forked from opnsense/src
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathkern_jail.c
4594 lines (4270 loc) · 115 KB
/
kern_jail.c
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
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*-
* SPDX-License-Identifier: BSD-2-Clause-FreeBSD
*
* Copyright (c) 1999 Poul-Henning Kamp.
* Copyright (c) 2008 Bjoern A. Zeeb.
* Copyright (c) 2009 James Gritton.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*/
#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");
#include "opt_ddb.h"
#include "opt_inet.h"
#include "opt_inet6.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/malloc.h>
#include <sys/osd.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/taskqueue.h>
#include <sys/fcntl.h>
#include <sys/jail.h>
#include <sys/linker.h>
#include <sys/lock.h>
#include <sys/mutex.h>
#include <sys/racct.h>
#include <sys/rctl.h>
#include <sys/refcount.h>
#include <sys/sx.h>
#include <sys/sysent.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/uuid.h>
#include <sys/vnode.h>
#include <net/if.h>
#include <net/vnet.h>
#include <netinet/in.h>
#ifdef DDB
#include <ddb/ddb.h>
#endif /* DDB */
#include <security/mac/mac_framework.h>
#define PRISON0_HOSTUUID_MODULE "hostuuid"
MALLOC_DEFINE(M_PRISON, "prison", "Prison structures");
static MALLOC_DEFINE(M_PRISON_RACCT, "prison_racct", "Prison racct structures");
/* Keep struct prison prison0 and some code in kern_jail_set() readable. */
#ifdef INET
#ifdef INET6
#define _PR_IP_SADDRSEL PR_IP4_SADDRSEL|PR_IP6_SADDRSEL
#else
#define _PR_IP_SADDRSEL PR_IP4_SADDRSEL
#endif
#else /* !INET */
#ifdef INET6
#define _PR_IP_SADDRSEL PR_IP6_SADDRSEL
#else
#define _PR_IP_SADDRSEL 0
#endif
#endif
/* prison0 describes what is "real" about the system. */
struct prison prison0 = {
.pr_id = 0,
.pr_name = "0",
.pr_ref = 1,
.pr_uref = 1,
.pr_path = "/",
.pr_securelevel = -1,
.pr_devfs_rsnum = 0,
.pr_state = PRISON_STATE_ALIVE,
.pr_childmax = JAIL_MAX,
.pr_hostuuid = DEFAULT_HOSTUUID,
.pr_children = LIST_HEAD_INITIALIZER(prison0.pr_children),
#ifdef VIMAGE
.pr_flags = PR_HOST|PR_VNET|_PR_IP_SADDRSEL,
#else
.pr_flags = PR_HOST|_PR_IP_SADDRSEL,
#endif
.pr_allow = PR_ALLOW_ALL_STATIC,
};
MTX_SYSINIT(prison0, &prison0.pr_mtx, "jail mutex", MTX_DEF);
struct bool_flags {
const char *name;
const char *noname;
volatile u_int flag;
};
struct jailsys_flags {
const char *name;
unsigned disable;
unsigned new;
};
/* allprison, allprison_racct and lastprid are protected by allprison_lock. */
struct sx allprison_lock;
SX_SYSINIT(allprison_lock, &allprison_lock, "allprison");
struct prisonlist allprison = TAILQ_HEAD_INITIALIZER(allprison);
LIST_HEAD(, prison_racct) allprison_racct;
int lastprid = 0;
static int get_next_prid(struct prison **insprp);
static int do_jail_attach(struct thread *td, struct prison *pr, int drflags);
static void prison_complete(void *context, int pending);
static void prison_deref(struct prison *pr, int flags);
static void prison_deref_kill(struct prison *pr, struct prisonlist *freeprison);
static int prison_lock_xlock(struct prison *pr, int flags);
static void prison_free_not_last(struct prison *pr);
static void prison_proc_free_not_last(struct prison *pr);
static void prison_set_allow_locked(struct prison *pr, unsigned flag,
int enable);
static char *prison_path(struct prison *pr1, struct prison *pr2);
#ifdef RACCT
static void prison_racct_attach(struct prison *pr);
static void prison_racct_modify(struct prison *pr);
static void prison_racct_detach(struct prison *pr);
#endif
/* Flags for prison_deref */
#define PD_DEREF 0x01 /* Decrement pr_ref */
#define PD_DEUREF 0x02 /* Decrement pr_uref */
#define PD_KILL 0x04 /* Remove jail, kill processes, etc */
#define PD_LOCKED 0x10 /* pr_mtx is held */
#define PD_LIST_SLOCKED 0x20 /* allprison_lock is held shared */
#define PD_LIST_XLOCKED 0x40 /* allprison_lock is held exclusive */
#define PD_OP_FLAGS 0x07 /* Operation flags */
#define PD_LOCK_FLAGS 0x70 /* Lock status flags */
/*
* Parameter names corresponding to PR_* flag values. Size values are for kvm
* as we cannot figure out the size of a sparse array, or an array without a
* terminating entry.
