Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/fs/namespace.c b/fs/namespace.c
index 1fce41b..2adfe7b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1,8 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  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.
@@ -20,12 +20,16 @@
 #include <linux/init.h>		/* init_rootfs */
 #include <linux/fs_struct.h>	/* get_fs_root et.al. */
 #include <linux/fsnotify.h>	/* fsnotify_vfsmount_delete */
+#include <linux/file.h>
 #include <linux/uaccess.h>
 #include <linux/proc_ns.h>
 #include <linux/magic.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/task_work.h>
 #include <linux/sched/task.h>
+#include <uapi/linux/mount.h>
+#include <linux/fs_context.h>
+#include <linux/shmem_fs.h>
 
 #include "pnode.h"
 #include "internal.h"
@@ -66,6 +70,8 @@
 static struct hlist_head *mountpoint_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
 static DECLARE_RWSEM(namespace_sem);
+static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
+static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
 
 /* /sys/fs */
 struct kobject *fs_kobj;
@@ -166,14 +172,6 @@
 #endif
 }
 
-static void drop_mountpoint(struct fs_pin *p)
-{
-	struct mount *m = container_of(p, struct mount, mnt_umount);
-	dput(m->mnt_ex_mountpoint);
-	pin_remove(p);
-	mntput(&m->mnt);
-}
-
 static struct mount *alloc_vfsmnt(const char *name)
 {
 	struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
@@ -211,7 +209,7 @@
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
 		INIT_LIST_HEAD(&mnt->mnt_umounting);
-		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
+		INIT_HLIST_HEAD(&mnt->mnt_stuck_children);
 	}
 	return mnt;
 
@@ -245,13 +243,9 @@
  * mnt_want/drop_write() will _keep_ the filesystem
  * r/w.
  */
-int __mnt_is_readonly(struct vfsmount *mnt)
+bool __mnt_is_readonly(struct vfsmount *mnt)
 {
-	if (mnt->mnt_flags & MNT_READONLY)
-		return 1;
-	if (sb_rdonly(mnt->mnt_sb))
-		return 1;
-	return 0;
+	return (mnt->mnt_flags & MNT_READONLY) || sb_rdonly(mnt->mnt_sb);
 }
 EXPORT_SYMBOL_GPL(__mnt_is_readonly);
 
@@ -507,11 +501,12 @@
 	return ret;
 }
 
-static void __mnt_unmake_readonly(struct mount *mnt)
+static int __mnt_unmake_readonly(struct mount *mnt)
 {
 	lock_mount_hash();
 	mnt->mnt.mnt_flags &= ~MNT_READONLY;
 	unlock_mount_hash();
+	return 0;
 }
 
 int sb_prepare_remount_readonly(struct super_block *sb)
@@ -739,7 +734,7 @@
 
 	/* Add the new mountpoint to the hash table */
 	read_seqlock_excl(&mount_lock);
-	new->m_dentry = dentry;
+	new->m_dentry = dget(dentry);
 	new->m_count = 1;
 	hlist_add_head(&new->m_hash, mp_hash(dentry));
 	INIT_HLIST_HEAD(&new->m_list);
@@ -752,7 +747,11 @@
 	return mp;
 }
 
-static void put_mountpoint(struct mountpoint *mp)
+/*
+ * vfsmount lock must be held.  Additionally, the caller is responsible
+ * for serializing calls for given disposal list.
+ */
+static void __put_mountpoint(struct mountpoint *mp, struct list_head *list)
 {
 	if (!--mp->m_count) {
 		struct dentry *dentry = mp->m_dentry;
@@ -760,11 +759,18 @@
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
+		dput_to_list(dentry, list);
 		hlist_del(&mp->m_hash);
 		kfree(mp);
 	}
 }
 
+/* called with namespace_lock and vfsmount lock */
+static void put_mountpoint(struct mountpoint *mp)
+{
+	__put_mountpoint(mp, &ex_mountpoints);
+}
+
 static inline int check_mnt(struct mount *mnt)
 {
 	return mnt->mnt_ns == current->nsproxy->mnt_ns;
@@ -795,25 +801,17 @@
 /*
  * vfsmount lock must be held for write
  */
-static void unhash_mnt(struct mount *mnt)
+static struct mountpoint *unhash_mnt(struct mount *mnt)
 {
+	struct mountpoint *mp;
 	mnt->mnt_parent = mnt;
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
 	hlist_del_init_rcu(&mnt->mnt_hash);
 	hlist_del_init(&mnt->mnt_mp_list);
-	put_mountpoint(mnt->mnt_mp);
+	mp = mnt->mnt_mp;
 	mnt->mnt_mp = NULL;
-}
-
-/*
- * vfsmount lock must be held for write
- */
-static void detach_mnt(struct mount *mnt, struct path *old_path)
-{
-	old_path->dentry = mnt->mnt_mountpoint;
-	old_path->mnt = &mnt->mnt_parent->mnt;
-	unhash_mnt(mnt);
+	return mp;
 }
 
 /*
@@ -821,9 +819,7 @@
  */
 static void umount_mnt(struct mount *mnt)
 {
-	/* old mountpoint will be dropped when we can do that */
-	mnt->mnt_ex_mountpoint = mnt->mnt_mountpoint;
-	unhash_mnt(mnt);
+	put_mountpoint(unhash_mnt(mnt));
 }
 
 /*
@@ -835,7 +831,7 @@
 {
 	mp->m_count++;
 	mnt_add_count(mnt, 1);	/* essentially, that's mntget */
-	child_mnt->mnt_mountpoint = dget(mp->m_dentry);
+	child_mnt->mnt_mountpoint = mp->m_dentry;
 	child_mnt->mnt_parent = mnt;
 	child_mnt->mnt_mp = mp;
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
@@ -862,7 +858,6 @@
 void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
 	struct mountpoint *old_mp = mnt->mnt_mp;
-	struct dentry *old_mountpoint = mnt->mnt_mountpoint;
 	struct mount *old_parent = mnt->mnt_parent;
 
 	list_del_init(&mnt->mnt_child);
@@ -872,22 +867,6 @@
 	attach_mnt(mnt, parent, mp);
 
 	put_mountpoint(old_mp);
-
-	/*
-	 * Safely avoid even the suggestion this code might sleep or
-	 * lock the mount hash by taking advantage of the knowledge that
-	 * mnt_change_mountpoint will not release the final reference
-	 * to a mountpoint.
-	 *
-	 * During mounting, the mount passed in as the parent mount will
-	 * continue to use the old mountpoint and during unmounting, the
-	 * old mountpoint will continue to exist until namespace_unlock,
-	 * which happens well after mnt_change_mountpoint.
-	 */
-	spin_lock(&old_mountpoint->d_lock);
-	old_mountpoint->d_lockref.count--;
-	spin_unlock(&old_mountpoint->d_lock);
-
 	mnt_add_count(old_parent, -1);
 }
 
@@ -942,38 +921,81 @@
 	return p;
 }
 
-struct vfsmount *
-vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data)
+/**
+ * vfs_create_mount - Create a mount for a configured superblock
+ * @fc: The configuration context with the superblock attached
+ *
+ * Create a mount to an already configured superblock.  If necessary, the
+ * caller should invoke vfs_get_tree() before calling this.
+ *
+ * Note that this does not attach the mount to anything.
+ */
+struct vfsmount *vfs_create_mount(struct fs_context *fc)
 {
 	struct mount *mnt;
-	struct dentry *root;
 
-	if (!type)
-		return ERR_PTR(-ENODEV);
+	if (!fc->root)
+		return ERR_PTR(-EINVAL);
 
-	mnt = alloc_vfsmnt(name);
+	mnt = alloc_vfsmnt(fc->source ?: "none");
 	if (!mnt)
 		return ERR_PTR(-ENOMEM);
 
