path: root/include/linux/cgroup.h

#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/rcupdate.h>
#include <linux/rculist.h>
#include <linux/cgroupstats.h>
#include <linux/prio_heap.h>
#include <linux/rwsem.h>
#include <linux/idr.h>
#include <linux/workqueue.h>
#include <linux/xattr.h>
#include <linux/fs.h>

#ifdef CONFIG_CGROUPS

struct cgroupfs_root;
struct cgroup_subsys;
struct inode;
struct cgroup;
struct css_id;
struct eventfd_ctx;

extern int cgroup_init_early(void);
extern int cgroup_init(void);
extern void cgroup_fork(struct task_struct *p);
extern void cgroup_post_fork(struct task_struct *p);
extern void cgroup_exit(struct task_struct *p, int run_callbacks);
extern int cgroupstats_build(struct cgroupstats *stats,
				struct dentry *dentry);
extern int cgroup_load_subsys(struct cgroup_subsys *ss);
extern void cgroup_unload_subsys(struct cgroup_subsys *ss);

extern int proc_cgroup_show(struct seq_file *, void *);

/*
 * Define the enumeration of all cgroup subsystems.
 *
 * We define ids for builtin subsystems and then modular ones.
 */
#define SUBSYS(_x) _x ## _subsys_id,
enum cgroup_subsys_id {
#define IS_SUBSYS_ENABLED(option) IS_BUILTIN(option)
#include <linux/cgroup_subsys.h>
#undef IS_SUBSYS_ENABLED
	CGROUP_BUILTIN_SUBSYS_COUNT,

	__CGROUP_SUBSYS_TEMP_PLACEHOLDER = CGROUP_BUILTIN_SUBSYS_COUNT - 1,

#define IS_SUBSYS_ENABLED(option) IS_MODULE(option)
#include <linux/cgroup_subsys.h>
#undef IS_SUBSYS_ENABLED
	CGROUP_SUBSYS_COUNT,
};
#undef SUBSYS

/* Per-subsystem/per-cgroup state maintained by the system. */
struct cgroup_subsys_state {
	/*
	 * The cgroup that this subsystem is attached to. Useful
	 * for subsystems that want to know about the cgroup
	 * hierarchy structure
	 */
	struct cgroup *cgroup;

	/*
	 * State maintained by the cgroup system to allow subsystems
	 * to be "busy". Should be accessed via css_get(),
	 * css_tryget() and css_put().
	 */

	atomic_t refcnt;

	unsigned long flags;
	/* ID for this css, if possible */
	struct css_id __rcu *id;

	/* Used to put @cgroup->dentry on the last css_put() */
	struct work_struct dput_work;
};

/* bits in struct cgroup_subsys_state flags field */
enum {
	CSS_ROOT	= (1 << 0), /* this CSS is the root of the subsystem */
	CSS_ONLINE	= (1 << 1), /* between ->css_online() and ->css_offline() */
};

/* Caller must verify that the css is not for root cgroup */
static inline void __css_get(struct cgroup_subsys_state *css, int count)
{
	atomic_add(count, &css->refcnt);
}

/*
 * Call css_get() to hold a reference on the css; it can be used
 * for a reference obtained via:
 * - an existing ref-counted reference to the css
 * - task->cgroups for a locked task
 */

static inline void css_get(struct cgroup_subsys_state *css)
{
	/* We don't need to reference count the root state */
	if (!(css->flags & CSS_ROOT))
		__css_get(css, 1);
}

/*
 * Call css_tryget() to take a reference on a css if your existing
 * (known-valid) reference isn't already ref-counted. Returns false if
 * the css has been destroyed.
 */

extern bool __css_tryget(struct cgroup_subsys_state *css);
static inline bool css_tryget(struct cgroup_subsys_state *css)
{
	if (css->flags & CSS_ROOT)
		return true;
	return __css_tryget(css);
}

