path: root/include/linux/cgroup-defs.h

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * 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>
#include <linux/refcount.h>
#include <linux/percpu-refcount.h>
#include <linux/percpu-rwsem.h>
#include <linux/u64_stats_sync.h>
#include <linux/workqueue.h>
#include <linux/bpf-cgroup.h>
#include <linux/psi_types.h>

#ifdef CONFIG_CGROUPS

struct cgroup;
struct cgroup_root;
struct cgroup_subsys;
struct cgroup_taskset;
struct kernfs_node;
struct kernfs_ops;
struct kernfs_open_file;
struct seq_file;
struct poll_table_struct;

#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 */
	CSS_VISIBLE	= (1 << 3), /* css is visible to userland */
	CSS_DYING	= (1 << 4), /* css is dying */
};

/* 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,

	/* Control group has to be frozen. */
	CGRP_FREEZE,

	/* Cgroup is frozen. */
	CGRP_FROZEN,
};

/* cgroup_root->flags */
enum {
	CGRP_ROOT_NOPREFIX	= (1 << 1), /* mounted subsystems have no named prefix */
	CGRP_ROOT_XATTR		= (1 << 2), /* supports extended attributes */

	/*
	 * 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),

	/*
	 * Enable cpuset controller in v1 cgroup to use v2 behavior.
	 */
	CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),

	/*
	 * Enable legacy local memory.events.
	 */
	CGRP_ROOT_MEMORY_LOCAL_EVENTS = (1 << 5),
};

/* 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 */
	CFTYPE_NS_DELEGATABLE	= (1 << 2),	/* writeable beyond delegation boundaries */

	CFTYPE_NO_PREFIX	= (1 << 3),	/* (DON'T USE FOR NEW FILES) no subsys prefix */
	CFTYPE_WORLD_WRITABLE	= (1 << 4),	/* (DON'T USE FOR NEW FILES) S_IWUGO */
	CFTYPE_DEBUG		= (1 << 5),	/* create when cgroup_debug */

	/* 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 */
};

/*
 * 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;
	unsigned long notified_at;
	struct timer_list notify_timer;
};

/*
 * 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;

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

	/*
	 * 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;

	/*
	 * Incremented by online self and children.  Used to guarantee that
	 * parents are not offlined before their children.
	 */
	atomic_t online_cnt;

	/* percpu_ref killing and RCU release */
	struct work_struct destroy_work;
	struct rcu_work destroy_rwork;

	/*
	 * PI: the parent css.	Placed here for cache proximity to following
	 * fields of the containing structure.
	 */
	struct cgroup_subsys_state *parent;
};

/*
 * 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 {
	/*
	 * 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).
	 */
	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];

	/* reference count */
	refcount_t refcount;

	/*
	 * 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;

	/* the default cgroup associated with this css_set */
	struct cgroup *dfl_cgrp;

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

	/*
	 * 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;
	struct list_head dying_tasks;

	/* all css_task_iters currently walking this cset */
	struct list_head task_iters;

	/*
	 * 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.
	 */
	struct list_head e_cset_node[CGROUP_SUBSYS_COUNT];

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

	/*
	 * List running through all cgroup groups in the same hash
	 * slot. Protected by css_set_lock
	 */
	struct hlist_node hlist;

	/*
	 * List of cgrp_cset_links pointing at cgroups referenced from this
	 * css_set.  Protected by css_set_lock.
	 */
	struct list_head cgrp_links;

	/*
	 * 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
	 * 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.
	 */
	struct cgroup *mg_src_cgrp;
	struct cgroup *mg_dst_cgrp;
	struct css_set *mg_dst_cset;

	/* dead and being drained, ignore for migration */
	bool dead