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/syscalls.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/acct.h>
#include <linux/capability.h>
#include <linux/cpumask.h>
#include <linux/module.h>
#include <linux/sysfs.h>
#include <linux/seq_file.h>
#include <linux/mnt_namespace.h>
#include <linux/namei.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/ramfs.h>
#include <linux/log2.h>
#include <linux/idr.h>
#include <linux/fs_struct.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include "pnode.h"
#include "internal.h"

#define HASH_SHIFT ilog2(PAGE_SIZE / sizeof(struct list_head))
#define HASH_SIZE (1UL << HASH_SHIFT)

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

static int event;
static DEFINE_IDA(mnt_id_ida);
static DEFINE_IDA(mnt_group_ida);

static struct list_head *mount_hashtable __read_mostly;
static struct kmem_cache *mnt_cache __read_mostly;
static struct rw_semaphore namespace_sem;

/* /sys/fs */
struct kobject *fs_kobj;
EXPORT_SYMBOL_GPL(fs_kobj);

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_SHIFT);
	return tmp & (HASH_SIZE - 1);
}

#define MNT_WRITER_UNDERFLOW_LIMIT -(1<<16)

/* allocation is serialized by namespace_sem */
static int mnt_alloc_id(struct vfsmount *mnt)
{
	int res;

retry:
	ida_pre_get(&mnt_id_ida, GFP_KERNEL);
	spin_lock(&vfsmount_lock);
	res = ida_get_new(&mnt_id_ida, &mnt->mnt_id);
	spin_unlock(&vfsmount_lock);
	if (res == -EAGAIN)
		goto retry;

	return res;
}

static void mnt_free_id(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	ida_remove(&mnt_id_ida, mnt->mnt_id);
	spin_unlock(&vfsmount_lock);
}

/*
 * Allocate a new peer group ID
 *
 * mnt_group_ida is protected by namespace_sem
 */
static int mnt_alloc_group_id(struct vfsmount *mnt)
{
	if (!ida_pre_get(&mnt_group_ida, GFP_KERNEL))
		return -ENOMEM;

	return ida_get_new_above(&mnt_group_ida, 1, &mnt->mnt_group_id);
}

/*
 * Release a peer group ID
 */
void mnt_release_group_id(struct vfsmount *mnt)
{
	ida_remove(&mnt_group_ida, mnt->mnt_group_id);
	mnt->mnt_group_id = 0;
}

struct vfsmount *alloc_vfsmnt(const char *name)
{
	struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
	if (mnt) {
		int err;

		err = mnt_alloc_id(mnt);
		if (err)
			goto out_free_cache;

		if (name) {
			mnt->mnt_devname = kstrdup(name, GFP_KERNEL);
			if (!mnt->mnt_devname)
				goto out_free_id;
		}

		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);
		INIT_LIST_HEAD(&mnt->mnt_share);
		INIT_LIST_HEAD(&mnt->mnt_slave_list);
		INIT_LIST_HEAD(&mnt->mnt_slave);
#ifdef CONFIG_SMP
		mnt->mnt_writers = alloc_percpu(int);
		if (!mnt->mnt_writers)
			goto out_free_devname;
#else
		mnt->mnt_writers = 0;
#endif
	}
	return mnt;

#ifdef CONFIG_SMP
out_free_devname:
	kfree(mnt->mnt_devname);
#endif
out_free_id:
	mnt_free_id(mnt);
out_free_cache:
	kmem_cache_free(mnt_cache, mnt);
	return NULL;
}

/*
 * Most r/o checks on a fs are for operations that take
 * discrete amounts of time, like a write() or unlink().
 * We must keep track of when those operations start
 * (for permission checks) and when they end, so that
 * we can determine when writes are able to occur to
 * a filesystem.
 */
/*
 * __mnt_is_readonly: check whether a mount is read-only
 * @mnt: the mount to check for its write status
 *
 * This shouldn't be used directly ouside of the VFS.
 * It does not guarantee that the filesystem will stay
 * r/w, just that it is right *now*.  This can not and
 * should not be used in place of IS_RDONLY(inode).
 * mnt_want/drop_write() will _keep_ the filesystem
 * r/w.
 */
int __mnt_is_readonly(struct vfsmount *mnt)
{
	if (mnt->mnt_flags & MNT_READONLY)
		return 1;
	if (mnt->mnt_sb->s_flags & MS_RDONLY)
		return 1;
	return 0;
}
EXPORT_SYMBOL_GPL(__mnt_is_readonly);

