File: lxc_controller.c

package info (click to toggle)
libvirt 0.8.3-5+squeeze5
  • links: PTS, VCS
  • area: main
  • in suites: squeeze
  • size: 77,288 kB
  • ctags: 30,516
  • sloc: ansic: 177,367; xml: 26,161; sh: 13,271; python: 4,929; makefile: 2,083; ml: 472; perl: 221; awk: 48; sed: 16
file content (845 lines) | stat: -rw-r--r-- 24,921 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
/*
 * Copyright IBM Corp. 2008
 *
 * lxc_controller.c: linux container process controller
 *
 * Authors:
 *  David L. Leskovec <dlesko at linux.vnet.ibm.com>
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2.1 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 */

#include <config.h>

#include <sys/epoll.h>
#include <sys/wait.h>
#include <sys/socket.h>
#include <sys/types.h>
#include <sys/un.h>
#include <unistd.h>
#include <paths.h>
#include <fcntl.h>
#include <signal.h>
#include <getopt.h>
#include <sys/mount.h>

#if HAVE_CAPNG
# include <cap-ng.h>
#endif

#include "virterror_internal.h"
#include "logging.h"
#include "util.h"

#include "lxc_conf.h"
#include "lxc_container.h"
#include "veth.h"
#include "memory.h"
#include "util.h"

#define VIR_FROM_THIS VIR_FROM_LXC

struct cgroup_device_policy {
    char type;
    int major;
    int minor;
};

/**
 * lxcSetContainerResources
 * @def: pointer to virtual machine structure
 *
 * Creates a cgroup for the container, moves the task inside,
 * and sets resource limits
 *
 * Returns 0 on success or -1 in case of error
 */
static int lxcSetContainerResources(virDomainDefPtr def)
{
    virCgroupPtr driver;
    virCgroupPtr cgroup;
    int rc = -1;
    int i;
    struct cgroup_device_policy devices[] = {
        {'c', LXC_DEV_MAJ_MEMORY, LXC_DEV_MIN_NULL},
        {'c', LXC_DEV_MAJ_MEMORY, LXC_DEV_MIN_ZERO},
        {'c', LXC_DEV_MAJ_MEMORY, LXC_DEV_MIN_FULL},
        {'c', LXC_DEV_MAJ_MEMORY, LXC_DEV_MIN_RANDOM},
        {'c', LXC_DEV_MAJ_MEMORY, LXC_DEV_MIN_URANDOM},
        {'c', LXC_DEV_MAJ_TTY, LXC_DEV_MIN_TTY},
        {'c', LXC_DEV_MAJ_TTY, LXC_DEV_MIN_CONSOLE},
        {'c', LXC_DEV_MAJ_TTY, LXC_DEV_MIN_PTMX},
        {0,   0, 0}};

    rc = virCgroupForDriver("lxc", &driver, 1, 0);
    if (rc != 0) {
        /* Skip all if no driver cgroup is configured */
        if (rc == -ENXIO || rc == -ENOENT)
            return 0;

        virReportSystemError(-rc, "%s",
                             _("Unable to get cgroup for driver"));
        return rc;
    }

    rc = virCgroupForDomain(driver, def->name, &cgroup, 1);
    if (rc != 0) {
        virReportSystemError(-rc,
                             _("Unable to create cgroup for domain %s"),
                             def->name);
        goto cleanup;
    }

    rc = virCgroupSetMemory(cgroup, def->maxmem);
    if (rc != 0) {
        virReportSystemError(-rc,
                             _("Unable to set memory limit for domain %s"),
                             def->name);
        /* Don't fail if we can't set memory due to lack of kernel support */
        if (rc != -ENOENT)
            goto cleanup;
    }

    rc = virCgroupDenyAllDevices(cgroup);
    if (rc != 0) {
        virReportSystemError(-rc,
                             _("Unable to deny devices for domain %s"),
                             def->name);
        goto cleanup;
    }

    for (i = 0; devices[i].type != 0; i++) {
        struct cgroup_device_policy *dev = &devices[i];
        rc = virCgroupAllowDevice(cgroup,
                                  dev->type,
                                  dev->major,
                                  dev->minor);
        if (rc != 0) {
            virReportSystemError(-rc,
                                 _("Unable to allow device %c:%d:%d for domain %s"),
                                 dev->type, dev->major, dev->minor, def->name);
            goto cleanup;
        }
    }

