-
-
Notifications
You must be signed in to change notification settings - Fork 3.6k
/
cgroup.c
3074 lines (2369 loc) · 114 KB
/
cgroup.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: LGPL-2.1+ */
#include <fcntl.h>
#include <fnmatch.h>
#include "alloc-util.h"
#include "blockdev-util.h"
#include "bpf-firewall.h"
#include "btrfs-util.h"
#include "bpf-devices.h"
#include "bus-error.h"
#include "cgroup-util.h"
#include "cgroup.h"
#include "fd-util.h"
#include "fileio.h"
#include "fs-util.h"
#include "parse-util.h"
#include "path-util.h"
#include "process-util.h"
#include "procfs-util.h"
#include "special.h"
#include "stat-util.h"
#include "stdio-util.h"
#include "string-table.h"
#include "string-util.h"
#include "virt.h"
#define CGROUP_CPU_QUOTA_PERIOD_USEC ((usec_t) 100 * USEC_PER_MSEC)
/* Returns the log level to use when cgroup attribute writes fail. When an attribute is missing or we have access
* problems we downgrade to LOG_DEBUG. This is supposed to be nice to container managers and kernels which want to mask
* out specific attributes from us. */
#define LOG_LEVEL_CGROUP_WRITE(r) (IN_SET(abs(r), ENOENT, EROFS, EACCES, EPERM) ? LOG_DEBUG : LOG_WARNING)
bool manager_owns_host_root_cgroup(Manager *m) {
assert(m);
/* Returns true if we are managing the root cgroup. Note that it isn't sufficient to just check whether the
* group root path equals "/" since that will also be the case if CLONE_NEWCGROUP is in the mix. Since there's
* appears to be no nice way to detect whether we are in a CLONE_NEWCGROUP namespace we instead just check if
* we run in any kind of container virtualization. */
if (MANAGER_IS_USER(m))
return false;
if (detect_container() > 0)
return false;
return empty_or_root(m->cgroup_root);
}
bool unit_has_host_root_cgroup(Unit *u) {
assert(u);
/* Returns whether this unit manages the root cgroup. This will return true if this unit is the root slice and
* the manager manages the root cgroup. */
if (!manager_owns_host_root_cgroup(u->manager))
return false;
return unit_has_name(u, SPECIAL_ROOT_SLICE);
}
static int set_attribute_and_warn(Unit *u, const char *controller, const char *attribute, const char *value) {
int r;
r = cg_set_attribute(controller, u->cgroup_path, attribute, value);
if (r < 0)
log_unit_full(u, LOG_LEVEL_CGROUP_WRITE(r), r, "Failed to set '%s' attribute on '%s' to '%.*s': %m",
strna(attribute), isempty(u->cgroup_path) ? "/" : u->cgroup_path, (int) strcspn(value, NEWLINE), value);
return r;
}
static void cgroup_compat_warn(void) {
static bool cgroup_compat_warned = false;
if (cgroup_compat_warned)
return;
log_warning("cgroup compatibility translation between legacy and unified hierarchy settings activated. "
"See cgroup-compat debug messages for details.");
cgroup_compat_warned = true;
}
#define log_cgroup_compat(unit, fmt, ...) do { \
cgroup_compat_warn(); \
log_unit_debug(unit, "cgroup-compat: " fmt, ##__VA_ARGS__); \
} while (false)
void cgroup_context_init(CGroupContext *c) {
assert(c);
/* Initialize everything to the kernel defaults. */
*c = (CGroupContext) {
.cpu_weight = CGROUP_WEIGHT_INVALID,
.startup_cpu_weight = CGROUP_WEIGHT_INVALID,
.cpu_quota_per_sec_usec = USEC_INFINITY,
.cpu_shares = CGROUP_CPU_SHARES_INVALID,
.startup_cpu_shares = CGROUP_CPU_SHARES_INVALID,
.memory_high = CGROUP_LIMIT_MAX,
.memory_max = CGROUP_LIMIT_MAX,
.memory_swap_max = CGROUP_LIMIT_MAX,
.memory_limit = CGROUP_LIMIT_MAX,
.io_weight = CGROUP_WEIGHT_INVALID,
.startup_io_weight = CGROUP_WEIGHT_INVALID,
.blockio_weight = CGROUP_BLKIO_WEIGHT_INVALID,