*/
static struct bool_flags pr_flag_bool[] = {
{"persist", "nopersist", PR_PERSIST},
#ifdef INET
{"ip4.saddrsel", "ip4.nosaddrsel", PR_IP4_SADDRSEL},
#endif
#ifdef INET6
{"ip6.saddrsel", "ip6.nosaddrsel", PR_IP6_SADDRSEL},
#endif
};
const size_t pr_flag_bool_size = sizeof(pr_flag_bool);
static struct jailsys_flags pr_flag_jailsys[] = {
{"host", 0, PR_HOST},
#ifdef VIMAGE
{"vnet", 0, PR_VNET},
#endif
#ifdef INET
{"ip4", PR_IP4_USER, PR_IP4_USER},
#endif
#ifdef INET6
{"ip6", PR_IP6_USER, PR_IP6_USER},
#endif
};
const size_t pr_flag_jailsys_size = sizeof(pr_flag_jailsys);
/*
* Make this array full-size so dynamic parameters can be added.
* It is protected by prison0.mtx, but lockless reading is allowed
* with an atomic check of the flag values.
*/
static struct bool_flags pr_flag_allow[NBBY * NBPW] = {
{"allow.set_hostname", "allow.noset_hostname", PR_ALLOW_SET_HOSTNAME},
{"allow.sysvipc", "allow.nosysvipc", PR_ALLOW_SYSVIPC},
{"allow.raw_sockets", "allow.noraw_sockets", PR_ALLOW_RAW_SOCKETS},
{"allow.chflags", "allow.nochflags", PR_ALLOW_CHFLAGS},
{"allow.mount", "allow.nomount", PR_ALLOW_MOUNT},
{"allow.quotas", "allow.noquotas", PR_ALLOW_QUOTAS},
{"allow.socket_af", "allow.nosocket_af", PR_ALLOW_SOCKET_AF},
{"allow.mlock", "allow.nomlock", PR_ALLOW_MLOCK},
{"allow.reserved_ports", "allow.noreserved_ports",
PR_ALLOW_RESERVED_PORTS},
{"allow.read_msgbuf", "allow.noread_msgbuf", PR_ALLOW_READ_MSGBUF},
{"allow.unprivileged_proc_debug", "allow.nounprivileged_proc_debug",
PR_ALLOW_UNPRIV_DEBUG},
{"allow.suser", "allow.nosuser", PR_ALLOW_SUSER},
};
static unsigned pr_allow_all = PR_ALLOW_ALL_STATIC;
const size_t pr_flag_allow_size = sizeof(pr_flag_allow);
#define JAIL_DEFAULT_ALLOW (PR_ALLOW_SET_HOSTNAME | \
PR_ALLOW_RESERVED_PORTS | \
PR_ALLOW_UNPRIV_DEBUG | \
PR_ALLOW_SUSER)
#define JAIL_DEFAULT_ENFORCE_STATFS 2
#define JAIL_DEFAULT_DEVFS_RSNUM 0
static unsigned jail_default_allow = JAIL_DEFAULT_ALLOW;
static int jail_default_enforce_statfs = JAIL_DEFAULT_ENFORCE_STATFS;
static int jail_default_devfs_rsnum = JAIL_DEFAULT_DEVFS_RSNUM;
#if defined(INET) || defined(INET6)
static unsigned jail_max_af_ips = 255;
#endif
/*
* Initialize the parts of prison0 that can't be static-initialized with
* constants. This is called from proc0_init() after creating thread0 cpuset.
