cgroup.h 28 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
2
3
4
5
6
7
8
9
10
11
12
13
14
#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>
15
#include <linux/rculist.h>
Balbir Singh's avatar
Balbir Singh committed
16
#include <linux/cgroupstats.h>
17
#include <linux/fs.h>
18
#include <linux/seq_file.h>
Tejun Heo's avatar
Tejun Heo committed
19
#include <linux/kernfs.h>
20
#include <linux/jump_label.h>
21
22
23
24
#include <linux/types.h>
#include <linux/ns_common.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.h>
25
#include <linux/refcount.h>
26
#include <linux/kernel_stat.h>
27

28
#include <linux/cgroup-defs.h>
29
30
31

#ifdef CONFIG_CGROUPS

32
33
34
35
36
37
38
39
40
/*
 * All weight knobs on the default hierarhcy should use the following min,
 * default and max values.  The default value is the logarithmic center of
 * MIN and MAX and allows 100x to be expressed in both directions.
 */
#define CGROUP_WEIGHT_MIN		1
#define CGROUP_WEIGHT_DFL		100
#define CGROUP_WEIGHT_MAX		10000

41
42
/* walk only threadgroup leaders */
#define CSS_TASK_ITER_PROCS		(1U << 0)
43
44
/* walk all threaded css_sets in the domain */
#define CSS_TASK_ITER_THREADED		(1U << 1)
45

46
47
48
/* a css_task_iter should be treated as an opaque object */
struct css_task_iter {
	struct cgroup_subsys		*ss;
49
	unsigned int			flags;
50
51
52

	struct list_head		*cset_pos;
	struct list_head		*cset_head;
53

54
55
56
	struct list_head		*tcset_pos;
	struct list_head		*tcset_head;

57
58
59
	struct list_head		*task_pos;
	struct list_head		*tasks_head;
	struct list_head		*mg_tasks_head;
60
61

	struct css_set			*cur_cset;
62
	struct css_set			*cur_dcset;
63
64
	struct task_struct		*cur_task;
	struct list_head		iters_node;	/* css_set->task_iters */
65
};
66

67
68
extern struct cgroup_root cgrp_dfl_root;
extern struct css_set init_css_set;
69

70
#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
71
72
73
#include <linux/cgroup_subsys.h>
#undef SUBSYS

74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
#define SUBSYS(_x)								\
	extern struct static_key_true _x ## _cgrp_subsys_enabled_key;		\
	extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key;
#include <linux/cgroup_subsys.h>
#undef SUBSYS

/**
 * cgroup_subsys_enabled - fast test on whether a subsys is enabled
 * @ss: subsystem in question
 */
#define cgroup_subsys_enabled(ss)						\
	static_branch_likely(&ss ## _enabled_key)

/**
 * cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy
 * @ss: subsystem in question
 */
#define cgroup_subsys_on_dfl(ss)						\
	static_branch_likely(&ss ## _on_dfl_key)

94
95
bool css_has_online_children(struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
96
97
struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup,
					 struct cgroup_subsys *ss);
98
99
100
101
102
struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
					     struct cgroup_subsys *ss);
struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
						       struct cgroup_subsys *ss);

103
struct cgroup *cgroup_get_from_path(const char *path);
104
struct cgroup *cgroup_get_from_fd(int fd);
105

106
107
108
109
110
111
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);

int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_rm_cftypes(struct cftype *cfts);
112
void cgroup_file_notify(struct cgroup_file *cfile);
113

114
int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
115
116
117
118
119
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
		     struct pid *pid, struct task_struct *tsk);

void cgroup_fork(struct task_struct *p);
120
121
122
extern int cgroup_can_fork(struct task_struct *p);
extern void cgroup_cancel_fork(struct task_struct *p);
extern void cgroup_post_fork(struct task_struct *p);
123
void cgroup_exit(struct task_struct *p);
124
void cgroup_release(struct task_struct *p);
125
void cgroup_free(struct task_struct *p);
126
127
128
129

int cgroup_init_early(void);
int cgroup_init(void);

