2019-05-28 10:10:12 -07:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-only */
|
2005-11-07 17:19:07 -05:00
|
|
|
/*
|
|
|
|
|
* linux/fs/pnode.h
|
|
|
|
|
*
|
|
|
|
|
* (C) Copyright IBM Corporation 2005.
|
|
|
|
|
*/
|
|
|
|
|
#ifndef _LINUX_PNODE_H
|
|
|
|
|
#define _LINUX_PNODE_H
|
|
|
|
|
|
|
|
|
|
#include <linux/list.h>
|
2011-11-23 19:26:23 -05:00
|
|
|
#include "mount.h"
|
2005-11-07 17:19:33 -05:00
|
|
|
|
2025-06-21 18:06:19 -04:00
|
|
|
#define IS_MNT_SHARED(m) ((m)->mnt_t_flags & T_SHARED)
|
2011-11-25 01:05:37 -05:00
|
|
|
#define IS_MNT_SLAVE(m) ((m)->mnt_master)
|
fix IS_MNT_PROPAGATING uses
propagate_mnt() does not attach anything to mounts created during
propagate_mnt() itself. What's more, anything on ->mnt_slave_list
of such new mount must also be new, so we don't need to even look
there.
When move_mount() had been introduced, we've got an additional
class of mounts to skip - if we are moving from anon namespace,
we do not want to propagate to mounts we are moving (i.e. all
mounts in that anon namespace).
Unfortunately, the part about "everything on their ->mnt_slave_list
will also be ignorable" is not true - if we have propagation graph
A -> B -> C
and do OPEN_TREE_CLONE open_tree() of B, we get
A -> [B <-> B'] -> C
as propagation graph, where B' is a clone of B in our detached tree.
Making B private will result in
A -> B' -> C
C still gets propagation from A, as it would after making B private
if we hadn't done that open_tree(), but now the propagation goes
through B'. Trying to move_mount() our detached tree on subdirectory
in A should have
* moved B' on that subdirectory in A
* skipped the corresponding subdirectory in B' itself
* copied B' on the corresponding subdirectory in C.
As it is, the logics in propagation_next() and friends ends up
skipping propagation into C, since it doesn't consider anything
downstream of B'.
IOW, walking the propagation graph should only skip the ->mnt_slave_list
of new mounts; the only places where the check for "in that one
anon namespace" are applicable are propagate_one() (where we should
treat that as the same kind of thing as "mountpoint we are looking
at is not visible in the mount we are looking at") and
propagation_would_overmount(). The latter is better dealt with
in the caller (can_move_mount_beneath()); on the first call of
propagation_would_overmount() the test is always false, on the
second it is always true in "move from anon namespace" case and
always false in "move within our namespace" one, so it's easier
to just use check_mnt() before bothering with the second call and
be done with that.
Fixes: 064fe6e233e8 ("mount: handle mount propagation for detached mount trees")
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2025-05-08 15:35:51 -04:00
|
|
|
#define IS_MNT_NEW(m) (!(m)->mnt_ns)
|
2025-06-21 18:06:19 -04:00
|
|
|
#define CLEAR_MNT_SHARED(m) ((m)->mnt_t_flags &= ~T_SHARED)
|
|
|
|
|
#define IS_MNT_UNBINDABLE(m) ((m)->mnt_t_flags & T_UNBINDABLE)
|
|
|
|
|
#define IS_MNT_MARKED(m) ((m)->mnt_t_flags & T_MARKED)
|
|
|
|
|
#define SET_MNT_MARK(m) ((m)->mnt_t_flags |= T_MARKED)
|
|
|
|
|
#define CLEAR_MNT_MARK(m) ((m)->mnt_t_flags &= ~T_MARKED)
|
2015-01-05 13:38:04 -06:00
|
|
|
#define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
|
2005-11-07 17:19:33 -05:00
|
|
|
|
2005-11-07 17:19:50 -05:00
|
|
|
#define CL_EXPIRE 0x01
|
2005-11-07 17:20:48 -05:00
|
|
|
#define CL_SLAVE 0x02
|
2013-03-30 01:35:18 -07:00
|
|
|
#define CL_COPY_UNBINDABLE 0x04
|
2005-11-07 17:19:50 -05:00
|
|
|
#define CL_MAKE_SHARED 0x08
|
2010-01-16 13:28:47 -05:00
|
|
|
#define CL_PRIVATE 0x10
|
2019-01-30 13:15:45 -05:00
|
|
|
#define CL_COPY_MNT_NS_FILE 0x40
|
2013-03-30 01:35:18 -07:00
|
|
|
|
2025-06-21 18:06:19 -04:00
|
|
|
/*
|
|
|
|
|
* EXCL[namespace_sem]
|
|
|
|
|
*/
|
2011-11-24 20:43:10 -05:00
|
|
|