.startup_blockio_weight = CGROUP_BLKIO_WEIGHT_INVALID,
.tasks_max = CGROUP_LIMIT_MAX,
};
}
void cgroup_context_free_device_allow(CGroupContext *c, CGroupDeviceAllow *a) {
assert(c);
assert(a);
LIST_REMOVE(device_allow, c->device_allow, a);
free(a->path);
free(a);
}
void cgroup_context_free_io_device_weight(CGroupContext *c, CGroupIODeviceWeight *w) {
assert(c);
assert(w);
LIST_REMOVE(device_weights, c->io_device_weights, w);
free(w->path);
free(w);
}
void cgroup_context_free_io_device_latency(CGroupContext *c, CGroupIODeviceLatency *l) {
assert(c);
assert(l);
LIST_REMOVE(device_latencies, c->io_device_latencies, l);
free(l->path);
free(l);
}
void cgroup_context_free_io_device_limit(CGroupContext *c, CGroupIODeviceLimit *l) {
assert(c);
assert(l);
LIST_REMOVE(device_limits, c->io_device_limits, l);
free(l->path);
free(l);
}
void cgroup_context_free_blockio_device_weight(CGroupContext *c, CGroupBlockIODeviceWeight *w) {
assert(c);
assert(w);
LIST_REMOVE(device_weights, c->blockio_device_weights, w);
free(w->path);
free(w);
}
void cgroup_context_free_blockio_device_bandwidth(CGroupContext *c, CGroupBlockIODeviceBandwidth *b) {
assert(c);
assert(b);
LIST_REMOVE(device_bandwidths, c->blockio_device_bandwidths, b);
free(b->path);
free(b);
}
void cgroup_context_done(CGroupContext *c) {
assert(c);
while (c->io_device_weights)
cgroup_context_free_io_device_weight(c, c->io_device_weights);
while (c->io_device_latencies)
cgroup_context_free_io_device_latency(c, c->io_device_latencies);
while (c->io_device_limits)
cgroup_context_free_io_device_limit(c, c->io_device_limits);
while (c->blockio_device_weights)
cgroup_context_free_blockio_device_weight(c, c->blockio_device_weights);
while (c->blockio_device_bandwidths)
cgroup_context_free_blockio_device_bandwidth(c, c->blockio_device_bandwidths);
while (c->device_allow)
cgroup_context_free_device_allow(c, c->device_allow);
c->ip_address_allow = ip_address_access_free_all(c->ip_address_allow);
c->ip_address_deny = ip_address_access_free_all(c->ip_address_deny);
}
void cgroup_context_dump(CGroupContext *c, FILE* f, const char *prefix) {
CGroupIODeviceLimit *il;
CGroupIODeviceWeight *iw;
CGroupIODeviceLatency *l;
CGroupBlockIODeviceBandwidth *b;
CGroupBlockIODeviceWeight *w;
CGroupDeviceAllow *a;
IPAddressAccessItem *iaai;
char u[FORMAT_TIMESPAN_MAX];
assert(c);
assert(f);
prefix = strempty(prefix);
fprintf(f,
"%sCPUAccounting=%s\n"
"%sIOAccounting=%s\n"
"%sBlockIOAccounting=%s\n"
"%sMemoryAccounting=%s\n"
"%sTasksAccounting=%s\n"
"%sIPAccounting=%s\n"
"%sCPUWeight=%" PRIu64 "\n"
"%sStartupCPUWeight=%" PRIu64 "\n"
"%sCPUShares=%" PRIu64 "\n"
"%sStartupCPUShares=%" PRIu64 "\n"
"%sCPUQuotaPerSecSec=%s\n"
"%sIOWeight=%" PRIu64 "\n"
"%sStartupIOWeight=%" PRIu64 "\n"
"%sBlockIOWeight=%" PRIu64 "\n"
"%sStartupBlockIOWeight=%" PRIu64 "\n"
"%sMemoryMin=%" PRIu64 "\n"
"%sMemoryLow=%" PRIu64 "\n"
"%sMemoryHigh=%" PRIu64 "\n"
"%sMemoryMax=%" PRIu64 "\n"
"%sMemorySwapMax=%" PRIu64 "\n"
"%sMemoryLimit=%" PRIu64 "\n"
"%sTasksMax=%" PRIu64 "\n"
"%sDevicePolicy=%s\n"
"%sDelegate=%s\n",
prefix, yes_no(c->cpu_accounting),
prefix, yes_no(c->io_accounting),
prefix, yes_no(c->blockio_accounting),
prefix, yes_no(c->memory_accounting),
prefix, yes_no(c->tasks_accounting),
prefix, yes_no(c->ip_accounting),
prefix, c->cpu_weight,
prefix, c->startup_cpu_weight,
prefix, c->cpu_shares,
prefix, c->startup_cpu_shares,
prefix, format_timespan(u, sizeof(u), c->cpu_quota_per_sec_usec, 1),
prefix, c->io_weight,
prefix, c->startup_io_weight,
prefix, c->blockio_weight,
prefix, c->startup_blockio_weight,