Tejun Heo's avatar
Tejun Heo committed
130
/*
131
132
133
134
135
136
137
138
139
140
141
 * Iteration helpers and macros.
 */

struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
					   struct cgroup_subsys_state *parent);
struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos,
						    struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos);
struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
						     struct cgroup_subsys_state *css);

142
143
144
145
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
					 struct cgroup_subsys_state **dst_cssp);
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
					struct cgroup_subsys_state **dst_cssp);
146

147
void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
			 struct css_task_iter *it);
struct task_struct *css_task_iter_next(struct css_task_iter *it);
void css_task_iter_end(struct css_task_iter *it);

/**
 * css_for_each_child - iterate through children of a css
 * @pos: the css * to use as the loop cursor
 * @parent: css whose children to walk
 *
 * Walk @parent's children.  Must be called under rcu_read_lock().
 *
 * If a subsystem synchronizes ->css_online() and the start of iteration, a
 * css which finished ->css_online() is guaranteed to be visible in the
 * future iterations and will stay visible until the last reference is put.
 * A css which hasn't finished ->css_online() or already finished
 * ->css_offline() may show up during traversal.  It's each subsystem's
 * responsibility to synchronize against on/offlining.
Tejun Heo's avatar
Tejun Heo committed
165
 *
166
167
168
 * It is allowed to temporarily drop RCU read lock during iteration.  The
 * caller is responsible for ensuring that @pos remains accessible until
 * the start of the next iteration by, for example, bumping the css refcnt.
Tejun Heo's avatar
Tejun Heo committed
169
 */
170
171
172
#define css_for_each_child(pos, parent)					\
	for ((pos) = css_next_child(NULL, (parent)); (pos);		\
	     (pos) = css_next_child((pos), (parent)))
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
/**
 * css_for_each_descendant_pre - pre-order walk of a css's descendants
 * @pos: the css * to use as the loop cursor
 * @root: css whose descendants to walk
 *
 * Walk @root's descendants.  @root is included in the iteration and the
 * first node to be visited.  Must be called under rcu_read_lock().
 *
 * If a subsystem synchronizes ->css_online() and the start of iteration, a
 * css which finished ->css_online() is guaranteed to be visible in the
 * future iterations and will stay visible until the last reference is put.
 * A css which hasn't finished ->css_online() or already finished
 * ->css_offline() may show up during traversal.  It's each subsystem's
 * responsibility to synchronize against on/offlining.
 *
 * For example, the following guarantees that a descendant can't escape
 * state updates of its ancestors.
 *
 * my_online(@css)
 * {
 *	Lock @css's parent and @css;
 *	Inherit state from the parent;
 *	Unlock both.
 * }
 *
 * my_update_state(@css)
 * {
 *	css_for_each_descendant_pre(@pos, @css) {
 *		Lock @pos;
 *		if (@pos == @css)
 *			Update @css's state;
 *		else
 *			Verify @pos is alive and inherit state from its parent;
 *		Unlock @pos;
 *	}
 * }
 *
 * As long as the inheriting step, including checking the parent state, is
 * enclosed inside @pos locking, double-locking the parent isn't necessary
 * while inheriting.  The state update to the parent is guaranteed to be
 * visible by walking order and, as long as inheriting operations to the
 * same @pos are atomic to each other, multiple updates racing each other
 * still result in the correct state.  It's guaranateed that at least one
 * inheritance happens for any css after the latest update to its parent.
 *
 * If checking parent's state requires locking the parent, each inheriting
 * iteration should lock and unlock both @pos->parent and @pos.
 *
 * Alternatively, a subsystem may choose to use a single global lock to
 * synchronize ->css_online() and ->css_offline() against tree-walking
 * operations.
 *
 * It is allowed to temporarily drop RCU read lock during iteration.  The
 * caller is responsible for ensuring that @pos remains accessible until
 * the start of the next iteration by, for example, bumping the css refcnt.
 */
#define css_for_each_descendant_pre(pos, css)				\
	for ((pos) = css_next_descendant_pre(NULL, (css)); (pos);	\
	     (pos) = css_next_descendant_pre((pos), (css)))

