sslutil: fall back to commonName when no dNSName in subjectAltName (issue2798)

Any entries in subjectAltName would prevent fallback to using commonName, but
RFC 2818 says:

    If a subjectAltName extension of type dNSName is present, that MUST
    be used as the identity. Otherwise, the (most specific) Common Name
    field in the Subject field of the certificate MUST be used.

We now only consider dNSNames in subjectAltName.

(dNSName is known as 'DNS' in OpenSSL/Python.)

mercurial/sslutil.py

@@ -1,128 +1,129
 # sslutil.py - SSL handling for mercurial
 #
 # Copyright 2005, 2006, 2007, 2008 Matt Mackall <[e-mail]>
 # Copyright 2006, 2007 Alexis S. L. Carvalho <[e-mail]>
 # Copyright 2006 Vadim Gelfer <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 import os
 
 from mercurial import util
 from mercurial.i18n import _
 try:
     # avoid using deprecated/broken FakeSocket in python 2.6
     import ssl
     ssl_wrap_socket = ssl.wrap_socket
     CERT_REQUIRED = ssl.CERT_REQUIRED
 except ImportError:
     CERT_REQUIRED = 2
 
     import socket, httplib
 
     def ssl_wrap_socket(sock, key_file, cert_file,
                         cert_reqs=CERT_REQUIRED, ca_certs=None):
         if ca_certs:
             raise util.Abort(_(
                 'certificate checking requires Python 2.6'))
 
         ssl = socket.ssl(sock, key_file, cert_file)
         return httplib.FakeSocket(sock, ssl)
 
 def _verifycert(cert, hostname):
     '''Verify that cert (in socket.getpeercert() format) matches hostname.
     CRLs is not handled.
 
     Returns error message if any problems are found and None on success.
     '''
     if not cert:
         return _('no certificate received')
     dnsname = hostname.lower()
     def matchdnsname(certname):
         return (certname == dnsname or
                 '.' in dnsname and certname == '*.' + dnsname.split('.', 1)[1])
 
     san = cert.get('subjectAltName', [])
     if san:
         certnames = [value.lower() for key, value in san if key == 'DNS']
         for name in certnames:
             if matchdnsname(name):
                 return None
-        return _('certificate is for %s') % ', '.join(certnames)
+        if certnames:
+            return _('certificate is for %s') % ', '.join(certnames)
 
     # subject is only checked when subjectAltName is empty
     for s in cert.get('subject', []):
         key, value = s[0]
         if key == 'commonName':
             try:
                 # 'subject' entries are unicode
                 certname = value.lower().encode('ascii')
             except UnicodeEncodeError:
                 return _('IDN in certificate not supported')
             if matchdnsname(certname):
                 return None
             return _('certificate is for %s') % certname
     return _('no commonName or subjectAltName found in certificate')
 
 
 # CERT_REQUIRED means fetch the cert from the server all the time AND
 # validate it against the CA store provided in web.cacerts.
 #
 # We COMPLETELY ignore CERT_REQUIRED on Python <= 2.5, as it's totally
 # busted on those versions.
 
 def sslkwargs(ui, host):
     cacerts = ui.config('web', 'cacerts')
     hostfingerprint = ui.config('hostfingerprints', host)
     if cacerts and not hostfingerprint:
         cacerts = util.expandpath(cacerts)
         if not os.path.exists(cacerts):
             raise util.Abort(_('could not find web.cacerts: %s') % cacerts)
         return {'ca_certs': cacerts,
                 'cert_reqs': CERT_REQUIRED,
                 }
     return {}
 
 class validator(object):
     def __init__(self, ui, host):
         self.ui = ui
         self.host = host
 
     def __call__(self, sock):
         host = self.host
         cacerts = self.ui.config('web', 'cacerts')
         hostfingerprint = self.ui.config('hostfingerprints', host)
         if cacerts and not hostfingerprint:
             msg = _verifycert(sock.getpeercert(), host)
             if msg:
                 raise util.Abort(_('%s certificate error: %s '
                                    '(use --insecure to connect '
                                    'insecurely)') % (host, msg))
             self.ui.debug('%s certificate successfully verified\n' % host)
         else:
             if getattr(sock, 'getpeercert', False):
                 peercert = sock.getpeercert(True)
                 peerfingerprint = util.sha1(peercert).hexdigest()
                 nicefingerprint = ":".join([peerfingerprint[x:x + 2]
                     for x in xrange(0, len(peerfingerprint), 2)])
                 if hostfingerprint:
                     if peerfingerprint.lower() != \
                             hostfingerprint.replace(':', '').lower():
                         raise util.Abort(_('invalid certificate for %s '
                                            'with fingerprint %s') %
                                          (host, nicefingerprint))
                     self.ui.debug('%s certificate matched fingerprint %s\n' %
                                   (host, nicefingerprint))
                 else:
                     self.ui.warn(_('warning: %s certificate '
                                    'with fingerprint %s not verified '
                                    '(check hostfingerprints or web.cacerts '
                                    'config setting)\n') %
                                  (host, nicefingerprint))
             else: # python 2.5 ?
                 if hostfingerprint:
                     raise util.Abort(_('no certificate for %s with '
                                        'configured hostfingerprint') % host)
                 self.ui.warn(_('warning: %s certificate not verified '
                                '(check web.cacerts config setting)\n') %
                              host)

