Merge branch 'c8-stream-2.7' into a8-stream-2.7

This commit is contained in:
Andrew Lukoshko 2023-06-30 11:43:35 +00:00
commit 0615792495
3 changed files with 167 additions and 2 deletions

View File

@ -96,3 +96,23 @@ index 00000000000..5185fac2e29
+length hostname involving bidirectional characters were decoded. Some protocols +length hostname involving bidirectional characters were decoded. Some protocols
+such as :mod:`urllib` http ``3xx`` redirects potentially allow for an attacker +such as :mod:`urllib` http ``3xx`` redirects potentially allow for an attacker
+to supply such a name. +to supply such a name.
diff -urNp a/Lib/encodings/idna.py b/Lib/encodings/idna.py
--- a/Lib/encodings/idna.py 2023-02-16 08:58:06.884171667 +0100
+++ b/Lib/encodings/idna.py 2023-02-16 08:59:31.931296399 +0100
@@ -101,6 +101,16 @@ def ToASCII(label):
raise UnicodeError("label empty or too long")
def ToUnicode(label):
+ if len(label) > 1024:
+ # Protection from https://github.com/python/cpython/issues/98433.
+ # https://datatracker.ietf.org/doc/html/rfc5894#section-6
+ # doesn't specify a label size limit prior to NAMEPREP. But having
+ # one makes practical sense.
+ # This leaves ample room for nameprep() to remove Nothing characters
+ # per https://www.rfc-editor.org/rfc/rfc3454#section-3.1 while still
+ # preventing us from wasting time decoding a big thing that'll just
+ # hit the actual <= 63 length limit in Step 6.
+ raise UnicodeError("label way too long")
# Step 1: Check for ASCII
if isinstance(label, str):
pure_ascii = True

View File

@ -0,0 +1,127 @@
From 0000000000000000000000000000000000000000 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/test/test_urlparse.py | 57 +++++++++++++++++++++++++++++++++++++++
Lib/urlparse.py | 10 +++++++
2 files changed, 67 insertions(+)
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index 16eefed56f6..419e9c2bdcc 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -666,7 +666,64 @@ class UrlParseTestCase(unittest.TestCase):
self.assertEqual(p.scheme, "https")
self.assertEqual(p.geturl(), "https://www.python.org/javascript:alert('msg')/?query=something#fragment")
+ 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."""
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
index 6cc40a8d2fb..0f03a7cc4a9 100644
--- a/Lib/urlparse.py
+++ b/Lib/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
@@ -63,6 +67,10 @@ 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']
@@ -201,6 +209,8 @@ def urlsplit(url, scheme='', allow_fragments=True):
(e.g. netloc is a single string) and we don't expand % escapes."""
url = _remove_unsafe_bytes_from_url(url)
scheme = _remove_unsafe_bytes_from_url(scheme)
+ 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)

View File

@ -105,7 +105,7 @@ Summary: An interpreted, interactive, object-oriented programming language
Name: %{python} Name: %{python}
# Remember to also rebase python2-docs when changing this: # Remember to also rebase python2-docs when changing this:
Version: 2.7.18 Version: 2.7.18
Release: 12%{?dist}.alma Release: 13%{?dist}.1.alma
License: Python License: Python
Group: Development/Languages Group: Development/Languages
Requires: %{python}-libs%{?_isa} = %{version}-%{release} Requires: %{python}-libs%{?_isa} = %{version}-%{release}
@ -817,6 +817,16 @@ Patch382: 00382-cve-2015-20107.patch
# Backported from python3. # Backported from python3.
Patch394: 00394-cve-2022-45061-cpu-denial-of-service-via-inefficient-idna-decoder.patch Patch394: 00394-cve-2022-45061-cpu-denial-of-service-via-inefficient-idna-decoder.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.
Patch399: 00399-cve-2023-24329.patch
# (New patches go here ^^^) # (New patches go here ^^^)
# #
# When adding new patches to "python2" and "python3" in Fedora, EL, etc., # When adding new patches to "python2" and "python3" in Fedora, EL, etc.,
@ -1152,6 +1162,7 @@ git apply %{PATCH351}
%patch378 -p1 %patch378 -p1
%patch382 -p1 %patch382 -p1
%patch394 -p1 %patch394 -p1
%patch399 -p1
# This shouldn't be necesarry, but is right now (2.2a3) # This shouldn't be necesarry, but is right now (2.2a3)
@ -2092,9 +2103,16 @@ fi
# ====================================================== # ======================================================
%changelog %changelog
* Tue May 16 2023 Andrew Lukoshko <alukoshko@almalinux.org> - 2.7.18-12.alma * Fri Jun 30 2023 Andrew Lukoshko <alukoshko@almalinux.org> - 2.7.18-13.1.alma
- Add AlmaLinux to supported distros - Add AlmaLinux to supported distros
* Thu May 25 2023 Charalampos Stratakis <cstratak@redhat.com> - 2.7.18-13.1
- Fix for CVE-2023-24329
Resolves: rhbz#2173917
* Thu Feb 16 2023 Josef Ridky <jridky@redhat.com> - 2.7.18-13
- Add missing part of fix for CVE-2022-45061 (#2145071)
* Wed Dec 21 2022 Charalampos Stratakis <cstratak@redhat.com> - 2.7.18-12 * Wed Dec 21 2022 Charalampos Stratakis <cstratak@redhat.com> - 2.7.18-12
- Security fix for CVE-2022-45061: CPU denial of service via inefficient IDNA decoder - Security fix for CVE-2022-45061: CPU denial of service via inefficient IDNA decoder
Resolves: rhbz#2144072 Resolves: rhbz#2144072