summaryrefslogtreecommitdiff
path: root/src/core/namespace.c
blob: 4f29217bc4a342e8cf56b4e6dd7f478078b6f681 (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
/***
  This file is part of systemd.

  Copyright 2010 Lennart Poettering

  systemd 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.

  systemd 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 systemd; If not, see <http://www.gnu.org/licenses/>.
***/

#include <errno.h>
#include <sched.h>
#include <stdio.h>
#include <string.h>
#include <sys/mount.h>
#include <sys/stat.h>
#include <unistd.h>
#include <linux/fs.h>

#include "alloc-util.h"
#include "dev-setup.h"
#include "fd-util.h"
#include "fs-util.h"
#include "loop-util.h"
#include "loopback-setup.h"
#include "missing.h"
#include "mkdir.h"
#include "mount-util.h"
#include "namespace.h"
#include "path-util.h"
#include "selinux-util.h"
#include "socket-util.h"
#include "string-table.h"
#include "string-util.h"
#include "strv.h"
#include "umask-util.h"
#include "user-util.h"
#include "util.h"

#define DEV_MOUNT_OPTIONS (MS_NOSUID|MS_STRICTATIME|MS_NOEXEC)

typedef enum MountMode {
        /* This is ordered by priority! */
        INACCESSIBLE,
        BIND_MOUNT,
        BIND_MOUNT_RECURSIVE,
        PRIVATE_TMP,
        PRIVATE_VAR_TMP,
        PRIVATE_DEV,
        BIND_DEV,
        SYSFS,
        PROCFS,
        READONLY,
        READWRITE,
} MountMode;

typedef struct MountEntry {
        const char *path_const;   /* Memory allocated on stack or static */
        MountMode mode:5;
        bool ignore:1;            /* Ignore if path does not exist? */
        bool has_prefix:1;        /* Already is prefixed by the root dir? */
        bool read_only:1;         /* Shall this mount point be read-only? */
        char *path_malloc;        /* Use this instead of 'path' if we had to allocate memory */
        const char *source_const; /* The source path, for bind mounts */
        char *source_malloc;
} MountEntry;

/* If MountAPIVFS= is used, let's mount /sys and /proc into the it, but only as a fallback if the user hasn't mounted
 * something there already. These mounts are hence overriden by any other explicitly configured mounts. */
static const MountEntry apivfs_table[] = {
        { "/proc",               PROCFS,       false },
        { "/dev",                BIND_DEV,     false },
        { "/sys",                SYSFS,        false },
};

/* ProtectKernelTunables= option and the related filesystem APIs */
static const MountEntry protect_kernel_tunables_table[] = {
        { "/proc/sys",           READONLY,     false },
        { "/proc/sysrq-trigger", READONLY,     true  },
        { "/proc/latency_stats", READONLY,     true  },
        { "/proc/mtrr",          READONLY,     true  },
        { "/proc/apm",           READONLY,     true  }, /* Obsolete API, there's no point in permitting access to this, ever */
        { "/proc/acpi",          READONLY,     true  },
        { "/proc/timer_stats",   READONLY,     true  },
        { "/proc/asound",        READONLY,     true  },
        { "/proc/bus",           READONLY,     true  },
        { "/proc/fs",            READONLY,     true  },
        { "/proc/irq",           READONLY,     true  },
        { "/sys",                READONLY,     false },
        { "/sys/kernel/debug",   READONLY,     true  },
        { "/sys/kernel/tracing", READONLY,     true  },
        { "/sys/fs/cgroup",      READWRITE,    false }, /* READONLY is set by ProtectControlGroups= option */
};

/* ProtectKernelModules= option */
static const MountEntry protect_kernel_modules_table[] = {
#ifdef HAVE_SPLIT_USR
        { "/lib/modules",        INACCESSIBLE, true  },
#endif
        { "/usr/lib/modules",    INACCESSIBLE, true  },
};

/*
 * ProtectHome=read-only table, protect $HOME and $XDG_RUNTIME_DIR and rest of
 * system should be protected by ProtectSystem=
 */
static const MountEntry protect_home_read_only_table[] = {
        { "/home",               READONLY,     true  },
        { "/run/user",           READONLY,     true  },
        { "/root",               READONLY,     true  },
};

/* ProtectHome=yes table */
static const MountEntry protect_home_yes_table[] = {
        { "/home",               INACCESSIBLE, true  },
        { "/run/user",           INACCESSIBLE, true  },
        { "/root",               INACCESSIBLE, true  },
};

/* ProtectSystem=yes table */
static const MountEntry protect_system_yes_table[] = {
        { "/usr",                READONLY,     false },
        { "/boot",               READONLY,     true  },
        { "/efi",                READONLY,     true  },
};

/* ProtectSystem=full includes ProtectSystem=yes */
static const MountEntry protect_system_full_table[] = {
        { "/usr",                READONLY,     false },
        { "/boot",               READONLY,     true  },
        { "/efi",                READONLY,     true  },
        { "/etc",                READONLY,     false },
};