static inline void inc_mnt_writers(struct vfsmount *mnt)
{
#ifdef CONFIG_SMP
	(*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))++;
#else
	mnt->mnt_writers++;
#endif
}

static inline void dec_mnt_writers(struct vfsmount *mnt)
{
#ifdef CONFIG_SMP
	(*per_cpu_ptr(mnt->mnt_writers, smp_processor_id()))--;
#else
	mnt->mnt_writers--;
#endif
}

static unsigned int count_mnt_writers(struct vfsmount *mnt)
{
#ifdef CONFIG_SMP
	unsigned int count = 0;
	int cpu;

	for_each_possible_cpu(cpu) {
		count += *per_cpu_ptr(mnt->mnt_writers, cpu);
	}

	return count;
#else
	return mnt->mnt_writers;
#endif
}

/*
 * Most r/o checks on a fs are for operations that take
 * discrete amounts of time, like a write() or unlink().
 * We must keep track of when those operations start
 * (for permission checks) and when they end, so that
 * we can determine when writes are able to occur to
 * a filesystem.
 */
/**
 * mnt_want_write - get write access to a mount
 * @mnt: the mount on which to take a write
 *
 * This tells the low-level filesystem that a write is
 * about to be performed to it, and makes sure that
 * writes are allowed before returning success.  When
 * the write operation is finished, mnt_drop_write()
 * must be called.  This is effectively a refcount.
 */
int mnt_want_write(struct vfsmount *mnt)
{
	int ret = 0;

	preempt_disable();
	inc_mnt_writers(mnt);
	/*
	 * The store to inc_mnt_writers must be visible before we pass
	 * MNT_WRITE_HOLD loop below, so that the slowpath can see our
	 * incremented count after it has set MNT_WRITE_HOLD.
	 */
	smp_mb();
	while (mnt->mnt_flags & MNT_WRITE_HOLD)
		cpu_relax();
	/*
	 * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
	 * be set to match its requirements. So we must not load that until
	 * MNT_WRITE_HOLD is cleared.
	 */
	smp_rmb();
	if (__mnt_is_readonly(mnt)) {
		dec_mnt_writers(mnt);
		ret = -EROFS;
		goto out;
	}
out:
	preempt_enable();
	return ret;
}
EXPORT_SYMBOL_GPL(mnt_want_write);

/**
 * mnt_drop_write - give up write access to a mount
 * @mnt: the mount on which to give up write access
 *
 * Tells the low-level filesystem that we are done
 * performing writes to it.  Must be matched with
 * mnt_want_write() call above.
 */
void mnt_drop_write(struct vfsmount *mnt)
{
	preempt_disable();
	dec_mnt_writers(mnt);
	preempt_enable();
}
EXPORT_SYMBOL_GPL(mnt_drop_write);

static int mnt_make_readonly(struct vfsmount *mnt)
{
	int ret = 0;

	spin_lock(&vfsmount_lock);
	mnt->mnt_flags |= MNT_WRITE_HOLD;
	/*
	 * After storing MNT_WRITE_HOLD, we'll read the counters. This store
	 * should be visible before we do.
	 */
	smp_mb();

	/*
	 * With writers on hold, if this value is zero, then there are
	 * definitely no active writers (although held writers may subsequently
	 * increment the count, they'll have to wait, and decrement it after
	 * seeing MNT_READONLY).
	 *
	 * It is OK to have counter incremented on one CPU and decremented on
	 * another: the sum will add up correctly. The danger would be when we
	 * sum up each counter, if we read a counter before it is incremented,
	 * but then read another CPU's count which it has been subsequently
	 * decremented from -- we would see more decrements than we should.
	 * MNT_WRITE_HOLD protects against this scenario, because
	 * mnt_want_write first increments count, then smp_mb, then spins on
	 * MNT_WRITE_HOLD, so it can't be decremented by another CPU while
	 * we're counting up here.
	 */
	if (count_mnt_writers(mnt) > 0)
		ret = -EBUSY;
	else
		mnt->mnt_flags |= MNT_READONLY;
	/*
	 * MNT_READONLY must become visible before ~MNT_WRITE_HOLD, so writers
	 * that become unheld will see MNT_READONLY.
	 */
	smp_wmb();
	mnt->mnt_flags &= ~MNT_WRITE_HOLD;
	spin_unlock(&vfsmount_lock);
	return ret;
}

static void __mnt_unmake_readonly(struct vfsmount *mnt)
{
	spin_lock(&vfsmount_lock);
	mnt->mnt_flags &= ~MNT_READONLY;
	spin_unlock(&vfsmount_lock);
}

void simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
{
	mnt->mnt_sb = sb;
	mnt->mnt_root = dget(sb->s_root);
}

