forked from containers/bubblewrap
-
Notifications
You must be signed in to change notification settings - Fork 0
/
utils.c
893 lines (737 loc) · 16.8 KB
/
utils.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
/* bubblewrap
* Copyright (C) 2016 Alexander Larsson
* SPDX-License-Identifier: LGPL-2.0-or-later
*
* This program 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 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, see <http://www.gnu.org/licenses/>.
*
*/
#include "config.h"
#include "utils.h"
#include <sys/syscall.h>
#include <sys/socket.h>
#ifdef HAVE_SELINUX
#include <selinux/selinux.h>
#endif
#ifndef HAVE_SELINUX_2_3
/* libselinux older than 2.3 weren't const-correct */
#define setexeccon(x) setexeccon ((security_context_t) x)
#define setfscreatecon(x) setfscreatecon ((security_context_t) x)
#define security_check_context(x) security_check_context ((security_context_t) x)
#endif
__attribute__((format(printf, 1, 0))) static void
warnv (const char *format, va_list args)
{
fprintf (stderr, "bwrap: ");
vfprintf (stderr, format, args);
fprintf (stderr, "\n");
}
void
warn (const char *format, ...)
{
va_list args;
va_start (args, format);
warnv (format, args);
va_end (args);
}
void
die_with_error (const char *format, ...)
{
va_list args;
int errsv;
errsv = errno;
fprintf (stderr, "bwrap: ");
va_start (args, format);
vfprintf (stderr, format, args);
va_end (args);
fprintf (stderr, ": %s\n", strerror (errsv));
exit (1);
}
void
die (const char *format, ...)
{
va_list args;
va_start (args, format);
warnv (format, args);
va_end (args);
exit (1);
}
void
die_unless_label_valid (UNUSED const char *label)
{
#ifdef HAVE_SELINUX
if (is_selinux_enabled () == 1)
{
if (security_check_context (label) < 0)
die_with_error ("invalid label %s", label);
return;
}
#endif
die ("labeling not supported on this system");
}
void
die_oom (void)
{
fputs ("Out of memory\n", stderr);
exit (1);
}
/* Fork, return in child, exiting the previous parent */
void
fork_intermediate_child (void)
{
int pid = fork ();
if (pid == -1)
die_with_error ("Can't fork for --pidns");
/* Parent is an process not needed */
if (pid != 0)
exit (0);
}
void *
xmalloc (size_t size)
{
void *res = malloc (size);
if (res == NULL)
die_oom ();
return res;
}
void *
xcalloc (size_t size)
{
void *res = calloc (1, size);
if (res == NULL)
die_oom ();
return res;
}
void *
xrealloc (void *ptr, size_t size)
{
void *res = realloc (ptr, size);
if (size != 0 && res == NULL)
die_oom ();
return res;
}
char *
xstrdup (const char *str)
{
char *res;
assert (str != NULL);
res = strdup (str);
if (res == NULL)
die_oom ();
return res;
}
void
strfreev (char **str_array)
{
if (str_array)
{
int i;
for (i = 0; str_array[i] != NULL; i++)
free (str_array[i]);
free (str_array);
}
}
/* Compares if str has a specific path prefix. This differs
from a regular prefix in two ways. First of all there may
be multiple slashes separating the path elements, and
secondly, if a prefix is matched that has to be en entire
path element. For instance /a/prefix matches /a/prefix/foo/bar,
but not /a/prefixfoo/bar. */
bool
has_path_prefix (const char *str,
const char *prefix)
{
while (TRUE)
{
/* Skip consecutive slashes to reach next path
element */
while (*str == '/')
str++;
while (*prefix == '/')
prefix++;
/* No more prefix path elements? Done! */
if (*prefix == 0)
return TRUE;
/* Compare path element */
while (*prefix != 0 && *prefix != '/')
{
if (*str != *prefix)
return FALSE;
str++;
prefix++;
}
/* Matched prefix path element,
must be entire str path element */
if (*str != '/' && *str != 0)
return FALSE;
}
}
bool
path_equal (const char *path1,
const char *path2)
