summaryrefslogtreecommitdiffstats
path: root/include/linux/cgroup.h
blob: 2162dca88dc0881623272fd56017a84ae0f663de (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
#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/rculist.h>
#include <linux/cgroupstats.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/kernfs.h>
#include <linux/jump_label.h>

#include <linux/cgroup-defs.h>

#ifdef CONFIG_CGROUPS

/*
 * 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

/* a css_task_iter should be treated as an opaque object */
struct css_task_iter {
	struct cgroup_subsys		*ss;

	struct list_head		*cset_pos;
	struct list_head		*cset_head;

	struct list_head		*task_pos;
	struct list_head		*tasks_head;
	struct list_head		*mg_tasks_head;

	struct css_set			*cur_cset;
	struct task_struct		*cur_task;
	struct list_head		iters_node;	/* css_set->task_iters */
};

extern struct cgroup_root cgrp_dfl_root;
extern struct css_set init_css_set;

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

#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)

bool css_has_online_children(struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
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);

struct cgroup *cgroup_get_from_path(const char *path);

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);
void cgroup_file_notify(struct cgroup_file *cfile);

char *task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
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);
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);
void cgroup_exit(struct task_struct *p);
void cgroup_free(struct task_struct *p);

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

/*
 * 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);

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);

void css_task_iter_start(struct cgroup_subsys_state *css,
			 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.
 *
 * 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_child(pos, parent)					\
	for ((pos) = css_next_child(NULL, (parent)); (pos);		\
	     (pos) = css_next_child((pos), (parent)))

/**
 * 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
 * @dst_css: the destination css
 * @tset: taskset to iterate
 *
 * @tset may contain multiple tasks and they may belong to multiple
 * 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.
 *
 * Iteration is not in any specific order.
 */
#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)))

/**
 * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
 * @leader: the loop cursor
 * @dst_css: the destination css
 * @tset: takset to iterate
 *
 * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
 * may not contain any.
 */
#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)))	\
		if ((leader) != (leader)->group_leader)			\
			;						\
		else

/*
 * Inline functions.
 */

/**
 * 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)
{
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_get(&css->refcnt);
}

/**
 * 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);
}

/**
 * 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;
}

/**
 * css_tryget_online - try to obtain a reference on the specified css if online
 * @css: target css
 *
 * 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
 * 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_online(struct cgroup_subsys_state *css)
{
	if (!(css->flags & CSS_NO_REF))
		return percpu_ref_tryget_live(&css->refcnt);
	return true;
}

/**
 * css_put - put a css reference
 * @css: target css
 *
 * Put a reference obtained via css_get() and css_tryget_online().
 */
static inline void css_put(struct cgroup_subsys_state *css)
{
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_put(&css->refcnt);
}

/**
 * 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().
 */
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);
}

static inline void cgroup_put(struct cgroup *cgrp)
{
	css_put(&cgrp->self);
}

/**
 * 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.
 */
#ifdef CONFIG_PROVE_RCU
extern struct mutex cgroup_mutex;
extern spinlock_t css_set_lock;
#define task_css_set_check(task, __c)					\
	rcu_dereference_check((task)->cgroups,				\
		lockdep_is_held(&cgroup_mutex) ||			\
		lockdep_is_held(&css_set_lock) ||			\
		((task)->flags & PF_EXITING) || (__c))
#else
#define task_css_set_check(task, __c)					\
	rcu_dereference((task)->cgroups)
#endif

/**
 * task_css_check - obtain css for (task, subsys) w/ extra access conds
 * @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().
 */
#define task_css_check(task, subsys_id, __c)				\
	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);
}

/**
 * task_css - obtain css for (task, subsys)
 * @task: the target task
 * @subsys_id: the target subsystem ID
 *
 * See task_css_check().
 */
static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
						   int subsys_id)
{
	return task_css_check(task, subsys_id, false);
}

/**
 * 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
 * valid css.
 */
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);
		if (likely(css_tryget_online(css)))
			break;
		cpu_relax();
	}
	rcu_read_unlock();
	return css;
}

/**
 * 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];
}

static inline struct cgroup *task_cgroup(struct task_struct *task,
					 int subsys_id)
{
	return task_css(task, subsys_id)->cgroup;
}

/**
 * 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;
}

/* no synchronization, the result can only be used as a hint */
static inline bool cgroup_is_populated(struct cgroup *cgrp)
{
	return cgrp->populated_cnt;
}

/* returns ino associated with a cgroup */
static inline ino_t cgroup_ino(struct cgroup *cgrp)
{
	return cgrp->kn->ino;
}

/* cft/css accessors for cftype->write() operation */
static inline struct cftype *of_cft(struct kernfs_open_file *of)
{
	return of->kn->priv;
}

struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);

/* cft/css accessors for cftype->seq_*() operations */
static inline struct cftype *seq_cft(struct seq_file *seq)
{
	return of_cft(seq->private);
}

static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
{
	return of_css(seq->private);
}

/*
 * Name / path handling functions.  All are thin wrappers around the kernfs
 * counterparts and can be called under any context.
 */

static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
{
	return kernfs_name(cgrp->kn, buf, buflen);
}

static inline char * __must_check cgroup_path(struct cgroup *cgrp, char *buf,
					      size_t buflen)
{
	return kernfs_path(cgrp->kn, buf, buflen);
}

static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
{
	pr_cont_kernfs_name(cgrp->kn);
}

static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
{
	pr_cont_kernfs_path(cgrp->kn);
}

#else /* !CONFIG_CGROUPS */

struct cgroup_subsys_state;

static inline void css_put(struct cgroup_subsys_state *css) {}
static inline int cgroup_attach_task_all(struct task_struct *from,
					 struct task_struct *t) { return 0; }
static inline int cgroupstats_build(struct cgroupstats *stats,
				    struct dentry *dentry) { return -EINVAL; }

static inline void cgroup_fork(struct task_struct *p) {}
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) {}
static inline void cgroup_exit(struct task_struct *p) {}
static inline void cgroup_free(struct task_struct *p) {}

static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }

#endif /* !CONFIG_CGROUPS */

/*
 * 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 */

#endif /* _LINUX_CGROUP_H */