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
|
#ifndef _LINUX_CGROUP_H
#define _LINUX_CGROUP_H
/*
* cgroup interface
*
* Copyright (C) 2003 BULL SA
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
*/
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/nodemask.h>
#include <linux/rcupdate.h>
#include <linux/rculist.h>
#include <linux/cgroupstats.h>
#include <linux/rwsem.h>
#include <linux/idr.h>
#include <linux/workqueue.h>
#include <linux/fs.h>
#include <linux/percpu-refcount.h>
#include <linux/seq_file.h>
#include <linux/kernfs.h>
#ifdef CONFIG_CGROUPS
struct cgroup_root;
struct cgroup_subsys;
struct inode;
struct cgroup;
extern int cgroup_init_early(void);
extern int cgroup_init(void);
extern void cgroup_fork(struct task_struct *p);
extern void cgroup_post_fork(struct task_struct *p);
extern void cgroup_exit(struct task_struct *p);
extern int cgroupstats_build(struct cgroupstats *stats,
struct dentry *dentry);
extern int proc_cgroup_show(struct seq_file *, void *);
/* define the enumeration of all cgroup subsystems */
#define SUBSYS(_x) _x ## _cgrp_id,
enum cgroup_subsys_id {
#include <linux/cgroup_subsys.h>
CGROUP_SUBSYS_COUNT,
};
#undef SUBSYS
/* Per-subsystem/per-cgroup state maintained by the system. */
struct cgroup_subsys_state {
/* the cgroup that this css is attached to */
struct cgroup *cgroup;
/* the cgroup subsystem that this css is attached to */
struct cgroup_subsys *ss;
/* reference count - access via css_[try]get() and css_put() */
struct percpu_ref refcnt;
/* the parent css */
struct cgroup_subsys_state *parent;
unsigned long flags;
/* percpu_ref killing and RCU release */
struct rcu_head rcu_head;
struct work_struct destroy_work;
};
/* bits in struct cgroup_subsys_state flags field */
enum {
CSS_ROOT = (1 << 0), /* this CSS is the root of the subsystem */
CSS_ONLINE = (1 << 1), /* between ->css_online() and ->css_offline() */
};
/**
* css_get - obtain a reference on the specified css
* @css: target css
*
* The caller must already have a reference.
*/
static inline void css_get(struct cgroup_subsys_state *css)
{
/* We don't need to reference count the root state */
if (!(css->flags & CSS_ROOT))
percpu_ref_get(&css->refcnt);
}
/**
* css_tryget - try to obtain a reference on the specified css
* @css: target css
*
* Obtain a reference on @css if it's alive. The caller naturally needs to
* ensure that @css is accessible but doesn't have to be holding a
* reference on it - IOW, RCU protected access is good enough for this
* function. Returns %true if a reference count was successfully obtained;
* %false otherwise.
*/
static inline bool css_tryget(struct cgroup_subsys_state *css)
{
if (css->flags & CSS_ROOT)
return true;
return percpu_ref_tryget(&css->refcnt);
}
/**
* css_put - put a css reference
* @css: target css
*
* Put a reference obtained via css_get() and css_tryget().
*/
static inline void css_put(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_ROOT))
percpu_ref_put(&css->refcnt);
}
/* bits in struct cgroup flags field */
enum {
/* Control Group is dead */
CGRP_DEAD,
/*
* Control Group has previously had a child cgroup or a task,
* but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
*/
CGRP_RELEASABLE,
/* Control Group requires release notifications to userspace */
CGRP_NOTIFY_ON_RELEASE,
/*
* Clone the parent's configuration when creating a new child
* cpuset cgroup. For historical reasons, this option can be
* specified at mount time and thus is implemented here.
*/
CGRP_CPUSET_CLONE_CHILDREN,
/* see the comment above CGRP_ROOT_SANE_BEHAVIOR for details */
CGRP_SANE_BEHAVIOR,
};
struct cgroup {
unsigned long flags; /* "unsigned long" so bitops work */
/*
* idr allocated in-hierarchy ID.
*
* The ID of the root cgroup is always 0, and a new cgroup
* will be assigned with a smallest available ID.
*
* Allocating/Removing ID must be protected by cgroup_mutex.