EXPORT_SYMBOL(simple_set_mnt);

void free_vfsmnt(struct vfsmount *mnt)
{
	kfree(mnt->mnt_devname);
	mnt_free_id(mnt);
#ifdef CONFIG_SMP
	free_percpu(mnt->mnt_writers);
#endif
	kmem_cache_free(mnt_cache, mnt);
}

/*
 * find the first or last mount at @dentry on vfsmount @mnt depending on
 * @dir. If @dir is set return the first mount else return the last mount.
 */
struct vfsmount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
			      int dir)
{
	struct list_head *head = mount_hashtable + hash(mnt, dentry);
	struct list_head *tmp = head;
	struct vfsmount *p, *found = NULL;

	for (;;) {
		tmp = dir ? tmp->next : tmp->prev;
		p = NULL;
		if (tmp == head)
			break;
		p = list_entry(tmp, struct vfsmount, mnt_hash);
		if (p->mnt_parent == mnt && p->mnt_mountpoint == dentry) {
			found = p;
			break;
		}
	}
	return found;
}

/*
 * lookup_mnt increments the ref count before returning
 * the vfsmount struct.
 */
struct vfsmount *lookup_mnt(struct path *path)
{
	struct vfsmount *child_mnt;
	spin_lock(&vfsmount_lock);
	if ((child_mnt = __lookup_mnt(path->mnt, path->dentry, 1)))
		mntget(child_mnt);
	spin_unlock(&vfsmount_lock);
	return child_mnt;
}

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

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

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

static void detach_mnt(struct vfsmount *mnt, struct path *old_path)
{
	old_path->dentry = mnt->mnt_mountpoint;
	old_path->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_path->dentry->d_mounted--;
}

void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
			struct vfsmount *child_mnt)
{
	child_mnt->mnt_parent = mntget(mnt);
	child_mnt->mnt_mountpoint = dget(dentry);
	dentry->d_mounted++;
}

static void attach_mnt(struct vfsmount *mnt, struct path *path)
{
	mnt_set_mountpoint(path->mnt, path->dentry, mnt);
	list_add_tail(&mnt->mnt_hash, mount_hashtable +
			hash(path->mnt, path->dentry));
	list_add_tail(&mnt->mnt_child, &path->mnt->mnt_mounts);
}

/*
 * the caller must hold vfsmount_lock
 */
static void commit_tree(struct vfsmount *mnt)
{
	struct vfsmount *parent = mnt->mnt_parent;
	struct vfsmount *m;
	LIST_HEAD(head);
	struct mnt_namespace *n = parent->mnt_ns;

	BUG_ON(parent == mnt);

	list_add_tail(&head, &mnt->mnt_list);
	list_for_each_entry(m, &head, mnt_list)
		m->mnt_ns = n;
	list_splice(&head, n->list.prev);

	list_add_tail(&mnt->mnt_hash, mount_hashtable +
				hash(parent, mnt->mnt_mountpoint));
	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
	touch_mnt_namespace(n);
}

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 *skip_mnt_tree(struct vfsmount *p)
{
	struct list_head *prev = p->mnt_mounts.prev;
	while (prev != &p->mnt_mounts) {
		p = list_entry(prev, struct vfsmount, mnt_child);
		prev = p->mnt_mounts.prev;
	}
	return p;
}

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) {
		if (flag & (CL_SLAVE | CL_PRIVATE))
			mnt->mnt_group_id = 0; /* not a peer of original */
		else
			mnt->mnt_group_id = old->mnt_group_id;

		if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
			int err = mnt_alloc_group_id(mnt);
			if (err)
				goto out_free;
		}

