cgroup-defs.h 25.8 KB
Newer Older
1
/* SPDX-License-Identifier: GPL-2.0 */
2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * linux/cgroup-defs.h - basic definitions for cgroup
 *
 * This file provides basic type and interface.  Include this file directly
 * only if necessary to avoid cyclic dependencies.
 */
#ifndef _LINUX_CGROUP_DEFS_H
#define _LINUX_CGROUP_DEFS_H

#include <linux/limits.h>
#include <linux/list.h>
#include <linux/idr.h>
#include <linux/wait.h>
#include <linux/mutex.h>
#include <linux/rcupdate.h>
17
#include <linux/refcount.h>
18
#include <linux/percpu-refcount.h>
19
#include <linux/percpu-rwsem.h>
20
#include <linux/u64_stats_sync.h>
21
#include <linux/workqueue.h>
22
#include <linux/bpf-cgroup.h>
23 24 25 26 27 28 29 30 31 32

#ifdef CONFIG_CGROUPS

struct cgroup;
struct cgroup_root;
struct cgroup_subsys;
struct cgroup_taskset;
struct kernfs_node;
struct kernfs_ops;
struct kernfs_open_file;
33
struct seq_file;
34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51

#define MAX_CGROUP_TYPE_NAMELEN 32
#define MAX_CGROUP_ROOT_NAMELEN 64
#define MAX_CFTYPE_NAME		64

/* define the enumeration of all cgroup subsystems */
#define SUBSYS(_x) _x ## _cgrp_id,
enum cgroup_subsys_id {
#include <linux/cgroup_subsys.h>
	CGROUP_SUBSYS_COUNT,
};
#undef SUBSYS

/* bits in struct cgroup_subsys_state flags field */
enum {
	CSS_NO_REF	= (1 << 0), /* no reference counting for this css */
	CSS_ONLINE	= (1 << 1), /* between ->css_online() and ->css_offline() */
	CSS_RELEASED	= (1 << 2), /* refcnt reached zero, released */
52
	CSS_VISIBLE	= (1 << 3), /* css is visible to userland */
53
	CSS_DYING	= (1 << 4), /* css is dying */
54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71
};

/* bits in struct cgroup flags field */
enum {
	/* Control Group requires release notifications to userspace */
	CGRP_NOTIFY_ON_RELEASE,
	/*
	 * Clone the parent's configuration when creating a new child
	 * cpuset cgroup.  For historical reasons, this option can be
	 * specified at mount time and thus is implemented here.
	 */
	CGRP_CPUSET_CLONE_CHILDREN,
};

/* cgroup_root->flags */
enum {
	CGRP_ROOT_NOPREFIX	= (1 << 1), /* mounted subsystems have no named prefix */
	CGRP_ROOT_XATTR		= (1 << 2), /* supports extended attributes */
72 73 74 75 76 77 78

	/*
	 * Consider namespaces as delegation boundaries.  If this flag is
	 * set, controller specific interface files in a namespace root
	 * aren't writeable from inside the namespace.
	 */
	CGRP_ROOT_NS_DELEGATE	= (1 << 3),
79 80 81 82 83

	/*
	 * Enable cpuset controller in v1 cgroup to use v2 behavior.
	 */
	CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
84 85 86 87 88 89
};

/* cftype->flags */
enum {
	CFTYPE_ONLY_ON_ROOT	= (1 << 0),	/* only create on root cgrp */
	CFTYPE_NOT_ON_ROOT	= (1 << 1),	/* don't create on root cgrp */
90 91
	CFTYPE_NS_DELEGATABLE	= (1 << 2),	/* writeable beyond delegation boundaries */

92
	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
93
	CFTYPE_WORLD_WRITABLE	= (1 << 4),	/* (DON'T USE FOR NEW FILES) S_IWUGO */
94 95 96 97 98 99

	/* internal flags, do not use outside cgroup core proper */
	__CFTYPE_ONLY_ON_DFL	= (1 << 16),	/* only on default hierarchy */
	__CFTYPE_NOT_ON_DFL	= (1 << 17),	/* not on default hierarchy */
};

100 101 102 103 104 105 106 107
/*
 * cgroup_file is the handle for a file instance created in a cgroup which
 * is used, for example, to generate file changed notifications.  This can
 * be obtained by setting cftype->file_offset.
 */
struct cgroup_file {
	/* do not access any fields from outside cgroup core */
	struct kernfs_node *kn;
108 109
	unsigned long notified_at;
	struct timer_list notify_timer;
110 111
};

