X-Git-Url: http://ftp.safe.ca/?p=safe%2Fjmp%2Flinux-2.6;a=blobdiff_plain;f=fs%2Fnamespace.c;h=c768f733c8d6585a87551190bdf1b71a14cab9fe;hp=e9c10cd01e1325cff95869cbb0f23aa8d14c10ce;hb=d5aa407f59f5b83d2c50ec88f5bf56d40f1f8978;hpb=13f14b4d8be225cbb11ff2be7c048590a9ccf87b

diff --git a/fs/namespace.c b/fs/namespace.c
index e9c10cd..c768f73 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -14,18 +14,21 @@
 #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/nsproxy.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"
@@ -38,6 +41,10 @@
 __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
 
 static int event;
+static DEFINE_IDA(mnt_id_ida);
+static DEFINE_IDA(mnt_group_ida);
+static int mnt_id_start = 0;
+static int mnt_group_start = 1;
 
 static struct list_head *mount_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
@@ -55,10 +62,85 @@ static inline unsigned long hash(struct vfsmount *mnt, struct dentry *dentry)
 	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_above(&mnt_id_ida, mnt_id_start, &mnt->mnt_id);
+	if (!res)
+		mnt_id_start = mnt->mnt_id + 1;
+	spin_unlock(&vfsmount_lock);
+	if (res == -EAGAIN)
+		goto retry;
+
+	return res;
+}
+
+static void mnt_free_id(struct vfsmount *mnt)
+{
+	int id = mnt->mnt_id;
+	spin_lock(&vfsmount_lock);
+	ida_remove(&mnt_id_ida, id);
+	if (mnt_id_start > id)
+		mnt_id_start = 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)
+{
+	int res;
+
+	if (!ida_pre_get(&mnt_group_ida, GFP_KERNEL))
+		return -ENOMEM;
+
+	res = ida_get_new_above(&mnt_group_ida,
+				mnt_group_start,
+				&mnt->mnt_group_id);
+	if (!res)
+		mnt_group_start = mnt->mnt_group_id + 1;
+
+	return res;
+}
+
+/*
+ * Release a peer group ID
+ */
+void mnt_release_group_id(struct vfsmount *mnt)
+{
+	int id = mnt->mnt_group_id;
+	ida_remove(&mnt_group_ida, id);
+	if (mnt_group_start > id)
+		mnt_group_start = 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);
@@ -68,23 +150,249 @@ struct vfsmount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_share);
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
-		if (name) {
-			int size = strlen(name) + 1;
-			char *newname = kmalloc(size, GFP_KERNEL);
-			if (newname) {
-				memcpy(newname, name, size);
-				mnt->mnt_devname = newname;
-			}
-		}
+#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_clone_write - get write access to a mount
+ * @mnt: the mount on which to take a write
+ *
+ * This is effectively like mnt_want_write, except
+ * it must only be used to take an extra write reference
+ * on a mountpoint that we already know has a write reference
+ * on it. This allows some optimisation.
+ *
+ * After finished, mnt_drop_write must be called as usual to
+ * drop the reference.
+ */
+int mnt_clone_write(struct vfsmount *mnt)
+{
+	/* superblock may be r/o */
+	if (__mnt_is_readonly(mnt))
+		return -EROFS;
+	preempt_disable();
+	inc_mnt_writers(mnt);
+	preempt_enable();
+	return 0;
 }
+EXPORT_SYMBOL_GPL(mnt_clone_write);
 
-int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb)
+/**
+ * mnt_want_write_file - get write access to a file's mount
+ * @file: the file who's mount on which to take a write
+ *
+ * This is like mnt_want_write, but it takes a file and can
+ * do some optimisations if the file is open for write already
+ */
+int mnt_want_write_file(struct file *file)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	if (!(file->f_mode & FMODE_WRITE) || special_file(inode->i_mode))
+		return mnt_want_write(file->f_path.mnt);
+	else
+		return mnt_clone_write(file->f_path.mnt);
+}
+EXPORT_SYMBOL_GPL(mnt_want_write_file);
+
+/**
+ * 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);
-	return 0;
 }
 
 EXPORT_SYMBOL(simple_set_mnt);
@@ -92,6 +400,10 @@ 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);
 }
 
@@ -124,11 +436,11 @@ struct vfsmount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry,
  * lookup_mnt increments the ref count before returning
  * the vfsmount struct.
  */
-struct vfsmount *lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
+struct vfsmount *lookup_mnt(struct path *path)
 {
 	struct vfsmount *child_mnt;
 	spin_lock(&vfsmount_lock);
-	if ((child_mnt = __lookup_mnt(mnt, dentry, 1)))
+	if ((child_mnt = __lookup_mnt(path->mnt, path->dentry, 1)))
 		mntget(child_mnt);
 	spin_unlock(&vfsmount_lock);
 	return child_mnt;
@@ -155,15 +467,15 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns)
 	}
 }
 
-static void detach_mnt(struct vfsmount *mnt, struct nameidata *old_nd)
+static void detach_mnt(struct vfsmount *mnt, struct path *old_path)
 {
-	old_nd->dentry = mnt->mnt_mountpoint;
-	old_nd->mnt = mnt->mnt_parent;
+	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_nd->dentry->d_mounted--;
+	old_path->dentry->d_mounted--;
 }
 
 void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
@@ -174,12 +486,12 @@ void mnt_set_mountpoint(struct vfsmount *mnt, struct dentry *dentry,
 	dentry->d_mounted++;
 }
 
-static void attach_mnt(struct vfsmount *mnt, struct nameidata *nd)
+static void attach_mnt(struct vfsmount *mnt, struct path *path)
 {
-	mnt_set_mountpoint(nd->mnt, nd->dentry, mnt);
+	mnt_set_mountpoint(path->mnt, path->dentry, mnt);
 	list_add_tail(&mnt->mnt_hash, mount_hashtable +
-			hash(nd->mnt, nd->dentry));
-	list_add_tail(&mnt->mnt_child, &nd->mnt->mnt_mounts);
+			hash(path->mnt, path->dentry));
+	list_add_tail(&mnt->mnt_child, &path->mnt->mnt_mounts);
 }
 
 /*
@@ -238,6 +550,17 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 	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;
@@ -262,18 +585,31 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 		/* 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;
+
+ 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);
@@ -320,20 +656,80 @@ void mnt_unpin(struct vfsmount *mnt)
 
 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 mnt_namespace *n = m->private;
+	struct proc_mounts *p = m->private;
 
 	down_read(&namespace_sem);
-	return seq_list_start(&n->list, *pos);
+	return seq_list_start(&p->ns->list, *pos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	struct mnt_namespace *n = m->private;
+	struct proc_mounts *p = m->private;
 
-	return seq_list_next(v, &n->list, pos);
+	return seq_list_next(v, &p->ns->list, pos);
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -341,69 +737,153 @@ static void m_stop(struct seq_file *m, void *v)
 	up_read(&namespace_sem);
 }
 
-static inline void mangle(struct seq_file *m, const char *s)
-{
-	seq_escape(m, s, " \t\n\\");
-}
+struct proc_fs_info {
+	int flag;
+	const char *str;
+};
 
