cgroup.c

Kernel code of linux kernel

		struct inode *inode;
		int i;

		BUG_ON(sb->s_root != NULL);

		ret = cgroup_get_rootdir(sb);
		if (ret)
			goto drop_new_super;
		inode = sb->s_root->d_inode;

		mutex_lock(&inode->i_mutex);
		mutex_lock(&cgroup_mutex);

		/*
		 * We're accessing css_set_count without locking
		 * css_set_lock here, but that's OK - it can only be
		 * increased by someone holding cgroup_lock, and
		 * that's us. The worst that can happen is that we
		 * have some link structures left over
		 */
		ret = allocate_cg_links(css_set_count, &tmp_cg_links);
		if (ret) {
			mutex_unlock(&cgroup_mutex);
			mutex_unlock(&inode->i_mutex);
			goto drop_new_super;
		}

		ret = rebind_subsystems(root, root->subsys_bits);
		if (ret == -EBUSY) {
			mutex_unlock(&cgroup_mutex);
			mutex_unlock(&inode->i_mutex);
			goto drop_new_super;
		}

		/* EBUSY should be the only error here */
		BUG_ON(ret);

		list_add(&root->root_list, &roots);
		root_count++;

		sb->s_root->d_fsdata = &root->top_cgroup;
		root->top_cgroup.dentry = sb->s_root;

		/* Link the top cgroup in this hierarchy into all
		 * the css_set objects */
		write_lock(&css_set_lock);
		for (i = 0; i < CSS_SET_TABLE_SIZE; i++) {
			struct hlist_head *hhead = &css_set_table[i];
			struct hlist_node *node;
			struct css_set *cg;

			hlist_for_each_entry(cg, node, hhead, hlist) {
				struct cg_cgroup_link *link;

				BUG_ON(list_empty(&tmp_cg_links));
				link = list_entry(tmp_cg_links.next,
						  struct cg_cgroup_link,
						  cgrp_link_list);
				list_del(&link->cgrp_link_list);
				link->cg = cg;
				list_add(&link->cgrp_link_list,
					 &root->top_cgroup.css_sets);
				list_add(&link->cg_link_list, &cg->cg_links);
			}
		}
		write_unlock(&css_set_lock);

		free_cg_links(&tmp_cg_links);

		BUG_ON(!list_empty(&cgrp->sibling));
		BUG_ON(!list_empty(&cgrp->children));
		BUG_ON(root->number_of_cgroups != 1);

		cgroup_populate_dir(cgrp);
		mutex_unlock(&inode->i_mutex);
		mutex_unlock(&cgroup_mutex);
	}

	return simple_set_mnt(mnt, sb);

 drop_new_super:
	up_write(&sb->s_umount);
	deactivate_super(sb);
	free_cg_links(&tmp_cg_links);
	return ret;
}

static void cgroup_kill_sb(struct super_block *sb) {
	struct cgroupfs_root *root = sb->s_fs_info;
	struct cgroup *cgrp = &root->top_cgroup;
	int ret;
	struct cg_cgroup_link *link;
	struct cg_cgroup_link *saved_link;

	BUG_ON(!root);

	BUG_ON(root->number_of_cgroups != 1);
	BUG_ON(!list_empty(&cgrp->children));
	BUG_ON(!list_empty(&cgrp->sibling));

	mutex_lock(&cgroup_mutex);

	/* Rebind all subsystems back to the default hierarchy */
	ret = rebind_subsystems(root, 0);
	/* Shouldn't be able to fail ... */
	BUG_ON(ret);

	/*
	 * Release all the links from css_sets to this hierarchy's
	 * root cgroup
	 */
	write_lock(&css_set_lock);

	list_for_each_entry_safe(link, saved_link, &cgrp->css_sets,
				 cgrp_link_list) {
		list_del(&link->cg_link_list);
		list_del(&link->cgrp_link_list);
		kfree(link);
	}
	write_unlock(&css_set_lock);

	if (!list_empty(&root->root_list)) {
		list_del(&root->root_list);
		root_count--;
	}
	mutex_unlock(&cgroup_mutex);

	kfree(root);
	kill_litter_super(sb);
}

static struct file_system_type cgroup_fs_type = {
	.name = "cgroup",
	.get_sb = cgroup_get_sb,
	.kill_sb = cgroup_kill_sb,
};

static inline struct cgroup *__d_cgrp(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

static inline struct cftype *__d_cft(struct dentry *dentry)
{
	return dentry->d_fsdata;
}

/**
 * cgroup_path - generate the path of a cgroup
 * @cgrp: the cgroup in question
 * @buf: the buffer to write the path into
 * @buflen: the length of the buffer
 *
 * Called with cgroup_mutex held. Writes path of cgroup into buf.
 * Returns 0 on success, -errno on error.
 */
int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen)
{
	char *start;

	if (cgrp == dummytop) {
		/*
		 * Inactive subsystems have no dentry for their root
		 * cgroup
		 */
		strcpy(buf, "/");
		return 0;
	}

	start = buf + buflen;