*/
int id;
/* the number of attached css's */
int nr_css;
atomic_t refcnt;
/*
* We link our 'sibling' struct into our parent's 'children'.
* Our children link their 'sibling' into our 'children'.
*/
struct list_head sibling; /* my parent's children */
struct list_head children; /* my children */
struct cgroup *parent; /* my parent */
struct kernfs_node *kn; /* cgroup kernfs entry */
/*
* Monotonically increasing unique serial number which defines a
* uniform order among all cgroups. It's guaranteed that all
* ->children lists are in the ascending order of ->serial_nr.
* It's used to allow interrupting and resuming iterations.
*/
u64 serial_nr;
/* the bitmask of subsystems enabled on the child cgroups */
unsigned long child_subsys_mask;
/* Private pointers for each registered subsystem */
struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
struct cgroup_root *root;
/*
* List of cgrp_cset_links pointing at css_sets with tasks in this
* cgroup. Protected by css_set_lock.
*/
struct list_head cset_links;
/*
* Linked list running through all cgroups that can
* potentially be reaped by the release agent. Protected by
* release_list_lock
*/
struct list_head release_list;
/*
* list of pidlists, up to two for each namespace (one for procs, one
* for tasks); created on demand.
*/
struct list_head pidlists;
struct mutex pidlist_mutex;
/* dummy css with NULL ->ss, points back to this cgroup */
struct cgroup_subsys_state dummy_css;
/* For css percpu_ref killing and RCU-protected deletion */
struct rcu_head rcu_head;
struct work_struct destroy_work;
};
#define MAX_CGROUP_ROOT_NAMELEN 64
/* cgroup_root->flags */
enum {
/*
* Unfortunately, cgroup core and various controllers are riddled
* with idiosyncrasies and pointless options. The following flag,
* when set, will force sane behavior - some options are forced on,
* others are disallowed, and some controllers will change their
* hierarchical or other behaviors.
*
* The set of behaviors affected by this flag are still being
* determined and developed and the mount option for this flag is
* prefixed with __DEVEL__. The prefix will be dropped once we
* reach the point where all behaviors are compatible with the
* planned unified hierarchy, which will automatically turn on this
* flag.
*
* The followings are the behaviors currently affected this flag.
*
* - Mount options "noprefix", "xattr", "clone_children",
* "release_agent" and "name" are disallowed.
*
* - When mounting an existing superblock, mount options should
* match.
*
* - Remount is disallowed.
*
* - rename(2) is disallowed.
*
* - "tasks" is removed. Everything should be at process
* granularity. Use "cgroup.procs" instead.
*
* - "cgroup.procs" is not sorted. pids will be unique unless they
* got recycled inbetween reads.
*
* - "release_agent" and "notify_on_release" are removed.
* Replacement notification mechanism will be implemented.
*
* - "cgroup.clone_children" is removed.
*
* - If mount is requested with sane_behavior but without any
* subsystem, the default unified hierarchy is mounted.
*
* - cpuset: tasks will be kept in empty cpusets when hotplug happens
* and take masks of ancestors with non-empty cpus/mems, instead of
* being moved to an ancestor.
*
* - cpuset: a task can be moved into an empty cpuset, and again it
* takes masks of ancestors.
*
* - memcg: use_hierarchy is on by default and the cgroup file for
* the flag is not created.
*
* - blkcg: blk-throttle becomes properly hierarchical.
*/
CGRP_ROOT_SANE_BEHAVIOR = (1 << 0),
CGRP_ROOT_NOPREFIX = (1 << 1), /* mounted subsystems have no named prefix */
CGRP_ROOT_XATTR = (1 << 2), /* supports extended attributes */
/* mount options live below bit 16 */
CGRP_ROOT_OPTION_MASK = (1 << 16) - 1,
};
/*
* A cgroup_root represents the root of a cgroup hierarchy, and may be
* associated with a kernfs_root to form an active hierarchy. This is
* internal to cgroup core. Don't access directly from controllers.
*/
struct cgroup_root {
struct kernfs_root *kf_root;
/* The bitmask of subsystems attached to this hierarchy */
unsigned long subsys_mask;
/* Unique id for this hierarchy. */
int hierarchy_id;
/* The root cgroup. Root is destroyed on its release. */
<
|