sshpeer: establish SSH connection before class instantiation

We want to move the handshake to before peers are created so
we can instantiate a different peer class depending on the
results of the handshake. This necessitates moving the SSH
process invocation to outside the peer class.

As part of the code move, some variables were renamed for
clarity. util.popen4() returns stdin, stdout, and stderr in
their typical file descriptor order. However, stdin and stdout
were being mapped to "pipeo" and "pipei" respectively. "o"
for "stdin" and "i" for "stdout" is a bit confusing. Although
it does make sense for "output" and "input" from the perspective
of the client. But in the context of the new function, it makes
sense to refer to these as their file descriptor names.

In addition, the last use of self._path disappeared, so we stop
setting that attribute and we can delete the redundant URL
parsing necessary to set it.

Differential Revision: https://phab.mercurial-scm.org/D2031

mercurial/sshpeer.py

@@ -1,385 +1,391 b''
 # sshpeer.py - ssh repository proxy class for mercurial
 #
 # Copyright 2005, 2006 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 re
 
 from .i18n import _
 from . import (
     error,
     pycompat,
     util,
     wireproto,
 )
 
 def _serverquote(s):
     """quote a string for the remote shell ... which we assume is sh"""
     if not s:
         return s
     if re.match('[a-zA-Z0-9@%_+=:,./-]*$', s):
         return s
     return "'%s'" % s.replace("'", "'\\''")
 
 def _forwardoutput(ui, pipe):
     """display all data currently available on pipe as remote output.
 
     This is non blocking."""
     s = util.readpipe(pipe)
     if s:
         for l in s.splitlines():
             ui.status(_("remote: "), l, '\n')
 
 class doublepipe(object):
     """Operate a side-channel pipe in addition of a main one
 
     The side-channel pipe contains server output to be forwarded to the user
     input. The double pipe will behave as the "main" pipe, but will ensure the
     content of the "side" pipe is properly processed while we wait for blocking
     call on the "main" pipe.
 
     If large amounts of data are read from "main", the forward will cease after
     the first bytes start to appear. This simplifies the implementation
     without affecting actual output of sshpeer too much as we rarely issue
     large read for data not yet emitted by the server.
 
     The main pipe is expected to be a 'bufferedinputpipe' from the util module
     that handle all the os specific bits. This class lives in this module
     because it focus on behavior specific to the ssh protocol."""
 
     def __init__(self, ui, main, side):
         self._ui = ui
         self._main = main
         self._side = side
 
     def _wait(self):
         """wait until some data are available on main or side
 
         return a pair of boolean (ismainready, issideready)
 
         (This will only wait for data if the setup is supported by `util.poll`)
         """
         if getattr(self._main, 'hasbuffer', False): # getattr for classic pipe
             return (True, True) # main has data, assume side is worth poking at.
         fds = [self._main.fileno(), self._side.fileno()]
         try:
             act = util.poll(fds)
         except NotImplementedError:
             # non supported yet case, assume all have data.
             act = fds
         return (self._main.fileno() in act, self._side.fileno() in act)
 
     def write(self, data):
         return self._call('write', data)
 
     def read(self, size):
         r = self._call('read', size)
         if size != 0 and not r:
             # We've observed a condition that indicates the
             # stdout closed unexpectedly. Check stderr one
             # more time and snag anything that's there before
             # letting anyone know the main part of the pipe
             # closed prematurely.
             _forwardoutput(self._ui, self._side)
         return r
 
     def readline(self):
         return self._call('readline')
 
     def _call(self, methname, data=None):
         """call <methname> on "main", forward output of "side" while blocking
         """
         # data can be '' or 0
         if (data is not None and not data) or self._main.closed:
             _forwardoutput(self._ui, self._side)
             return ''
         while True:
             mainready, sideready = self._wait()
             if sideready:
                 _forwardoutput(self._ui, self._side)
             if mainready:
                 meth = getattr(self._main, methname)
                 if data is None:
                     return meth()
                 else:
                     return meth(data)
 
     def close(self):
         return self._main.close()
 
     def flush(self):
         return self._main.flush()
 
 def _cleanuppipes(ui, pipei, pipeo, pipee):
     """Clean up pipes used by an SSH connection."""
     if pipeo:
         pipeo.close()
     if pipei:
         pipei.close()
 
     if pipee:
         # Try to read from the err descriptor until EOF.
         try:
             for l in pipee:
                 ui.status(_('remote: '), l)
         except (IOError, ValueError):
             pass
 
         pipee.close()
 