112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
/*
 * Per-subsystem/per-cgroup state maintained by the system.  This is the
 * fundamental structural building block that controllers deal with.
 *
 * Fields marked with "PI:" are public and immutable and may be accessed
 * directly without synchronization.
 */
struct cgroup_subsys_state {
	/* PI: the cgroup that this css is attached to */
	struct cgroup *cgroup;

	/* PI: the cgroup subsystem that this css is attached to */
	struct cgroup_subsys *ss;

	/* reference count - access via css_[try]get() and css_put() */
	struct percpu_ref refcnt;

	/* siblings list anchored at the parent's ->children */
	struct list_head sibling;
	struct list_head children;

133 134 135
	/* flush target list anchored at cgrp->rstat_css_list */
	struct list_head rstat_css_node;

136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151
	/*
	 * PI: Subsys-unique ID.  0 is unused and root is always 1.  The
	 * matching css can be looked up using css_from_id().
	 */
	int id;

	unsigned int flags;

	/*
	 * Monotonically increasing unique serial number which defines a
	 * uniform order among all csses.  It's guaranteed that all
	 * ->children lists are in the ascending order of ->serial_nr and
	 * used to allow interrupting and resuming iterations.
	 */
	u64 serial_nr;

152 153 154 155 156 157
	/*
	 * Incremented by online self and children.  Used to guarantee that
	 * parents are not offlined before their children.
	 */
	atomic_t online_cnt;

158 159
	/* percpu_ref killing and RCU release */
	struct work_struct destroy_work;
160
	struct rcu_work destroy_rwork;
161 162 163 164 165 166

	/*
	 * PI: the parent css.	Placed here for cache proximity to following
	 * fields of the containing structure.
	 */
	struct cgroup_subsys_state *parent;
167 168 169 170 171 172 173 174 175 176 177
};

/*
 * 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 {
	/*
T
Tejun Heo 已提交
178 179 180
	 * 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).
181
	 */
T
Tejun Heo 已提交
182 183 184
	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];

	/* reference count */
185
	refcount_t refcount;
T
Tejun Heo 已提交
186

187 188 189 190 191 192 193 194
	/*
	 * For a domain cgroup, the following points to self.  If threaded,
	 * to the matching cset of the nearest domain ancestor.  The
	 * dom_cset provides access to the domain cgroup and its csses to
	 * which domain level resource consumptions should be charged.
	 */
	struct css_set *dom_cset;

T
Tejun Heo 已提交
195 196
	/* the default cgroup associated with this css_set */
	struct cgroup *dfl_cgrp;
197

198 199 200
	/* internal task count, protected by css_set_lock */
	int nr_tasks;

201 202 203 204 205 206 207 208 209
	/*
	 * Lists running through all tasks using this cgroup group.
	 * mg_tasks lists tasks which belong to this cset but are in the
	 * process of being migrated out or in.  Protected by
	 * css_set_rwsem, but, during migration, once tasks are moved to
	 * mg_tasks, it can be read safely while holding cgroup_mutex.
	 */
	struct list_head tasks;
	struct list_head mg_tasks;
210
	struct list_head dying_tasks;
211

T
Tejun Heo 已提交
212 213 214
	/* all css_task_iters currently walking this cset */
	struct list_head task_iters;

215
	/*
T
Tejun Heo 已提交
216 217 218 219 220
	 * On the default hierarhcy, ->subsys[ssid] may point to a css
	 * attached to an ancestor instead of the cgroup this css_set is
	 * associated with.  The following node is anchored at
	 * ->subsys[ssid]->cgroup->e_csets[ssid] and provides a way to
	 * iterate through all css's attached to a given cgroup.
221
	 */
T
Tejun Heo 已提交
222
	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];
223

224 225 226 227
	/* all threaded csets whose ->dom_cset points to this cset */
	struct list_head threaded_csets;
	struct list_head threaded_csets_node;

T
Tejun Heo 已提交
228 229 230 231 232
	/*
	 * List running through all cgroup groups in the same hash
	 * slot. Protected by css_set_lock
	 */
	struct hlist_node hlist;
233 234

