cgroup.c

			stats->nr_stopped++;
			break;
		default:
			if (delayacct_is_task_waiting_on_io(tsk))
				stats->nr_io_wait++;
			break;
		}
	}
	cgroup_iter_end(cgrp, &it);

	rcu_read_unlock();
err:
	return ret;
}

static int cmppid(const void *a, const void *b)
{
	return *(pid_t *)a - *(pid_t *)b;
}

/*
 * Convert array 'a' of 'npids' pid_t's to a string of newline separated
 * decimal pids in 'buf'.  Don't write more than 'sz' chars, but return
 * count 'cnt' of how many chars would be written if buf were large enough.
 */
static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids)
{
	int cnt = 0;
	int i;

	for (i = 0; i < npids; i++)
		cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
	return cnt;
}

/*
 * Handle an open on 'tasks' file.  Prepare a buffer listing the
 * process id's of tasks currently attached to the cgroup being opened.
 *
 * Does not require any specific cgroup mutexes, and does not take any.
 */
static int cgroup_tasks_open(struct inode *unused, struct file *file)
{
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
	struct ctr_struct *ctr;
	pid_t *pidarray;
	int npids;
	char c;

	if (!(file->f_mode & FMODE_READ))
		return 0;

	ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
	if (!ctr)
		goto err0;

	/*
	 * If cgroup gets more users after we read count, we won't have
	 * enough space - tough.  This race is indistinguishable to the
	 * caller from the case that the additional cgroup users didn't
	 * show up until sometime later on.
	 */
	npids = cgroup_task_count(cgrp);
	if (npids) {
		pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
		if (!pidarray)
			goto err1;

		npids = pid_array_load(pidarray, npids, cgrp);
		sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);

		/* Call pid_array_to_buf() twice, first just to get bufsz */
		ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1;
		ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL);
		if (!ctr->buf)
			goto err2;
		ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids);

		kfree(pidarray);
	} else {
		ctr->buf = 0;
		ctr->bufsz = 0;
	}
	file->private_data = ctr;
	return 0;

err2:
	kfree(pidarray);
err1:
	kfree(ctr);
err0:
	return -ENOMEM;
}

static ssize_t cgroup_tasks_read(struct cgroup *cgrp,
				    struct cftype *cft,
				    struct file *file, char __user *buf,
				    size_t nbytes, loff_t *ppos)
{
	struct ctr_struct *ctr = file->private_data;

	return simple_read_from_buffer(buf, nbytes, ppos, ctr->buf, ctr->bufsz);
}

static int cgroup_tasks_release(struct inode *unused_inode,
					struct file *file)
{
	struct ctr_struct *ctr;

	if (file->f_mode & FMODE_READ) {
		ctr = file->private_data;
		kfree(ctr->buf);
		kfree(ctr);
	}
	return 0;
}

static u64 cgroup_read_notify_on_release(struct cgroup *cgrp,
					    struct cftype *cft)
{
	return notify_on_release(cgrp);
}

static u64 cgroup_read_releasable(struct cgroup *cgrp, struct cftype *cft)
{
	return test_bit(CGRP_RELEASABLE, &cgrp->flags);
}

/*
 * for the common functions, 'private' gives the type of file
 */
static struct cftype files[] = {
	{
		.name = "tasks",
		.open = cgroup_tasks_open,
		.read = cgroup_tasks_read,
		.write = cgroup_common_file_write,
		.release = cgroup_tasks_release,
		.private = FILE_TASKLIST,
	},

	{
		.name = "notify_on_release",
		.read_uint = cgroup_read_notify_on_release,
		.write = cgroup_common_file_write,
		.private = FILE_NOTIFY_ON_RELEASE,
	},

	{
		.name = "releasable",
		.read_uint = cgroup_read_releasable,
		.private = FILE_RELEASABLE,
	}
};

static struct cftype cft_release_agent = {
	.name = "release_agent",
	.read = cgroup_common_file_read,
	.write = cgroup_common_file_write,
	.private = FILE_RELEASE_AGENT,
};

static int cgroup_populate_dir(struct cgroup *cgrp)
{
	int err;
	struct cgroup_subsys *ss;

