cgroup.c

/*
 *  Generic process-grouping system.
 *
 *  Based originally on the cpuset system, extracted by Paul Menage
 *  Copyright (C) 2006 Google, Inc
 *
 *  Notifications support
 *  Copyright (C) 2009 Nokia Corporation
 *  Author: Kirill A. Shutemov
 *
 *  Copyright notices from the original cpuset code:
 *  --------------------------------------------------
 *  Copyright (C) 2003 BULL SA.
 *  Copyright (C) 2004-2006 Silicon Graphics, Inc.
 *
 *  Portions derived from Patrick Mochel's sysfs code.
 *  sysfs is Copyright (c) 2001-3 Patrick Mochel
 *
 *  2003-10-10 Written by Simon Derr.
 *  2003-10-22 Updates by Stephen Hemminger.
 *  2004 May-July Rework by Paul Jackson.
 *  ---------------------------------------------------
 *
 *  This file is subject to the terms and conditions of the GNU General Public
 *  License.  See the file COPYING in the main directory of the Linux
 *  distribution for more details.
 */

#include <linux/cgroup.h>
#include <linux/ctype.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/mount.h>
#include <linux/pagemap.h>
#include <linux/proc_fs.h>
#include <linux/rcupdate.h>
#include <linux/sched.h>
#include <linux/backing-dev.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/magic.h>
#include <linux/spinlock.h>
#include <linux/string.h>
#include <linux/sort.h>
#include <linux/kmod.h>
#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/cgroupstats.h>
#include <linux/hash.h>
#include <linux/namei.h>
#include <linux/pid_namespace.h>
#include <linux/idr.h>
#include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
#include <linux/eventfd.h>
#include <linux/poll.h>
#include <linux/flex_array.h> /* used in cgroup_attach_proc */

#include <asm/atomic.h>

static DEFINE_MUTEX(cgroup_mutex);

/*
 * Generate an array of cgroup subsystem pointers. At boot time, this is
 * populated up to CGROUP_BUILTIN_SUBSYS_COUNT, and modular subsystems are
 * registered after that. The mutable section of this array is protected by
 * cgroup_mutex.
 */
#define SUBSYS(_x) &_x ## _subsys,
static struct cgroup_subsys *subsys[CGROUP_SUBSYS_COUNT] = {
#include <linux/cgroup_subsys.h>
};

#define MAX_CGROUP_ROOT_NAMELEN 64

/*
 * A cgroupfs_root represents the root of a cgroup hierarchy,
 * and may be associated with a superblock to form an active
 * hierarchy
 */
struct cgroupfs_root {
	struct super_block *sb;

	/*
	 * The bitmask of subsystems intended to be attached to this
	 * hierarchy
	 */
	unsigned long subsys_bits;

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

	/* The bitmask of subsystems currently attached to this hierarchy */
	unsigned long actual_subsys_bits;

	/* A list running through the attached subsystems */
	struct list_head subsys_list;

	/* The root cgroup for this hierarchy */
	struct cgroup top_cgroup;

	/* Tracks how many cgroups are currently defined in hierarchy.*/
	int number_of_cgroups;

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

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

	/* 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];
};

/*
 * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
 * subsystems that are otherwise unattached - it never has more than a
 * single cgroup, and all tasks are part of that cgroup.
 */
static struct cgroupfs_root rootnode;

/*
 * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
 * cgroup_subsys->use_id != 0.
 */
#define CSS_ID_MAX	(65535)
struct css_id {
	/*
	 * The css to which this ID points. This pointer is set to valid value
	 * after cgroup is populated. If cgroup is removed, this will be NULL.
	 * This pointer is expected to be RCU-safe because destroy()
	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
	 * css_tryget() should be used for avoiding race.
	 */
	struct cgroup_subsys_state __rcu *css;
	/*
	 * ID of this css.
	 */
	unsigned short id;
	/*
	 * Depth in hierarchy which this ID belongs to.
	 */
	unsigned short depth;
	/*
	 * ID is freed by RCU. (and lookup routine is RCU safe.)
	 */
	struct rcu_head rcu_head;
	/*
	 * Hierarchy of CSS ID belongs to.
	 */
	unsigned short stack[0]; /* Array of Length (depth+1) */
};

