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
|
/*-
* ----------------------------------------------------------------------------
* "THE BEER-WARE LICENSE" (Revision 42):
* <phk@FreeBSD.ORG> wrote this file. As long as you retain this notice you
* can do whatever you want with this stuff. If we meet some day, and you think
* this stuff is worth it, you can buy me a beer in return. Poul-Henning Kamp
* ----------------------------------------------------------------------------
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_mac.h"
#include <sys/param.h>
#include <sys/types.h>
#include <sys/kernel.h>
#include <sys/systm.h>
#include <sys/errno.h>
#include <sys/sysproto.h>
#include <sys/mac.h>
#include <sys/malloc.h>
#include <sys/proc.h>
#include <sys/taskqueue.h>
#include <sys/jail.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/namei.h>
#include <sys/mount.h>
#include <sys/queue.h>
#include <sys/socket.h>
#include <sys/syscallsubr.h>
#include <sys/sysctl.h>
#include <sys/vnode.h>
#include <net/if.h>
#include <netinet/in.h>
MALLOC_DEFINE(M_PRISON, "prison", "Prison structures");
SYSCTL_DECL(_security);
SYSCTL_NODE(_security, OID_AUTO, jail, CTLFLAG_RW, 0,
"Jail rules");
int jail_set_hostname_allowed = 1;
SYSCTL_INT(_security_jail, OID_AUTO, set_hostname_allowed, CTLFLAG_RW,
&jail_set_hostname_allowed, 0,
"Processes in jail can set their hostnames");
int jail_socket_unixiproute_only = 1;
SYSCTL_INT(_security_jail, OID_AUTO, socket_unixiproute_only, CTLFLAG_RW,
&jail_socket_unixiproute_only, 0,
"Processes in jail are limited to creating UNIX/IPv4/route sockets only");
int jail_sysvipc_allowed = 0;
SYSCTL_INT(_security_jail, OID_AUTO, sysvipc_allowed, CTLFLAG_RW,
&jail_sysvipc_allowed, 0,
"Processes in jail can use System V IPC primitives");
static int jail_enforce_statfs = 2;
SYSCTL_INT(_security_jail, OID_AUTO, enforce_statfs, CTLFLAG_RW,
&jail_enforce_statfs, 0,
"Processes in jail cannot see all mounted file systems");
int jail_allow_raw_sockets = 0;
SYSCTL_INT(_security_jail, OID_AUTO, allow_raw_sockets, CTLFLAG_RW,
&jail_allow_raw_sockets, 0,
"Prison root can create raw sockets");
int jail_chflags_allowed = 0;
SYSCTL_INT(_security_jail, OID_AUTO, chflags_allowed, CTLFLAG_RW,
&jail_chflags_allowed, 0,
"Processes in jail can alter system file flags");
/* allprison, lastprid, and prisoncount are protected by allprison_mtx. */
struct prisonlist allprison;
struct mtx allprison_mtx;
int lastprid = 0;
int prisoncount = 0;
static void init_prison(void *);
static void prison_complete(void *context, int pending);
static struct prison *prison_find(int);
static int sysctl_jail_list(SYSCTL_HANDLER_ARGS);
static void
init_prison(void *data __unused)
{
mtx_init(&allprison_mtx, "allprison", NULL, MTX_DEF);
LIST_INIT(&allprison);
}
SYSINIT(prison, SI_SUB_INTRINSIC, SI_ORDER_ANY, init_prison, NULL);
/*
* MPSAFE
*
* struct jail_args {
* struct jail *jail;
* };
*/
int
jail(struct thread *td, struct jail_args *uap)
{
struct nameidata nd;
struct prison *pr, *tpr;
struct jail j;
struct jail_attach_args jaa;
int error, tryprid;
error = copyin(uap->jail, &j, sizeof(j));
