cgroup.c

out_free:
	kfree(buf);
out:
	return retval;
}

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

	seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n");
	/*
	 * ideally we don't want subsystems moving around while we do this.
	 * cgroup_mutex is also necessary to guarantee an atomic snapshot of
	 * subsys/hierarchy state.
	 */
	mutex_lock(&cgroup_mutex);

	for_each_subsys(ss, i)
		seq_printf(m, "%s\t%d\t%d\t%d\n",
			   ss->name, ss->root->hierarchy_id,
			   ss->root->number_of_cgroups, !ss->disabled);

	mutex_unlock(&cgroup_mutex);
	return 0;
}

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

static const 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.
 * @child: 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);
	get_css_set(task_css_set(current));
	child->cgroups = current->cgroups;
	task_unlock(current);
	INIT_LIST_HEAD(&child->cg_list);
}

/**
 * cgroup_post_fork - called on a new task after adding it to the task list
 * @child: the task in question
 *
 * Adds the task to the list running through its css_set if necessary and
 * call the subsystem fork() callbacks.  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)
{
	struct cgroup_subsys *ss;
	int i;

	/*
	 * use_task_css_set_links is set to 1 before we walk the tasklist
	 * under the tasklist_lock and we read it here after we added the child
	 * to the tasklist under the tasklist_lock as well. If the child wasn't
	 * yet in the tasklist when we walked through it from
	 * cgroup_enable_task_cg_lists(), then use_task_css_set_links value
	 * should be visible now due to the paired locking and barriers implied
	 * by LOCK/UNLOCK: it is written before the tasklist_lock unlock
	 * in cgroup_enable_task_cg_lists() and read here after the tasklist_lock
	 * lock on fork.
	 */
	if (use_task_css_set_links) {
		write_lock(&css_set_lock);
		task_lock(child);
		if (list_empty(&child->cg_list))
			list_add(&child->cg_list, &task_css_set(child)->tasks);
		task_unlock(child);
		write_unlock(&css_set_lock);
	}

	/*
	 * Call ss->fork().  This must happen after @child is linked on
	 * css_set; otherwise, @child might change state between ->fork()
	 * and addition to css_set.
	 */
	if (need_forkexit_callback) {
		/*
		 * fork/exit callbacks are supported only for builtin
		 * subsystems, and the builtin section of the subsys
		 * array is immutable, so we don't need to lock the
		 * subsys array here. On the other hand, modular section
		 * of the array can be freed at module unload, so we
		 * can't touch that.
		 */
		for_each_builtin_subsys(ss, i)
			if (ss->fork)
				ss->fork(child);
	}
}

/**
 * cgroup_exit - detach cgroup from exiting task
 * @tsk: pointer to task_struct of exiting process
 * @run_callback: run exit callbacks?
 *
 * 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)
{
	struct cgroup_subsys *ss;
	struct css_set *cset;
	int i;

	/*
	 * 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_init(&tsk->cg_list);
		write_unlock(&css_set_lock);
	}

	/* Reassign the task to the init_css_set. */
	task_lock(tsk);
	cset = task_css_set(tsk);
	RCU_INIT_POINTER(tsk->cgroups, &init_css_set);

	if (run_callbacks && need_forkexit_callback) {
		/*
		 * fork/exit callbacks are supported only for builtin
		 * subsystems, see cgroup_post_fork() for details.
		 */
		for_each_builtin_subsys(ss, i) {
			if (ss->exit) {
				struct cgroup *old_cgrp = cset->subsys[i]->cgroup;
				struct cgroup *cgrp = task_cgroup(tsk, i);

				ss->exit(cgrp, old_cgrp, tsk);
			}
		}
	}
	task_unlock(tsk);

	put_css_set_taskexit(cset);
}

static void check_for_release(struct cgroup *cgrp)
{
	if (cgroup_is_releasable(cgrp) &&
	    list_empty(&cgrp->cset_links) && list_empty(&cgrp->children)) {
		/*
		 * 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_dead(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);
	}
}

/*
 * 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)
{
	struct cgroup_subsys *ss;
	char *token;
	int i;

	while ((token = strsep(&str, ",")) != NULL) {
		if (!*token)
			continue;

		/*
		 * cgroup_disable, being at boot time, can't know about
		 * module subsystems, so we don't worry about them.
		 */
		for_each_builtin_subsys(ss, i) {
			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_dead() */
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_raw(css->id);

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

/**
 *  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 = rcu_dereference_protected(css->id, true);

	/* 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;
	RCU_INIT_POINTER(newid->css, rootcss);
	RCU_INIT_POINTER(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 = rcu_dereference_protected(parent_css->id, true);
	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);

/*
 * 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 *cgrp)
{
	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 *cgrp)
{
	kfree(cgrp->subsys[debug_subsys_id]);
}

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

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

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

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

static int current_css_set_cg_links_read(struct cgroup *cgrp,
					 struct cftype *cft,
					 struct seq_file *seq)
{
	struct cgrp_cset_link *link;
	struct css_set *cset;

	read_lock(&css_set_lock);
	rcu_read_lock();
	cset = rcu_dereference(current->cgroups);
	list_for_each_entry(link, &cset->cgrp_links, cgrp_link) {
		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 *cgrp,
				 struct cftype *cft,
				 struct seq_file *seq)
{
	struct cgrp_cset_link *link;

	read_lock(&css_set_lock);
	list_for_each_entry(link, &cgrp->cset_links, cset_link) {
		struct css_set *cset = link->cset;
		struct task_struct *task;
		int count = 0;
		seq_printf(seq, "css_set %p\n", cset);
		list_for_each_entry(task, &cset->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 = "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 */