	/*
T
Tejun Heo 已提交
235 236
	 * List of cgrp_cset_links pointing at cgroups referenced from this
	 * css_set.  Protected by css_set_lock.
237
	 */
T
Tejun Heo 已提交
238
	struct list_head cgrp_links;
239 240 241 242 243 244 245 246 247 248

	/*
	 * List of csets participating in the on-going migration either as
	 * source or destination.  Protected by cgroup_mutex.
	 */
	struct list_head mg_preload_node;
	struct list_head mg_node;

	/*
	 * If this cset is acting as the source of migration the following
249 250 251 252
	 * two fields are set.  mg_src_cgrp and mg_dst_cgrp are
	 * respectively the source and destination cgroups of the on-going
	 * migration.  mg_dst_cset is the destination cset the target tasks
	 * on this cset should be migrated to.  Protected by cgroup_mutex.
253 254
	 */
	struct cgroup *mg_src_cgrp;
255
	struct cgroup *mg_dst_cgrp;
256 257
	struct css_set *mg_dst_cset;

258 259 260
	/* dead and being drained, ignore for migration */
	bool dead;

261 262 263 264
	/* For RCU-protected deletion */
	struct rcu_head rcu_head;
};

265 266 267 268
struct cgroup_base_stat {
	struct task_cputime cputime;
};

269
/*
T
Tejun Heo 已提交
270 271 272
 * rstat - cgroup scalable recursive statistics.  Accounting is done
 * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the
 * hierarchy on reads.
273
 *
T
Tejun Heo 已提交
274
 * When a stat gets updated, the cgroup_rstat_cpu and its ancestors are
275 276 277 278 279 280 281 282 283
 * linked into the updated tree.  On the following read, propagation only
 * considers and consumes the updated tree.  This makes reading O(the
 * number of descendants which have been active since last read) instead of
 * O(the total number of descendants).
 *
 * This is important because there can be a lot of (draining) cgroups which
 * aren't active and stat may be read frequently.  The combination can
 * become very expensive.  By propagating selectively, increasing reading
 * frequency decreases the cost of each read.
284 285 286 287
 *
 * This struct hosts both the fields which implement the above -
 * updated_children and updated_next - and the fields which track basic
 * resource statistics on top of it - bsync, bstat and last_bstat.
288
 */
T
Tejun Heo 已提交
289
struct cgroup_rstat_cpu {
290
	/*
291 292
	 * ->bsync protects ->bstat.  These are the only fields which get
	 * updated in the hot path.
293
	 */
294 295
	struct u64_stats_sync bsync;
	struct cgroup_base_stat bstat;
296 297 298 299 300

	/*
	 * Snapshots at the last reading.  These are used to calculate the
	 * deltas to propagate to the global counters.
	 */
301
	struct cgroup_base_stat last_bstat;
302 303 304 305 306 307 308 309 310 311

	/*
	 * Child cgroups with stat updates on this cpu since the last read
	 * are linked on the parent's ->updated_children through
	 * ->updated_next.
	 *
	 * In addition to being more compact, singly-linked list pointing
	 * to the cgroup makes it unnecessary for each per-cpu struct to
	 * point back to the associated cgroup.
	 *
T
Tejun Heo 已提交
312
	 * Protected by per-cpu cgroup_rstat_cpu_lock.
313 314 315 316 317
	 */
	struct cgroup *updated_children;	/* terminated by self cgroup */
	struct cgroup *updated_next;		/* NULL iff not on the list */
};

318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333
struct cgroup {
	/* self css with NULL ->ss, points back to this cgroup */
	struct cgroup_subsys_state self;

	unsigned long flags;		/* "unsigned long" so bitops work */

	/*
	 * idr allocated in-hierarchy ID.
	 *
	 * ID 0 is not used, the ID of the root cgroup is always 1, and a
	 * new cgroup will be assigned with a smallest available ID.
	 *
	 * Allocating/Removing ID must be protected by cgroup_mutex.
	 */
	int id;

334 335 336 337 338 339 340 341
	/*
	 * The depth this cgroup is at.  The root is at depth zero and each
	 * step down the hierarchy increments the level.  This along with
	 * ancestor_ids[] can determine whether a given cgroup is a
	 * descendant of another without traversing the hierarchy.
	 */
	int level;

342 343 344
	/* Maximum allowed descent tree depth */
	int max_depth;