    rc = virCgroupAllowDeviceMajor(cgroup, 'c', LXC_DEV_MAJ_PTY);
    if (rc != 0) {
        virReportSystemError(-rc,
                             _("Unable to allow PYT devices for domain %s"),
                             def->name);
        goto cleanup;
    }

    rc = virCgroupAddTask(cgroup, getpid());
    if (rc != 0) {
        virReportSystemError(-rc,
                             _("Unable to add task %d to cgroup for domain %s"),
                             getpid(), def->name);
    }

cleanup:
    virCgroupFree(&driver);
    virCgroupFree(&cgroup);

    return rc;
}

static char*lxcMonitorPath(virDomainDefPtr def)
{
    char *sockpath;

    if (virAsprintf(&sockpath, "%s/%s.sock",
                    LXC_STATE_DIR, def->name) < 0)
        virReportOOMError();
    return sockpath;
}

static int lxcMonitorServer(const char *sockpath)
{
    int fd;
    struct sockaddr_un addr;

    if ((fd = socket(PF_UNIX, SOCK_STREAM, 0)) < 0) {
        virReportSystemError(errno,
                             _("failed to create server socket '%s'"),
                             sockpath);
        goto error;
    }

    unlink(sockpath);
    memset(&addr, 0, sizeof(addr));
    addr.sun_family = AF_UNIX;
    if (virStrcpyStatic(addr.sun_path, sockpath) == NULL) {
        lxcError(VIR_ERR_INTERNAL_ERROR,
                 _("Socket path %s too long for destination"), sockpath);
        goto error;
    }

    if (bind(fd, (struct sockaddr *) &addr, sizeof(addr)) < 0) {
        virReportSystemError(errno,
                             _("failed to bind server socket '%s'"),
                             sockpath);
        goto error;
    }
    if (listen(fd, 30 /* backlog */ ) < 0) {
        virReportSystemError(errno,
                             _("failed to listen server socket %s"),
                             sockpath);
        goto error;
    }

    return fd;

error:
    if (fd != -1)
        close(fd);
    return -1;
}

/**
 * lxcFdForward:
 * @readFd: file descriptor to read
 * @writeFd: file desriptor to write
 *
 * Reads 1 byte of data from readFd and writes to writeFd.
 *
 * Returns 0 on success, EAGAIN if returned on read, or -1 in case of error
 */
static int lxcFdForward(int readFd, int writeFd)
{
    int rc = -1;
    char buf[2];

    if (1 != (saferead(readFd, buf, 1))) {
        if (EAGAIN == errno) {
            rc = EAGAIN;
            goto cleanup;
        }

        virReportSystemError(errno,
                             _("read of fd %d failed"),
                             readFd);
        goto cleanup;
    }

    if (1 != (safewrite(writeFd, buf, 1))) {
        virReportSystemError(errno,
                             _("write to fd %d failed"),
                             writeFd);
        goto cleanup;
    }

    rc = 0;

cleanup:
    return rc;
}


static int lxcControllerClearCapabilities(void)
{
#if HAVE_CAPNG
    int ret;

    capng_clear(CAPNG_SELECT_BOTH);

    if ((ret = capng_apply(CAPNG_SELECT_BOTH)) < 0) {
        lxcError(VIR_ERR_INTERNAL_ERROR,
                 _("failed to apply capabilities: %d"), ret);
        return -1;
    }
#else
    VIR_WARN0("libcap-ng support not compiled in, unable to clear capabilities");
#endif
    return 0;
}

typedef struct _lxcTtyForwardFd_t {
    int fd;
    int active;
} lxcTtyForwardFd_t;

/* Return true if it is ok to ignore an accept-after-epoll syscall
   that fails with the specified errno value.  Else false.  */
static bool
ignorable_epoll_accept_errno(int errnum)
{
  return (errnum == EINVAL
          || errnum == ECONNABORTED
          || errnum == EAGAIN
          || errnum == EWOULDBLOCK);
}