/**
 * css_for_each_descendant_post - post-order walk of a css's descendants
 * @pos: the css * to use as the loop cursor
 * @css: css whose descendants to walk
 *
 * Similar to css_for_each_descendant_pre() but performs post-order
 * traversal instead.  @root is included in the iteration and the last
 * node to be visited.
 *
 * If a subsystem synchronizes ->css_online() and the start of iteration, a
 * css which finished ->css_online() is guaranteed to be visible in the
 * future iterations and will stay visible until the last reference is put.
 * A css which hasn't finished ->css_online() or already finished
 * ->css_offline() may show up during traversal.  It's each subsystem's
 * responsibility to synchronize against on/offlining.
 *
 * Note that the walk visibility guarantee example described in pre-order
 * walk doesn't apply the same to post-order walks.
 */
#define css_for_each_descendant_post(pos, css)				\
	for ((pos) = css_next_descendant_post(NULL, (css)); (pos);	\
	     (pos) = css_next_descendant_post((pos), (css)))

/**
 * cgroup_taskset_for_each - iterate cgroup_taskset
 * @task: the loop cursor
260
 * @dst_css: the destination css
261
 * @tset: taskset to iterate
262
263
 *
 * @tset may contain multiple tasks and they may belong to multiple
264
265
266
267
268
269
270
271
 * processes.
 *
 * On the v2 hierarchy, there may be tasks from multiple processes and they
 * may not share the source or destination csses.
 *
 * On traditional hierarchies, when there are multiple tasks in @tset, if a
 * task of a process is in @tset, all tasks of the process are in @tset.
 * Also, all are guaranteed to share the same source and destination csses.
272
273
 *
 * Iteration is not in any specific order.
274
 */
275
276
277
278
#define cgroup_taskset_for_each(task, dst_css, tset)			\
	for ((task) = cgroup_taskset_first((tset), &(dst_css));		\
	     (task);							\
	     (task) = cgroup_taskset_next((tset), &(dst_css)))
279

280
281
282
/**
 * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
 * @leader: the loop cursor
283
 * @dst_css: the destination css
Geliang Tang's avatar
Geliang Tang committed
284
 * @tset: taskset to iterate
285
286
287
288
 *
 * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
 * may not contain any.
 */
289
290
291
292
#define cgroup_taskset_for_each_leader(leader, dst_css, tset)		\
	for ((leader) = cgroup_taskset_first((tset), &(dst_css));	\
	     (leader);							\
	     (leader) = cgroup_taskset_next((tset), &(dst_css)))	\
293
294
295
296
		if ((leader) != (leader)->group_leader)			\
			;						\
		else

297
298
299
/*
 * Inline functions.
 */
300

301
302
303
304
305
/**
 * css_get - obtain a reference on the specified css
 * @css: target css
 *
 * The caller must already have a reference.
306
307
308
 */
static inline void css_get(struct cgroup_subsys_state *css)
{
309
310
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_get(&css->refcnt);
311
}
Paul Menage's avatar
Paul Menage committed
312

313
314
315
316
317
318
319
320
321
322
323
324
325
/**
 * css_get_many - obtain references on the specified css
 * @css: target css
 * @n: number of references to get
 *
 * The caller must already have a reference.
 */
static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n)
{
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_get_many(&css->refcnt, n);
}

Tejun Heo's avatar
Tejun Heo committed
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
/**
 * css_tryget - try to obtain a reference on the specified css
 * @css: target css
 *
 * Obtain a reference on @css unless it already has reached zero and is
 * being released.  This function doesn't care whether @css is on or
 * offline.  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_NO_REF))
		return percpu_ref_tryget(&css->refcnt);
	return true;
}