prefix, c->memory_min,
prefix, c->memory_low,
prefix, c->memory_high,
prefix, c->memory_max,
prefix, c->memory_swap_max,
prefix, c->memory_limit,
prefix, c->tasks_max,
prefix, cgroup_device_policy_to_string(c->device_policy),
prefix, yes_no(c->delegate));
if (c->delegate) {
_cleanup_free_ char *t = NULL;
(void) cg_mask_to_string(c->delegate_controllers, &t);
fprintf(f, "%sDelegateControllers=%s\n",
prefix,
strempty(t));
}
LIST_FOREACH(device_allow, a, c->device_allow)
fprintf(f,
"%sDeviceAllow=%s %s%s%s\n",
prefix,
a->path,
a->r ? "r" : "", a->w ? "w" : "", a->m ? "m" : "");
LIST_FOREACH(device_weights, iw, c->io_device_weights)
fprintf(f,
"%sIODeviceWeight=%s %" PRIu64 "\n",
prefix,
iw->path,
iw->weight);
LIST_FOREACH(device_latencies, l, c->io_device_latencies)
fprintf(f,
"%sIODeviceLatencyTargetSec=%s %s\n",
prefix,
l->path,
format_timespan(u, sizeof(u), l->target_usec, 1));
LIST_FOREACH(device_limits, il, c->io_device_limits) {
char buf[FORMAT_BYTES_MAX];
CGroupIOLimitType type;
for (type = 0; type < _CGROUP_IO_LIMIT_TYPE_MAX; type++)
if (il->limits[type] != cgroup_io_limit_defaults[type])
fprintf(f,
"%s%s=%s %s\n",
prefix,
cgroup_io_limit_type_to_string(type),
il->path,
format_bytes(buf, sizeof(buf), il->limits[type]));
}
LIST_FOREACH(device_weights, w, c->blockio_device_weights)
fprintf(f,
"%sBlockIODeviceWeight=%s %" PRIu64,
prefix,
w->path,
w->weight);
LIST_FOREACH(device_bandwidths, b, c->blockio_device_bandwidths) {
char buf[FORMAT_BYTES_MAX];
if (b->rbps != CGROUP_LIMIT_MAX)
fprintf(f,
"%sBlockIOReadBandwidth=%s %s\n",
prefix,
b->path,
format_bytes(buf, sizeof(buf), b->rbps));
if (b->wbps != CGROUP_LIMIT_MAX)
fprintf(f,
"%sBlockIOWriteBandwidth=%s %s\n",
prefix,
b->path,
format_bytes(buf, sizeof(buf), b->wbps));
}
LIST_FOREACH(items, iaai, c->ip_address_allow) {
_cleanup_free_ char *k = NULL;
(void) in_addr_to_string(iaai->family, &iaai->address, &k);
fprintf(f, "%sIPAddressAllow=%s/%u\n", prefix, strnull(k), iaai->prefixlen);
}
LIST_FOREACH(items, iaai, c->ip_address_deny) {
_cleanup_free_ char *k = NULL;
(void) in_addr_to_string(iaai->family, &iaai->address, &k);
fprintf(f, "%sIPAddressDeny=%s/%u\n", prefix, strnull(k), iaai->prefixlen);
}
}
int cgroup_add_device_allow(CGroupContext *c, const char *dev, const char *mode) {
_cleanup_free_ CGroupDeviceAllow *a = NULL;
_cleanup_free_ char *d = NULL;
assert(c);
assert(dev);
assert(isempty(mode) || in_charset(mode, "rwm"));
a = new(CGroupDeviceAllow, 1);
if (!a)
return -ENOMEM;
d = strdup(dev);
if (!d)
return -ENOMEM;
*a = (CGroupDeviceAllow) {
.path = TAKE_PTR(d),
.r = isempty(mode) || strchr(mode, 'r'),
.w = isempty(mode) || strchr(mode, 'w'),
.m = isempty(mode) || strchr(mode, 'm'),
};
LIST_PREPEND(device_allow, c->device_allow, a);
TAKE_PTR(a);
return 0;
}
static void cgroup_xattr_apply(Unit *u) {
char ids[SD_ID128_STRING_MAX];
int r;
assert(u);
if (!MANAGER_IS_SYSTEM(u->manager))
return;
if (sd_id128_is_null(u->invocation_id))
return;
r = cg_set_xattr(SYSTEMD_CGROUP_CONTROLLER, u->cgroup_path,
"trusted.invocation_id",
sd_id128_to_string(u->invocation_id, ids), 32,
0);
if (r < 0)
log_unit_debug_errno(u, r, "Failed to set invocation ID on control group %s, ignoring: %m", u->cgroup_path);
}
static int lookup_block_device(const char *p, dev_t *ret) {
dev_t rdev, dev = 0;
mode_t mode;
int r;
assert(p);
assert(ret);
r = device_path_parse_major_minor(p, &mode, &rdev);
if (r == -ENODEV) { /* not a parsable device node, need to go to disk */
struct stat st;
if (stat(p, &st) < 0)
return log_warning_errno(errno, "Couldn't stat device '%s': %m", p);