/**
 * lxcControllerMain
 * @monitor: server socket fd to accept client requests
 * @client: initial client which is the libvirtd daemon
 * @appPty: open fd for application facing Pty
 * @contPty: open fd for container facing Pty
 *
 * Forwards traffic between fds.  Data read from appPty will be written to contPty
 * This process loops forever.
 * This uses epoll in edge triggered mode to avoid a hard loop on POLLHUP
 * events when the user disconnects the virsh console via ctrl-]
 *
 * Returns 0 on success or -1 in case of error
 */
static int lxcControllerMain(int monitor,
                             int client,
                             int appPty,
                             int contPty)
{
    int rc = -1;
    int epollFd;
    struct epoll_event epollEvent;
    int numEvents;
    int numActive = 0;
    lxcTtyForwardFd_t fdArray[2];
    int timeout = -1;
    int curFdOff = 0;
    int writeFdOff = 0;

    fdArray[0].fd = appPty;
    fdArray[0].active = 0;
    fdArray[1].fd = contPty;
    fdArray[1].active = 0;

    VIR_DEBUG("monitor=%d client=%d appPty=%d contPty=%d",
              monitor, client, appPty, contPty);

    /* create the epoll fild descriptor */
    epollFd = epoll_create(2);
    if (0 > epollFd) {
        virReportSystemError(errno, "%s",
                             _("epoll_create(2) failed"));
        goto cleanup;
    }

    /* add the file descriptors the epoll fd */
    memset(&epollEvent, 0x00, sizeof(epollEvent));
    epollEvent.events = EPOLLIN|EPOLLET;    /* edge triggered */
    epollEvent.data.fd = appPty;
    if (0 > epoll_ctl(epollFd, EPOLL_CTL_ADD, appPty, &epollEvent)) {
        virReportSystemError(errno, "%s",
                             _("epoll_ctl(appPty) failed"));
        goto cleanup;
    }
    epollEvent.data.fd = contPty;
    if (0 > epoll_ctl(epollFd, EPOLL_CTL_ADD, contPty, &epollEvent)) {
        virReportSystemError(errno, "%s",
                             _("epoll_ctl(contPty) failed"));
        goto cleanup;
    }

    epollEvent.events = EPOLLIN;
    epollEvent.data.fd = monitor;
    if (0 > epoll_ctl(epollFd, EPOLL_CTL_ADD, monitor, &epollEvent)) {
        virReportSystemError(errno, "%s",
                             _("epoll_ctl(monitor) failed"));
        goto cleanup;
    }

    epollEvent.events = EPOLLHUP;
    epollEvent.data.fd = client;
    if (0 > epoll_ctl(epollFd, EPOLL_CTL_ADD, client, &epollEvent)) {
        virReportSystemError(errno, "%s",
                             _("epoll_ctl(client) failed"));
        goto cleanup;
    }

    while (1) {
        /* if active fd's, return if no events, else wait forever */
        timeout = (numActive > 0) ? 0 : -1;
        numEvents = epoll_wait(epollFd, &epollEvent, 1, timeout);
        if (numEvents > 0) {
            if (epollEvent.data.fd == monitor) {
                int fd = accept(monitor, NULL, 0);
                if (fd < 0) {
                    /* First reflex may be simply to declare accept failure
                       to be a fatal error.  However, accept may fail when
                       a client quits between the above epoll_wait and here.
                       That case is not fatal, but rather to be expected,
                       if not common, so ignore it.  */
                    if (ignorable_epoll_accept_errno(errno))
                        continue;
                    virReportSystemError(errno, "%s",
                                         _("accept(monitor,...) failed"));
                    goto cleanup;
                }
                if (client != -1) { /* Already connected, so kick new one out */
                    close(fd);
                    continue;
                }
                client = fd;
                epollEvent.events = EPOLLHUP;
                epollEvent.data.fd = client;
                if (0 > epoll_ctl(epollFd, EPOLL_CTL_ADD, client, &epollEvent)) {
                    virReportSystemError(errno, "%s",
                                         _("epoll_ctl(client) failed"));
                    goto cleanup;
                }
            } else if (client != -1 && epollEvent.data.fd == client) {
                if (0 > epoll_ctl(epollFd, EPOLL_CTL_DEL, client, &epollEvent)) {
                    virReportSystemError(errno, "%s",
                                         _("epoll_ctl(client) failed"));
                    goto cleanup;
                }
                close(client);
                client = -1;
            } else {
                if (epollEvent.events & EPOLLIN) {
                    curFdOff = epollEvent.data.fd == appPty ? 0 : 1;
                    if (!fdArray[curFdOff].active) {
                        fdArray[curFdOff].active = 1;
                        ++numActive;
                    }
                } else if (epollEvent.events & EPOLLHUP) {
                    DEBUG("EPOLLHUP from fd %d", epollEvent.data.fd);
                    continue;
                } else {
                    lxcError(VIR_ERR_INTERNAL_ERROR,
                             _("error event %d"), epollEvent.events);
                    goto cleanup;
                }
            }
        } else if (0 == numEvents) {
            if (2 == numActive) {
                /* both fds active, toggle between the two */
                curFdOff ^= 1;
            } else {
                /* only one active, if current is active, use it, else it */
                /* must be the other one (ie. curFd just went inactive) */
                curFdOff = fdArray[curFdOff].active ? curFdOff : curFdOff ^ 1;
            }