/*
 * ProtectSystem=strict table. In this strict mode, we mount everything
 * read-only, except for /proc, /dev, /sys which are the kernel API VFS,
 * which are left writable, but PrivateDevices= + ProtectKernelTunables=
 * protect those, and these options should be fully orthogonal.
 * (And of course /home and friends are also left writable, as ProtectHome=
 * shall manage those, orthogonally).
 */
static const MountEntry protect_system_strict_table[] = {
        { "/",                   READONLY,     false },
        { "/proc",               READWRITE,    false },      /* ProtectKernelTunables= */
        { "/sys",                READWRITE,    false },      /* ProtectKernelTunables= */
        { "/dev",                READWRITE,    false },      /* PrivateDevices= */
        { "/home",               READWRITE,    true  },      /* ProtectHome= */
        { "/run/user",           READWRITE,    true  },      /* ProtectHome= */
        { "/root",               READWRITE,    true  },      /* ProtectHome= */
};

static const char *mount_entry_path(const MountEntry *p) {
        assert(p);

        /* Returns the path of this bind mount. If the malloc()-allocated ->path_buffer field is set we return that,
         * otherwise the stack/static ->path field is returned. */

        return p->path_malloc ?: p->path_const;
}

static bool mount_entry_read_only(const MountEntry *p) {
        assert(p);

        return p->read_only || IN_SET(p->mode, READONLY, INACCESSIBLE);
}

static const char *mount_entry_source(const MountEntry *p) {
        assert(p);

        return p->source_malloc ?: p->source_const;
}

static void mount_entry_done(MountEntry *p) {
        assert(p);

        p->path_malloc = mfree(p->path_malloc);
        p->source_malloc = mfree(p->source_malloc);
}

static int append_access_mounts(MountEntry **p, char **strv, MountMode mode) {
        char **i;

        assert(p);

        /* Adds a list of user-supplied READWRITE/READONLY/INACCESSIBLE entries */

        STRV_FOREACH(i, strv) {
                bool ignore = false, needs_prefix = false;
                const char *e = *i;

                /* Look for any prefixes */
                if (startswith(e, "-")) {
                        e++;
                        ignore = true;
                }
                if (startswith(e, "+")) {
                        e++;
                        needs_prefix = true;
                }

                if (!path_is_absolute(e))
                        return -EINVAL;

                *((*p)++) = (MountEntry) {
                        .path_const = e,
                        .mode = mode,
                        .ignore = ignore,
                        .has_prefix = !needs_prefix,
                };
        }

        return 0;
}

static int append_bind_mounts(MountEntry **p, const BindMount *binds, unsigned n) {
        unsigned i;

        assert(p);

        for (i = 0; i < n; i++) {
                const BindMount *b = binds + i;

                *((*p)++) = (MountEntry) {
                        .path_const = b->destination,
                        .mode = b->recursive ? BIND_MOUNT_RECURSIVE : BIND_MOUNT,
                        .read_only = b->read_only,
                        .source_const = b->source,
                };
        }

        return 0;
}

static int append_static_mounts(MountEntry **p, const MountEntry *mounts, unsigned n, bool ignore_protect) {
        unsigned i;

        assert(p);
        assert(mounts);

        /* Adds a list of static pre-defined entries */

        for (i = 0; i < n; i++)
                *((*p)++) = (MountEntry) {
                        .path_const = mount_entry_path(mounts+i),
                        .mode = mounts[i].mode,
                        .ignore = mounts[i].ignore || ignore_protect,
                };

        return 0;
}

static int append_protect_home(MountEntry **p, ProtectHome protect_home, bool ignore_protect) {
        assert(p);

        switch (protect_home) {

        case PROTECT_HOME_NO:
                return 0;

        case PROTECT_HOME_READ_ONLY:
                return append_static_mounts(p, protect_home_read_only_table, ELEMENTSOF(protect_home_read_only_table), ignore_protect);

        case PROTECT_HOME_YES:
                return append_static_mounts(p, protect_home_yes_table, ELEMENTSOF(protect_home_yes_table), ignore_protect);

        default:
                assert_not_reached("Unexpected ProtectHome= value");
        }
}

static int append_protect_system(MountEntry **p, ProtectSystem protect_system, bool ignore_protect) {
        assert(p);

        switch (protect_system) {

        case PROTECT_SYSTEM_NO:
                return 0;

        case PROTECT_SYSTEM_STRICT:
                return append_static_mounts(p, protect_system_strict_table, ELEMENTSOF(protect_system_strict_table), ignore_protect);

        case PROTECT_SYSTEM_YES:
                return append_static_mounts(p, protect_system_yes_table, ELEMENTSOF(protect_system_yes_table), ignore_protect);

        case PROTECT_SYSTEM_FULL:
                return append_static_mounts(p, protect_system_full_table, ELEMENTSOF(protect_system_full_table), ignore_protect);

        default:
                assert_not_reached("Unexpected ProtectSystem= value");
        }
}

static int mount_path_compare(const void *a, const void *b) {
        const MountEntry *p = a, *q = b;
        int d;