/*
 * cgroup_event represents events which userspace want to receive.
 */
struct cgroup_event {
	/*
	 * Cgroup which the event belongs to.
	 */
	struct cgroup *cgrp;
	/*
	 * Control file which the event associated.
	 */
	struct cftype *cft;
	/*
	 * eventfd to signal userspace about the event.
	 */
	struct eventfd_ctx *eventfd;
	/*
	 * Each of these stored in a list by the cgroup.
	 */
	struct list_head list;
	/*
	 * All fields below needed to unregister event when
	 * userspace closes eventfd.
	 */
	poll_table pt;
	wait_queue_head_t *wqh;
	wait_queue_t wait;
	struct work_struct remove;
};

/* The list of hierarchy roots */

static LIST_HEAD(roots);
static int root_count;

static DEFINE_IDA(hierarchy_ida);
static int next_hierarchy_id;
static DEFINE_SPINLOCK(hierarchy_id_lock);

/* dummytop is a shorthand for the dummy hierarchy's top cgroup */
#define dummytop (&rootnode.top_cgroup)

/* This flag indicates whether tasks in the fork and exit paths should
 * check for fork/exit handlers to call. This avoids us having to do
 * extra work in the fork/exit path if none of the subsystems need to
 * be called.
 */
static int need_forkexit_callback __read_mostly;

#ifdef CONFIG_PROVE_LOCKING
int cgroup_lock_is_held(void)
{
	return lockdep_is_held(&cgroup_mutex);
}
#else /* #ifdef CONFIG_PROVE_LOCKING */
int cgroup_lock_is_held(void)
{
	return mutex_is_locked(&cgroup_mutex);
}
#endif /* #else #ifdef CONFIG_PROVE_LOCKING */

EXPORT_SYMBOL_GPL(cgroup_lock_is_held);

/* convenient tests for these bits */
inline int cgroup_is_removed(const struct cgroup *cgrp)
{
	return test_bit(CGRP_REMOVED, &cgrp->flags);
}

/* bits in struct cgroupfs_root flags field */
enum {
	ROOT_NOPREFIX, /* mounted subsystems have no named prefix */
};

static int cgroup_is_releasable(const struct cgroup *cgrp)
{
	const int bits =
		(1 << CGRP_RELEASABLE) |
		(1 << CGRP_NOTIFY_ON_RELEASE);
	return (cgrp->flags & bits) == bits;
}

static int notify_on_release(const struct cgroup *cgrp)
{
	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
}

static int clone_children(const struct cgroup *cgrp)
{
	return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
}

/*
 * for_each_subsys() allows you to iterate on each subsystem attached to
 * an active hierarchy
 */
#define for_each_subsys(_root, _ss) \
list_for_each_entry(_ss, &_root->subsys_list, sibling)

/* for_each_active_root() allows you to iterate across the active hierarchies */
#define for_each_active_root(_root) \
list_for_each_entry(_root, &roots, root_list)

/* the list of cgroups eligible for automatic release. Protected by
 * release_list_lock */
static LIST_HEAD(release_list);
static DEFINE_SPINLOCK(release_list_lock);
static void cgroup_release_agent(struct work_struct *work);
static DECLARE_WORK(release_agent_work, cgroup_release_agent);
static void check_for_release(struct cgroup *cgrp);

/* Link structure for associating css_set objects with cgroups */
struct cg_cgroup_link {
	/*
	 * List running through cg_cgroup_links associated with a
	 * cgroup, anchored on cgroup->css_sets
	 */
	struct list_head cgrp_link_list;
	struct cgroup *cgrp;
	/*
	 * List running through cg_cgroup_links pointing at a
	 * single css_set object, anchored on css_set->cg_links
	 */
	struct list_head cg_link_list;
	struct css_set *cg;
};

/* The default css_set - used by init and its children prior to any
 * hierarchies being mounted. It contains a pointer to the root state
 * for each subsystem. Also used to anchor the list of css_sets. Not
 * reference-counted, to improve performance when child cgroups
 * haven't been created.
 */

static struct css_set init_css_set;
static struct cg_cgroup_link init_css_set_link;

static int cgroup_init_idr(struct cgroup_subsys *ss,
			   struct cgroup_subsys_state *css);

/* css_set_lock protects the list of css_set objects, and the
 * chain of tasks off each css_set.  Nests outside task->alloc_lock
 * due to cgroup_iter_start() */
static DEFINE_RWLOCK(css_set_lock);
static int css_set_count;