	/* First clear out any existing files */
	cgroup_clear_directory(cgrp->dentry);

	err = cgroup_add_files(cgrp, NULL, files, ARRAY_SIZE(files));
	if (err < 0)
		return err;

	if (cgrp == cgrp->top_cgroup) {
		if ((err = cgroup_add_file(cgrp, NULL, &cft_release_agent)) < 0)
			return err;
	}

	for_each_subsys(cgrp->root, ss) {
		if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
			return err;
	}

	return 0;
}

static void init_cgroup_css(struct cgroup_subsys_state *css,
			       struct cgroup_subsys *ss,
			       struct cgroup *cgrp)
{
	css->cgroup = cgrp;
	atomic_set(&css->refcnt, 0);
	css->flags = 0;
	if (cgrp == dummytop)
		set_bit(CSS_ROOT, &css->flags);
	BUG_ON(cgrp->subsys[ss->subsys_id]);
	cgrp->subsys[ss->subsys_id] = css;
}

/*
 *	cgroup_create - create a cgroup
 *	parent:	cgroup that will be parent of the new cgroup.
 *	name:		name of the new cgroup. Will be strcpy'ed.
 *	mode:		mode to set on new inode
 *
 *	Must be called with the mutex on the parent inode held
 */

static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
			     int mode)
{
	struct cgroup *cgrp;
	struct cgroupfs_root *root = parent->root;
	int err = 0;
	struct cgroup_subsys *ss;
	struct super_block *sb = root->sb;

	cgrp = kzalloc(sizeof(*cgrp), GFP_KERNEL);
	if (!cgrp)
		return -ENOMEM;

	/* Grab a reference on the superblock so the hierarchy doesn't
	 * get deleted on unmount if there are child cgroups.  This
	 * can be done outside cgroup_mutex, since the sb can't
	 * disappear while someone has an open control file on the
	 * fs */
	atomic_inc(&sb->s_active);

	mutex_lock(&cgroup_mutex);

	cgrp->flags = 0;
	INIT_LIST_HEAD(&cgrp->sibling);
	INIT_LIST_HEAD(&cgrp->children);
	INIT_LIST_HEAD(&cgrp->css_sets);
	INIT_LIST_HEAD(&cgrp->release_list);

	cgrp->parent = parent;
	cgrp->root = parent->root;
	cgrp->top_cgroup = parent->top_cgroup;

	for_each_subsys(root, ss) {
		struct cgroup_subsys_state *css = ss->create(ss, cgrp);
		if (IS_ERR(css)) {
			err = PTR_ERR(css);
			goto err_destroy;
		}
		init_cgroup_css(css, ss, cgrp);
	}

	list_add(&cgrp->sibling, &cgrp->parent->children);
	root->number_of_cgroups++;

	err = cgroup_create_dir(cgrp, dentry, mode);
	if (err < 0)
		goto err_remove;

	/* The cgroup directory was pre-locked for us */
	BUG_ON(!mutex_is_locked(&cgrp->dentry->d_inode->i_mutex));

	err = cgroup_populate_dir(cgrp);
	/* If err < 0, we have a half-filled directory - oh well ;) */

	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);

	return 0;

 err_remove:

	list_del(&cgrp->sibling);
	root->number_of_cgroups--;

 err_destroy:

	for_each_subsys(root, ss) {
		if (cgrp->subsys[ss->subsys_id])
			ss->destroy(ss, cgrp);
	}

	mutex_unlock(&cgroup_mutex);

	/* Release the reference count that we took on the superblock */
	deactivate_super(sb);

	kfree(cgrp);
	return err;
}

static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	struct cgroup *c_parent = dentry->d_parent->d_fsdata;

	/* the vfs holds inode->i_mutex already */
	return cgroup_create(c_parent, dentry, mode | S_IFDIR);
}

static inline int cgroup_has_css_refs(struct cgroup *cgrp)
{
	/* Check the reference count on each subsystem. Since we
	 * already established that there are no tasks in the
	 * cgroup, if the css refcount is also 0, then there should
	 * be no outstanding references, so the subsystem is safe to
	 * destroy. We scan across all subsystems rather than using
	 * the per-hierarchy linked list of mounted subsystems since
	 * we can be called via check_for_release() with no
	 * synchronization other than RCU, and the subsystem linked
	 * list isn't RCU-safe */
	int i;
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		struct cgroup_subsys_state *css;
		/* Skip subsystems not in this hierarchy */
		if (ss->root != cgrp->root)
			continue;
		css = cgrp->subsys[ss->subsys_id];
		/* When called from check_for_release() it's possible
		 * that by this point the cgroup has been removed
		 * and the css deleted. But a false-positive doesn't
		 * matter, since it can only happen if the cgroup
		 * has been deleted and hence no longer needs the
		 * release agent to be called anyway. */
		if (css && atomic_read(&css->refcnt))
			return 1;
	}
	return 0;
}