tests/test-url.py

@@ -1,217 +1,221
 import sys
 
 def check(a, b):
     if a != b:
         print (a, b)
 
 def cert(cn):
     return dict(subject=((('commonName', cn),),))
 
 from mercurial.sslutil import _verifycert
 
 # Test non-wildcard certificates
 check(_verifycert(cert('example.com'), 'example.com'),
       None)
 check(_verifycert(cert('example.com'), 'www.example.com'),
       'certificate is for example.com')
 check(_verifycert(cert('www.example.com'), 'example.com'),
       'certificate is for www.example.com')
 
 # Test wildcard certificates
 check(_verifycert(cert('*.example.com'), 'www.example.com'),
       None)
 check(_verifycert(cert('*.example.com'), 'example.com'),
       'certificate is for *.example.com')
 check(_verifycert(cert('*.example.com'), 'w.w.example.com'),
       'certificate is for *.example.com')
 
 # Test subjectAltName
 san_cert = {'subject': ((('commonName', 'example.com'),),),
             'subjectAltName': (('DNS', '*.example.net'),
                                ('DNS', 'example.net'))}
 check(_verifycert(san_cert, 'example.net'),
       None)
 check(_verifycert(san_cert, 'foo.example.net'),
       None)
-# subject is only checked when subjectAltName is empty
+# no fallback to subject commonName when subjectAltName has DNS
 check(_verifycert(san_cert, 'example.com'),
       'certificate is for *.example.net, example.net')
+# fallback to subject commonName when no DNS in subjectAltName
+san_cert = {'subject': ((('commonName', 'example.com'),),),
+            'subjectAltName': (('IP Address', '8.8.8.8'),)}
+check(_verifycert(san_cert, 'example.com'), None)
 
 # Avoid some pitfalls
 check(_verifycert(cert('*.foo'), 'foo'),
       'certificate is for *.foo')
 check(_verifycert(cert('*o'), 'foo'),
       'certificate is for *o')
 
 check(_verifycert({'subject': ()},
                   'example.com'),
       'no commonName or subjectAltName found in certificate')
 check(_verifycert(None, 'example.com'),
       'no certificate received')
 
+# Unicode (IDN) certname isn't supported
+check(_verifycert(cert(u'\u4f8b.jp'), 'example.jp'),
+      'IDN in certificate not supported')
+
 import doctest
 
 def test_url():
     """
     >>> from mercurial.util import url
 
     This tests for edge cases in url.URL's parsing algorithm. Most of
     these aren't useful for documentation purposes, so they aren't
     part of the class's doc tests.
 
     Query strings and fragments:
 
     >>> url('http://host/a?b#c')
     <url scheme: 'http', host: 'host', path: 'a', query: 'b', fragment: 'c'>
     >>> url('http://host/a?')
     <url scheme: 'http', host: 'host', path: 'a'>
     >>> url('http://host/a#b#c')
     <url scheme: 'http', host: 'host', path: 'a', fragment: 'b#c'>
     >>> url('http://host/a#b?c')
     <url scheme: 'http', host: 'host', path: 'a', fragment: 'b?c'>
     >>> url('http://host/?a#b')
     <url scheme: 'http', host: 'host', path: '', query: 'a', fragment: 'b'>
     >>> url('http://host/?a#b', parsequery=False)
     <url scheme: 'http', host: 'host', path: '?a', fragment: 'b'>
     >>> url('http://host/?a#b', parsefragment=False)
     <url scheme: 'http', host: 'host', path: '', query: 'a#b'>
     >>> url('http://host/?a#b', parsequery=False, parsefragment=False)
     <url scheme: 'http', host: 'host', path: '?a#b'>
 
     IPv6 addresses:
 
     >>> url('ldap://[2001:db8::7]/c=GB?objectClass?one')
     <url scheme: 'ldap', host: '[2001:db8::7]', path: 'c=GB',
          query: 'objectClass?one'>
     >>> url('ldap://joe:xxx@[2001:db8::7]:80/c=GB?objectClass?one')
     <url scheme: 'ldap', user: 'joe', passwd: 'xxx', host: '[2001:db8::7]',
          port: '80', path: 'c=GB', query: 'objectClass?one'>
 
     Missing scheme, host, etc.:
 
