1 files changed, 185 insertions, 209 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index ddfd4457d338..dc01b14c58cd 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -33,6 +33,7 @@
 #include <linux/shmem_fs.h>
 #include <linux/mnt_idmapping.h>
 #include <linux/pidfs.h>
+#include <linux/nstree.h>
 
 #include "pnode.h"
 #include "internal.h"
@@ -65,6 +66,15 @@ static int __init set_mphash_entries(char *str)
 }
 __setup("mphash_entries=", set_mphash_entries);
 
+static char * __initdata initramfs_options;
+static int __init initramfs_options_setup(char *str)
+{
+	initramfs_options = str;
+	return 1;
+}
+
+__setup("initramfs_options=", initramfs_options_setup);
+
 static u64 event;
 static DEFINE_XARRAY_FLAGS(mnt_id_xa, XA_FLAGS_ALLOC);
 static DEFINE_IDA(mnt_group_ida);
@@ -80,13 +90,10 @@ static DECLARE_RWSEM(namespace_sem);
 static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
 static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
 static struct mnt_namespace *emptied_ns; /* protected by namespace_sem */
-static DEFINE_SEQLOCK(mnt_ns_tree_lock);
 
 #ifdef CONFIG_FSNOTIFY
 LIST_HEAD(notify_list); /* protected by namespace_sem */
 #endif
-static struct rb_root mnt_ns_tree = RB_ROOT; /* protected by mnt_ns_tree_lock */
-static LIST_HEAD(mnt_ns_list); /* protected by mnt_ns_tree_lock */
 
 enum mount_kattr_flags_t {
 	MOUNT_KATTR_RECURSE		= (1 << 0),
@@ -119,59 +126,18 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(mount_lock);
 
 static inline struct mnt_namespace *node_to_mnt_ns(const struct rb_node *node)
 {
+	struct ns_common *ns;
+
 	if (!node)
 		return NULL;
-	return rb_entry(node, struct mnt_namespace, mnt_ns_tree_node);
-}
-
-static int mnt_ns_cmp(struct rb_node *a, const struct rb_node *b)
-{
-	struct mnt_namespace *ns_a = node_to_mnt_ns(a);
-	struct mnt_namespace *ns_b = node_to_mnt_ns(b);
-	u64 seq_a = ns_a->seq;
-	u64 seq_b = ns_b->seq;
-
-	if (seq_a < seq_b)
-		return -1;
-	if (seq_a > seq_b)
-		return 1;
-	return 0;
-}
-
-static inline void mnt_ns_tree_write_lock(void)
-{
-	write_seqlock(&mnt_ns_tree_lock);
-}
-
-static inline void mnt_ns_tree_write_unlock(void)
-{
-	write_sequnlock(&mnt_ns_tree_lock);
-}
-
-static void mnt_ns_tree_add(struct mnt_namespace *ns)
-{
-	struct rb_node *node, *prev;
-
-	mnt_ns_tree_write_lock();
-	node = rb_find_add_rcu(&ns->mnt_ns_tree_node, &mnt_ns_tree, mnt_ns_cmp);
-	/*
-	 * If there's no previous entry simply add it after the
-	 * head and if there is add it after the previous entry.
-	 */
-	prev = rb_prev(&ns->mnt_ns_tree_node);
-	if (!prev)
-		list_add_rcu(&ns->mnt_ns_list, &mnt_ns_list);
-	else
-		list_add_rcu(&ns->mnt_ns_list, &node_to_mnt_ns(prev)->mnt_ns_list);
-	mnt_ns_tree_write_unlock();
-
-	WARN_ON_ONCE(node);
+	ns = rb_entry(node, struct ns_common, ns_tree_node);
+	return container_of(ns, struct mnt_namespace, ns);
 }
 
 static void mnt_ns_release(struct mnt_namespace *ns)
 {
 	/* keep alive for {list,stat}mount() */
-	if (refcount_dec_and_test(&ns->passive)) {
+	if (ns && refcount_dec_and_test(&ns->passive)) {
 		fsnotify_mntns_delete(ns);
 		put_user_ns(ns->user_ns);
 		kfree(ns);
@@ -181,32 +147,16 @@ DEFINE_FREE(mnt_ns_release, struct mnt_namespace *, if (_T) mnt_ns_release(_T))
 