{
while (TRUE)
{
/* Skip consecutive slashes to reach next path
element */
while (*path1 == '/')
path1++;
while (*path2 == '/')
path2++;
/* No more prefix path elements? Done! */
if (*path1 == 0 || *path2 == 0)
return *path1 == 0 && *path2 == 0;
/* Compare path element */
while (*path1 != 0 && *path1 != '/')
{
if (*path1 != *path2)
return FALSE;
path1++;
path2++;
}
/* Matched path1 path element, must be entire path element */
if (*path2 != '/' && *path2 != 0)
return FALSE;
}
}
bool
has_prefix (const char *str,
const char *prefix)
{
return strncmp (str, prefix, strlen (prefix)) == 0;
}
void
xclearenv (void)
{
if (clearenv () != 0)
die_with_error ("clearenv failed");
}
void
xsetenv (const char *name, const char *value, int overwrite)
{
if (setenv (name, value, overwrite))
die ("setenv failed");
}
void
xunsetenv (const char *name)
{
if (unsetenv (name))
die ("unsetenv failed");
}
char *
strconcat (const char *s1,
const char *s2)
{
size_t len = 0;
char *res;
if (s1)
len += strlen (s1);
if (s2)
len += strlen (s2);
res = xmalloc (len + 1);
*res = 0;
if (s1)
strcat (res, s1);
if (s2)
strcat (res, s2);
return res;
}
char *
strconcat3 (const char *s1,
const char *s2,
const char *s3)
{
size_t len = 0;
char *res;
if (s1)
len += strlen (s1);
if (s2)
len += strlen (s2);
if (s3)
len += strlen (s3);
res = xmalloc (len + 1);
*res = 0;
if (s1)
strcat (res, s1);
if (s2)
strcat (res, s2);
if (s3)
strcat (res, s3);
return res;
}
char *
xasprintf (const char *format,
...)
{
char *buffer = NULL;
va_list args;
va_start (args, format);
if (vasprintf (&buffer, format, args) == -1)
die_oom ();
va_end (args);
return buffer;
}
int
fdwalk (int proc_fd, int (*cb)(void *data,
int fd), void *data)
{
int open_max;
int fd;
int dfd;
int res = 0;
DIR *d;
dfd = openat (proc_fd, "self/fd", O_DIRECTORY | O_RDONLY | O_NONBLOCK | O_CLOEXEC | O_NOCTTY);
if (dfd == -1)
return res;
if ((d = fdopendir (dfd)))
{
struct dirent *de;
while ((de = readdir (d)))
{
long l;
char *e = NULL;
if (de->d_name[0] == '.')
continue;
errno = 0;
l = strtol (de->d_name, &e, 10);
if (errno != 0 || !e || *e)
continue;
fd = (int) l;
if ((long) fd != l)
continue;
if (fd == dirfd (d))
continue;
if ((res = cb (data, fd)) != 0)
break;
}
closedir (d);
return res;
}
open_max = sysconf (_SC_OPEN_MAX);
for (fd = 0; fd < open_max; fd++)
if ((res = cb (data, fd)) != 0)
break;
return res;
}
/* Sets errno on error (!= 0), ENOSPC on short write */
int
write_to_fd (int fd,
const char *content,
ssize_t len)
{
ssize_t res;
while (len > 0)
{
res = write (fd, content, len);
if (res < 0 && errno == EINTR)
continue;
if (res <= 0)
{
if (res == 0) /* Unexpected short write, should not happen when writing to a file */
errno = ENOSPC;
return -1;
}
len -= res;
content += res;
}
return 0;
}
/* Sets errno on error (!= 0), ENOSPC on short write */
int
write_file_at (int dirfd,
const char *path,
const char *content)
{
int fd;
bool res;
int errsv;
fd = openat (dirfd, path, O_RDWR | O_CLOEXEC, 0);
if (fd == -1)
return -1;
res = 0;
if (content)
res = write_to_fd (fd, content, strlen (content));
errsv = errno;
close (fd);
errno = errsv;
return res;
}
/* Sets errno on error (!= 0), ENOSPC on short write */
int
create_file (const char *path,
mode_t mode,
const char *content)
{
int fd;
int res;
int errsv;
fd = creat (path, mode);
if (fd == -1)
return -1;
res = 0;
if (content)
res = write_to_fd (fd, content, strlen (content));
errsv = errno;
close (fd);
errno = errsv;
return res;
}
int
ensure_file (const char *path,
mode_t mode)
{
struct stat buf;
/* We check this ahead of time, otherwise
the create file will fail in the read-only
case with EROFS instead of EEXIST.