if (error)
return (error);
if (j.version != 0)
return (EINVAL);
MALLOC(pr, struct prison *, sizeof(*pr), M_PRISON, M_WAITOK | M_ZERO);
mtx_init(&pr->pr_mtx, "jail mutex", NULL, MTX_DEF);
pr->pr_ref = 1;
error = copyinstr(j.path, &pr->pr_path, sizeof(pr->pr_path), 0);
if (error)
goto e_killmtx;
mtx_lock(&Giant);
NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE, pr->pr_path, td);
error = namei(&nd);
if (error) {
mtx_unlock(&Giant);
goto e_killmtx;
}
pr->pr_root = nd.ni_vp;
VOP_UNLOCK(nd.ni_vp, 0, td);
NDFREE(&nd, NDF_ONLY_PNBUF);
mtx_unlock(&Giant);
error = copyinstr(j.hostname, &pr->pr_host, sizeof(pr->pr_host), 0);
if (error)
goto e_dropvnref;
pr->pr_ip = j.ip_number;
pr->pr_linux = NULL;
pr->pr_securelevel = securelevel;
/* Determine next pr_id and add prison to allprison list. */
mtx_lock(&allprison_mtx);
tryprid = lastprid + 1;
if (tryprid == JAIL_MAX)
tryprid = 1;
next:
LIST_FOREACH(tpr, &allprison, pr_list) {
if (tpr->pr_id == tryprid) {
tryprid++;
if (tryprid == JAIL_MAX) {
mtx_unlock(&allprison_mtx);
error = EAGAIN;
goto e_dropvnref;
}
goto next;
}
}
pr->pr_id = jaa.jid = lastprid = tryprid;
LIST_INSERT_HEAD(&allprison, pr, pr_list);
prisoncount++;
mtx_unlock(&allprison_mtx);
error = jail_attach(td, &jaa);
if (error)
goto e_dropprref;
mtx_lock(&pr->pr_mtx);
pr->pr_ref--;
mtx_unlock(&pr->pr_mtx);
td->td_retval[0] = jaa.jid;
return (0);
e_dropprref:
mtx_lock(&allprison_mtx);
LIST_REMOVE(pr, pr_list);
prisoncount--;
mtx_unlock(&allprison_mtx);
e_dropvnref:
mtx_lock(&Giant);
vrele(pr->pr_root);
mtx_unlock(&Giant);
e_killmtx:
mtx_destroy(&pr->pr_mtx);
FREE(pr, M_PRISON);
return (error);
}
/*
* MPSAFE
*
* struct jail_attach_args {
* int jid;
* };
*/
int
jail_attach(struct thread *td, struct jail_attach_args *uap)
{
struct proc *p;
struct ucred *newcred, *oldcred;
struct prison *pr;
int error;
/*
* XXX: Note that there is a slight race here if two threads
* in the same privileged process attempt to attach to two
* different jails at the same time. It is important for
* user processes not to do this, or they might end up with
* a process root from one prison, but attached to the jail
* of another.
*/
error = suser(td);
if (error)
return (error);
p = td->td_proc;
mtx_lock(&allprison_mtx);
pr = prison_find(uap->jid);
if (pr == NULL) {
mtx_unlock(&allprison_mtx);
return (EINVAL);
}
pr->pr_ref++;
mtx_unlock(&pr->pr_mtx);
mtx_unlock(&allprison_mtx);
mtx_lock(&Giant);
vn_lock(pr->pr_root, LK_EXCLUSIVE | LK_RETRY, td);
if ((error = change_dir(pr->pr_root, td)) != 0)
goto e_unlock;
#ifdef MAC
if ((error = mac_check_vnode_chroot(td->td_ucred, pr->pr_root)))
goto e_unlock;
#endif
VOP_UNLOCK(pr->pr_root, 0, td);
change_root(pr->pr_root, td);
mtx_unlock(&Giant);
newcred = crget();
PROC_LOCK(p);
oldcred = p->p_ucred;
setsugid(p);
crcopy(newcred, oldcred);
newcred->cr_prison = pr;
p->p_ucred = newcred;
PROC_UNLOCK(p);
crfree(oldcred);
return (0);
e_unlock:
VOP_UNLOCK(pr->pr_root, 0, td);
mtx_unlock(&Giant);
mtx_lock(&pr->pr_mtx);
pr->pr_ref--;
mtx_unlock(&pr->pr_mtx);
return (error);
}
/*
* Returns a locked prison instance, or NULL on failure.