static inline void set_mnt_shared(struct mount *mnt)
|
2005-11-07 17:19:50 -05:00
|
|
|
{
|
2025-06-21 18:06:19 -04:00
|
|
|
mnt->mnt_t_flags &= ~T_SHARED_MASK;
|
|
|
|
|
mnt->mnt_t_flags |= T_SHARED;
|
2005-11-07 17:19:50 -05:00
|
|
|
}
|
|
|
|
|
|
2025-05-08 17:28:00 -04:00
|
|
|
static inline bool peers(const struct mount *m1, const struct mount *m2)
|
|
|
|
|
{
|
|
|
|
|
return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
|
|
|
|
|
}
|
|
|
|
|
|
2011-11-24 20:43:10 -05:00
|
|
|
void change_mnt_propagation(struct mount *, int);
|
2025-08-19 12:22:03 -04:00
|
|
|
void bulk_make_private(struct list_head *);
|
2013-03-15 10:53:28 -04:00
|
|
|
int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
|
2014-03-20 21:10:51 -04:00
|
|
|
struct hlist_head *);
|
2025-05-14 20:50:06 -04:00
|
|
|
void propagate_umount(struct list_head *);
|
2011-11-24 21:35:16 -05:00
|
|
|
int propagate_mount_busy(struct mount *, int);
|
2015-01-03 05:39:35 -06:00
|
|
|
void propagate_mount_unlock(struct mount *);
|
2011-11-24 19:54:23 -05:00
|
|
|
void mnt_release_group_id(struct mount *);
|
2011-11-24 23:35:54 -05:00
|
|
|
int get_dominating_id(struct mount *mnt, const struct path *root);
|
2020-10-31 21:40:21 -07:00
|
|
|
int mnt_get_count(struct mount *mnt);
|
2013-03-15 10:53:28 -04:00
|
|
|
void mnt_set_mountpoint(struct mount *, struct mountpoint *,
|
2011-11-24 21:28:22 -05:00
|
|
|
struct mount *);
|
2017-01-20 18:28:35 +13:00
|
|
|
void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
|
|
|
|
|
struct mount *mnt);
|
2011-11-24 21:24:27 -05:00
|
|
|
struct mount *copy_tree(struct mount *, struct dentry *, int);
|
2011-11-24 22:00:28 -05:00
|
|
|
bool is_path_reachable(struct mount *, struct dentry *,
|
2011-11-23 19:34:49 -05:00
|
|
|
const struct path *root);
|
2016-09-28 00:27:17 -05:00
|
|
|
int count_mounts(struct mnt_namespace *ns, struct mount *mnt);
|
fs: allow to mount beneath top mount
Various distributions are adding or are in the process of adding support
for system extensions and in the future configuration extensions through
various tools. A more detailed explanation on system and configuration
extensions can be found on the manpage which is listed below at [1].
System extension images may – dynamically at runtime — extend the /usr/
and /opt/ directory hierarchies with additional files. This is
particularly useful on immutable system images where a /usr/ and/or
/opt/ hierarchy residing on a read-only file system shall be extended
temporarily at runtime without making any persistent modifications.
When one or more system extension images are activated, their /usr/ and
/opt/ hierarchies are combined via overlayfs with the same hierarchies
of the host OS, and the host /usr/ and /opt/ overmounted with it
("merging"). When they are deactivated, the mount point is disassembled
— again revealing the unmodified original host version of the hierarchy
("unmerging"). Merging thus makes the extension's resources suddenly
appear below the /usr/ and /opt/ hierarchies as if they were included in
the base OS image itself. Unmerging makes them disappear again, leaving
in place only the files that were shipped with the base OS image itself.
System configuration images are similar but operate on directories
containing system or service configuration.
On nearly all modern distributions mount propagation plays a crucial
role and the rootfs of the OS is a shared mount in a peer group (usually
with peer group id 1):
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/ / ext4 shared:1 29 1
On such systems all services and containers run in a separate mount
namespace and are pivot_root()ed into their rootfs. A separate mount
namespace is almost always used as it is the minimal isolation mechanism
services have. But usually they are even much more isolated up to the
point where they almost become indistinguishable from containers.
