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/rwsem.h>
#include <linux/idr.h>
#include <linux/workqueue.h>
#include <linux/fs.h>
#include <linux/percpu-refcount.h>
#include <linux/seq_file.h>
#include <linux/kernfs.h>

#ifdef CONFIG_CGROUPS

struct cgroup_root;
struct cgroup_subsys;
struct inode;
struct cgroup;

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);
extern int cgroupstats_build(struct cgroupstats *stats,
				struct dentry *dentry);

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

/* 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

/* Per-subsystem/per-cgroup state maintained by the system. */
struct cgroup_subsys_state {
	/* the cgroup that this css is attached to */
	struct cgroup *cgroup;

	/* 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;

	/* the parent css */
	struct cgroup_subsys_state *parent;

	unsigned long flags;

	/* percpu_ref killing and RCU release */
	struct rcu_head rcu_head;
	struct work_struct destroy_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() */
};

/**
 * 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)
{
	/* We don't need to reference count the root state */
	if (!(css->flags & CSS_ROOT))
		percpu_ref_get(&css->refcnt);
}

/**
 * css_tryget - try to obtain a reference on the specified css
 * @css: target css
 *
 * Obtain a reference on @css if it's alive.  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_ROOT)
		return true;
	return percpu_ref_tryget(&css->refcnt);
}

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

/* bits in struct cgroup flags field */
enum {
	/* Control Group is dead */
	CGRP_DEAD,
	/*
	 * 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 {
	unsigned long flags;		/* "unsigned long" so bitops work */

	/*
	 * idr allocated in-hierarchy ID.
	 *
	 * The ID of the root cgroup is always 0, and a new cgroup
	 * will be assigned with a smallest available ID.
	 *
	 * Allocating/Removing ID must be protected by cgroup_mutex.
	 */
	int id;

	/* the number of attached css's */
	int nr_css;

	atomic_t refcnt;

	/*
	 * 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 cgroup *parent;		/* my parent */
	struct kernfs_node *kn;		/* cgroup kernfs entry */

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

	/* the bitmask of subsystems enabled on the child cgroups */
	unsigned long child_subsys_mask;

	/* 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;

	/*
	 * 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;

	/* dummy css with NULL ->ss, points back to this cgroup */
	struct cgroup_subsys_state dummy_css;

	/* For css percpu_ref killing and RCU-protected deletion */
	struct rcu_head rcu_head;
	struct work_struct destroy_work;
};

#define MAX_CGROUP_ROOT_NAMELEN 64

/* cgroup_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", "xattr", "clone_children",
	 *   "release_agent" and "name" are disallowed.
	 *
	 * - When mounting an existing superblock, mount options should
	 *   match.
	 *
	 * - Remount is disallowed.
	 *
	 * - rename(2) is disallowed.
	 *
	 * - "tasks" is removed.  Everything should be at process
	 *   granularity.  Use "cgroup.procs" instead.
	 *
	 * - "cgroup.procs" is not sorted.  pids will be unique unless they
	 *   got recycled inbetween reads.
	 *
	 * - "release_agent" and "notify_on_release" are removed.
	 *   Replacement notification mechanism will be implemented.
	 *
	 * - "cgroup.clone_children" is removed.
	 *
	 * - If mount is requested with sane_behavior but without any
	 *   subsystem, the default unified hierarchy is mounted.
	 *
	 * - cpuset: tasks will be kept in empty cpusets when hotplug happens
	 *   and take masks of ancestors with non-empty cpus/mems, instead of
	 *   being moved to an ancestor.
	 *
	 * - cpuset: a task can be moved into an empty cpuset, and again it
	 *   takes masks of ancestors.
	 *
	 * - memcg: use_hierarchy is on by default and the cgroup file for
	 *   the flag is not created.
	 *
	 * - blkcg: blk-throttle becomes properly hierarchical.
	 */
	CGRP_ROOT_SANE_BEHAVIOR	= (1 << 0),

	CGRP_ROOT_NOPREFIX	= (1 << 1), /* mounted subsystems have no named prefix */
	CGRP_ROOT_XATTR		= (1 << 2), /* supports extended attributes */

	/* mount options live below bit 16 */
	CGRP_ROOT_OPTION_MASK	= (1 << 16) - 1,
};

/*
 * 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 long subsys_mask;

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

	/* The root cgroup.  Root is destroyed on its release. */
	<