345 346 347 348
	/*
	 * Keep track of total numbers of visible and dying descent cgroups.
	 * Dying cgroups are cgroups which were deleted by a user,
	 * but are still existing because someone else is holding a reference.
349
	 * max_descendants is a maximum allowed number of descent cgroups.
350 351 352 353 354
	 *
	 * nr_descendants and nr_dying_descendants are protected
	 * by cgroup_mutex and css_set_lock. It's fine to read them holding
	 * any of cgroup_mutex and css_set_lock; for writing both locks
	 * should be held.
355 356 357
	 */
	int nr_descendants;
	int nr_dying_descendants;
358
	int max_descendants;
359

360
	/*
361
	 * Each non-empty css_set associated with this cgroup contributes
362 363 364 365
	 * one to nr_populated_csets.  The counter is zero iff this cgroup
	 * doesn't have any tasks.
	 *
	 * All children which have non-zero nr_populated_csets and/or
366 367 368 369
	 * nr_populated_children of their own contribute one to either
	 * nr_populated_domain_children or nr_populated_threaded_children
	 * depending on their type.  Each counter is zero iff all cgroups
	 * of the type in the subtree proper don't have any tasks.
370
	 */
371
	int nr_populated_csets;
372 373 374 375
	int nr_populated_domain_children;
	int nr_populated_threaded_children;

	int nr_threaded_children;	/* # of live threaded child cgroups */
376 377

	struct kernfs_node *kn;		/* cgroup kernfs entry */
378 379
	struct cgroup_file procs_file;	/* handle for "cgroup.procs" */
	struct cgroup_file events_file;	/* handle for "cgroup.events" */
380 381 382 383

	/*
	 * The bitmask of subsystems enabled on the child cgroups.
	 * ->subtree_control is the one configured through
384 385 386
	 * "cgroup.subtree_control" while ->child_ss_mask is the effective
	 * one which may have more subsystems enabled.  Controller knobs
	 * are made available iff it's enabled in ->subtree_control.
387
	 */
388 389
	u16 subtree_control;
	u16 subtree_ss_mask;
390 391
	u16 old_subtree_control;
	u16 old_subtree_ss_mask;
392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412

	/* Private pointers for each registered subsystem */
	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];

	struct cgroup_root *root;

	/*
	 * List of cgrp_cset_links pointing at css_sets with tasks in this
	 * cgroup.  Protected by css_set_lock.
	 */
	struct list_head cset_links;

	/*
	 * On the default hierarchy, a css_set for a cgroup with some
	 * susbsys disabled will point to css's which are associated with
	 * the closest ancestor which has the subsys enabled.  The
	 * following lists all css_sets which point to this cgroup's css
	 * for the given subsystem.
	 */
	struct list_head e_csets[CGROUP_SUBSYS_COUNT];

413 414 415 416 417 418 419 420
	/*
	 * If !threaded, self.  If threaded, it points to the nearest
	 * domain ancestor.  Inside a threaded subtree, cgroups are exempt
	 * from process granularity and no-internal-task constraint.
	 * Domain level resource consumptions which aren't tied to a
	 * specific task are charged to the dom_cgrp.
	 */
	struct cgroup *dom_cgrp;
421
	struct cgroup *old_dom_cgrp;		/* used while enabling threaded */
422

T
Tejun Heo 已提交
423 424
	/* per-cpu recursive resource statistics */
	struct cgroup_rstat_cpu __percpu *rstat_cpu;
425
	struct list_head rstat_css_list;
T
Tejun Heo 已提交
426

427
	/* cgroup basic resource statistics */
428 429 430
	struct cgroup_base_stat pending_bstat;	/* pending from children */
	struct cgroup_base_stat bstat;
	struct prev_cputime prev_cputime;	/* for printing out cputime */
431

432 433 434 435 436 437 438 439 440 441 442 443
	/*
	 * 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;

	/* used to wait for offlining of csses */
	wait_queue_head_t offline_waitq;

	/* used to schedule release agent */
	struct work_struct release_agent_work;
444

445 446 447
	/* used to store eBPF programs */
	struct cgroup_bpf bpf;

448 449 450
	/* If there is block congestion on this cgroup. */
	atomic_t congestion_count;

451 452
	/* ids of the ancestors at each level including self */
	int ancestor_ids[];
453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471
};

/*
 * A cgroup_root represents the root of a cgroup hierarchy, and may be
 * associated with a kernfs_root to form an active hierarchy.  This is
 * internal to cgroup core.  Don't access directly from controllers.
 */
struct cgroup_root {
	struct kernfs_root *kf_root;