 static void mnt_ns_release_rcu(struct rcu_head *rcu)
 {
-	mnt_ns_release(container_of(rcu, struct mnt_namespace, mnt_ns_rcu));
+	mnt_ns_release(container_of(rcu, struct mnt_namespace, ns.ns_rcu));
 }
 
 static void mnt_ns_tree_remove(struct mnt_namespace *ns)
 {
 	/* remove from global mount namespace list */
-	if (!is_anon_ns(ns)) {
-		mnt_ns_tree_write_lock();
-		rb_erase(&ns->mnt_ns_tree_node, &mnt_ns_tree);
-		list_bidir_del_rcu(&ns->mnt_ns_list);
-		mnt_ns_tree_write_unlock();
-	}
-
-	call_rcu(&ns->mnt_ns_rcu, mnt_ns_release_rcu);
-}
+	if (ns_tree_active(ns))
+		ns_tree_remove(ns);
 
-static int mnt_ns_find(const void *key, const struct rb_node *node)
-{
-	const u64 mnt_ns_id = *(u64 *)key;
-	const struct mnt_namespace *ns = node_to_mnt_ns(node);
-
-	if (mnt_ns_id < ns->seq)
-		return -1;
-	if (mnt_ns_id > ns->seq)
-		return 1;
-	return 0;
+	call_rcu(&ns->ns.ns_rcu, mnt_ns_release_rcu);
 }
 
 /*
@@ -225,28 +175,21 @@ static int mnt_ns_find(const void *key, const struct rb_node *node)
  */
 static struct mnt_namespace *lookup_mnt_ns(u64 mnt_ns_id)
 {
-	struct mnt_namespace *ns;
-	struct rb_node *node;
-	unsigned int seq;
+	struct mnt_namespace *mnt_ns;
+	struct ns_common *ns;
 
 	guard(rcu)();
-	do {
-		seq = read_seqbegin(&mnt_ns_tree_lock);
-		node = rb_find_rcu(&mnt_ns_id, &mnt_ns_tree, mnt_ns_find);
-		if (node)
-			break;
-	} while (read_seqretry(&mnt_ns_tree_lock, seq));
-
-	if (!node)
+	ns = ns_tree_lookup_rcu(mnt_ns_id, CLONE_NEWNS);
+	if (!ns)
 		return NULL;
 
 	/*
 	 * The last reference count is put with RCU delay so we can
 	 * unconditonally acquire a reference here.
 	 */
-	ns = node_to_mnt_ns(node);
-	refcount_inc(&ns->passive);
-	return ns;
+	mnt_ns = container_of(ns, struct mnt_namespace, ns);
+	refcount_inc(&mnt_ns->passive);
+	return mnt_ns;
 }
 
 static inline void lock_mount_hash(void)
@@ -1017,7 +960,7 @@ static inline bool check_anonymous_mnt(struct mount *mnt)
 		return false;
 
 	seq = mnt->mnt_ns->seq_origin;
-	return !seq || (seq == current->nsproxy->mnt_ns->seq);
+	return !seq || (seq == current->nsproxy->mnt_ns->ns.ns_id);
 }
 
 /*
@@ -1197,10 +1140,7 @@ static void commit_tree(struct mount *mnt)
 
 	if (!mnt_ns_attached(mnt)) {
 		for (struct mount *m = mnt; m; m = next_mnt(m, mnt))
-			if (unlikely(mnt_ns_attached(m)))
-				m = skip_mnt_tree(m);
-			else
-				mnt_add_to_ns(n, m);
+			mnt_add_to_ns(n, m);
 		n->nr_mounts += n->pending_mounts;
 		n->pending_mounts = 0;
 	}
@@ -2155,19 +2095,16 @@ struct ns_common *from_mnt_ns(struct mnt_namespace *mnt)
 
 struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mntns, bool previous)
 {
+	struct ns_common *ns;
+
 	guard(rcu)();
 
 	for (;;) {
-		struct list_head *list;
-
-		if (previous)
-			list = rcu_dereference(list_bidir_prev_rcu(&mntns->mnt_ns_list));
-		else
-			list = rcu_dereference(list_next_rcu(&mntns->mnt_ns_list));
-		if (list_is_head(list, &mnt_ns_list))
-			return ERR_PTR(-ENOENT);
+		ns = ns_tree_adjoined_rcu(mntns, previous);
+		if (IS_ERR(ns))
+			return ERR_CAST(ns);
 