Mount propagation again plays a crucial role here. The rootfs of all
these services is a slave mount to the peer group of the host rootfs.
This is done so the service will receive mount propagation events from
the host when certain files or directories are updated.
In addition, the rootfs of each service, container, and sandbox is also
a shared mount in its separate peer group:
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/ / ext4 shared:24 master:1 71 47
For people not too familiar with mount propagation, the master:1 means
that this is a slave mount to peer group 1. Which as one can see is the
host rootfs as indicated by shared:1 above. The shared:24 indicates that
the service rootfs is a shared mount in a separate peer group with peer
group id 24.
A service may run other services. Such nested services will also have a
rootfs mount that is a slave to the peer group of the outer service
rootfs mount.
For containers things are just slighly different. A container's rootfs
isn't a slave to the service's or host rootfs' peer group. The rootfs
mount of a container is simply a shared mount in its own peer group:
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/home/ubuntu/debian-tree / ext4 shared:99 61 60
So whereas services are isolated OS components a container is treated
like a separate world and mount propagation into it is restricted to a
single well known mount that is a slave to the peer group of the shared
mount /run on the host:
TARGET SOURCE FSTYPE PROPAGATION MNT_ID PARENT_ID
/propagate/debian-tree /run/host/incoming tmpfs master:5 71 68
Here, the master:5 indicates that this mount is a slave to the peer
group with peer group id 5. This allows to propagate mounts into the
container and served as a workaround for not being able to insert mounts
into mount namespaces directly. But the new mount api does support
inserting mounts directly. For the interested reader the blogpost in [2]
might be worth reading where I explain the old and the new approach to
inserting mounts into mount namespaces.
Containers of course, can themselves be run as services. They often run
full systems themselves which means they again run services and
containers with the exact same propagation settings explained above.
The whole system is designed so that it can be easily updated, including
all services in various fine-grained ways without having to enter every
single service's mount namespace which would be prohibitively expensive.
The mount propagation layout has been carefully chosen so it is possible
to propagate updates for system extensions and configurations from the
host into all services.
The simplest model to update the whole system is to mount on top of
/usr, /opt, or /etc on the host. The new mount on /usr, /opt, or /etc
will then propagate into every service. This works cleanly the first
time. However, when the system is updated multiple times it becomes
necessary to unmount the first update on /opt, /usr, /etc and then
propagate the new update. But this means, there's an interval where the
old base system is accessible. This has to be avoided to protect against
downgrade attacks.
The vfs already exposes a mechanism to userspace whereby mounts can be
mounted beneath an existing mount. Such mounts are internally referred
to as "tucked". The patch series exposes the ability to mount beneath a
top mount through the new MOVE_MOUNT_BENEATH flag for the move_mount()
system call. This allows userspace to seamlessly upgrade mounts. After
this series the only thing that will have changed is that mounting
beneath an existing mount can be done explicitly instead of just
implicitly.
Today, there are two scenarios where a mount can be mounted beneath an
existing mount instead of on top of it:
(1) When a service or container is started in a new mount namespace and
pivot_root()s into its new rootfs. The way this is done is by
mounting the new rootfs beneath the old rootfs:
fd_newroot = open("/var/lib/machines/fedora", ...);
fd_oldroot = open("/", ...);
fchdir(fd_newroot);
pivot_root(".", ".");
After the pivot_root(".", ".") call the new rootfs is mounted
beneath the old rootfs which can then be unmounted to reveal the
underlying mount:
fchdir(fd_oldroot);
umount2(".", MNT_DETACH);
Since pivot_root() moves the caller into a new rootfs no mounts must
be propagated out of the new rootfs as a consequence of the
pivot_root() call. Thus, the mounts cannot be shared.
(2) When a mount is propagated to a mount that already has another mount
mounted on the same dentry.