*/
void
prison0_init(void)
{
uint8_t *file, *data;
size_t size;
prison0.pr_cpuset = cpuset_ref(thread0.td_cpuset);
prison0.pr_osreldate = osreldate;
strlcpy(prison0.pr_osrelease, osrelease, sizeof(prison0.pr_osrelease));
/* If we have a preloaded hostuuid, use it. */
file = preload_search_by_type(PRISON0_HOSTUUID_MODULE);
if (file != NULL) {
data = preload_fetch_addr(file);
size = preload_fetch_size(file);
if (data != NULL) {
/*
* The preloaded data may include trailing whitespace, almost
* certainly a newline; skip over any whitespace or
* non-printable characters to be safe.
*/
while (size > 0 && data[size - 1] <= 0x20) {
size--;
}
if (validate_uuid(data, size, NULL, 0) == 0) {
(void)strlcpy(prison0.pr_hostuuid, data,
size + 1);
} else if (bootverbose) {
printf("hostuuid: preload data malformed: '%.*s'\n",
(int)size, data);
}
}
}
if (bootverbose)
printf("hostuuid: using %s\n", prison0.pr_hostuuid);
}
/*
* struct jail_args {
* struct jail *jail;
* };
*/
int
sys_jail(struct thread *td, struct jail_args *uap)
{
uint32_t version;
int error;
struct jail j;
error = copyin(uap->jail, &version, sizeof(uint32_t));
if (error)
return (error);
switch (version) {
case 0:
{
struct jail_v0 j0;
/* FreeBSD single IPv4 jails. */
bzero(&j, sizeof(struct jail));
error = copyin(uap->jail, &j0, sizeof(struct jail_v0));
if (error)
return (error);
j.version = j0.version;
j.path = j0.path;
j.hostname = j0.hostname;
j.ip4s = htonl(j0.ip_number); /* jail_v0 is host order */
break;
}
case 1:
/*
* Version 1 was used by multi-IPv4 jail implementations
* that never made it into the official kernel.
*/
return (EINVAL);
case 2: /* JAIL_API_VERSION */
/* FreeBSD multi-IPv4/IPv6,noIP jails. */
error = copyin(uap->jail, &j, sizeof(struct jail));
if (error)
return (error);
break;
default:
/* Sci-Fi jails are not supported, sorry. */
return (EINVAL);
}
return (kern_jail(td, &j));
}
int
kern_jail(struct thread *td, struct jail *j)
{
struct iovec optiov[2 * (4 + nitems(pr_flag_allow)
#ifdef INET
+ 1
#endif
#ifdef INET6
+ 1
#endif
)];
struct uio opt;
char *u_path, *u_hostname, *u_name;
struct bool_flags *bf;
#ifdef INET
uint32_t ip4s;
struct in_addr *u_ip4;
#endif
#ifdef INET6
struct in6_addr *u_ip6;
#endif
size_t tmplen;
int error, enforce_statfs;
bzero(&optiov, sizeof(optiov));
opt.uio_iov = optiov;
opt.uio_iovcnt = 0;
opt.uio_offset = -1;
opt.uio_resid = -1;
opt.uio_segflg = UIO_SYSSPACE;
opt.uio_rw = UIO_READ;
opt.uio_td = td;
/* Set permissions for top-level jails from sysctls. */
if (!jailed(td->td_ucred)) {
for (bf = pr_flag_allow;
bf < pr_flag_allow + nitems(pr_flag_allow) &&
atomic_load_int(&bf->flag) != 0;
bf++) {
optiov[opt.uio_iovcnt].iov_base = __DECONST(char *,