-		mntns = list_entry_rcu(list, struct mnt_namespace, mnt_ns_list);
+		mntns = to_mnt_ns(ns);
 
 		/*
 		 * The last passive reference count is put with RCU
@@ -2182,7 +2119,7 @@ struct mnt_namespace *get_sequential_mnt_ns(struct mnt_namespace *mntns, bool pr
 		 * the mount namespace and it might already be on its
 		 * deathbed.
 		 */
-		if (!refcount_inc_not_zero(&mntns->ns.count))
+		if (!ns_ref_get(mntns))
 			continue;
 
 		return mntns;
@@ -2207,7 +2144,7 @@ static bool mnt_ns_loop(struct dentry *dentry)
 	if (!mnt_ns)
 		return false;
 
-	return current->nsproxy->mnt_ns->seq >= mnt_ns->seq;
+	return current->nsproxy->mnt_ns->ns.ns_id >= mnt_ns->ns.ns_id;
 }
 
 struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
@@ -2458,7 +2395,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
 			return ERR_PTR(-EINVAL);
 	}
 
-        if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
+	if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
 	if (__has_locked_children(old_mnt, path->dentry))
@@ -2704,6 +2641,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 			lock_mnt_tree(child);
 		q = __lookup_mnt(&child->mnt_parent->mnt,
 				 child->mnt_mountpoint);
+		commit_tree(child);
 		if (q) {
 			struct mountpoint *mp = root.mp;
 			struct mount *r = child;
@@ -2713,7 +2651,6 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 				mp = shorter;
 			mnt_change_mountpoint(r, mp, q);
 		}
-		commit_tree(child);
 	}
 	unpin_mountpoint(&root);
 	unlock_mount_hash();
@@ -2862,6 +2799,19 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
 	return attach_recursive_mnt(mnt, p, mp);
 }
 
+static int may_change_propagation(const struct mount *m)
+{
+        struct mnt_namespace *ns = m->mnt_ns;
+
+	 // it must be mounted in some namespace
+	 if (IS_ERR_OR_NULL(ns))         // is_mounted()
+		 return -EINVAL;
+	 // and the caller must be admin in userns of that namespace
+	 if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
+		 return -EPERM;
+	 return 0;
+}
+
 /*
  * Sanity check the flags to change_mnt_propagation.
  */
@@ -2898,10 +2848,10 @@ static int do_change_type(struct path *path, int ms_flags)
 		return -EINVAL;
 
 	namespace_lock();
-	if (!check_mnt(mnt)) {
-		err = -EINVAL;
+	err = may_change_propagation(mnt);
+	if (err)
 		goto out_unlock;
-	}
+
 	if (type == MS_SHARED) {
 		err = invent_group_ids(mnt, recurse);
 		if (err)
@@ -3070,7 +3020,7 @@ static struct file *open_detached_copy(struct path *path, bool recursive)
 		if (is_anon_ns(src_mnt_ns))
 			ns->seq_origin = src_mnt_ns->seq_origin;
 		else
-			ns->seq_origin = src_mnt_ns->seq;
+			ns->seq_origin = src_mnt_ns->ns.ns_id;
 	}
 
 	mnt = __do_loopback(path, recursive);
@@ -3279,7 +3229,7 @@ static int do_reconfigure_mnt(struct path *path, unsigned int mnt_flags)
  * If you've mounted a non-root directory somewhere and want to do remount
  * on it - tough luck.
  */
-static int do_remount(struct path *path, int ms_flags, int sb_flags,
+static int do_remount(struct path *path, int sb_flags,
 		      int mnt_flags, void *data)
 {
 	int err;
@@ -3347,18 +3297,11 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 
 	namespace_lock();
 
