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/quotaops.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 <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 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)

struct vfsmount *alloc_vfsmnt(const char *name)
{
	struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
	if (mnt) {
		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);
		atomic_set(&mnt->__mnt_writers, 0);
		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;
}

/*
 * 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);

struct mnt_writer {
	/*
	 * If holding multiple instances of this lock, they
	 * must be ordered by cpu number.
	 */
	spinlock_t lock;
	struct lock_class_key lock_class; /* compiles out with !lockdep */
	unsigned long count;
	struct vfsmount *mnt;
} ____cacheline_aligned_in_smp;
static DEFINE_PER_CPU(struct mnt_writer, mnt_writers);

static int __init init_mnt_writers(void)
{
	int cpu;
	for_each_possible_cpu(cpu) {
		struct mnt_writer *writer = &per_cpu(mnt_writers, cpu);
		spin_lock_init(&writer->lock);
		lockdep_set_class(&writer->lock, &writer->lock_class);
		writer->count = 0;
	}
	return 0;
}
fs_initcall(init_mnt_writers);

static void unlock_mnt_writers(void)
{
	int cpu;
	struct mnt_writer *cpu_writer;

	for_each_possible_cpu(cpu) {
		cpu_writer = &per_cpu(mnt_writers, cpu);
		spin_unlock(&cpu_writer->lock);
	}
}

static inline void __clear_mnt_count(struct mnt_writer *cpu_writer)
{
	if (!cpu_writer->mnt)
		return;
	/*
	 * This is in case anyone ever leaves an invalid,
	 * old ->mnt and a count of 0.
	 */
	if (!cpu_writer->count)
		return;
	atomic_add(cpu_writer->count, &cpu_writer->mnt->__mnt_writers);
	cpu_writer->count = 0;
}
 /*
 * must hold cpu_writer->lock
 */
static inline void use_cpu_writer_for_mount(struct mnt_writer *cpu_writer,
					  struct vfsmount *mnt)
{
	if (cpu_writer->mnt == mnt)
		return;
	__clear_mnt_count(cpu_writer);
	cpu_writer->mnt = mnt;
}

/*
 * 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;
	struct mnt_writer *cpu_writer;

	cpu_writer = &get_cpu_var(mnt_writers);
	spin_lock(&cpu_writer->lock);
	if (__mnt_is_readonly(mnt)) {
		ret = -EROFS;
		goto out;
	}
	use_cpu_writer_for_mount(cpu_writer, mnt);
	cpu_writer->count++;
out:
	spin_unlock(&cpu_writer->lock);
	put_cpu_var(mnt_writers);
	return ret;
}
EXPORT_SYMBOL_GPL(mnt_want_write);

static void lock_mnt_writers(void)
{
	int cpu;
	struct mnt_writer *cpu_writer;

	for_each_possible_cpu(cpu) {
		cpu_writer = &per_cpu(mnt_writers, cpu);
		spin_lock(&cpu_writer->lock);
		__clear_mnt_count(cpu_writer);
		cpu_writer->mnt = NULL;
	}
}

/*
 * These per-cpu write counts are not guaranteed to have
 * matched increments and decrements on any given cpu.
 * A file open()ed for write on one cpu and close()d on
 * another cpu will imbalance this count.  Make sure it
 * does not get too far out of whack.
 */
static void handle_write_count_underflow(struct vfsmount *mnt)
{
	if (atomic_read(&mnt->__mnt_writers) >=
	    MNT_WRITER_UNDERFLOW_LIMIT)
		return;
	/*
	 * It isn't necessary to hold all of the locks
	 * at the same time, but doing it this way makes
	 * us share a lot more code.
	 */
	lock_mnt_writers();
	/*
	 * vfsmount_lock is for mnt_flags.
	 */
	spin_lock(&vfsmount_lock);
	/*
	 * If coalescing the per-cpu writer counts did not
	 * get us back to a positive writer count, we have
	 * a bug.
	 */
	if ((atomic_read(&mnt->__mnt_writers) < 0) &&
	    !(mnt->mnt_flags & MNT_IMBALANCED_WRITE_COUNT)) {
		printk(KERN_DEBUG "leak detected on mount(%p) writers "
				"count: %d\n",
			mnt, atomic_read(&mnt->__mnt_writers));
		WARN_ON(1);
		/* use the flag to keep the dmesg spam down */
		mnt->mnt_flags |= MNT_IMBALANCED_WRITE_COUNT;
	}
	spin_unlock(&vfsmount_lock);
	unlock_mnt_writers();
}