-	if (flags & SB_KERNMOUNT)
+	if (fc->sb_flags & SB_KERNMOUNT)
 		mnt->mnt.mnt_flags = MNT_INTERNAL;
 
-	root = mount_fs(type, flags, name, data);
-	if (IS_ERR(root)) {
-		mnt_free_id(mnt);
-		free_vfsmnt(mnt);
-		return ERR_CAST(root);
-	}
+	atomic_inc(&fc->root->d_sb->s_active);
+	mnt->mnt.mnt_sb		= fc->root->d_sb;
+	mnt->mnt.mnt_root	= dget(fc->root);
+	mnt->mnt_mountpoint	= mnt->mnt.mnt_root;
+	mnt->mnt_parent		= mnt;
 
-	mnt->mnt.mnt_root = root;
-	mnt->mnt.mnt_sb = root->d_sb;
-	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
-	mnt->mnt_parent = mnt;
 	lock_mount_hash();
-	list_add_tail(&mnt->mnt_instance, &root->d_sb->s_mounts);
+	list_add_tail(&mnt->mnt_instance, &mnt->mnt.mnt_sb->s_mounts);
 	unlock_mount_hash();
 	return &mnt->mnt;
 }
+EXPORT_SYMBOL(vfs_create_mount);
+
+struct vfsmount *fc_mount(struct fs_context *fc)
+{
+	int err = vfs_get_tree(fc);
+	if (!err) {
+		up_write(&fc->root->d_sb->s_umount);
+		return vfs_create_mount(fc);
+	}
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL(fc_mount);
+
+struct vfsmount *vfs_kern_mount(struct file_system_type *type,
+				int flags, const char *name,
+				void *data)
+{
+	struct fs_context *fc;
+	struct vfsmount *mnt;
+	int ret = 0;
+
+	if (!type)
+		return ERR_PTR(-EINVAL);
+
+	fc = fs_context_for_mount(type, flags);
+	if (IS_ERR(fc))
+		return ERR_CAST(fc);
+
+	if (name)
+		ret = vfs_parse_fs_string(fc, "source",
+					  name, strlen(name));
+	if (!ret)
+		ret = parse_monolithic_mount_data(fc, data);
+	if (!ret)
+		mnt = fc_mount(fc);
+	else
+		mnt = ERR_PTR(ret);
+
+	put_fs_context(fc);
+	return mnt;
+}
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
 struct vfsmount *
@@ -1015,27 +1037,6 @@
 
 	mnt->mnt.mnt_flags = old->mnt.mnt_flags;
 	mnt->mnt.mnt_flags &= ~(MNT_WRITE_HOLD|MNT_MARKED|MNT_INTERNAL);
-	/* Don't allow unprivileged users to change mount flags */
-	if (flag & CL_UNPRIVILEGED) {
-		mnt->mnt.mnt_flags |= MNT_LOCK_ATIME;
-
-		if (mnt->mnt.mnt_flags & MNT_READONLY)
-			mnt->mnt.mnt_flags |= MNT_LOCK_READONLY;
-
-		if (mnt->mnt.mnt_flags & MNT_NODEV)
-			mnt->mnt.mnt_flags |= MNT_LOCK_NODEV;
-
-		if (mnt->mnt.mnt_flags & MNT_NOSUID)
-			mnt->mnt.mnt_flags |= MNT_LOCK_NOSUID;
-
-		if (mnt->mnt.mnt_flags & MNT_NOEXEC)
-			mnt->mnt.mnt_flags |= MNT_LOCK_NOEXEC;
-	}
-
-	/* Don't allow unprivileged users to reveal what is under a mount */
-	if ((flag & CL_UNPRIVILEGED) &&
-	    (!(flag & CL_EXPIRE) || list_empty(&old->mnt_expire)))
-		mnt->mnt.mnt_flags |= MNT_LOCKED;
 
 	atomic_inc(&sb->s_active);
 	mnt->mnt.mnt_sb = sb;
@@ -1080,19 +1081,22 @@
 
 static void cleanup_mnt(struct mount *mnt)
 {
+	struct hlist_node *p;
+	struct mount *m;
 	/*
-	 * 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.
-	 */
-	/*
+	 * The warning here 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.
 	 * The locking used to deal with mnt_count decrement provides barriers,
 	 * so mnt_get_writers() below is safe.
 	 */
 	WARN_ON(mnt_get_writers(mnt));
 	if (unlikely(mnt->mnt_pins.first))
 		mnt_pin_kill(mnt);
+	hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) {
+		hlist_del(&m->mnt_umount);
+		mntput(&m->mnt);
+	}
 	fsnotify_vfsmount_delete(&mnt->mnt);
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
@@ -1118,6 +1122,8 @@
 
 static void mntput_no_expire(struct mount *mnt)
 {
+	LIST_HEAD(list);
+
 	rcu_read_lock();
 	if (likely(READ_ONCE(mnt->mnt_ns))) {
 		/*
@@ -1158,10 +1164,12 @@
 	if (unlikely(!list_empty(&mnt->mnt_mounts))) {
 		struct mount *p, *tmp;
 		list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts,  mnt_child) {
-			umount_mnt(p);
+			__put_mountpoint(unhash_mnt(p), &list);
+			hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children);
 		}
 	}
 	unlock_mount_hash();
+	shrink_dentry_list(&list);
 
 	if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) {
 		struct task_struct *task = current;
@@ -1347,22 +1355,29 @@
 
 EXPORT_SYMBOL(may_umount);
 
-static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
-
 static void namespace_unlock(void)
 {
 	struct hlist_head head;
+	struct hlist_node *p;
+	struct mount *m;
+	LIST_HEAD(list);
 
 	hlist_move_list(&unmounted, &head);
+	list_splice_init(&ex_mountpoints, &list);
 
 	up_write(&namespace_sem);
 
+	shrink_dentry_list(&list);
+
 	if (likely(hlist_empty(&head)))
 		return;
 
-	synchronize_rcu();
+	synchronize_rcu_expedited();
 
-	group_pin_kill(&head);
+	hlist_for_each_entry_safe(m, p, &head, mnt_umount) {
+		hlist_del(&m->mnt_umount);
+		mntput(&m->mnt);
+	}
 }
 
 static inline void namespace_lock(void)
@@ -1448,9 +1463,6 @@
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 
 		disconnect = disconnect_mount(p, how);
-
-		pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt,
-				 disconnect ? &unmounted : NULL);
 		if (mnt_has_parent(p)) {
 			mnt_add_count(p->mnt_parent, -1);
 			if (!disconnect) {
@@ -1461,11 +1473,36 @@
 			}
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
+		if (disconnect)
+			hlist_add_head(&p->mnt_umount, &unmounted);
 	}
 }
 
 static void shrink_submounts(struct mount *mnt);
 
+static int do_umount_root(struct super_block *sb)
+{
+	int ret = 0;
+
+	down_write(&sb->s_umount);
+	if (!sb_rdonly(sb)) {
+		struct fs_context *fc;
+
+		fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY,
+						SB_RDONLY);
+		if (IS_ERR(fc)) {
+			ret = PTR_ERR(fc);
+		} else {
+			ret = parse_monolithic_mount_data(fc, NULL);
+			if (!ret)
+				ret = reconfigure_super(fc);
+			put_fs_context(fc);
+		}
+	}
+	up_write(&sb->s_umount);
+	return ret;
+}
+
 static int do_umount(struct mount *mnt, int flags)
 {
 	struct super_block *sb = mnt->mnt.mnt_sb;
@@ -1531,11 +1568,7 @@
 		 */
 		if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
 			return -EPERM;
-		down_write(&sb->s_umount);
-		if (!sb_rdonly(sb))
-			retval = do_remount_sb(sb, SB_RDONLY, NULL, 0);
-		up_write(&sb->s_umount);
-		return retval;
+		return do_umount_root(sb);
 	}
 
 	namespace_lock();
@@ -1584,15 +1617,15 @@
 	namespace_lock();
 	lock_mount_hash();
 	mp = lookup_mountpoint(dentry);
-	if (IS_ERR_OR_NULL(mp))
+	if (!mp)
 		goto out_unlock;
 
 	event++;
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
-			hlist_add_head(&mnt->mnt_umount.s_list, &unmounted);
 			umount_mnt(mnt);
+			hlist_add_head(&mnt->mnt_umount, &unmounted);
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
@@ -1610,13 +1643,18 @@
 	return ns_capable(current->nsproxy->mnt_ns->user_ns, CAP_SYS_ADMIN);
 }
 
