path: root/fs/namespace.c

/*
 *  linux/fs/namespace.c
 *
 * (C) Copyright Al Viro 2000, 2001
 *	Released under GPL v2.
 *
 * Based on code from fs/super.c, copyright Linus Torvalds and others.
 * Heavily rewritten.
 */

#include <linux/config.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/quotaops.h>
#include <linux/acct.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/namespace.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>

extern int __init init_rootfs(void);

#define CL_EXPIRE 	0x01

#ifdef CONFIG_SYSFS
extern int __init sysfs_init(void);
#else
static inline int sysfs_init(void)
{
	return 0;
}
#endif

/* spinlock for vfsmount related operations, inplace of dcache_lock */
__cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);

static int event;

static struct list_head *mount_hashtable;
static int hash_mask __read_mostly, hash_bits __read_mostly;
static kmem_cache_t *mnt_cache;

static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
{
	unsigned long tmp = ((unsigned long)mnt / L1_CACHE_BYTES);
	tmp += ((unsigned long)dentry / L1_CACHE_BYTES);
	tmp = tmp + (tmp >> hash_bits);
	return tmp & hash_mask;
}

struct vfsmount *alloc_vfsmnt(const char *name)
{
	struct vfsmount *mnt = kmem_cache_alloc(mnt_cache, GFP_KERNEL);
	if (mnt) {
		memset(mnt, 0, sizeof(struct vfsmount));
		atomic_set(&mnt->mnt_count, 1);
		INIT_LIST_HEAD(&mnt->mnt_hash);
		INIT_LIST_HEAD(&mnt->mnt_child);
		INIT_LIST_HEAD(&mnt->mnt_mounts);
		INIT_LIST_HEAD(&mnt->mnt_list);
		INIT_LIST_HEAD(&mnt->mnt_expire);
		if (name) {
			int size = strlen(name) + 1;
			char *newname = kmalloc(size, GFP_KERNEL);
			if (newname) {
				memcpy(newname, name, size);
				mnt->mnt_devname = newname;
			}
		}
	}
	return mnt;
}

void free_vfsmnt(struct vfsmount *mnt)
{
	kfree(mnt->mnt_devname);
	kmem_cache_free(mnt_cache, mnt);
}

/*
 * Now, lookup_mnt increments the ref count before returning
 * the vfsmount struct.
 */
struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
{
	struct list_head *head = mount_hashtable + hash(mnt, dentry);
	struct list_head *tmp = head;
	struct vfsmount *p, *found = NULL;

	spin_lock(&vfsmount_lock);
	for (;;) {
		tmp = tmp->next;
		p = NULL;
		if (tmp == head)
			break;
		p = list_entry(tmp, struct vfsmount, mnt_hash);
		if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) {
			found = mntget(p);
			break;
		}
	}
	spin_unlock(&vfsmount_lock);
	return found;
}

static inline int check_mnt(struct vfsmount *mnt)
{
	return mnt->mnt_namespace == current->namespace;
}

static void touch_namespace(struct namespace *ns)
{
	if (ns) {
		ns->event = ++event;
		wake_up_interruptible(&ns->poll);
	}
}

static void __touch_namespace(struct namespace *ns)
{
	if (ns && ns->event != event) {
		ns->event = event;
		wake_up_interruptible(&ns->poll);
	}
}

static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd)
{
	old_nd->dentry = mnt->mnt_mountpoint;
	old_nd->mnt = mnt->mnt_parent;
	mnt->mnt_parent = mnt;
	mnt->mnt_mountpoint = mnt->mnt_root;
	list_del_init(&mnt->mnt_child);
	list_del_init(&mnt->mnt_hash);
	old_nd->dentry->d_mounted--;
}

static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd)
{
	mnt->mnt_parent = mntget(nd->mnt);
	mnt->mnt_mountpoint = dget(nd->dentry);
	list_add(&mnt->mnt_hash, mount_hashtable + hash(nd->mnt, nd->dentry));
	list_add_tail(&mnt->mnt_child, &nd->mnt->mnt_mounts);
	nd->dentry->d_mounted++;
}

static struct vfsmount *next_mnt(struct vfsmount *p, struct vfsmount *root)
{
	struct list_head *next = p->mnt_mounts.next;
	if (next == &p->mnt_mounts) {
		while (1) {
			if (p == root)
				return NULL;
			next = p->mnt_child.next;
			if (next != &p->mnt_parent->mnt_mounts)
				break;
			p = p->mnt_parent;
		}
	}
	return list_entry(next, struct vfsmount, mnt_child);
}

static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
					int flag)
{
	struct super_block *sb = old->mnt_sb;
	struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname);

	if (mnt) {
		mnt->mnt_flags = old->mnt_flags;
		atomic_inc(&sb->s_active);
		mnt->mnt_sb = sb;
		mnt->mnt_root = dget(root);
		mnt->mnt_mountpoint = mnt->mnt_root;
		mnt->mnt_parent = mnt;
		mnt->mnt_namespace = current->namespace;

