cgroup.c

Kernel code of linux kernel

		goto again;
	}
	if (heap == &tmp_heap)
		heap_free(&tmp_heap);
	return 0;
}

/*
 * Stuff for reading the 'tasks' file.
 *
 * Reading this file can return large amounts of data if a cgroup has
 * *lots* of attached tasks. So it may need several calls to read(),
 * but we cannot guarantee that the information we produce is correct
 * unless we produce it entirely atomically.
 *
 * Upon tasks file open(), a struct ctr_struct is allocated, that
 * will have a pointer to an array (also allocated here).  The struct
 * ctr_struct * is stored in file->private_data.  Its resources will
 * be freed by release() when the file is closed.  The array is used
 * to sprintf the PIDs and then used by read().
 */
struct ctr_struct {
	char *buf;
	int bufsz;
};

/*
 * Load into 'pidarray' up to 'npids' of the tasks using cgroup
 * 'cgrp'.  Return actual number of pids loaded.  No need to
 * task_lock(p) when reading out p->cgroup, since we're in an RCU
 * read section, so the css_set can't go away, and is
 * immutable after creation.
 */
static int pid_array_load(pid_t *pidarray, int npids, struct cgroup *cgrp)
{
	int n = 0;
	struct cgroup_iter it;
	struct task_struct *tsk;
	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		if (unlikely(n == npids))
			break;
		pidarray[n++] = task_pid_vnr(tsk);
	}
	cgroup_iter_end(cgrp, &it);
	return n;
}

/**
 * cgroupstats_build - build and fill cgroupstats
 * @stats: cgroupstats to fill information into
 * @dentry: A dentry entry belonging to the cgroup for which stats have
 * been requested.
 *
 * Build and fill cgroupstats so that taskstats can export it to user
 * space.
 */
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry)
{
	int ret = -EINVAL;
	struct cgroup *cgrp;
	struct cgroup_iter it;
	struct task_struct *tsk;
	/*
	 * Validate dentry by checking the superblock operations
	 */
	if (dentry->d_sb->s_op != &cgroup_ops)
		 goto err;

	ret = 0;
	cgrp = dentry->d_fsdata;
	rcu_read_lock();

	cgroup_iter_start(cgrp, &it);
	while ((tsk = cgroup_iter_next(cgrp, &it))) {
		switch (tsk->state) {
		case TASK_RUNNING:
			stats->nr_running++;
			break;
		case TASK_INTERRUPTIBLE:
			stats->nr_sleeping++;
			break;
		case TASK_UNINTERRUPTIBLE:
			stats->nr_uninterruptible++;
			break;
		case TASK_STOPPED:
			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 = NULL;
		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 int cgroup_write_notify_on_release(struct cgroup *cgrp,
					  struct cftype *cft,
					  u64 val)
{
	clear_bit(CGRP_RELEASABLE, &cgrp->flags);
	if (val)
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
	else
		clear_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
	return 0;
}

/*
 * 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_u64 = cgroup_tasks_write,
		.release = cgroup_tasks_release,
		.private = FILE_TASKLIST,
	},

	{
		.name = "notify_on_release",
		.read_u64 = cgroup_read_notify_on_release,
		.write_u64 = cgroup_write_notify_on_release,
		.private = FILE_NOTIFY_ON_RELEASE,
	},
};

static struct cftype cft_release_agent = {
	.name = "release_agent",
	.read_seq_string = cgroup_release_agent_show,
	.write_string = cgroup_release_agent_write,
	.max_write_len = PATH_MAX,
	.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
 * @dentry: dentry of the new cgroup
 * @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);

	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;

	if (notify_on_release(parent))
		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);

	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 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. Notify subsystems
	 * that rmdir() request comes.
	 */
	cgroup_call_pre_destroy(cgrp);

	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);
	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 __init cgroup_init_subsys(struct cgroup_subsys *ss)
{
	struct cgroup_subsys_state *css;

	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 the init_css_set to contain a subsys
	 * pointer to this state - since the subsystem is
	 * newly registered, all tasks and hence the
	 * init_css_set is in the subsystem's top cgroup. */
	init_css_set.subsys[ss->subsys_id] = dummytop->subsys[ss->subsys_id];

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