/*
 * hash table for cgroup groups. This improves the performance to find
 * an existing css_set. This hash doesn't (currently) take into
 * account cgroups in empty hierarchies.
 */
#define CSS_SET_HASH_BITS	7
#define CSS_SET_TABLE_SIZE	(1 << CSS_SET_HASH_BITS)
static struct hlist_head css_set_table[CSS_SET_TABLE_SIZE];

static struct hlist_head *css_set_hash(struct cgroup_subsys_state *css[])
{
	int i;
	int index;
	unsigned long tmp = 0UL;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++)
		tmp += (unsigned long)css[i];
	tmp = (tmp >> 16) ^ tmp;

	index = hash_long(tmp, CSS_SET_HASH_BITS);

	return &css_set_table[index];
}

/* We don't maintain the lists running through each css_set to its
 * task until after the first call to cgroup_iter_start(). This
 * reduces the fork()/exit() overhead for people who have cgroups
 * compiled into their kernel but not actually in use */
static int use_task_css_set_links __read_mostly;

static void __put_css_set(struct css_set *cg, int taskexit)
{
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;
	/*
	 * Ensure that the refcount doesn't hit zero while any readers
	 * can see it. Similar to atomic_dec_and_lock(), but for an
	 * rwlock
	 */
	if (atomic_add_unless(&cg->refcount, -1, 1))
		return;
	write_lock(&css_set_lock);
	if (!atomic_dec_and_test(&cg->refcount)) {
		write_unlock(&css_set_lock);
		return;
	}

	/* This css_set is dead. unlink it and release cgroup refcounts */
	hlist_del(&cg->hlist);
	css_set_count--;

	list_for_each_entry_safe(link, saved_link, &cg->cg_links,
				 cg_link_list) {
		struct cgroup *cgrp = link->cgrp;
		list_del(&link->cg_link_list);
		list_del(&link->cgrp_link_list);
		if (atomic_dec_and_test(&cgrp->count) &&
		    notify_on_release(cgrp)) {
			if (taskexit)
				set_bit(CGRP_RELEASABLE, &cgrp->flags);
			check_for_release(cgrp);
		}

		kfree(link);
	}

	write_unlock(&css_set_lock);
	kfree_rcu(cg, rcu_head);
}

/*
 * refcounted get/put for css_set objects
 */
static inline void get_css_set(struct css_set *cg)
{
	atomic_inc(&cg->refcount);
}

static inline void put_css_set(struct css_set *cg)
{
	__put_css_set(cg, 0);
}

static inline void put_css_set_taskexit(struct css_set *cg)
{
	__put_css_set(cg, 1);
}

/*
 * compare_css_sets - helper function for find_existing_css_set().
 * @cg: candidate css_set being tested
 * @old_cg: existing css_set for a task
 * @new_cgrp: cgroup that's being entered by the task
 * @template: desired set of css pointers in css_set (pre-calculated)
 *
 * Returns true if "cg" matches "old_cg" except for the hierarchy
 * which "new_cgrp" belongs to, for which it should match "new_cgrp".
 */
static bool compare_css_sets(struct css_set *cg,
			     struct css_set *old_cg,
			     struct cgroup *new_cgrp,
			     struct cgroup_subsys_state *template[])
{
	struct list_head *l1, *l2;

	if (memcmp(template, cg->subsys, sizeof(cg->subsys))) {
		/* Not all subsystems matched */
		return false;
	}

	/*
	 * Compare cgroup pointers in order to distinguish between
	 * different cgroups in heirarchies with no subsystems. We
	 * could get by with just this check alone (and skip the
	 * memcmp above) but on most setups the memcmp check will
	 * avoid the need for this more expensive check on almost all
	 * candidates.
	 */

	l1 = &cg->cg_links;
	l2 = &old_cg->cg_links;
	while (1) {
		struct cg_cgroup_link *cgl1, *cgl2;
		struct cgroup *cg1, *cg2;

		l1 = l1->next;
		l2 = l2->next;
		/* See if we reached the end - both lists are equal length. */
		if (l1 == &cg->cg_links) {
			BUG_ON(l2 != &old_cg->cg_links);
			break;
		} else {
			BUG_ON(l2 == &old_cg->cg_links);
		}
		/* Locate the cgroups associated with these links. */
		cgl1 = list_entry(l1, struct cg_cgroup_link, cg_link_list);
		cgl2 = list_entry(l2, struct cg_cgroup_link, cg_link_list);
		cg1 = cgl1->cgrp;
		cg2 = cgl2->cgrp;
		/* Hierarchies should be linked in the same order. */
		BUG_ON(cg1->root != cg2->root);

