cgroup.c

		write_lock(&css_set_lock);
		if (!list_empty(&tsk->cg_list))
			list_del_init(&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;

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

			/* modular subsystems can't use callbacks */
			if (!ss || ss->module)
				continue;

			if (ss->exit) {
				struct cgroup *old_cgrp =
					rcu_dereference_raw(cg->subsys[i])->cgroup;
				struct cgroup *cgrp = task_cgroup(tsk, i);
				ss->exit(cgrp, old_cgrp, tsk);
			}
		}
	}
	task_unlock(tsk);

	put_css_set_taskexit(cg);
}

/**
 * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
 * @cgrp: the cgroup in question
 * @task: the task in question
 *
 * See if @cgrp is a descendant of @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, struct task_struct *task)
{
	int ret;
	struct cgroup *target;

	if (cgrp == dummytop)
		return 1;

	target = task_cgroup_from_root(task, cgrp->root);
	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;
		raw_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;
		}
		raw_spin_unlock(&release_list_lock);
		if (need_schedule_work)
			schedule_work(&release_agent_work);
	}
}

/* Caller must verify that the css is not for root cgroup */
bool __css_tryget(struct cgroup_subsys_state *css)
{
	while (true) {
		int t, v;

		v = css_refcnt(css);
		t = atomic_cmpxchg(&css->refcnt, v, v + 1);
		if (likely(t == v))
			return true;
		else if (t < 0)
			return false;
		cpu_relax();
	}
}
EXPORT_SYMBOL_GPL(__css_tryget);

/* Caller must verify that the css is not for root cgroup */
void __css_put(struct cgroup_subsys_state *css)
{
	struct cgroup *cgrp = css->cgroup;
	int v;

	rcu_read_lock();
	v = css_unbias_refcnt(atomic_dec_return(&css->refcnt));

	switch (v) {
	case 1:
		if (notify_on_release(cgrp)) {
			set_bit(CGRP_RELEASABLE, &cgrp->flags);
			check_for_release(cgrp);
		}
		break;
	case 0:
		schedule_work(&css->dput_work);
		break;
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(__css_put);

/*
 * 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);
	raw_spin_lock(&release_list_lock);
	while (!list_empty(&release_list)) {
		char *argv[3], *envp[3];
		int i;
		char *pathbuf = NULL, *agentbuf = NULL;
		struct cgroup *cgrp = list_entry(release_list.next,
						    struct cgroup,
						    release_list);
		list_del_init(&cgrp->release_list);
		raw_spin_unlock(&release_list_lock);
		pathbuf = kmalloc(PAGE_SIZE, GFP_KERNEL);
		if (!pathbuf)
			goto continue_free;
		if (cgroup_path(cgrp, pathbuf, PAGE_SIZE) < 0)
			goto continue_free;
		agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL);
		if (!agentbuf)
			goto continue_free;

		i = 0;
		argv[i++] = agentbuf;
		argv[i++] = 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);
		mutex_lock(&cgroup_mutex);
 continue_free:
		kfree(pathbuf);
		kfree(agentbuf);
		raw_spin_lock(&release_list_lock);
	}
	raw_spin_unlock(&release_list_lock);
	mutex_unlock(&cgroup_mutex);
}

static int __init cgroup_disable(char *str)
{
	int i;
	char *token;

	while ((token = strsep(&str, ",")) != NULL) {
		if (!*token)
			continue;
		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
			struct cgroup_subsys *ss = subsys[i];

			/*
			 * cgroup_disable, being at boot time, can't
			 * know about module subsystems, so we don't
			 * worry about them.
			 */
			if (!ss || ss->module)
				continue;

			if (!strcmp(token, ss->name)) {
				ss->disabled = 1;
				printk(KERN_INFO "Disabling %s control group"
					" subsystem\n", ss->name);
				break;
			}
		}
	}
	return 1;
}
__setup("cgroup_disable=", cgroup_disable);

/*
 * Functons for CSS ID.
 */

/*
 *To get ID other than 0, this should be called when !cgroup_is_removed().
 */
unsigned short css_id(struct cgroup_subsys_state *css)
{
	struct css_id *cssid;

	/*
	 * This css_id() can return correct value when somone has refcnt
	 * on this or this is under rcu_read_lock(). Once css->id is allocated,
	 * it's unchanged until freed.
	 */
	cssid = rcu_dereference_check(css->id, css_refcnt(css));

	if (cssid)
		return cssid->id;
	return 0;
}
EXPORT_SYMBOL_GPL(css_id);

unsigned short css_depth(struct cgroup_subsys_state *css)
{
	struct css_id *cssid;

	cssid = rcu_dereference_check(css->id, css_refcnt(css));

	if (cssid)
		return cssid->depth;
	return 0;
}
EXPORT_SYMBOL_GPL(css_depth);

