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
|
#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/cgroupstats.h>
#include <linux/prio_heap.h>
#include <linux/rwsem.h>
#include <linux/idr.h>
#include <linux/workqueue.h>
#ifdef CONFIG_CGROUPS
struct cgroupfs_root;
struct cgroup_subsys;
struct inode;
struct cgroup;
struct css_id;
extern int cgroup_init_early(void);
extern int cgroup_init(void);
extern void cgroup_lock(void);
extern int cgroup_lock_is_held(void);
extern bool cgroup_lock_live_group(struct cgroup *cgrp);
extern void cgroup_unlock(void);
extern void cgroup_fork(struct task_struct *p);
extern void cgroup_fork_callbacks(struct task_struct *p);
extern void cgroup_post_fork(struct task_struct *p);
extern void cgroup_exit(struct task_struct *p, int run_callbacks);
extern int cgroupstats_build(struct cgroupstats *stats,
struct dentry *dentry);
extern int cgroup_load_subsys(struct cgroup_subsys *ss);
extern void cgroup_unload_subsys(struct cgroup_subsys *ss);
extern const struct file_operations proc_cgroup_operations;
/* Define the enumeration of all builtin cgroup subsystems */
#define SUBSYS(_x) _x ## _subsys_id,
enum cgroup_subsys_id {
#include <linux/cgroup_subsys.h>
CGROUP_BUILTIN_SUBSYS_COUNT
};
#undef SUBSYS
/*
* This define indicates the maximum number of subsystems that can be loaded
* at once. We limit to this many since cgroupfs_root has subsys_bits to keep
* track of all of them.
*/
#define CGROUP_SUBSYS_COUNT (BITS_PER_BYTE*sizeof(unsigned long))
/* Per-subsystem/per-cgroup state maintained by the system. */
struct cgroup_subsys_state {
/*
* The cgroup that this subsystem is attached to. Useful
* for subsystems that want to know about the cgroup
* hierarchy structure
*/
struct cgroup *cgroup;
/*
* State maintained by the cgroup system to allow subsystems
* to be "busy". Should be accessed via css_get(),
* css_tryget() and and css_put().
*/
atomic_t refcnt;
unsigned long flags;
/* ID for this css, if possible */
struct css_id __rcu *id;
/* Used to put @cgroup->dentry on the last css_put() */
struct work_struct dput_work;
};
/* bits in struct cgroup_subsys_state flags field */
enum {
CSS_ROOT, /* This CSS is the root of the subsystem */
CSS_REMOVED, /* This CSS is dead */
CSS_CLEAR_CSS_REFS, /* @ss->__DEPRECATED_clear_css_refs */
};
/* Caller must verify that the css is not for root cgroup */
static inline void __css_get(struct cgroup_subsys_state *css, int count)
{
atomic_add(count, &css->refcnt);
}
/*
* Call css_get() to hold a reference on the css; it can be used
* for a reference obtained via:
* - an existing ref-counted reference to the css
* - task->cgroups for a locked task
*/
static inline void css_get(struct cgroup_subsys_state *css)
{
/* We don't need to reference count the root state */
if (!test_bit(CSS_ROOT, &css->flags))
__css_get(css, 1);
}
static inline bool css_is_removed(struct cgroup_subsys_state *css)
{
return test_bit(CSS_REMOVED, &css->flags);
}
/*
* Call css_tryget() to take a reference on a css if your existing
* (known-valid) reference isn't already ref-counted. Returns false if
* the css has been destroyed.
*/
extern bool __css_tryget(struct cgroup_subsys_state *css);
static inline bool css_tryget(struct cgroup_subsys_state *css)
{
if (test_bit(CSS_ROOT, &css->flags))
return true;
return __css_tryget(css);
}
/*
* css_put() should be called to release a reference taken by
* css_get() or css_tryget()
*/
extern void __css_put(struct cgroup_subsys_state *css);
static inline void css_put(struct cgroup_subsys_state *css)
{
if (!test_bit(CSS_ROOT, &css->flags))
__css_put(css);
}
/* bits in struct cgroup flags field */
enum {
/* Control Group is dead */
CGRP_REMOVED,
/*
* 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,
/*
* A thread in rmdir() is wating for this cgroup.