344
/**
345
 * css_tryget_online - try to obtain a reference on the specified css if online
346
347
 * @css: target css
 *
348
349
 * Obtain a reference on @css if it's online.  The caller naturally needs
 * to ensure that @css is accessible but doesn't have to be holding a
350
351
352
353
 * reference on it - IOW, RCU protected access is good enough for this
 * function.  Returns %true if a reference count was successfully obtained;
 * %false otherwise.
 */
354
static inline bool css_tryget_online(struct cgroup_subsys_state *css)
Paul Menage's avatar
Paul Menage committed
355
{
356
357
358
	if (!(css->flags & CSS_NO_REF))
		return percpu_ref_tryget_live(&css->refcnt);
	return true;
Paul Menage's avatar
Paul Menage committed
359
}
360

361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
/**
 * css_is_dying - test whether the specified css is dying
 * @css: target css
 *
 * Test whether @css is in the process of offlining or already offline.  In
 * most cases, ->css_online() and ->css_offline() callbacks should be
 * enough; however, the actual offline operations are RCU delayed and this
 * test returns %true also when @css is scheduled to be offlined.
 *
 * This is useful, for example, when the use case requires synchronous
 * behavior with respect to cgroup removal.  cgroup removal schedules css
 * offlining but the css can seem alive while the operation is being
 * delayed.  If the delay affects user visible semantics, this test can be
 * used to resolve the situation.
 */
static inline bool css_is_dying(struct cgroup_subsys_state *css)
{
	return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt);
}

381
/**
382
383
384
 * css_put - put a css reference
 * @css: target css
 *
385
 * Put a reference obtained via css_get() and css_tryget_online().
386
 */
387
388
static inline void css_put(struct cgroup_subsys_state *css)
{
389
390
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_put(&css->refcnt);
391
}
392

393
394
395
396
397
398
/**
 * css_put_many - put css references
 * @css: target css
 * @n: number of references to put
 *
 * Put references obtained via css_get() and css_tryget_online().
399
 */
400
401
402
403
404
static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
{
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_put_many(&css->refcnt, n);
}
405

Tejun Heo's avatar
Tejun Heo committed
406
407
408
409
410
411
412
413
414
415
static inline void cgroup_get(struct cgroup *cgrp)
{
	css_get(&cgrp->self);
}

static inline bool cgroup_tryget(struct cgroup *cgrp)
{
	return css_tryget(&cgrp->self);
}

416
417
418
419
420
static inline void cgroup_put(struct cgroup *cgrp)
{
	css_put(&cgrp->self);
}

421
422
423
424
425
426
427
428
429
430
431
432
/**
 * task_css_set_check - obtain a task's css_set with extra access conditions
 * @task: the task to obtain css_set for
 * @__c: extra condition expression to be passed to rcu_dereference_check()
 *
 * A task's css_set is RCU protected, initialized and exited while holding
 * task_lock(), and can only be modified while holding both cgroup_mutex
 * and task_lock() while the task is alive.  This macro verifies that the
 * caller is inside proper critical section and returns @task's css_set.
 *
 * The caller can also specify additional allowed conditions via @__c, such
 * as locks used during the cgroup_subsys::attach() methods.
433
 */
434
435
#ifdef CONFIG_PROVE_RCU
extern struct mutex cgroup_mutex;
436
extern spinlock_t css_set_lock;
437
438
#define task_css_set_check(task, __c)					\
	rcu_dereference_check((task)->cgroups,				\
439
		lockdep_is_held(&cgroup_mutex) ||			\
440
		lockdep_is_held(&css_set_lock) ||			\
441
		((task)->flags & PF_EXITING) || (__c))
442
#else
443
444
#define task_css_set_check(task, __c)					\
	rcu_dereference((task)->cgroups)
445
#endif
446