rdev = (dev_t)st.st_rdev;
dev = (dev_t)st.st_dev;
mode = st.st_mode;
} else if (r < 0)
return log_warning_errno(r, "Failed to parse major/minor from path '%s': %m", p);
if (S_ISCHR(mode)) {
log_warning("Device node '%s' is a character device, but block device needed.", p);
return -ENOTBLK;
} else if (S_ISBLK(mode))
*ret = rdev;
else if (major(dev) != 0)
*ret = dev; /* If this is not a device node then use the block device this file is stored on */
else {
/* If this is btrfs, getting the backing block device is a bit harder */
r = btrfs_get_block_device(p, ret);
if (r < 0 && r != -ENOTTY)
return log_warning_errno(r, "Failed to determine block device backing btrfs file system '%s': %m", p);
if (r == -ENOTTY) {
log_warning("'%s' is not a block device node, and file system block device cannot be determined or is not local.", p);
return -ENODEV;
}
}
/* If this is a LUKS device, try to get the originating block device */
(void) block_get_originating(*ret, ret);
/* If this is a partition, try to get the originating block device */
(void) block_get_whole_disk(*ret, ret);
return 0;
}
static int whitelist_device(BPFProgram *prog, const char *path, const char *node, const char *acc) {
dev_t rdev;
mode_t mode;
int r;
assert(path);
assert(acc);
/* Some special handling for /dev/block/%u:%u, /dev/char/%u:%u, /run/systemd/inaccessible/chr and
* /run/systemd/inaccessible/blk paths. Instead of stat()ing these we parse out the major/minor directly. This
* means clients can use these path without the device node actually around */
r = device_path_parse_major_minor(node, &mode, &rdev);
if (r < 0) {
if (r != -ENODEV)
return log_warning_errno(r, "Couldn't parse major/minor from device path '%s': %m", node);
struct stat st;
if (stat(node, &st) < 0)
return log_warning_errno(errno, "Couldn't stat device %s: %m", node);
if (!S_ISCHR(st.st_mode) && !S_ISBLK(st.st_mode)) {
log_warning("%s is not a device.", node);
return -ENODEV;
}
rdev = (dev_t) st.st_rdev;
mode = st.st_mode;
}
if (cg_all_unified() > 0) {
if (!prog)
return 0;
return cgroup_bpf_whitelist_device(prog, S_ISCHR(mode) ? BPF_DEVCG_DEV_CHAR : BPF_DEVCG_DEV_BLOCK,
major(rdev), minor(rdev), acc);
} else {
char buf[2+DECIMAL_STR_MAX(dev_t)*2+2+4];
sprintf(buf,
"%c %u:%u %s",
S_ISCHR(mode) ? 'c' : 'b',
major(rdev), minor(rdev),
acc);
/* Changing the devices list of a populated cgroup might result in EINVAL, hence ignore EINVAL here. */
r = cg_set_attribute("devices", path, "devices.allow", buf);
if (r < 0)
return log_full_errno(IN_SET(r, -ENOENT, -EROFS, -EINVAL, -EACCES, -EPERM) ? LOG_DEBUG : LOG_WARNING,
r, "Failed to set devices.allow on %s: %m", path);
return 0;
}
}
static int whitelist_major(BPFProgram *prog, const char *path, const char *name, char type, const char *acc) {
_cleanup_fclose_ FILE *f = NULL;
char buf[2+DECIMAL_STR_MAX(unsigned)+3+4];
bool good = false;
unsigned maj;
int r;
assert(path);
assert(acc);
assert(IN_SET(type, 'b', 'c'));
if (streq(name, "*")) {
/* If the name is a wildcard, then apply this list to all devices of this type */
if (cg_all_unified() > 0) {
if (!prog)
return 0;
(void) cgroup_bpf_whitelist_class(prog, type == 'c' ? BPF_DEVCG_DEV_CHAR : BPF_DEVCG_DEV_BLOCK, acc);
} else {
xsprintf(buf, "%c *:* %s", type, acc);
r = cg_set_attribute("devices", path, "devices.allow", buf);
if (r < 0)
log_full_errno(IN_SET(r, -ENOENT, -EROFS, -EINVAL, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
"Failed to set devices.allow on %s: %m", path);
return 0;
}
}
if (safe_atou(name, &maj) >= 0 && DEVICE_MAJOR_VALID(maj)) {