	/* The bitmask of subsystems attached to this hierarchy */
	unsigned int subsys_mask;

	/* Unique id for this hierarchy. */
	int hierarchy_id;

	/* The root cgroup.  Root is destroyed on its release. */
	struct cgroup cgrp;

472 473 474
	/* for cgrp->ancestor_ids[0] */
	int cgrp_ancestor_id_storage;

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
	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
	atomic_t nr_cgrps;

	/* A list running through the active hierarchies */
	struct list_head root_list;

	/* Hierarchy-specific flags */
	unsigned int flags;

	/* IDs for cgroups in this hierarchy */
	struct idr cgroup_idr;

	/* The path to use for release notifications. */
	char release_agent_path[PATH_MAX];

	/* The name for this hierarchy - may be empty */
	char name[MAX_CGROUP_ROOT_NAMELEN];
};

/*
 * struct cftype: handler definitions for cgroup control files
 *
 * When reading/writing to a file:
 *	- the cgroup to use is file->f_path.dentry->d_parent->d_fsdata
 *	- the 'cftype' of the file is file->f_path.dentry->d_fsdata
 */
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];
508
	unsigned long private;
509 510 511 512 513 514 515 516 517 518

	/*
	 * The maximum length of string, excluding trailing nul, that can
	 * be passed to write.  If < PAGE_SIZE-1, PAGE_SIZE-1 is assumed.
	 */
	size_t max_write_len;

	/* CFTYPE_* flags */
	unsigned int flags;

519 520 521 522 523 524 525 526
	/*
	 * If non-zero, should contain the offset from the start of css to
	 * a struct cgroup_file field.  cgroup will record the handle of
	 * the created file into it.  The recorded handle can be used as
	 * long as the containing css remains accessible.
	 */
	unsigned int file_offset;

527 528 529 530 531 532 533 534
	/*
	 * Fields used for internal bookkeeping.  Initialized automatically
	 * during registration.
	 */
	struct cgroup_subsys *ss;	/* NULL for cgroup core files */
	struct list_head node;		/* anchored at ss->cfts */
	struct kernfs_ops *kf_ops;

535 536 537
	int (*open)(struct kernfs_open_file *of);
	void (*release)(struct kernfs_open_file *of);

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
	/*
	 * 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_subsys_state *css, struct cftype *cft);
	/*
	 * read_s64() is a signed version of read_u64()
	 */
	s64 (*read_s64)(struct cgroup_subsys_state *css, struct cftype *cft);

	/* generic seq_file read interface */
	int (*seq_show)(struct seq_file *sf, void *v);

	/* optional ops, implement all or none */
	void *(*seq_start)(struct seq_file *sf, loff_t *ppos);
	void *(*seq_next)(struct seq_file *sf, void *v, loff_t *ppos);
	void (*seq_stop)(struct seq_file *sf, void *v);

	/*
	 * write_u64() is a shortcut for the common case of accepting
	 * a single integer (as parsed by simple_strtoull) from
	 * userspace. Use in place of write(); return 0 or error.
	 */
	int (*write_u64)(struct cgroup_subsys_state *css, struct cftype *cft,
			 u64 val);
	/*
	 * write_s64() is a signed version of write_u64()
	 */
	int (*write_s64)(struct cgroup_subsys_state *css, struct cftype *cft,
			 s64 val);

	/*
	 * write() is the generic write callback which maps directly to
	 * kernfs write operation and overrides all other operations.
	 * Maximum write size is determined by ->max_write_len.  Use
	 * of_css/cft() to access the associated css and cft.
	 */
	ssize_t (*write)(struct kernfs_open_file *of,
			 char *buf, size_t nbytes, loff_t off);

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lock_class_key	lockdep_key;
#endif
};

/*
 * Control Group subsystem type.
585
 * See Documentation/cgroup-v1/cgroups.txt for details
586 587 588 589 590 591 592 593
 */
struct cgroup_subsys {
	struct cgroup_subsys_state *(*css_alloc)(struct cgroup_subsys_state *parent_css);
	int (*css_online)(struct cgroup_subsys_state *css);
	void (*css_offline)(struct cgroup_subsys_state *css);
	void (*css_released)(struct cgroup_subsys_state *css);
	void (*css_free)(struct cgroup_subsys_state *css);
	void (*css_reset)(struct cgroup_subsys_state *css);
594
	void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu);
595 596
	int (*css_extra_stat_show)(struct seq_file *seq,
				   struct cgroup_subsys_state *css);
597