+def _makeconnection(ui, sshcmd, args, remotecmd, path, sshenv=None):
+    """Create an SSH connection to a server.
+
+    Returns a tuple of (process, stdin, stdout, stderr) for the
+    spawned process.
+    """
+    cmd = '%s %s %s' % (
+        sshcmd,
+        args,
+        util.shellquote('%s -R %s serve --stdio' % (
+            _serverquote(remotecmd), _serverquote(path))))
+
+    ui.debug('running %s\n' % cmd)
+    cmd = util.quotecommand(cmd)
+
+    # no buffer allow the use of 'select'
+    # feel free to remove buffering and select usage when we ultimately
+    # move to threading.
+    stdin, stdout, stderr, proc = util.popen4(cmd, bufsize=0, env=sshenv)
+
+    stdout = doublepipe(ui, util.bufferedinputpipe(stdout), stderr)
+    stdin = doublepipe(ui, stdin, stderr)
+
+    return proc, stdin, stdout, stderr
+
 class sshpeer(wireproto.wirepeer):
     def __init__(self, ui, path, create=False, sshstate=None):
         self._url = path
         self._ui = ui
-        self._pipeo = self._pipei = self._pipee = None
+        # self._subprocess is unused. Keeping a handle on the process
+        # holds a reference and prevents it from being garbage collected.
+        self._subprocess, self._pipei, self._pipeo, self._pipee = sshstate
 
-        u = util.url(path, parsequery=False, parsefragment=False)
-        self._path = u.path or '.'
-
-        self._validaterepo(*sshstate)
+        self._validaterepo()
 
     # Begin of _basepeer interface.
 
     @util.propertycache
     def ui(self):
         return self._ui
 
     def url(self):
         return self._url
 
     def local(self):
         return None
 
     def peer(self):
         return self
 
     def canpush(self):
         return True
 
     def close(self):
         pass
 
     # End of _basepeer interface.
 
     # Begin of _basewirecommands interface.
 
     def capabilities(self):
         return self._caps
 
     # End of _basewirecommands interface.
 
-    def _validaterepo(self, sshcmd, args, remotecmd, sshenv=None):
-        assert self._pipei is None
-
-        cmd = '%s %s %s' % (sshcmd, args,
-            util.shellquote("%s -R %s serve --stdio" %
-                (_serverquote(remotecmd), _serverquote(self._path))))
-        self.ui.debug('running %s\n' % cmd)
-        cmd = util.quotecommand(cmd)
-
-        # while self._subprocess isn't used, having it allows the subprocess to
-        # to clean up correctly later
-        #
-        # no buffer allow the use of 'select'
-        # feel free to remove buffering and select usage when we ultimately
-        # move to threading.
-        sub = util.popen4(cmd, bufsize=0, env=sshenv)
-        self._pipeo, self._pipei, self._pipee, self._subprocess = sub
-
-        self._pipei = util.bufferedinputpipe(self._pipei)
-        self._pipei = doublepipe(self.ui, self._pipei, self._pipee)
-        self._pipeo = doublepipe(self.ui, self._pipeo, self._pipee)
-
+    def _validaterepo(self):
         def badresponse():
             msg = _("no suitable response from remote hg")
             hint = self.ui.config("ui", "ssherrorhint")
             self._abort(error.RepoError(msg, hint=hint))
 
         try:
             # skip any noise generated by remote shell
             self._callstream("hello")
             r = self._callstream("between", pairs=("%s-%s" % ("0"*40, "0"*40)))
         except IOError:
             badresponse()
 