447
/**
448
 * task_css_check - obtain css for (task, subsys) w/ extra access conds
449
450
451
452
453
454
455
 * @task: the target task
 * @subsys_id: the target subsystem ID
 * @__c: extra condition expression to be passed to rcu_dereference_check()
 *
 * Return the cgroup_subsys_state for the (@task, @subsys_id) pair.  The
 * synchronization rules are the same as task_css_set_check().
 */
456
#define task_css_check(task, subsys_id, __c)				\
457
458
459
460
461
462
463
464
465
466
467
468
469
470
	task_css_set_check((task), (__c))->subsys[(subsys_id)]

/**
 * task_css_set - obtain a task's css_set
 * @task: the task to obtain css_set for
 *
 * See task_css_set_check().
 */
static inline struct css_set *task_css_set(struct task_struct *task)
{
	return task_css_set_check(task, false);
}

/**
471
 * task_css - obtain css for (task, subsys)
472
473
474
 * @task: the target task
 * @subsys_id: the target subsystem ID
 *
475
 * See task_css_check().
476
 */
477
478
static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
						   int subsys_id)
479
{
480
	return task_css_check(task, subsys_id, false);
481
482
}

483
484
485
486
487
488
489
/**
 * task_get_css - find and get the css for (task, subsys)
 * @task: the target task
 * @subsys_id: the target subsystem ID
 *
 * Find the css for the (@task, @subsys_id) combination, increment a
 * reference on and return it.  This function is guaranteed to return a
490
 * valid css.  The returned css may already have been offlined.
491
492
493
494
495
496
497
498
499
 */
static inline struct cgroup_subsys_state *
task_get_css(struct task_struct *task, int subsys_id)
{
	struct cgroup_subsys_state *css;

	rcu_read_lock();
	while (true) {
		css = task_css(task, subsys_id);
500
501
502
503
504
505
506
		/*
		 * Can't use css_tryget_online() here.  A task which has
		 * PF_EXITING set may stay associated with an offline css.
		 * If such task calls this function, css_tryget_online()
		 * will keep failing.
		 */
		if (likely(css_tryget(css)))
507
508
509
510
511
512
513
			break;
		cpu_relax();
	}
	rcu_read_unlock();
	return css;
}

514
515
516
517
518
519
520
521
522
523
524
525
526
527
/**
 * task_css_is_root - test whether a task belongs to the root css
 * @task: the target task
 * @subsys_id: the target subsystem ID
 *
 * Test whether @task belongs to the root css on the specified subsystem.
 * May be invoked in any context.
 */
static inline bool task_css_is_root(struct task_struct *task, int subsys_id)
{
	return task_css_check(task, subsys_id, true) ==
		init_css_set.subsys[subsys_id];
}

528
529
static inline struct cgroup *task_cgroup(struct task_struct *task,
					 int subsys_id)
530
{
531
	return task_css(task, subsys_id)->cgroup;
532
533
}

Tejun Heo's avatar
Tejun Heo committed
534
535
536
537
538
539
540
541
542
543
544
545
546
547
static inline struct cgroup *task_dfl_cgroup(struct task_struct *task)
{
	return task_css_set(task)->dfl_cgrp;
}

static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
{
	struct cgroup_subsys_state *parent_css = cgrp->self.parent;

	if (parent_css)
		return container_of(parent_css, struct cgroup, self);
	return NULL;
}

548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
/**
 * cgroup_is_descendant - test ancestry
 * @cgrp: the cgroup to be tested
 * @ancestor: possible ancestor of @cgrp
 *
 * Test whether @cgrp is a descendant of @ancestor.  It also returns %true
 * if @cgrp == @ancestor.  This function is safe to call as long as @cgrp
 * and @ancestor are accessible.
 */
static inline bool cgroup_is_descendant(struct cgroup *cgrp,
					struct cgroup *ancestor)
{
	if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
		return false;
	return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
}