		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;

		if (flag & CL_SLAVE) {
			list_add(&mnt->mnt_slave, &old->mnt_slave_list);
			mnt->mnt_master = old;
			CLEAR_MNT_SHARED(mnt);
		} else if (!(flag & CL_PRIVATE)) {
			if ((flag & CL_PROPAGATION) || IS_MNT_SHARED(old))
				list_add(&mnt->mnt_share, &old->mnt_share);
			if (IS_MNT_SLAVE(old))
				list_add(&mnt->mnt_slave, &old->mnt_slave);
			mnt->mnt_master = old->mnt_master;
		}
		if (flag & CL_MAKE_SHARED)
			set_mnt_shared(mnt);

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

 out_free:
	free_vfsmnt(mnt);
	return NULL;
}

static inline void __mntput(struct vfsmount *mnt)
{
	struct super_block *sb = mnt->mnt_sb;
	/*
	 * This probably indicates that somebody messed
	 * up a mnt_want/drop_write() pair.  If this
	 * happens, the filesystem was probably unable
	 * to make r/w->r/o transitions.
	 */
	/*
	 * atomic_dec_and_lock() used to deal with ->mnt_count decrements
	 * provides barriers, so count_mnt_writers() below is safe.  AV
	 */
	WARN_ON(count_mnt_writers(mnt));
	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);

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

/*
 * Simple .show_options callback for filesystems which don't want to
 * implement more complex mount option showing.
 *
 * See also save_mount_options().
 */
int generic_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	const char *options;

	rcu_read_lock();
	options = rcu_dereference(mnt->mnt_sb->s_options);

	if (options != NULL && options[0]) {
		seq_putc(m, ',');
		mangle(m, options);
	}
	rcu_read_unlock();

	return 0;
}
EXPORT_SYMBOL(generic_show_options);

/*
 * If filesystem uses generic_show_options(), this function should be
 * called from the fill_super() callback.
 *
 * The .remount_fs callback usually needs to be handled in a special
 * way, to make sure, that previous options are not overwritten if the
 * remount fails.
 *
 * Also note, that if the filesystem's .remount_fs function doesn't
 * reset all options to their default value, but changes only newly
 * given options, then the displayed options will not reflect reality
 * any more.
 */
void save_mount_options(struct super_block *sb, char *options)
{
	BUG_ON(sb->s_options);
	rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL));
}
EXPORT_SYMBOL(save_mount_options);

void replace_mount_options(struct super_block *sb, char *options)
{
	char *old = sb->s_options;
	rcu_assign_pointer(sb->s_options, options);
	if (old) {
		synchronize_rcu();
		kfree(old);
	}
}
EXPORT_SYMBOL(replace_mount_options);

#ifdef CONFIG_PROC_FS
/* iterator */
static void *m_start(struct seq_file *m, loff_t *pos)
{
	struct proc_mounts *p = m->private;

	down_read(&namespace_sem);
	return seq_list_start(&p->ns->list, *pos);
}

static void *m_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct proc_mounts *p = m->private;

	return seq_list_next(v, &p->ns->list, pos);
}

static void m_stop(struct seq_file *m, void *v)
{
	up_read(&namespace_sem);
}

struct proc_fs_info {
	int flag;
	const char *str;
};

static int show_sb_opts(struct seq_file *m, struct super_block *sb)
{
	static const struct proc_fs_info fs_info[] = {
		{ MS_SYNCHRONOUS, ",sync" },
		{ MS_DIRSYNC, ",dirsync" },
		{ MS_MANDLOCK, ",mand" },
		{ 0, NULL }
	};
	const struct proc_fs_info *fs_infop;

	for (fs_infop = fs_info; fs_infop->flag; fs_infop++) {
		if (sb->s_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}

	return security_sb_show_options(m, sb);
}

static void show_mnt_opts(struct seq_file *m, struct vfsmount *mnt)
{
	static const struct proc_fs_info mnt_info[] = {
		{ MNT_NOSUID, ",nosuid" },
		{ MNT_NODEV, ",nodev" },
		{ MNT_NOEXEC, ",noexec" },
		{ MNT_NOATIME, ",noatime" },
		{ MNT_NODIRATIME, ",nodiratime" },
		{ MNT_RELATIME, ",relatime" },
		{ MNT_STRICTATIME, ",strictatime" },
		{ 0, NULL }
	};
	const struct proc_fs_info *fs_infop;

	for (fs_infop = mnt_info; fs_infop->flag; fs_infop++) {
		if (mnt->mnt_flags & fs_infop->flag)
			seq_puts(m, fs_infop->str);
	}
}

static void show_type(struct seq_file *m, struct super_block *sb)
{
	mangle(m, sb->s_type->name);
	if (sb->s_subtype && sb->s_subtype[0]) {
		seq_putc(m, '.');
		mangle(m, sb->s_subtype);
	}
}

static int show_vfsmnt(struct seq_file *m, void *v)
{
	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
	int err = 0;
	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };

