}-c-stackless
%changelog
* Mon May 29 2023 Charalampos Stratakis <cstratak@redhat.com> - 7.3.11-3
- Security fix for CVE-2023-24329
Resolves: rhbz#2174018
* Fri Jan 20 2023 Fedora Release Engineering <releng@fedoraproject.org> - 7.3.11-2
- Rebuilt for https://fedoraproject.org/wiki/Fedora_38_Mass_Rebuild