565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
/**
 * cgroup_ancestor - find ancestor of cgroup
 * @cgrp: cgroup to find ancestor of
 * @ancestor_level: level of ancestor to find starting from root
 *
 * Find ancestor of cgroup at specified level starting from root if it exists
 * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at
 * @ancestor_level.
 *
 * This function is safe to call as long as @cgrp is accessible.
 */
static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
					     int ancestor_level)
{
	if (cgrp->level < ancestor_level)
		return NULL;
581
582
583
	while (cgrp && cgrp->level > ancestor_level)
		cgrp = cgroup_parent(cgrp);
	return cgrp;
584
585
}

586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
/**
 * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry
 * @task: the task to be tested
 * @ancestor: possible ancestor of @task's cgroup
 *
 * Tests whether @task's default cgroup hierarchy is a descendant of @ancestor.
 * It follows all the same rules as cgroup_is_descendant, and only applies
 * to the default hierarchy.
 */
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
					       struct cgroup *ancestor)
{
	struct css_set *cset = task_css_set(task);

	return cgroup_is_descendant(cset->dfl_cgrp, ancestor);
}

603
/* no synchronization, the result can only be used as a hint */
604
static inline bool cgroup_is_populated(struct cgroup *cgrp)
605
{
606
607
	return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children +
		cgrp->nr_populated_threaded_children;
608
}
609

610
/* returns ino associated with a cgroup */
Tejun Heo's avatar
Tejun Heo committed
611
612
static inline ino_t cgroup_ino(struct cgroup *cgrp)
{
Shaohua Li's avatar
Shaohua Li committed
613
	return cgrp->kn->id.ino;
Tejun Heo's avatar
Tejun Heo committed
614
}
615

Tejun Heo's avatar
Tejun Heo committed
616
617
/* cft/css accessors for cftype->write() operation */
static inline struct cftype *of_cft(struct kernfs_open_file *of)
618
{
Tejun Heo's avatar
Tejun Heo committed
619
	return of->kn->priv;
620
}
Tejun Heo's avatar
Tejun Heo committed
621

Tejun Heo's avatar
Tejun Heo committed
622
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
623

Tejun Heo's avatar
Tejun Heo committed
624
625
626
627
628
/* cft/css accessors for cftype->seq_*() operations */
static inline struct cftype *seq_cft(struct seq_file *seq)
{
	return of_cft(seq->private);
}
629

Tejun Heo's avatar
Tejun Heo committed
630
631
632
633
static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
{
	return of_css(seq->private);
}
Michael S. Tsirkin's avatar
Michael S. Tsirkin committed
634

Tejun Heo's avatar
Tejun Heo committed
635
636
637
638
/*
 * Name / path handling functions.  All are thin wrappers around the kernfs
 * counterparts and can be called under any context.
 */
KAMEZAWA Hiroyuki's avatar
KAMEZAWA Hiroyuki committed
639

Tejun Heo's avatar
Tejun Heo committed
640
641
static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
{
642
	return kernfs_name(cgrp->kn, buf, buflen);
Tejun Heo's avatar
Tejun Heo committed
643
}
644

645
static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
Tejun Heo's avatar
Tejun Heo committed
646
{
647
	return kernfs_path(cgrp->kn, buf, buflen);
Tejun Heo's avatar
Tejun Heo committed
648
}
649

Tejun Heo's avatar
Tejun Heo committed
650
651
static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
{
652
	pr_cont_kernfs_name(cgrp->kn);
Tejun Heo's avatar
Tejun Heo committed
653
}
654

Tejun Heo's avatar
Tejun Heo committed
655
static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
Balbir Singh's avatar
Balbir Singh committed
656
{
657
	pr_cont_kernfs_path(cgrp->kn);
Balbir Singh's avatar
Balbir Singh committed
658
}
659

Johannes Weiner's avatar
Johannes Weiner committed
660
661
662
663
664
static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
{
	return &cgrp->psi;
}

665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
static inline void cgroup_init_kthreadd(void)
{
	/*
	 * kthreadd is inherited by all kthreads, keep it in the root so
	 * that the new kthreads are guaranteed to stay in the root until
	 * initialization is finished.
	 */
	current->no_cgroup_migration = 1;
}

static inline void cgroup_kthread_ready(void)
{
	/*
	 * This kthread finished initialization.  The creator should have
	 * set PF_NO_SETAFFINITY if this kthread should stay in the root.
	 */
	current->no_cgroup_migration = 0;
}