/**
 *  css_is_ancestor - test "root" css is an ancestor of "child"
 * @child: the css to be tested.
 * @root: the css supporsed to be an ancestor of the child.
 *
 * Returns true if "root" is an ancestor of "child" in its hierarchy. Because
 * this function reads css->id, the caller must hold rcu_read_lock().
 * But, considering usual usage, the csses should be valid objects after test.
 * Assuming that the caller will do some action to the child if this returns
 * returns true, the caller must take "child";s reference count.
 * If "child" is valid object and this returns true, "root" is valid, too.
 */

bool css_is_ancestor(struct cgroup_subsys_state *child,
		    const struct cgroup_subsys_state *root)
{
	struct css_id *child_id;
	struct css_id *root_id;

	child_id  = rcu_dereference(child->id);
	if (!child_id)
		return false;
	root_id = rcu_dereference(root->id);
	if (!root_id)
		return false;
	if (child_id->depth < root_id->depth)
		return false;
	if (child_id->stack[root_id->depth] != root_id->id)
		return false;
	return true;
}

void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
{
	struct css_id *id = css->id;
	/* When this is called before css_id initialization, id can be NULL */
	if (!id)
		return;

	BUG_ON(!ss->use_id);

	rcu_assign_pointer(id->css, NULL);
	rcu_assign_pointer(css->id, NULL);
	spin_lock(&ss->id_lock);
	idr_remove(&ss->idr, id->id);
	spin_unlock(&ss->id_lock);
	kfree_rcu(id, rcu_head);
}
EXPORT_SYMBOL_GPL(free_css_id);

/*
 * This is called by init or create(). Then, calls to this function are
 * always serialized (By cgroup_mutex() at create()).
 */

static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
{
	struct css_id *newid;
	int ret, size;

	BUG_ON(!ss->use_id);

	size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
	newid = kzalloc(size, GFP_KERNEL);
	if (!newid)
		return ERR_PTR(-ENOMEM);

	idr_preload(GFP_KERNEL);
	spin_lock(&ss->id_lock);
	/* Don't use 0. allocates an ID of 1-65535 */
	ret = idr_alloc(&ss->idr, newid, 1, CSS_ID_MAX + 1, GFP_NOWAIT);
	spin_unlock(&ss->id_lock);
	idr_preload_end();

	/* Returns error when there are no free spaces for new ID.*/
	if (ret < 0)
		goto err_out;

	newid->id = ret;
	newid->depth = depth;
	return newid;
err_out:
	kfree(newid);
	return ERR_PTR(ret);

}

static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
					    struct cgroup_subsys_state *rootcss)
{
	struct css_id *newid;

	spin_lock_init(&ss->id_lock);
	idr_init(&ss->idr);

	newid = get_new_cssid(ss, 0);
	if (IS_ERR(newid))
		return PTR_ERR(newid);

	newid->stack[0] = newid->id;
	newid->css = rootcss;
	rootcss->id = newid;
	return 0;
}

static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
			struct cgroup *child)
{
	int subsys_id, i, depth = 0;
	struct cgroup_subsys_state *parent_css, *child_css;
	struct css_id *child_id, *parent_id;

	subsys_id = ss->subsys_id;
	parent_css = parent->subsys[subsys_id];
	child_css = child->subsys[subsys_id];
	parent_id = parent_css->id;
	depth = parent_id->depth + 1;

	child_id = get_new_cssid(ss, depth);
	if (IS_ERR(child_id))
		return PTR_ERR(child_id);

	for (i = 0; i < depth; i++)
		child_id->stack[i] = parent_id->stack[i];
	child_id->stack[depth] = child_id->id;
	/*
	 * child_id->css pointer will be set after this cgroup is available
	 * see cgroup_populate_dir()
	 */
	rcu_assign_pointer(child_css->id, child_id);

	return 0;
}

/**
 * css_lookup - lookup css by id
 * @ss: cgroup subsys to be looked into.
 * @id: the id
 *
 * Returns pointer to cgroup_subsys_state if there is valid one with id.
 * NULL if not. Should be called under rcu_read_lock()
 */
struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
{
	struct css_id *cssid = NULL;

	BUG_ON(!ss->use_id);
	cssid = idr_find(&ss->idr, id);

	if (unlikely(!cssid))
		return NULL;

	return rcu_dereference(cssid->css);
}
EXPORT_SYMBOL_GPL(css_lookup);

/**
 * css_get_next - lookup next cgroup under specified hierarchy.
 * @ss: pointer to subsystem
 * @id: current position of iteration.
 * @root: pointer to css. search tree under this.
 * @foundid: position of found object.
 *
 * Search next css under the specified hierarchy of rootid. Calling under
 * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
 */
struct cgroup_subsys_state *
css_get_next(struct cgroup_subsys *ss, int id,
	     struct cgroup_subsys_state *root, int *foundid)
{
	struct cgroup_subsys_state *ret = NULL;
	struct css_id *tmp;
	int tmpid;
	int rootid = css_id(root);
	int depth = css_depth(root);

	if (!rootid)
		return NULL;

	BUG_ON(!ss->use_id);
	WARN_ON_ONCE(!rcu_read_lock_held());