The easiest example for this is to create a new mount namespace. The
following commands will create a mount namespace where the rootfs
mount / will be a slave to the peer group of the host rootfs /
mount's peer group. IOW, it will receive propagation from the host:
mount --make-shared /
unshare --mount --propagation=slave
Now a new mount on the /mnt dentry in that mount namespace is
created. (As it can be confusing it should be spelled out that the
tmpfs mount on the /mnt dentry that was just created doesn't
propagate back to the host because the rootfs mount / of the mount
namespace isn't a peer of the host rootfs.):
mount -t tmpfs tmpfs /mnt
TARGET SOURCE FSTYPE PROPAGATION
└─/mnt tmpfs tmpfs
Now another terminal in the host mount namespace can observe that
the mount indeed hasn't propagated back to into the host mount
namespace. A new mount can now be created on top of the /mnt dentry
with the rootfs mount / as its parent:
mount --bind /opt /mnt
TARGET SOURCE FSTYPE PROPAGATION
└─/mnt /dev/sda2[/opt] ext4 shared:1
The mount namespace that was created earlier can now observe that
the bind mount created on the host has propagated into it:
TARGET SOURCE FSTYPE PROPAGATION
└─/mnt /dev/sda2[/opt] ext4 master:1
└─/mnt tmpfs tmpfs
But instead of having been mounted on top of the tmpfs mount at the
/mnt dentry the /opt mount has been mounted on top of the rootfs
mount at the /mnt dentry. And the tmpfs mount has been remounted on
top of the propagated /opt mount at the /opt dentry. So in other
words, the propagated mount has been mounted beneath the preexisting
mount in that mount namespace.
Mount namespaces make this easy to illustrate but it's also easy to
mount beneath an existing mount in the same mount namespace
(The following example assumes a shared rootfs mount / with peer
group id 1):
mount --bind /opt /opt
TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION
└─/opt /dev/sda2[/opt] ext4 188 29 shared:1
If another mount is mounted on top of the /opt mount at the /opt
dentry:
mount --bind /tmp /opt
The following clunky mount tree will result:
TARGET SOURCE FSTYPE MNT_ID PARENT_ID PROPAGATION
└─/opt /dev/sda2[/tmp] ext4 405 29 shared:1
└─/opt /dev/sda2[/opt] ext4 188 405 shared:1
└─/opt /dev/sda2[/tmp] ext4 404 188 shared:1
The /tmp mount is mounted beneath the /opt mount and another copy is
mounted on top of the /opt mount. This happens because the rootfs /
and the /opt mount are shared mounts in the same peer group.
When the new /tmp mount is supposed to be mounted at the /opt dentry
then the /tmp mount first propagates to the root mount at the /opt
dentry. But there already is the /opt mount mounted at the /opt
dentry. So the old /opt mount at the /opt dentry will be mounted on
top of the new /tmp mount at the /tmp dentry, i.e. @opt->mnt_parent
is @tmp and @opt->mnt_mountpoint is /tmp (Note that @opt->mnt_root
is /opt which is what shows up as /opt under SOURCE). So again, a
mount will be mounted beneath a preexisting mount.
(Fwiw, a few iterations of mount --bind /opt /opt in a loop on a
shared rootfs is a good example of what could be referred to as
mount explosion.)
The main point is that such mounts allows userspace to umount a top
mount and reveal an underlying mount. So for example, umounting the
tmpfs mount on /mnt that was created in example (1) using mount
namespaces reveals the /opt mount which was mounted beneath it.
In (2) where a mount was mounted beneath the top mount in the same mount
namespace unmounting the top mount would unmount both the top mount and
the mount beneath. In the process the original mount would be remounted
on top of the rootfs mount / at the /opt dentry again.
This again, is a result of mount propagation only this time it's umount
propagation. However, this can be avoided by simply making the parent
mount / of the @opt mount a private or slave mount. Then the top mount
and the original mount can be unmounted to reveal the mount beneath.
These two examples are fairly arcane and are merely added to make it
clear how mount propagation has effects on current and future features.
More common use-cases will just be things like:
mount -t btrfs /dev/sdA /mnt
mount -t xfs /dev/sdB --beneath /mnt
umount /mnt
after which we'll have updated from a btrfs filesystem to a xfs
filesystem without ever revealing the underlying mountpoint.
The crux is that the proposed mechanism already exists and that it is so
powerful as to cover cases where mounts are supposed to be updated with
new versions. Crucially, it offers an important flexibility. Namely that
updates to a system may either be forced or can be delayed and the
umount of the top mount be left to a service if it is a cooperative one.
This adds a new flag to move_mount() that allows to explicitly move a
beneath the top mount adhering to the following semantics:
* Mounts cannot be mounted beneath the rootfs. This restriction
encompasses the rootfs but also chroots via chroot() and pivot_root().
To mount a mount beneath the rootfs or a chroot, pivot_root() can be
used as illustrated above.
* The source mount must be a private mount to force the kernel to
allocate a new, unused peer group id. This isn't a required
restriction but a voluntary one. It avoids repeating a semantical
quirk that already exists today. If bind mounts which already have a
peer group id are inserted into mount trees that have the same peer
group id this can cause a lot of mount propagation events to be
generated (For example, consider running mount --bind /opt /opt in a
loop where the parent mount is a shared mount.).