We're trying to set up a mount point for a non-directory, so any
non-directory, non-symlink is acceptable - it doesn't necessarily
have to be a regular file. */
if (stat (path, &buf) == 0 &&
!S_ISDIR (buf.st_mode) &&
!S_ISLNK (buf.st_mode))
return 0;
if (create_file (path, mode, NULL) != 0 && errno != EEXIST)
return -1;
return 0;
}
#define BUFSIZE 8192
/* Sets errno on error (!= 0), ENOSPC on short write */
int
copy_file_data (int sfd,
int dfd)
{
char buffer[BUFSIZE];
ssize_t bytes_read;
while (TRUE)
{
bytes_read = read (sfd, buffer, BUFSIZE);
if (bytes_read == -1)
{
if (errno == EINTR)
continue;
return -1;
}
if (bytes_read == 0)
break;
if (write_to_fd (dfd, buffer, bytes_read) != 0)
return -1;
}
return 0;
}
/* Sets errno on error (!= 0), ENOSPC on short write */
int
copy_file (const char *src_path,
const char *dst_path,
mode_t mode)
{
int sfd;
int dfd;
int res;
int errsv;
sfd = open (src_path, O_CLOEXEC | O_RDONLY);
if (sfd == -1)
return -1;
dfd = creat (dst_path, mode);
if (dfd == -1)
{
errsv = errno;
close (sfd);
errno = errsv;
return -1;
}
res = copy_file_data (sfd, dfd);
errsv = errno;
close (sfd);
close (dfd);
errno = errsv;
return res;
}
/* Sets errno on error (== NULL),
* Always ensures terminating zero */
char *
load_file_data (int fd,
size_t *size)
{
cleanup_free char *data = NULL;
ssize_t data_read;
ssize_t data_len;
ssize_t res;
data_read = 0;
data_len = 4080;
data = xmalloc (data_len);
do
{
if (data_len == data_read + 1)
{
data_len *= 2;
data = xrealloc (data, data_len);
}
do
res = read (fd, data + data_read, data_len - data_read - 1);
while (res < 0 && errno == EINTR);
if (res < 0)
return NULL;
data_read += res;
}
while (res > 0);
data[data_read] = 0;
if (size)
*size = (size_t) data_read;
return steal_pointer (&data);
}
/* Sets errno on error (== NULL),
* Always ensures terminating zero */
char *
load_file_at (int dirfd,
const char *path)
{
int fd;
char *data;
int errsv;
fd = openat (dirfd, path, O_CLOEXEC | O_RDONLY);
if (fd == -1)
return NULL;
data = load_file_data (fd, NULL);
errsv = errno;
close (fd);
errno = errsv;
return data;
}
/* Sets errno on error (< 0) */
int
get_file_mode (const char *pathname)
{
struct stat buf;
if (stat (pathname, &buf) != 0)
return -1;
return buf.st_mode & S_IFMT;
}
int
ensure_dir (const char *path,
mode_t mode)
{
struct stat buf;
/* We check this ahead of time, otherwise
the mkdir call can fail in the read-only
case with EROFS instead of EEXIST on some
filesystems (such as NFS) */
if (stat (path, &buf) == 0)
{
if (!S_ISDIR (buf.st_mode))
{
errno = ENOTDIR;
return -1;
}
return 0;
}
if (mkdir (path, mode) == -1 && errno != EEXIST)
return -1;
return 0;
}
/* Sets errno on error (!= 0) */
int
mkdir_with_parents (const char *pathname,
mode_t mode,
bool create_last)
{
cleanup_free char *fn = NULL;
char *p;
if (pathname == NULL || *pathname == '\0')
{
errno = EINVAL;
return -1;
}
fn = xstrdup (pathname);
p = fn;
while (*p == '/')
p++;
do
{
while (*p && *p != '/')
p++;
if (!*p)
p = NULL;
else
*p = '\0';
if (!create_last && p == NULL)
break;
if (ensure_dir (fn, mode) != 0)
return -1;
if (p)
{
*p++ = '/';
while (*p && *p == '/')
p++;
}
}
while (p);
return 0;
}
/* Send an ucred with current pid/uid/gid over a socket, it can be
read back with read_pid_from_socket(), and then the kernel has
translated it between namespaces as needed. */
void
send_pid_on_socket (int socket)
{
char buf[1] = { 0 };
struct msghdr msg = {};
struct iovec iov = { buf, sizeof (buf) };
const ssize_t control_len_snd = CMSG_SPACE(sizeof(struct ucred));