	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
	seq_putc(m, ' ');
	seq_path(m, &mnt_path, " \t\n\\");
	seq_putc(m, ' ');
	show_type(m, mnt->mnt_sb);
	seq_puts(m, __mnt_is_readonly(mnt) ? " ro" : " rw");
	err = show_sb_opts(m, mnt->mnt_sb);
	if (err)
		goto out;
	show_mnt_opts(m, mnt);
	if (mnt->mnt_sb->s_op->show_options)
		err = mnt->mnt_sb->s_op->show_options(m, mnt);
	seq_puts(m, " 0 0\n");
out:
	return err;
}

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

static int show_mountinfo(struct seq_file *m, void *v)
{
	struct proc_mounts *p = m->private;
	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
	struct super_block *sb = mnt->mnt_sb;
	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
	struct path root = p->root;
	int err = 0;

	seq_printf(m, "%i %i %u:%u ", mnt->mnt_id, mnt->mnt_parent->mnt_id,
		   MAJOR(sb->s_dev), MINOR(sb->s_dev));
	seq_dentry(m, mnt->mnt_root, " \t\n\\");
	seq_putc(m, ' ');
	seq_path_root(m, &mnt_path, &root, " \t\n\\");
	if (root.mnt != p->root.mnt || root.dentry != p->root.dentry) {
		/*
		 * Mountpoint is outside root, discard that one.  Ugly,
		 * but less so than trying to do that in iterator in a
		 * race-free way (due to renames).
		 */
		return SEQ_SKIP;
	}
	seq_puts(m, mnt->mnt_flags & MNT_READONLY ? " ro" : " rw");
	show_mnt_opts(m, mnt);

	/* Tagged fields ("foo:X" or "bar") */
	if (IS_MNT_SHARED(mnt))
		seq_printf(m, " shared:%i", mnt->mnt_group_id);
	if (IS_MNT_SLAVE(mnt)) {
		int master = mnt->mnt_master->mnt_group_id;
		int dom = get_dominating_id(mnt, &p->root);
		seq_printf(m, " master:%i", master);
		if (dom && dom != master)
			seq_printf(m, " propagate_from:%i", dom);
	}
	if (IS_MNT_UNBINDABLE(mnt))
		seq_puts(m, " unbindable");

	/* Filesystem specific data */
	seq_puts(m, " - ");
	show_type(m, sb);
	seq_putc(m, ' ');
	mangle(m, mnt->mnt_devname ? mnt->mnt_devname : "none");
	seq_puts(m, sb->s_flags & MS_RDONLY ? " ro" : " rw");
	err = show_sb_opts(m, sb);
	if (err)
		goto out;
	if (sb->s_op->show_options)
		err = sb->s_op->show_options(m, mnt);
	seq_putc(m, '\n');
out:
	return err;
}

const struct seq_operations mountinfo_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_mountinfo,
};

static int show_vfsstat(struct seq_file *m, void *v)
{
	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
	struct path mnt_path = { .dentry = mnt->mnt_root, .mnt = mnt };
	int err = 0;

	/* device */
	if (mnt->mnt_devname) {
		seq_puts(m, "device ");
		mangle(m, mnt->mnt_devname);
	} else
		seq_puts(m, "no device");

	/* mount point */
	seq_puts(m, " mounted on ");
	seq_path(m, &mnt_path, " \t\n\\");
	seq_putc(m, ' ');

	/* file system type */
	seq_puts(m, "with fstype ");
	show_type(m, mnt->mnt_sb);

	/* optional statistics */
	if (mnt->mnt_sb->s_op->show_stats) {
		seq_putc(m, ' ');
		err = mnt->mnt_sb->s_op->show_stats(m, mnt);
	}

	seq_putc(m, '\n');
	return err;
}

const struct seq_operations mountstats_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_vfsstat,
};
#endif  /* CONFIG_PROC_FS */