+#ifdef	CONFIG_MANDATORY_FILE_LOCKING
 static inline bool may_mandlock(void)
 {
-#ifndef	CONFIG_MANDATORY_FILE_LOCKING
-	return false;
-#endif
 	return capable(CAP_SYS_ADMIN);
 }
+#else
+static inline bool may_mandlock(void)
+{
+	pr_warn("VFS: \"mand\" mount option not supported");
+	return false;
+}
+#endif
 
 /*
  * Now umount can handle mount points as well as block devices.
@@ -1790,6 +1828,27 @@
 	return &tree->mnt;
 }
 
+static void free_mnt_ns(struct mnt_namespace *);
+static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *, bool);
+
+void dissolve_on_fput(struct vfsmount *mnt)
+{
+	struct mnt_namespace *ns;
+	namespace_lock();
+	lock_mount_hash();
+	ns = real_mount(mnt)->mnt_ns;
+	if (ns) {
+		if (is_anon_ns(ns))
+			umount_tree(real_mount(mnt), UMOUNT_CONNECTED);
+		else
+			ns = NULL;
+	}
+	unlock_mount_hash();
+	namespace_unlock();
+	if (ns)
+		free_mnt_ns(ns);
+}
+
 void drop_collected_mounts(struct vfsmount *mnt)
 {
 	namespace_lock();
@@ -1839,6 +1898,33 @@
 	return 0;
 }
 
+static void lock_mnt_tree(struct mount *mnt)
+{
+	struct mount *p;
+
+	for (p = mnt; p; p = next_mnt(p, mnt)) {
+		int flags = p->mnt.mnt_flags;
+		/* Don't allow unprivileged users to change mount flags */
+		flags |= MNT_LOCK_ATIME;
+
+		if (flags & MNT_READONLY)
+			flags |= MNT_LOCK_READONLY;
+
+		if (flags & MNT_NODEV)
+			flags |= MNT_LOCK_NODEV;
+
+		if (flags & MNT_NOSUID)
+			flags |= MNT_LOCK_NOSUID;
+
+		if (flags & MNT_NOEXEC)
+			flags |= MNT_LOCK_NOEXEC;
+		/* Don't allow unprivileged users to reveal what is under a mount */
+		if (list_empty(&p->mnt_expire))
+			flags |= MNT_LOCKED;
+		p->mnt.mnt_flags = flags;
+	}
+}
+
 static void cleanup_group_ids(struct mount *mnt, struct mount *end)
 {
 	struct mount *p;
@@ -1954,8 +2040,9 @@
 static int attach_recursive_mnt(struct mount *source_mnt,
 			struct mount *dest_mnt,
 			struct mountpoint *dest_mp,
-			struct path *parent_path)
+			bool moving)
 {
+	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	HLIST_HEAD(tree_list);
 	struct mnt_namespace *ns = dest_mnt->mnt_ns;
 	struct mountpoint *smp;
@@ -1971,7 +2058,7 @@
 		return PTR_ERR(smp);
 
 	/* Is there space to add these mounts to the mount namespace? */
-	if (!parent_path) {
+	if (!moving) {
 		err = count_mounts(ns, source_mnt);
 		if (err)
 			goto out;
@@ -1990,11 +2077,15 @@
 	} else {
 		lock_mount_hash();
 	}
-	if (parent_path) {
-		detach_mnt(source_mnt, parent_path);
+	if (moving) {
+		unhash_mnt(source_mnt);
 		attach_mnt(source_mnt, dest_mnt, dest_mp);
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
+		if (source_mnt->mnt_ns) {
+			/* move from anon - the caller will destroy */
+			list_del_init(&source_mnt->mnt_ns->list);
+		}
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
 		commit_tree(source_mnt);
 	}
@@ -2006,6 +2097,10 @@
 				 child->mnt_mountpoint);
 		if (q)
 			mnt_change_mountpoint(child, smp, q);
+		/* Notice when we are propagating across user namespaces */
+		if (child->mnt_parent->mnt_ns->user_ns != user_ns)
+			lock_mnt_tree(child);
+		child->mnt.mnt_flags &= ~MNT_LOCKED;
 		commit_tree(child);
 	}
 	put_mountpoint(smp);
@@ -2081,7 +2176,7 @@
 	      d_is_dir(mnt->mnt.mnt_root))
 		return -ENOTDIR;
 
-	return attach_recursive_mnt(mnt, p, mp, NULL);
+	return attach_recursive_mnt(mnt, p, mp, false);
 }
 
 /*
@@ -2149,6 +2244,30 @@
 	return false;
 }
 
+static struct mount *__do_loopback(struct path *old_path, int recurse)
+{
+	struct mount *mnt = ERR_PTR(-EINVAL), *old = real_mount(old_path->mnt);
+
+	if (IS_MNT_UNBINDABLE(old))
+		return mnt;
+
+	if (!check_mnt(old) && old_path->dentry->d_op != &ns_dentry_operations)
+		return mnt;
+
+	if (!recurse && has_locked_children(old, old_path->dentry))
+		return mnt;
+
+	if (recurse)
+		mnt = copy_tree(old, old_path->dentry, CL_COPY_MNT_NS_FILE);
+	else
+		mnt = clone_mnt(old, old_path->dentry, 0);
+
+	if (!IS_ERR(mnt))
+		mnt->mnt.mnt_flags &= ~MNT_LOCKED;
+
+	return mnt;
+}
+
 /*
  * do loopback mount.
  */
@@ -2156,7 +2275,7 @@
 				int recurse)
 {
 	struct path old_path;
-	struct mount *mnt = NULL, *old, *parent;
+	struct mount *mnt = NULL, *parent;
 	struct mountpoint *mp;
 	int err;
 	if (!old_name || !*old_name)
@@ -2170,38 +2289,21 @@
 		goto out;
 
 	mp = lock_mount(path);
-	err = PTR_ERR(mp);
-	if (IS_ERR(mp))
+	if (IS_ERR(mp)) {
+		err = PTR_ERR(mp);
 		goto out;
+	}
 
-	old = real_mount(old_path.mnt);
 	parent = real_mount(path->mnt);
-
-	err = -EINVAL;
-	if (IS_MNT_UNBINDABLE(old))
-		goto out2;
-
 	if (!check_mnt(parent))
 		goto out2;
 
-	if (!check_mnt(old) && old_path.dentry->d_op != &ns_dentry_operations)
-		goto out2;
-
-	if (!recurse && has_locked_children(old, old_path.dentry))
-		goto out2;
-
-	if (recurse)
-		mnt = copy_tree(old, old_path.dentry, CL_COPY_MNT_NS_FILE);
-	else
-		mnt = clone_mnt(old, old_path.dentry, 0);
-
+	mnt = __do_loopback(&old_path, recurse);
 	if (IS_ERR(mnt)) {
 		err = PTR_ERR(mnt);
 		goto out2;
 	}
 
-	mnt->mnt.mnt_flags &= ~MNT_LOCKED;
-
 	err = graft_tree(mnt, parent, mp);
 	if (err) {
 		lock_mount_hash();
@@ -2215,21 +2317,206 @@
 	return err;
 }
 