        } else  {
            if (EINTR == errno) {
                continue;
            }

            /* error */
            virReportSystemError(errno, "%s",
                                 _("epoll_wait() failed"));
            goto cleanup;

        }

        if (0 < numActive) {
            writeFdOff = curFdOff ^ 1;
            rc = lxcFdForward(fdArray[curFdOff].fd, fdArray[writeFdOff].fd);

            if (EAGAIN == rc) {
                /* this fd no longer has data, set it as inactive */
                --numActive;
                fdArray[curFdOff].active = 0;
            } else if (-1 == rc) {
                goto cleanup;
            }

        }

    }

    rc = 0;

cleanup:
    close(appPty);
    close(contPty);
    close(epollFd);
    return rc;
}



/**
 * lxcControllerMoveInterfaces
 * @nveths: number of interfaces
 * @veths: interface names
 * @container: pid of container
 *
 * Moves network interfaces into a container's namespace
 *
 * Returns 0 on success or -1 in case of error
 */
static int lxcControllerMoveInterfaces(unsigned int nveths,
                                       char **veths,
                                       pid_t container)
{
    unsigned int i;
    for (i = 0 ; i < nveths ; i++)
        if (moveInterfaceToNetNs(veths[i], container) < 0)
            return -1;

    return 0;
}


/**
 * lxcCleanupInterfaces:
 * @nveths: number of interfaces
 * @veths: interface names
 *
 * Cleans up the container interfaces by deleting the veth device pairs.
 *
 * Returns 0 on success or -1 in case of error
 */
static int lxcControllerCleanupInterfaces(unsigned int nveths,
                                          char **veths)
{
    unsigned int i;
    for (i = 0 ; i < nveths ; i++)
        vethDelete(veths[i]);

    return 0;
}

#ifndef MS_REC
# define MS_REC          16384
#endif

#ifndef MS_SLAVE
# define MS_SLAVE              (1<<19)
#endif

static int
lxcControllerRun(virDomainDefPtr def,
                 unsigned int nveths,
                 char **veths,
                 int monitor,
                 int client,
                 int appPty)
{
    int rc = -1;
    int control[2] = { -1, -1};
    int containerPty = -1;
    char *containerPtyPath;
    pid_t container = -1;
    virDomainFSDefPtr root;
    char *devpts = NULL;
    char *devptmx = NULL;

    if (socketpair(PF_UNIX, SOCK_STREAM, 0, control) < 0) {
        virReportSystemError(errno, "%s",
                             _("sockpair failed"));
        goto cleanup;
    }

    root = virDomainGetRootFilesystem(def);

    if (lxcSetContainerResources(def) < 0)
        goto cleanup;