/**
 * 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)
{
	int must_check_underflow = 0;
	struct mnt_writer *cpu_writer;

	cpu_writer = &get_cpu_var(mnt_writers);
	spin_lock(&cpu_writer->lock);

	use_cpu_writer_for_mount(cpu_writer, mnt);
	if (cpu_writer->count > 0) {
		cpu_writer->count--;
	} else {
		must_check_underflow = 1;
		atomic_dec(&mnt->__mnt_writers);
	}

	spin_unlock(&cpu_writer->lock);
	/*
	 * Logically, we could call this each time,
	 * but the __mnt_writers cacheline tends to
	 * be cold, and makes this expensive.
	 */
	if (must_check_underflow)
		handle_write_count_underflow(mnt);
	/*
	 * This could be done right after the spinlock
	 * is taken because the spinlock keeps us on
	 * the cpu, and disables preemption.  However,
	 * putting it here bounds the amount that
	 * __mnt_writers can underflow.  Without it,
	 * we could theoretically wrap __mnt_writers.
	 */
	put_cpu_var(mnt_writers);
}
EXPORT_SYMBOL_GPL(mnt_drop_write);

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

	lock_mnt_writers();
	/*
	 * With all the locks held, this value is stable
	 */
	if (atomic_read(&mnt->__mnt_writers) > 0) {
		ret = -EBUSY;
		goto out;
	}
	/*
	 * nobody can do a successful mnt_want_write() with all
	 * of the counts in MNT_DENIED_WRITE and the locks held.
	 */
	spin_lock(&vfsmount_lock);
	if (!ret)
		mnt->mnt_flags |= MNT_READONLY;
	spin_unlock(&vfsmount_lock);
out:
	unlock_mnt_writers();
	return ret;
}

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

int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
{
	mnt->mnt_sb = sb;
	mnt->mnt_root = dget(sb->s_root);
	return 0;
}

EXPORT_SYMBOL(simple_set_mnt);

void free_vfsmnt(struct vfsmount *mnt)
{
	kfree(mnt->mnt_devname);
	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 vfsmount *mnt, struct dentry *dentry)
{
	struct vfsmount *child_mnt;
	spin_lock(&vfsmount_lock);
	if ((child_mnt = __lookup_mnt(mnt, 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) {
		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;
}

static inline void __mntput(struct vfsmount *mnt)
{
	int cpu;
	struct super_block *sb = mnt->mnt_sb;
	/*
	 * We don't have to hold all of the locks at the
	 * same time here because we know that we're the
	 * last reference to mnt and that no new writers
	 * can come in.
	 */
	for_each_possible_cpu(cpu) {
		struct mnt_writer *cpu_writer = &per_cpu(mnt_writers, cpu);
		if (cpu_writer->mnt != mnt)
			continue;
		spin_lock(&cpu_writer->lock);
		atomic_add(cpu_writer->count, &mnt->__mnt_writers);
		cpu_writer->count = 0;
		/*
		 * Might as well do this so that no one
		 * ever sees the pointer and expects
		 * it to be valid.
		 */
		cpu_writer->mnt = NULL;
		spin_unlock(&cpu_writer->lock);
	}
	/*
	 * 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.
	 */
	WARN_ON(atomic_read(&mnt->__mnt_writers));
	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 = mnt->mnt_sb->s_options;

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

	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)
{
	kfree(sb->s_options);
	sb->s_options = kstrdup(options, GFP_KERNEL);
}
EXPORT_SYMBOL(save_mount_options);

