[RFC PATCH v4 09/14] fs: Support MOVE_MOUNT_T_MNTNS in move_mount()
From: Jarkko Sakkinen
Date: Thu Nov 19 2026 - 17:44:55 EST
move_mount() currently resolves target paths only against the caller's
filesystem view or anonymous mount fds, preventing an external manager
from populating an empty mount namespace or hot-mounting into an
existing container's mount namespace without entering it first.
Add MOVE_MOUNT_T_MNTNS to attach detached anonymous mount trees into a
target mount namespace nsfs file descriptor. Installing "/" attaches the
initial root mount onto the nullfs root of an empty mount namespace at
most once, while relative target paths resolve with LOOKUP_IN_ROOT
beneath the live mount namespace root and reject root-mount aliases
under namespace_lock().
Check CAP_SYS_ADMIN in the target mount namespace's owning user
namespace instead of caller may_mount(), check nsfs mount loops against
the destination mount namespace, and lock moved mount trees inside
attach_recursive_mnt() when crossing user namespace boundaries.
Co-developed-by: David Howells <dhowells@xxxxxxxxxx>
Signed-off-by: David Howells <dhowells@xxxxxxxxxx>
Signed-off-by: Jarkko Sakkinen <jarkko@xxxxxxxxxx>
---
fs/namespace.c | 218 +++++++++++++++++++++++++++++++------
include/uapi/linux/mount.h | 3 +-
2 files changed, 184 insertions(+), 37 deletions(-)
diff --git a/fs/namespace.c b/fs/namespace.c
index dfe0ee9ecdcd..36ed48c3f646 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2202,7 +2202,8 @@ struct mnt_namespace *mnt_ns_from_dentry(struct dentry *dentry)
return to_mnt_ns(get_proc_ns(dentry->d_inode));
}
-static bool mnt_ns_loop(struct dentry *dentry)
+static bool mnt_ns_loop_target(struct dentry *dentry,
+ struct mnt_namespace *target_mnt_ns)
{
/* Could bind mounting the mount namespace inode cause a
* mount namespace loop?
@@ -2212,7 +2213,12 @@ static bool mnt_ns_loop(struct dentry *dentry)
if (!mnt_ns)
return false;
- return current->nsproxy->mnt_ns->ns.ns_id >= mnt_ns->ns.ns_id;
+ return target_mnt_ns->ns.ns_id >= mnt_ns->ns.ns_id;
+}
+
+static bool mnt_ns_loop(struct dentry *dentry)
+{
+ return mnt_ns_loop_target(dentry, current->nsproxy->mnt_ns);
}
struct mount *copy_tree(struct mount *src_root, struct dentry *dentry,
@@ -2423,10 +2429,11 @@ static bool __has_children(struct mount *mnt, struct dentry *dentry)
*
* locks: mount_locked_reader || namespace_shared && pinned(subtree)
*/
-static bool check_for_nsfs_mounts(struct mount *subtree)
+static bool check_for_nsfs_mounts(struct mount *subtree,
+ struct mnt_namespace *target_mnt_ns)
{
for (struct mount *p = subtree; p; p = next_mnt(p, subtree))
- if (mnt_ns_loop(p->mnt.mnt_root))
+ if (mnt_ns_loop_target(p->mnt.mnt_root, target_mnt_ns))
return false;
return true;
}
@@ -2464,7 +2471,7 @@ struct vfsmount *clone_private_mount(const struct path *path)
if (!anon_ns_root(old_mnt))
return ERR_PTR(-EINVAL);
- if (!check_for_nsfs_mounts(old_mnt))
+ if (!check_for_nsfs_mounts(old_mnt, current->nsproxy->mnt_ns))
return ERR_PTR(-EINVAL);
}
@@ -2564,12 +2571,15 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
enum mnt_tree_flags_t {
MNT_TREE_BENEATH = BIT(0),
MNT_TREE_PROPAGATION = BIT(1),
+ MNT_TREE_MNTNS = BIT(2),
+ MNT_TREE_MNTNS_INIT = BIT(3),
};
/**
* attach_recursive_mnt - attach a source mount tree
* @source_mnt: mount tree to be attached
* @dest: the context for mounting at the place where the tree should go
+ * @move_mntns: whether @source_mnt is attached via MOVE_MOUNT_T_MNTNS
*
* NOTE: in the table below explains the semantics when a source mount
* of a given type is attached to a destination mount of a given type.