/*
 * css_put() should be called to release a reference taken by
 * css_get() or css_tryget()
 */

extern void __css_put(struct cgroup_subsys_state *css);
static inline void css_put(struct cgroup_subsys_state *css)
{
	if (!(css->flags & CSS_ROOT))
		__css_put(css);
}

/* bits in struct cgroup flags field */
enum {
	/* Control Group is dead */
	CGRP_REMOVED,
	/*
	 * Control Group has previously had a child cgroup or a task,
	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
	 */
	CGRP_RELEASABLE,
	/* 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,
	/* see the comment above CGRP_ROOT_SANE_BEHAVIOR for details */
	CGRP_SANE_BEHAVIOR,
};

struct cgroup_name {
	struct rcu_head rcu_head;
	char name[];
};

struct cgroup {
	unsigned long flags;		/* "unsigned long" so bitops work */

	/*
	 * count users of this cgroup. >0 means busy, but doesn't
	 * necessarily indicate the number of tasks in the cgroup
	 */
	atomic_t count;

	int id;				/* ida allocated in-hierarchy ID */

	/*
	 * We link our 'sibling' struct into our parent's 'children'.
	 * Our children link their 'sibling' into our 'children'.
	 */
	struct list_head sibling;	/* my parent's children */
	struct list_head children;	/* my children */
	struct list_head files;		/* my files */

	struct cgroup *parent;		/* my parent */
	struct dentry *dentry;		/* cgroup fs entry, RCU protected */

	/*
	 * This is a copy of dentry->d_name, and it's needed because
	 * we can't use dentry->d_name in cgroup_path().
	 *
	 * You must acquire rcu_read_lock() to access cgrp->name, and
	 * the only place that can change it is rename(), which is
	 * protected by parent dir's i_mutex.
	 *
	 * Normally you should use cgroup_name() wrapper rather than
	 * access it directly.
	 */
	struct cgroup_name __rcu *name;

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

	struct cgroupfs_root *root;

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

	struct list_head allcg_node;	/* cgroupfs_root->allcg_list */
	struct list_head cft_q_node;	/* used during cftype add/rm */

	/*
	 * Linked list running through all cgroups that can
	 * potentially be reaped by the release agent. Protected by
	 * release_list_lock
	 */
	struct list_head release_list;

	/*
	 * 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;

	/* For RCU-protected deletion */
	struct rcu_head rcu_head;
	struct work_struct free_work;

	/* List of events which userspace want to receive */
	struct list_head event_list;
	spinlock_t event_list_lock;

	/* directory xattrs */
	struct simple_xattrs xattrs;
};

#define MAX_CGROUP_ROOT_NAMELEN 64

/* cgroupfs_root->flags */
enum {
	/*
	 * Unfortunately, cgroup core and various controllers are riddled
	 * with idiosyncrasies and pointless options.  The following flag,
	 * when set, will force sane behavior - some options are forced on,
	 * others are disallowed, and some controllers will change their
	 * hierarchical or other behaviors.
	 *
	 * The set of behaviors affected by this flag are still being
	 * determined and developed and the mount option for this flag is
	 * prefixed with __DEVEL__.  The prefix will be dropped once we
	 * reach the point where all behaviors are compatible with the
	 * planned unified hierarchy, which will automatically turn on this
	 * flag.
	 *
	 * The followings are the behaviors currently affected this flag.
	 *
	 * - Mount options "noprefix" and "clone_children" are disallowed.
	 *   Also, cgroupfs file cgroup.clone_children is not created.
	 *
	 * - When mounting an existing superblock, mount options should
	 *   match.
	 *
	 * - Remount is disallowed.
	 *
	 * - memcg: use_hierarchy is on by default and the cgroup file for
	 *   the flag is not created.
	 *
	 * The followings are planned changes.
	 *
	 * - release_agent will be disallowed once replacement notification
	 *   mechanism is implemented.