	/* fill start point for scan */
	tmpid = id;
	while (1) {
		/*
		 * scan next entry from bitmap(tree), tmpid is updated after
		 * idr_get_next().
		 */
		tmp = idr_get_next(&ss->idr, &tmpid);
		if (!tmp)
			break;
		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
			ret = rcu_dereference(tmp->css);
			if (ret) {
				*foundid = tmpid;
				break;
			}
		}
		/* continue to scan from next id */
		tmpid = tmpid + 1;
	}
	return ret;
}

/*
 * get corresponding css from file open on cgroupfs directory
 */
struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id)
{
	struct cgroup *cgrp;
	struct inode *inode;
	struct cgroup_subsys_state *css;

	inode = file_inode(f);
	/* check in cgroup filesystem dir */
	if (inode->i_op != &cgroup_dir_inode_operations)
		return ERR_PTR(-EBADF);

	if (id < 0 || id >= CGROUP_SUBSYS_COUNT)
		return ERR_PTR(-EINVAL);

	/* get cgroup */
	cgrp = __d_cgrp(f->f_dentry);
	css = cgrp->subsys[id];
	return css ? css : ERR_PTR(-ENOENT);
}

#ifdef CONFIG_CGROUP_DEBUG
static struct cgroup_subsys_state *debug_css_alloc(struct cgroup *cont)
{
	struct cgroup_subsys_state *css = kzalloc(sizeof(*css), GFP_KERNEL);

	if (!css)
		return ERR_PTR(-ENOMEM);

	return css;
}

static void debug_css_free(struct cgroup *cont)
{
	kfree(cont->subsys[debug_subsys_id]);
}

static u64 cgroup_refcount_read(struct cgroup *cont, struct cftype *cft)
{
	return atomic_read(&cont->count);
}

static u64 debug_taskcount_read(struct cgroup *cont, struct cftype *cft)
{
	return cgroup_task_count(cont);
}

static u64 current_css_set_read(struct cgroup *cont, struct cftype *cft)
{
	return (u64)(unsigned long)current->cgroups;
}

static u64 current_css_set_refcount_read(struct cgroup *cont,
					   struct cftype *cft)
{
	u64 count;

	rcu_read_lock();
	count = atomic_read(&current->cgroups->refcount);
	rcu_read_unlock();
	return count;
}

static int current_css_set_cg_links_read(struct cgroup *cont,
					 struct cftype *cft,
					 struct seq_file *seq)
{
	struct cg_cgroup_link *link;
	struct css_set *cg;

	read_lock(&css_set_lock);
	rcu_read_lock();
	cg = rcu_dereference(current->cgroups);
	list_for_each_entry(link, &cg->cg_links, cg_link_list) {
		struct cgroup *c = link->cgrp;
		const char *name;

		if (c->dentry)
			name = c->dentry->d_name.name;
		else
			name = "?";
		seq_printf(seq, "Root %d group %s\n",
			   c->root->hierarchy_id, name);
	}
	rcu_read_unlock();
	read_unlock(&css_set_lock);
	return 0;
}

#define MAX_TASKS_SHOWN_PER_CSS 25
static int cgroup_css_links_read(struct cgroup *cont,
				 struct cftype *cft,
				 struct seq_file *seq)
{
	struct cg_cgroup_link *link;

	read_lock(&css_set_lock);
	list_for_each_entry(link, &cont->css_sets, cgrp_link_list) {
		struct css_set *cg = link->cg;
		struct task_struct *task;
		int count = 0;
		seq_printf(seq, "css_set %p\n", cg);
		list_for_each_entry(task, &cg->tasks, cg_list) {
			if (count++ > MAX_TASKS_SHOWN_PER_CSS) {
				seq_puts(seq, "  ...\n");
				break;
			} else {
				seq_printf(seq, "  task %d\n",
					   task_pid_vnr(task));
			}
		}
	}
	read_unlock(&css_set_lock);
	return 0;
}

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

static struct cftype debug_files[] =  {
	{
		.name = "cgroup_refcount",
		.read_u64 = cgroup_refcount_read,
	},
	{
		.name = "taskcount",
		.read_u64 = debug_taskcount_read,
	},

	{
		.name = "current_css_set",
		.read_u64 = current_css_set_read,
	},

	{
		.name = "current_css_set_refcount",
		.read_u64 = current_css_set_refcount_read,
	},

	{
		.name = "current_css_set_cg_links",
		.read_seq_string = current_css_set_cg_links_read,
	},

	{
		.name = "cgroup_css_links",
		.read_seq_string = cgroup_css_links_read,
	},

	{
		.name = "releasable",
		.read_u64 = releasable_read,
	},

	{ }	/* terminate */
};

struct cgroup_subsys debug_subsys = {
	.name = "debug",
	.css_alloc = debug_css_alloc,
	.css_free = debug_css_free,
	.subsys_id = debug_subsys_id,
	.base_cftypes = debug_files,
};
#endif /* CONFIG_CGROUP_DEBUG */