        /* If the paths are not equal, then order prefixes first */
        d = path_compare(mount_entry_path(p), mount_entry_path(q));
        if (d != 0)
                return d;

        /* If the paths are equal, check the mode */
        if (p->mode < q->mode)
                return -1;

        if (p->mode > q->mode)
                return 1;

        return 0;
}

static int prefix_where_needed(MountEntry *m, unsigned n, const char *root_directory) {
        unsigned i;

        /* Prefixes all paths in the bind mount table with the root directory if it is specified and the entry needs
         * that. */

        if (!root_directory)
                return 0;

        for (i = 0; i < n; i++) {
                char *s;

                if (m[i].has_prefix)
                        continue;

                s = prefix_root(root_directory, mount_entry_path(m+i));
                if (!s)
                        return -ENOMEM;

                free(m[i].path_malloc);
                m[i].path_malloc = s;

                m[i].has_prefix = true;
        }

        return 0;
}

static void drop_duplicates(MountEntry *m, unsigned *n) {
        MountEntry *f, *t, *previous;

        assert(m);
        assert(n);

        /* Drops duplicate entries. Expects that the array is properly ordered already. */

        for (f = m, t = m, previous = NULL; f < m + *n; f++) {

                /* The first one wins (which is the one with the more restrictive mode), see mount_path_compare()
                 * above. */
                if (previous && path_equal(mount_entry_path(f), mount_entry_path(previous))) {
                        log_debug("%s is duplicate.", mount_entry_path(f));
                        previous->read_only = previous->read_only || mount_entry_read_only(f); /* Propagate the read-only flag to the remaining entry */
                        mount_entry_done(f);
                        continue;
                }

                *t = *f;
                previous = t;
                t++;
        }

        *n = t - m;
}

static void drop_inaccessible(MountEntry *m, unsigned *n) {
        MountEntry *f, *t;
        const char *clear = NULL;

        assert(m);
        assert(n);

        /* Drops all entries obstructed by another entry further up the tree. Expects that the array is properly
         * ordered already. */

        for (f = m, t = m; f < m + *n; f++) {

                /* If we found a path set for INACCESSIBLE earlier, and this entry has it as prefix we should drop
                 * it, as inaccessible paths really should drop the entire subtree. */
                if (clear && path_startswith(mount_entry_path(f), clear)) {
                        log_debug("%s is masked by %s.", mount_entry_path(f), clear);
                        mount_entry_done(f);
                        continue;
                }

                clear = f->mode == INACCESSIBLE ? mount_entry_path(f) : NULL;

                *t = *f;
                t++;
        }

        *n = t - m;
}

static void drop_nop(MountEntry *m, unsigned *n) {
        MountEntry *f, *t;

        assert(m);
        assert(n);

        /* Drops all entries which have an immediate parent that has the same type, as they are redundant. Assumes the
         * list is ordered by prefixes. */

        for (f = m, t = m; f < m + *n; f++) {

                /* Only suppress such subtrees for READONLY and READWRITE entries */
                if (IN_SET(f->mode, READONLY, READWRITE)) {
                        MountEntry *p;
                        bool found = false;

                        /* Now let's find the first parent of the entry we are looking at. */
                        for (p = t-1; p >= m; p--) {
                                if (path_startswith(mount_entry_path(f), mount_entry_path(p))) {
                                        found = true;
                                        break;
                                }
                        }

                        /* We found it, let's see if it's the same mode, if so, we can drop this entry */
                        if (found && p->mode == f->mode) {
                                log_debug("%s is redundant by %s", mount_entry_path(f), mount_entry_path(p));
                                mount_entry_done(f);
                                continue;
                        }
                }

                *t = *f;
                t++;
        }

        *n = t - m;
}

static void drop_outside_root(const char *root_directory, MountEntry *m, unsigned *n) {
        MountEntry *f, *t;

        assert(m);
        assert(n);

        /* Nothing to do */
        if (!root_directory)
                return;

        /* Drops all mounts that are outside of the root directory. */

        for (f = m, t = m; f < m + *n; f++) {

                if (!path_startswith(mount_entry_path(f), root_directory)) {
                        log_debug("%s is outside of root directory.", mount_entry_path(f));
                        mount_entry_done(f);
                        continue;
                }

                *t = *f;
                t++;
        }

        *n = t - m;
}

static int mount_private_dev(MountEntry *m) {
        static const char devnodes[] =
                "/dev/null\0"
                "/dev/zero\0"
                "/dev/full\0"
                "/dev/random\0"
                "/dev/urandom\0"
                "/dev/tty\0";

        char temporary_mount[] = "/tmp/namespace-dev-XXXXXX";
        const char *d, *dev = NULL, *devpts = NULL, *devshm = NULL, *devhugepages = NULL, *devmqueue = NULL, *devlog = NULL, *devptmx = NULL;
        _cleanup_umask_ mode_t u;
        int r;

        assert(m);

        u = umask(0000);

        if (!mkdtemp(temporary_mount))
                return -errno;