*/
CGRP_WAIT_ON_RMDIR,
/*
* Clone cgroup values when creating a new child cgroup
*/
CGRP_CLONE_CHILDREN,
};
struct cgroup {
unsigned long flags; /* "unsigned long" so bitops work */
/*
* count users of this cgroup. >0 means busy, but doesn't
* necessarily indicate the number of tasks in the cgroup
*/
atomic_t count;
/*
* 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 list_head files; /* my files */
struct cgroup *parent; /* my parent */
struct dentry __rcu *dentry; /* cgroup fs entry, RCU protected */
/* Private pointers for each registered subsystem */
struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
struct cgroupfs_root *root;
struct cgroup *top_cgroup;
/*
* List of cg_cgroup_links pointing at css_sets with
* tasks in this cgroup. Protected by css_set_lock
*/
struct list_head css_sets;
struct list_head allcg_node; /* cgroupfs_root->allcg_list */
struct list_head cft_q_node; /* used during cftype add/rm */
/*
* 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;
/* For RCU-protected deletion */
struct rcu_head rcu_head;
/* List of events which userspace want to receive */
struct list_head event_list;
spinlock_t event_list_lock;
};
/*
* A css_set is a structure holding pointers to a set of
* cgroup_subsys_state objects. This saves space in the task struct
* object and speeds up fork()/exit(), since a single inc/dec and a
* list_add()/del() can bump the reference count on the entire cgroup
* set for a task.
*/
struct css_set {
/* Reference count */
atomic_t refcount;
/*
* List running through all cgroup groups in the same hash
* slot. Protected by css_set_lock
*/
struct hlist_node hlist;
/*
* List running through all tasks using this cgroup
* group. Protected by css_set_lock
*/
struct list_head tasks;
/*
* List of cg_cgroup_link objects on link chains from
* cgroups referenced from this css_set. Protected by
* css_set_lock
*/
struct list_head cg_links;
/*
* Set of subsystem states, one for each subsystem. This array
* is immutable after creation apart from the init_css_set
* during subsystem registration (at boot time) and modular subsystem
* loading/unloading.
*/
struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];
/* For RCU-protected deletion */
struct rcu_head rcu_head;
};
/*
* cgroup_map_cb is an abstract callback API for reporting map-valued
* control files
*/
struct cgroup_map_cb {
int (*fill)(struct cgroup_map_cb *cb, const char *key, u64 value);
void *state;
};
/*
* struct cftype: handler definitions for cgroup control files
*
* When reading/writing to a file:
* - the cgroup to use is file->f_dentry->d_parent->d_fsdata
* - the 'cftype' of the file is file->f_dentry->d_fsdata
*/
/* cftype->flags */
#define CFTYPE_ONLY_ON_ROOT (1U << 0) /* only create on root cg */
#define CFTYPE_NOT_ON_ROOT (1U << 1) /* don't create onp root cg */
#define MAX_CFTYPE_NAME 64
struct cftype {
/*
* By convention, the name should begin with the name of the
* subsystem, followed by a period. Zero length string indicates
* end of cftype array.
*/
char name[MAX_CFTYPE_NAME];
int private;
/*
* If not 0, file mode is set to this value, otherwise it will
* be figured out automatically
*/
umode_t mode;
/*
* If non-zero, defines the maximum length of string that can
* be passed to write_string; defaults to 64
*/
size_t max_write_len;
/* CFTYPE_* flags */
unsigned int flags;
int (*open)(struct inode *inode, struct file *file);
ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft,
struct file *file,
char __user *buf, size_t nbytes, loff_t *ppos);
/*
* read_u64() is a shortcut for the common case of returning a
* single integer. Use it in place of read()
*/
u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft);
/*
* read_s64() is a signed version of read_u64()
*/
s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft);
/*
* read_map() is used for defining a map of key/value
* pairs. It should call cb->fill(cb, key, value) for each
* entry. The key/value pairs (and their ordering) should not
* change between reboots.
*/
int (*read_map)(struct
|