		/* stick the duplicate mount on the same expiry list
		 * as the original if that was on one */
		if (flag & CL_EXPIRE) {
			spin_lock(&vfsmount_lock);
			if (!list_empty(&old->mnt_expire))
				list_add(&mnt->mnt_expire, &old->mnt_expire);
			spin_unlock(&vfsmount_lock);
		}
	}
	return mnt;
}

static inline void __mntput(struct vfsmount *mnt)
{
	struct super_block *sb = mnt->mnt_sb;
	dput(mnt->mnt_root);
	free_vfsmnt(mnt);
	deactivate_super(sb);
}

void mntput_no_expire(struct vfsmount *mnt)
{
repeat:
	if (atomic_dec_and_lock(&mnt->mnt_count, &vfsmount_lock)) {
		if (likely(!mnt->mnt_pinned)) {
			spin_unlock(&vfsmount_lock);
			__mntput(mnt);
			return;
		}
		atomic_add(mnt->mnt_pinned + 1, &mnt->mnt_count);
		mnt->mnt_pinned = 0;
		spin_unlock(&vfsmount_lock);
		acct_auto_close_mnt(mnt);
		security_sb_umount_close(mnt);
		goto repeat;
	}
}

EXPORT_SYMBOL(mntput_no_expire);

void mnt_pin(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	mnt->mnt_pinned++;
	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL(mnt_pin);

void mnt_unpin(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	if (mnt->mnt_pinned) {
		atomic_inc(&mnt->mnt_count);
		mnt->mnt_pinned--;
	}
	spin_unlock(&vfsmount_lock);
}

EXPORT_SYMBOL(mnt_unpin);

/* iterator */
static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct namespace *n = m->private;
	struct list_head *p;
	loff_t l = *pos;

	down_read(&n->sem);
	list_for_each(p, &n->list)
		if (!l--)
			return list_entry(p, struct vfsmount, mnt_list);
	return NULL;
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct namespace *n = m->private;
	struct list_head *p = ((struct vfsmount *)v)->mnt_list.next;
	(*pos)++;
	return p == &n->list ? NULL : list_entry(p, struct vfsmount, mnt_list);
}

static void m_stop(struct seq_file *m, void *v)
{
	struct namespace *n = m->private;
	up_read(&n->sem);
}

static inline void mangle(struct seq_file *m, const char *s)
{
	seq_escape(m, s, " \t\n\\");
}

static int show_vfsmnt(struct seq_file *m, void *v)
{
	struct vfsmount *mnt = v;
	int err = 0;
	static struct proc_fs_info {
		int flag;
		char *str;
	} fs_info[] = {
		{ MS_SYNCHRONOUS, ",sync" },
		{ MS_DIRSYNC, ",dirsync" },
		{ MS_MANDLOCK, ",mand" },
		{ MS_NOATIME, ",noatime" },
		{ MS_NODIRATIME, ",nodiratime" },
		{ 0, NULL }
	};
	static struct proc_fs_info mnt_info[] = {
		{ MNT_NOSUID, ",nosuid" },
		{ MNT_NODEV, ",nodev" },
		{ MNT_NOEXEC, ",noexec" },
		{ 0, NULL }
	};
	struct proc_fs_info *fs_infop;

	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
	seq_putc(m, ' ');
	seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
	seq_putc(m, ' ');
	mangle(m, mnt->mnt_sb->s_type->name);
	seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? " ro" : " rw");
	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_sb->s_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
	if (mnt->mnt_sb->s_op->show_options)
		err = mnt->mnt_sb->s_op->show_options(m, mnt);
	seq_puts(m, " 0 0\n");
	return err;
}

struct seq_operations mounts_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_vfsmnt
};

/**
 * may_umount_tree - check if a mount tree is busy
 * @mnt: roo