598 599 600
	int (*can_attach)(struct cgroup_taskset *tset);
	void (*cancel_attach)(struct cgroup_taskset *tset);
	void (*attach)(struct cgroup_taskset *tset);
601
	void (*post_attach)(void);
602 603 604
	int (*can_fork)(struct task_struct *task);
	void (*cancel_fork)(struct task_struct *task);
	void (*fork)(struct task_struct *task);
605
	void (*exit)(struct task_struct *task);
606
	void (*release)(struct task_struct *task);
607 608
	void (*bind)(struct cgroup_subsys_state *root_css);

609
	bool early_init:1;
610

611 612 613 614 615 616 617 618 619 620 621 622 623
	/*
	 * If %true, the controller, on the default hierarchy, doesn't show
	 * up in "cgroup.controllers" or "cgroup.subtree_control", is
	 * implicitly enabled on all cgroups on the default hierarchy, and
	 * bypasses the "no internal process" constraint.  This is for
	 * utility type controllers which is transparent to userland.
	 *
	 * An implicit controller can be stolen from the default hierarchy
	 * anytime and thus must be okay with offline csses from previous
	 * hierarchies coexisting with csses for the current one.
	 */
	bool implicit_on_dfl:1;

624 625 626 627 628 629 630 631 632 633 634 635
	/*
	 * If %true, the controller, supports threaded mode on the default
	 * hierarchy.  In a threaded subtree, both process granularity and
	 * no-internal-process constraint are ignored and a threaded
	 * controllers should be able to handle that.
	 *
	 * Note that as an implicit controller is automatically enabled on
	 * all cgroups on the default hierarchy, it should also be
	 * threaded.  implicit && !threaded is not supported.
	 */
	bool threaded:1;

636 637 638 639 640 641 642 643 644 645 646 647
	/*
	 * If %false, this subsystem is properly hierarchical -
	 * configuration, resource accounting and restriction on a parent
	 * cgroup cover those of its children.  If %true, hierarchy support
	 * is broken in some ways - some subsystems ignore hierarchy
	 * completely while others are only implemented half-way.
	 *
	 * It's now disallowed to create nested cgroups if the subsystem is
	 * broken and cgroup core will emit a warning message on such
	 * cases.  Eventually, all subsystems will be made properly
	 * hierarchical and this will go away.
	 */
648 649
	bool broken_hierarchy:1;
	bool warned_broken_hierarchy:1;
650 651 652 653 654

	/* the following two fields are initialized automtically during boot */
	int id;
	const char *name;

655 656 657
	/* optional, initialized automatically during boot if not set */
	const char *legacy_name;

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
	/* link to parent, protected by cgroup_lock() */
	struct cgroup_root *root;

	/* idr for css->id */
	struct idr css_idr;

	/*
	 * List of cftypes.  Each entry is the first entry of an array
	 * terminated by zero length name.
	 */
	struct list_head cfts;

	/*
	 * Base cftypes which are automatically registered.  The two can
	 * point to the same array.
	 */
	struct cftype *dfl_cftypes;	/* for the default hierarchy */
	struct cftype *legacy_cftypes;	/* for the legacy hierarchies */

	/*
	 * A subsystem may depend on other subsystems.  When such subsystem
	 * is enabled on a cgroup, the depended-upon subsystems are enabled
	 * together if available.  Subsystems enabled due to dependency are
	 * not visible to userland until explicitly enabled.  The following
	 * specifies the mask of subsystems that this one depends on.
	 */
	unsigned int depends_on;
};

687 688 689 690 691 692
extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;

/**
 * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
 * @tsk: target task
 *
693 694
 * Allows cgroup operations to synchronize against threadgroup changes
 * using a percpu_rw_semaphore.
695 696 697 698 699 700 701 702 703 704
 */
static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
{
	percpu_down_read(&cgroup_threadgroup_rwsem);
}

/**
 * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups
 * @tsk: target task
 *
705
 * Counterpart of cgroup_threadcgroup_change_begin().
706 707 708 709 710
 */
static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
{
	percpu_up_read(&cgroup_threadgroup_rwsem);
}
711 712 713

#else	/* CONFIG_CGROUPS */

714 715
#define CGROUP_SUBSYS_COUNT 0

716 717 718 719 720
static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
{
	might_sleep();
}