-static int change_mount_flags(struct vfsmount *mnt, int ms_flags)
+static struct file *open_detached_copy(struct path *path, bool recursive)
 {
-	int error = 0;
-	int readonly_request = 0;
+	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
+	struct mnt_namespace *ns = alloc_mnt_ns(user_ns, true);
+	struct mount *mnt, *p;
+	struct file *file;
 
-	if (ms_flags & MS_RDONLY)
-		readonly_request = 1;
-	if (readonly_request == __mnt_is_readonly(mnt))
+	if (IS_ERR(ns))
+		return ERR_CAST(ns);
+
+	namespace_lock();
+	mnt = __do_loopback(path, recursive);
+	if (IS_ERR(mnt)) {
+		namespace_unlock();
+		free_mnt_ns(ns);
+		return ERR_CAST(mnt);
+	}
+
+	lock_mount_hash();
+	for (p = mnt; p; p = next_mnt(p, mnt)) {
+		p->mnt_ns = ns;
+		ns->mounts++;
+	}
+	ns->root = mnt;
+	list_add_tail(&ns->list, &mnt->mnt_list);
+	mntget(&mnt->mnt);
+	unlock_mount_hash();
+	namespace_unlock();
+
+	mntput(path->mnt);
+	path->mnt = &mnt->mnt;
+	file = dentry_open(path, O_PATH, current_cred());
+	if (IS_ERR(file))
+		dissolve_on_fput(path->mnt);
+	else
+		file->f_mode |= FMODE_NEED_UNMOUNT;
+	return file;
+}
+
+SYSCALL_DEFINE3(open_tree, int, dfd, const char *, filename, unsigned, flags)
+{
+	struct file *file;
+	struct path path;
+	int lookup_flags = LOOKUP_AUTOMOUNT | LOOKUP_FOLLOW;
+	bool detached = flags & OPEN_TREE_CLONE;
+	int error;
+	int fd;
+
+	BUILD_BUG_ON(OPEN_TREE_CLOEXEC != O_CLOEXEC);
+
+	if (flags & ~(AT_EMPTY_PATH | AT_NO_AUTOMOUNT | AT_RECURSIVE |
+		      AT_SYMLINK_NOFOLLOW | OPEN_TREE_CLONE |
+		      OPEN_TREE_CLOEXEC))
+		return -EINVAL;
+
+	if ((flags & (AT_RECURSIVE | OPEN_TREE_CLONE)) == AT_RECURSIVE)
+		return -EINVAL;
+
+	if (flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_EMPTY_PATH)
+		lookup_flags |= LOOKUP_EMPTY;
+
+	if (detached && !may_mount())
+		return -EPERM;
+
+	fd = get_unused_fd_flags(flags & O_CLOEXEC);
+	if (fd < 0)
+		return fd;
+
+	error = user_path_at(dfd, filename, lookup_flags, &path);
+	if (unlikely(error)) {
+		file = ERR_PTR(error);
+	} else {
+		if (detached)
+			file = open_detached_copy(&path, flags & AT_RECURSIVE);
+		else
+			file = dentry_open(&path, O_PATH, current_cred());
+		path_put(&path);
+	}
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		return PTR_ERR(file);
+	}
+	fd_install(fd, file);
+	return fd;
+}
+
+/*
+ * Don't allow locked mount flags to be cleared.
+ *
+ * No locks need to be held here while testing the various MNT_LOCK
+ * flags because those flags can never be cleared once they are set.
+ */
+static bool can_change_locked_flags(struct mount *mnt, unsigned int mnt_flags)
+{
+	unsigned int fl = mnt->mnt.mnt_flags;
+
+	if ((fl & MNT_LOCK_READONLY) &&
+	    !(mnt_flags & MNT_READONLY))
+		return false;
+
+	if ((fl & MNT_LOCK_NODEV) &&
+	    !(mnt_flags & MNT_NODEV))
+		return false;
+
+	if ((fl & MNT_LOCK_NOSUID) &&
+	    !(mnt_flags & MNT_NOSUID))
+		return false;
+
+	if ((fl & MNT_LOCK_NOEXEC) &&
+	    !(mnt_flags & MNT_NOEXEC))
+		return false;
+
+	if ((fl & MNT_LOCK_ATIME) &&
+	    ((fl & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK)))
+		return false;
+
+	return true;
+}
+
+static int change_mount_ro_state(struct mount *mnt, unsigned int mnt_flags)
+{
+	bool readonly_request = (mnt_flags & MNT_READONLY);
+
+	if (readonly_request == __mnt_is_readonly(&mnt->mnt))
 		return 0;
 
 	if (readonly_request)
-		error = mnt_make_readonly(real_mount(mnt));
-	else
-		__mnt_unmake_readonly(real_mount(mnt));
-	return error;
+		return mnt_make_readonly(mnt);
+
+	return __mnt_unmake_readonly(mnt);
+}
+
+/*
+ * Update the user-settable attributes on a mount.  The caller must hold
+ * sb->s_umount for writing.
+ */
+static void set_mount_attributes(struct mount *mnt, unsigned int mnt_flags)
+{
+	lock_mount_hash();
+	mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
+	mnt->mnt.mnt_flags = mnt_flags;
+	touch_mnt_namespace(mnt->mnt_ns);
+	unlock_mount_hash();
+}
+
+static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *mnt)
+{
+	struct super_block *sb = mnt->mnt_sb;
+
+	if (!__mnt_is_readonly(mnt) &&
+	   (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) {
+		char *buf = (char *)__get_free_page(GFP_KERNEL);
+		char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM);
+		struct tm tm;
+
+		time64_to_tm(sb->s_time_max, 0, &tm);
+
+		pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n",
+			sb->s_type->name,
+			is_mounted(mnt) ? "remounted" : "mounted",
+			mntpath,
+			tm.tm_year+1900, (unsigned long long)sb->s_time_max);
+
+		free_page((unsigned long)buf);
+	}
+}
+
+/*
+ * Handle reconfiguration of the mountpoint only without alteration of the
+ * superblock it refers to.  This is triggered by specifying MS_REMOUNT|MS_BIND
+ * to mount(2).
+ */
+static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags)
+{
+	struct super_block *sb = path->mnt->mnt_sb;
+	struct mount *mnt = real_mount(path->mnt);
+	int ret;
+
+	if (!check_mnt(mnt))
+		return -EINVAL;
+
+	if (path->dentry != mnt->mnt.mnt_root)
+		return -EINVAL;
+
+	if (!can_change_locked_flags(mnt, mnt_flags))
+		return -EPERM;
+
+	down_write(&sb->s_umount);
+	ret = change_mount_ro_state(mnt, mnt_flags);
+	if (ret == 0)
+		set_mount_attributes(mnt, mnt_flags);
+	up_write(&sb->s_umount);
+
+	mnt_warn_timestamp_expiry(path, &mnt->mnt);
+
+	return ret;
 }
 
 /*
@@ -2243,6 +2530,7 @@
 	int err;
 	struct super_block *sb = path->mnt->mnt_sb;
 	struct mount *mnt = real_mount(path->mnt);
+	struct fs_context *fc;
 
 	if (!check_mnt(mnt))
 		return -EINVAL;
@@ -2250,52 +2538,28 @@
 	if (path->dentry != path->mnt->mnt_root)
 		return -EINVAL;
 
-	/* Don't allow changing of locked mnt flags.
-	 *
-	 * No locks need to be held here while testing the various
-	 * MNT_LOCK flags because those flags can never be cleared
-	 * once they are set.
-	 */
-	if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
-	    !(mnt_flags & MNT_READONLY)) {
+	if (!can_change_locked_flags(mnt, mnt_flags))
 		return -EPERM;
-	}
-	if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
-	    !(mnt_flags & MNT_NODEV)) {
-		return -EPERM;
-	}
-	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
-	    !(mnt_flags & MNT_NOSUID)) {
-		return -EPERM;
-	}
-	if ((mnt->mnt.mnt_flags & MNT_LOCK_NOEXEC) &&
-	    !(mnt_flags & MNT_NOEXEC)) {
-		return -EPERM;
-	}
-	if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
-	    ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (mnt_flags & MNT_ATIME_MASK))) {
-		return -EPERM;
-	}
 