static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
{
	struct cgroup *cgrp = dentry->d_fsdata;
	struct dentry *d;
	struct cgroup *parent;
	struct super_block *sb;
	struct cgroupfs_root *root;

	/* the vfs holds both inode->i_mutex already */

	mutex_lock(&cgroup_mutex);
	if (atomic_read(&cgrp->count) != 0) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}
	if (!list_empty(&cgrp->children)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}

	parent = cgrp->parent;
	root = cgrp->root;
	sb = root->sb;
	/*
	 * Call pre_destroy handlers of subsys
	 */
	cgroup_call_pre_destroy(cgrp);
	/*
	 * Notify subsyses that rmdir() request comes.
	 */

	if (cgroup_has_css_refs(cgrp)) {
		mutex_unlock(&cgroup_mutex);
		return -EBUSY;
	}

	spin_lock(&release_list_lock);
	set_bit(CGRP_REMOVED, &cgrp->flags);
	if (!list_empty(&cgrp->release_list))
		list_del(&cgrp->release_list);
	spin_unlock(&release_list_lock);
	/* delete my sibling from parent->children */
	list_del(&cgrp->sibling);
	spin_lock(&cgrp->dentry->d_lock);
	d = dget(cgrp->dentry);
	cgrp->dentry = NULL;
	spin_unlock(&d->d_lock);

	cgroup_d_remove_dir(d);
	dput(d);

	set_bit(CGRP_RELEASABLE, &parent->flags);
	check_for_release(parent);

	mutex_unlock(&cgroup_mutex);
	return 0;
}

static void cgroup_init_subsys(struct cgroup_subsys *ss)
{
	struct cgroup_subsys_state *css;
	struct list_head *l;

	printk(KERN_INFO "Initializing cgroup subsys %s\n", ss->name);

	/* Create the top cgroup state for this subsystem */
	ss->root = &rootnode;
	css = ss->create(ss, dummytop);
	/* We don't handle early failures gracefully */
	BUG_ON(IS_ERR(css));
	init_cgroup_css(css, ss, dummytop);

	/* Update all cgroup groups to contain a subsys
	 * pointer to this state - since the subsystem is
	 * newly registered, all tasks and hence all cgroup
	 * groups are in the subsystem's top cgroup. */
	write_lock(&css_set_lock);
	l = &init_css_set.list;
	do {
		struct css_set *cg =
			list_entry(l, struct css_set, list);
		cg->subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];
		l = l->next;
	} while (l != &init_css_set.list);
	write_unlock(&css_set_lock);

 	/* If this subsystem requested that it be notified with fork
 	 * events, we should send it one now for every process in the
 	 * system */
	if (ss->fork) {
		struct task_struct *g, *p;

		read_lock(&tasklist_lock);
		do_each_thread(g, p) {
			ss->fork(ss, p);
		} while_each_thread(g, p);
		read_unlock(&tasklist_lock);
	}

	need_forkexit_callback |= ss->fork || ss->exit;

	ss->active = 1;
}

/**
 * cgroup_init_early - initialize cgroups at system boot, and
 * initialize any subsystems that request early init.
 */
int __init cgroup_init_early(void)
{
	int i;
	kref_init(&init_css_set.ref);
	kref_get(&init_css_set.ref);
	INIT_LIST_HEAD(&init_css_set.list);
	INIT_LIST_HEAD(&init_css_set.cg_links);
	INIT_LIST_HEAD(&init_css_set.tasks);
	css_set_count = 1;
	init_cgroup_root(&rootnode);
	list_add(&rootnode.root_list, &roots);
	root_count = 1;
	init_task.cgroups = &init_css_set;

	init_css_set_link.cg = &init_css_set;
	list_add(&init_css_set_link.cgrp_link_list,
		 &rootnode.top_cgroup.css_sets);
	list_add(&init_css_set_link.cg_link_list,
		 &init_css_set.cg_links);