/* The name is numeric and suitable as major. In that case, let's take is major, and create the entry
* directly */
if (cg_all_unified() > 0) {
if (!prog)
return 0;
(void) cgroup_bpf_whitelist_major(prog,
type == 'c' ? BPF_DEVCG_DEV_CHAR : BPF_DEVCG_DEV_BLOCK,
maj, acc);
} else {
xsprintf(buf, "%c %u:* %s", type, maj, acc);
r = cg_set_attribute("devices", path, "devices.allow", buf);
if (r < 0)
log_full_errno(IN_SET(r, -ENOENT, -EROFS, -EINVAL, -EACCES) ? LOG_DEBUG : LOG_WARNING, r,
"Failed to set devices.allow on %s: %m", path);
}
return 0;
}
f = fopen("/proc/devices", "re");
if (!f)
return log_warning_errno(errno, "Cannot open /proc/devices to resolve %s (%c): %m", name, type);
for (;;) {
_cleanup_free_ char *line = NULL;
char *w, *p;
r = read_line(f, LONG_LINE_MAX, &line);
if (r < 0)
return log_warning_errno(r, "Failed to read /proc/devices: %m");
if (r == 0)
break;
if (type == 'c' && streq(line, "Character devices:")) {
good = true;
continue;
}
if (type == 'b' && streq(line, "Block devices:")) {
good = true;
continue;
}
if (isempty(line)) {
good = false;
continue;
}
if (!good)
continue;
p = strstrip(line);
w = strpbrk(p, WHITESPACE);
if (!w)
continue;
*w = 0;
r = safe_atou(p, &maj);
if (r < 0)
continue;
if (maj <= 0)
continue;
w++;
w += strspn(w, WHITESPACE);
if (fnmatch(name, w, 0) != 0)
continue;
if (cg_all_unified() > 0) {
if (!prog)
continue;
(void) cgroup_bpf_whitelist_major(prog,
type == 'c' ? BPF_DEVCG_DEV_CHAR : BPF_DEVCG_DEV_BLOCK,
maj, acc);
} else {
sprintf(buf,
"%c %u:* %s",
type,
maj,
acc);
/* Changing the devices list of a populated cgroup might result in EINVAL, hence ignore EINVAL
* here. */
r = cg_set_attribute("devices", path, "devices.allow", buf);
if (r < 0)
log_full_errno(IN_SET(r, -ENOENT, -EROFS, -EINVAL, -EACCES, -EPERM) ? LOG_DEBUG : LOG_WARNING,
r, "Failed to set devices.allow on %s: %m", path);
}
}
return 0;
}
static bool cgroup_context_has_cpu_weight(CGroupContext *c) {
return c->cpu_weight != CGROUP_WEIGHT_INVALID ||
c->startup_cpu_weight != CGROUP_WEIGHT_INVALID;
}
static bool cgroup_context_has_cpu_shares(CGroupContext *c) {
return c->cpu_shares != CGROUP_CPU_SHARES_INVALID ||
c->startup_cpu_shares != CGROUP_CPU_SHARES_INVALID;
}
static uint64_t cgroup_context_cpu_weight(CGroupContext *c, ManagerState state) {
if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
c->startup_cpu_weight != CGROUP_WEIGHT_INVALID)
return c->startup_cpu_weight;
else if (c->cpu_weight != CGROUP_WEIGHT_INVALID)
return c->cpu_weight;
else
return CGROUP_WEIGHT_DEFAULT;
}
static uint64_t cgroup_context_cpu_shares(CGroupContext *c, ManagerState state) {
if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
c->startup_cpu_shares != CGROUP_CPU_SHARES_INVALID)
return c->startup_cpu_shares;
else if (c->cpu_shares != CGROUP_CPU_SHARES_INVALID)
return c->cpu_shares;
else
return CGROUP_CPU_SHARES_DEFAULT;
}
static void cgroup_apply_unified_cpu_weight(Unit *u, uint64_t weight) {
char buf[DECIMAL_STR_MAX(uint64_t) + 2];
xsprintf(buf, "%" PRIu64 "\n", weight);
(void) set_attribute_and_warn(u, "cpu", "cpu.weight", buf);
}
static void cgroup_apply_unified_cpu_quota(Unit *u, usec_t quota) {
char buf[(DECIMAL_STR_MAX(usec_t) + 1) * 2 + 1];
if (quota != USEC_INFINITY)
xsprintf(buf, USEC_FMT " " USEC_FMT "\n",
quota * CGROUP_CPU_QUOTA_PERIOD_USEC / USEC_PER_SEC, CGROUP_CPU_QUOTA_PERIOD_USEC);
else
xsprintf(buf, "max " USEC_FMT "\n", CGROUP_CPU_QUOTA_PERIOD_USEC);
(void) set_attribute_and_warn(u, "cpu", "cpu.max", buf);
}
static void cgroup_apply_legacy_cpu_shares(Unit *u, uint64_t shares) {