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

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

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

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

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

static int show_vfsmnt(struct seq_file *m, void *v)
{
	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
	int err = 0;
	static struct proc_fs_info {
		int flag;
		char *str;
	} fs_info[] = {
		{ MS_SYNCHRONOUS, ",sync" },
		{ MS_DIRSYNC, ",dirsync" },
		{ MS_MANDLOCK, ",mand" },
		{ 0, NULL }
	};
	static struct proc_fs_info mnt_info[] = {
		{ MNT_NOSUID, ",nosuid" },
		{ MNT_NODEV, ",nodev" },
		{ MNT_NOEXEC, ",noexec" },
		{ MNT_NOATIME, ",noatime" },
		{ MNT_NODIRATIME, ",nodiratime" },
		{ MNT_RELATIME, ",relatime" },
		{ 0, NULL }
	};
	struct proc_fs_info *fs_infop;
	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, ' ');
	mangle(m, mnt->mnt_sb->s_type->name);
	if (mnt->mnt_sb->s_subtype && mnt->mnt_sb->s_subtype[0]) {
		seq_putc(m, '.');
		mangle(m, mnt->mnt_sb->s_subtype);
	}
	seq_puts(m, __mnt_is_readonly(mnt) ? " 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
};

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 ");
	mangle(m, mnt->mnt_sb->s_type->name);

	/* 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;
}

struct seq_operations mountstats_op = {
	.start	= m_start,
	.next	= m_next,
	.stop	= m_stop,
	.show	= show_vfsstat,
};

/**
 * 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
	 * about for the moment.
	 */

	lock_kernel();
	if (sb->s_op->umount_begin)
		sb->s_op->umount_begin(mnt, flags);
	unlock_kernel();

	/*
	 * No sense to grab the lock for this test, but test itself looks
	 * somewhat bogus. Suggestions for better replacement?
	 * Ho-hum... In principle, we might treat that as umount + switch
	 * to rootfs. GC would eventually take care of the old vfsmount.
	 * Actually it makes sense, especially if rootfs would contain a
	 * /reboot - static binary that would close all descriptors and
	 * call reboot(9). Then init(8) could umount root and exec /reboot.
	 */
	if (mnt == current->fs->root.mnt && !(flags & MNT_DETACH)) {
		/*
		 * Special case for "unmounting" root ...
		 * we just try to remount it readonly.
		 */
		down_write(&sb->s_umount);
		if (!(sb->s_flags & MS_RDONLY)) {
			lock_kernel();
			DQUOT_OFF(sb);
			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
			unlock_kernel();
		}
		up_write(&sb->s_umount);
		return retval;
	}

	down_write(&namespace_sem);
	spin_lock(&vfsmount_lock);
	event++;

	if (!(flags & MNT_DETACH))
		shrink_submounts(mnt, &umount_list);

	retval = -EBUSY;
	if (flags & MNT_DETACH || !propagate_mount_busy(mnt, 2)) {
		if (!list_empty(&mnt->mnt_list))
			umount_tree(mnt, 1, &umount_list);
		retval = 0;
	}
	spin_unlock(&vfsmount_lock);
	if (retval)
		security_sb_umount_busy(mnt);
	up_write(&namespace_sem);
	release_mounts(&umount_list);
	return retval;
}

/*
 * Now umount can handle mount points as well as block devices.
 * This is important for filesystems which use unnamed block devices.
 *
 * We now support a flag for forced unmount like the other 'big iron'
 * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
 */

asmlinkage long sys_umount(char __user * name, int flags)
{
	struct nameidata nd;
	int retval;

	retval = __user_walk(name, LOOKUP_FOLLOW, &nd);
	if (retval)
		goto out;
	retval = -EINVAL;
	if (nd.path.dentry != nd.path.mnt->mnt_root)
		goto dput_and_out;
	if (!check_mnt(nd.path.mnt))
		goto dput_and_out;

	retval = -EPERM;
	if (!capable(CAP_SYS_ADMIN))
		goto dput_and_out;

	retval = do_umount(nd.path.mnt, flags);
dput_and_out:
	/* we mustn't call path_put() as that would clear mnt_expiry_mark */
	dput(nd.path.dentry);
	mntput_no_expire(nd.path.mnt);
out:
	return retval;
}

#ifdef __ARCH_WANT_SYS_OLDUMOUNT

/*