char control_buf_snd[control_len_snd];
struct cmsghdr *cmsg;
struct ucred *cred;
msg.msg_iov = &iov;
msg.msg_iovlen = 1;
msg.msg_control = control_buf_snd;
msg.msg_controllen = control_len_snd;
cmsg = CMSG_FIRSTHDR(&msg);
cmsg->cmsg_level = SOL_SOCKET;
cmsg->cmsg_type = SCM_CREDENTIALS;
cmsg->cmsg_len = CMSG_LEN(sizeof(struct ucred));
cred = (struct ucred *)CMSG_DATA(cmsg);
cred->pid = getpid ();
cred->uid = geteuid ();
cred->gid = getegid ();
if (sendmsg (socket, &msg, 0) < 0)
die_with_error ("Can't send pid");
}
void
create_pid_socketpair (int sockets[2])
{
int enable = 1;
if (socketpair (AF_UNIX, SOCK_SEQPACKET | SOCK_CLOEXEC, 0, sockets) != 0)
die_with_error ("Can't create intermediate pids socket");
if (setsockopt (sockets[0], SOL_SOCKET, SO_PASSCRED, &enable, sizeof (enable)) < 0)
die_with_error ("Can't set SO_PASSCRED");
}
int
read_pid_from_socket (int socket)
{
char recv_buf[1] = { 0 };
struct msghdr msg = {};
struct iovec iov = { recv_buf, sizeof (recv_buf) };
const ssize_t control_len_rcv = CMSG_SPACE(sizeof(struct ucred));
char control_buf_rcv[control_len_rcv];
struct cmsghdr* cmsg;
msg.msg_iov = &iov;
msg.msg_iovlen = 1;
msg.msg_control = control_buf_rcv;
msg.msg_controllen = control_len_rcv;
if (recvmsg (socket, &msg, 0) < 0)
die_with_error ("Can't read pid from socket");
if (msg.msg_controllen <= 0)
die ("Unexpected short read from pid socket");
for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg))
{
const unsigned payload_len = cmsg->cmsg_len - CMSG_LEN(0);
if (cmsg->cmsg_level == SOL_SOCKET &&
cmsg->cmsg_type == SCM_CREDENTIALS &&
payload_len == sizeof(struct ucred))
{
struct ucred *cred = (struct ucred *)CMSG_DATA(cmsg);
return cred->pid;
}
}
die ("No pid returned on socket");
}
/* Sets errno on error (== NULL),
* Always ensures terminating zero */
char *
readlink_malloc (const char *pathname)
{
size_t size = 50;
ssize_t n;
cleanup_free char *value = NULL;
do
{
size *= 2;
value = xrealloc (value, size);
n = readlink (pathname, value, size - 1);
if (n < 0)
return NULL;
}
while (size - 2 < (size_t)n);
value[n] = 0;
return steal_pointer (&value);
}
char *
get_oldroot_path (const char *path)
{
while (*path == '/')
path++;
return strconcat ("/oldroot/", path);
}
char *
get_newroot_path (const char *path)
{
while (*path == '/')
path++;
return strconcat ("/newroot/", path);
}
int
raw_clone (unsigned long flags,
void *child_stack)
{
#if defined(__s390__) || defined(__CRIS__)
/* On s390 and cris the order of the first and second arguments
* of the raw clone() system call is reversed. */
return (int) syscall (__NR_clone, child_stack, flags);
#else
return (int) syscall (__NR_clone, flags, child_stack);
#endif
}
int
pivot_root (const char * new_root, const char * put_old)
{
#ifdef __NR_pivot_root
return syscall (__NR_pivot_root, new_root, put_old);
#else
errno = ENOSYS;
return -1;
#endif
}
char *
label_mount (const char *opt, UNUSED const char *mount_label)
{
#ifdef HAVE_SELINUX
if (mount_label)
{
if (opt)
return xasprintf ("%s,context=\"%s\"", opt, mount_label);
else
return xasprintf ("context=\"%s\"", mount_label);
}
#endif
if (opt)
return xstrdup (opt);
return NULL;
}
int
label_create_file (UNUSED const char *file_label)
{
#ifdef HAVE_SELINUX
if (is_selinux_enabled () > 0 && file_label)
return setfscreatecon (file_label);
#endif
return 0;
}
int
label_exec (UNUSED const char *exec_label)
{
#ifdef HAVE_SELINUX
if (is_selinux_enabled () > 0 && exec_label)
return setexeccon (exec_label);
#endif
return 0;
}