(jail_default_allow & bf->flag)
? bf->name : bf->noname);
optiov[opt.uio_iovcnt].iov_len =
strlen(optiov[opt.uio_iovcnt].iov_base) + 1;
opt.uio_iovcnt += 2;
}
optiov[opt.uio_iovcnt].iov_base = "enforce_statfs";
optiov[opt.uio_iovcnt].iov_len = sizeof("enforce_statfs");
opt.uio_iovcnt++;
enforce_statfs = jail_default_enforce_statfs;
optiov[opt.uio_iovcnt].iov_base = &enforce_statfs;
optiov[opt.uio_iovcnt].iov_len = sizeof(enforce_statfs);
opt.uio_iovcnt++;
}
tmplen = MAXPATHLEN + MAXHOSTNAMELEN + MAXHOSTNAMELEN;
#ifdef INET
ip4s = (j->version == 0) ? 1 : j->ip4s;
if (ip4s > jail_max_af_ips)
return (EINVAL);
tmplen += ip4s * sizeof(struct in_addr);
#else
if (j->ip4s > 0)
return (EINVAL);
#endif
#ifdef INET6
if (j->ip6s > jail_max_af_ips)
return (EINVAL);
tmplen += j->ip6s * sizeof(struct in6_addr);
#else
if (j->ip6s > 0)
return (EINVAL);
#endif
u_path = malloc(tmplen, M_TEMP, M_WAITOK);
u_hostname = u_path + MAXPATHLEN;
u_name = u_hostname + MAXHOSTNAMELEN;
#ifdef INET
u_ip4 = (struct in_addr *)(u_name + MAXHOSTNAMELEN);
#endif
#ifdef INET6
#ifdef INET
u_ip6 = (struct in6_addr *)(u_ip4 + ip4s);
#else
u_ip6 = (struct in6_addr *)(u_name + MAXHOSTNAMELEN);
#endif
#endif
optiov[opt.uio_iovcnt].iov_base = "path";
optiov[opt.uio_iovcnt].iov_len = sizeof("path");
opt.uio_iovcnt++;
optiov[opt.uio_iovcnt].iov_base = u_path;
error = copyinstr(j->path, u_path, MAXPATHLEN,
&optiov[opt.uio_iovcnt].iov_len);
if (error) {
free(u_path, M_TEMP);
return (error);
}
opt.uio_iovcnt++;
optiov[opt.uio_iovcnt].iov_base = "host.hostname";
optiov[opt.uio_iovcnt].iov_len = sizeof("host.hostname");
opt.uio_iovcnt++;
optiov[opt.uio_iovcnt].iov_base = u_hostname;
error = copyinstr(j->hostname, u_hostname, MAXHOSTNAMELEN,
&optiov[opt.uio_iovcnt].iov_len);
if (error) {
free(u_path, M_TEMP);
return (error);
}
opt.uio_iovcnt++;
if (j->jailname != NULL) {
optiov[opt.uio_iovcnt].iov_base = "name";
optiov[opt.uio_iovcnt].iov_len = sizeof("name");
opt.uio_iovcnt++;
optiov[opt.uio_iovcnt].iov_base = u_name;
error = copyinstr(j->jailname, u_name, MAXHOSTNAMELEN,
&optiov[opt.uio_iovcnt].iov_len);
if (error) {
free(u_path, M_TEMP);
return (error);
}
opt.uio_iovcnt++;
}
#ifdef INET
optiov[opt.uio_iovcnt].iov_base = "ip4.addr";
optiov[opt.uio_iovcnt].iov_len = sizeof("ip4.addr");
opt.uio_iovcnt++;
optiov[opt.uio_iovcnt].iov_base = u_ip4;
optiov[opt.uio_iovcnt].iov_len = ip4s * sizeof(struct in_addr);
if (j->version == 0)
u_ip4->s_addr = j->ip4s;
else {
error = copyin(j->ip4, u_ip4, optiov[opt.uio_iovcnt].iov_len);
if (error) {
free(u_path, M_TEMP);
return (error);
}
}
opt.uio_iovcnt++;
#endif
#ifdef INET6
optiov[opt.uio_iovcnt].iov_base = "ip6.addr";