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];

		BUG_ON(!ss->name);
		BUG_ON(strlen(ss->name) > MAX_CGROUP_TYPE_NAMELEN);
		BUG_ON(!ss->create);
		BUG_ON(!ss->destroy);
		if (ss->subsys_id != i) {
			printk(KERN_ERR "cgroup: Subsys %s id == %d\n",
			       ss->name, ss->subsys_id);
			BUG();
		}

		if (ss->early_init)
			cgroup_init_subsys(ss);
	}
	return 0;
}

/**
 * cgroup_init - register cgroup filesystem and /proc file, and
 * initialize any subsystems that didn't request early init.
 */
int __init cgroup_init(void)
{
	int err;
	int i;
	struct proc_dir_entry *entry;

	err = bdi_init(&cgroup_backing_dev_info);
	if (err)
		return err;

	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		if (!ss->early_init)
			cgroup_init_subsys(ss);
	}

	err = register_filesystem(&cgroup_fs_type);
	if (err < 0)
		goto out;

	entry = create_proc_entry("cgroups", 0, NULL);
	if (entry)
		entry->proc_fops = &proc_cgroupstats_operations;

out:
	if (err)
		bdi_destroy(&cgroup_backing_dev_info);

	return err;
}

/*
 * proc_cgroup_show()
 *  - Print task's cgroup paths into seq_file, one line for each hierarchy
 *  - Used for /proc/<pid>/cgroup.
 *  - No need to task_lock(tsk) on this tsk->cgroup reference, as it
 *    doesn't really matter if tsk->cgroup changes after we read it,
 *    and we take cgroup_mutex, keeping cgroup_attach_task() from changing it
 *    anyway.  No need to check that tsk->cgroup != NULL, thanks to
 *    the_top_cgroup_hack in cgroup_exit(), which sets an exiting tasks
 *    cgroup to top_cgroup.
 */

/* TODO: Use a proper seq_file iterator */
static int proc_cgroup_show(struct seq_file *m, void *v)
{
	struct pid *pid;
	struct task_struct *tsk;
	char *buf;
	int retval;
	struct cgroupfs_root *root;

	retval = -ENOMEM;
	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
	if (!buf)
		goto out;

	retval = -ESRCH;
	pid = m->private;
	tsk = get_pid_task(pid, PIDTYPE_PID);
	if (!tsk)
		goto out_free;

	retval = 0;

	mutex_lock(&cgroup_mutex);

	for_each_root(root) {
		struct cgroup_subsys *ss;
		struct cgroup *cgrp;
		int subsys_id;
		int count = 0;

		/* Skip this hierarchy if it has no active subsystems */
		if (!root->actual_subsys_bits)
			continue;
		for_each_subsys(root, ss)
			seq_printf(m, "%s%s", count++ ? "," : "", ss->name);
		seq_putc(m, ':');
		get_first_subsys(&root->top_cgroup, NULL, &subsys_id);
		cgrp = task_cgroup(tsk, subsys_id);
		retval = cgroup_path(cgrp, buf, PAGE_SIZE);
		if (retval < 0)
			goto out_unlock;
		seq_puts(m, buf);
		seq_putc(m, '\n');
	}

out_unlock:
	mutex_unlock(&cgroup_mutex);
	put_task_struct(tsk);
out_free:
	kfree(buf);
out:
	return retval;
}

static int cgroup_open(struct inode *inode, struct file *file)
{
	struct pid *pid = PROC_I(inode)->pid;
	return single_open(file, proc_cgroup_show, pid);
}

struct file_operations proc_cgroup_operations = {
	.open		= cgroup_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

/* Display information about each subsystem and each hierarchy */
static int proc_cgroupstats_show(struct seq_file *m, void *v)
{
	int i;

	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\n");
	mutex_lock(&cgroup_mutex);
	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
		struct cgroup_subsys *ss = subsys[i];
		seq_printf(m, "%s\t%lu\t%d\n",
			   ss->name, ss->root->subsys_bits,
			   ss->root->number_of_cgroups);
	}
	mutex_unlock(&cgroup_mutex);
	return 0;
}

static int cgroupstats_open(struct inode *inode, struct file *file)
{
	return single_open(file, proc_cgroupstats_show, 0);
}

static struct file_operations proc_cgroupstats_operations = {
	.open = cgroupstats_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