    /*
     * If doing a chroot style setup, we need to prepare
     * a private /dev/pts for the child now, which they
     * will later move into position.
     *
     * This is complex because 'virsh console' needs to
     * use /dev/pts from the host OS, and the guest OS
     * needs to use /dev/pts from the guest.
     *
     * This means that we (libvirt_lxc) need to see and
     * use both /dev/pts instances. We're running in the
     * host OS context though and don't want to expose
     * the guest OS /dev/pts there.
     *
     * Thus we call unshare(CLONE_NS) so that we can see
     * the guest's new /dev/pts, without it becoming
     * visible to the host OS. We also put the root FS
     * into slave mode, just in case it was currently
     * marked as shared
     */
    if (root) {
        VIR_DEBUG0("Setting up private /dev/pts");
        if (unshare(CLONE_NEWNS) < 0) {
            virReportSystemError(errno, "%s",
                                 _("Cannot unshare mount namespace"));
            goto cleanup;
        }

        if (mount("", "/", NULL, MS_SLAVE|MS_REC, NULL) < 0) {
            virReportSystemError(errno, "%s",
                                 _("Failed to switch root mount into slave mode"));
            goto cleanup;
        }

        if (virAsprintf(&devpts, "%s/dev/pts", root->src) < 0 ||
            virAsprintf(&devptmx, "%s/dev/pts/ptmx", root->src) < 0) {
            virReportOOMError();
            goto cleanup;
        }

        if (virFileMakePath(devpts) != 0) {
            virReportSystemError(errno,
                                 _("Failed to make path %s"),
                                 devpts);
            goto cleanup;
        }

        VIR_DEBUG("Mouting 'devpts' on %s", devpts);
        if (mount("devpts", devpts, "devpts", 0, "newinstance,ptmxmode=0666") < 0) {
            virReportSystemError(errno,
                                 _("Failed to mount devpts on %s"),
                                 devpts);
            goto cleanup;
        }

        if (access(devptmx, R_OK) < 0) {
            VIR_WARN0("Kernel does not support private devpts, using shared devpts");
            VIR_FREE(devptmx);
        }
    }

    if (devptmx) {
        VIR_DEBUG("Opening tty on private %s", devptmx);
        if (virFileOpenTtyAt(devptmx,
                             &containerPty,
                             &containerPtyPath,
                             0) < 0) {
            virReportSystemError(errno, "%s",
                                 _("Failed to allocate tty"));
            goto cleanup;
        }
    } else {
        VIR_DEBUG0("Opening tty on shared /dev/ptmx");
        if (virFileOpenTty(&containerPty,
                           &containerPtyPath,
                           0) < 0) {
            virReportSystemError(errno, "%s",
                                 _("Failed to allocate tty"));
            goto cleanup;
        }
    }


    if ((container = lxcContainerStart(def,
                                       nveths,
                                       veths,
                                       control[1],
                                       containerPtyPath)) < 0)
        goto cleanup;
    close(control[1]);
    control[1] = -1;

    if (lxcControllerMoveInterfaces(nveths, veths, container) < 0)
        goto cleanup;

    if (lxcContainerSendContinue(control[0]) < 0)
        goto cleanup;

    /* Now the container is running, there's no need for us to keep
       any elevated capabilities */
    if (lxcControllerClearCapabilities() < 0)
        goto cleanup;

    rc = lxcControllerMain(monitor, client, appPty, containerPty);

cleanup:
    VIR_FREE(devptmx);
    VIR_FREE(devpts);
    if (control[0] != -1)
        close(control[0]);
    if (control[1] != -1)
        close(control[1]);
    VIR_FREE(containerPtyPath);
    if (containerPty != -1)
        close(containerPty);

    if (container > 1) {
        int status;
        kill(container, SIGTERM);
        if (!(waitpid(container, &status, WNOHANG) == 0 &&
            WIFEXITED(status)))
            kill(container, SIGKILL);
        waitpid(container, NULL, 0);
    }
    return rc;
}


int main(int argc, char *argv[])
{
    pid_t pid;
    int rc = 1;
    int client;
    char *name = NULL;
    int nveths = 0;
    char **veths = NULL;
    int monitor = -1;
    int appPty = -1;
    int bg = 0;
    virCapsPtr caps = NULL;
    virDomainDefPtr def = NULL;
    char *configFile = NULL;
    char *sockpath = NULL;
    const struct option options[] = {
        { "background", 0, NULL, 'b' },
        { "name",   1, NULL, 'n' },
        { "veth",   1, NULL, 'v' },
        { "console", 1, NULL, 'c' },
        { "help", 0, NULL, 'h' },
        { 0, 0, 0, 0 },
    };

    while (1) {
        int c;