optiov[opt.uio_iovcnt].iov_len = sizeof("ip6.addr");
opt.uio_iovcnt++;
optiov[opt.uio_iovcnt].iov_base = u_ip6;
optiov[opt.uio_iovcnt].iov_len = j->ip6s * sizeof(struct in6_addr);
error = copyin(j->ip6, u_ip6, optiov[opt.uio_iovcnt].iov_len);
if (error) {
free(u_path, M_TEMP);
return (error);
}
opt.uio_iovcnt++;
#endif
KASSERT(opt.uio_iovcnt <= nitems(optiov),
("kern_jail: too many iovecs (%d)", opt.uio_iovcnt));
error = kern_jail_set(td, &opt, JAIL_CREATE | JAIL_ATTACH);
free(u_path, M_TEMP);
return (error);
}
/*
* struct jail_set_args {
* struct iovec *iovp;
* unsigned int iovcnt;
* int flags;
* };
*/
int
sys_jail_set(struct thread *td, struct jail_set_args *uap)
{
struct uio *auio;
int error;
/* Check that we have an even number of iovecs. */
if (uap->iovcnt & 1)
return (EINVAL);
error = copyinuio(uap->iovp, uap->iovcnt, &auio);
if (error)
return (error);
error = kern_jail_set(td, auio, uap->flags);
free(auio, M_IOV);
return (error);
}
int
kern_jail_set(struct thread *td, struct uio *optuio, int flags)
{
struct nameidata nd;
#ifdef INET
struct in_addr *ip4;
#endif
#ifdef INET6
struct in6_addr *ip6;
#endif
struct vfsopt *opt;
struct vfsoptlist *opts;
struct prison *pr, *deadpr, *inspr, *mypr, *ppr, *tpr;
struct vnode *root;
char *domain, *errmsg, *host, *name, *namelc, *p, *path, *uuid;
char *g_path, *osrelstr;
struct bool_flags *bf;
struct jailsys_flags *jsf;
#if defined(INET) || defined(INET6)
struct prison *tppr;
void *op;
#endif
unsigned long hid;
size_t namelen, onamelen, pnamelen;
int born, created, cuflags, descend, drflags, enforce;
int error, errmsg_len, errmsg_pos;
int gotchildmax, gotenforce, gothid, gotrsnum, gotslevel;
int jid, jsys, len, level;
int childmax, osreldt, rsnum, slevel;
#if defined(INET) || defined(INET6)
int ii, ij;
#endif
#ifdef INET
int ip4s, redo_ip4;
#endif
#ifdef INET6
int ip6s, redo_ip6;
#endif
uint64_t pr_allow, ch_allow, pr_flags, ch_flags;
uint64_t pr_allow_diff;
unsigned tallow;
char numbuf[12];
error = priv_check(td, PRIV_JAIL_SET);
if (!error && (flags & JAIL_ATTACH))
error = priv_check(td, PRIV_JAIL_ATTACH);
if (error)
return (error);
mypr = td->td_ucred->cr_prison;
if ((flags & JAIL_CREATE) && mypr->pr_childmax == 0)
return (EPERM);
if (flags & ~JAIL_SET_MASK)
return (EINVAL);
/*
* Check all the parameters before committing to anything. Not all
* errors can be caught early, but we may as well try. Also, this
* takes care of some expensive stuff (path lookup) before getting
* the allprison lock.
*
* XXX Jails are not filesystems, and jail parameters are not mount
* options. But it makes more sense to re-use the vfsopt code
* than duplicate it under a different name.
