cgroup.c

Kernel code of linux kernel

 * 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);
}

/**
 * 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);
}

/*
 * 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 int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry);
static int cgroup_populate_dir(struct cgroup *cgrp);
static struct inode_operations cgroup_dir_inode_operations;
static struct file_operations proc_cgroupstats_operations;

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

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

	if (inode) {
		inode->i_mode = mode;
		inode->i_uid = current->fsuid;
		inode->i_gid = current->fsgid;
		inode->i_blocks = 0;
		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 void cgroup_call_pre_destroy(struct cgroup *cgrp)
{
	struct cgroup_subsys *ss;
	for_each_subsys(cgrp->root, ss)
		if (ss->pre_destroy && cgrp->subsys[ss->subsys_id])
			ss->pre_destroy(ss, cgrp);
	return;
}

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) {
			if (cgrp->subsys[ss->subsys_id])
				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);

		kfree(cgrp);
	}
	iput(inode);
}

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(&dcache_lock);
	node = dentry->d_subdirs.next;
	while (node != &dentry->d_subdirs) {
		struct dentry *d = list_entry(node, struct dentry, d_u.d_child);
		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);
			d = dget_locked(d);
			spin_unlock(&dcache_lock);
			d_delete(d);
			simple_unlink(dentry->d_inode, d);
			dput(d);
			spin_lock(&dcache_lock);
		}
		node = dentry->d_subdirs.next;
	}
	spin_unlock(&dcache_lock);
}

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

	spin_lock(&dcache_lock);
	list_del_init(&dentry->d_u.d_child);
	spin_unlock(&dcache_lock);
	remove_dir(dentry);
}

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;

	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;
		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 (!list_empty(&cgrp->children))
		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(cgrp->subsys[i]);
			BUG_ON(!dummytop->subsys[i]);
			BUG_ON(dummytop->subsys[i]->cgroup != dummytop);
			cgrp->subsys[i] = dummytop->subsys[i];
			cgrp->subsys[i]->cgroup = cgrp;
			list_add(&ss->sibling, &root->subsys_list);
			rcu_assign_pointer(ss->root, root);
			if (ss->bind)
				ss->bind(ss, cgrp);

		} else if (bit & removed_bits) {
			/* We're removing this subsystem */
			BUG_ON(cgrp->subsys[i] != dummytop->subsys[i]);
			BUG_ON(cgrp->subsys[i]->cgroup != cgrp);
			if (ss->bind)
				ss->bind(ss, dummytop);
			dummytop->subsys[i]->cgroup = dummytop;
			cgrp->subsys[i] = NULL;
			rcu_assign_pointer(subsys[i]->root, &rootnode);
			list_del(&ss->sibling);
		} else if (bit & final_bits) {
			/* Subsystem state should already exist */
			BUG_ON(!cgrp->subsys[i]);
		} else {
			/* Subsystem state shouldn't exist */
			BUG_ON(cgrp->subsys[i]);
		}
	}
	root->subsys_bits = root->actual_subsys_bits = final_bits;
	synchronize_rcu();

	return 0;
}

static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct cgroupfs_root *root = vfs->mnt_sb->s_fs_info;
	struct cgroup_subsys *ss;

	mutex_lock(&cgroup_mutex);
	for_each_subsys(root, ss)
		seq_printf(seq, ",%s", ss->name);
	if (test_bit(ROOT_NOPREFIX, &root->flags))
		seq_puts(seq, ",noprefix");
	if (strlen(root->release_agent_path))
		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
	mutex_unlock(&cgroup_mutex);
	return 0;
}

struct cgroup_sb_opts {
	unsigned long subsys_bits;
	unsigned long flags;
	char *release_agent;
};

/* Convert a hierarchy specifier into a bitmask of subsystems and
 * flags. */
static int parse_cgroupfs_options(char *data,
				     struct cgroup_sb_opts *opts)
{
	char *token, *o = data ?: "all";

	opts->subsys_bits = 0;
	opts->flags = 0;
	opts->release_agent = NULL;

	while ((token = strsep(&o, ",")) != NULL) {
		if (!*token)
			return -EINVAL;
		if (!strcmp(token, "all")) {
			/* Add all non-disabled subsystems */
			int i;
			opts->subsys_bits = 0;
			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
				struct cgroup_subsys *ss = subsys[i];
				if (!ss->disabled)
					opts->subsys_bits |= 1ul << i;
			}
		} else if (!strcmp(token, "noprefix")) {
			set_bit(ROOT_NOPREFIX, &opts->flags);
		} else if (!strncmp(token, "release_agent=", 14)) {
			/* Specifying two release agents is forbidden */
			if (opts->release_agent)
				return -EINVAL;
			opts->release_agent = kzalloc(PATH_MAX, GFP_KERNEL);
			if (!opts->release_agent)
				return -ENOMEM;
			strncpy(opts->release_agent, token + 14, PATH_MAX - 1);
			opts->release_agent[PATH_MAX - 1] = 0;
		} else {
			struct cgroup_subsys *ss;
			int i;
			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
				ss = subsys[i];
				if (!strcmp(token, ss->name)) {
					if (!ss->disabled)
						set_bit(i, &opts->subsys_bits);
					break;
				}
			}
			if (i == CGROUP_SUBSYS_COUNT)
				return -ENOENT;
		}
	}