        dev = strjoina(temporary_mount, "/dev");
        (void) mkdir(dev, 0755);
        if (mount("tmpfs", dev, "tmpfs", DEV_MOUNT_OPTIONS, "mode=755") < 0) {
                r = -errno;
                goto fail;
        }

        devpts = strjoina(temporary_mount, "/dev/pts");
        (void) mkdir(devpts, 0755);
        if (mount("/dev/pts", devpts, NULL, MS_BIND, NULL) < 0) {
                r = -errno;
                goto fail;
        }

        devptmx = strjoina(temporary_mount, "/dev/ptmx");
        if (symlink("pts/ptmx", devptmx) < 0) {
                r = -errno;
                goto fail;
        }

        devshm = strjoina(temporary_mount, "/dev/shm");
        (void) mkdir(devshm, 01777);
        r = mount("/dev/shm", devshm, NULL, MS_BIND, NULL);
        if (r < 0) {
                r = -errno;
                goto fail;
        }

        devmqueue = strjoina(temporary_mount, "/dev/mqueue");
        (void) mkdir(devmqueue, 0755);
        (void) mount("/dev/mqueue", devmqueue, NULL, MS_BIND, NULL);

        devhugepages = strjoina(temporary_mount, "/dev/hugepages");
        (void) mkdir(devhugepages, 0755);
        (void) mount("/dev/hugepages", devhugepages, NULL, MS_BIND, NULL);

        devlog = strjoina(temporary_mount, "/dev/log");
        (void) symlink("/run/systemd/journal/dev-log", devlog);

        NULSTR_FOREACH(d, devnodes) {
                _cleanup_free_ char *dn = NULL;
                struct stat st;

                r = stat(d, &st);
                if (r < 0) {

                        if (errno == ENOENT)
                                continue;

                        r = -errno;
                        goto fail;
                }

                if (!S_ISBLK(st.st_mode) &&
                    !S_ISCHR(st.st_mode)) {
                        r = -EINVAL;
                        goto fail;
                }

                if (st.st_rdev == 0)
                        continue;

                dn = strappend(temporary_mount, d);
                if (!dn) {
                        r = -ENOMEM;
                        goto fail;
                }

                mac_selinux_create_file_prepare(d, st.st_mode);
                r = mknod(dn, st.st_mode, st.st_rdev);
                mac_selinux_create_file_clear();

                if (r < 0) {
                        r = -errno;
                        goto fail;
                }
        }

        dev_setup(temporary_mount, UID_INVALID, GID_INVALID);

        /* Create the /dev directory if missing. It is more likely to be
         * missing when the service is started with RootDirectory. This is
         * consistent with mount units creating the mount points when missing.
         */
        (void) mkdir_p_label(mount_entry_path(m), 0755);

        /* Unmount everything in old /dev */
        umount_recursive(mount_entry_path(m), 0);
        if (mount(dev, mount_entry_path(m), NULL, MS_MOVE, NULL) < 0) {
                r = -errno;
                goto fail;
        }

        rmdir(dev);
        rmdir(temporary_mount);

        return 0;

fail:
        if (devpts)
                umount(devpts);

        if (devshm)
                umount(devshm);

        if (devhugepages)
                umount(devhugepages);

        if (devmqueue)
                umount(devmqueue);

        umount(dev);
        rmdir(dev);
        rmdir(temporary_mount);

        return r;
}

static int mount_bind_dev(MountEntry *m) {
        int r;

        assert(m);

        /* Implements the little brother of mount_private_dev(): simply bind mounts the host's /dev into the service's
         * /dev. This is only used when RootDirectory= is set. */

        r = path_is_mount_point(mount_entry_path(m), NULL, 0);
        if (r < 0)
                return log_debug_errno(r, "Unable to determine whether /dev is already mounted: %m");
        if (r > 0) /* make this a NOP if /dev is already a mount point */
                return 0;

        if (mount("/dev", mount_entry_path(m), NULL, MS_BIND|MS_REC, NULL) < 0)
                return log_debug_errno(errno, "Failed to bind mount %s: %m", mount_entry_path(m));

        return 1;
}

static int mount_sysfs(MountEntry *m) {
        int r;

        assert(m);

        r = path_is_mount_point(mount_entry_path(m), NULL, 0);
        if (r < 0)
                return log_debug_errno(r, "Unable to determine whether /sys is already mounted: %m");
        if (r > 0) /* make this a NOP if /sys is already a mount point */
                return 0;

        /* Bind mount the host's version so that we get all child mounts of it, too. */
        if (mount("/sys", mount_entry_path(m), NULL, MS_BIND|MS_REC, NULL) < 0)
                return log_debug_errno(errno, "Failed to mount %s: %m", mount_entry_path(m));

        return 1;
}

static int mount_procfs(MountEntry *m) {
        int r;

        assert(m);

        r = path_is_mount_point(mount_entry_path(m), NULL, 0);
        if (r < 0)
                return log_debug_errno(r, "Unable to determine whether /proc is already mounted: %m");
        if (r > 0) /* make this a NOP if /proc is already a mount point */
                return 0;