-static int show_vfsmnt(struct seq_file *m, void *v)
+static int show_sb_opts(struct seq_file *m, struct super_block *sb)
 {
-	struct vfsmount *mnt = list_entry(v, struct vfsmount, mnt_list);
-	int err = 0;
-	static struct proc_fs_info {
-		int flag;
-		char *str;
-	} fs_info[] = {
+	static const struct proc_fs_info fs_info[] = {
 		{ MS_SYNCHRONOUS, ",sync" },
 		{ MS_DIRSYNC, ",dirsync" },
 		{ MS_MANDLOCK, ",mand" },
 		{ 0, NULL }
 	};
-	static struct proc_fs_info mnt_info[] = {
+	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 }
 	};
-	struct proc_fs_info *fs_infop;
+	const 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);
-	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->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);
 	}
+}
+
+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;
 }
 
-struct seq_operations mounts_op = {
+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 */
@@ -415,12 +895,12 @@ static int show_vfsstat(struct seq_file *m, void *v)
 
 	/* mount point */
 	seq_puts(m, " mounted on ");
-	seq_path(m, mnt, mnt->mnt_root, " \t\n\\");
+	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);
+	show_type(m, mnt->mnt_sb);
 
 	/* optional statistics */
 	if (mnt->mnt_sb->s_op->show_stats) {
@@ -432,12 +912,13 @@ static int show_vfsstat(struct seq_file *m, void *v)
 	return err;
 }
 
-struct seq_operations mountstats_op = {
+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
@@ -484,10 +965,12 @@ EXPORT_SYMBOL(may_umount_tree);
 int may_umount(struct vfsmount *mnt)
 {
 	int ret = 1;
+	down_read(&namespace_sem);
 	spin_lock(&vfsmount_lock);
 	if (propagate_mount_busy(mnt, 2))
 		ret = 0;
 	spin_unlock(&vfsmount_lock);
+	up_read(&namespace_sem);
 	return ret;
 }
 
@@ -507,6 +990,7 @@ void release_mounts(struct list_head *head)
 			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);
@@ -531,12 +1015,16 @@ void umount_tree(struct vfsmount *mnt, int propagate, struct list_head *kill)
 		__touch_mnt_namespace(p->mnt_ns);
 		p->mnt_ns = NULL;
 		list_del_init(&p->mnt_child);
-		if (p->mnt_parent != p)
+		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;
@@ -554,7 +1042,7 @@ static int do_umount(struct vfsmount *mnt, int flags)
 	 *  (2) the usage count == 1 [parent vfsmount] + 1 [sys_umount]
 	 */
 	if (flags & MNT_EXPIRE) {
-		if (mnt == current->fs->rootmnt ||
+		if (mnt == current->fs->root.mnt ||
 		    flags & (MNT_FORCE | MNT_DETACH))
 			return -EINVAL;
 
@@ -575,10 +1063,9 @@ static int do_umount(struct vfsmount *mnt, int flags)
 	 * about for the moment.
 	 */
 
-	lock_kernel();
-	if (sb->s_op->umount_begin)
-		sb->s_op->umount_begin(mnt, flags);
-	unlock_kernel();
+	if (flags & MNT_FORCE && sb->s_op->umount_begin) {
+		sb->s_op->umount_begin(sb);
+	}
 
 	/*
 	 * No sense to grab the lock for this test, but test itself looks
@@ -589,18 +1076,14 @@ static int do_umount(struct vfsmount *mnt, int flags)
 	 * /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->rootmnt && !(flags & MNT_DETACH)) {
+	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);
+		if (!(sb->s_flags & MS_RDONLY))
 			retval = do_remount_sb(sb, MS_RDONLY, NULL, 0);
-			unlock_kernel();
-		}
 		up_write(&sb->s_umount);
 		return retval;
 	}
@@ -609,6 +1092,9 @@ static int do_umount(struct vfsmount *mnt, int flags)
 	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))
@@ -631,27 +1117,29 @@ static int do_umount(struct vfsmount *mnt, int flags)
  * unixes. Our API is identical to OSF/1 to avoid making a mess of AMD
  */
 
-asmlinkage long sys_umount(char __user * name, int flags)
+SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
 {
-	struct nameidata nd;
+	struct path path;
 	int retval;
 
-	retval = __user_walk(name, LOOKUP_FOLLOW, &nd);
+	retval = user_path(name, &path);
 	if (retval)
 		goto out;
 	retval = -EINVAL;
-	if (nd.dentry != nd.mnt->mnt_root)
+	if (path.dentry != path.mnt->mnt_root)
 		goto dput_and_out;
-	if (!check_mnt(nd.mnt))
+	if (!check_mnt(path.mnt))
 		goto dput_and_out;
 
 	retval = -EPERM;
 	if (!capable(CAP_SYS_ADMIN))
 		goto dput_and_out;
 
-	retval = do_umount(nd.mnt, flags);
+	retval = do_umount(path.mnt, flags);
 dput_and_out:
-	path_release_on_umount(&nd);
+	/* we mustn't call path_put() as that would clear mnt_expiry_mark */
+	dput(path.dentry);
+	mntput_no_expire(path.mnt);
 out:
 	return retval;
 }
@@ -661,47 +1149,36 @@ out:
 /*
  *	The 2.0 compatible umount. No flags.
  */
-asmlinkage long sys_oldumount(char __user * name)
+SYSCALL_DEFINE1(oldumount, char __user *, name)
 {
 	return sys_umount(name, 0);
 }
 
 #endif
 
-static int mount_is_safe(struct nameidata *nd)
+static int mount_is_safe(struct path *path)
 {
 	if (capable(CAP_SYS_ADMIN))
 		return 0;
 	return -EPERM;
 #ifdef notyet
-	if (S_ISLNK(nd->dentry->d_inode->i_mode))
+	if (S_ISLNK(path->dentry->d_inode->i_mode))
 		return -EPERM;
-	if (nd->dentry->d_inode->i_mode & S_ISVTX) {
-		if (current->uid != nd->dentry->d_inode->i_uid)
+	if (path->dentry->d_inode->i_mode & S_ISVTX) {
+		if (current_uid() != path->dentry->d_inode->i_uid)
 			return -EPERM;
 	}
-	if (vfs_permission(nd, MAY_WRITE))
+	if (inode_permission(path->dentry->d_inode, MAY_WRITE))
 		return -EPERM;
 	return 0;
 #endif
 }
 
-static int lives_below_in_same_fs(struct dentry *d, struct dentry *dentry)
-{
-	while (1) {
-		if (d == dentry)
-			return 1;
-		if (d == NULL || d == d->d_parent)
-			return 0;
-		d = d->d_parent;
-	}
-}
-
 struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
 					int flag)
 {
 	struct vfsmount *res, *p, *q, *r, *s;
-	struct nameidata nd;
+	struct path path;
 
 	if (!(flag & CL_COPY_ALL) && IS_MNT_UNBINDABLE(mnt))
 		return NULL;
@@ -713,7 +1190,7 @@ struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
 
 	p = mnt;
 	list_for_each_entry(r, &mnt->mnt_mounts, mnt_child) {
-		if (!lives_below_in_same_fs(r->mnt_mountpoint, dentry))
+		if (!is_subdir(r->mnt_mountpoint, dentry))
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
@@ -726,14 +1203,14 @@ struct vfsmount *copy_tree(struct vfsmount *mnt, struct dentry *dentry,
 				q = q->mnt_parent;
 			}
 			p = s;
-			nd.mnt = q;
-			nd.dentry = p->mnt_mountpoint;
+			path.mnt = q;
+			path.dentry = p->mnt_mountpoint;
 			q = clone_mnt(p, p->mnt_root, flag);
 			if (!q)
 				goto Enomem;
 			spin_lock(&vfsmount_lock);
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			attach_mnt(q, &nd);
+			attach_mnt(q, &path);
 			spin_unlock(&vfsmount_lock);
 		}
 	}
@@ -749,26 +1226,53 @@ Enomem:
 	return NULL;
 }
 