@@ -2632,7 +2642,8 @@ enum mnt_tree_flags_t {
* Otherwise a negative error code is returned.
*/
static int attach_recursive_mnt(struct mount *source_mnt,
- const struct pinned_mountpoint *dest)
+ const struct pinned_mountpoint *dest,
+ bool move_mntns)
{
struct mount *dest_mnt = dest->parent;
struct mountpoint *dest_mp = dest->mp;
@@ -2641,6 +2652,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
struct user_namespace *user_ns = ns->user_ns;
struct pinned_mountpoint root = {};
struct mountpoint *shorter = NULL;
+ struct mnt_namespace *src_ns;
struct mount *child, *p;
struct mount *top;
struct hlist_node *n;
@@ -2662,6 +2674,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
user_ns = current->nsproxy->mnt_ns->user_ns;
else
user_ns = ns->user_ns;
+ src_ns = moving ? NULL : source_mnt->mnt_ns;
/*
* Preallocate a mountpoint in case the new mounts need to be
@@ -2694,6 +2707,12 @@ static int attach_recursive_mnt(struct mount *source_mnt,
if (err)
goto out_cleanup_ids;
+ if (move_mntns && src_ns && src_ns->user_ns != user_ns) {
+ lock_mnt_tree(source_mnt);
+ if (list_empty(&source_mnt->mnt_expire))
+ source_mnt->mnt.mnt_flags |= MNT_LOCKED;
+ }
+
if (IS_MNT_SHARED(dest_mnt)) {
for (p = source_mnt; p; p = next_mnt(p, source_mnt))
set_mnt_shared(p);
@@ -2937,7 +2956,7 @@ static int graft_tree(struct mount *mnt, const struct pinned_mountpoint *mp)
d_is_dir(mnt->mnt.mnt_root))
return -ENOTDIR;
- return attach_recursive_mnt(mnt, mp);
+ return attach_recursive_mnt(mnt, mp, false);
}
static int may_change_propagation(const struct mount *m)
@@ -3131,7 +3150,7 @@ static int do_loopback(const struct path *path, const char *old_name,
return PTR_ERR(mnt);
/* the copy may carry mount namespace files from below the source */
- if (recurse && !check_for_nsfs_mounts(mnt))
+ if (recurse && !check_for_nsfs_mounts(mnt, current->nsproxy->mnt_ns))
err = -EINVAL;
else
err = graft_tree(mnt, &mp);
@@ -3776,9 +3795,11 @@ static inline bool may_use_mount(struct mount *mnt)
static int do_move_mount(const struct path *old_path,
const struct path *new_path,
- enum mnt_tree_flags_t flags)
+ enum mnt_tree_flags_t flags,
+ struct mnt_namespace *target_mnt_ns)
{
struct mount *old = real_mount(old_path->mnt);
+ struct mnt_namespace *dest_mnt_ns;
int err;
bool beneath = flags & MNT_TREE_BENEATH;
@@ -3792,7 +3813,23 @@ static int do_move_mount(const struct path *old_path,
if (IS_ERR(mp.parent))
return PTR_ERR(mp.parent);
- if (check_mnt(old)) {
+ if (flags & MNT_TREE_MNTNS) {
+ if (!anon_ns_root(old) || old->mnt_ns == mp.parent->mnt_ns ||
+ mp.parent->mnt_ns != target_mnt_ns)
+ return -EINVAL;
+ if (flags & MNT_TREE_MNTNS_INIT) {
+ if (mp.parent != target_mnt_ns->root)
+ return -EBUSY;
+ } else if (mp.mp->m_dentry == mp.parent->mnt.mnt_root) {
+ const struct mount *m = mp.parent;
+
+ while (m != target_mnt_ns->root && mnt_has_parent(m) &&
+ m->mnt_mountpoint == m->mnt_parent->mnt.mnt_root)
+ m = m->mnt_parent;
+ if (m == target_mnt_ns->root)
+ return beneath ? -EINVAL : -EBUSY;
+ }
+ } else if (check_mnt(old)) {
/* if the source is in our namespace... */
/* ... it should be detachable from parent */
if (!mnt_has_parent(old) || IS_MNT_LOCKED(old))
@@ -3840,12 +3877,14 @@ static int do_move_mount(const struct path *old_path,
*/
if (IS_MNT_SHARED(mp.parent) && tree_contains_unbindable(old))
return -EINVAL;
- if (!check_for_nsfs_mounts(old))
+ dest_mnt_ns = is_anon_ns(mp.parent->mnt_ns) ?