-	err = security_sb_remount(sb, data);
-	if (err)
-		return err;
+	fc = fs_context_for_reconfigure(path->dentry, sb_flags, MS_RMT_MASK);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
 
-	down_write(&sb->s_umount);
-	if (ms_flags & MS_BIND)
-		err = change_mount_flags(path->mnt, ms_flags);
-	else if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN))
-		err = -EPERM;
-	else
-		err = do_remount_sb(sb, sb_flags, data, 0);
+	err = parse_monolithic_mount_data(fc, data);
 	if (!err) {
-		lock_mount_hash();
-		mnt_flags |= mnt->mnt.mnt_flags & ~MNT_USER_SETTABLE_MASK;
-		mnt->mnt.mnt_flags = mnt_flags;
-		touch_mnt_namespace(mnt->mnt_ns);
-		unlock_mount_hash();
+		down_write(&sb->s_umount);
+		err = -EPERM;
+		if (ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) {
+			err = reconfigure_super(fc);
+			if (!err)
+				set_mount_attributes(mnt, mnt_flags);
+		}
+		up_write(&sb->s_umount);
 	}
-	up_write(&sb->s_umount);
+
+	mnt_warn_timestamp_expiry(path, &mnt->mnt);
+
+	put_fs_context(fc);
 	return err;
 }
 
@@ -2309,97 +2573,125 @@
 	return 0;
 }
 
-static int do_move_mount(struct path *path, const char *old_name)
+/*
+ * Check that there aren't references to earlier/same mount namespaces in the
+ * specified subtree.  Such references can act as pins for mount namespaces
+ * that aren't checked by the mount-cycle checking code, thereby allowing
+ * cycles to be made.
+ */
+static bool check_for_nsfs_mounts(struct mount *subtree)
 {
-	struct path old_path, parent_path;
+	struct mount *p;
+	bool ret = false;
+
+	lock_mount_hash();
+	for (p = subtree; p; p = next_mnt(p, subtree))
+		if (mnt_ns_loop(p->mnt.mnt_root))
+			goto out;
+
+	ret = true;
+out:
+	unlock_mount_hash();
+	return ret;
+}
+
+static int do_move_mount(struct path *old_path, struct path *new_path)
+{
+	struct mnt_namespace *ns;
 	struct mount *p;
 	struct mount *old;
-	struct mountpoint *mp;
+	struct mount *parent;
+	struct mountpoint *mp, *old_mp;
 	int err;
-	if (!old_name || !*old_name)
-		return -EINVAL;
-	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
-	if (err)
-		return err;
+	bool attached;
 
-	mp = lock_mount(path);
-	err = PTR_ERR(mp);
+	mp = lock_mount(new_path);
 	if (IS_ERR(mp))
+		return PTR_ERR(mp);
+
+	old = real_mount(old_path->mnt);
+	p = real_mount(new_path->mnt);
+	parent = old->mnt_parent;
+	attached = mnt_has_parent(old);
+	old_mp = old->mnt_mp;
+	ns = old->mnt_ns;
+
+	err = -EINVAL;
+	/* The mountpoint must be in our namespace. */
+	if (!check_mnt(p))
 		goto out;
 
-	old = real_mount(old_path.mnt);
-	p = real_mount(path->mnt);
+	/* The thing moved must be mounted... */
+	if (!is_mounted(&old->mnt))
+		goto out;
 
-	err = -EINVAL;
-	if (!check_mnt(p) || !check_mnt(old))
-		goto out1;
+	/* ... and either ours or the root of anon namespace */
+	if (!(attached ? check_mnt(old) : is_anon_ns(ns)))
+		goto out;
 
 	if (old->mnt.mnt_flags & MNT_LOCKED)
-		goto out1;
+		goto out;
 
-	err = -EINVAL;
-	if (old_path.dentry != old_path.mnt->mnt_root)
-		goto out1;
+	if (old_path->dentry != old_path->mnt->mnt_root)
+		goto out;
 
-	if (!mnt_has_parent(old))
-		goto out1;
-
-	if (d_is_dir(path->dentry) !=
-	      d_is_dir(old_path.dentry))
-		goto out1;
+	if (d_is_dir(new_path->dentry) !=
+	    d_is_dir(old_path->dentry))
+		goto out;
 	/*
 	 * Don't move a mount residing in a shared parent.
 	 */
-	if (IS_MNT_SHARED(old->mnt_parent))
-		goto out1;
+	if (attached && IS_MNT_SHARED(parent))
+		goto out;
 	/*
 	 * Don't move a mount tree containing unbindable mounts to a destination
 	 * mount which is shared.
 	 */
 	if (IS_MNT_SHARED(p) && tree_contains_unbindable(old))
-		goto out1;
+		goto out;
 	err = -ELOOP;
+	if (!check_for_nsfs_mounts(old))
+		goto out;
 	for (; mnt_has_parent(p); p = p->mnt_parent)
 		if (p == old)
-			goto out1;
+			goto out;
 
-	err = attach_recursive_mnt(old, real_mount(path->mnt), mp, &parent_path);
+	err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp,
+				   attached);
 	if (err)
-		goto out1;
+		goto out;
 
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
 	list_del_init(&old->mnt_expire);
-out1:
-	unlock_mount(mp);
+	if (attached)
+		put_mountpoint(old_mp);
 out:
-	if (!err)
-		path_put(&parent_path);
-	path_put(&old_path);
+	unlock_mount(mp);
+	if (!err) {
+		if (attached)
+			mntput_no_expire(parent);
+		else
+			free_mnt_ns(ns);
+	}
 	return err;
 }
 
-static struct vfsmount *fs_set_subtype(struct vfsmount *mnt, const char *fstype)
+static int do_move_mount_old(struct path *path, const char *old_name)
 {
+	struct path old_path;
 	int err;
-	const char *subtype = strchr(fstype, '.');
-	if (subtype) {
-		subtype++;
-		err = -EINVAL;
-		if (!subtype[0])
-			goto err;
-	} else
-		subtype = "";
 
-	mnt->mnt_sb->s_subtype = kstrdup(subtype, GFP_KERNEL);
-	err = -ENOMEM;
-	if (!mnt->mnt_sb->s_subtype)
-		goto err;
-	return mnt;
+	if (!old_name || !*old_name)
+		return -EINVAL;
 
- err:
-	mntput(mnt);
-	return ERR_PTR(err);
+	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
+	if (err)
+		return err;
+
+	err = do_move_mount(&old_path, path);
+	path_put(&old_path);
+	return err;
 }
 
 /*
@@ -2446,7 +2738,41 @@
 	return err;
 }
 
-static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags);
+static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags);
+
+/*
+ * Create a new mount using a superblock configuration and request it
+ * be added to the namespace tree.
+ */
+static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint,
+			   unsigned int mnt_flags)
+{
+	struct vfsmount *mnt;
+	struct super_block *sb = fc->root->d_sb;
+	int error;
+
+	error = security_sb_kern_mount(sb);
+	if (!error && mount_too_revealing(sb, &mnt_flags))
+		error = -EPERM;
+
+	if (unlikely(error)) {
+		fc_drop_locked(fc);
+		return error;
+	}
+
+	up_write(&sb->s_umount);
+
+	mnt = vfs_create_mount(fc);
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+
+	mnt_warn_timestamp_expiry(mountpoint, mnt);
+
+	error = do_add_mount(real_mount(mnt), mountpoint, mnt_flags);
+	if (error < 0)
+		mntput(mnt);
+	return error;
+}
 
