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/cgroupstats.h>
#include <linux/prio_heap.h>
#include <linux/rwsem.h>
#include <linux/idr.h>
#include <linux/workqueue.h>

#ifdef CONFIG_CGROUPS

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

extern int cgroup_init_early(void);
extern int cgroup_init(void);
extern void cgroup_lock(void);
extern int cgroup_lock_is_held(void);
extern bool cgroup_lock_live_group(struct cgroup *cgrp);
extern void cgroup_unlock(void);
extern void cgroup_fork(struct task_struct *p);
extern void cgroup_fork_callbacks(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 const struct file_operations proc_cgroup_operations;

/* Define the enumeration of all builtin cgroup subsystems */
#define SUBSYS(_x) _x ## _subsys_id,
enum cgroup_subsys_id {
#include <linux/cgroup_subsys.h>
	CGROUP_BUILTIN_SUBSYS_COUNT
};
#undef SUBSYS
/*
 * This define indicates the maximum number of subsystems that can be loaded
 * at once. We limit to this many since cgroupfs_root has subsys_bits to keep
 * track of all of them.
 */
#define CGROUP_SUBSYS_COUNT (BITS_PER_BYTE*sizeof(unsigned long))

/* 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 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, /* This CSS is the root of the subsystem */
	CSS_REMOVED, /* This CSS is dead */
	CSS_CLEAR_CSS_REFS,		/* @ss->__DEPRECATED_clear_css_refs */
};

/* 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 (!test_bit(CSS_ROOT, &css->flags))
		__css_get(css, 1);
}

static inline bool css_is_removed(struct cgroup_subsys_state *css)
{
	return test_bit(CSS_REMOVED, &css->flags);
}

/*
 * 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 (test_bit(CSS_ROOT, &css->flags))
		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 (!test_bit(CSS_ROOT, &css->flags))
		__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,
	/*
	 * A thread in rmdir() is wating for this cgroup.
	 */
	CGRP_WAIT_ON_RMDIR,
	/*
	 * Clone cgroup values when creating a new child cgroup
	 */
	CGRP_CLONE_CHILDREN,
};

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;

	/*
	 * 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 __rcu *dentry;	/* cgroup fs entry, RCU protected */

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

	struct cgroupfs_root *root;
	struct cgroup *top_cgroup;

	/*
	 * 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;

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

/*
 * 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 {

	/* Reference count */
	atomic_t refcount;

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

	/*
	 * List running through all tasks using this cgroup
	 * group. Protected by css_set_lock
	 */
	struct list_head tasks;

	/*
	 * List of cg_cgroup_link objects on link chains from
	 * cgroups referenced from this css_set. Protected by
	 * css_set_lock
	 */
	struct list_head cg_links;

	/*
	 * 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) and modular subsystem
	 * loading/unloading.
	 */
	struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT];

	/* For RCU-protected deletion */
	struct rcu_head rcu_head;
};

/*
 * cgroup_map_cb is an abstract callback API for reporting map-valued
 * control files
 */

struct cgroup_map_cb {
	int (*fill)(struct cgroup_map_cb *cb, const char *key, u64 value);
	void *state;
};

/*
 * struct cftype: handler definitions for cgroup control files
 *
 * When reading/writing to a file:
 *	- the cgroup to use is file->f_dentry->d_parent->d_fsdata
 *	- the 'cftype' of the file is file->f_dentry->d_fsdata
 */

/* cftype->flags */
#define CFTYPE_ONLY_ON_ROOT	(1U << 0)	/* only create on root cg */
#define CFTYPE_NOT_ON_ROOT	(1U << 1)	/* don't create onp root cg */

#define MAX_CFTYPE_NAME		64

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];
	int private;
	/*
	 * If not 0, file mode is set to this value, otherwise it will
	 * be figured out automatically
	 */
	umode_t mode;

	/*
	 * If non-zero, defines the maximum length of string that can
	 * be passed to write_string; defaults to 64
	 */
	size_t max_write_len;

	/* CFTYPE_* flags */
	unsigned int flags;

	int (*open)(struct inode *inode, struct file *file);
	ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft,
			struct file *file,
			char __user *buf, size_t nbytes, loff_t *ppos);
	/*
	 * 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 *cgrp, struct cftype *cft);
	/*
	 * read_s64() is a signed version of read_u64()
	 */
	s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft);
	/*
	 * read_map() is used for defining a map of key/value
	 * pairs. It should call cb->fill(cb, key, value) for each
	 * entry. The key/value pairs (and their ordering) should not
	 * change between reboots.
	 */
	int (*read_map)(struct