        /* Mount a new instance, so that we get the one that matches our user namespace, if we are running in one */
        if (mount("proc", mount_entry_path(m), "proc", MS_NOSUID|MS_NOEXEC|MS_NODEV, NULL) < 0)
                return log_debug_errno(errno, "Failed to mount %s: %m", mount_entry_path(m));

        return 1;
}

static int mount_entry_chase(
                const char *root_directory,
                MountEntry *m,
                const char *path,
                char **location) {

        char *chased;
        int r;

        assert(m);

        /* Since mount() will always follow symlinks and we need to take the different root directory into account we
         * chase the symlinks on our own first. This is called for the destination path, as well as the source path (if
         * that applies). The result is stored in "location". */

        r = chase_symlinks(path, root_directory, 0, &chased);
        if (r == -ENOENT && m->ignore) {
                log_debug_errno(r, "Path %s does not exist, ignoring.", path);
                return 0;
        }
        if (r < 0)
                return log_debug_errno(r, "Failed to follow symlinks on %s: %m", path);

        log_debug("Followed symlinks %s → %s.", path, chased);

        free(*location);
        *location = chased;

        return 1;
}

static int apply_mount(
                const char *root_directory,
                MountEntry *m,
                const char *tmp_dir,
                const char *var_tmp_dir) {

        const char *what;
        bool rbind = true;
        int r;

        assert(m);

        r = mount_entry_chase(root_directory, m, mount_entry_path(m), &m->path_malloc);
        if (r <= 0)
                return r;

        log_debug("Applying namespace mount on %s", mount_entry_path(m));

        switch (m->mode) {

        case INACCESSIBLE: {
                struct stat target;

                /* First, get rid of everything that is below if there
                 * is anything... Then, overmount it with an
                 * inaccessible path. */
                (void) umount_recursive(mount_entry_path(m), 0);

                if (lstat(mount_entry_path(m), &target) < 0)
                        return log_debug_errno(errno, "Failed to lstat() %s to determine what to mount over it: %m", mount_entry_path(m));

                what = mode_to_inaccessible_node(target.st_mode);
                if (!what) {
                        log_debug("File type not supported for inaccessible mounts. Note that symlinks are not allowed");
                        return -ELOOP;
                }
                break;
        }

        case READONLY:
        case READWRITE:
                r = path_is_mount_point(mount_entry_path(m), root_directory, 0);
                if (r < 0)
                        return log_debug_errno(r, "Failed to determine whether %s is already a mount point: %m", mount_entry_path(m));
                if (r > 0) /* Nothing to do here, it is already a mount. We just later toggle the MS_RDONLY bit for the mount point if needed. */
                        return 0;
                /* This isn't a mount point yet, let's make it one. */
                what = mount_entry_path(m);
                break;

        case BIND_MOUNT:
                rbind = false;
                /* fallthrough */

        case BIND_MOUNT_RECURSIVE:
                /* Also chase the source mount */

                r = mount_entry_chase(root_directory, m, mount_entry_source(m), &m->source_malloc);
                if (r <= 0)
                        return r;

                what = mount_entry_source(m);
                break;

        case PRIVATE_TMP:
                what = tmp_dir;
                break;

        case PRIVATE_VAR_TMP:
                what = var_tmp_dir;
                break;

        case PRIVATE_DEV:
                return mount_private_dev(m);

        case BIND_DEV:
                return mount_bind_dev(m);

        case SYSFS:
                return mount_sysfs(m);

        case PROCFS:
                return mount_procfs(m);

        default:
                assert_not_reached("Unknown mode");
        }

        assert(what);

        if (mount(what, mount_entry_path(m), NULL, MS_BIND|(rbind ? MS_REC : 0), NULL) < 0)
                return log_debug_errno(errno, "Failed to mount %s to %s: %m", what, mount_entry_path(m));

        log_debug("Successfully mounted %s to %s", what, mount_entry_path(m));
        return 0;
}

static int make_read_only(MountEntry *m, char **blacklist) {
        int r = 0;

        assert(m);

        if (mount_entry_read_only(m))
                r = bind_remount_recursive(mount_entry_path(m), true, blacklist);
        else if (m->mode == PRIVATE_DEV) { /* Superblock can be readonly but the submounts can't */
                if (mount(NULL, mount_entry_path(m), NULL, MS_REMOUNT|DEV_MOUNT_OPTIONS|MS_RDONLY, NULL) < 0)
                        r = -errno;
        } else
                return 0;

        /* Not that we only turn on the MS_RDONLY flag here, we never turn it off. Something that was marked read-only
         * already stays this way. This improves compatibility with container managers, where we won't attempt to undo
         * read-only mounts already applied. */

        if (r == -ENOENT && m->ignore)
                r = 0;

        return r;
}

static bool namespace_info_mount_apivfs(const NameSpaceInfo *ns_info) {
        assert(ns_info);