/**
 * cgroup_fork - attach newly forked task to its parents cgroup.
 * @tsk: pointer to task_struct of forking parent process.
 *
 * Description: A task inherits its parent's cgroup at fork().
 *
 * A pointer to the shared css_set was automatically copied in
 * fork.c by dup_task_struct().  However, we ignore that copy, since
 * it was not made under the protection of RCU or cgroup_mutex, so
 * might no longer be a valid cgroup pointer.  cgroup_attach_task() might
 * have already changed current->cgroups, allowing the previously
 * referenced cgroup group to be removed and freed.
 *
 * At the point that cgroup_fork() is called, 'current' is the parent
 * task, and the passed argument 'child' points to the child task.
 */
void cgroup_fork(struct task_struct *child)
{
	task_lock(current);
	child->cgroups = current->cgroups;
	get_css_set(child->cgroups);
	task_unlock(current);
	INIT_LIST_HEAD(&child->cg_list);
}

/**
 * cgroup_fork_callbacks - called on a new task very soon before
 * adding it to the tasklist. No need to take any locks since no-one
 * can be operating on this task
 */
void cgroup_fork_callbacks(struct task_struct *child)
{
	if (need_forkexit_callback) {
		int i;
		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];
			if (ss->fork)
				ss->fork(ss, child);
		}
	}
}

/**
 * cgroup_post_fork - called on a new task after adding it to the
 * task list. Adds the task to the list running through its css_set
 * if necessary. Has to be after the task is visible on the task list
 * in case we race with the first call to cgroup_iter_start() - to
 * guarantee that the new task ends up on its list. */
void cgroup_post_fork(struct task_struct *child)
{
	if (use_task_css_set_links) {
		write_lock(&css_set_lock);
		if (list_empty(&child->cg_list))
			list_add(&child->cg_list, &child->cgroups->tasks);
		write_unlock(&css_set_lock);
	}
}
/**
 * cgroup_exit - detach cgroup from exiting task
 * @tsk: pointer to task_struct of exiting process
 *
 * Description: Detach cgroup from @tsk and release it.
 *
 * Note that cgroups marked notify_on_release force every task in
 * them to take the global cgroup_mutex mutex when exiting.
 * This could impact scaling on very large systems.  Be reluctant to
 * use notify_on_release cgroups where very high task exit scaling
 * is required on large systems.
 *
 * the_top_cgroup_hack:
 *
 *    Set the exiting tasks cgroup to the root cgroup (top_cgroup).
 *
 *    We call cgroup_exit() while the task is still competent to
 *    handle notify_on_release(), then leave the task attached to the
 *    root cgroup in each hierarchy for the remainder of its exit.
 *
 *    To do this properly, we would increment the reference count on
 *    top_cgroup, and near the very end of the kernel/exit.c do_exit()
 *    code we would add a second cgroup function call, to drop that
 *    reference.  This would just create an unnecessary hot spot on
 *    the top_cgroup reference count, to no avail.
 *
 *    Normally, holding a reference to a cgroup without bumping its
 *    count is unsafe.   The cgroup could go away, or someone could
 *    attach us to a different cgroup, decrementing the count on
 *    the first cgroup that we never incremented.  But in this case,
 *    top_cgroup isn't going away, and either task has PF_EXITING set,
 *    which wards off any cgroup_attach_task() attempts, or task is a failed
 *    fork, never visible to cgroup_attach_task.
 *
 */
void cgroup_exit(struct task_struct *tsk, int run_callbacks)
{
	int i;
	struct css_set *cg;

	if (run_callbacks && need_forkexit_callback) {
		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];
			if (ss->exit)
				ss->exit(ss, tsk);
		}
	}

	/*
	 * Unlink from the css_set task list if necessary.
	 * Optimistically check cg_list before taking
	 * css_set_lock
	 */
	if (!list_empty(&tsk->cg_list)) {
		write_lock(&css_set_lock);
		if (!list_empty(&tsk->cg_list))
			list_del(&tsk->cg_list);
		write_unlock(&css_set_lock);
	}