684
685
686
687
static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
{
	return &cgrp->kn->id;
}
688
689
690

void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
					char *buf, size_t buflen);
691
692
#else /* !CONFIG_CGROUPS */

693
struct cgroup_subsys_state;
694
struct cgroup;
695

696
static inline void css_put(struct cgroup_subsys_state *css) {}
Michael S. Tsirkin's avatar
Michael S. Tsirkin committed
697
static inline int cgroup_attach_task_all(struct task_struct *from,
698
699
700
701
					 struct task_struct *t) { return 0; }
static inline int cgroupstats_build(struct cgroupstats *stats,
				    struct dentry *dentry) { return -EINVAL; }

702
static inline void cgroup_fork(struct task_struct *p) {}
703
704
705
static inline int cgroup_can_fork(struct task_struct *p) { return 0; }
static inline void cgroup_cancel_fork(struct task_struct *p) {}
static inline void cgroup_post_fork(struct task_struct *p) {}
706
static inline void cgroup_exit(struct task_struct *p) {}
707
static inline void cgroup_release(struct task_struct *p) {}
708
static inline void cgroup_free(struct task_struct *p) {}
709

710
711
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
712
713
static inline void cgroup_init_kthreadd(void) {}
static inline void cgroup_kthread_ready(void) {}
714
715
716
717
static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
{
	return NULL;
}
718

Johannes Weiner's avatar
Johannes Weiner committed
719
720
721
722
723
724
725
726
727
728
static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
{
	return NULL;
}

static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
{
	return NULL;
}

729
730
731
732
733
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
					       struct cgroup *ancestor)
{
	return true;
}
734
735
736

static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
	char *buf, size_t buflen) {}
737
738
#endif /* !CONFIG_CGROUPS */

739
#ifdef CONFIG_CGROUPS
740
/*
741
 * cgroup scalable recursive statistics.
742
 */
743
744
void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
void cgroup_rstat_flush(struct cgroup *cgrp);
745
void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp);
746
747
void cgroup_rstat_flush_hold(struct cgroup *cgrp);
void cgroup_rstat_flush_release(void);
748

749
750
751
/*
 * Basic resource stats.
 */
752
753
754
755
756
757
758
759
760
#ifdef CONFIG_CGROUP_CPUACCT
void cpuacct_charge(struct task_struct *tsk, u64 cputime);
void cpuacct_account_field(struct task_struct *tsk, int index, u64 val);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
static inline void cpuacct_account_field(struct task_struct *tsk, int index,
					 u64 val) {}
#endif

761
762
763
764
void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec);
void __cgroup_account_cputime_field(struct cgroup *cgrp,
				    enum cpu_usage_stat index, u64 delta_exec);

765
766
767
static inline void cgroup_account_cputime(struct task_struct *task,
					  u64 delta_exec)
{
768
769
	struct cgroup *cgrp;

770
	cpuacct_charge(task, delta_exec);
771
772
773
774
775
776

	rcu_read_lock();
	cgrp = task_dfl_cgroup(task);
	if (cgroup_parent(cgrp))
		__cgroup_account_cputime(cgrp, delta_exec);
	rcu_read_unlock();
777
778
779
780
781
782
}

static inline void cgroup_account_cputime_field(struct task_struct *task,
						enum cpu_usage_stat index,
						u64 delta_exec)
{
783
784
	struct cgroup *cgrp;

785
	cpuacct_account_field(task, index, delta_exec);
786
787
788
789
790
791

	rcu_read_lock();
	cgrp = task_dfl_cgroup(task);
	if (cgroup_parent(cgrp))
		__cgroup_account_cputime_field(cgrp, index, delta_exec);
	rcu_read_unlock();
792
793
794
795
796
797
798
799
800
801
802
803
}