-	err = -EINVAL;
-	/* To and From must be mounted */
-	if (!is_mounted(&from->mnt))
-		goto out;
-	if (!is_mounted(&to->mnt))
-		goto out;
-
-	err = -EPERM;
-	/* We should be allowed to modify mount namespaces of both mounts */
-	if (!ns_capable(from->mnt_ns->user_ns, CAP_SYS_ADMIN))
+	err = may_change_propagation(from);
+	if (err)
 		goto out;
-	if (!ns_capable(to->mnt_ns->user_ns, CAP_SYS_ADMIN))
+	err = may_change_propagation(to);
+	if (err)
 		goto out;
 
 	err = -EINVAL;
@@ -3724,8 +3667,10 @@ static int do_new_mount_fc(struct fs_context *fc, struct path *mountpoint,
 	int error;
 
 	error = security_sb_kern_mount(sb);
-	if (!error && mount_too_revealing(sb, &mnt_flags))
+	if (!error && mount_too_revealing(sb, &mnt_flags)) {
+		errorfcp(fc, "VFS", "Mount too revealing");
 		error = -EPERM;
+	}
 
 	if (unlikely(error)) {
 		fc_drop_locked(fc);
@@ -4109,7 +4054,7 @@ int path_mount(const char *dev_name, struct path *path,
 	if ((flags & (MS_REMOUNT | MS_BIND)) == (MS_REMOUNT | MS_BIND))
 		return do_reconfigure_mnt(path, mnt_flags);
 	if (flags & MS_REMOUNT)
-		return do_remount(path, flags, sb_flags, mnt_flags, data_page);
+		return do_remount(path, sb_flags, mnt_flags, data_page);
 	if (flags & MS_BIND)
 		return do_loopback(path, dev_name, flags & MS_REC);
 	if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE))
@@ -4148,20 +4093,11 @@ static void dec_mnt_namespaces(struct ucounts *ucounts)
 static void free_mnt_ns(struct mnt_namespace *ns)
 {
 	if (!is_anon_ns(ns))
-		ns_free_inum(&ns->ns);
+		ns_common_free(ns);
 	dec_mnt_namespaces(ns->ucounts);
 	mnt_ns_tree_remove(ns);
 }
 
-/*
- * Assign a sequence number so we can detect when we attempt to bind
- * mount a reference to an older mount namespace into the current
- * mount namespace, preventing reference counting loops.  A 64bit
- * number incrementing at 10Ghz will take 12,427 years to wrap which
- * is effectively never, so we can ignore the possibility.
- */
-static atomic64_t mnt_ns_seq = ATOMIC64_INIT(1);
-
 static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool anon)
 {
 	struct mnt_namespace *new_ns;
@@ -4177,22 +4113,20 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 		dec_mnt_namespaces(ucounts);
 		return ERR_PTR(-ENOMEM);
 	}
-	if (!anon) {
-		ret = ns_alloc_inum(&new_ns->ns);
-		if (ret) {
-			kfree(new_ns);
-			dec_mnt_namespaces(ucounts);
-			return ERR_PTR(ret);
-		}
+
+	if (anon)
+		ret = ns_common_init_inum(new_ns, MNT_NS_ANON_INO);
+	else
+		ret = ns_common_init(new_ns);
+	if (ret) {
+		kfree(new_ns);
+		dec_mnt_namespaces(ucounts);
+		return ERR_PTR(ret);
 	}
-	new_ns->ns.ops = &mntns_operations;
 	if (!anon)
-		new_ns->seq = atomic64_inc_return(&mnt_ns_seq);
-	refcount_set(&new_ns->ns.count, 1);
+		ns_tree_gen_id(&new_ns->ns);
 	refcount_set(&new_ns->passive, 1);
 	new_ns->mounts = RB_ROOT;
-	INIT_LIST_HEAD(&new_ns->mnt_ns_list);
-	RB_CLEAR_NODE(&new_ns->mnt_ns_tree_node);
 	init_waitqueue_head(&new_ns->poll);
 	new_ns->user_ns = get_user_ns(user_ns);
 	new_ns->ucounts = ucounts;
@@ -4200,7 +4134,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 }
 