	*--start = '\0';
	for (;;) {
		int len = cgrp->dentry->d_name.len;
		if ((start -= len) < buf)
			return -ENAMETOOLONG;
		memcpy(start, cgrp->dentry->d_name.name, len);
		cgrp = cgrp->parent;
		if (!cgrp)
			break;
		if (!cgrp->parent)
			continue;
		if (--start < buf)
			return -ENAMETOOLONG;
		*start = '/';
	}
	memmove(buf, start, buf + buflen - start);
	return 0;
}

/*
 * Return the first subsystem attached to a cgroup's hierarchy, and
 * its subsystem id.
 */

static void get_first_subsys(const struct cgroup *cgrp,
			struct cgroup_subsys_state **css, int *subsys_id)
{
	const struct cgroupfs_root *root = cgrp->root;
	const struct cgroup_subsys *test_ss;
	BUG_ON(list_empty(&root->subsys_list));
	test_ss = list_entry(root->subsys_list.next,
			     struct cgroup_subsys, sibling);
	if (css) {
		*css = cgrp->subsys[test_ss->subsys_id];
		BUG_ON(!*css);
	}
	if (subsys_id)
		*subsys_id = test_ss->subsys_id;
}

/**
 * cgroup_attach_task - attach task 'tsk' to cgroup 'cgrp'
 * @cgrp: the cgroup the task is attaching to
 * @tsk: the task to be attached
 *
 * Call holding cgroup_mutex. May take task_lock of
 * the task 'tsk' during call.
 */
int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
{
	int retval = 0;
	struct cgroup_subsys *ss;
	struct cgroup *oldcgrp;
	struct css_set *cg = tsk->cgroups;
	struct css_set *newcg;
	struct cgroupfs_root *root = cgrp->root;
	int subsys_id;

	get_first_subsys(cgrp, NULL, &subsys_id);

	/* Nothing to do if the task is already in that cgroup */
	oldcgrp = task_cgroup(tsk, subsys_id);
	if (cgrp == oldcgrp)
		return 0;

	for_each_subsys(root, ss) {
		if (ss->can_attach) {
			retval = ss->can_attach(ss, cgrp, tsk);
			if (retval)
				return retval;
		}
	}

	/*
	 * Locate or allocate a new css_set for this task,
	 * based on its final set of cgroups
	 */
	newcg = find_css_set(cg, cgrp);
	if (!newcg)
		return -ENOMEM;

	task_lock(tsk);
	if (tsk->flags & PF_EXITING) {
		task_unlock(tsk);
		put_css_set(newcg);
		return -ESRCH;
	}
	rcu_assign_pointer(tsk->cgroups, newcg);
	task_unlock(tsk);

	/* Update the css_set linked lists if we're using them */
	write_lock(&css_set_lock);
	if (!list_empty(&tsk->cg_list)) {
		list_del(&tsk->cg_list);
		list_add(&tsk->cg_list, &newcg->tasks);
	}
	write_unlock(&css_set_lock);

	for_each_subsys(root, ss) {
		if (ss->attach)
			ss->attach(ss, cgrp, oldcgrp, tsk);
	}
	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
	synchronize_rcu();
	put_css_set(cg);
	return 0;
}

/*
 * Attach task with pid 'pid' to cgroup 'cgrp'. Call with cgroup_mutex
 * held. May take task_lock of task
 */
static int attach_task_by_pid(struct cgroup *cgrp, u64 pid)
{
	struct task_struct *tsk;
	int ret;

	if (pid) {
		rcu_read_lock();
		tsk = find_task_by_vpid(pid);
		if (!tsk || tsk->flags & PF_EXITING) {
			rcu_read_unlock();
			return -ESRCH;
		}
		get_task_struct(tsk);
		rcu_read_unlock();

		if ((current->euid) && (current->euid != tsk->uid)
		    && (current->euid != tsk->suid)) {
			put_task_struct(tsk);
			return -EACCES;
		}
	} else {
		tsk = current;
		get_task_struct(tsk);
	}

	ret = cgroup_attach_task(cgrp, tsk);
	put_task_struct(tsk);
	return ret;
}

static int cgroup_tasks_write(struct cgroup *cgrp, struct cftype *cft, u64 pid)
{
	int ret;
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	ret = attach_task_by_pid(cgrp, pid);
	cgroup_unlock();
	return ret;
}

/* The various types of files and directories in a cgroup file system */
enum cgroup_filetype {
	FILE_ROOT,
	FILE_DIR,
	FILE_TASKLIST,
	FILE_NOTIFY_ON_RELEASE,
	FILE_RELEASE_AGENT,
};