         lines = ["", "dummy"]
         max_noise = 500
         while lines[-1] and max_noise:
             try:
                 l = r.readline()
                 self._readerr()
                 if lines[-1] == "1\n" and l == "\n":
                     break
                 if l:
                     self.ui.debug("remote: ", l)
                 lines.append(l)
                 max_noise -= 1
             except IOError:
                 badresponse()
         else:
             badresponse()
 
         self._caps = set()
         for l in reversed(lines):
             if l.startswith("capabilities:"):
                 self._caps.update(l[:-1].split(":")[1].split())
                 break
 
     def _readerr(self):
         _forwardoutput(self.ui, self._pipee)
 
     def _abort(self, exception):
         self._cleanup()
         raise exception
 
     def _cleanup(self):
         _cleanuppipes(self.ui, self._pipei, self._pipeo, self._pipee)
 
     __del__ = _cleanup
 
     def _submitbatch(self, req):
         rsp = self._callstream("batch", cmds=wireproto.encodebatchcmds(req))
         available = self._getamount()
         # TODO this response parsing is probably suboptimal for large
         # batches with large responses.
         toread = min(available, 1024)
         work = rsp.read(toread)
         available -= toread
         chunk = work
         while chunk:
             while ';' in work:
                 one, work = work.split(';', 1)
                 yield wireproto.unescapearg(one)
             toread = min(available, 1024)
             chunk = rsp.read(toread)
             available -= toread
             work += chunk
         yield wireproto.unescapearg(work)
 
     def _callstream(self, cmd, **args):
         args = pycompat.byteskwargs(args)
         if (self.ui.debugflag
             and self.ui.configbool('devel', 'debug.peer-request')):
             dbg = self.ui.debug
             line = 'devel-peer-request: %s\n'
             dbg(line % cmd)
             for key, value in sorted(args.items()):
                 if not isinstance(value, dict):
                     dbg(line % '  %s: %d bytes' % (key, len(value)))
                 else:
                     for dk, dv in sorted(value.items()):
                         dbg(line % '  %s-%s: %d' % (key, dk, len(dv)))
         self.ui.debug("sending %s command\n" % cmd)
         self._pipeo.write("%s\n" % cmd)
         _func, names = wireproto.commands[cmd]
         keys = names.split()
         wireargs = {}
         for k in keys:
             if k == '*':
                 wireargs['*'] = args
                 break
             else:
                 wireargs[k] = args[k]
                 del args[k]
         for k, v in sorted(wireargs.iteritems()):
             self._pipeo.write("%s %d\n" % (k, len(v)))
             if isinstance(v, dict):
                 for dk, dv in v.iteritems():
                     self._pipeo.write("%s %d\n" % (dk, len(dv)))
                     self._pipeo.write(dv)
             else:
                 self._pipeo.write(v)
         self._pipeo.flush()
 
         return self._pipei
 
     def _callcompressable(self, cmd, **args):
         return self._callstream(cmd, **args)
 
     def _call(self, cmd, **args):
         self._callstream(cmd, **args)
         return self._recv()
 
     def _callpush(self, cmd, fp, **args):
         r = self._call(cmd, **args)
         if r:
             return '', r
         for d in iter(lambda: fp.read(4096), ''):
             self._send(d)
         self._send("", flush=True)
         r = self._recv()
         if r:
             return '', r
         return self._recv(), ''
 
     def _calltwowaystream(self, cmd, fp, **args):
         r = self._call(cmd, **args)
         if r:
             # XXX needs to be made better
             raise error.Abort(_('unexpected remote reply: %s') % r)
         for d in iter(lambda: fp.read(4096), ''):
             self._send(d)
         self._send("", flush=True)
         return self._pipei
 
     def _getamount(self):
         l = self._pipei.readline()
         if l == '\n':
             self._readerr()
             msg = _('check previous remote output')
             self._abort(error.OutOfBandError(hint=msg))
         self._readerr()
         try:
             return int(l)
         except ValueError:
             self._abort(error.ResponseError(_("unexpected response:"), l))
 
     def _recv(self):
         return self._pipei.read(self._getamount())
 
     def _send(self, data, flush=False):
         self._pipeo.write("%d\n" % len(data))
         if data:
             self._pipeo.write(data)
         if flush:
             self._pipeo.flush()
         self._readerr()
 
 def instance(ui, path, create):
     """Create an SSH peer.
 