 __latent_entropy
-struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
+struct mnt_namespace *copy_mnt_ns(u64 flags, struct mnt_namespace *ns,
 		struct user_namespace *user_ns, struct fs_struct *new_fs)
 {
 	struct mnt_namespace *new_ns;
@@ -4231,7 +4165,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	new = copy_tree(old, old->mnt.mnt_root, copy_flags);
 	if (IS_ERR(new)) {
 		namespace_unlock();
-		ns_free_inum(&new_ns->ns);
+		ns_common_free(ns);
 		dec_mnt_namespaces(new_ns->ucounts);
 		mnt_ns_release(new_ns);
 		return ERR_CAST(new);
@@ -4278,7 +4212,7 @@ struct mnt_namespace *copy_mnt_ns(unsigned long flags, struct mnt_namespace *ns,
 	if (pwdmnt)
 		mntput(pwdmnt);
 
-	mnt_ns_tree_add(new_ns);
+	ns_tree_add_raw(new_ns);
 	return new_ns;
 }
 
@@ -4441,7 +4375,7 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
 
 	ret = -EPERM;
 	if (mount_too_revealing(fc->root->d_sb, &mnt_flags)) {
-		pr_warn("VFS: Mount too revealing\n");
+		errorfcp(fc, "VFS", "Mount too revealing");
 		goto err_unlock;
 	}
 
@@ -4551,20 +4485,10 @@ SYSCALL_DEFINE5(move_mount,
 	if (flags & MOVE_MOUNT_SET_GROUP)	mflags |= MNT_TREE_PROPAGATION;
 	if (flags & MOVE_MOUNT_BENEATH)		mflags |= MNT_TREE_BENEATH;
 
-	lflags = 0;
-	if (flags & MOVE_MOUNT_F_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
-	if (flags & MOVE_MOUNT_F_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
 	uflags = 0;
-	if (flags & MOVE_MOUNT_F_EMPTY_PATH)	uflags = AT_EMPTY_PATH;
-	from_name = getname_maybe_null(from_pathname, uflags);
-	if (IS_ERR(from_name))
-		return PTR_ERR(from_name);
+	if (flags & MOVE_MOUNT_T_EMPTY_PATH)
+		uflags = AT_EMPTY_PATH;
 
-	lflags = 0;
-	if (flags & MOVE_MOUNT_T_SYMLINKS)	lflags |= LOOKUP_FOLLOW;
-	if (flags & MOVE_MOUNT_T_AUTOMOUNTS)	lflags |= LOOKUP_AUTOMOUNT;
-	uflags = 0;
-	if (flags & MOVE_MOUNT_T_EMPTY_PATH)	uflags = AT_EMPTY_PATH;
 	to_name = getname_maybe_null(to_pathname, uflags);
 	if (IS_ERR(to_name))
 		return PTR_ERR(to_name);
@@ -4577,11 +4501,24 @@ SYSCALL_DEFINE5(move_mount,
 		to_path = fd_file(f_to)->f_path;
 		path_get(&to_path);
 	} else {
+		lflags = 0;
+		if (flags & MOVE_MOUNT_T_SYMLINKS)
+			lflags |= LOOKUP_FOLLOW;
+		if (flags & MOVE_MOUNT_T_AUTOMOUNTS)
+			lflags |= LOOKUP_AUTOMOUNT;
 		ret = filename_lookup(to_dfd, to_name, lflags, &to_path, NULL);
 		if (ret)
 			return ret;
 	}
 
+	uflags = 0;
+	if (flags & MOVE_MOUNT_F_EMPTY_PATH)
+		uflags = AT_EMPTY_PATH;
+
+	from_name = getname_maybe_null(from_pathname, uflags);
+	if (IS_ERR(from_name))
+		return PTR_ERR(from_name);
+
 	if (!from_name && from_dfd >= 0) {
 		CLASS(fd_raw, f_from)(from_dfd);
 		if (fd_empty(f_from))
@@ -4590,6 +4527,11 @@ SYSCALL_DEFINE5(move_mount,
 		return vfs_move_mount(&fd_file(f_from)->f_path, &to_path, mflags);
 	}
 