/**
 * cgroup_lock_live_group - take cgroup_mutex and check that cgrp is alive.
 * @cgrp: the cgroup to be checked for liveness
 *
 * On success, returns true; the lock should be later released with
 * cgroup_unlock(). On failure returns false with no lock held.
 */
bool cgroup_lock_live_group(struct cgroup *cgrp)
{
	mutex_lock(&cgroup_mutex);
	if (cgroup_is_removed(cgrp)) {
		mutex_unlock(&cgroup_mutex);
		return false;
	}
	return true;
}

static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
				      const char *buffer)
{
	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	strcpy(cgrp->root->release_agent_path, buffer);
	cgroup_unlock();
	return 0;
}

static int cgroup_release_agent_show(struct cgroup *cgrp, struct cftype *cft,
				     struct seq_file *seq)
{
	if (!cgroup_lock_live_group(cgrp))
		return -ENODEV;
	seq_puts(seq, cgrp->root->release_agent_path);
	seq_putc(seq, '\n');
	cgroup_unlock();
	return 0;
}

/* A buffer size big enough for numbers or short strings */
#define CGROUP_LOCAL_BUFFER_SIZE 64

static ssize_t cgroup_write_X64(struct cgroup *cgrp, struct cftype *cft,
				struct file *file,
				const char __user *userbuf,
				size_t nbytes, loff_t *unused_ppos)
{
	char buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	char *end;

	if (!nbytes)
		return -EINVAL;
	if (nbytes >= sizeof(buffer))
		return -E2BIG;
	if (copy_from_user(buffer, userbuf, nbytes))
		return -EFAULT;

	buffer[nbytes] = 0;     /* nul-terminate */
	strstrip(buffer);
	if (cft->write_u64) {
		u64 val = simple_strtoull(buffer, &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_u64(cgrp, cft, val);
	} else {
		s64 val = simple_strtoll(buffer, &end, 0);
		if (*end)
			return -EINVAL;
		retval = cft->write_s64(cgrp, cft, val);
	}
	if (!retval)
		retval = nbytes;
	return retval;
}

static ssize_t cgroup_write_string(struct cgroup *cgrp, struct cftype *cft,
				   struct file *file,
				   const char __user *userbuf,
				   size_t nbytes, loff_t *unused_ppos)
{
	char local_buffer[CGROUP_LOCAL_BUFFER_SIZE];
	int retval = 0;
	size_t max_bytes = cft->max_write_len;
	char *buffer = local_buffer;

	if (!max_bytes)
		max_bytes = sizeof(local_buffer) - 1;
	if (nbytes >= max_bytes)
		return -E2BIG;
	/* Allocate a dynamic buffer if we need one */
	if (nbytes >= sizeof(local_buffer)) {
		buffer = kmalloc(nbytes + 1, GFP_KERNEL);
		if (buffer == NULL)
			return -ENOMEM;
	}
	if (nbytes && copy_from_user(buffer, userbuf, nbytes)) {
		retval = -EFAULT;
		goto out;
	}

	buffer[nbytes] = 0;     /* nul-terminate */
	strstrip(buffer);
	retval = cft->write_string(cgrp, cft, buffer);
	if (!retval)
		retval = nbytes;
out:
	if (buffer != local_buffer)
		kfree(buffer);
	return retval;
}

static ssize_t cgroup_file_write(struct file *file, const char __user *buf,
						size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (!cft || cgroup_is_removed(cgrp))
		return -ENODEV;
	if (cft->write)
		return cft->write(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_u64 || cft->write_s64)
		return cgroup_write_X64(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->write_string)
		return cgroup_write_string(cgrp, cft, file, buf, nbytes, ppos);
	if (cft->trigger) {
		int ret = cft->trigger(cgrp, (unsigned int)cft->private);
		return ret ? ret : nbytes;
	}
	return -EINVAL;
}

static ssize_t cgroup_read_u64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	u64 val = cft->read_u64(cgrp, cft);
	int len = sprintf(tmp, "%llu\n", (unsigned long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_read_s64(struct cgroup *cgrp, struct cftype *cft,
			       struct file *file,
			       char __user *buf, size_t nbytes,
			       loff_t *ppos)
{
	char tmp[CGROUP_LOCAL_BUFFER_SIZE];
	s64 val = cft->read_s64(cgrp, cft);
	int len = sprintf(tmp, "%lld\n", (long long) val);

	return simple_read_from_buffer(buf, nbytes, ppos, tmp, len);
}

static ssize_t cgroup_file_read(struct file *file, char __user *buf,
				   size_t nbytes, loff_t *ppos)
{
	struct cftype *cft = __d_cft(file->f_dentry);
	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);

	if (!cft || cgroup_is_removed(cgrp))