-struct vfsmount *collect_mounts(struct vfsmount *mnt, struct dentry *dentry)
+struct vfsmount *collect_mounts(struct path *path)
 {
 	struct vfsmount *tree;
-	down_read(&namespace_sem);
-	tree = copy_tree(mnt, dentry, CL_COPY_ALL | CL_PRIVATE);
-	up_read(&namespace_sem);
+	down_write(&namespace_sem);
+	tree = copy_tree(path->mnt, path->dentry, CL_COPY_ALL | CL_PRIVATE);
+	up_write(&namespace_sem);
 	return tree;
 }
 
 void drop_collected_mounts(struct vfsmount *mnt)
 {
 	LIST_HEAD(umount_list);
-	down_read(&namespace_sem);
+	down_write(&namespace_sem);
 	spin_lock(&vfsmount_lock);
 	umount_tree(mnt, 0, &umount_list);
 	spin_unlock(&vfsmount_lock);
-	up_read(&namespace_sem);
+	up_write(&namespace_sem);
 	release_mounts(&umount_list);
 }
 
+static void cleanup_group_ids(struct vfsmount *mnt, struct vfsmount *end)
+{
+	struct vfsmount *p;
+
+	for (p = mnt; p != end; p = next_mnt(p, mnt)) {
+		if (p->mnt_group_id && !IS_MNT_SHARED(p))
+			mnt_release_group_id(p);
+	}
+}
+
+static int invent_group_ids(struct vfsmount *mnt, bool recurse)
+{
+	struct vfsmount *p;
+
+	for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
+		if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
+			int err = mnt_alloc_group_id(p);
+			if (err) {
+				cleanup_group_ids(mnt, p);
+				return err;
+			}
+		}
+	}
+
+	return 0;
+}
+
 /*
  *  @source_mnt : mount tree to be attached
  *  @nd         : place the mount tree @source_mnt is attached
@@ -833,26 +1337,33 @@ void drop_collected_mounts(struct vfsmount *mnt)
  * in allocations.
  */
 static int attach_recursive_mnt(struct vfsmount *source_mnt,
-			struct nameidata *nd, struct nameidata *parent_nd)
+			struct path *path, struct path *parent_path)
 {
 	LIST_HEAD(tree_list);
-	struct vfsmount *dest_mnt = nd->mnt;
-	struct dentry *dest_dentry = nd->dentry;
+	struct vfsmount *dest_mnt = path->mnt;
+	struct dentry *dest_dentry = path->dentry;
 	struct vfsmount *child, *p;
+	int err;
 
-	if (propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list))
-		return -EINVAL;
+	if (IS_MNT_SHARED(dest_mnt)) {
+		err = invent_group_ids(source_mnt, true);
+		if (err)
+			goto out;
+	}
+	err = propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list);
+	if (err)
+		goto out_cleanup_ids;
+
+	spin_lock(&vfsmount_lock);
 
 	if (IS_MNT_SHARED(dest_mnt)) {
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
 			set_mnt_shared(p);
 	}
-
-	spin_lock(&vfsmount_lock);
-	if (parent_nd) {
-		detach_mnt(source_mnt, parent_nd);
-		attach_mnt(source_mnt, nd);
-		touch_mnt_namespace(current->nsproxy->mnt_ns);
+	if (parent_path) {
+		detach_mnt(source_mnt, parent_path);
+		attach_mnt(source_mnt, path);
+		touch_mnt_namespace(parent_path->mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_dentry, source_mnt);
 		commit_tree(source_mnt);
@@ -864,95 +1375,111 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
 	}
 	spin_unlock(&vfsmount_lock);
 	return 0;
+
+ out_cleanup_ids:
+	if (IS_MNT_SHARED(dest_mnt))
+		cleanup_group_ids(source_mnt, NULL);
+ out:
+	return err;
 }
 
-static int graft_tree(struct vfsmount *mnt, struct nameidata *nd)
+static int graft_tree(struct vfsmount *mnt, struct path *path)
 {
 	int err;
 	if (mnt->mnt_sb->s_flags & MS_NOUSER)
 		return -EINVAL;
 
-	if (S_ISDIR(nd->dentry->d_inode->i_mode) !=
+	if (S_ISDIR(path->dentry->d_inode->i_mode) !=
 	      S_ISDIR(mnt->mnt_root->d_inode->i_mode))
 		return -ENOTDIR;
 
 	err = -ENOENT;
-	mutex_lock(&nd->dentry->d_inode->i_mutex);
-	if (IS_DEADDIR(nd->dentry->d_inode))
+	mutex_lock(&path->dentry->d_inode->i_mutex);
+	if (IS_DEADDIR(path->dentry->d_inode))
 		goto out_unlock;
 
-	err = security_sb_check_sb(mnt, nd);
+	err = security_sb_check_sb(mnt, path);
 	if (err)
 		goto out_unlock;
 
 	err = -ENOENT;
-	if (IS_ROOT(nd->dentry) || !d_unhashed(nd->dentry))
-		err = attach_recursive_mnt(mnt, nd, NULL);
+	if (!d_unlinked(path->dentry))
+		err = attach_recursive_mnt(mnt, path, NULL);
 out_unlock:
-	mutex_unlock(&nd->dentry->d_inode->i_mutex);
+	mutex_unlock(&path->dentry->d_inode->i_mutex);
 	if (!err)
-		security_sb_post_addmount(mnt, nd);
+		security_sb_post_addmount(mnt, path);
 	return err;
 }
 
 /*
  * recursively change the type of the mountpoint.
  */
-static int do_change_type(struct nameidata *nd, int flag)
+static int do_change_type(struct path *path, int flag)
 {
-	struct vfsmount *m, *mnt = nd->mnt;
+	struct vfsmount *m, *mnt = path->mnt;
 	int recurse = flag & MS_REC;
 	int type = flag & ~MS_REC;
+	int err = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (nd->dentry != nd->mnt->mnt_root)
+	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
 	down_write(&namespace_sem);
+	if (type == MS_SHARED) {
+		err = invent_group_ids(mnt, recurse);
+		if (err)
+			goto out_unlock;
+	}
+
 	spin_lock(&vfsmount_lock);
 	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
 		change_mnt_propagation(m, type);
 	spin_unlock(&vfsmount_lock);
+
+ out_unlock:
 	up_write(&namespace_sem);
-	return 0;
+	return err;
 }
 