        /* ProtectControlGroups= and ProtectKernelTunables= imply MountAPIVFS=, since to protect the API VFS mounts,
         * they need to be around in the first place... */

        return ns_info->mount_apivfs ||
                ns_info->protect_control_groups ||
                ns_info->protect_kernel_tunables;
}

static unsigned namespace_calculate_mounts(
                const NameSpaceInfo *ns_info,
                char** read_write_paths,
                char** read_only_paths,
                char** inaccessible_paths,
                const BindMount *bind_mounts,
                unsigned n_bind_mounts,
                const char* tmp_dir,
                const char* var_tmp_dir,
                ProtectHome protect_home,
                ProtectSystem protect_system) {

        unsigned protect_home_cnt;
        unsigned protect_system_cnt =
                (protect_system == PROTECT_SYSTEM_STRICT ?
                 ELEMENTSOF(protect_system_strict_table) :
                 ((protect_system == PROTECT_SYSTEM_FULL) ?
                  ELEMENTSOF(protect_system_full_table) :
                  ((protect_system == PROTECT_SYSTEM_YES) ?
                   ELEMENTSOF(protect_system_yes_table) : 0)));

        protect_home_cnt =
                (protect_home == PROTECT_HOME_YES ?
                 ELEMENTSOF(protect_home_yes_table) :
                 ((protect_home == PROTECT_HOME_READ_ONLY) ?
                  ELEMENTSOF(protect_home_read_only_table) : 0));

        return !!tmp_dir + !!var_tmp_dir +
                strv_length(read_write_paths) +
                strv_length(read_only_paths) +
                strv_length(inaccessible_paths) +
                n_bind_mounts +
                ns_info->private_dev +
                (ns_info->protect_kernel_tunables ? ELEMENTSOF(protect_kernel_tunables_table) : 0) +
                (ns_info->protect_control_groups ? 1 : 0) +
                (ns_info->protect_kernel_modules ? ELEMENTSOF(protect_kernel_modules_table) : 0) +
                protect_home_cnt + protect_system_cnt +
                (namespace_info_mount_apivfs(ns_info) ? ELEMENTSOF(apivfs_table) : 0);
}

int setup_namespace(
                const char* root_directory,
                const char* root_image,
                const NameSpaceInfo *ns_info,
                char** read_write_paths,
                char** read_only_paths,
                char** inaccessible_paths,
                const BindMount *bind_mounts,
                unsigned n_bind_mounts,
                const char* tmp_dir,
                const char* var_tmp_dir,
                ProtectHome protect_home,
                ProtectSystem protect_system,
                unsigned long mount_flags,
                DissectImageFlags dissect_image_flags) {

        _cleanup_(loop_device_unrefp) LoopDevice *loop_device = NULL;
        _cleanup_(decrypted_image_unrefp) DecryptedImage *decrypted_image = NULL;
        _cleanup_(dissected_image_unrefp) DissectedImage *dissected_image = NULL;
        _cleanup_free_ void *root_hash = NULL;
        MountEntry *m, *mounts = NULL;
        size_t root_hash_size = 0;
        bool make_slave = false;
        unsigned n_mounts;
        int r = 0;

        assert(ns_info);

        if (mount_flags == 0)
                mount_flags = MS_SHARED;

        if (root_image) {
                dissect_image_flags |= DISSECT_IMAGE_REQUIRE_ROOT;

                if (protect_system == PROTECT_SYSTEM_STRICT && strv_isempty(read_write_paths))
                        dissect_image_flags |= DISSECT_IMAGE_READ_ONLY;

                r = loop_device_make_by_path(root_image,
                                             dissect_image_flags & DISSECT_IMAGE_READ_ONLY ? O_RDONLY : O_RDWR,
                                             &loop_device);
                if (r < 0)
                        return r;

                r = root_hash_load(root_image, &root_hash, &root_hash_size);
                if (r < 0)
                        return r;

                r = dissect_image(loop_device->fd, root_hash, root_hash_size, dissect_image_flags, &dissected_image);
                if (r < 0)
                        return r;

                r = dissected_image_decrypt(dissected_image, NULL, root_hash, root_hash_size, dissect_image_flags, &decrypted_image);
                if (r < 0)
                        return r;

                if (!root_directory) {
                        /* Create a mount point for the image, if it's still missing. We use the same mount point for
                         * all images, which is safe, since they all live in their own namespaces after all, and hence
                         * won't see each other. */
                        root_directory = "/run/systemd/unit-root";
                        (void) mkdir(root_directory, 0700);
                }
        }

        n_mounts = namespace_calculate_mounts(
                        ns_info,
                        read_write_paths,
                        read_only_paths,
                        inaccessible_paths,
                        bind_mounts, n_bind_mounts,
                        tmp_dir, var_tmp_dir,
                        protect_home, protect_system);