* Avoid getting rid of the top mount in the kernel. Cooperative services
need to be able to unmount the top mount themselves.
This also avoids a good deal of additional complexity. The umount
would have to be propagated which would be another rather expensive
operation. So namespace_lock() and lock_mount_hash() would potentially
have to be held for a long time for both a mount and umount
propagation. That should be avoided.
* The path to mount beneath must be mounted and attached.
* The top mount and its parent must be in the caller's mount namespace
and the caller must be able to mount in that mount namespace.
* The caller must be able to unmount the top mount to prove that they
could reveal the underlying mount.
* The propagation tree is calculated based on the destination mount's
parent mount and the destination mount's mountpoint on the parent
mount. Of course, if the parent of the destination mount and the
destination mount are shared mounts in the same peer group and the
mountpoint of the new mount to be mounted is a subdir of their
->mnt_root then both will receive a mount of /opt. That's probably
easier to understand with an example. Assuming a standard shared
rootfs /:
mount --bind /opt /opt
mount --bind /tmp /opt
will cause the same mount tree as:
mount --bind /opt /opt
mount --beneath /tmp /opt
because both / and /opt are shared mounts/peers in the same peer
group and the /opt dentry is a subdirectory of both the parent's and
the child's ->mnt_root. If a mount tree like that is created it almost
always is an accident or abuse of mount propagation. Realistically
what most people probably mean in this scenarios is:
mount --bind /opt /opt
mount --make-private /opt
mount --make-shared /opt
This forces the allocation of a new separate peer group for the /opt
mount. Aferwards a mount --bind or mount --beneath actually makes
sense as the / and /opt mount belong to different peer groups. Before
that it's likely just confusion about what the user wanted to achieve.
* Refuse MOVE_MOUNT_BENEATH if:
(1) the @mnt_from has been overmounted in between path resolution and
acquiring @namespace_sem when locking @mnt_to. This avoids the
proliferation of shadow mounts.
(2) if @to_mnt is moved to a different mountpoint while acquiring
@namespace_sem to lock @to_mnt.
(3) if @to_mnt is unmounted while acquiring @namespace_sem to lock
@to_mnt.
(4) if the parent of the target mount propagates to the target mount
at the same mountpoint.
This would mean mounting @mnt_from on @mnt_to->mnt_parent and then
propagating a copy @c of @mnt_from onto @mnt_to. This defeats the
whole purpose of mounting @mnt_from beneath @mnt_to.
(5) if the parent mount @mnt_to->mnt_parent propagates to @mnt_from at
the same mountpoint.
If @mnt_to->mnt_parent propagates to @mnt_from this would mean
propagating a copy @c of @mnt_from on top of @mnt_from. Afterwards
@mnt_from would be mounted on top of @mnt_to->mnt_parent and
@mnt_to would be unmounted from @mnt->mnt_parent and remounted on
@mnt_from. But since @c is already mounted on @mnt_from, @mnt_to
would ultimately be remounted on top of @c. Afterwards, @mnt_from
would be covered by a copy @c of @mnt_from and @c would be covered
by @mnt_from itself. This defeats the whole purpose of mounting
@mnt_from beneath @mnt_to.
Cases (1) to (3) are required as they deal with races that would cause
bugs or unexpected behavior for users. Cases (4) and (5) refuse
semantical quirks that would not be a bug but would cause weird mount
trees to be created. While they can already be created via other means
(mount --bind /opt /opt x n) there's no reason to repeat past mistakes
in new features.
Link: https://man7.org/linux/man-pages/man8/systemd-sysext.8.html [1]
Link: https://brauner.io/2023/02/28/mounting-into-mount-namespaces.html [2]
Link: https://github.com/flatcar/sysext-bakery
Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_1
Link: https://fedoraproject.org/wiki/Changes/Unified_Kernel_Support_Phase_2
Link: https://github.com/systemd/systemd/pull/26013
Reviewed-by: Seth Forshee (DigitalOcean) <sforshee@kernel.org>
Message-Id: <20230202-fs-move-mount-replace-v4-4-98f3d80d7eaa@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
2023-05-03 13:18:42 +02:00
|
|
|
bool propagation_would_overmount(const struct mount *from,
|
|
|
|
|
const struct mount *to,
|
|
|
|
|
const struct mountpoint *mp);
|
2005-11-07 17:19:07 -05:00
|
|
|
#endif /* _LINUX_PNODE_H */
|