From a4d48ab5dc499ce0ff6d0e08b3f7b08296088b62 Mon Sep 17 00:00:00 2001 From: Andrew Lukoshko Date: Thu, 22 Jun 2023 10:25:13 +0000 Subject: [PATCH 1/2] import python3-3.6.8-51.0.1.el8_8.1 --- SOURCES/00399-cve-2023-24329.patch | 223 ++++++++++++++++++++++++++ SOURCES/add-oracle-distribution.patch | 12 ++ SPECS/python3.spec | 24 ++- 3 files changed, 258 insertions(+), 1 deletion(-) create mode 100644 SOURCES/00399-cve-2023-24329.patch create mode 100644 SOURCES/add-oracle-distribution.patch diff --git a/SOURCES/00399-cve-2023-24329.patch b/SOURCES/00399-cve-2023-24329.patch new file mode 100644 index 0000000..36bf6e9 --- /dev/null +++ b/SOURCES/00399-cve-2023-24329.patch @@ -0,0 +1,223 @@ +From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001 +From: "Miss Islington (bot)" + <31488909+miss-islington@users.noreply.github.com> +Date: Mon, 22 May 2023 03:42:37 -0700 +Subject: [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 + +(cherry picked from commit f48a96a28012d28ae37a2f4587a780a5eb779946) + +Co-authored-by: Illia Volochii +Co-authored-by: Gregory P. Smith [Google] +--- + Doc/library/urllib.parse.rst | 40 +++++++++++- + Lib/test/test_urlparse.py | 61 ++++++++++++++++++- + Lib/urllib/parse.py | 12 ++++ + ...-03-07-20-59-17.gh-issue-102153.14CLSZ.rst | 3 + + 4 files changed, 113 insertions(+), 3 deletions(-) + create mode 100644 Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst + +diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst +index b717d7cc05..83a7a82089 100644 +--- a/Doc/library/urllib.parse.rst ++++ b/Doc/library/urllib.parse.rst +@@ -126,6 +126,12 @@ or on combining URL components into a URL string. + ``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is + decomposed before parsing, no error will be raised. + ++ ++ .. warning:: ++ ++ :func:`urlparse` does not perform validation. See :ref:`URL parsing ++ security ` for details. ++ + .. versionchanged:: 3.2 + Added IPv6 URL parsing capabilities. + +@@ -288,8 +294,14 @@ or on combining URL components into a URL string. + ``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is + decomposed before parsing, no error will be raised. + +- Following the `WHATWG spec`_ that updates RFC 3986, ASCII newline +- ``\n``, ``\r`` and tab ``\t`` characters are stripped from the URL. ++ Following some of the `WHATWG spec`_ that updates RFC 3986, leading C0 ++ control and space characters are stripped from the URL. ``\n``, ++ ``\r`` and tab ``\t`` characters are removed from the URL at any position. ++ ++ .. warning:: ++ ++ :func:`urlsplit` does not perform validation. See :ref:`URL parsing ++ security ` for details. + + .. versionchanged:: 3.6 + Out-of-range port numbers now raise :exc:`ValueError`, instead of +@@ -302,6 +314,9 @@ or on combining URL components into a URL string. + .. versionchanged:: 3.6.14 + ASCII newline and tab characters are stripped from the URL. + ++ .. versionchanged:: 3.6.15 ++ Leading WHATWG C0 control and space characters are stripped from the URL. ++ + .. _WHATWG spec: https://url.spec.whatwg.org/#concept-basic-url-parser + + .. function:: urlunsplit(parts) +@@ -371,6 +386,27 @@ or on combining URL components into a URL string. + .. versionchanged:: 3.2 + Result is a structured object rather than a simple 2-tuple. + ++.. _url-parsing-security: ++ ++URL parsing security ++-------------------- ++ ++The :func:`urlsplit` and :func:`urlparse` APIs do not perform **validation** of ++inputs. They may not raise errors on inputs that other applications consider ++invalid. They may also succeed on some inputs that might not be considered ++URLs elsewhere. Their purpose is for practical functionality rather than ++purity. ++ ++Instead of raising an exception on unusual input, they may instead return some ++component parts as empty strings. Or components may contain more than perhaps ++they should. ++ ++We recommend that users of these APIs where the