721 722
static inline void cgroup_threadgroup_change_end(struct task_struct *tsk) {}

723
#endif	/* CONFIG_CGROUPS */
724

725 726
#ifdef CONFIG_SOCK_CGROUP_DATA

T
Tejun Heo 已提交
727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753
/*
 * sock_cgroup_data is embedded at sock->sk_cgrp_data and contains
 * per-socket cgroup information except for memcg association.
 *
 * On legacy hierarchies, net_prio and net_cls controllers directly set
 * attributes on each sock which can then be tested by the network layer.
 * On the default hierarchy, each sock is associated with the cgroup it was
 * created in and the networking layer can match the cgroup directly.
 *
 * To avoid carrying all three cgroup related fields separately in sock,
 * sock_cgroup_data overloads (prioidx, classid) and the cgroup pointer.
 * On boot, sock_cgroup_data records the cgroup that the sock was created
 * in so that cgroup2 matches can be made; however, once either net_prio or
 * net_cls starts being used, the area is overriden to carry prioidx and/or
 * classid.  The two modes are distinguished by whether the lowest bit is
 * set.  Clear bit indicates cgroup pointer while set bit prioidx and
 * classid.
 *
 * While userland may start using net_prio or net_cls at any time, once
 * either is used, cgroup2 matching no longer works.  There is no reason to
 * mix the two and this is in line with how legacy and v2 compatibility is
 * handled.  On mode switch, cgroup references which are already being
 * pointed to by socks may be leaked.  While this can be remedied by adding
 * synchronization around sock_cgroup_data, given that the number of leaked
 * cgroups is bound and highly unlikely to be high, this seems to be the
 * better trade-off.
 */
754
struct sock_cgroup_data {
T
Tejun Heo 已提交
755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772
	union {
#ifdef __LITTLE_ENDIAN
		struct {
			u8	is_data;
			u8	padding;
			u16	prioidx;
			u32	classid;
		} __packed;
#else
		struct {
			u32	classid;
			u16	prioidx;
			u8	padding;
			u8	is_data;
		} __packed;
#endif
		u64		val;
	};
773 774
};

T
Tejun Heo 已提交
775 776 777 778 779
/*
 * There's a theoretical window where the following accessors race with
 * updaters and return part of the previous pointer as the prioidx or
 * classid.  Such races are short-lived and the result isn't critical.
 */
780
static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
781
{
T
Tejun Heo 已提交
782 783
	/* fallback to 1 which is always the ID of the root cgroup */
	return (skcd->is_data & 1) ? skcd->prioidx : 1;
784 785
}

786
static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
787
{
T
Tejun Heo 已提交
788 789
	/* fallback to 0 which is the unconfigured default classid */
	return (skcd->is_data & 1) ? skcd->classid : 0;
790 791
}

T
Tejun Heo 已提交
792 793 794 795
/*
 * If invoked concurrently, the updaters may clobber each other.  The
 * caller is responsible for synchronization.
 */
796 797 798
static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
					   u16 prioidx)
{
799
	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
T
Tejun Heo 已提交
800 801 802 803 804 805 806 807 808 809 810

	if (sock_cgroup_prioidx(&skcd_buf) == prioidx)
		return;

	if (!(skcd_buf.is_data & 1)) {
		skcd_buf.val = 0;
		skcd_buf.is_data = 1;
	}

	skcd_buf.prioidx = prioidx;
	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
811 812 813 814 815
}

static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
					   u32 classid)
{
816
	struct sock_cgroup_data skcd_buf = {{ .val = READ_ONCE(skcd->val) }};
T
Tejun Heo 已提交
817 818 819 820 821 822 823 824 825 826 827

	if (sock_cgroup_classid(&skcd_buf) == classid)
		return;

	if (!(skcd_buf.is_data & 1)) {
		skcd_buf.val = 0;
		skcd_buf.is_data = 1;
	}

	skcd_buf.classid = classid;
	WRITE_ONCE(skcd->val, skcd_buf.val);	/* see sock_cgroup_ptr() */
828 829 830 831 832 833 834 835 836
}

#else	/* CONFIG_SOCK_CGROUP_DATA */

struct sock_cgroup_data {
};

#endif	/* CONFIG_SOCK_CGROUP_DATA */

837
#endif	/* _LINUX_CGROUP_DEFS_H */