        /* Set mount slave mode */
        if (root_directory || n_mounts > 0)
                make_slave = true;

        if (n_mounts > 0) {
                m = mounts = (MountEntry *) alloca0(n_mounts * sizeof(MountEntry));
                r = append_access_mounts(&m, read_write_paths, READWRITE);
                if (r < 0)
                        goto finish;

                r = append_access_mounts(&m, read_only_paths, READONLY);
                if (r < 0)
                        goto finish;

                r = append_access_mounts(&m, inaccessible_paths, INACCESSIBLE);
                if (r < 0)
                        goto finish;

                r = append_bind_mounts(&m, bind_mounts, n_bind_mounts);
                if (r < 0)
                        goto finish;

                if (tmp_dir) {
                        *(m++) = (MountEntry) {
                                .path_const = "/tmp",
                                .mode = PRIVATE_TMP,
                        };
                }

                if (var_tmp_dir) {
                        *(m++) = (MountEntry) {
                                .path_const = "/var/tmp",
                                .mode = PRIVATE_VAR_TMP,
                        };
                }

                if (ns_info->private_dev) {
                        *(m++) = (MountEntry) {
                                .path_const = "/dev",
                                .mode = PRIVATE_DEV,
                        };
                }

                if (ns_info->protect_kernel_tunables) {
                        r = append_static_mounts(&m, protect_kernel_tunables_table, ELEMENTSOF(protect_kernel_tunables_table), ns_info->ignore_protect_paths);
                        if (r < 0)
                                goto finish;
                }

                if (ns_info->protect_kernel_modules) {
                        r = append_static_mounts(&m, protect_kernel_modules_table, ELEMENTSOF(protect_kernel_modules_table), ns_info->ignore_protect_paths);
                        if (r < 0)
                                goto finish;
                }

                if (ns_info->protect_control_groups) {
                        *(m++) = (MountEntry) {
                                .path_const = "/sys/fs/cgroup",
                                .mode = READONLY,
                        };
                }

                r = append_protect_home(&m, protect_home, ns_info->ignore_protect_paths);
                if (r < 0)
                        goto finish;

                r = append_protect_system(&m, protect_system, false);
                if (r < 0)
                        goto finish;

                if (namespace_info_mount_apivfs(ns_info)) {
                        r = append_static_mounts(&m, apivfs_table, ELEMENTSOF(apivfs_table), ns_info->ignore_protect_paths);
                        if (r < 0)
                                goto finish;
                }

                assert(mounts + n_mounts == m);

                /* Prepend the root directory where that's necessary */
                r = prefix_where_needed(mounts, n_mounts, root_directory);
                if (r < 0)
                        goto finish;

                qsort(mounts, n_mounts, sizeof(MountEntry), mount_path_compare);

                drop_duplicates(mounts, &n_mounts);
                drop_outside_root(root_directory, mounts, &n_mounts);
                drop_inaccessible(mounts, &n_mounts);
                drop_nop(mounts, &n_mounts);
        }

        if (unshare(CLONE_NEWNS) < 0) {
                r = -errno;
                goto finish;
        }

        if (make_slave) {
                /* Remount / as SLAVE so that nothing now mounted in the namespace
                   shows up in the parent */
                if (mount(NULL, "/", NULL, MS_SLAVE|MS_REC, NULL) < 0) {
                        r = -errno;
                        goto finish;
                }
        }

        if (root_image) {
                r = dissected_image_mount(dissected_image, root_directory, dissect_image_flags);
                if (r < 0)
                        goto finish;

                r = decrypted_image_relinquish(decrypted_image);
                if (r < 0)
                        goto finish;

                loop_device_relinquish(loop_device);

        } else if (root_directory) {

                /* Turn directory into bind mount, if it isn't one yet */
                r = path_is_mount_point(root_directory, NULL, AT_SYMLINK_FOLLOW);
                if (r < 0)
                        goto finish;
                if (r == 0) {
                        if (mount(root_directory, root_directory, NULL, MS_BIND|MS_REC, NULL) < 0) {
                                r = -errno;
                                goto finish;
                        }
                }
        }

        if (n_mounts > 0) {
                char **blacklist;
                unsigned j;

                /* First round, add in all special mounts we need */
                for (m = mounts; m < mounts + n_mounts; ++m) {
                        r = apply_mount(root_directory, m, tmp_dir, var_tmp_dir);
                        if (r < 0)
                                goto finish;
                }

                /* Create a blacklist we can pass to bind_mount_recursive() */
                blacklist = newa(char*, n_mounts+1);
                for (j = 0; j < n_mounts; j++)
                        blacklist[j] = (char*) mount_entry_path(mounts+j);
                blacklist[j] = NULL;

                /* Second round, flip the ro bits if necessary. */
                for (m = mounts; m < mounts + n_mounts; ++m) {
                        r = make_read_only(m, blacklist);
                        if (r < 0)
                                goto finish;
                }
        }

        if (root_directory) {
                /* MS_MOVE does not work on MS_SHARED so the remount MS_SHARED will be done later */
                r = mount_move_root(root_directory);
                if (r < 0)
                        goto finish;
        }

