cgroup.h 22.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
#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>
14
#include <linux/rculist.h>
B
Balbir Singh 已提交
15
#include <linux/cgroupstats.h>
16
#include <linux/fs.h>
17
#include <linux/seq_file.h>
T
Tejun Heo 已提交
18
#include <linux/kernfs.h>
19
#include <linux/jump_label.h>
20 21 22 23
#include <linux/types.h>
#include <linux/ns_common.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.h>
24
#include <linux/refcount.h>
25

26
#include <linux/cgroup-defs.h>
27 28 29

#ifdef CONFIG_CGROUPS

30 31 32 33 34 35 36 37 38
/*
 * 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

39 40 41
/* walk only threadgroup leaders */
#define CSS_TASK_ITER_PROCS		(1U << 0)

42 43 44
/* a css_task_iter should be treated as an opaque object */
struct css_task_iter {
	struct cgroup_subsys		*ss;
45
	unsigned int			flags;
46 47 48

	struct list_head		*cset_pos;
	struct list_head		*cset_head;
49

50 51 52
	struct list_head		*task_pos;
	struct list_head		*tasks_head;
	struct list_head		*mg_tasks_head;
53 54 55 56

	struct css_set			*cur_cset;
	struct task_struct		*cur_task;
	struct list_head		iters_node;	/* css_set->task_iters */
57
};
58

59 60
extern struct cgroup_root cgrp_dfl_root;
extern struct css_set init_css_set;
61

62
#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
63 64 65
#include <linux/cgroup_subsys.h>
#undef SUBSYS

66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85
#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)

86 87 88 89 90 91 92
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);

93
struct cgroup *cgroup_get_from_path(const char *path);
94
struct cgroup *cgroup_get_from_fd(int fd);
95

96 97 98 99 100 101
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);
102
void cgroup_file_notify(struct cgroup_file *cfile);
103

104
int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
105 106 107 108 109
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);
110 111 112
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);
113
void cgroup_exit(struct task_struct *p);
114
void cgroup_free(struct task_struct *p);
115 116 117 118

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

T
Tejun Heo 已提交
119
/*
120 121 122 123 124 125 126 127 128 129 130
 * 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);

131 132 133 134
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);
135

136
void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
			 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.
T
Tejun Heo 已提交
154
 *
155 156 157
 * 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.
T
Tejun Heo 已提交
158
 */
159 160 161
#define css_for_each_child(pos, parent)					\
	for ((pos) = css_next_child(NULL, (parent)); (pos);		\
	     (pos) = css_next_child((pos), (parent)))
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
/**
 * 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
249
 * @dst_css: the destination css
250
 * @tset: taskset to iterate
251 252
 *
 * @tset may contain multiple tasks and they may belong to multiple
253 254 255 256 257 258 259 260
 * 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.
261 262
 *
 * Iteration is not in any specific order.
263
 */
264 265 266 267
#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)))
268

269 270 271
/**
 * cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
 * @leader: the loop cursor
272
 * @dst_css: the destination css
G
Geliang Tang 已提交
273
 * @tset: taskset to iterate
274 275 276 277
 *
 * Iterate threadgroup leaders of @tset.  For single-task migrations, @tset
 * may not contain any.
 */
278 279 280 281
#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)))	\
282 283 284 285
		if ((leader) != (leader)->group_leader)			\
			;						\
		else

286 287 288
/*
 * Inline functions.
 */
289

290 291 292 293 294
/**
 * css_get - obtain a reference on the specified css
 * @css: target css
 *
 * The caller must already have a reference.
295 296 297
 */
static inline void css_get(struct cgroup_subsys_state *css)
{
298 299
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_get(&css->refcnt);
300
}
P
Paul Menage 已提交
301

302 303 304 305 306 307 308 309 310 311 312 313 314
/**
 * 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);
}

T
Tejun Heo 已提交
315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332
/**
 * 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;
}

333
/**
334
 * css_tryget_online - try to obtain a reference on the specified css if online
335 336
 * @css: target css
 *
337 338
 * 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
339 340 341 342
 * reference on it - IOW, RCU protected access is good enough for this
 * function.  Returns %true if a reference count was successfully obtained;
 * %false otherwise.
 */
343
static inline bool css_tryget_online(struct cgroup_subsys_state *css)
P
Paul Menage 已提交
344
{
345 346 347
	if (!(css->flags & CSS_NO_REF))
		return percpu_ref_tryget_live(&css->refcnt);
	return true;
P
Paul Menage 已提交
348
}
349

350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
/**
 * 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);
}

370
/**
371 372 373
 * css_put - put a css reference
 * @css: target css
 *
374
 * Put a reference obtained via css_get() and css_tryget_online().
375
 */
376 377
static inline void css_put(struct cgroup_subsys_state *css)
{
378 379
	if (!(css->flags & CSS_NO_REF))
		percpu_ref_put(&css->refcnt);
380
}
381

382 383 384 385 386 387
/**
 * 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().
388
 */
389 390 391 392 393
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);
}
394

395 396 397 398 399
static inline void cgroup_put(struct cgroup *cgrp)
{
	css_put(&cgrp->self);
}