 /*
  * create a new mount for userspace and request it to be added into the
@@ -2456,8 +2782,9 @@
 			int mnt_flags, const char *name, void *data)
 {
 	struct file_system_type *type;
-	struct vfsmount *mnt;
-	int err;
+	struct fs_context *fc;
+	const char *subtype = NULL;
+	int err = 0;
 
 	if (!fstype)
 		return -EINVAL;
@@ -2466,23 +2793,37 @@
 	if (!type)
 		return -ENODEV;
 
-	mnt = vfs_kern_mount(type, sb_flags, name, data);
-	if (!IS_ERR(mnt) && (type->fs_flags & FS_HAS_SUBTYPE) &&
-	    !mnt->mnt_sb->s_subtype)
-		mnt = fs_set_subtype(mnt, fstype);
-
-	put_filesystem(type);
-	if (IS_ERR(mnt))
-		return PTR_ERR(mnt);
-
-	if (mount_too_revealing(mnt, &mnt_flags)) {
-		mntput(mnt);
-		return -EPERM;
+	if (type->fs_flags & FS_HAS_SUBTYPE) {
+		subtype = strchr(fstype, '.');
+		if (subtype) {
+			subtype++;
+			if (!*subtype) {
+				put_filesystem(type);
+				return -EINVAL;
+			}
+		}
 	}
 
-	err = do_add_mount(real_mount(mnt), path, mnt_flags);
-	if (err)
-		mntput(mnt);
+	fc = fs_context_for_mount(type, sb_flags);
+	put_filesystem(type);
+	if (IS_ERR(fc))
+		return PTR_ERR(fc);
+
+	if (subtype)
+		err = vfs_parse_fs_string(fc, "subtype",
+					  subtype, strlen(subtype));
+	if (!err && name)
+		err = vfs_parse_fs_string(fc, "source", name, strlen(name));
+	if (!err)
+		err = parse_monolithic_mount_data(fc, data);
+	if (!err && !mount_capable(fc))
+		err = -EPERM;
+	if (!err)
+		err = vfs_get_tree(fc);
+	if (!err)
+		err = do_new_mount_fc(fc, path, mnt_flags);
+
+	put_fs_context(fc);
 	return err;
 }
 
@@ -2651,7 +2992,7 @@
 	const char __user *f = from;
 	char c;
 
-	if (!access_ok(VERIFY_READ, from, n))
+	if (!access_ok(from, n))
 		return n;
 
 	while (n) {
@@ -2684,7 +3025,7 @@
 	 * the remainder of the page.
 	 */
 	/* copy_from_user cannot cross TASK_SIZE ! */
-	size = TASK_SIZE - (unsigned long)data;
+	size = TASK_SIZE - (unsigned long)untagged_addr(data);
 	if (size > PAGE_SIZE)
 		size = PAGE_SIZE;
 
@@ -2700,7 +3041,7 @@
 
 char *copy_mount_string(const void __user *data)
 {
-	return data ? strndup_user(data, PAGE_SIZE) : NULL;
+	return data ? strndup_user(data, PATH_MAX) : NULL;
 }
 
 /*
@@ -2736,7 +3077,7 @@
 		return -EINVAL;
 
 	/* ... and get the mountpoint */
-	retval = user_path(dir_name, &path);
+	retval = user_path_at(AT_FDCWD, dir_name, LOOKUP_FOLLOW, &path);
 	if (retval)
 		return retval;
 
@@ -2786,7 +3127,9 @@
 			    SB_LAZYTIME |
 			    SB_I_VERSION);
 
-	if (flags & MS_REMOUNT)
+	if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND))
+		retval = do_reconfigure_mnt(&path, mnt_flags);
+	else if (flags & MS_REMOUNT)
 		retval = do_remount(&path, flags, sb_flags, mnt_flags,
 				    data_page);
 	else if (flags & MS_BIND)
@@ -2794,7 +3137,7 @@
 	else if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
 		retval = do_change_type(&path, flags);
 	else if (flags & MS_MOVE)
-		retval = do_move_mount(&path, dev_name);
+		retval = do_move_mount_old(&path, dev_name);
 	else
 		retval = do_new_mount(&path, type_page, sb_flags, mnt_flags,
 				      dev_name, data_page);
@@ -2815,7 +3158,8 @@
 
 static void free_mnt_ns(struct mnt_namespace *ns)
 {
-	ns_free_inum(&ns->ns);
+	if (!is_anon_ns(ns))
+		ns_free_inum(&ns->ns);
 	dec_mnt_namespaces(ns->ucounts);
 	put_user_ns(ns->user_ns);
 	kfree(ns);
@@ -2830,7 +3174,7 @@
  */
 static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
 
-static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns)
+static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon)
 {
 	struct mnt_namespace *new_ns;
 	struct ucounts *ucounts;
@@ -2840,28 +3184,27 @@
 	if (!ucounts)
 		return ERR_PTR(-ENOSPC);
 
-	new_ns = kmalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
+	new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
 	if (!new_ns) {
 		dec_mnt_namespaces(ucounts);
 		return ERR_PTR(-ENOMEM);
 	}
-	ret = ns_alloc_inum(&new_ns->ns);
-	if (ret) {
-		kfree(new_ns);
-		dec_mnt_namespaces(ucounts);
-		return ERR_PTR(ret);
+	if (!anon) {
+		ret = ns_alloc_inum(&new_ns->ns);
+		if (ret) {
+			kfree(new_ns);
+			dec_mnt_namespaces(ucounts);
+			return ERR_PTR(ret);
+		}
 	}
 	new_ns->ns.ops = &mntns_operations;
-	new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
+	if (!anon)
+		new_ns->seq = atomic64_add_return(1, &mnt_ns_seq);
 	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;
 	new_ns->user_ns = get_user_ns(user_ns);
 	new_ns->ucounts = ucounts;
-	new_ns->mounts = 0;
-	new_ns->pending_mounts = 0;
 	return new_ns;
 }
 
@@ -2885,7 +3228,7 @@
 
 	old = ns->root;
 
-	new_ns = alloc_mnt_ns(user_ns);
+	new_ns = alloc_mnt_ns(user_ns, false);
 	if (IS_ERR(new_ns))
 		return new_ns;
 
@@ -2893,13 +3236,18 @@
 	/* First pass: copy the tree topology */
 	copy_flags = CL_COPY_UNBINDABLE | CL_EXPIRE;
 	if (user_ns != ns->user_ns)
-		copy_flags |= CL_SHARED_TO_SLAVE | CL_UNPRIVILEGED;
+		copy_flags |= CL_SHARED_TO_SLAVE;
 	new = copy_tree(old, old->mnt.mnt_root, copy_flags);
 	if (IS_ERR(new)) {
 		namespace_unlock();
 		free_mnt_ns(new_ns);
 		return ERR_CAST(new);
 	}
+	if (user_ns != ns->user_ns) {
+		lock_mount_hash();
+		lock_mnt_tree(new);
+		unlock_mount_hash();
+	}
 	new_ns->root = new;
 	list_add_tail(&new_ns->list, &new->mnt_list);
 
@@ -2940,37 +3288,25 @@
 	return new_ns;
 }
 
-/**
- * create_mnt_ns - creates a private namespace and adds a root filesystem
- * @mnt: pointer to the new root filesystem mountpoint
- */
-static struct mnt_namespace *create_mnt_ns(struct vfsmount *m)
+struct dentry *mount_subtree(struct vfsmount *m, const char *name)
 {
-	struct mnt_namespace *new_ns = alloc_mnt_ns(&init_user_ns);
-	if (!IS_ERR(new_ns)) {
-		struct mount *mnt = real_mount(m);
-		mnt->mnt_ns = new_ns;
-		new_ns->root = mnt;
-		new_ns->mounts++;
-		list_add(&mnt->mnt_list, &new_ns->list);
-	} else {
-		mntput(m);
-	}
-	return new_ns;
-}
-
-struct dentry *mount_subtree(struct vfsmount *mnt, const char *name)
-{
+	struct mount *mnt = real_mount(m);
 	struct mnt_namespace *ns;
 	struct super_block *s;
 	struct path path;
 	int err;
 