 /*
  * do loopback mount.
  */
-static int do_loopback(struct nameidata *nd, char *old_name, int recurse)
+static int do_loopback(struct path *path, char *old_name,
+				int recurse)
 {
-	struct nameidata old_nd;
+	struct path old_path;
 	struct vfsmount *mnt = NULL;
-	int err = mount_is_safe(nd);
+	int err = mount_is_safe(path);
 	if (err)
 		return err;
 	if (!old_name || !*old_name)
 		return -EINVAL;
-	err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
+	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
 	if (err)
 		return err;
 
 	down_write(&namespace_sem);
 	err = -EINVAL;
-	if (IS_MNT_UNBINDABLE(old_nd.mnt))
- 		goto out;
+	if (IS_MNT_UNBINDABLE(old_path.mnt))
+		goto out;
 
-	if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt))
+	if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
 		goto out;
 
 	err = -ENOMEM;
 	if (recurse)
-		mnt = copy_tree(old_nd.mnt, old_nd.dentry, 0);
+		mnt = copy_tree(old_path.mnt, old_path.dentry, 0);
 	else
-		mnt = clone_mnt(old_nd.mnt, old_nd.dentry, 0);
+		mnt = clone_mnt(old_path.mnt, old_path.dentry, 0);
 
 	if (!mnt)
 		goto out;
 
-	err = graft_tree(mnt, nd);
+	err = graft_tree(mnt, path);
 	if (err) {
 		LIST_HEAD(umount_list);
 		spin_lock(&vfsmount_lock);
@@ -963,37 +1490,66 @@ static int do_loopback(struct nameidata *nd, char *old_name, int recurse)
 
 out:
 	up_write(&namespace_sem);
-	path_release(&old_nd);
+	path_put(&old_path);
 	return err;
 }
 
+static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
+{
+	int error = 0;
+	int readonly_request = 0;
+
+	if (ms_flags & MS_RDONLY)
+		readonly_request = 1;
+	if (readonly_request == __mnt_is_readonly(mnt))
+		return 0;
+
+	if (readonly_request)
+		error = mnt_make_readonly(mnt);
+	else
+		__mnt_unmake_readonly(mnt);
+	return error;
+}
+
 /*
  * change filesystem flags. dir should be a physical root of filesystem.
  * If you've mounted a non-root directory somewhere and want to do remount
  * on it - tough luck.
  */
-static int do_remount(struct nameidata *nd, int flags, int mnt_flags,
+static int do_remount(struct path *path, int flags, int mnt_flags,
 		      void *data)
 {
 	int err;
-	struct super_block *sb = nd->mnt->mnt_sb;
+	struct super_block *sb = path->mnt->mnt_sb;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!check_mnt(nd->mnt))
+	if (!check_mnt(path->mnt))
 		return -EINVAL;
 
-	if (nd->dentry != nd->mnt->mnt_root)
+	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
 	down_write(&sb->s_umount);
-	err = do_remount_sb(sb, flags, data, 0);
-	if (!err)
-		nd->mnt->mnt_flags = mnt_flags;
+	if (flags & MS_BIND)
+		err = change_mount_flags(path->mnt, flags);
+	else
+		err = do_remount_sb(sb, flags, data, 0);
+	if (!err) {
+		spin_lock(&vfsmount_lock);
+		mnt_flags |= path->mnt->mnt_flags & MNT_PNODE_MASK;
+		path->mnt->mnt_flags = mnt_flags;
+		spin_unlock(&vfsmount_lock);
+	}
 	up_write(&sb->s_umount);
-	if (!err)
-		security_sb_post_remount(nd->mnt, flags, data);
+	if (!err) {
+		security_sb_post_remount(path->mnt, flags, data);
+
+		spin_lock(&vfsmount_lock);
+		touch_mnt_namespace(path->mnt->mnt_ns);
+		spin_unlock(&vfsmount_lock);
+	}
 	return err;
 }
 
@@ -1007,75 +1563,77 @@ static inline int tree_contains_unbindable(struct vfsmount *mnt)
 	return 0;
 }
 
-static int do_move_mount(struct nameidata *nd, char *old_name)
+static int do_move_mount(struct path *path, char *old_name)
 {
-	struct nameidata old_nd, parent_nd;
+	struct path old_path, parent_path;
 	struct vfsmount *p;
 	int err = 0;
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (!old_name || !*old_name)
 		return -EINVAL;
-	err = path_lookup(old_name, LOOKUP_FOLLOW, &old_nd);
+	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
 	if (err)
 		return err;
 
 	down_write(&namespace_sem);
-	while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
+	while (d_mountpoint(path->dentry) &&
+	       follow_down(path))
 		;
 	err = -EINVAL;
-	if (!check_mnt(nd->mnt) || !check_mnt(old_nd.mnt))
+	if (!check_mnt(path->mnt) || !check_mnt(old_path.mnt))
 		goto out;
 
 	err = -ENOENT;
-	mutex_lock(&nd->dentry->d_inode->i_mutex);
-	if (IS_DEADDIR(nd->dentry->d_inode))
+	mutex_lock(&path->dentry->d_inode->i_mutex);
+	if (IS_DEADDIR(path->dentry->d_inode))
 		goto out1;
 
-	if (!IS_ROOT(nd->dentry) && d_unhashed(nd->dentry))
+	if (d_unlinked(path->dentry))
 		goto out1;
 
 	err = -EINVAL;
-	if (old_nd.dentry != old_nd.mnt->mnt_root)
+	if (old_path.dentry != old_path.mnt->mnt_root)
 		goto out1;
 
-	if (old_nd.mnt == old_nd.mnt->mnt_parent)
+	if (old_path.mnt == old_path.mnt->mnt_parent)
 		goto out1;
 
-	if (S_ISDIR(nd->dentry->d_inode->i_mode) !=
-	      S_ISDIR(old_nd.dentry->d_inode->i_mode))
+	if (S_ISDIR(path->dentry->d_inode->i_mode) !=
+	      S_ISDIR(old_path.dentry->d_inode->i_mode))
 		goto out1;
 	/*
 	 * Don't move a mount residing in a shared parent.
 	 */
-	if (old_nd.mnt->mnt_parent && IS_MNT_SHARED(old_nd.mnt->mnt_parent))
+	if (old_path.mnt->mnt_parent &&
+	    IS_MNT_SHARED(old_path.mnt->mnt_parent))
 		goto out1;
 	/*
 	 * Don't move a mount tree containing unbindable mounts to a destination
 	 * mount which is shared.
 	 */
-	if (IS_MNT_SHARED(nd->mnt) && tree_contains_unbindable(old_nd.mnt))
+	if (IS_MNT_SHARED(path->mnt) &&
+	    tree_contains_unbindable(old_path.mnt))
 		goto out1;
 	err = -ELOOP;
-	for (p = nd->mnt; p->mnt_parent != p; p = p->mnt_parent)
-		if (p == old_nd.mnt)
+	for (p = path->mnt; p->mnt_parent != p; p = p->mnt_parent)
+		if (p == old_path.mnt)
 			goto out1;
 
-	if ((err = attach_recursive_mnt(old_nd.mnt, nd, &parent_nd)))
+	err = attach_recursive_mnt(old_path.mnt, path, &parent_path);
+	if (err)
 		goto out1;
 
-	spin_lock(&vfsmount_lock);
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
-	list_del_init(&old_nd.mnt->mnt_expire);
-	spin_unlock(&vfsmount_lock);
+	list_del_init(&old_path.mnt->mnt_expire);
 out1:
-	mutex_unlock(&nd->dentry->d_inode->i_mutex);
+	mutex_unlock(&path->dentry->d_inode->i_mutex);
 out:
 	up_write(&namespace_sem);
 	if (!err)
-		path_release(&parent_nd);
-	path_release(&old_nd);
+		path_put(&parent_path);
+	path_put(&old_path);
 	return err;
 }
 