*/
static struct prison *
prison_find(int prid)
{
struct prison *pr;
mtx_assert(&allprison_mtx, MA_OWNED);
LIST_FOREACH(pr, &allprison, pr_list) {
if (pr->pr_id == prid) {
mtx_lock(&pr->pr_mtx);
return (pr);
}
}
return (NULL);
}
void
prison_free(struct prison *pr)
{
mtx_lock(&allprison_mtx);
mtx_lock(&pr->pr_mtx);
pr->pr_ref--;
if (pr->pr_ref == 0) {
LIST_REMOVE(pr, pr_list);
mtx_unlock(&pr->pr_mtx);
prisoncount--;
mtx_unlock(&allprison_mtx);
TASK_INIT(&pr->pr_task, 0, prison_complete, pr);
taskqueue_enqueue(taskqueue_thread, &pr->pr_task);
return;
}
mtx_unlock(&pr->pr_mtx);
mtx_unlock(&allprison_mtx);
}
static void
prison_complete(void *context, int pending)
{
struct prison *pr;
pr = (struct prison *)context;
mtx_lock(&Giant);
vrele(pr->pr_root);
mtx_unlock(&Giant);
mtx_destroy(&pr->pr_mtx);
if (pr->pr_linux != NULL)
FREE(pr->pr_linux, M_PRISON);
FREE(pr, M_PRISON);
}
void
prison_hold(struct prison *pr)
{
mtx_lock(&pr->pr_mtx);
pr->pr_ref++;
mtx_unlock(&pr->pr_mtx);
}
u_int32_t
prison_getip(struct ucred *cred)
{
return (cred->cr_prison->pr_ip);
}
int
prison_ip(struct ucred *cred, int flag, u_int32_t *ip)
{
u_int32_t tmp;
if (!jailed(cred))
return (0);
if (flag)
tmp = *ip;
else
tmp = ntohl(*ip);
if (tmp == INADDR_ANY) {
if (flag)
*ip = cred->cr_prison->pr_ip;
else
*ip = htonl(cred->cr_prison->pr_ip);
return (0);
}
if (tmp == INADDR_LOOPBACK) {
if (flag)
*ip = cred->cr_prison->pr_ip;
else
*ip = htonl(cred->cr_prison->pr_ip);
return (0);
}
if (cred->cr_prison->pr_ip != tmp)
return (1);
return (0);
}
void
prison_remote_ip(struct ucred *cred, int flag, u_int32_t *ip)
{
u_int32_t tmp;
if (!jailed(cred))
return;
if (flag)
tmp = *ip;
else
tmp = ntohl(*ip);
if (tmp == INADDR_LOOPBACK) {
if (flag)
*ip = cred->cr_prison->pr_ip;
else
*ip = htonl(cred->cr_prison->pr_ip);
return;
}
return;
}
int
prison_if(struct ucred *cred, struct sockaddr *sa)
{
struct sockaddr_in *sai;
int ok;
sai = (struct sockaddr_in *)sa;
if ((sai->sin_family != AF_INET) && jail_socket_unixiproute_only)
ok = 1;
else if (sai->sin_family != AF_INET)
ok = 0;
else if (cred->cr_prison->pr_ip != ntohl(sai->sin_addr.s_addr))
ok = 1;
else
ok = 0;
return (ok);
}
/*
* Return 0 if jails permit p1 to frob p2, otherwise ESRCH.
*/
int
prison_check(struct ucred *cred1, struct ucred *cred2)
{
if (jailed(cred1)) {
if (!jailed(cred2))
return (ESRCH);
if (cred2->cr_prison != cred1->cr_prison)
return (ESRCH);
}
return (0);
}
/*
* Return 1 if the passed credential is in a jail, otherwise 0.
*/
int
jailed(struct ucred *cred)
{
return (cred->cr_prison != NULL);
}
/*
* Return the correct hostname for the passed credential.
*/
void
getcredhostname(struct ucred *cred, char *buf, size_t size)
{
if (jailed(cred)) {
mtx_lock(&cred->cr_prison->pr_mtx);
strlcpy(buf, cred->cr_prison->pr_host, size);
mtx_unlock(&cred->cr_prison->pr_mtx);
} else
strlcpy(buf, hostname, size);
}
/*
* Determine whether the subject represented by cred can "see"
* status of a mount point.
* Returns: 0 for permitted, ENOENT otherwise.
* XXX: This function should be called cr_canseemount() and should be
* placed in kern_prot.c.
*/
int
prison_canseemount(struct ucred *cred, struct mount *mp)
{
struct prison *pr;
struct statfs *sp;
size_t len;
if (!jailed(cred) || jail_enforce_statfs == 0)
return (0);
pr = cred->cr_prison;
if (pr->pr_root->v_mount == mp)
return (0);
if (jail_enforce_statfs == 2)
return (ENOENT);
/*
* If jail's chroot directory is set to "/" we should be able to see
* all mount-points from inside a jail.