*/
error = vfs_buildopts(optuio, &opts);
if (error)
return (error);
#ifdef INET
ip4 = NULL;
#endif
#ifdef INET6
ip6 = NULL;
#endif
g_path = NULL;
cuflags = flags & (JAIL_CREATE | JAIL_UPDATE);
if (!cuflags) {
error = EINVAL;
vfs_opterror(opts, "no valid operation (create or update)");
goto done_errmsg;
}
error = vfs_copyopt(opts, "jid", &jid, sizeof(jid));
if (error == ENOENT)
jid = 0;
else if (error != 0)
goto done_free;
error = vfs_copyopt(opts, "securelevel", &slevel, sizeof(slevel));
if (error == ENOENT)
gotslevel = 0;
else if (error != 0)
goto done_free;
else
gotslevel = 1;
error =
vfs_copyopt(opts, "children.max", &childmax, sizeof(childmax));
if (error == ENOENT)
gotchildmax = 0;
else if (error != 0)
goto done_free;
else
gotchildmax = 1;
error = vfs_copyopt(opts, "enforce_statfs", &enforce, sizeof(enforce));
if (error == ENOENT)
gotenforce = 0;
else if (error != 0)
goto done_free;
else if (enforce < 0 || enforce > 2) {
error = EINVAL;
goto done_free;
} else
gotenforce = 1;
error = vfs_copyopt(opts, "devfs_ruleset", &rsnum, sizeof(rsnum));
if (error == ENOENT)
gotrsnum = 0;
else if (error != 0)
goto done_free;
else
gotrsnum = 1;
pr_flags = ch_flags = 0;
for (bf = pr_flag_bool;
bf < pr_flag_bool + nitems(pr_flag_bool);
bf++) {
vfs_flagopt(opts, bf->name, &pr_flags, bf->flag);
vfs_flagopt(opts, bf->noname, &ch_flags, bf->flag);
}
ch_flags |= pr_flags;
for (jsf = pr_flag_jailsys;
jsf < pr_flag_jailsys + nitems(pr_flag_jailsys);
jsf++) {
error = vfs_copyopt(opts, jsf->name, &jsys, sizeof(jsys));
if (error == ENOENT)
continue;
if (error != 0)
goto done_free;
switch (jsys) {
case JAIL_SYS_DISABLE:
if (!jsf->disable) {
error = EINVAL;
goto done_free;
}
pr_flags |= jsf->disable;
break;
case JAIL_SYS_NEW:
pr_flags |= jsf->new;
break;
case JAIL_SYS_INHERIT:
break;
default:
error = EINVAL;
goto done_free;
}
ch_flags |= jsf->new | jsf->disable;
}
if ((flags & (JAIL_CREATE | JAIL_ATTACH)) == JAIL_CREATE
&& !(pr_flags & PR_PERSIST)) {
error = EINVAL;
vfs_opterror(opts, "new jail must persist or attach");
goto done_errmsg;
}
#ifdef VIMAGE
if ((flags & JAIL_UPDATE) && (ch_flags & PR_VNET)) {
error = EINVAL;
vfs_opterror(opts, "vnet cannot be changed after creation");
goto done_errmsg;
}
#endif
#ifdef INET
if ((flags & JAIL_UPDATE) && (ch_flags & PR_IP4_USER)) {
error = EINVAL;
vfs_opterror(opts, "ip4 cannot be changed after creation");
goto done_errmsg;
}
#endif
#ifdef INET6
if ((flags & JAIL_UPDATE) && (ch_flags & PR_IP6_USER)) {
error = EINVAL;
vfs_opterror(opts, "ip6 cannot be changed after creation");
goto done_errmsg;
}
#endif
pr_allow = ch_allow = 0;
for (bf = pr_flag_allow;
bf < pr_flag_allow + nitems(pr_flag_allow) &&
atomic_load_int(&bf->flag) != 0;
bf++) {
vfs_flagopt(opts, bf->name, &pr_allow, bf->flag);
vfs_flagopt(opts, bf->noname, &ch_allow, bf->flag);