	/* We can't have an empty hierarchy */
	if (!opts->subsys_bits)
		return -EINVAL;

	return 0;
}

static int cgroup_remount(struct super_block *sb, int *flags, char *data)
{
	int ret = 0;
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cgrp = &root->top_cgroup;
	struct cgroup_sb_opts opts;

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

	/* See what subsystems are wanted */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret)
		goto out_unlock;

	/* Don't allow flags to change at remount */
	if (opts.flags != root->flags) {
		ret = -EINVAL;
		goto out_unlock;
	}

	ret = rebind_subsystems(root, opts.subsys_bits);

	/* (re)populate subsystem files */
	if (!ret)
		cgroup_populate_dir(cgrp);

	if (opts.release_agent)
		strcpy(root->release_agent_path, opts.release_agent);
 out_unlock:
	if (opts.release_agent)
		kfree(opts.release_agent);
	mutex_unlock(&cgroup_mutex);
	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
	return ret;
}

static struct super_operations cgroup_ops = {
	.statfs = simple_statfs,
	.drop_inode = generic_delete_inode,
	.show_options = cgroup_show_options,
	.remount_fs = cgroup_remount,
};

static void init_cgroup_root(struct cgroupfs_root *root)
{
	struct cgroup *cgrp = &root->top_cgroup;
	INIT_LIST_HEAD(&root->subsys_list);
	INIT_LIST_HEAD(&root->root_list);
	root->number_of_cgroups = 1;
	cgrp->root = root;
	cgrp->top_cgroup = cgrp;
	INIT_LIST_HEAD(&cgrp->sibling);
	INIT_LIST_HEAD(&cgrp->children);
	INIT_LIST_HEAD(&cgrp->css_sets);
	INIT_LIST_HEAD(&cgrp->release_list);
}

static int cgroup_test_super(struct super_block *sb, void *data)
{
	struct cgroupfs_root *new = data;
	struct cgroupfs_root *root = sb->s_fs_info;

	/* First check subsystems */
	if (new->subsys_bits != root->subsys_bits)
	    return 0;

	/* Next check flags */
	if (new->flags != root->flags)
		return 0;

	return 1;
}

static int cgroup_set_super(struct super_block *sb, void *data)
{
	int ret;
	struct cgroupfs_root *root = data;

	ret = set_anon_super(sb, NULL);
	if (ret)
		return ret;

	sb->s_fs_info = root;
	root->sb = sb;

	sb->s_blocksize = PAGE_CACHE_SIZE;
	sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
	sb->s_magic = CGROUP_SUPER_MAGIC;
	sb->s_op = &cgroup_ops;

	return 0;
}

static int cgroup_get_rootdir(struct super_block *sb)
{
	struct inode *inode =
		cgroup_new_inode(S_IFDIR | S_IRUGO | S_IXUGO | S_IWUSR, sb);
	struct dentry *dentry;

	if (!inode)
		return -ENOMEM;

	inode->i_fop = &simple_dir_operations;
	inode->i_op = &cgroup_dir_inode_operations;
	/* directories start off with i_nlink == 2 (for "." entry) */
	inc_nlink(inode);
	dentry = d_alloc_root(inode);
	if (!dentry) {
		iput(inode);
		return -ENOMEM;
	}
	sb->s_root = dentry;
	return 0;
}

static int cgroup_get_sb(struct file_system_type *fs_type,
			 int flags, const char *unused_dev_name,
			 void *data, struct vfsmount *mnt)
{
	struct cgroup_sb_opts opts;
	int ret = 0;
	struct super_block *sb;
	struct cgroupfs_root *root;
	struct list_head tmp_cg_links;

	/* First find the desired set of subsystems */
	ret = parse_cgroupfs_options(data, &opts);
	if (ret) {
		if (opts.release_agent)
			kfree(opts.release_agent);
		return ret;
	}

	root = kzalloc(sizeof(*root), GFP_KERNEL);
	if (!root) {
		if (opts.release_agent)
			kfree(opts.release_agent);
		return -ENOMEM;
	}

	init_cgroup_root(root);
	root->subsys_bits = opts.subsys_bits;
	root->flags = opts.flags;
	if (opts.release_agent) {
		strcpy(root->release_agent_path, opts.release_agent);
		kfree(opts.release_agent);
	}

	sb = sget(fs_type, cgroup_test_super, cgroup_set_super, root);

	if (IS_ERR(sb)) {
		kfree(root);
		return PTR_ERR(sb);
	}

	if (sb->s_fs_info != root) {
		/* Reusing an existing superblock */
		BUG_ON(sb->s_root == NULL);
		kfree(root);
		root = NULL;
	} else {
		/* New superblock */
		struct cgroup *cgrp = &root->top_cgroup;