+	lflags = 0;
+	if (flags & MOVE_MOUNT_F_SYMLINKS)
+		lflags |= LOOKUP_FOLLOW;
+	if (flags & MOVE_MOUNT_F_AUTOMOUNTS)
+		lflags |= LOOKUP_AUTOMOUNT;
 	ret = filename_lookup(from_dfd, from_name, lflags, &from_path, NULL);
 	if (ret)
 		return ret;
@@ -4996,7 +4938,7 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize,
 		return -EINVAL;
 
 	ns = get_proc_ns(file_inode(fd_file(f)));
-	if (ns->ops->type != CLONE_NEWUSER)
+	if (ns->ns_type != CLONE_NEWUSER)
 		return -EINVAL;
 
 	/*
@@ -5176,7 +5118,8 @@ SYSCALL_DEFINE5(open_tree_attr, int, dfd, const char __user *, filename,
 		int ret;
 		struct mount_kattr kattr = {};
 
-		kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE;
+		if (flags & OPEN_TREE_CLONE)
+			kattr.kflags = MOUNT_KATTR_IDMAP_REPLACE;
 		if (flags & AT_RECURSIVE)
 			kattr.kflags |= MOUNT_KATTR_RECURSE;
 
@@ -5388,7 +5331,7 @@ static int statmount_sb_source(struct kstatmount *s, struct seq_file *seq)
 static void statmount_mnt_ns_id(struct kstatmount *s, struct mnt_namespace *ns)
 {
 	s->sm.mask |= STATMOUNT_MNT_NS_ID;
-	s->sm.mnt_ns_id = ns->seq;
+	s->sm.mnt_ns_id = ns->ns.ns_id;
 }
 
 static int statmount_mnt_opts(struct kstatmount *s, struct seq_file *seq)
@@ -5699,7 +5642,6 @@ static int grab_requested_root(struct mnt_namespace *ns, struct path *root)
 static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 			struct mnt_namespace *ns)
 {
-	struct path root __free(path_put) = {};
 	struct mount *m;
 	int err;
 
@@ -5711,7 +5653,7 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 	if (!s->mnt)
 		return -ENOENT;
 
-	err = grab_requested_root(ns, &root);
+	err = grab_requested_root(ns, &s->root);
 	if (err)
 		return err;
 
@@ -5720,7 +5662,7 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 	 * mounts to show users.
 	 */
 	m = real_mount(s->mnt);
-	if (!is_path_reachable(m, m->mnt.mnt_root, &root) &&
+	if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) &&
 	    !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
@@ -5728,8 +5670,6 @@ static int do_statmount(struct kstatmount *s, u64 mnt_id, u64 mnt_ns_id,
 	if (err)
 		return err;
 
-	s->root = root;
-
 	/*
 	 * Note that mount properties in mnt->mnt_flags, mnt->mnt_idmap
 	 * can change concurrently as we only hold the read-side of the
@@ -5898,7 +5838,7 @@ static struct mnt_namespace *grab_requested_mnt_ns(const struct mnt_id_req *kreq
 			return ERR_PTR(-EINVAL);
 
 		ns = get_proc_ns(file_inode(fd_file(f)));
-		if (ns->ops->type != CLONE_NEWNS)
+		if (ns->ns_type != CLONE_NEWNS)
 			return ERR_PTR(-EINVAL);
 
 		mnt_ns = to_mnt_ns(ns);
@@ -5951,28 +5891,40 @@ retry:
 	if (!ret)
 		ret = copy_statmount_to_user(ks);
 	kvfree(ks->seq.buf);
+	path_put(&ks->root);
 	if (retry_statmount(ret, &seq_size))
 		goto retry;
 	return ret;
 }
 
