From e42be9b593f1d5e83a947f73058b919395398424 Mon Sep 17 00:00:00 2001
From: Julian Berman <Julian+Hg@GrayVines.com>
Date: Fri, 23 Sep 2022 11:30:55 +0200
Subject: [PATCH] Pull in the http.server vulnerability fix from
 python/cpython#87389

Fixes an open redirection vulnerability for paths starting with `//`.

Closes: #3812

--HG--
branch : http_server_vuln_fix
---
 lib-python/3/http/server.py           |  7 ++++
 lib-python/3/test/test_httpservers.py | 49 +++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/lib-python/3/http/server.py b/lib-python/3/http/server.py
index 38f7accad7..39de35458c 100644
--- a/lib-python/3/http/server.py
+++ b/lib-python/3/http/server.py
@@ -332,6 +332,13 @@ class BaseHTTPRequestHandler(socketserver.StreamRequestHandler):
                 return False
         self.command, self.path = command, path
 
+        # gh-87389: The purpose of replacing '//' with '/' is to protect
+        # against open redirect attacks possibly triggered if the path starts
+        # with '//' because http clients treat //path as an absolute URI
+        # without scheme (similar to http://path) rather than a path.
+        if self.path.startswith('//'):
+            self.path = '/' + self.path.lstrip('/')  # Reduce to a single /
+
         # Examine the headers and look for a Connection directive.
         try:
             self.headers = http.client.parse_headers(self.rfile,
diff --git a/lib-python/3/test/test_httpservers.py b/lib-python/3/test/test_httpservers.py
index c5b833723e..97dae7a7ce 100644
--- a/lib-python/3/test/test_httpservers.py
+++ b/lib-python/3/test/test_httpservers.py
@@ -416,6 +416,55 @@ class SimpleHTTPServerTestCase(BaseTestCase):
         self.check_status_and_reason(response, HTTPStatus.OK,
                                      data=support.TESTFN_UNDECODABLE)
 
+    def test_get_dir_redirect_location_domain_injection_bug(self):
+        """Ensure //evil.co/..%2f../../X does not put //evil.co/ in Location.
+
+        //netloc/ in a Location header is a redirect to a new host.
+        https://github.com/python/cpython/issues/87389
+
+        This checks that a path resolving to a directory on our server cannot
+        resolve into a redirect to another server.
+        """
+        os.mkdir(os.path.join(self.tempdir, 'existing_directory'))
+        url = f'/python.org/..%2f..%2f..%2f..%2f..%2f../%0a%0d/../{self.tempdir_name}/existing_directory'
+        expected_location = f'{url}/'  # /python.org.../ single slash single prefix, trailing slash
+        # Canonicalizes to /tmp/tempdir_name/existing_directory which does
+        # exist and is a dir, triggering the 301 redirect logic.
+        response = self.request(url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        location = response.getheader('Location')
+        self.assertEqual(location, expected_location, msg='non-attack failed!')
+
+        # //python.org... multi-slash prefix, no trailing slash
+        attack_url = f'/{url}'
+        response = self.request(attack_url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        location = response.getheader('Location')
+        self.assertFalse(location.startswith('//'), msg=location)
+        self.assertEqual(location, expected_location,
+                msg='Expected Location header to start with a single / and '
+                'end with a / as this is a directory redirect.')
+
+        # ///python.org... triple-slash prefix, no trailing slash
+        attack3_url = f'//{url}'
+        response = self.request(attack3_url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        self.assertEqual(response.getheader('Location'), expected_location)
+
+        # If the second word in the http request (Request-URI for the http
+        # method) is a full URI, we don't worry about it, as that'll be parsed
+        # and reassembled as a full URI within BaseHTTPRequestHandler.send_head
+        # so no errant scheme-less //netloc//evil.co/ domain mixup can happen.
+        attack_scheme_netloc_2slash_url = f'https://pypi.org/{url}'
+        expected_scheme_netloc_location = f'{attack_scheme_netloc_2slash_url}/'
+        response = self.request(attack_scheme_netloc_2slash_url)
+        self.check_status_and_reason(response, HTTPStatus.MOVED_PERMANENTLY)
+        location = response.getheader('Location')
+        # We're just ensuring that the scheme and domain make it through, if
+        # there are or aren't multiple slashes at the start of the path that
+        # follows that isn't important in this Location: header.
+        self.assertTrue(location.startswith('https://pypi.org/'), msg=location)
+
     def test_get(self):
         #constructs the path relative to the root directory of the HTTPServer
         response = self.request(self.base_url + '/test')
-- 
GitLab