}
ch_allow |= pr_allow;
error = vfs_getopt(opts, "name", (void **)&name, &len);
if (error == ENOENT)
name = NULL;
else if (error != 0)
goto done_free;
else {
if (len == 0 || name[len - 1] != '\0') {
error = EINVAL;
goto done_free;
}
if (len > MAXHOSTNAMELEN) {
error = ENAMETOOLONG;
goto done_free;
}
}
error = vfs_getopt(opts, "host.hostname", (void **)&host, &len);
if (error == ENOENT)
host = NULL;
else if (error != 0)
goto done_free;
else {
ch_flags |= PR_HOST;
pr_flags |= PR_HOST;
if (len == 0 || host[len - 1] != '\0') {
error = EINVAL;
goto done_free;
}
if (len > MAXHOSTNAMELEN) {
error = ENAMETOOLONG;
goto done_free;
}
}
error = vfs_getopt(opts, "host.domainname", (void **)&domain, &len);
if (error == ENOENT)
domain = NULL;
else if (error != 0)
goto done_free;
else {
ch_flags |= PR_HOST;
pr_flags |= PR_HOST;
if (len == 0 || domain[len - 1] != '\0') {
error = EINVAL;
goto done_free;
}
if (len > MAXHOSTNAMELEN) {
error = ENAMETOOLONG;
goto done_free;
}
}
error = vfs_getopt(opts, "host.hostuuid", (void **)&uuid, &len);
if (error == ENOENT)
uuid = NULL;
else if (error != 0)
goto done_free;
else {
ch_flags |= PR_HOST;
pr_flags |= PR_HOST;
if (len == 0 || uuid[len - 1] != '\0') {
error = EINVAL;
goto done_free;
}
if (len > HOSTUUIDLEN) {
error = ENAMETOOLONG;
goto done_free;
}
}
#ifdef COMPAT_FREEBSD32
if (SV_PROC_FLAG(td->td_proc, SV_ILP32)) {
uint32_t hid32;
error = vfs_copyopt(opts, "host.hostid", &hid32, sizeof(hid32));
hid = hid32;
} else
#endif
error = vfs_copyopt(opts, "host.hostid", &hid, sizeof(hid));
if (error == ENOENT)
gothid = 0;
else if (error != 0)
goto done_free;
else {
gothid = 1;
ch_flags |= PR_HOST;
pr_flags |= PR_HOST;
}
#ifdef INET
error = vfs_getopt(opts, "ip4.addr", &op, &ip4s);
if (error == ENOENT)
ip4s = 0;
else if (error != 0)
goto done_free;
else if (ip4s & (sizeof(*ip4) - 1)) {
error = EINVAL;
goto done_free;
} else {
ch_flags |= PR_IP4_USER;
pr_flags |= PR_IP4_USER;
if (ip4s > 0) {
ip4s /= sizeof(*ip4);
if (ip4s > jail_max_af_ips) {
error = EINVAL;
vfs_opterror(opts, "too many IPv4 addresses");
goto done_errmsg;
}
ip4 = malloc(ip4s * sizeof(*ip4), M_PRISON, M_WAITOK);
bcopy(op, ip4, ip4s * sizeof(*ip4));
/*
* IP addresses are all sorted but ip[0] to preserve
* the primary IP address as given from userland.
* This special IP is used for unbound outgoing
* connections as well for "loopback" traffic in case
* source address selection cannot find any more fitting
* address to connect from.
*/
if (ip4s > 1)
qsort(ip4 + 1, ip4s - 1, sizeof(*ip4),
prison_qcmp_v4);
/*
* Check for duplicate addresses and do some simple
* zero and broadcast checks. If users give other bogus
* addresses it is their problem.
*
* We do not have to care about byte order for these
* checks so we will do them in NBO.