@@ -1083,46 +1641,51 @@ out:
  * create a new mount for userspace and request it to be added into the
  * namespace's tree
  */
-static int do_new_mount(struct nameidata *nd, char *type, int flags,
+static int do_new_mount(struct path *path, char *type, int flags,
 			int mnt_flags, char *name, void *data)
 {
 	struct vfsmount *mnt;
 
-	if (!type || !memchr(type, 0, PAGE_SIZE))
+	if (!type)
 		return -EINVAL;
 
 	/* we need capabilities... */
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
+	lock_kernel();
 	mnt = do_kern_mount(type, flags, name, data);
+	unlock_kernel();
 	if (IS_ERR(mnt))
 		return PTR_ERR(mnt);
 
-	return do_add_mount(mnt, nd, mnt_flags, NULL);
+	return do_add_mount(mnt, path, mnt_flags, NULL);
 }
 
 /*
  * add a mount into a namespace's mount tree
  * - provide the option of adding the new mount to an expiration list
  */
-int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
+int do_add_mount(struct vfsmount *newmnt, struct path *path,
 		 int mnt_flags, struct list_head *fslist)
 {
 	int err;
 
+	mnt_flags &= ~(MNT_SHARED | MNT_WRITE_HOLD);
+
 	down_write(&namespace_sem);
 	/* Something was mounted here while we slept */
-	while (d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry))
+	while (d_mountpoint(path->dentry) &&
+	       follow_down(path))
 		;
 	err = -EINVAL;
-	if (!check_mnt(nd->mnt))
+	if (!(mnt_flags & MNT_SHRINKABLE) && !check_mnt(path->mnt))
 		goto unlock;
 
 	/* Refuse the same filesystem on the same mount point */
 	err = -EBUSY;
-	if (nd->mnt->mnt_sb == newmnt->mnt_sb &&
-	    nd->mnt->mnt_root == nd->dentry)
+	if (path->mnt->mnt_sb == newmnt->mnt_sb &&
+	    path->mnt->mnt_root == path->dentry)
 		goto unlock;
 
 	err = -EINVAL;
@@ -1130,15 +1693,12 @@ int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd,
 		goto unlock;
 
 	newmnt->mnt_flags = mnt_flags;
-	if ((err = graft_tree(newmnt, nd)))
+	if ((err = graft_tree(newmnt, path)))
 		goto unlock;
 
-	if (fslist) {
-		/* add to the specified expiration list */
-		spin_lock(&vfsmount_lock);
+	if (fslist) /* add to the specified expiration list */
 		list_add_tail(&newmnt->mnt_expire, fslist);
-		spin_unlock(&vfsmount_lock);
-	}
+
 	up_write(&namespace_sem);
 	return 0;
 
@@ -1150,75 +1710,6 @@ unlock:
 
 EXPORT_SYMBOL_GPL(do_add_mount);
 
-static void expire_mount(struct vfsmount *mnt, struct list_head *mounts,
-				struct list_head *umounts)
-{
-	spin_lock(&vfsmount_lock);
-
-	/*
-	 * Check if mount is still attached, if not, let whoever holds it deal
-	 * with the sucker
-	 */
-	if (mnt->mnt_parent == mnt) {
-		spin_unlock(&vfsmount_lock);
-		return;
-	}
-
-	/*
-	 * Check that it is still dead: the count should now be 2 - as
-	 * contributed by the vfsmount parent and the mntget above
-	 */
-	if (!propagate_mount_busy(mnt, 2)) {
-		/* delete from the namespace */
-		touch_mnt_namespace(mnt->mnt_ns);
-		list_del_init(&mnt->mnt_list);
-		mnt->mnt_ns = NULL;
-		umount_tree(mnt, 1, umounts);
-		spin_unlock(&vfsmount_lock);
-	} else {
-		/*
-		 * Someone brought it back to life whilst we didn't have any
-		 * locks held so return it to the expiration list
-		 */
-		list_add_tail(&mnt->mnt_expire, mounts);
-		spin_unlock(&vfsmount_lock);
-	}
-}
-
-/*
- * go through the vfsmounts we've just consigned to the graveyard to
- * - check that they're still dead
- * - delete the vfsmount from the appropriate namespace under lock
- * - dispose of the corpse
- */
-static void expire_mount_list(struct list_head *graveyard, struct list_head *mounts)
-{
-	struct mnt_namespace *ns;
-	struct vfsmount *mnt;
-
-	while (!list_empty(graveyard)) {
-		LIST_HEAD(umounts);
-		mnt = list_first_entry(graveyard, struct vfsmount, mnt_expire);
-		list_del_init(&mnt->mnt_expire);
-
-		/* don't do anything if the namespace is dead - all the
-		 * vfsmounts from it are going away anyway */
-		ns = mnt->mnt_ns;
-		if (!ns || !ns->root)
-			continue;
-		get_mnt_ns(ns);
-
-		spin_unlock(&vfsmount_lock);
-		down_write(&namespace_sem);
-		expire_mount(mnt, mounts, &umounts);
-		up_write(&namespace_sem);
-		release_mounts(&umounts);
-		mntput(mnt);
-		put_mnt_ns(ns);
-		spin_lock(&vfsmount_lock);
-	}
-}
-
 /*
  * process a list of expirable mountpoints with the intent of discarding any
  * mountpoints that aren't in use and haven't been touched since last we came
@@ -1228,10 +1719,12 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 {
 	struct vfsmount *mnt, *next;
 	LIST_HEAD(graveyard);
+	LIST_HEAD(umounts);
 
 	if (list_empty(mounts))
 		return;
 
+	down_write(&namespace_sem);
 	spin_lock(&vfsmount_lock);
 
 	/* extract from the expiration list every vfsmount that matches the
@@ -1242,16 +1735,19 @@ void mark_mounts_for_expiry(struct list_head *mounts)
 	 */
 	list_for_each_entry_safe(mnt, next, mounts, mnt_expire) {
 		if (!xchg(&mnt->mnt_expiry_mark, 1) ||
-		    atomic_read(&mnt->mnt_count) != 1)
+			propagate_mount_busy(mnt, 1))
 			continue;
-
-		mntget(mnt);
 		list_move(&mnt->mnt_expire, &graveyard);
 	}
-
-	expire_mount_list(&graveyard, mounts);
-
+	while (!list_empty(&graveyard)) {
+		mnt = list_first_entry(&graveyard, struct vfsmount, mnt_expire);
+		touch_mnt_namespace(mnt->mnt_ns);
+		umount_tree(mnt, 1, &umounts);
+	}
 	spin_unlock(&vfsmount_lock);
+	up_write(&namespace_sem);
+
+	release_mounts(&umounts);
 }
 
