Rearrange daemonization/syslog stuff and make it more resilient.

Rename --background to -D/--daemon, to match other programs (like smbd).

You can now have --syslog even without --daemon.

Avoid using atexit(); try/finally is better.

Don't just close stderr; we'll end up eating error output from ssh!
Instead, redirect stderr to a 'logger' subprocess that will send to syslog.

Delay redirecting stderr until after we know we're daemonizing, so handy
error messages can go to stderr instead of syslog.

Make pidfile stuff more resilient: support already-existing files, files
with strict permissions, outdated files containing an already-dead pid.  Add
a --pidfile option to let you specify the pidfile path.

chdir("/") while daemonizing, so that the filesystem containing $PWD can
later be unmounted without killing the daemon.

fw.done() can't wait on the firewall subprocess on exit when daemonized; we
no longer are the parent of that process.

5 files changed, 132 insertions, 62 deletions

diff --git a/client.py b/client.py
index 46f38b5..b9555f1 100644
--- a/client.py
+++ b/client.py
@@ -1,10 +1,97 @@
-import struct, socket, select, errno, re
+import struct, socket, select, errno, re, signal
 import compat.ssubprocess as ssubprocess
 import helpers, ssnet, ssh
 from ssnet import SockWrapper, Handler, Proxy, Mux, MuxWrapper
 from helpers import *
 
-import os, sys, atexit, signal, syslog
+
+_loggerp = None
+def start_syslog():
+    global _loggerp
+    _loggerp = ssubprocess.Popen(['logger',
+                                  '-p', 'daemon.info',
+                                  '-t', 'sshuttle'], stdin=ssubprocess.PIPE)
+
+
+def stderr_to_syslog():
+    sys.stdout.flush()
+    sys.stderr.flush()
+    os.dup2(_loggerp.stdin.fileno(), 1)
+    os.dup2(_loggerp.stdin.fileno(), 2)
+
+
+def got_signal(signum, frame):
+    log('exiting on signal %d\n' % signum)
+    sys.exit(1)
+
+
+_pidname = None
+def check_daemon(pidfile):
+    global _pidname
+    _pidname = os.path.abspath(pidfile)
+    try:
+        oldpid = open(_pidname).read(1024)
+    except IOError, e:
+        if e.errno == errno.ENOENT:
+            return  # no pidfile, ok
+        else:
+            raise Fatal("can't read %s: %s" % (_pidname, e))
+    if not oldpid:
+        os.unlink(_pidname)
+        return  # invalid pidfile, ok
+    oldpid = int(oldpid.strip() or 0)
+    if oldpid <= 0:
+        os.unlink(_pidname)
+        return  # invalid pidfile, ok
+    try:
+        os.kill(oldpid, 0)
+    except OSError, e:
+        if e.errno == errno.ESRCH:
+            os.unlink(_pidname)
+            return  # outdated pidfile, ok
+        elif e.errno == errno.EPERM:
+            pass
+        else:
+            raise
+    raise Fatal("%s: sshuttle is already running (pid=%d)"
+                % (_pidname, oldpid))
+
+
+def daemonize():
+    if os.fork():
+        os._exit(0)
+    os.setsid()
+    if os.fork():
+        os._exit(0)
+
+    outfd = os.open(_pidname, os.O_WRONLY|os.O_CREAT|os.O_EXCL, 0666)
+    try:
+        os.write(outfd, '%d\n' % os.getpid())
+    finally:
+        os.close(outfd)
+    os.chdir("/")
+
+    # Normal exit when killed, or try/finally won't work and the pidfile won't
+    # be deleted.
+    signal.signal(signal.SIGTERM, got_signal)
+    
+    si = open('/dev/null', 'r+')
+    os.dup2(si.fileno(), 0)
+    si.close()
+
+    stderr_to_syslog()
+    log('daemonizing (%s).\n' % _pidname)
+
+
+def daemon_cleanup():
+    try:
+        os.unlink(_pidname)
+    except OSError, e:
+        if e.errno == errno.ENOENT:
+            pass
+        else:
+            raise
+
 
 def original_dst(sock):
     try:
@@ -98,11 +185,9 @@ class FirewallClient:
         if rv:
             raise Fatal('cleanup: %r returned %d' % (self.argv, rv))
 