		/*
		 * If this hierarchy is the hierarchy of the cgroup
		 * that's changing, then we need to check that this
		 * css_set points to the new cgroup; if it's any other
		 * hierarchy, then this css_set should point to the
		 * same cgroup as the old css_set.
		 */
		if (cg1->root == new_cgrp->root) {
			if (cg1 != new_cgrp)
				return false;
		} else {
			if (cg1 != cg2)
				return false;
		}
	}
	return true;
}

/*
 * find_existing_css_set() is a helper for
 * find_css_set(), and checks to see whether an existing
 * css_set is suitable.
 *
 * oldcg: the cgroup group that we're using before the cgroup
 * transition
 *
 * cgrp: the cgroup that we're moving into
 *
 * template: location in which to build the desired set of subsystem
 * state objects for the new cgroup group
 */
static struct css_set *find_existing_css_set(
	struct css_set *oldcg,
	struct cgroup *cgrp,
	struct cgroup_subsys_state *template[])
{
	int i;
	struct cgroupfs_root *root = cgrp->root;
	struct hlist_head *hhead;
	struct hlist_node *node;
	struct css_set *cg;

	/*
	 * Build the set of subsystem state objects that we want to see in the
	 * new css_set. while subsystems can change globally, the entries here
	 * won't change, so no need for locking.
	 */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		if (root->subsys_bits & (1UL << i)) {
			/* Subsystem is in this hierarchy. So we want
			 * the subsystem state from the new
			 * cgroup */
			template[i] = cgrp->subsys[i];
		} else {
			/* Subsystem is not in this hierarchy, so we
			 * don't want to change the subsystem state */
			template[i] = oldcg->subsys[i];
		}
	}

	hhead = css_set_hash(template);
	hlist_for_each_entry(cg, node, hhead, hlist) {
		if (!compare_css_sets(cg, oldcg, cgrp, template))
			continue;

		/* This css_set matches what we need */
		return cg;
	}

	/* No existing cgroup group matched */
	return NULL;
}

static void free_cg_links(struct list_head *tmp)
{
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;

	list_for_each_entry_safe(link, saved_link, tmp, cgrp_link_list) {
		list_del(&link->cgrp_link_list);
		kfree(link);
	}
}

/*
 * allocate_cg_links() allocates "count" cg_cgroup_link structures
 * and chains them on tmp through their cgrp_link_list fields. Returns 0 on
 * success or a negative error
 */
static int allocate_cg_links(int count, struct list_head *tmp)
{
	struct cg_cgroup_link *link;
	int i;
	INIT_LIST_HEAD(tmp);
	for (i = 0; i < count; i++) {
		link = kmalloc(sizeof(*link), GFP_KERNEL);
		if (!link) {
			free_cg_links(tmp);
			return -ENOMEM;
		}
		list_add(&link->cgrp_link_list, tmp);
	}
	return 0;
}

/**
 * link_css_set - a helper function to link a css_set to a cgroup
 * @tmp_cg_links: cg_cgroup_link objects allocated by allocate_cg_links()
 * @cg: the css_set to be linked
 * @cgrp: the destination cgroup
 */
static void link_css_set(struct list_head *tmp_cg_links,
			 struct css_set *cg, struct cgroup *cgrp)
{
	struct cg_cgroup_link *link;

	BUG_ON(list_empty(tmp_cg_links));
	link = list_first_entry(tmp_cg_links, struct cg_cgroup_link,
				cgrp_link_list);
	link->cg = cg;
	link->cgrp = cgrp;
	atomic_inc(&cgrp->count);
	list_move(&link->cgrp_link_list, &cgrp->css_sets);
	/*
	 * Always add links to the tail of the list so that the list
	 * is sorted by order of hierarchy creation
	 */
	list_add_tail(&link->cg_link_list, &cg->cg_links);
}

/*
 * find_css_set() takes an existing cgroup group and a
 * cgroup object, and returns a css_set object that's
 * equivalent to the old group, but with the given cgroup
 * substituted into the appropriate hierarchy. Must be called with
 * cgroup_mutex held
 */
static struct css_set *find_css_set(
	struct css_set *oldcg, struct cgroup *cgrp)
{
	struct css_set *res;
	struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT];

	struct list_head tmp_cg_links;

	struct hlist_head *hhead;
	struct cg_cgroup_link *link;