400 401 402 403 404 405 406 407 408 409 410 411
/**
 * 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.
412
 */
T
Tejun Heo 已提交
413 414
#ifdef CONFIG_PROVE_RCU
extern struct mutex cgroup_mutex;
415
extern spinlock_t css_set_lock;
416 417
#define task_css_set_check(task, __c)					\
	rcu_dereference_check((task)->cgroups,				\
418
		lockdep_is_held(&cgroup_mutex) ||			\
419
		lockdep_is_held(&css_set_lock) ||			\
420
		((task)->flags & PF_EXITING) || (__c))
T
Tejun Heo 已提交
421
#else
422 423
#define task_css_set_check(task, __c)					\
	rcu_dereference((task)->cgroups)
T
Tejun Heo 已提交
424
#endif
425

426
/**
427
 * task_css_check - obtain css for (task, subsys) w/ extra access conds
428 429 430 431 432 433 434
 * @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().
 */
435
#define task_css_check(task, subsys_id, __c)				\
436 437 438 439 440 441 442 443 444 445 446 447 448 449
	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);
}

/**
450
 * task_css - obtain css for (task, subsys)
451 452 453
 * @task: the target task
 * @subsys_id: the target subsystem ID
 *
454
 * See task_css_check().
455
 */
456 457
static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
						   int subsys_id)
458
{
459
	return task_css_check(task, subsys_id, false);
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
/**
 * 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;
}

T
Tejun Heo 已提交
487 488 489 490 491 492 493 494 495 496 497 498 499 500
/**
 * 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];
}

501 502
static inline struct cgroup *task_cgroup(struct task_struct *task,
					 int subsys_id)
503
{
504
	return task_css(task, subsys_id)->cgroup;
505 506
}

507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
/**
 * 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;
}

524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540
/**
 * 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);
}

541
/* no synchronization, the result can only be used as a hint */
542
static inline bool cgroup_is_populated(struct cgroup *cgrp)
543
{
544
	return cgrp->nr_populated_csets + cgrp->nr_populated_children;
545
}
546

547
/* returns ino associated with a cgroup */
T
Tejun Heo 已提交
548 549
static inline ino_t cgroup_ino(struct cgroup *cgrp)
{
550
	return cgrp->kn->ino;
T
Tejun Heo 已提交
551
}
552

T
Tejun Heo 已提交
553 554
/* cft/css accessors for cftype->write() operation */
static inline struct cftype *of_cft(struct kernfs_open_file *of)
555
{
T
Tejun Heo 已提交
556
	return of->kn->priv;
557
}
T
Tejun Heo 已提交
558

T
Tejun Heo 已提交
559
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
560

T
Tejun Heo 已提交
561 562 563 564 565
/* cft/css accessors for cftype->seq_*() operations */
static inline struct cftype *seq_cft(struct seq_file *seq)
{
	return of_cft(seq->private);
}
T
Tejun Heo 已提交
566

T
Tejun Heo 已提交
567 568 569 570
static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
{
	return of_css(seq->private);
}
M
Michael S. Tsirkin 已提交
571

T
Tejun Heo 已提交
572 573 574 575
/*
 * Name / path handling functions.  All are thin wrappers around the kernfs
 * counterparts and can be called under any context.
 */
K
KAMEZAWA Hiroyuki 已提交
576

T
Tejun Heo 已提交
577 578
static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
{
579
	return kernfs_name(cgrp->kn, buf, buflen);
T
Tejun Heo 已提交
580
}
581

582
static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
T
Tejun Heo 已提交
583
{
584
	return kernfs_path(cgrp->kn, buf, buflen);
T
Tejun Heo 已提交
585
}
586

T
Tejun Heo 已提交
587 588
static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
{
589
	pr_cont_kernfs_name(cgrp->kn);
T
Tejun Heo 已提交
590
}
591

T
Tejun Heo 已提交
592
static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
B
Balbir Singh 已提交
593
{
594
	pr_cont_kernfs_path(cgrp->kn);
B
Balbir Singh 已提交
595
}
596

597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615
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;
}

616 617
#else /* !CONFIG_CGROUPS */

618
struct cgroup_subsys_state;
619
struct cgroup;
620

621
static inline void css_put(struct cgroup_subsys_state *css) {}
M
Michael S. Tsirkin 已提交
622
static inline int cgroup_attach_task_all(struct task_struct *from,
623 624 625 626
					 struct task_struct *t) { return 0; }
static inline int cgroupstats_build(struct cgroupstats *stats,
				    struct dentry *dentry) { return -EINVAL; }

627
static inline void cgroup_fork(struct task_struct *p) {}
628 629 630
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) {}
631
static inline void cgroup_exit(struct task_struct *p) {}
632
static inline void cgroup_free(struct task_struct *p) {}
633

634 635
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
636 637
static inline void cgroup_init_kthreadd(void) {}
static inline void cgroup_kthread_ready(void) {}
638

639 640 641 642 643
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
					       struct cgroup *ancestor)
{
	return true;
}
644 645
#endif /* !CONFIG_CGROUPS */

T
Tejun Heo 已提交
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
/*
 * 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 */

687
struct cgroup_namespace {
688
	refcount_t		count;
689 690
	struct ns_common	ns;
	struct user_namespace	*user_ns;
691
	struct ucounts		*ucounts;
692 693 694 695 696 697 698 699 700 701 702 703 704
	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);

705 706
int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
		   struct cgroup_namespace *ns);
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722

#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)
723
		refcount_inc(&ns->count);
724 725 726 727
}

static inline void put_cgroup_ns(struct cgroup_namespace *ns)
{
728
	if (ns && refcount_dec_and_test(&ns->count))
729 730 731
		free_cgroup_ns(ns);
}

732
#endif /* _LINUX_CGROUP_H */