/**
 * may_umount_tree - check if a mount tree is busy
 * @mnt: root of mount tree
 *
 * This is called to check if a tree of mounts has any
 * open files, pwds, chroots or sub mounts that are
 * busy.
 */
int may_umount_tree(struct vfsmount *mnt)
{
	int actual_refs = 0;
	int minimum_refs = 0;
	struct vfsmount *p;

	spin_lock(&vfsmount_lock);
	for (p = mnt; p; p = next_mnt(p, mnt)) {
		actual_refs += atomic_read(&p->mnt_count);
		minimum_refs += 2;
	}
	spin_unlock(&vfsmount_lock);

	if (actual_refs > minimum_refs)
		return 0;

	return 1;
}

EXPORT_SYMBOL(may_umount_tree);

/**
 * may_umount - check if a mount point is busy
 * @mnt: root of mount
 *
 * This is called to check if a mount point has any
 * open files, pwds, chroots or sub mounts. If the
 * mount has sub mounts this will return busy
 * regardless of whether the sub mounts are busy.
 *
 * Doesn't take quota and stuff into account. IOW, in some cases it will
 * give false negatives. The main reason why it's here is that we need
 * a non-destructive way to look for easily umountable filesystems.
 */
int may_umount(struct vfsmount *mnt)
{
	int ret = 1;
	spin_lock(&vfsmount_lock);
	if (propagate_mount_busy(mnt, 2))
		ret = 0;
	spin_unlock(&vfsmount_lock);
	return ret;
}

EXPORT_SYMBOL(may_umount);

void release_mounts(struct list_head *head)
{
	struct vfsmount *mnt;
	while (!list_empty(head)) {
		mnt = list_first_entry(head, struct vfsmount, mnt_hash);
		list_del_init(&mnt->mnt_hash);
		if (mnt->mnt_parent != mnt) {
			struct dentry *dentry;
			struct vfsmount *m;
			spin_lock(&vfsmount_lock);
			dentry = mnt->mnt_mountpoint;
			m = mnt->mnt_parent;
			mnt->mnt_mountpoint = mnt->mnt_root;
			mnt->mnt_parent = mnt;
			m->mnt_ghosts--;
			spin_unlock(&vfsmount_lock);
			dput(dentry);
			mntput(m);
		}
		mntput(mnt);
	}
}

void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
{
	struct vfsmount *p;

	for (p = mnt; p; p = next_mnt(p, mnt))
		list_move(&p->mnt_hash, kill);

	if (propagate)
		propagate_umount(kill);

	list_for_each_entry(p, kill, mnt_hash) {
		list_del_init(&p->mnt_expire);
		list_del_init(&p->mnt_list);
		__touch_mnt_namespace(p->mnt_ns);
		p->mnt_ns = NULL;
		list_del_init(&p->mnt_child);
		if (p->mnt_parent != p) {
			p->mnt_parent->mnt_ghosts++;
			p->mnt_mountpoint->d_mounted--;
		}
		change_mnt_propagation(p, MS_PRIVATE);
	}
}

static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts);

static int do_umount(struct vfsmount *mnt, int flags)
{
	struct super_block *sb = mnt->mnt_sb;
	int retval;
	LIST_HEAD(umount_list);

	retval = security_sb_umount(mnt, flags);
	if (retval)
		return retval;

	/*
	 * Allow userspace to request a mountpoint be expired rather than
	 * unmounting unconditionally. Unmount only happens if:
	 *  (1) the mark is already set (the mark is cleared by mntput())
	 *  (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
	 */
	if (flags & MNT_EXPIRE) {
		if (mnt == current->fs->root.mnt ||
		    flags & (MNT_FORCE | MNT_DETACH))
			return -EINVAL;

		if (atomic_read(&mnt->mnt_count) != 2)
			return -EBUSY;

		if (!xchg(&mnt->mnt_expiry_mark, 1))
			return -EAGAIN;
	}

	/*
	 * If we may have to abort operations to get out of this
	 * mount, and they will themselves hold resources we must
	 * allow the fs to do things. In the Unix tradition of
	 * 'Gee thats tricky lets do it in userspace' the umount_begin
	 * might fail to complete on the first run through as other tasks
	 * must return, and the like. Thats for the mount program to worry