char buf[DECIMAL_STR_MAX(uint64_t) + 2];
xsprintf(buf, "%" PRIu64 "\n", shares);
(void) set_attribute_and_warn(u, "cpu", "cpu.shares", buf);
}
static void cgroup_apply_legacy_cpu_quota(Unit *u, usec_t quota) {
char buf[DECIMAL_STR_MAX(usec_t) + 2];
xsprintf(buf, USEC_FMT "\n", CGROUP_CPU_QUOTA_PERIOD_USEC);
(void) set_attribute_and_warn(u, "cpu", "cpu.cfs_period_us", buf);
if (quota != USEC_INFINITY) {
xsprintf(buf, USEC_FMT "\n", quota * CGROUP_CPU_QUOTA_PERIOD_USEC / USEC_PER_SEC);
(void) set_attribute_and_warn(u, "cpu", "cpu.cfs_quota_us", buf);
} else
(void) set_attribute_and_warn(u, "cpu", "cpu.cfs_quota_us", "-1\n");
}
static uint64_t cgroup_cpu_shares_to_weight(uint64_t shares) {
return CLAMP(shares * CGROUP_WEIGHT_DEFAULT / CGROUP_CPU_SHARES_DEFAULT,
CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX);
}
static uint64_t cgroup_cpu_weight_to_shares(uint64_t weight) {
return CLAMP(weight * CGROUP_CPU_SHARES_DEFAULT / CGROUP_WEIGHT_DEFAULT,
CGROUP_CPU_SHARES_MIN, CGROUP_CPU_SHARES_MAX);
}
static bool cgroup_context_has_io_config(CGroupContext *c) {
return c->io_accounting ||
c->io_weight != CGROUP_WEIGHT_INVALID ||
c->startup_io_weight != CGROUP_WEIGHT_INVALID ||
c->io_device_weights ||
c->io_device_latencies ||
c->io_device_limits;
}
static bool cgroup_context_has_blockio_config(CGroupContext *c) {
return c->blockio_accounting ||
c->blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID ||
c->startup_blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID ||
c->blockio_device_weights ||
c->blockio_device_bandwidths;
}
static uint64_t cgroup_context_io_weight(CGroupContext *c, ManagerState state) {
if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
c->startup_io_weight != CGROUP_WEIGHT_INVALID)
return c->startup_io_weight;
else if (c->io_weight != CGROUP_WEIGHT_INVALID)
return c->io_weight;
else
return CGROUP_WEIGHT_DEFAULT;
}
static uint64_t cgroup_context_blkio_weight(CGroupContext *c, ManagerState state) {
if (IN_SET(state, MANAGER_STARTING, MANAGER_INITIALIZING) &&
c->startup_blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID)
return c->startup_blockio_weight;
else if (c->blockio_weight != CGROUP_BLKIO_WEIGHT_INVALID)
return c->blockio_weight;
else
return CGROUP_BLKIO_WEIGHT_DEFAULT;
}
static uint64_t cgroup_weight_blkio_to_io(uint64_t blkio_weight) {
return CLAMP(blkio_weight * CGROUP_WEIGHT_DEFAULT / CGROUP_BLKIO_WEIGHT_DEFAULT,
CGROUP_WEIGHT_MIN, CGROUP_WEIGHT_MAX);
}
static uint64_t cgroup_weight_io_to_blkio(uint64_t io_weight) {
return CLAMP(io_weight * CGROUP_BLKIO_WEIGHT_DEFAULT / CGROUP_WEIGHT_DEFAULT,
CGROUP_BLKIO_WEIGHT_MIN, CGROUP_BLKIO_WEIGHT_MAX);
}
static void cgroup_apply_io_device_weight(Unit *u, const char *dev_path, uint64_t io_weight) {
char buf[DECIMAL_STR_MAX(dev_t)*2+2+DECIMAL_STR_MAX(uint64_t)+1];
dev_t dev;
int r;
r = lookup_block_device(dev_path, &dev);
if (r < 0)
return;
xsprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), io_weight);
(void) set_attribute_and_warn(u, "io", "io.weight", buf);
}
static void cgroup_apply_blkio_device_weight(Unit *u, const char *dev_path, uint64_t blkio_weight) {
char buf[DECIMAL_STR_MAX(dev_t)*2+2+DECIMAL_STR_MAX(uint64_t)+1];
dev_t dev;
int r;
r = lookup_block_device(dev_path, &dev);
if (r < 0)
return;
xsprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), blkio_weight);
(void) set_attribute_and_warn(u, "blkio", "blkio.weight_device", buf);
}
static void cgroup_apply_io_device_latency(Unit *u, const char *dev_path, usec_t target) {
char buf[DECIMAL_STR_MAX(dev_t)*2+2+7+DECIMAL_STR_MAX(uint64_t)+1];