-static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id,
-			    u64 last_mnt_id, u64 *mnt_ids, size_t nr_mnt_ids,
-			    bool reverse)
+struct klistmount {
+	u64 last_mnt_id;
+	u64 mnt_parent_id;
+	u64 *kmnt_ids;
+	u32 nr_mnt_ids;
+	struct mnt_namespace *ns;
+	struct path root;
+};
+
+static ssize_t do_listmount(struct klistmount *kls, bool reverse)
 {
-	struct path root __free(path_put) = {};
+	struct mnt_namespace *ns = kls->ns;
+	u64 mnt_parent_id = kls->mnt_parent_id;
+	u64 last_mnt_id = kls->last_mnt_id;
+	u64 *mnt_ids = kls->kmnt_ids;
+	size_t nr_mnt_ids = kls->nr_mnt_ids;
 	struct path orig;
 	struct mount *r, *first;
 	ssize_t ret;
 
 	rwsem_assert_held(&namespace_sem);
 
-	ret = grab_requested_root(ns, &root);
+	ret = grab_requested_root(ns, &kls->root);
 	if (ret)
 		return ret;
 
 	if (mnt_parent_id == LSMT_ROOT) {
-		orig = root;
+		orig = kls->root;
 	} else {
 		orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns);
 		if (!orig.mnt)
@@ -5984,7 +5936,7 @@ static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id,
 	 * Don't trigger audit denials. We just want to determine what
 	 * mounts to show users.
 	 */
-	if (!is_path_reachable(real_mount(orig.mnt), orig.dentry, &root) &&
+	if (!is_path_reachable(real_mount(orig.mnt), orig.dentry, &kls->root) &&
 	    !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
 		return -EPERM;
 
@@ -6017,14 +5969,45 @@ static ssize_t do_listmount(struct mnt_namespace *ns, u64 mnt_parent_id,
 	return ret;
 }
 
+static void __free_klistmount_free(const struct klistmount *kls)
+{
+	path_put(&kls->root);
+	kvfree(kls->kmnt_ids);
+	mnt_ns_release(kls->ns);
+}
+
+static inline int prepare_klistmount(struct klistmount *kls, struct mnt_id_req *kreq,
+				     size_t nr_mnt_ids)
+{
+
+	u64 last_mnt_id = kreq->param;
+
+	/* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */
+	if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET)
+		return -EINVAL;
+
+	kls->last_mnt_id = last_mnt_id;
+
+	kls->nr_mnt_ids = nr_mnt_ids;
+	kls->kmnt_ids = kvmalloc_array(nr_mnt_ids, sizeof(*kls->kmnt_ids),
+				       GFP_KERNEL_ACCOUNT);
+	if (!kls->kmnt_ids)
+		return -ENOMEM;
+
+	kls->ns = grab_requested_mnt_ns(kreq);
+	if (!kls->ns)
+		return -ENOENT;
+
+	kls->mnt_parent_id = kreq->mnt_id;
+	return 0;
+}
+
 SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 		u64 __user *, mnt_ids, size_t, nr_mnt_ids, unsigned int, flags)
 {
-	u64 *kmnt_ids __free(kvfree) = NULL;
+	struct klistmount kls __free(klistmount_free) = {};
 	const size_t maxcount = 1000000;
-	struct mnt_namespace *ns __free(mnt_ns_release) = NULL;
 	struct mnt_id_req kreq;
-	u64 last_mnt_id;
 	ssize_t ret;
 
 	if (flags & ~LISTMOUNT_REVERSE)
@@ -6045,22 +6028,12 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	if (ret)
 		return ret;
 
-	last_mnt_id = kreq.param;
-	/* The first valid unique mount id is MNT_UNIQUE_ID_OFFSET + 1. */
-	if (last_mnt_id != 0 && last_mnt_id <= MNT_UNIQUE_ID_OFFSET)
-		return -EINVAL;
-
-	kmnt_ids = kvmalloc_array(nr_mnt_ids, sizeof(*kmnt_ids),
-				  GFP_KERNEL_ACCOUNT);
-	if (!kmnt_ids)
-		return -ENOMEM;
-
-	ns = grab_requested_mnt_ns(&kreq);
-	if (!ns)
-		return -ENOENT;
+	ret = prepare_klistmount(&kls, &kreq, nr_mnt_ids);
+	if (ret)
+		return ret;
 