	/* Reassign the task to the init_css_set. */
	task_lock(tsk);
	cg = tsk->cgroups;
	tsk->cgroups = &init_css_set;
	task_unlock(tsk);
	if (cg)
		put_css_set_taskexit(cg);
}

/**
 * cgroup_clone - duplicate the current cgroup in the hierarchy
 * that the given subsystem is attached to, and move this task into
 * the new child
 */
int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys)
{
	struct dentry *dentry;
	int ret = 0;
	char nodename[MAX_CGROUP_TYPE_NAMELEN];
	struct cgroup *parent, *child;
	struct inode *inode;
	struct css_set *cg;
	struct cgroupfs_root *root;
	struct cgroup_subsys *ss;

	/* We shouldn't be called by an unregistered subsystem */
	BUG_ON(!subsys->active);

	/* First figure out what hierarchy and cgroup we're dealing
	 * with, and pin them so we can drop cgroup_mutex */
	mutex_lock(&cgroup_mutex);
 again:
	root = subsys->root;
	if (root == &rootnode) {
		printk(KERN_INFO
		       "Not cloning cgroup for unused subsystem %s\n",
		       subsys->name);
		mutex_unlock(&cgroup_mutex);
		return 0;
	}
	cg = tsk->cgroups;
	parent = task_cgroup(tsk, subsys->subsys_id);

	snprintf(nodename, MAX_CGROUP_TYPE_NAMELEN, "node_%d", tsk->pid);

	/* Pin the hierarchy */
	atomic_inc(&parent->root->sb->s_active);

	/* Keep the cgroup alive */
	get_css_set(cg);
	mutex_unlock(&cgroup_mutex);

	/* Now do the VFS work to create a cgroup */
	inode = parent->dentry->d_inode;

	/* Hold the parent directory mutex across this operation to
	 * stop anyone else deleting the new cgroup */
	mutex_lock(&inode->i_mutex);
	dentry = lookup_one_len(nodename, parent->dentry, strlen(nodename));
	if (IS_ERR(dentry)) {
		printk(KERN_INFO
		       "cgroup: Couldn't allocate dentry for %s: %ld\n", nodename,
		       PTR_ERR(dentry));
		ret = PTR_ERR(dentry);
		goto out_release;
	}

	/* Create the cgroup directory, which also creates the cgroup */
	ret = vfs_mkdir(inode, dentry, S_IFDIR | 0755);
	child = __d_cgrp(dentry);
	dput(dentry);
	if (ret) {
		printk(KERN_INFO
		       "Failed to create cgroup %s: %d\n", nodename,
		       ret);
		goto out_release;
	}

	if (!child) {
		printk(KERN_INFO
		       "Couldn't find new cgroup %s\n", nodename);
		ret = -ENOMEM;
		goto out_release;
	}

	/* The cgroup now exists. Retake cgroup_mutex and check
	 * that we're still in the same state that we thought we
	 * were. */
	mutex_lock(&cgroup_mutex);
	if ((root != subsys->root) ||
	    (parent != task_cgroup(tsk, subsys->subsys_id))) {
		/* Aargh, we raced ... */
		mutex_unlock(&inode->i_mutex);
		put_css_set(cg);

		deactivate_super(parent->root->sb);
		/* The cgroup is still accessible in the VFS, but
		 * we're not going to try to rmdir() it at this
		 * point. */
		printk(KERN_INFO
		       "Race in cgroup_clone() - leaking cgroup %s\n",
		       nodename);
		goto again;
	}

	/* do any required auto-setup */
	for_each_subsys(root, ss) {
		if (ss->post_clone)
			ss->post_clone(ss, child);
	}

	/* All seems fine. Finish by moving the task into the new cgroup */
	ret = cgroup_attach_task(child, tsk);
	mutex_unlock(&cgroup_mutex);

 out_release:
	mutex_unlock(&inode->i_mutex);

	mutex_lock(&cgroup_mutex);
	put_css_set(cg);
	mutex_unlock(&cgroup_mutex);
	deactivate_super(parent->root->sb);
	return ret;
}