-	ns = create_mnt_ns(mnt);
-	if (IS_ERR(ns))
+	ns = alloc_mnt_ns(&init_user_ns, true);
+	if (IS_ERR(ns)) {
+		mntput(m);
 		return ERR_CAST(ns);
+	}
+	mnt->mnt_ns = ns;
+	ns->root = mnt;
+	ns->mounts++;
+	list_add(&mnt->mnt_list, &ns->list);
 
-	err = vfs_path_lookup(mnt->mnt_root, mnt,
+	err = vfs_path_lookup(m->mnt_root, m,
 			name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 
 	put_mnt_ns(ns);
@@ -2989,8 +3325,8 @@
 }
 EXPORT_SYMBOL(mount_subtree);
 
-int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type,
-	       unsigned long flags, void __user *data)
+int ksys_mount(const char __user *dev_name, const char __user *dir_name,
+	       const char __user *type, unsigned long flags, void __user *data)
 {
 	int ret;
 	char *kernel_type;
@@ -3030,6 +3366,204 @@
 }
 
 /*
+ * Create a kernel mount representation for a new, prepared superblock
+ * (specified by fs_fd) and attach to an open_tree-like file descriptor.
+ */
+SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
+		unsigned int, attr_flags)
+{
+	struct mnt_namespace *ns;
+	struct fs_context *fc;
+	struct file *file;
+	struct path newmount;
+	struct mount *mnt;
+	struct fd f;
+	unsigned int mnt_flags = 0;
+	long ret;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if ((flags & ~(FSMOUNT_CLOEXEC)) != 0)
+		return -EINVAL;
+
+	if (attr_flags & ~(MOUNT_ATTR_RDONLY |
+			   MOUNT_ATTR_NOSUID |
+			   MOUNT_ATTR_NODEV |
+			   MOUNT_ATTR_NOEXEC |
+			   MOUNT_ATTR__ATIME |
+			   MOUNT_ATTR_NODIRATIME))
+		return -EINVAL;
+
+	if (attr_flags & MOUNT_ATTR_RDONLY)
+		mnt_flags |= MNT_READONLY;
+	if (attr_flags & MOUNT_ATTR_NOSUID)
+		mnt_flags |= MNT_NOSUID;
+	if (attr_flags & MOUNT_ATTR_NODEV)
+		mnt_flags |= MNT_NODEV;
+	if (attr_flags & MOUNT_ATTR_NOEXEC)
+		mnt_flags |= MNT_NOEXEC;
+	if (attr_flags & MOUNT_ATTR_NODIRATIME)
+		mnt_flags |= MNT_NODIRATIME;
+
+	switch (attr_flags & MOUNT_ATTR__ATIME) {
+	case MOUNT_ATTR_STRICTATIME:
+		break;
+	case MOUNT_ATTR_NOATIME:
+		mnt_flags |= MNT_NOATIME;
+		break;
+	case MOUNT_ATTR_RELATIME:
+		mnt_flags |= MNT_RELATIME;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	f = fdget(fs_fd);
+	if (!f.file)
+		return -EBADF;
+
+	ret = -EINVAL;
+	if (f.file->f_op != &fscontext_fops)
+		goto err_fsfd;
+
+	fc = f.file->private_data;
+
+	ret = mutex_lock_interruptible(&fc->uapi_mutex);
+	if (ret < 0)
+		goto err_fsfd;
+
+	/* There must be a valid superblock or we can't mount it */
+	ret = -EINVAL;
+	if (!fc->root)
+		goto err_unlock;
+
+	ret = -EPERM;
+	if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) {
+		pr_warn("VFS: Mount too revealing\n");
+		goto err_unlock;
+	}
+
+	ret = -EBUSY;
+	if (fc->phase != FS_CONTEXT_AWAITING_MOUNT)
+		goto err_unlock;
+
+	ret = -EPERM;
+	if ((fc->sb_flags & SB_MANDLOCK) && !may_mandlock())
+		goto err_unlock;
+
+	newmount.mnt = vfs_create_mount(fc);
+	if (IS_ERR(newmount.mnt)) {
+		ret = PTR_ERR(newmount.mnt);
+		goto err_unlock;
+	}
+	newmount.dentry = dget(fc->root);
+	newmount.mnt->mnt_flags = mnt_flags;
+
+	/* We've done the mount bit - now move the file context into more or
+	 * less the same state as if we'd done an fspick().  We don't want to
+	 * do any memory allocation or anything like that at this point as we
+	 * don't want to have to handle any errors incurred.
+	 */
+	vfs_clean_context(fc);
+
+	ns = alloc_mnt_ns(current->nsproxy->mnt_ns->user_ns, true);
+	if (IS_ERR(ns)) {
+		ret = PTR_ERR(ns);
+		goto err_path;
+	}
+	mnt = real_mount(newmount.mnt);
+	mnt->mnt_ns = ns;
+	ns->root = mnt;
+	ns->mounts = 1;
+	list_add(&mnt->mnt_list, &ns->list);
+	mntget(newmount.mnt);
+
+	/* Attach to an apparent O_PATH fd with a note that we need to unmount
+	 * it, not just simply put it.
+	 */
+	file = dentry_open(&newmount, O_PATH, fc->cred);
+	if (IS_ERR(file)) {
+		dissolve_on_fput(newmount.mnt);
+		ret = PTR_ERR(file);
+		goto err_path;
+	}
+	file->f_mode |= FMODE_NEED_UNMOUNT;
+
+	ret = get_unused_fd_flags((flags & FSMOUNT_CLOEXEC) ? O_CLOEXEC : 0);
+	if (ret >= 0)
+		fd_install(ret, file);
+	else
+		fput(file);
+
+err_path:
+	path_put(&newmount);
+err_unlock:
+	mutex_unlock(&fc->uapi_mutex);
+err_fsfd:
+	fdput(f);
+	return ret;
+}
+
+/*
+ * Move a mount from one place to another.  In combination with
+ * fsopen()/fsmount() this is used to install a new mount and in combination
+ * with open_tree(OPEN_TREE_CLONE [| AT_RECURSIVE]) it can be used to copy
+ * a mount subtree.
+ *
+ * Note the flags value is a combination of MOVE_MOUNT_* flags.
+ */
+SYSCALL_DEFINE5(move_mount,
+		int, from_dfd, const char *, from_pathname,
+		int, to_dfd, const char *, to_pathname,
+		unsigned int, flags)
+{
+	struct path from_path, to_path;
+	unsigned int lflags;
+	int ret = 0;
+
+	if (!may_mount())
+		return -EPERM;
+
+	if (flags & ~MOVE_MOUNT__MASK)
+		return -EINVAL;
+
+	/* If someone gives a pathname, they aren't permitted to move
+	 * from an fd that requires unmount as we can't get at the flag
+	 * to clear it afterwards.
+	 */
+	lflags = 0;
+	if (flags & MOVE_MOUNT_F_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_F_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
+	if (flags & MOVE_MOUNT_F_EMPTY_PATH)	lflags |= LOOKUP_EMPTY;
+
+	ret = user_path_at(from_dfd, from_pathname, lflags, &from_path);
+	if (ret < 0)
+		return ret;
+
+	lflags = 0;
+	if (flags & MOVE_MOUNT_T_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_T_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
+	if (flags & MOVE_MOUNT_T_EMPTY_PATH)	lflags |= LOOKUP_EMPTY;
+
+	ret = user_path_at(to_dfd, to_pathname, lflags, &to_path);
+	if (ret < 0)
+		goto out_from;
+
+	ret = security_move_mount(&from_path, &to_path);
+	if (ret < 0)
+		goto out_to;
+
+	ret = do_move_mount(&from_path, &to_path);
+
+out_to:
+	path_put(&to_path);
+out_from:
+	path_put(&from_path);
+	return ret;
+}
+
+/*
  * Return true if path is reachable from root
  *
  * namespace_sem or mount_lock is held
@@ -3082,19 +3616,21 @@
 SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 		const char __user *, put_old)
 {
-	struct path new, old, parent_path, root_parent, root;
-	struct mount *new_mnt, *root_mnt, *old_mnt;
+	struct path new, old, root;
+	struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent;
 	struct mountpoint *old_mp, *root_mp;
 	int error;
 
 	if (!may_mount())
 		return -EPERM;
 