+ current->nsproxy->mnt_ns : mp.parent->mnt_ns;
+ if (!check_for_nsfs_mounts(old, dest_mnt_ns))
return -ELOOP;
if (mount_is_ancestor(old, mp.parent))
return -ELOOP;
- return attach_recursive_mnt(old, &mp);
+ return attach_recursive_mnt(old, &mp, flags & MNT_TREE_MNTNS);
}
static int do_move_mount_old(const struct path *path, const char *old_name)
@@ -3860,7 +3899,7 @@ static int do_move_mount_old(const struct path *path, const char *old_name)
if (err)
return err;
- return do_move_mount(&old_path, path, 0);
+ return do_move_mount(&old_path, path, 0, NULL);
}
/*
@@ -4740,7 +4779,8 @@ SYSCALL_DEFINE3(fsmount, int, fs_fd, unsigned int, flags,
static inline int vfs_move_mount(const struct path *from_path,
const struct path *to_path,
- enum mnt_tree_flags_t mflags)
+ enum mnt_tree_flags_t mflags,
+ struct mnt_namespace *target_mnt_ns)
{
int ret;
@@ -4751,7 +4791,123 @@ static inline int vfs_move_mount(const struct path *from_path,
if (mflags & MNT_TREE_PROPAGATION)
return do_set_group(from_path, to_path);
- return do_move_mount(from_path, to_path, mflags);
+ return do_move_mount(from_path, to_path, mflags, target_mnt_ns);
+}
+
+static int lookup_move_mount_from(int from_dfd,
+ const char __user *from_pathname,
+ unsigned int flags, struct path *from_path)
+{
+ unsigned int uflags = 0;
+ unsigned int lflags = 0;
+
+ if (flags & MOVE_MOUNT_F_EMPTY_PATH)
+ uflags = AT_EMPTY_PATH;
+
+ CLASS(filename_maybe_null, from_name)(from_pathname, uflags);
+ if (!from_name && from_dfd >= 0) {
+ CLASS(fd_raw, f_from)(from_dfd);
+ if (fd_empty(f_from))
+ return -EBADF;
+
+ *from_path = fd_file(f_from)->f_path;
+ path_get(from_path);
+ return 0;
+ }
+
+ if (flags & MOVE_MOUNT_F_SYMLINKS)
+ lflags |= LOOKUP_FOLLOW;
+ if (flags & MOVE_MOUNT_F_AUTOMOUNTS)
+ lflags |= LOOKUP_AUTOMOUNT;
+ return filename_lookup(from_dfd, from_name, lflags, from_path, NULL);
+}
+
+/**
+ * DOC: MOVE_MOUNT_T_MNTNS
+ *
+ * ``MOVE_MOUNT_T_MNTNS`` installs detached anonymous mount trees into a target
+ * mount namespace ``nsfs`` file descriptor supplied as ``to_dfd``:
+ *
+ * 1. ``to_pathname`` of ``"/"`` attaches the initial root mount onto the
+ * ``nullfs`` root of an empty mount namespace at most once.
+ *
+ * 2. Relative ``to_pathname`` values resolve beneath the live root of the
+ * target mount namespace.
+ *
+ * Capability is checked against ``CAP_SYS_ADMIN`` in the target mount
+ * namespace's owning user namespace, and source trees crossing user namespace
+ * boundaries are locked with ``MNT_LOCKED`` and locked mount flags.