 EXPORT_SYMBOL_GPL(mark_mounts_for_expiry);
@@ -1287,7 +1783,6 @@ resume:
 		}
 
 		if (!propagate_mount_busy(mnt, 1)) {
-			mntget(mnt);
 			list_move_tail(&mnt->mnt_expire, graveyard);
 			found++;
 		}
@@ -1307,22 +1802,22 @@ resume:
  * process a list of expirable mountpoints with the intent of discarding any
  * submounts of a specific parent mountpoint
  */
-void shrink_submounts(struct vfsmount *mountpoint, struct list_head *mounts)
+static void shrink_submounts(struct vfsmount *mnt, struct list_head *umounts)
 {
 	LIST_HEAD(graveyard);
-	int found;
-
-	spin_lock(&vfsmount_lock);
+	struct vfsmount *m;
 
 	/* extract submounts of 'mountpoint' from the expiration list */
-	while ((found = select_submounts(mountpoint, &graveyard)) != 0)
-		expire_mount_list(&graveyard, mounts);
-
-	spin_unlock(&vfsmount_lock);
+	while (select_submounts(mnt, &graveyard)) {
+		while (!list_empty(&graveyard)) {
+			m = list_first_entry(&graveyard, struct vfsmount,
+						mnt_expire);
+			touch_mnt_namespace(m->mnt_ns);
+			umount_tree(m, 1, umounts);
+		}
+	}
 }
 
-EXPORT_SYMBOL_GPL(shrink_submounts);
-
 /*
  * Some copy_from_user() implementations do not return the exact number of
  * bytes remaining to copy on a fault.  But copy_mount_options() requires that.
@@ -1384,6 +1879,23 @@ int copy_mount_options(const void __user * data, unsigned long *where)
 	return 0;
 }
 
+int copy_mount_string(const void __user *data, char **where)
+{
+	char *tmp;
+
+	if (!data) {
+		*where = NULL;
+		return 0;
+	}
+
+	tmp = strndup_user(data, PAGE_SIZE);
+	if (IS_ERR(tmp))
+		return PTR_ERR(tmp);
+
+	*where = tmp;
+	return 0;
+}
+
 /*
  * Flags is a 32-bit value that allows up to 31 non-fs dependent flags to
  * be given to the mount() call (ie: read-only, no-dev, no-suid etc).
@@ -1401,7 +1913,7 @@ int copy_mount_options(const void __user * data, unsigned long *where)
 long do_mount(char *dev_name, char *dir_name, char *type_page,
 		  unsigned long flags, void *data_page)
 {
-	struct nameidata nd;
+	struct path path;
 	int retval = 0;
 	int mnt_flags = 0;
 
@@ -1413,12 +1925,24 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
 
 	if (!dir_name || !*dir_name || !memchr(dir_name, 0, PAGE_SIZE))
 		return -EINVAL;
-	if (dev_name && !memchr(dev_name, 0, PAGE_SIZE))
-		return -EINVAL;
 
 	if (data_page)
 		((char *)data_page)[PAGE_SIZE - 1] = 0;
 
+	/* ... and get the mountpoint */
+	retval = kern_path(dir_name, LOOKUP_FOLLOW, &path);
+	if (retval)
+		return retval;
+
+	retval = security_sb_mount(dev_name, &path,
+				   type_page, flags, data_page);
+	if (retval)
+		goto dput_out;
+
+	/* Default to relatime unless overriden */
+	if (!(flags & MS_NOATIME))
+		mnt_flags |= MNT_RELATIME;
+
 	/* Separate the per-mountpoint flags */
 	if (flags & MS_NOSUID)
 		mnt_flags |= MNT_NOSUID;
@@ -1430,57 +1954,61 @@ long do_mount(char *dev_name, char *dir_name, char *type_page,
 		mnt_flags |= MNT_NOATIME;
 	if (flags & MS_NODIRATIME)
 		mnt_flags |= MNT_NODIRATIME;
-	if (flags & MS_RELATIME)
-		mnt_flags |= MNT_RELATIME;
+	if (flags & MS_STRICTATIME)
+		mnt_flags &= ~(MNT_RELATIME | MNT_NOATIME);
+	if (flags & MS_RDONLY)
+		mnt_flags |= MNT_READONLY;
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE |
-		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT);
-
-	/* ... and get the mountpoint */
-	retval = path_lookup(dir_name, LOOKUP_FOLLOW, &nd);
-	if (retval)
-		return retval;
-
-	retval = security_sb_mount(dev_name, &nd, type_page, flags, data_page);
-	if (retval)
-		goto dput_out;
+		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
+		   MS_STRICTATIME);
 
 	if (flags & MS_REMOUNT)
-		retval = do_remount(&nd, flags & ~MS_REMOUNT, mnt_flags,
+		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
 				    data_page);
 	else if (flags & MS_BIND)
-		retval = do_loopback(&nd, dev_name, flags & MS_REC);
+		retval = do_loopback(&path, dev_name, flags & MS_REC);
 	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
-		retval = do_change_type(&nd, flags);
+		retval = do_change_type(&path, flags);
 	else if (flags & MS_MOVE)
-		retval = do_move_mount(&nd, dev_name);
+		retval = do_move_mount(&path, dev_name);
 	else
-		retval = do_new_mount(&nd, type_page, flags, mnt_flags,
+		retval = do_new_mount(&path, type_page, flags, mnt_flags,
 				      dev_name, data_page);
 dput_out:
-	path_release(&nd);
+	path_put(&path);
 	return retval;
 }
 
-/*
- * Allocate a new namespace structure and populate it with contents
- * copied from the namespace of the passed in task structure.
- */
-static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
-		struct fs_struct *fs)
+static struct mnt_namespace *alloc_mnt_ns(void)
 {
 	struct mnt_namespace *new_ns;
-	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL, *altrootmnt = NULL;
-	struct vfsmount *p, *q;
 
 	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
-
 	atomic_set(&new_ns->count, 1);
+	new_ns->root = NULL;
 	INIT_LIST_HEAD(&new_ns->list);
 	init_waitqueue_head(&new_ns->poll);
 	new_ns->event = 0;
+	return new_ns;
+}
+
+/*
+ * Allocate a new namespace structure and populate it with contents
+ * copied from the namespace of the passed in task structure.
+ */
+static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
+		struct fs_struct *fs)
+{
+	struct mnt_namespace *new_ns;
+	struct vfsmount *rootmnt = NULL, *pwdmnt = NULL;
+	struct vfsmount *p, *q;
+
+	new_ns = alloc_mnt_ns();
+	if (IS_ERR(new_ns))
+		return new_ns;
 
 	down_write(&namespace_sem);
 	/* First pass: copy the tree topology */
@@ -1489,7 +2017,7 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	if (!new_ns->root) {
 		up_write(&namespace_sem);
 		kfree(new_ns);
-		return ERR_PTR(-ENOMEM);;
+		return ERR_PTR(-ENOMEM);
 	}
 	spin_lock(&vfsmount_lock);
 	list_add_tail(&new_ns->list, &new_ns->root->mnt_list);
@@ -1505,17 +2033,13 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 	while (p) {
 		q->mnt_ns = new_ns;
 		if (fs) {
-			if (p == fs->rootmnt) {
+			if (p == fs->root.mnt) {
 				rootmnt = p;
-				fs->rootmnt = mntget(q);
+				fs->root.mnt = mntget(q);
 			}
-			if (p == fs->pwdmnt) {
+			if (p == fs->pwd.mnt) {
 				pwdmnt = p;
-				fs->pwdmnt = mntget(q);
-			}
-			if (p == fs->altrootmnt) {
-				altrootmnt = p;
-				fs->altrootmnt = mntget(q);
+				fs->pwd.mnt = mntget(q);
 			}
 		}
 		p = next_mnt(p, mnt_ns->root);
@@ -1527,8 +2051,6 @@ static struct mnt_namespace *dup_mnt_ns(struct mnt_namespace *mnt_ns,
 		mntput(rootmnt);
 	if (pwdmnt)
 		mntput(pwdmnt);
-	if (altrootmnt)
-		mntput(altrootmnt);
 
 	return new_ns;
 }
@@ -1550,115 +2072,63 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	return new_ns;
 }
 