     The returned object conforms to the ``wireproto.wirepeer`` interface.
     """
     u = util.url(path, parsequery=False, parsefragment=False)
     if u.scheme != 'ssh' or not u.host or u.path is None:
         raise error.RepoError(_("couldn't parse location %s") % path)
 
     util.checksafessh(path)
 
     if u.passwd is not None:
         raise error.RepoError(_('password in URL not supported'))
 
     sshcmd = ui.config('ui', 'ssh')
     remotecmd = ui.config('ui', 'remotecmd')
     sshaddenv = dict(ui.configitems('sshenv'))
     sshenv = util.shellenviron(sshaddenv)
     remotepath = u.path or '.'
 
     args = util.sshargs(sshcmd, u.host, u.user, u.port)
 
     if create:
         cmd = '%s %s %s' % (sshcmd, args,
             util.shellquote('%s init %s' %
                 (_serverquote(remotecmd), _serverquote(remotepath))))
         ui.debug('running %s\n' % cmd)
         res = ui.system(cmd, blockedtag='sshpeer', environ=sshenv)
         if res != 0:
             raise error.RepoError(_('could not create remote repo'))
 
-    sshstate = (sshcmd, args, remotecmd, sshenv)
+    proc, stdin, stdout, stderr = _makeconnection(ui, sshcmd, args, remotecmd,
+                                                  remotepath, sshenv)
+
+    sshstate = (proc, stdout, stdin, stderr)
 
     return sshpeer(ui, path, create=create, sshstate=sshstate)

tests/test-check-interfaces.py

@@ -1,77 +1,78 b''
 # Test that certain objects conform to well-defined interfaces.
 
 from __future__ import absolute_import, print_function
 
 from mercurial import (
     bundlerepo,
     httppeer,
     localrepo,
     sshpeer,
     statichttprepo,
     ui as uimod,
     unionrepo,
 )
 
 def checkobject(o):
     """Verify a constructed object conforms to interface rules.
 
     An object must have __abstractmethods__ defined.
 
     All "public" attributes of the object (attributes not prefixed with
     an underscore) must be in __abstractmethods__ or appear on a base class
     with __abstractmethods__.
     """
     name = o.__class__.__name__
 
     allowed = set()
     for cls in o.__class__.__mro__:
         if not getattr(cls, '__abstractmethods__', set()):
             continue
 
         allowed |= cls.__abstractmethods__
         allowed |= {a for a in dir(cls) if not a.startswith('_')}
 
     if not allowed:
         print('%s does not have abstract methods' % name)
         return
 
     public = {a for a in dir(o) if not a.startswith('_')}
 
     for attr in sorted(public - allowed):
         print('public attributes not in abstract interface: %s.%s' % (
             name, attr))
 
 # Facilitates testing localpeer.
 class dummyrepo(object):
     def __init__(self):
         self.ui = uimod.ui()
     def filtered(self, name):
         pass
     def _restrictcapabilities(self, caps):
         pass
 
 # Facilitates testing sshpeer without requiring an SSH server.
 class testingsshpeer(sshpeer.sshpeer):
     def _validaterepo(self, *args, **kwargs):
         pass
 
 class badpeer(httppeer.httppeer):
     def __init__(self):
         super(badpeer, self).__init__(uimod.ui(), 'http://localhost')
         self.badattribute = True
 
     def badmethod(self):
         pass
 
 def main():
     ui = uimod.ui()
 
     checkobject(badpeer())
     checkobject(httppeer.httppeer(ui, 'http://localhost'))
     checkobject(localrepo.localpeer(dummyrepo()))
-    checkobject(testingsshpeer(ui, 'ssh://localhost/foo', False, ()))
+    checkobject(testingsshpeer(ui, 'ssh://localhost/foo', False,
+                               (None, None, None, None)))
     checkobject(bundlerepo.bundlepeer(dummyrepo()))
     checkobject(statichttprepo.statichttppeer(dummyrepo()))
     checkobject(unionrepo.unionpeer(dummyrepo()))
 
 main()