        c = getopt_long(argc, argv, "dn:v:m:c:h",
                       options, NULL);

        if (c == -1)
            break;

        switch (c) {
        case 'b':
            bg = 1;
            break;

        case 'n':
            if ((name = strdup(optarg)) == NULL) {
                virReportOOMError();
                goto cleanup;
            }
            break;

        case 'v':
            if (VIR_REALLOC_N(veths, nveths+1) < 0) {
                virReportOOMError();
                goto cleanup;
            }
            if ((veths[nveths++] = strdup(optarg)) == NULL) {
                virReportOOMError();
                goto cleanup;
            }
            break;

        case 'c':
            if (virStrToLong_i(optarg, NULL, 10, &appPty) < 0) {
                fprintf(stderr, "malformed --console argument '%s'", optarg);
                goto cleanup;
            }
            break;

        case 'h':
        case '?':
            fprintf(stderr, "\n");
            fprintf(stderr, "syntax: %s [OPTIONS]\n", argv[0]);
            fprintf(stderr, "\n");
            fprintf(stderr, "Options\n");
            fprintf(stderr, "\n");
            fprintf(stderr, "  -b, --background\n");
            fprintf(stderr, "  -n NAME, --name NAME\n");
            fprintf(stderr, "  -c FD, --console FD\n");
            fprintf(stderr, "  -v VETH, --veth VETH\n");
            fprintf(stderr, "  -h, --help\n");
            fprintf(stderr, "\n");
            goto cleanup;
        }
    }


    if (name == NULL) {
        fprintf(stderr, "%s: missing --name argument for configuration\n", argv[0]);
        goto cleanup;
    }

    if (appPty < 0) {
        fprintf(stderr, "%s: missing --console argument for container PTY\n", argv[0]);
        goto cleanup;
    }

    if (getuid() != 0) {
        fprintf(stderr, "%s: must be run as the 'root' user\n", argv[0]);
        goto cleanup;
    }

    if ((caps = lxcCapsInit()) == NULL)
        goto cleanup;

    if ((configFile = virDomainConfigFile(LXC_STATE_DIR,
                                          name)) == NULL)
        goto cleanup;

    if ((def = virDomainDefParseFile(caps, configFile,
                                     VIR_DOMAIN_XML_INACTIVE)) == NULL)
        goto cleanup;

    if (def->nnets != nveths) {
        fprintf(stderr, "%s: expecting %d veths, but got %d\n",
                argv[0], def->nnets, nveths);
        goto cleanup;
    }

    if ((sockpath = lxcMonitorPath(def)) == NULL)
        goto cleanup;

    if ((monitor = lxcMonitorServer(sockpath)) < 0)
        goto cleanup;

    if (bg) {
        if ((pid = fork()) < 0)
            goto cleanup;

        if (pid > 0) {
            if ((rc = virFileWritePid(LXC_STATE_DIR, name, pid)) != 0) {
                virReportSystemError(rc,
                                     _("Unable to write pid file '%s/%s.pid'"),
                                     LXC_STATE_DIR, name);
                _exit(1);
            }

            /* First child now exits, allowing original caller
             * (ie libvirtd's LXC driver to complete their
             * waitpid & continue */
            _exit(0);
        }

        /* Don't hold onto any cwd we inherit from libvirtd either */
        if (chdir("/") < 0) {
            virReportSystemError(errno, "%s",
                                 _("Unable to change to root dir"));
            goto cleanup;
        }

        if (setsid() < 0) {
            virReportSystemError(errno, "%s",
                                 _("Unable to become session leader"));
            goto cleanup;
        }
    }

    /* Initialize logging */
    virLogSetFromEnv();

    /* Accept initial client which is the libvirtd daemon */
    if ((client = accept(monitor, NULL, 0)) < 0) {
        virReportSystemError(errno, "%s",
                             _("Failed to accept a connection from driver"));
        goto cleanup;
    }

    rc = lxcControllerRun(def, nveths, veths, monitor, client, appPty);


cleanup:
    if (def)
        virFileDeletePid(LXC_STATE_DIR, def->name);
    lxcControllerCleanupInterfaces(nveths, veths);
    if (sockpath)
        unlink(sockpath);
    VIR_FREE(sockpath);

    return rc;
}