+ */
+static int move_mount_mntns(int from_dfd, const char __user *from_pathname,
+ int to_dfd, const char __user *to_pathname,
+ unsigned int flags, enum mnt_tree_flags_t mflags)
+{
+ struct path from_path __free(path_put) = {};
+ struct path to_path __free(path_put) = {};
+ struct mnt_namespace *target_mnt_ns;
+ unsigned int lflags;
+ struct ns_common *ns;
+ bool is_root;
+ int ret;
+
+ CLASS(filename_maybe_null, to_name)(to_pathname, AT_EMPTY_PATH);
+ if (IS_ERR(to_name))
+ return PTR_ERR(to_name);
+ if (!to_name)
+ return -EINVAL;
+
+ CLASS(fd, f_mntns)(to_dfd);
+ if (fd_empty(f_mntns))
+ return -EBADF;
+ if (!proc_ns_file(fd_file(f_mntns)))
+ return -EINVAL;
+
+ ns = get_proc_ns(file_inode(fd_file(f_mntns)));
+ if (ns->ns_type != CLONE_NEWNS)
+ return -EINVAL;
+
+ target_mnt_ns = to_mnt_ns(ns);
+ if (is_anon_ns(target_mnt_ns))
+ return -EINVAL;
+ if (!ns_capable(target_mnt_ns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ is_root = to_name->name[0] == '/' && to_name->name[1] == '\0';
+ if (is_root) {
+ if (flags & MOVE_MOUNT_BENEATH)
+ return -EINVAL;
+
+ to_path.mnt = mntget(&target_mnt_ns->root->mnt);
+ to_path.dentry = dget(target_mnt_ns->root->mnt.mnt_root);
+ mflags |= MNT_TREE_MNTNS_INIT;
+ } else {
+ struct path mntns_root __free(path_put) = {};
+
+ if (to_name->name[0] == '/')
+ return -EINVAL;
+
+ ret = mnt_ns_get_root(target_mnt_ns, &mntns_root);
+ if (ret)
+ return ret;
+
+ lflags = LOOKUP_IN_ROOT;
+ if (flags & MOVE_MOUNT_T_SYMLINKS)
+ lflags |= LOOKUP_FOLLOW;
+ if (flags & MOVE_MOUNT_T_AUTOMOUNTS)
+ lflags |= LOOKUP_AUTOMOUNT;
+ ret = filename_lookup(AT_FDCWD, to_name, lflags, &to_path,
+ &mntns_root);
+ if (ret)
+ return ret;
+ }
+
+ ret = lookup_move_mount_from(from_dfd, from_pathname, flags,
+ &from_path);
+ if (ret)
+ return ret;
+
+ return vfs_move_mount(&from_path, &to_path, mflags | MNT_TREE_MNTNS,
+ target_mnt_ns);
}
/*
@@ -4773,7 +4929,7 @@ SYSCALL_DEFINE5(move_mount,
enum mnt_tree_flags_t mflags = 0;
int ret = 0;
- if (!may_mount())
+ if (!(flags & MOVE_MOUNT_T_MNTNS) && !may_mount())
return -EPERM;
if (flags & ~MOVE_MOUNT__MASK)
@@ -4786,6 +4942,13 @@ SYSCALL_DEFINE5(move_mount,
if (flags & MOVE_MOUNT_SET_GROUP) mflags |= MNT_TREE_PROPAGATION;
if (flags & MOVE_MOUNT_BENEATH) mflags |= MNT_TREE_BENEATH;
+ if (unlikely(flags & MOVE_MOUNT_T_MNTNS)) {
+ if (flags & (MOVE_MOUNT_T_EMPTY_PATH | MOVE_MOUNT_SET_GROUP))
+ return -EINVAL;
+ return move_mount_mntns(from_dfd, from_pathname,
+ to_dfd, to_pathname, flags, mflags);
+ }
+
uflags = 0;
if (flags & MOVE_MOUNT_T_EMPTY_PATH)
uflags = AT_EMPTY_PATH;
@@ -4809,29 +4972,12 @@ SYSCALL_DEFINE5(move_mount,
return ret;
}
- uflags = 0;
- if (flags & MOVE_MOUNT_F_EMPTY_PATH)
- uflags = AT_EMPTY_PATH;
-
- CLASS(filename_maybe_null,from_name)(from_pathname, uflags);
- if (!from_name && from_dfd >= 0) {
- CLASS(fd_raw, f_from)(from_dfd);
- if (fd_empty(f_from))
- return -EBADF;
-
- 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);
+ ret = lookup_move_mount_from(from_dfd, from_pathname, flags,
+ &from_path);
if (ret)
return ret;
- return vfs_move_mount(&from_path, &to_path, mflags);
+ return vfs_move_mount(&from_path, &to_path, mflags, NULL);
}
/*
diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h
index cb55cfcfc92e..7fa93de08ceb 100644
--- a/include/uapi/linux/mount.h
+++ b/include/uapi/linux/mount.h
@@ -75,9 +75,10 @@
#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */
#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */
#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
+#define MOVE_MOUNT_T_MNTNS 0x00000080 /* Resolve to_dfd as mntns fd */
#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */
#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */
-#define MOVE_MOUNT__MASK 0x00000377
+#define MOVE_MOUNT__MASK 0x000003f7
/*
* fsopen() flags.
--
2.47.3