	/* First see if we already have a cgroup group that matches
	 * the desired set */
	read_lock(&css_set_lock);
	res = find_existing_css_set(oldcg, cgrp, template);
	if (res)
		get_css_set(res);
	read_unlock(&css_set_lock);

	if (res)
		return res;

	res = kmalloc(sizeof(*res), GFP_KERNEL);
	if (!res)
		return NULL;

	/* Allocate all the cg_cgroup_link objects that we'll need */
	if (allocate_cg_links(root_count, &tmp_cg_links) < 0) {
		kfree(res);
		return NULL;
	}

	atomic_set(&res->refcount, 1);
	INIT_LIST_HEAD(&res->cg_links);
	INIT_LIST_HEAD(&res->tasks);
	INIT_HLIST_NODE(&res->hlist);

	/* Copy the set of subsystem state objects generated in
	 * find_existing_css_set() */
	memcpy(res->subsys, template, sizeof(res->subsys));

	write_lock(&css_set_lock);
	/* Add reference counts and links from the new css_set. */
	list_for_each_entry(link, &oldcg->cg_links, cg_link_list) {
		struct cgroup *c = link->cgrp;
		if (c->root == cgrp->root)
			c = cgrp;
		link_css_set(&tmp_cg_links, res, c);
	}

	BUG_ON(!list_empty(&tmp_cg_links));

	css_set_count++;

	/* Add this cgroup group to the hash table */
	hhead = css_set_hash(res->subsys);
	hlist_add_head(&res->hlist, hhead);

	write_unlock(&css_set_lock);

	return res;
}

/*
 * Return the cgroup for "task" from the given hierarchy. Must be
 * called with cgroup_mutex held.
 */
static struct cgroup *task_cgroup_from_root(struct task_struct *task,
					    struct cgroupfs_root *root)
{
	struct css_set *css;
	struct cgroup *res = NULL;

	BUG_ON(!mutex_is_locked(&cgroup_mutex));
	read_lock(&css_set_lock);
	/*
	 * No need to lock the task - since we hold cgroup_mutex the
	 * task can't change groups, so the only thing that can happen
	 * is that it exits and its css is set back to init_css_set.
	 */
	css = task->cgroups;
	if (css == &init_css_set) {
		res = &root->top_cgroup;
	} else {
		struct cg_cgroup_link *link;
		list_for_each_entry(link, &css->cg_links, cg_link_list) {
			struct cgroup *c = link->cgrp;
			if (c->root == root) {
				res = c;
				break;
			}
		}
	}
	read_unlock(&css_set_lock);
	BUG_ON(!res);
	return res;
}

/*
 * There is one global cgroup mutex. We also require taking
 * task_lock() when dereferencing a task's cgroup subsys pointers.
 * See "The task_lock() exception", at the end of this comment.
 *
 * A task must hold cgroup_mutex to modify cgroups.
 *
 * Any task can increment and decrement the count field without lock.
 * So in general, code holding cgroup_mutex can't rely on the count
 * field not changing.  However, if the count goes to zero, then only
 * cgroup_attach_task() can increment it again.  Because a count of zero
 * means that no tasks are currently attached, therefore there is no
 * way a task attached to that cgroup can fork (the other way to
 * increment the count).  So code holding cgroup_mutex can safely
 * assume that if the count is zero, it will stay zero. Similarly, if
 * a task holds cgroup_mutex on a cgroup with zero count, it
 * knows that the cgroup won't be removed, as cgroup_rmdir()
 * needs that mutex.
 *
 * The fork and exit callbacks cgroup_fork() and cgroup_exit(), don't
 * (usually) take cgroup_mutex.  These are the two most performance
 * critical pieces of code here.  The exception occurs on cgroup_exit(),
 * when a task in a notify_on_release cgroup exits.  Then cgroup_mutex
 * is taken, and if the cgroup count is zero, a usermode call made
 * to the release agent with the name of the cgroup (path relative to
 * the root of cgroup file system) as the argument.
 *
 * A cgroup can only be deleted if both its 'count' of using tasks
 * is zero, and its list of 'children' cgroups is empty.  Since all
 * tasks in the system use _some_ cgroup, and since there is always at
 * least one task in the system (init, pid == 1), therefore, top_cgroup
 * always has either children cgroups and/or using tasks.  So we don't
 * need a special hack to ensure that top_cgroup cannot be deleted.
 *
 *	The task_lock() exception
 *
 * The need for this exception arises from the action of
 * cgroup_attach_task(), which overwrites one tasks cgroup pointer with
 * another.  It does so using cgroup_mutex, however there are
 * several performance critical places that need to reference
 * task->cgroup without the expense of grabbing a system global
 * mutex.  Therefore except as noted below, when dereferencing or, as
 * in cgroup_attach_task(), modifying a task'ss cgroup pointer we use
 * task_lock(), which acts on a spinlock (task->alloc_lock) already in
 * the task_struct routinely used for such matters.
 *
 * P.S.  One more locking exception.  RCU is used to guard the
 * update of a tasks cgroup pointer by cgroup_attach_task()
 */