-	error = user_path_dir(new_root, &new);
+	error = user_path_at(AT_FDCWD, new_root,
+			     LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &new);
 	if (error)
 		goto out0;
 
-	error = user_path_dir(put_old, &old);
+	error = user_path_at(AT_FDCWD, put_old,
+			     LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &old);
 	if (error)
 		goto out1;
 
@@ -3112,9 +3648,11 @@
 	new_mnt = real_mount(new.mnt);
 	root_mnt = real_mount(root.mnt);
 	old_mnt = real_mount(old.mnt);
+	ex_parent = new_mnt->mnt_parent;
+	root_parent = root_mnt->mnt_parent;
 	if (IS_MNT_SHARED(old_mnt) ||
-		IS_MNT_SHARED(new_mnt->mnt_parent) ||
-		IS_MNT_SHARED(root_mnt->mnt_parent))
+		IS_MNT_SHARED(ex_parent) ||
+		IS_MNT_SHARED(root_parent))
 		goto out4;
 	if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
 		goto out4;
@@ -3131,7 +3669,6 @@
 		goto out4; /* not a mountpoint */
 	if (!mnt_has_parent(root_mnt))
 		goto out4; /* not attached */
-	root_mp = root_mnt->mnt_mp;
 	if (new.mnt->mnt_root != new.dentry)
 		goto out4; /* not a mountpoint */
 	if (!mnt_has_parent(new_mnt))
@@ -3142,10 +3679,9 @@
 	/* make certain new is below the root */
 	if (!is_path_reachable(new_mnt, new.dentry, &root))
 		goto out4;
-	root_mp->m_count++; /* pin it so it won't go away */
 	lock_mount_hash();
-	detach_mnt(new_mnt, &parent_path);
-	detach_mnt(root_mnt, &root_parent);
+	umount_mnt(new_mnt);
+	root_mp = unhash_mnt(root_mnt);  /* we'll need its mountpoint */
 	if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
 		new_mnt->mnt.mnt_flags |= MNT_LOCKED;
 		root_mnt->mnt.mnt_flags &= ~MNT_LOCKED;
@@ -3153,7 +3689,8 @@
 	/* mount old root on put_old */
 	attach_mnt(root_mnt, old_mnt, old_mp);
 	/* mount new_root on / */
-	attach_mnt(new_mnt, real_mount(root_parent.mnt), root_mp);
+	attach_mnt(new_mnt, root_parent, root_mp);
+	mnt_add_count(root_parent, -1);
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	/* A moved mount should not expire automatically */
 	list_del_init(&new_mnt->mnt_expire);
@@ -3163,10 +3700,8 @@
 	error = 0;
 out4:
 	unlock_mount(old_mp);
-	if (!error) {
-		path_put(&root_parent);
-		path_put(&parent_path);
-	}
+	if (!error)
+		mntput_no_expire(ex_parent);
 out3:
 	path_put(&root);
 out2:
@@ -3180,22 +3715,22 @@
 static void __init init_mount_tree(void)
 {
 	struct vfsmount *mnt;
+	struct mount *m;
 	struct mnt_namespace *ns;
 	struct path root;
-	struct file_system_type *type;
 
-	type = get_fs_type("rootfs");
-	if (!type)
-		panic("Can't find rootfs type");
-	mnt = vfs_kern_mount(type, 0, "rootfs", NULL);
-	put_filesystem(type);
+	mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL);
 	if (IS_ERR(mnt))
 		panic("Can't create rootfs");
 
-	ns = create_mnt_ns(mnt);
+	ns = alloc_mnt_ns(&init_user_ns, false);
 	if (IS_ERR(ns))
 		panic("Can't allocate initial namespace");
-
+	m = real_mount(mnt);
+	m->mnt_ns = ns;
+	ns->root = m;
+	ns->mounts = 1;
+	list_add(&m->mnt_list, &ns->list);
 	init_task.nsproxy->mnt_ns = ns;
 	get_mnt_ns(ns);
 
@@ -3237,6 +3772,7 @@
 	fs_kobj = kobject_create_and_add("fs", NULL);
 	if (!fs_kobj)
 		printk(KERN_WARNING "%s: kobj create error\n", __func__);
+	shmem_init();
 	init_rootfs();
 	init_mount_tree();
 }
@@ -3249,10 +3785,10 @@
 	free_mnt_ns(ns);
 }
 
-struct vfsmount *kern_mount_data(struct file_system_type *type, void *data)
+struct vfsmount *kern_mount(struct file_system_type *type)
 {
 	struct vfsmount *mnt;
-	mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, data);
+	mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
 	if (!IS_ERR(mnt)) {
 		/*
 		 * it is a longterm mount, don't release mnt until
@@ -3262,7 +3798,7 @@
 	}
 	return mnt;
 }
-EXPORT_SYMBOL_GPL(kern_mount_data);
+EXPORT_SYMBOL_GPL(kern_mount);
 
 void kern_unmount(struct vfsmount *mnt)
 {
@@ -3304,7 +3840,8 @@
 	return chrooted;
 }
 
-static bool mnt_already_visible(struct mnt_namespace *ns, struct vfsmount *new,
+static bool mnt_already_visible(struct mnt_namespace *ns,
+				const struct super_block *sb,
 				int *new_mnt_flags)
 {
 	int new_flags = *new_mnt_flags;
@@ -3316,7 +3853,7 @@
 		struct mount *child;
 		int mnt_flags;
 
-		if (mnt->mnt.mnt_sb->s_type != new->mnt_sb->s_type)
+		if (mnt->mnt.mnt_sb->s_type != sb->s_type)
 			continue;
 
 		/* This mount is not fully visible if it's root directory
@@ -3367,7 +3904,7 @@
 	return visible;
 }
 
-static bool mount_too_revealing(struct vfsmount *mnt, int *new_mnt_flags)
+static bool mount_too_revealing(const struct super_block *sb, int *new_mnt_flags)
 {
 	const unsigned long required_iflags = SB_I_NOEXEC | SB_I_NODEV;
 	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
@@ -3377,7 +3914,7 @@
 		return false;
 
 	/* Can this filesystem be too revealing? */
-	s_iflags = mnt->mnt_sb->s_iflags;
+	s_iflags = sb->s_iflags;
 	if (!(s_iflags & SB_I_USERNS_VISIBLE))
 		return false;
 
@@ -3387,7 +3924,7 @@
 		return true;
 	}
 
-	return !mnt_already_visible(ns, mnt, new_mnt_flags);
+	return !mnt_already_visible(ns, sb, new_mnt_flags);
 }
 
 bool mnt_may_suid(struct vfsmount *mnt)
@@ -3436,6 +3973,9 @@
 	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
 		return -EPERM;
 
+	if (is_anon_ns(mnt_ns))
+		return -EINVAL;
+
 	if (fs->users != 1)
 		return -EINVAL;