-asmlinkage long sys_mount(char __user * dev_name, char __user * dir_name,
-			  char __user * type, unsigned long flags,
-			  void __user * data)
+/**
+ * create_mnt_ns - creates a private namespace and adds a root filesystem
+ * @mnt: pointer to the new root filesystem mountpoint
+ */
+struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
 {
-	int retval;
-	unsigned long data_page;
-	unsigned long type_page;
-	unsigned long dev_page;
-	char *dir_page;
-
-	retval = copy_mount_options(type, &type_page);
-	if (retval < 0)
-		return retval;
-
-	dir_page = getname(dir_name);
-	retval = PTR_ERR(dir_page);
-	if (IS_ERR(dir_page))
-		goto out1;
-
-	retval = copy_mount_options(dev_name, &dev_page);
-	if (retval < 0)
-		goto out2;
+	struct mnt_namespace *new_ns;
 
-	retval = copy_mount_options(data, &data_page);
-	if (retval < 0)
-		goto out3;
+	new_ns = alloc_mnt_ns();
+	if (!IS_ERR(new_ns)) {
+		mnt->mnt_ns = new_ns;
+		new_ns->root = mnt;
+		list_add(&new_ns->list, &new_ns->root->mnt_list);
+	}
+	return new_ns;
+}
+EXPORT_SYMBOL(create_mnt_ns);
 
-	lock_kernel();
-	retval = do_mount((char *)dev_page, dir_page, (char *)type_page,
-			  flags, (void *)data_page);
-	unlock_kernel();
-	free_page(data_page);
+SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
+		char __user *, type, unsigned long, flags, void __user *, data)
+{
+	int ret;
+	char *kernel_type;
+	char *kernel_dir;
+	char *kernel_dev;
+	unsigned long data_page;
 
-out3:
-	free_page(dev_page);
-out2:
-	putname(dir_page);
-out1:
-	free_page(type_page);
-	return retval;
-}
+	ret = copy_mount_string(type, &kernel_type);
+	if (ret < 0)
+		goto out_type;
 
-/*
- * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
- * It can block. Requires the big lock held.
- */
-void set_fs_root(struct fs_struct *fs, struct vfsmount *mnt,
-		 struct dentry *dentry)
-{
-	struct dentry *old_root;
-	struct vfsmount *old_rootmnt;
-	write_lock(&fs->lock);
-	old_root = fs->root;
-	old_rootmnt = fs->rootmnt;
-	fs->rootmnt = mntget(mnt);
-	fs->root = dget(dentry);
-	write_unlock(&fs->lock);
-	if (old_root) {
-		dput(old_root);
-		mntput(old_rootmnt);
+	kernel_dir = getname(dir_name);
+	if (IS_ERR(kernel_dir)) {
+		ret = PTR_ERR(kernel_dir);
+		goto out_dir;
 	}
-}
 
-/*
- * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
- * It can block. Requires the big lock held.
- */
-void set_fs_pwd(struct fs_struct *fs, struct vfsmount *mnt,
-		struct dentry *dentry)
-{
-	struct dentry *old_pwd;
-	struct vfsmount *old_pwdmnt;
-
-	write_lock(&fs->lock);
-	old_pwd = fs->pwd;
-	old_pwdmnt = fs->pwdmnt;
-	fs->pwdmnt = mntget(mnt);
-	fs->pwd = dget(dentry);
-	write_unlock(&fs->lock);
-
-	if (old_pwd) {
-		dput(old_pwd);
-		mntput(old_pwdmnt);
-	}
-}
+	ret = copy_mount_string(dev_name, &kernel_dev);
+	if (ret < 0)
+		goto out_dev;
 
-static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd)
-{
-	struct task_struct *g, *p;
-	struct fs_struct *fs;
+	ret = copy_mount_options(data, &data_page);
+	if (ret < 0)
+		goto out_data;
 
-	read_lock(&tasklist_lock);
-	do_each_thread(g, p) {
-		task_lock(p);
-		fs = p->fs;
-		if (fs) {
-			atomic_inc(&fs->count);
-			task_unlock(p);
-			if (fs->root == old_nd->dentry
-			    && fs->rootmnt == old_nd->mnt)
-				set_fs_root(fs, new_nd->mnt, new_nd->dentry);
-			if (fs->pwd == old_nd->dentry
-			    && fs->pwdmnt == old_nd->mnt)
-				set_fs_pwd(fs, new_nd->mnt, new_nd->dentry);
-			put_fs_struct(fs);
-		} else
-			task_unlock(p);
-	} while_each_thread(g, p);
-	read_unlock(&tasklist_lock);
+	ret = do_mount(kernel_dev, kernel_dir, kernel_type, flags,
+		(void *) data_page);
+
+	free_page(data_page);
+out_data:
+	kfree(kernel_dev);
+out_dev:
+	putname(kernel_dir);
+out_dir:
+	kfree(kernel_type);
+out_type:
+	return ret;
 }
 
 /*
@@ -1686,102 +2156,102 @@ static void chroot_fs_refs(struct nameidata *old_nd, struct nameidata *new_nd)
  *    though, so you may need to say mount --bind /nfs/my_root /nfs/my_root
  *    first.
  */
-asmlinkage long sys_pivot_root(const char __user * new_root,
-			       const char __user * put_old)
+SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
+		const char __user *, put_old)
 {
 	struct vfsmount *tmp;
-	struct nameidata new_nd, old_nd, parent_nd, root_parent, user_nd;
+	struct path new, old, parent_path, root_parent, root;
 	int error;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	lock_kernel();
-
-	error = __user_walk(new_root, LOOKUP_FOLLOW | LOOKUP_DIRECTORY,
-			    &new_nd);
+	error = user_path_dir(new_root, &new);
 	if (error)
 		goto out0;
 	error = -EINVAL;
-	if (!check_mnt(new_nd.mnt))
+	if (!check_mnt(new.mnt))
 		goto out1;
 
-	error = __user_walk(put_old, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old_nd);
+	error = user_path_dir(put_old, &old);
 	if (error)
 		goto out1;
 