-def exit_cleanup():
-    debug1('exit cleanup\n')
-    os.unlink('sshuttle.pid')
 
-def _main(listener, fw, ssh_cmd, remotename, python, seed_hosts, auto_nets, background):
+def _main(listener, fw, ssh_cmd, remotename, python, seed_hosts, auto_nets,
+          syslog, daemon):
     handlers = []
     if helpers.verbose >= 1:
         helpers.logprefix = 'c : '
@@ -110,30 +195,9 @@ def _main(listener, fw, ssh_cmd, remotename, python, seed_hosts, auto_nets, back
         helpers.logprefix = 'client: '
     debug1('connecting to server...\n')
 
-    if background:
-        helpers.do_syslog = True
-        syslog.openlog('sshuttle')
-
-        # we're redirecting the standard outputs here early so that
-        # the stderr debug message of ssh subprocess would be
-        # redirected properly 
-
-        # TODO: redirecting stderr of ssh to syslog
-
-        sys.stdout.flush()
-        sys.stderr.flush()
-        si = file('/dev/null', 'r')
-        so = file('/dev/null', 'a+')
-        se = file('/dev/null', 'a+', 0)
-        os.dup2(si.fileno(), sys.stdin.fileno())
-        os.dup2(so.fileno(), sys.stdout.fileno())
-        os.dup2(se.fileno(), sys.stderr.fileno())
-        si.close()
-        so.close()
-        se.close()
-
     try:
-        (serverproc, serversock) = ssh.connect(ssh_cmd, remotename, python)
+        (serverproc, serversock) = ssh.connect(ssh_cmd, remotename, python,
+                                               stderr=_loggerp.stdin)
     except socket.error, e:
         if e.errno == errno.EPIPE:
             raise Fatal("failed to establish ssh session")
@@ -153,22 +217,10 @@ def _main(listener, fw, ssh_cmd, remotename, python, seed_hosts, auto_nets, back
         raise Fatal('expected server init string %r; got %r'
                         % (expected, initstring))
     debug1('connected.\n')
-    if background:
-        debug1('daemonizing\n')
-        if os.fork(): 
-            os._exit(0)
-        os.setsid() 
-        if os.fork(): 
-            os._exit(0)
-
-        outfd = os.open('sshuttle.pid', 
-                        os.O_WRONLY | os.O_CREAT | os.O_EXCL)
-        os.write(outfd, '%i' % os.getpid())
-        os.close(outfd)
-
-        atexit.register(exit_cleanup)
-        # Normal exit when killed, or atexit won't work
-        signal.signal(signal.SIGTERM, lambda signum, stack_frame: sys.exit(1))
+    if daemon:
+        daemonize()
+    elif syslog:
+        stderr_to_syslog()
 
     def onroutes(routestr):
         if auto_nets:
@@ -225,7 +277,15 @@ def _main(listener, fw, ssh_cmd, remotename, python, seed_hosts, auto_nets, back
 
 
 def main(listenip, ssh_cmd, remotename, python, seed_hosts, auto_nets,
-         subnets_include, subnets_exclude, background):
+         subnets_include, subnets_exclude, syslog, daemon, pidfile):
+    if syslog:
+        start_syslog()
+    if daemon:
+        try:
+            check_daemon(pidfile)
+        except Fatal, e:
+            log("%s\n" % e)
+            return 5
     debug1('Starting sshuttle proxy.\n')
     listener = socket.socket()
     listener.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
@@ -256,6 +316,13 @@ def main(listenip, ssh_cmd, remotename, python, seed_hosts, auto_nets,
     
     try:
         return _main(listener, fw, ssh_cmd, remotename,
-                     python, seed_hosts, auto_nets, background)
+                     python, seed_hosts, auto_nets, syslog, daemon)
     finally:
-        fw.done()
+        try:
+            if daemon:
+                # it's not our child anymore; can't waitpid
+                fw.p.returncode = 0
+            fw.done()
+        finally:
+            if daemon:
+                daemon_cleanup()
diff --git a/helpers.py b/helpers.py
index a5b152b..18871a2 100644
--- a/helpers.py
+++ b/helpers.py
@@ -1,17 +1,13 @@
-import sys, os, syslog
+import sys, os
 