* This is ugly check, but this is the only situation when jail's
* directory ends with '/'.
*/
if (strcmp(pr->pr_path, "/") == 0)
return (0);
len = strlen(pr->pr_path);
sp = &mp->mnt_stat;
if (strncmp(pr->pr_path, sp->f_mntonname, len) != 0)
return (ENOENT);
/*
* Be sure that we don't have situation where jail's root directory
* is "/some/path" and mount point is "/some/pathpath".
*/
if (sp->f_mntonname[len] != '\0' && sp->f_mntonname[len] != '/')
return (ENOENT);
return (0);
}
void
prison_enforce_statfs(struct ucred *cred, struct mount *mp, struct statfs *sp)
{
char jpath[MAXPATHLEN];
struct prison *pr;
size_t len;
if (!jailed(cred) || jail_enforce_statfs == 0)
return;
pr = cred->cr_prison;
if (prison_canseemount(cred, mp) != 0) {
/* Should never happen. */
bzero(sp->f_mntonname, sizeof(sp->f_mntonname));
strlcpy(sp->f_mntonname, "[restricted]",
sizeof(sp->f_mntonname));
return;
}
if (pr->pr_root->v_mount == mp) {
/*
* Clear current buffer data, so we are sure nothing from
* the valid path left there.
*/
bzero(sp->f_mntonname, sizeof(sp->f_mntonname));
*sp->f_mntonname = '/';
return;
}
/*
* If jail's chroot directory is set to "/" we should be able to see
* all mount-points from inside a jail.
*/
if (strcmp(pr->pr_path, "/") == 0)
return;
len = strlen(pr->pr_path);
strlcpy(jpath, sp->f_mntonname + len, sizeof(jpath));
/*
* Clear current buffer data, so we are sure nothing from
* the valid path left there.
*/
bzero(sp->f_mntonname, sizeof(sp->f_mntonname));
if (*jpath == '\0') {
/* Should never happen. */
*sp->f_mntonname = '/';
} else {
strlcpy(sp->f_mntonname, jpath, sizeof(sp->f_mntonname));
}
}
static int
sysctl_jail_list(SYSCTL_HANDLER_ARGS)
{
struct xprison *xp, *sxp;
struct prison *pr;
int count, error;
mtx_assert(&Giant, MA_OWNED);
if (jailed(req->td->td_ucred))
return (0);
retry:
mtx_lock(&allprison_mtx);
count = prisoncount;
mtx_unlock(&allprison_mtx);
if (count == 0)
return (0);
sxp = xp = malloc(sizeof(*xp) * count, M_TEMP, M_WAITOK | M_ZERO);
mtx_lock(&allprison_mtx);
if (count != prisoncount) {
mtx_unlock(&allprison_mtx);
free(sxp, M_TEMP);
goto retry;
}
LIST_FOREACH(pr, &allprison, pr_list) {
mtx_lock(&pr->pr_mtx);
xp->pr_version = XPRISON_VERSION;
xp->pr_id = pr->pr_id;
strlcpy(xp->pr_path, pr->pr_path, sizeof(xp->pr_path));
strlcpy(xp->pr_host, pr->pr_host, sizeof(xp->pr_host));
xp->pr_ip = pr->pr_ip;
mtx_unlock(&pr->pr_mtx);
xp++;
}
mtx_unlock(&allprison_mtx);
error = SYSCTL_OUT(req, sxp, sizeof(*sxp) * count);
free(sxp, M_TEMP);
if (error)
return (error);
return (0);
}
SYSCTL_OID(_security_jail, OID_AUTO, list, CTLTYPE_STRUCT | CTLFLAG_RD,
NULL, 0, sysctl_jail_list, "S", "List of active jails");
static int
sysctl_jail_jailed(SYSCTL_HANDLER_ARGS)
{
int error, injail;
injail = jailed(req->td->td_ucred);
error = SYSCTL_OUT(req, &injail, sizeof(injail));
return (error);
}
SYSCTL_PROC(_security_jail, OID_AUTO, jailed, CTLTYPE_INT | CTLFLAG_RD,
NULL, 0, sysctl_jail_jailed, "I", "Process in jail?");
|