-	if (kreq.mnt_ns_id && (ns != current->nsproxy->mnt_ns) &&
-	    !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
+	if (kreq.mnt_ns_id && (kls.ns != current->nsproxy->mnt_ns) &&
+	    !ns_capable_noaudit(kls.ns->user_ns, CAP_SYS_ADMIN))
 		return -ENOENT;
 
 	/*
@@ -6068,39 +6041,43 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
 	 * listmount() doesn't care about any mount properties.
 	 */
 	scoped_guard(rwsem_read, &namespace_sem)
-		ret = do_listmount(ns, kreq.mnt_id, last_mnt_id, kmnt_ids,
-				   nr_mnt_ids, (flags & LISTMOUNT_REVERSE));
+		ret = do_listmount(&kls, (flags & LISTMOUNT_REVERSE));
 	if (ret <= 0)
 		return ret;
 
-	if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids)))
+	if (copy_to_user(mnt_ids, kls.kmnt_ids, ret * sizeof(*mnt_ids)))
 		return -EFAULT;
 
 	return ret;
 }
 
+struct mnt_namespace init_mnt_ns = {
+	.ns.inum	= ns_init_inum(&init_mnt_ns),
+	.ns.ops		= &mntns_operations,
+	.user_ns	= &init_user_ns,
+	.ns.__ns_ref	= REFCOUNT_INIT(1),
+	.ns.ns_type	= ns_common_type(&init_mnt_ns),
+	.passive	= REFCOUNT_INIT(1),
+	.mounts		= RB_ROOT,
+	.poll		= __WAIT_QUEUE_HEAD_INITIALIZER(init_mnt_ns.poll),
+};
+
 static void __init init_mount_tree(void)
 {
 	struct vfsmount *mnt;
 	struct mount *m;
-	struct mnt_namespace *ns;
 	struct path root;
 
-	mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", NULL);
+	mnt = vfs_kern_mount(&rootfs_fs_type, 0, "rootfs", initramfs_options);
 	if (IS_ERR(mnt))
 		panic("Can't create rootfs");
 
-	ns = alloc_mnt_ns(&init_user_ns, true);
-	if (IS_ERR(ns))
-		panic("Can't allocate initial namespace");
-	ns->seq = atomic64_inc_return(&mnt_ns_seq);
-	ns->ns.inum = PROC_MNT_INIT_INO;
 	m = real_mount(mnt);
-	ns->root = m;
-	ns->nr_mounts = 1;
-	mnt_add_to_ns(ns, m);
-	init_task.nsproxy->mnt_ns = ns;
-	get_mnt_ns(ns);
+	init_mnt_ns.root = m;
+	init_mnt_ns.nr_mounts = 1;
+	mnt_add_to_ns(&init_mnt_ns, m);
+	init_task.nsproxy->mnt_ns = &init_mnt_ns;
+	get_mnt_ns(&init_mnt_ns);
 
 	root.mnt = mnt;
 	root.dentry = mnt->mnt_root;
@@ -6108,7 +6085,7 @@ static void __init init_mount_tree(void)
 	set_fs_pwd(current->fs, &root);
 	set_fs_root(current->fs, &root);
 
-	mnt_ns_tree_add(ns);
+	ns_tree_add(&init_mnt_ns);
 }
 
 void __init mnt_init(void)
@@ -6148,7 +6125,7 @@ void __init mnt_init(void)
 
 void put_mnt_ns(struct mnt_namespace *ns)
 {
-	if (!refcount_dec_and_test(&ns->ns.count))
+	if (!ns_ref_put(ns))
 		return;
 	namespace_lock();
 	emptied_ns = ns;
@@ -6397,7 +6374,6 @@ static struct user_namespace *mntns_owner(struct ns_common *ns)
 
 const struct proc_ns_operations mntns_operations = {
 	.name		= "mnt",
-	.type		= CLONE_NEWNS,
 	.get		= mntns_get,
 	.put		= mntns_put,
 	.install	= mntns_install,