dev_t dev;
int r;
r = lookup_block_device(dev_path, &dev);
if (r < 0)
return;
if (target != USEC_INFINITY)
xsprintf(buf, "%u:%u target=%" PRIu64 "\n", major(dev), minor(dev), target);
else
xsprintf(buf, "%u:%u target=max\n", major(dev), minor(dev));
(void) set_attribute_and_warn(u, "io", "io.latency", buf);
}
static void cgroup_apply_io_device_limit(Unit *u, const char *dev_path, uint64_t *limits) {
char limit_bufs[_CGROUP_IO_LIMIT_TYPE_MAX][DECIMAL_STR_MAX(uint64_t)];
char buf[DECIMAL_STR_MAX(dev_t)*2+2+(6+DECIMAL_STR_MAX(uint64_t)+1)*4];
CGroupIOLimitType type;
dev_t dev;
int r;
r = lookup_block_device(dev_path, &dev);
if (r < 0)
return;
for (type = 0; type < _CGROUP_IO_LIMIT_TYPE_MAX; type++)
if (limits[type] != cgroup_io_limit_defaults[type])
xsprintf(limit_bufs[type], "%" PRIu64, limits[type]);
else
xsprintf(limit_bufs[type], "%s", limits[type] == CGROUP_LIMIT_MAX ? "max" : "0");
xsprintf(buf, "%u:%u rbps=%s wbps=%s riops=%s wiops=%s\n", major(dev), minor(dev),
limit_bufs[CGROUP_IO_RBPS_MAX], limit_bufs[CGROUP_IO_WBPS_MAX],
limit_bufs[CGROUP_IO_RIOPS_MAX], limit_bufs[CGROUP_IO_WIOPS_MAX]);
(void) set_attribute_and_warn(u, "io", "io.max", buf);
}
static void cgroup_apply_blkio_device_limit(Unit *u, const char *dev_path, uint64_t rbps, uint64_t wbps) {
char buf[DECIMAL_STR_MAX(dev_t)*2+2+DECIMAL_STR_MAX(uint64_t)+1];
dev_t dev;
int r;
r = lookup_block_device(dev_path, &dev);
if (r < 0)
return;
sprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), rbps);
(void) set_attribute_and_warn(u, "blkio", "blkio.throttle.read_bps_device", buf);
sprintf(buf, "%u:%u %" PRIu64 "\n", major(dev), minor(dev), wbps);
(void) set_attribute_and_warn(u, "blkio", "blkio.throttle.write_bps_device", buf);
}
static bool cgroup_context_has_unified_memory_config(CGroupContext *c) {
return c->memory_min > 0 || c->memory_low > 0 || c->memory_high != CGROUP_LIMIT_MAX || c->memory_max != CGROUP_LIMIT_MAX || c->memory_swap_max != CGROUP_LIMIT_MAX;
}
static void cgroup_apply_unified_memory_limit(Unit *u, const char *file, uint64_t v) {
char buf[DECIMAL_STR_MAX(uint64_t) + 1] = "max\n";
if (v != CGROUP_LIMIT_MAX)
xsprintf(buf, "%" PRIu64 "\n", v);
(void) set_attribute_and_warn(u, "memory", file, buf);
}
static void cgroup_apply_firewall(Unit *u) {
assert(u);
/* Best-effort: let's apply IP firewalling and/or accounting if that's enabled */
if (bpf_firewall_compile(u) < 0)
return;
(void) bpf_firewall_install(u);
}
static void cgroup_context_apply(
Unit *u,
CGroupMask apply_mask,
ManagerState state) {
const char *path;
CGroupContext *c;
bool is_host_root, is_local_root;
int r;
assert(u);
/* Nothing to do? Exit early! */
if (apply_mask == 0)
return;
/* Some cgroup attributes are not supported on the host root cgroup, hence silently ignore them here. And other
* attributes should only be managed for cgroups further down the tree. */
is_local_root = unit_has_name(u, SPECIAL_ROOT_SLICE);
is_host_root = unit_has_host_root_cgroup(u);
assert_se(c = unit_get_cgroup_context(u));
assert_se(path = u->cgroup_path);
if (is_local_root) /* Make sure we don't try to display messages with an empty path. */
path = "/";
/* We generally ignore errors caused by read-only mounted cgroup trees (assuming we are running in a container
* then), and missing cgroups, i.e. EROFS and ENOENT. */
/* In fully unified mode these attributes don't exist on the host cgroup root. On legacy the weights exist, but
* setting the weight makes very little sense on the host root cgroup, as there are no other cgroups at this