/**
 * cgroup_lock - lock out any changes to cgroup structures
 *
 */
void cgroup_lock(void)
{
	mutex_lock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_lock);

/**
 * cgroup_unlock - release lock on cgroup changes
 *
 * Undo the lock taken in a previous cgroup_lock() call.
 */
void cgroup_unlock(void)
{
	mutex_unlock(&cgroup_mutex);
}
EXPORT_SYMBOL_GPL(cgroup_unlock);

/*
 * A couple of forward declarations required, due to cyclic reference loop:
 * cgroup_mkdir -> cgroup_create -> cgroup_populate_dir ->
 * cgroup_add_file -> cgroup_create_file -> cgroup_dir_inode_operations
 * -> cgroup_mkdir.
 */

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode);
static struct dentry *cgroup_lookup(struct inode *, struct dentry *, struct nameidata *);
static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static const struct inode_operations cgroup_dir_inode_operations;
static const struct file_operations proc_cgroupstats_operations;

static struct backing_dev_info cgroup_backing_dev_info = {
	.name		= "cgroup",
	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
};

static int alloc_css_id(struct cgroup_subsys *ss,
			struct cgroup *parent, struct cgroup *child);

static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
{
	struct inode *inode = new_inode(sb);

	if (inode) {
		inode->i_ino = get_next_ino();
		inode->i_mode = mode;
		inode->i_uid = current_fsuid();
		inode->i_gid = current_fsgid();
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info;
	}
	return inode;
}

/*
 * Call subsys's pre_destroy handler.
 * This is called before css refcnt check.
 */
static int cgroup_call_pre_destroy(struct cgroup *cgrp)
{
	struct cgroup_subsys *ss;
	int ret = 0;

	for_each_subsys(cgrp->root, ss)
		if (ss->pre_destroy) {
			ret = ss->pre_destroy(ss, cgrp);
			if (ret)
				break;
		}

	return ret;
}

static void cgroup_diput(struct dentry *dentry, struct inode *inode)
{
	/* is dentry a directory ? if so, kfree() associated cgroup */
	if (S_ISDIR(inode->i_mode)) {
		struct cgroup *cgrp = dentry->d_fsdata;
		struct cgroup_subsys *ss;
		BUG_ON(!(cgroup_is_removed(cgrp)));
		/* It's possible for external users to be holding css
		 * reference counts on a cgroup; css_put() needs to
		 * be able to access the cgroup after decrementing
		 * the reference count in order to know if it needs to
		 * queue the cgroup to be handled by the release
		 * agent */
		synchronize_rcu();

		mutex_lock(&cgroup_mutex);
		/*
		 * Release the subsystem state objects.
		 */
		for_each_subsys(cgrp->root, ss)
			ss->destroy(ss, cgrp);

		cgrp->root->number_of_cgroups--;
		mutex_unlock(&cgroup_mutex);

		/*
		 * Drop the active superblock reference that we took when we
		 * created the cgroup
		 */
		deactivate_super(cgrp->root->sb);

		/*
		 * if we're getting rid of the cgroup, refcount should ensure
		 * that there are no pidlists left.
		 */
		BUG_ON(!list_empty(&cgrp->pidlists));

		kfree_rcu(cgrp, rcu_head);
	}
	iput(inode);
}

static int cgroup_delete(const struct dentry *d)
{
	return 1;
}

static void remove_dir(struct dentry *d)
{
	struct dentry *parent = dget(d->d_parent);

	d_delete(d);
	simple_rmdir(parent->d_inode, d);
	dput(parent);
}

static void cgroup_clear_directory(struct dentry *dentry)
{
	struct list_head *node;