*/
for (ii = 0; ii < ip4s; ii++) {
if (ip4[ii].s_addr == INADDR_ANY ||
ip4[ii].s_addr == INADDR_BROADCAST) {
error = EINVAL;
goto done_free;
}
if ((ii+1) < ip4s &&
(ip4[0].s_addr == ip4[ii+1].s_addr ||
ip4[ii].s_addr == ip4[ii+1].s_addr)) {
error = EINVAL;
goto done_free;
}
}
}
}
#endif
#ifdef INET6
error = vfs_getopt(opts, "ip6.addr", &op, &ip6s);
if (error == ENOENT)
ip6s = 0;
else if (error != 0)
goto done_free;
else if (ip6s & (sizeof(*ip6) - 1)) {
error = EINVAL;
goto done_free;
} else {
ch_flags |= PR_IP6_USER;
pr_flags |= PR_IP6_USER;
if (ip6s > 0) {
ip6s /= sizeof(*ip6);
if (ip6s > jail_max_af_ips) {
error = EINVAL;
vfs_opterror(opts, "too many IPv6 addresses");
goto done_errmsg;
}
ip6 = malloc(ip6s * sizeof(*ip6), M_PRISON, M_WAITOK);
bcopy(op, ip6, ip6s * sizeof(*ip6));
if (ip6s > 1)
qsort(ip6 + 1, ip6s - 1, sizeof(*ip6),
prison_qcmp_v6);
for (ii = 0; ii < ip6s; ii++) {
if (IN6_IS_ADDR_UNSPECIFIED(&ip6[ii])) {
error = EINVAL;
goto done_free;
}
if ((ii+1) < ip6s &&
(IN6_ARE_ADDR_EQUAL(&ip6[0], &ip6[ii+1]) ||
IN6_ARE_ADDR_EQUAL(&ip6[ii], &ip6[ii+1])))
{
error = EINVAL;
goto done_free;
}
}
}
}
#endif
#if defined(VIMAGE) && (defined(INET) || defined(INET6))
if ((ch_flags & PR_VNET) && (ch_flags & (PR_IP4_USER | PR_IP6_USER))) {
error = EINVAL;
vfs_opterror(opts,
"vnet jails cannot have IP address restrictions");
goto done_errmsg;
}
#endif
error = vfs_getopt(opts, "osrelease", (void **)&osrelstr, &len);
if (error == ENOENT)
osrelstr = NULL;
else if (error != 0)
goto done_free;
else {
if (flags & JAIL_UPDATE) {
error = EINVAL;
vfs_opterror(opts,
"osrelease cannot be changed after creation");
goto done_errmsg;
}
if (len == 0 || osrelstr[len - 1] != '\0') {
error = EINVAL;
goto done_free;
}
if (len >= OSRELEASELEN) {
error = ENAMETOOLONG;
vfs_opterror(opts,
"osrelease string must be 1-%d bytes long",
OSRELEASELEN - 1);
goto done_errmsg;
}
}
error = vfs_copyopt(opts, "osreldate", &osreldt, sizeof(osreldt));
if (error == ENOENT)
osreldt = 0;
else if (error != 0)
goto done_free;
else {
if (flags & JAIL_UPDATE) {
error = EINVAL;
vfs_opterror(opts,
"osreldate cannot be changed after creation");
goto done_errmsg;
}
if (osreldt == 0) {
error = EINVAL;
vfs_opterror(opts, "osreldate cannot be 0");
goto done_errmsg;
}
}
root = NULL;
error = vfs_getopt(opts, "path", (void **)&path, &len);
if (error == ENOENT)
path = NULL;
else if (error != 0)
goto done_free;
else {
if (flags & JAIL_UPDATE) {
error = EINVAL;
vfs_opterror(opts,
"path cannot be changed after creation");
goto done_errmsg;
}
if (len == 0 || path[len - 1] != '\0') {
error = EINVAL;
goto done_free;
}
NDINIT(&nd, LOOKUP, FOLLOW | LOCKLEAF, UIO_SYSSPACE,
path, td);
error = namei(&nd);
if (error)
goto done_free;
root = nd.ni_vp;
NDFREE(&nd, NDF_ONLY_PNBUF);
g_path = malloc(MAXPATHLEN, M_TEMP, M_WAITOK);
strlcpy(g_path, path, MAXPATHLEN);
error = vn_path_to_global_path(td, root, g_path, MAXPATHLEN);
if (error == 0) {
path = g_path;
} else {
/* exit on other errors */
goto done_free;
}
if (root->v_type != VDIR) {
error = ENOTDIR;
vput(root);
goto done_free;
}
VOP_UNLOCK(root);
}
/*
* Find the specified jail, or at least its parent.
* This abuses the file error codes ENOENT and EEXIST.
*/
pr = NULL;
inspr = NULL;
if (cuflags == JAIL_CREATE && jid == 0 && name != NULL) {
namelc = strrchr(name, '.');
jid = strtoul(namelc != NULL ? namelc + 1 : name, &p, 10);
if (*p != '\0')
jid = 0;
}