#else	/* CONFIG_CGROUPS */

static inline void cgroup_account_cputime(struct task_struct *task,
					  u64 delta_exec) {}
static inline void cgroup_account_cputime_field(struct task_struct *task,
						enum cpu_usage_stat index,
						u64 delta_exec) {}

#endif	/* CONFIG_CGROUPS */

Tejun Heo's avatar
Tejun Heo committed
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
/*
 * sock->sk_cgrp_data handling.  For more info, see sock_cgroup_data
 * definition in cgroup-defs.h.
 */
#ifdef CONFIG_SOCK_CGROUP_DATA

#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
extern spinlock_t cgroup_sk_update_lock;
#endif

void cgroup_sk_alloc_disable(void);
void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
void cgroup_sk_free(struct sock_cgroup_data *skcd);

static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
{
#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
	unsigned long v;

	/*
	 * @skcd->val is 64bit but the following is safe on 32bit too as we
	 * just need the lower ulong to be written and read atomically.
	 */
	v = READ_ONCE(skcd->val);

	if (v & 1)
		return &cgrp_dfl_root.cgrp;

	return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
#else
	return (struct cgroup *)(unsigned long)skcd->val;
#endif
}

#else	/* CONFIG_CGROUP_DATA */

static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}

#endif	/* CONFIG_CGROUP_DATA */

845
struct cgroup_namespace {
846
	refcount_t		count;
847
848
	struct ns_common	ns;
	struct user_namespace	*user_ns;
849
	struct ucounts		*ucounts;
850
851
852
853
854
855
856
857
858
859
860
861
862
	struct css_set          *root_cset;
};

extern struct cgroup_namespace init_cgroup_ns;

#ifdef CONFIG_CGROUPS

void free_cgroup_ns(struct cgroup_namespace *ns);

struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
					struct user_namespace *user_ns,
					struct cgroup_namespace *old_ns);

863
864
int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
		   struct cgroup_namespace *ns);
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880

#else /* !CONFIG_CGROUPS */

static inline void free_cgroup_ns(struct cgroup_namespace *ns) { }
static inline struct cgroup_namespace *
copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
	       struct cgroup_namespace *old_ns)
{
	return old_ns;
}

#endif /* !CONFIG_CGROUPS */

static inline void get_cgroup_ns(struct cgroup_namespace *ns)
{
	if (ns)
881
		refcount_inc(&ns->count);
882
883
884
885
}

static inline void put_cgroup_ns(struct cgroup_namespace *ns)
{
886
	if (ns && refcount_dec_and_test(&ns->count))
887
888
889
		free_cgroup_ns(ns);
}

Roman Gushchin's avatar
Roman Gushchin committed
890
891
892
893
894
895
896
897
#ifdef CONFIG_CGROUPS

void cgroup_enter_frozen(void);
void cgroup_leave_frozen(bool always_leave);
void cgroup_update_frozen(struct cgroup *cgrp);
void cgroup_freeze(struct cgroup *cgrp, bool freeze);
void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src,
				 struct cgroup *dst);
898

Roman Gushchin's avatar
Roman Gushchin committed
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
static inline bool cgroup_task_freeze(struct task_struct *task)
{
	bool ret;

	if (task->flags & PF_KTHREAD)
		return false;

	rcu_read_lock();
	ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags);
	rcu_read_unlock();

	return ret;
}

static inline bool cgroup_task_frozen(struct task_struct *task)
{
	return task->frozen;
}

#else /* !CONFIG_CGROUPS */

static inline void cgroup_enter_frozen(void) { }
static inline void cgroup_leave_frozen(bool always_leave) { }
static inline bool cgroup_task_freeze(struct task_struct *task)
{
	return false;
}
static inline bool cgroup_task_frozen(struct task_struct *task)
{
	return false;
}

#endif /* !CONFIG_CGROUPS */

933
#endif /* _LINUX_CGROUP_H */