* level. The quota exists there too, but any attempt to write to it is refused with EINVAL. Inside of
* containers we want to leave control of these to the container manager (and if cgroup v2 delegation is used
* we couldn't even write to them if we wanted to). */
if ((apply_mask & CGROUP_MASK_CPU) && !is_local_root) {
if (cg_all_unified() > 0) {
uint64_t weight;
if (cgroup_context_has_cpu_weight(c))
weight = cgroup_context_cpu_weight(c, state);
else if (cgroup_context_has_cpu_shares(c)) {
uint64_t shares;
shares = cgroup_context_cpu_shares(c, state);
weight = cgroup_cpu_shares_to_weight(shares);
log_cgroup_compat(u, "Applying [Startup]CPUShares=%" PRIu64 " as [Startup]CPUWeight=%" PRIu64 " on %s",
shares, weight, path);
} else
weight = CGROUP_WEIGHT_DEFAULT;
cgroup_apply_unified_cpu_weight(u, weight);
cgroup_apply_unified_cpu_quota(u, c->cpu_quota_per_sec_usec);
} else {
uint64_t shares;
if (cgroup_context_has_cpu_weight(c)) {
uint64_t weight;
weight = cgroup_context_cpu_weight(c, state);
shares = cgroup_cpu_weight_to_shares(weight);
log_cgroup_compat(u, "Applying [Startup]CPUWeight=%" PRIu64 " as [Startup]CPUShares=%" PRIu64 " on %s",
weight, shares, path);
} else if (cgroup_context_has_cpu_shares(c))
shares = cgroup_context_cpu_shares(c, state);
else
shares = CGROUP_CPU_SHARES_DEFAULT;
cgroup_apply_legacy_cpu_shares(u, shares);
cgroup_apply_legacy_cpu_quota(u, c->cpu_quota_per_sec_usec);
}
}
/* The 'io' controller attributes are not exported on the host's root cgroup (being a pure cgroup v2
* controller), and in case of containers we want to leave control of these attributes to the container manager
* (and we couldn't access that stuff anyway, even if we tried if proper delegation is used). */
if ((apply_mask & CGROUP_MASK_IO) && !is_local_root) {
char buf[8+DECIMAL_STR_MAX(uint64_t)+1];
bool has_io, has_blockio;
uint64_t weight;
has_io = cgroup_context_has_io_config(c);
has_blockio = cgroup_context_has_blockio_config(c);
if (has_io)
weight = cgroup_context_io_weight(c, state);
else if (has_blockio) {
uint64_t blkio_weight;
blkio_weight = cgroup_context_blkio_weight(c, state);
weight = cgroup_weight_blkio_to_io(blkio_weight);
log_cgroup_compat(u, "Applying [Startup]BlockIOWeight=%" PRIu64 " as [Startup]IOWeight=%" PRIu64,
blkio_weight, weight);
} else
weight = CGROUP_WEIGHT_DEFAULT;
xsprintf(buf, "default %" PRIu64 "\n", weight);
(void) set_attribute_and_warn(u, "io", "io.weight", buf);
if (has_io) {
CGroupIODeviceLatency *latency;
CGroupIODeviceLimit *limit;
CGroupIODeviceWeight *w;
LIST_FOREACH(device_weights, w, c->io_device_weights)
cgroup_apply_io_device_weight(u, w->path, w->weight);
LIST_FOREACH(device_limits, limit, c->io_device_limits)
cgroup_apply_io_device_limit(u, limit->path, limit->limits);
LIST_FOREACH(device_latencies, latency, c->io_device_latencies)
cgroup_apply_io_device_latency(u, latency->path, latency->target_usec);
} else if (has_blockio) {
CGroupBlockIODeviceWeight *w;
CGroupBlockIODeviceBandwidth *b;
LIST_FOREACH(device_weights, w, c->blockio_device_weights) {
weight = cgroup_weight_blkio_to_io(w->weight);
log_cgroup_compat(u, "Applying BlockIODeviceWeight=%" PRIu64 " as IODeviceWeight=%" PRIu64 " for %s",
w->weight, weight, w->path);
cgroup_apply_io_device_weight(u, w->path, weight);
}
LIST_FOREACH(device_bandwidths, b, c->blockio_device_bandwidths) {
uint64_t limits[_CGROUP_IO_LIMIT_TYPE_MAX];
CGroupIOLimitType type;
for (type = 0; type < _CGROUP_IO_LIMIT_TYPE_MAX; type++)
limits[type] = cgroup_io_limit_defaults[type];
limits[CGROUP_IO_RBPS_MAX] = b->rbps;
limits[CGROUP_IO_WBPS_MAX] = b->wbps;