/*
 * See if "cgrp" is a descendant of the current task's cgroup in
 * the appropriate hierarchy
 *
 * If we are sending in dummytop, then presumably we are creating
 * the top cgroup in the subsystem.
 *
 * Called only by the ns (nsproxy) cgroup.
 */
int cgroup_is_descendant(const struct cgroup *cgrp)
{
	int ret;
	struct cgroup *target;
	int subsys_id;

	if (cgrp == dummytop)
		return 1;

	get_first_subsys(cgrp, NULL, &subsys_id);
	target = task_cgroup(current, subsys_id);
	while (cgrp != target && cgrp!= cgrp->top_cgroup)
		cgrp = cgrp->parent;
	ret = (cgrp == target);
	return ret;
}

static void check_for_release(struct cgroup *cgrp)
{
	/* All of these checks rely on RCU to keep the cgroup
	 * structure alive */
	if (cgroup_is_releasable(cgrp) && !atomic_read(&cgrp->count)
	    && list_empty(&cgrp->children) && !cgroup_has_css_refs(cgrp)) {
		/* Control Group is currently removeable. If it's not
		 * already queued for a userspace notification, queue
		 * it now */
		int need_schedule_work = 0;
		spin_lock(&release_list_lock);
		if (!cgroup_is_removed(cgrp) &&
		    list_empty(&cgrp->release_list)) {
			list_add(&cgrp->release_list, &release_list);
			need_schedule_work = 1;
		}
		spin_unlock(&release_list_lock);
		if (need_schedule_work)
			schedule_work(&release_agent_work);
	}
}

void __css_put(struct cgroup_subsys_state *css)
{
	struct cgroup *cgrp = css->cgroup;
	rcu_read_lock();
	if (atomic_dec_and_test(&css->refcnt) && notify_on_release(cgrp)) {
		set_bit(CGRP_RELEASABLE, &cgrp->flags);
		check_for_release(cgrp);
	}
	rcu_read_unlock();
}

/*
 * Notify userspace when a cgroup is released, by running the
 * configured release agent with the name of the cgroup (path
 * relative to the root of cgroup file system) as the argument.
 *
 * Most likely, this user command will try to rmdir this cgroup.
 *
 * This races with the possibility that some other task will be
 * attached to this cgroup before it is removed, or that some other
 * user task will 'mkdir' a child cgroup of this cgroup.  That's ok.
 * The presumed 'rmdir' will fail quietly if this cgroup is no longer
 * unused, and this cgroup will be reprieved from its death sentence,
 * to continue to serve a useful existence.  Next time it's released,
 * we will get notified again, if it still has 'notify_on_release' set.
 *
 * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which
 * means only wait until the task is successfully execve()'d.  The
 * separate release agent task is forked by call_usermodehelper(),
 * then control in this thread returns here, without waiting for the
 * release agent task.  We don't bother to wait because the caller of
 * this routine has no use for the exit status of the release agent
 * task, so no sense holding our caller up for that.
 *
 */

static void cgroup_release_agent(struct work_struct *work)
{
	BUG_ON(work != &release_agent_work);
	mutex_lock(&cgroup_mutex);
	spin_lock(&release_list_lock);
	while (!list_empty(&release_list)) {
		char *argv[3], *envp[3];
		int i;
		char *pathbuf;
		struct cgroup *cgrp = list_entry(release_list.next,
						    struct cgroup,
						    release_list);
		list_del_init(&cgrp->release_list);
		spin_unlock(&release_list_lock);
		pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
		if (!pathbuf) {
			spin_lock(&release_list_lock);
			continue;
		}

		if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0) {
			kfree(pathbuf);
			spin_lock(&release_list_lock);
			continue;
		}

		i = 0;
		argv[i++] = cgrp->root->release_agent_path;
		argv[i++] = (char *)pathbuf;
		argv[i] = NULL;

		i = 0;
		/* minimal command environment */
		envp[i++] = "HOME=/";
		envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
		envp[i] = NULL;

		/* Drop the lock while we invoke the usermode helper,
		 * since the exec could involve hitting disk and hence
		 * be a slow process */
		mutex_unlock(&cgroup_mutex);
		call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
		kfree(pathbuf);
		mutex_lock(&cgroup_mutex);
		spin_lock(&release_list_lock);
	}
	spin_unlock(&release_list_lock);
	mutex_unlock(&cgroup_mutex);
}