     >>> url('://192.0.2.16:80/')
     <url path: '://192.0.2.16:80/'>
     >>> url('http://mercurial.selenic.com')
     <url scheme: 'http', host: 'mercurial.selenic.com'>
     >>> url('/foo')
     <url path: '/foo'>
     >>> url('bundle:/foo')
     <url scheme: 'bundle', path: '/foo'>
     >>> url('a?b#c')
     <url path: 'a?b', fragment: 'c'>
     >>> url('http://x.com?arg=/foo')
     <url scheme: 'http', host: 'x.com', query: 'arg=/foo'>
     >>> url('http://joe:xxx@/foo')
     <url scheme: 'http', user: 'joe', passwd: 'xxx', path: 'foo'>
 
     Just a scheme and a path:
 
     >>> url('mailto:[e-mail]')
     <url scheme: 'mailto', path: '[e-mail]'>
     >>> url('a:b:c:d')
     <url path: 'a:b:c:d'>
     >>> url('aa:bb:cc:dd')
     <url scheme: 'aa', path: 'bb:cc:dd'>
 
     SSH examples:
 
     >>> url('ssh://joe@host//home/joe')
     <url scheme: 'ssh', user: 'joe', host: 'host', path: '/home/joe'>
     >>> url('ssh://joe:xxx@host/src')
     <url scheme: 'ssh', user: 'joe', passwd: 'xxx', host: 'host', path: 'src'>
     >>> url('ssh://joe:xxx@host')
     <url scheme: 'ssh', user: 'joe', passwd: 'xxx', host: 'host'>
     >>> url('ssh://joe@host')
     <url scheme: 'ssh', user: 'joe', host: 'host'>
     >>> url('ssh://host')
     <url scheme: 'ssh', host: 'host'>
     >>> url('ssh://')
     <url scheme: 'ssh'>
     >>> url('ssh:')
     <url scheme: 'ssh'>
 
     Non-numeric port:
 
     >>> url('http://example.com:dd')
     <url scheme: 'http', host: 'example.com', port: 'dd'>
     >>> url('ssh://joe:xxx@host:ssh/foo')
     <url scheme: 'ssh', user: 'joe', passwd: 'xxx', host: 'host', port: 'ssh',
          path: 'foo'>
 
     Bad authentication credentials:
 
     >>> url('http://joe@joeville:123@4:@host/a?b#c')
     <url scheme: 'http', user: 'joe@joeville', passwd: '123@4:',
          host: 'host', path: 'a', query: 'b', fragment: 'c'>
     >>> url('http://!*#?/@!*#?/:@host/a?b#c')
     <url scheme: 'http', host: '!*', fragment: '?/@!*#?/:@host/a?b#c'>
     >>> url('http://!*#?@!*#?:@host/a?b#c')
     <url scheme: 'http', host: '!*', fragment: '?@!*#?:@host/a?b#c'>
     >>> url('http://!*@:!*@@host/a?b#c')
     <url scheme: 'http', user: '!*@', passwd: '!*@', host: 'host',
          path: 'a', query: 'b', fragment: 'c'>
 
     File paths:
 
     >>> url('a/b/c/d.g.f')
     <url path: 'a/b/c/d.g.f'>
     >>> url('/x///z/y/')
     <url path: '/x///z/y/'>
     >>> url('/foo:bar')
     <url path: '/foo:bar'>
     >>> url('\\\\foo:bar')
     <url path: '\\\\foo:bar'>
     >>> url('./foo:bar')
     <url path: './foo:bar'>
 
     Non-localhost file URL:
 
     >>> u = url('file://mercurial.selenic.com/foo')
     Traceback (most recent call last):
       File "<stdin>", line 1, in ?
     Abort: file:// URLs can only refer to localhost
 
     Empty URL:
 
     >>> u = url('')
     >>> u
     <url path: ''>
     >>> str(u)
     ''
 
     Empty path with query string:
 
     >>> str(url('http://foo/?bar'))
     'http://foo/?bar'
 
     Invalid path:
 
     >>> u = url('http://foo/bar')
     >>> u.path = 'bar'
     >>> str(u)
     'http://foo/bar'
 
     >>> u = url('file:/foo/bar/baz')
     >>> u
     <url scheme: 'file', path: '/foo/bar/baz'>
     >>> str(u)
     'file:///foo/bar/baz'
 
     >>> u = url('file:///foo/bar/baz')
     >>> u
     <url scheme: 'file', path: '/foo/bar/baz'>
     >>> str(u)
     'file:///foo/bar/baz'
 
     >>> u = url('file:foo/bar/baz')
     >>> u
     <url scheme: 'file', path: 'foo/bar/baz'>
     >>> str(u)
     'file:foo/bar/baz'
     """
 
 doctest.testmod(optionflags=doctest.NORMALIZE_WHITESPACE)
-
-# Unicode (IDN) certname isn't supported
-check(_verifycert(cert(u'\u4f8b.jp'), 'example.jp'),
-      'IDN in certificate not supported')