        /* Remount / as the desired mode. Not that this will not
         * reestablish propagation from our side to the host, since
         * what's disconnected is disconnected. */
        if (mount(NULL, "/", NULL, mount_flags | MS_REC, NULL) < 0) {
                r = -errno;
                goto finish;
        }

        r = 0;

finish:
        for (m = mounts; m < mounts + n_mounts; m++)
                mount_entry_done(m);

        return r;
}

void bind_mount_free_many(BindMount *b, unsigned n) {
        unsigned i;

        assert(b || n == 0);

        for (i = 0; i < n; i++) {
                free(b[i].source);
                free(b[i].destination);
        }

        free(b);
}

int bind_mount_add(BindMount **b, unsigned *n, const BindMount *item) {
        _cleanup_free_ char *s = NULL, *d = NULL;
        BindMount *c;

        assert(b);
        assert(n);
        assert(item);

        s = strdup(item->source);
        if (!s)
                return -ENOMEM;

        d = strdup(item->destination);
        if (!d)
                return -ENOMEM;

        c = realloc_multiply(*b, sizeof(BindMount), *n + 1);
        if (!c)
                return -ENOMEM;

        *b = c;

        c[(*n) ++] = (BindMount) {
                .source = s,
                .destination = d,
                .read_only = item->read_only,
                .recursive = item->recursive,
                .ignore_enoent = item->ignore_enoent,
        };

        s = d = NULL;
        return 0;
}

static int setup_one_tmp_dir(const char *id, const char *prefix, char **path) {
        _cleanup_free_ char *x = NULL;
        char bid[SD_ID128_STRING_MAX];
        sd_id128_t boot_id;
        int r;

        assert(id);
        assert(prefix);
        assert(path);

        /* We include the boot id in the directory so that after a
         * reboot we can easily identify obsolete directories. */

        r = sd_id128_get_boot(&boot_id);
        if (r < 0)
                return r;

        x = strjoin(prefix, "/systemd-private-", sd_id128_to_string(boot_id, bid), "-", id, "-XXXXXX");
        if (!x)
                return -ENOMEM;

        RUN_WITH_UMASK(0077)
                if (!mkdtemp(x))
                        return -errno;

        RUN_WITH_UMASK(0000) {
                char *y;

                y = strjoina(x, "/tmp");

                if (mkdir(y, 0777 | S_ISVTX) < 0)
                        return -errno;
        }

        *path = x;
        x = NULL;

        return 0;
}

int setup_tmp_dirs(const char *id, char **tmp_dir, char **var_tmp_dir) {
        char *a, *b;
        int r;

        assert(id);
        assert(tmp_dir);
        assert(var_tmp_dir);

        r = setup_one_tmp_dir(id, "/tmp", &a);
        if (r < 0)
                return r;

        r = setup_one_tmp_dir(id, "/var/tmp", &b);
        if (r < 0) {
                char *t;

                t = strjoina(a, "/tmp");
                rmdir(t);
                rmdir(a);

                free(a);
                return r;
        }

        *tmp_dir = a;
        *var_tmp_dir = b;

        return 0;
}

int setup_netns(int netns_storage_socket[2]) {
        _cleanup_close_ int netns = -1;
        int r, q;

        assert(netns_storage_socket);
        assert(netns_storage_socket[0] >= 0);
        assert(netns_storage_socket[1] >= 0);

        /* We use the passed socketpair as a storage buffer for our
         * namespace reference fd. Whatever process runs this first
         * shall create a new namespace, all others should just join
         * it. To serialize that we use a file lock on the socket
         * pair.
         *
         * It's a bit crazy, but hey, works great! */

        if (lockf(netns_storage_socket[0], F_LOCK, 0) < 0)
                return -errno;

        netns = receive_one_fd(netns_storage_socket[0], MSG_DONTWAIT);
        if (netns == -EAGAIN) {
                /* Nothing stored yet, so let's create a new namespace */

                if (unshare(CLONE_NEWNET) < 0) {
                        r = -errno;
                        goto fail;
                }

                loopback_setup();

                netns = open("/proc/self/ns/net", O_RDONLY|O_CLOEXEC|O_NOCTTY);
                if (netns < 0) {
                        r = -errno;
                        goto fail;
                }

                r = 1;

        } else if (netns < 0) {
                r = netns;
                goto fail;

        } else {
                /* Yay, found something, so let's join the namespace */
                if (setns(netns, CLONE_NEWNET) < 0) {
                        r = -errno;
                        goto fail;
                }

                r = 0;
        }

        q = send_one_fd(netns_storage_socket[1], netns, MSG_DONTWAIT);
        if (q < 0) {
                r = q;
                goto fail;
        }

fail:
        (void) lockf(netns_storage_socket[0], F_ULOCK, 0);
        return r;
}

static const char *const protect_home_table[_PROTECT_HOME_MAX] = {
        [PROTECT_HOME_NO] = "no",
        [PROTECT_HOME_YES] = "yes",
        [PROTECT_HOME_READ_ONLY] = "read-only",
};

DEFINE_STRING_TABLE_LOOKUP(protect_home, ProtectHome);

static const char *const protect_system_table[_PROTECT_SYSTEM_MAX] = {
        [PROTECT_SYSTEM_NO] = "no",
        [PROTECT_SYSTEM_YES] = "yes",
        [PROTECT_SYSTEM_FULL] = "full",
        [PROTECT_SYSTEM_STRICT] = "strict",
};

DEFINE_STRING_TABLE_LOOKUP(protect_system, ProtectSystem);