view mercurial/hgweb/protocol.py @ 35848:ff4bc0ab6740 stable

wireproto: check permissions when executing "batch" command (BC) (SEC)

For as long as the "batch" command has existed (introduced by
bd88561afb4b and first released as part of Mercurial 1.9), that command
(like most wire commands introduced after 2008) lacked an entry in
the hgweb permissions table. And since we don't verify permissions if
an entry is missing from the permissions table, this meant that
executing a command via "batch" would bypass all permissions
checks.

The security implications are significant: a Mercurial HTTP server
would allow writes via "batch" wire protocol commands as long as
the HTTP request were processed by Mercurial and the process running
the Mercurial HTTP server had write access to the repository. The
Mercurial defaults of servers being read-only and the various web.*
config options to define access control were bypassed.

In addition, "batch" could be used to exfiltrate data from servers
that were configured to not allow read access.

Both forms of permissions bypass could be mitigated to some extent
by using HTTP authentication. This would prevent HTTP requests from
hitting Mercurial's server logic. However, any authenticated request
would still be able to bypass permissions checks via "batch" commands.

The easiest exploit was to send "pushkey" commands via "batch" and
modify the state of bookmarks, phases, and obsolescence markers.
However, I suspect a well-crafted HTTP request could trick the server
into running the "unbundle" wire protocol command, effectively
performing a full `hg push` to create new changesets on the remote.

This commit plugs this gaping security hole by having the "batch"
command perform permissions checking on each sub-command that is
being batched. We do this by threading a permissions checking
callable all the way to the protocol handler. The threading is a
bit hacky from a code perspective. But it preserves API compatibility,
which is the proper thing to do on the stable branch.

One of the subtle things we do is assume that a command with an
undefined permission is a "push" command. This is the safest thing to
do from a security perspective: we don't want to take chances that
a command could perform a write even though the server is configured
to not allow writes.

As the test changes demonstrate, it is no longer possible to bypass
permissions via the "batch" wire protocol command.

.. bc::

   The "batch" wire protocol command now enforces permissions of
   each invoked sub-command. Wire protocol commands must define
   their operation type or the "batch" command will assume they
   can write data and will prevent their execution on HTTP servers
   unless the HTTP request method is POST, the server is configured
   to allow pushes, and the (possibly authenticated) HTTP user is
   authorized to perform a push.

#
# Copyright 21 May 2005 - (c) 2005 Jake Edge <[e-mail]>
# Copyright 2005-2007 Matt Mackall <[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.

from __future__ import absolute_import

import cgi
import struct

from .common import (
    HTTP_OK,
)

from .. import (
    error,
    pycompat,
    util,
    wireproto,
)
stringio = util.stringio

urlerr = util.urlerr
urlreq = util.urlreq

HGTYPE = 'application/mercurial-0.1'
HGTYPE2 = 'application/mercurial-0.2'
HGERRTYPE = 'application/hg-error'

def decodevaluefromheaders(req, headerprefix):
    """Decode a long value from multiple HTTP request headers.

    Returns the value as a bytes, not a str.
    """
    chunks = []
    i = 1
    prefix = headerprefix.upper().replace(r'-', r'_')
    while True:
        v = req.env.get(r'HTTP_%s_%d' % (prefix, i))
        if v is None:
            break
        chunks.append(pycompat.bytesurl(v))
        i += 1

    return ''.join(chunks)

class webproto(wireproto.abstractserverproto):
    def __init__(self, req, ui):
        self.req = req
        self.response = ''
        self.ui = ui
        self.name = 'http'
        self.checkperm = req.checkperm

    def getargs(self, args):
        knownargs = self._args()
        data = {}
        keys = args.split()
        for k in keys:
            if k == '*':
                star = {}
                for key in knownargs.keys():
                    if key != 'cmd' and key not in keys:
                        star[key] = knownargs[key][0]
                data['*'] = star
            else:
                data[k] = knownargs[k][0]
        return [data[k] for k in keys]
    def _args(self):
        args = self.req.form.copy()
        if pycompat.ispy3:
            args = {k.encode('ascii'): [v.encode('ascii') for v in vs]
                    for k, vs in args.items()}
        postlen = int(self.req.env.get(r'HTTP_X_HGARGS_POST', 0))
        if postlen:
            args.update(cgi.parse_qs(
                self.req.read(postlen), keep_blank_values=True))
            return args