 logprefix = ''
 verbose = 0
-do_syslog = False
 
 def log(s):
     try:
-        if do_syslog:
-            syslog.syslog(logprefix + s)
-        else:
-            sys.stdout.flush()
-            sys.stderr.write(logprefix + s)
-            sys.stderr.flush()
+        sys.stdout.flush()
+        sys.stderr.write(logprefix + s)
+        sys.stderr.flush()
     except IOError:
         # this could happen if stderr gets forcibly disconnected, eg. because
         # our tty closes.  That sucks, but it's no reason to abort the program.
diff --git a/main.py b/main.py
index 7a7a6a4..1c96340 100755
--- a/main.py
+++ b/main.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 import sys, os, re
 import helpers, options, client, server, firewall, hostwatch
+import compat.ssubprocess as ssubprocess
 from helpers import *
 
 
@@ -45,11 +46,11 @@ def parse_ipport(s):
 
 
 optspec = """
-sshuttle [-b] [-l [ip:]port] [-r [username@]sshserver[:port]] <subnets...>
-sshuttle --firewall <port> <subnets...>
+sshuttle [-l [ip:]port] [-r [username@]sshserver[:port]] <subnets...>
 sshuttle --server
+sshuttle --firewall <port> <subnets...>
+sshuttle --hostwatch
 --
-b,background run in background as daemon
 l,listen=  transproxy to this ip address and port number [0.0.0.0:0]
 H,auto-hosts scan for remote hostnames and update local /etc/hosts
 N,auto-nets  automatically determine subnets to route
@@ -59,6 +60,9 @@ x,exclude= exclude this subnet (can be used more than once)
 v,verbose  increase debug message verbosity
 e,ssh-cmd= the command to use to connect to the remote [ssh]
 seed-hosts= with -H, use these hostnames for initial scan (comma-separated)
+D,daemon   run in the background as a daemon
+syslog     send log messages to syslog (default if you use --daemon)
+pidfile=   pidfile name (only if using --daemon) [./sshuttle.pid]
 server     (internal use only)
 firewall   (internal use only)
 hostwatch  (internal use only)
@@ -66,6 +70,8 @@ hostwatch  (internal use only)
 o = options.Options('sshuttle', optspec)
 (opt, flags, extra) = o.parse(sys.argv[1:])
 
+if opt.daemon:
+    opt.syslog = 1
 helpers.verbose = opt.verbose
 
 try:
@@ -106,7 +112,7 @@ try:
                              opt.auto_nets,
                              parse_subnets(includes),
                              parse_subnets(excludes),
-                             opt.background))
+                             opt.syslog, opt.daemon, opt.pidfile))
 except Fatal, e:
     log('fatal: %s\n' % e)
     sys.exit(99)
diff --git a/server.py b/server.py
index 08af657..24dd462 100644
--- a/server.py
+++ b/server.py
@@ -166,6 +166,7 @@ def main():
 
     while mux.ok:
         if hw.pid:
+            assert(hw.pid > 0)
             (rpid, rv) = os.waitpid(hw.pid, os.WNOHANG)
             if rpid:
                 raise Fatal('hostwatch exited unexpectedly: code 0x%04x\n' % rv)
diff --git a/ssh.py b/ssh.py
index dd9e042..ac7f411 100644
--- a/ssh.py
+++ b/ssh.py
@@ -21,7 +21,7 @@ def empackage(z, filename):
     return '%s\n%d\n%s' % (basename,len(content), content)
 
 
-def connect(ssh_cmd, rhostport, python):
+def connect(ssh_cmd, rhostport, python, stderr):
     main_exe = sys.argv[0]
     portl = []
 
@@ -87,7 +87,7 @@ def connect(ssh_cmd, rhostport, python):
     s1.close()
     debug2('executing: %r\n' % argv)
     p = ssubprocess.Popen(argv, stdin=s1a, stdout=s1b, preexec_fn=setup,
-                         close_fds=True)
+                          close_fds=True, stderr=stderr)
     os.close(s1a)
     os.close(s1b)
     s2.sendall(content)