values may be used anywhere ++with security implications code defensively. Do some verification within your ++code before trusting a returned component part. Does that ``scheme`` make ++sense? Is that a sensible ``path``? Is there anything strange about that ++``hostname``? etc. ++ + .. _parsing-ascii-encoded-bytes: + + Parsing ASCII Encoded Bytes +diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py +index 3509278a01..7fd61ffea9 100644 +--- a/Lib/test/test_urlparse.py ++++ b/Lib/test/test_urlparse.py +@@ -660,6 +660,65 @@ 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 = bytes(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 = urllib.parse.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 = urllib.parse.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 = urllib.parse.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 = urllib.parse.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(urllib.parse.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 = urllib.parse.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 invalid ports.""" + for bytes in (False, True): +@@ -667,7 +726,7 @@ class UrlParseTestCase(unittest.TestCase): + for port in ("foo", "1.5", "-1", "0x10"): + with self.subTest(bytes=bytes, parse=parse, port=port): + netloc = "www.example.net:" + port +- url = "http://" + netloc ++ url = "http://" + netloc + "/" + if bytes: + netloc = netloc.encode("ascii") + url = url.encode("ascii") +diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py +index ac6e7a9cee..717e990997 100644 +--- a/Lib/urllib/parse.py ++++ b/Lib/urllib/parse.py +@@ -25,6 +25,10 @@ currently not entirely compliant with this RFC due to defacto + 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 +@@ -76,6 +80,10 @@ 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'] + +@@ -426,6 +434,10 @@ def urlsplit(url, scheme='', allow_fragments=True): + url, scheme, _coerce_result = _coerce_args(url, scheme) + url = _remove_unsafe_bytes_from_url(url) + scheme = _remove_unsafe_bytes_from_url(scheme) ++ # Only lstrip url as some applications rely on preserving trailing space. ++ # (https://url.spec.whatwg.org/#concept-basic-url-parser would strip both) ++ 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) +diff --git a/Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst b/Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst +new file mode 100644 +index 0000000000..e57ac4ed3a +--- /dev/null ++++ b/Misc/NEWS.d/next/Security/2023-03-07-20-59-17.gh-issue-102153.14CLSZ.rst +@@ -0,0 +1,3 @@ ++:func:`urllib.parse.urlsplit` now strips leading C0 control and space ++characters following the specification for URLs defined by WHATWG in ++response to CVE-2023-24329. Patch by Illia Volochii. diff --git a/SOURCES/add-oracle-distribution.patch b/SOURCES/add-oracle-distribution.patch new file mode 100644 index 0000000..c0a0fe2 --- /dev/null +++ b/SOURCES/add-oracle-distribution.patch @@ -0,0 +1,12 @@ +diff -ru Python-3.6.6.orig/Lib/platform.py Python-3.6.6/Lib/platform.py +--- Python-3.6.6.orig/Lib/platform.py 2018-06-26 16:39:50.000000000 -0700 ++++ Python-3.6.6/Lib/platform.py 2019-02-15 15:36:37.535102909 -0800 +@@ -265,7 +265,7 @@ + # and http://www.die.net/doc/linux/man/man1/lsb_release.1.html + + _supported_dists = ( +- 'SuSE', 'debian', 'fedora', 'redhat', 'centos', ++ 'SuSE', 'debian', 'fedora', 'redhat', 'centos', 'oracle', + 'mandrake', 'mandriva', 'rocks', 'slackware', 'yellowdog', 'gentoo', + 'UnitedLinux', 'turbolinux', 'arch', 'mageia') + diff --git a/SPECS/python3.spec b/SPECS/python3.spec index 5f7c0a2..abc6f71 100644 --- a/SPECS/python3.spec +++ b/SPECS/python3.spec @@ -14,7 +14,7 @@ URL: https://www.python.org/ # WARNING When rebasing to a new Python version, # remember to update the python3-docs package as well Version: %{pybasever}.8 -Release: 51%{?dist} +Release: 51.0.1%{?dist}.1 License: Python @@ -505,6 +505,7 @@ Patch332: 00332-CVE-2019-16056.patch # https://bugs.python.org/issue37667 # Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1749576 Patch333: 00333-reduce-pgo-tests.patch +Patch10000: add-oracle-distribution.patch # 00338 # # Fix test_gdb for when compiling python with Link Time Optimizations @@ -765,6 +766,18 @@ Patch387: 00387-cve-2020-10735-prevent-dos-by-very-large-int.patch # the behavior to linear. Patch394: 00394-cve-2022-45061-cpu-denial-of-service-via-inefficient-idna-decoder.