-	error = security_sb_pivotroot(&old_nd, &new_nd);
+	error = security_sb_pivotroot(&old, &new);
 	if (error) {
-		path_release(&old_nd);
+		path_put(&old);
 		goto out1;
 	}
 
 	read_lock(&current->fs->lock);
-	user_nd.mnt = mntget(current->fs->rootmnt);
-	user_nd.dentry = dget(current->fs->root);
+	root = current->fs->root;
+	path_get(&current->fs->root);
 	read_unlock(&current->fs->lock);
 	down_write(&namespace_sem);
-	mutex_lock(&old_nd.dentry->d_inode->i_mutex);
+	mutex_lock(&old.dentry->d_inode->i_mutex);
 	error = -EINVAL;
-	if (IS_MNT_SHARED(old_nd.mnt) ||
-		IS_MNT_SHARED(new_nd.mnt->mnt_parent) ||
-		IS_MNT_SHARED(user_nd.mnt->mnt_parent))
+	if (IS_MNT_SHARED(old.mnt) ||
+		IS_MNT_SHARED(new.mnt->mnt_parent) ||
+		IS_MNT_SHARED(root.mnt->mnt_parent))
 		goto out2;
-	if (!check_mnt(user_nd.mnt))
+	if (!check_mnt(root.mnt))
 		goto out2;
 	error = -ENOENT;
-	if (IS_DEADDIR(new_nd.dentry->d_inode))
+	if (IS_DEADDIR(new.dentry->d_inode))
 		goto out2;
-	if (d_unhashed(new_nd.dentry) && !IS_ROOT(new_nd.dentry))
+	if (d_unlinked(new.dentry))
 		goto out2;
-	if (d_unhashed(old_nd.dentry) && !IS_ROOT(old_nd.dentry))
+	if (d_unlinked(old.dentry))
 		goto out2;
 	error = -EBUSY;
-	if (new_nd.mnt == user_nd.mnt || old_nd.mnt == user_nd.mnt)
+	if (new.mnt == root.mnt ||
+	    old.mnt == root.mnt)
 		goto out2; /* loop, on the same file system  */
 	error = -EINVAL;
-	if (user_nd.mnt->mnt_root != user_nd.dentry)
+	if (root.mnt->mnt_root != root.dentry)
 		goto out2; /* not a mountpoint */
-	if (user_nd.mnt->mnt_parent == user_nd.mnt)
+	if (root.mnt->mnt_parent == root.mnt)
 		goto out2; /* not attached */
-	if (new_nd.mnt->mnt_root != new_nd.dentry)
+	if (new.mnt->mnt_root != new.dentry)
 		goto out2; /* not a mountpoint */
-	if (new_nd.mnt->mnt_parent == new_nd.mnt)
+	if (new.mnt->mnt_parent == new.mnt)
 		goto out2; /* not attached */
-	tmp = old_nd.mnt; /* make sure we can reach put_old from new_root */
+	/* make sure we can reach put_old from new_root */
+	tmp = old.mnt;
 	spin_lock(&vfsmount_lock);
-	if (tmp != new_nd.mnt) {
+	if (tmp != new.mnt) {
 		for (;;) {
 			if (tmp->mnt_parent == tmp)
 				goto out3; /* already mounted on put_old */
-			if (tmp->mnt_parent == new_nd.mnt)
+			if (tmp->mnt_parent == new.mnt)
 				break;
 			tmp = tmp->mnt_parent;
 		}
-		if (!is_subdir(tmp->mnt_mountpoint, new_nd.dentry))
+		if (!is_subdir(tmp->mnt_mountpoint, new.dentry))
 			goto out3;
-	} else if (!is_subdir(old_nd.dentry, new_nd.dentry))
+	} else if (!is_subdir(old.dentry, new.dentry))
 		goto out3;
-	detach_mnt(new_nd.mnt, &parent_nd);
-	detach_mnt(user_nd.mnt, &root_parent);
-	attach_mnt(user_nd.mnt, &old_nd);     /* mount old root on put_old */
-	attach_mnt(new_nd.mnt, &root_parent); /* mount new_root on / */
+	detach_mnt(new.mnt, &parent_path);
+	detach_mnt(root.mnt, &root_parent);
+	/* mount old root on put_old */
+	attach_mnt(root.mnt, &old);
+	/* mount new_root on / */
+	attach_mnt(new.mnt, &root_parent);
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	spin_unlock(&vfsmount_lock);
-	chroot_fs_refs(&user_nd, &new_nd);
-	security_sb_post_pivotroot(&user_nd, &new_nd);
+	chroot_fs_refs(&root, &new);
+	security_sb_post_pivotroot(&root, &new);
 	error = 0;
-	path_release(&root_parent);
-	path_release(&parent_nd);
+	path_put(&root_parent);
+	path_put(&parent_path);
 out2:
-	mutex_unlock(&old_nd.dentry->d_inode->i_mutex);
+	mutex_unlock(&old.dentry->d_inode->i_mutex);
 	up_write(&namespace_sem);
-	path_release(&user_nd);
-	path_release(&old_nd);
+	path_put(&root);
+	path_put(&old);
 out1:
-	path_release(&new_nd);
+	path_put(&new);
 out0:
-	unlock_kernel();
 	return error;
 out3:
 	spin_unlock(&vfsmount_lock);
@@ -1792,26 +2262,23 @@ static void __init init_mount_tree(void)
 {
 	struct vfsmount *mnt;
 	struct mnt_namespace *ns;
+	struct path root;
 
 	mnt = do_kern_mount("rootfs", 0, "rootfs", NULL);
 	if (IS_ERR(mnt))
 		panic("Can't create rootfs");
-	ns = kmalloc(sizeof(*ns), GFP_KERNEL);
-	if (!ns)
+	ns = create_mnt_ns(mnt);
+	if (IS_ERR(ns))
 		panic("Can't allocate initial namespace");
-	atomic_set(&ns->count, 1);
-	INIT_LIST_HEAD(&ns->list);
-	init_waitqueue_head(&ns->poll);
-	ns->event = 0;
-	list_add(&mnt->mnt_list, &ns->list);
-	ns->root = mnt;
-	mnt->mnt_ns = ns;
 
 	init_task.nsproxy->mnt_ns = ns;
 	get_mnt_ns(ns);
 
-	set_fs_pwd(current->fs, ns->root, ns->root->mnt_root);
-	set_fs_root(current->fs, ns->root, ns->root->mnt_root);
+	root.mnt = ns->root;
+	root.dentry = ns->root->mnt_root;
+
+	set_fs_pwd(current->fs, &root);
+	set_fs_root(current->fs, &root);
 }
 
 void __init mnt_init(void)
@@ -1837,18 +2304,22 @@ void __init mnt_init(void)
 	err = sysfs_init();
 	if (err)
 		printk(KERN_WARNING "%s: sysfs_init error: %d\n",
-			__FUNCTION__, err);
+			__func__, err);
 	fs_kobj = kobject_create_and_add("fs", NULL);
 	if (!fs_kobj)
-		printk(KERN_WARNING "%s: kobj create error\n", __FUNCTION__);
+		printk(KERN_WARNING "%s: kobj create error\n", __func__);
 	init_rootfs();
 	init_mount_tree();
 }
 
-void __put_mnt_ns(struct mnt_namespace *ns)
+void put_mnt_ns(struct mnt_namespace *ns)
 {
-	struct vfsmount *root = ns->root;
+	struct vfsmount *root;
 	LIST_HEAD(umount_list);
+
+	if (!atomic_dec_and_lock(&ns->count, &vfsmount_lock))
+		return;
+	root = ns->root;
 	ns->root = NULL;
 	spin_unlock(&vfsmount_lock);
 	down_write(&namespace_sem);
@@ -1859,3 +2330,4 @@ void __put_mnt_ns(struct mnt_namespace *ns)
 	release_mounts(&umount_list);
 	kfree(ns);
 }
+EXPORT_SYMBOL(put_mnt_ns);