        argvalue = decodevaluefromheaders(self.req, r'X-HgArg')
        args.update(cgi.parse_qs(argvalue, keep_blank_values=True))
        return args
    def getfile(self, fp):
        length = int(self.req.env[r'CONTENT_LENGTH'])
        # If httppostargs is used, we need to read Content-Length
        # minus the amount that was consumed by args.
        length -= int(self.req.env.get(r'HTTP_X_HGARGS_POST', 0))
        for s in util.filechunkiter(self.req, limit=length):
            fp.write(s)
    def redirect(self):
        self.oldio = self.ui.fout, self.ui.ferr
        self.ui.ferr = self.ui.fout = stringio()
    def restore(self):
        val = self.ui.fout.getvalue()
        self.ui.ferr, self.ui.fout = self.oldio
        return val

    def _client(self):
        return 'remote:%s:%s:%s' % (
            self.req.env.get('wsgi.url_scheme') or 'http',
            urlreq.quote(self.req.env.get('REMOTE_HOST', '')),
            urlreq.quote(self.req.env.get('REMOTE_USER', '')))

    def responsetype(self, prefer_uncompressed):
        """Determine the appropriate response type and compression settings.

        Returns a tuple of (mediatype, compengine, engineopts).
        """
        # Determine the response media type and compression engine based
        # on the request parameters.
        protocaps = decodevaluefromheaders(self.req, r'X-HgProto').split(' ')

        if '0.2' in protocaps:
            # All clients are expected to support uncompressed data.
            if prefer_uncompressed:
                return HGTYPE2, util._noopengine(), {}

            # Default as defined by wire protocol spec.
            compformats = ['zlib', 'none']
            for cap in protocaps:
                if cap.startswith('comp='):
                    compformats = cap[5:].split(',')
                    break

            # Now find an agreed upon compression format.
            for engine in wireproto.supportedcompengines(self.ui, self,
                                                         util.SERVERROLE):
                if engine.wireprotosupport().name in compformats:
                    opts = {}
                    level = self.ui.configint('server',
                                              '%slevel' % engine.name())
                    if level is not None:
                        opts['level'] = level

                    return HGTYPE2, engine, opts

            # No mutually supported compression format. Fall back to the
            # legacy protocol.

        # Don't allow untrusted settings because disabling compression or
        # setting a very high compression level could lead to flooding
        # the server's network or CPU.
        opts = {'level': self.ui.configint('server', 'zliblevel')}
        return HGTYPE, util.compengines['zlib'], opts

def iscmd(cmd):
    return cmd in wireproto.commands

def call(repo, req, cmd):
    p = webproto(req, repo.ui)

    def genversion2(gen, engine, engineopts):
        # application/mercurial-0.2 always sends a payload header
        # identifying the compression engine.
        name = engine.wireprotosupport().name
        assert 0 < len(name) < 256
        yield struct.pack('B', len(name))
        yield name

        for chunk in gen:
            yield chunk

    rsp = wireproto.dispatch(repo, p, cmd)
    if isinstance(rsp, bytes):
        req.respond(HTTP_OK, HGTYPE, body=rsp)
        return []
    elif isinstance(rsp, wireproto.streamres_legacy):
        gen = rsp.gen
        req.respond(HTTP_OK, HGTYPE)
        return gen
    elif isinstance(rsp, wireproto.streamres):
        gen = rsp.gen

        # This code for compression should not be streamres specific. It
        # is here because we only compress streamres at the moment.
        mediatype, engine, engineopts = p.responsetype(rsp.prefer_uncompressed)
        gen = engine.compressstream(gen, engineopts)

        if mediatype == HGTYPE2:
            gen = genversion2(gen, engine, engineopts)

        req.respond(HTTP_OK, mediatype)
        return gen
    elif isinstance(rsp, wireproto.pushres):
        val = p.restore()
        rsp = '%d\n%s' % (rsp.res, val)
        req.respond(HTTP_OK, HGTYPE, body=rsp)
        return []
    elif isinstance(rsp, wireproto.pusherr):
        # drain the incoming bundle
        req.drain()
        p.restore()
        rsp = '0\n%s\n' % rsp.res
        req.respond(HTTP_OK, HGTYPE, body=rsp)
        return []
    elif isinstance(rsp, wireproto.ooberror):
        rsp = rsp.message
        req.respond(HTTP_OK, HGERRTYPE, body=rsp)
        return []
    raise error.ProgrammingError('hgweb.protocol internal failure', rsp)