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: 00399-cve-2023-24329.patch + # (New patches go here ^^^) # # When adding new patches to "python" and "python3" in Fedora, EL, etc., @@ -1085,6 +1098,7 @@ rm Lib/ensurepip/_bundled/*.whl %patch344 -p1 %patch345 -p1 %patch346 -p1 +%patch10000 -p1 # Patch 351 adds binary file for testing. We need to apply it using Git. git apply %{PATCH351} @@ -1110,6 +1124,7 @@ git apply %{PATCH351} %patch386 -p1 %patch387 -p1 %patch394 -p1 +%patch399 -p1 # Remove files that should be generated by the build # (This is after patching, so that we can use patches directly from upstream) @@ -2041,6 +2056,13 @@ fi # ====================================================== %changelog +* Wed Jun 14 2023 EL Errata - 3.6.8-51.0.1 +- Add Oracle Linux distribution in platform.py [Orabug: 20812544] + +* Wed May 31 2023 Charalampos Stratakis - 3.6.8-51.1 +- Security fix for CVE-2023-24329 +Resolves: rhbz#2173917 + * Tue Jan 24 2023 Charalampos Stratakis - 3.6.8-51 - Properly strip the LTO bytecode from python.o Resolves: rhbz#2137707 From b1403574181374659a667bdae25a57d8239352d4 Mon Sep 17 00:00:00 2001 From: Andrew Lukoshko Date: Thu, 22 Jun 2023 10:25:59 +0000 Subject: [PATCH 2/2] Debrand --- SOURCES/add-oracle-distribution.patch | 12 ------------ SPECS/python3.spec | 7 +------ 2 files changed, 1 insertion(+), 18 deletions(-) delete mode 100644 SOURCES/add-oracle-distribution.patch diff --git a/SOURCES/add-oracle-distribution.patch b/SOURCES/add-oracle-distribution.patch deleted file mode 100644 index c0a0fe2..0000000 --- a/SOURCES/add-oracle-distribution.patch +++ /dev/null @@ -1,12 +0,0 @@ -diff -ru Python-3.6.6.orig/Lib/platform.py Python-3.6.6/Lib/platform.py ---- Python-3.6.6.orig/Lib/platform.py 2018-06-26 16:39:50.000000000 -0700 -+++ Python-3.6.6/Lib/platform.py 2019-02-15 15:36:37.535102909 -0800 -@@ -265,7 +265,7 @@ - # and http://www.die.net/doc/linux/man/man1/lsb_release.1.html - - _supported_dists = ( -- 'SuSE', 'debian', 'fedora', 'redhat', 'centos', -+ 'SuSE', 'debian', 'fedora', 'redhat', 'centos', 'oracle', - 'mandrake', 'mandriva', 'rocks', 'slackware', 'yellowdog', 'gentoo', - 'UnitedLinux', 'turbolinux', 'arch', 'mageia') - diff --git a/SPECS/python3.spec b/SPECS/python3.spec index abc6f71..136bb55 100644 --- a/SPECS/python3.spec +++ b/SPECS/python3.spec @@ -14,7 +14,7 @@ URL: https://www.python.org/ # WARNING When rebasing to a new Python version, # remember to update the python3-docs package as well Version: %{pybasever}.8 -Release: 51.0.1%{?dist}.1 +Release: 51%{?dist}.1 License: Python @@ -505,7 +505,6 @@ Patch332: 00332-CVE-2019-16056.patch # https://bugs.python.org/issue37667 # Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1749576 Patch333: 00333-reduce-pgo-tests.patch -Patch10000: add-oracle-distribution.patch # 00338 # # Fix test_gdb for when compiling python with Link Time Optimizations @@ -1098,7 +1097,6 @@ rm Lib/ensurepip/_bundled/*.whl %patch344 -p1 %patch345 -p1 %patch346 -p1 -%patch10000 -p1 # Patch 351 adds binary file for testing. We need to apply it using Git. git apply %{PATCH351} @@ -2056,9 +2054,6 @@ fi # ====================================================== %changelog -* Wed Jun 14 2023 EL Errata - 3.6.8-51.0.1 -- Add Oracle Linux distribution in platform.py [Orabug: 20812544] - * Wed May 31 2023 Charalampos Stratakis - 3.6.8-51.1 - Security fix for CVE-2023-24329 Resolves: rhbz#2173917