	BUG_ON(!mutex_is_locked(&dentry->d_inode->i_mutex));
	spin_lock(&dentry->d_lock);
	node = dentry->d_subdirs.next;
	while (node != &dentry->d_subdirs) {
		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);

		spin_lock_nested(&d->d_lock, DENTRY_D_LOCK_NESTED);
		list_del_init(node);
		if (d->d_inode) {
			/* This should never be called on a cgroup
			 * directory with child cgroups */
			BUG_ON(d->d_inode->i_mode & S_IFDIR);
			dget_dlock(d);
			spin_unlock(&d->d_lock);
			spin_unlock(&dentry->d_lock);
			d_delete(d);
			simple_unlink(dentry->d_inode, d);
			dput(d);
			spin_lock(&dentry->d_lock);
		} else
			spin_unlock(&d->d_lock);
		node = dentry->d_subdirs.next;
	}
	spin_unlock(&dentry->d_lock);
}

/*
 * NOTE : the dentry must have been dget()'ed
 */
static void cgroup_d_remove_dir(struct dentry *dentry)
{
	struct dentry *parent;

	cgroup_clear_directory(dentry);

	parent = dentry->d_parent;
	spin_lock(&parent->d_lock);
	spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED);
	list_del_init(&dentry->d_u.d_child);
	spin_unlock(&dentry->d_lock);
	spin_unlock(&parent->d_lock);
	remove_dir(dentry);
}

/*
 * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
 * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
 * reference to css->refcnt. In general, this refcnt is expected to goes down
 * to zero, soon.
 *
 * CGRP_WAIT_ON_RMDIR flag is set under cgroup's inode->i_mutex;
 */
DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);

static void cgroup_wakeup_rmdir_waiter(struct cgroup *cgrp)
{
	if (unlikely(test_and_clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
		wake_up_all(&cgroup_rmdir_waitq);
}

void cgroup_exclude_rmdir(struct cgroup_subsys_state *css)
{
	css_get(css);
}

void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css)
{
	cgroup_wakeup_rmdir_waiter(css->cgroup);
	css_put(css);
}

/*
 * Call with cgroup_mutex held. Drops reference counts on modules, including
 * any duplicate ones that parse_cgroupfs_options took. If this function
 * returns an error, no reference counts are touched.
 */
static int rebind_subsystems(struct cgroupfs_root *root,
			      unsigned long final_bits)
{
	unsigned long added_bits, removed_bits;
	struct cgroup *cgrp = &root->top_cgroup;
	int i;

	BUG_ON(!mutex_is_locked(&cgroup_mutex));

	removed_bits = root->actual_subsys_bits & ~final_bits;
	added_bits = final_bits & ~root->actual_subsys_bits;
	/* Check that any added subsystems are currently free */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		unsigned long bit = 1UL << i;
		struct cgroup_subsys *ss = subsys[i];
		if (!(bit & added_bits))
			continue;
		/*
		 * Nobody should tell us to do a subsys that doesn't exist:
		 * parse_cgroupfs_options should catch that case and refcounts
		 * ensure that subsystems won't disappear once selected.
		 */
		BUG_ON(ss == NULL);
		if (ss->root != &rootnode) {
			/* Subsystem isn't free */
			return -EBUSY;
		}
	}

	/* Currently we don't handle adding/removing subsystems when
	 * any child cgroups exist. This is theoretically supportable
	 * but involves complex error handling, so it's being left until
	 * later */
	if (root->number_of_cgroups > 1)
		return -EBUSY;

	/* Process each subsystem */
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		unsigned long bit = 1UL << i;
		if (bit & added_bits) {
			/* We're binding this subsystem to this hierarchy */
			BUG_ON(ss == NULL);
			BUG_ON(cgrp->subsys[i]);
			BUG_ON(!dummytop->subsys[i]);
			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
			mutex_lock(&ss->hierarchy_mutex);
			cgrp->subsys[i] = dummytop->subsys[i];
			cgrp->subsys[i]->cgroup = cgrp;
			list_move(&ss->sibling, &root->subsys_list);
			ss->root = root;
			if (ss->bind)
				ss->bind(ss, cgrp);
			mutex_unlock(&ss->hierarchy_mutex);
			/* refcount was already taken, and we're keeping it */