2018-11-01 23:07:23 +00:00
|
|
|
#ifndef _UAPI_LINUX_MOUNT_H
|
|
|
|
#define _UAPI_LINUX_MOUNT_H
|
|
|
|
|
fs: add mount_setattr()
This implements the missing mount_setattr() syscall. While the new mount
api allows to change the properties of a superblock there is currently
no way to change the properties of a mount or a mount tree using file
descriptors which the new mount api is based on. In addition the old
mount api has the restriction that mount options cannot be applied
recursively. This hasn't changed since changing mount options on a
per-mount basis was implemented in [1] and has been a frequent request
not just for convenience but also for security reasons. The legacy
mount syscall is unable to accommodate this behavior without introducing
a whole new set of flags because MS_REC | MS_REMOUNT | MS_BIND |
MS_RDONLY | MS_NOEXEC | [...] only apply the mount option to the topmost
mount. Changing MS_REC to apply to the whole mount tree would mean
introducing a significant uapi change and would likely cause significant
regressions.
The new mount_setattr() syscall allows to recursively clear and set
mount options in one shot. Multiple calls to change mount options
requesting the same changes are idempotent:
int mount_setattr(int dfd, const char *path, unsigned flags,
struct mount_attr *uattr, size_t usize);
Flags to modify path resolution behavior are specified in the @flags
argument. Currently, AT_EMPTY_PATH, AT_RECURSIVE, AT_SYMLINK_NOFOLLOW,
and AT_NO_AUTOMOUNT are supported. If useful, additional lookup flags to
restrict path resolution as introduced with openat2() might be supported
in the future.
The mount_setattr() syscall can be expected to grow over time and is
designed with extensibility in mind. It follows the extensible syscall
pattern we have used with other syscalls such as openat2(), clone3(),
sched_{set,get}attr(), and others.
The set of mount options is passed in the uapi struct mount_attr which
currently has the following layout:
struct mount_attr {
__u64 attr_set;
__u64 attr_clr;
__u64 propagation;
__u64 userns_fd;
};
The @attr_set and @attr_clr members are used to clear and set mount
options. This way a user can e.g. request that a set of flags is to be
raised such as turning mounts readonly by raising MOUNT_ATTR_RDONLY in
@attr_set while at the same time requesting that another set of flags is
to be lowered such as removing noexec from a mount tree by specifying
MOUNT_ATTR_NOEXEC in @attr_clr.
Note, since the MOUNT_ATTR_<atime> values are an enum starting from 0,
not a bitmap, users wanting to transition to a different atime setting
cannot simply specify the atime setting in @attr_set, but must also
specify MOUNT_ATTR__ATIME in the @attr_clr field. So we ensure that
MOUNT_ATTR__ATIME can't be partially set in @attr_clr and that @attr_set
can't have any atime bits set if MOUNT_ATTR__ATIME isn't set in
@attr_clr.
The @propagation field lets callers specify the propagation type of a
mount tree. Propagation is a single property that has four different
settings and as such is not really a flag argument but an enum.
Specifically, it would be unclear what setting and clearing propagation
settings in combination would amount to. The legacy mount() syscall thus
forbids the combination of multiple propagation settings too. The goal
is to keep the semantics of mount propagation somewhat simple as they
are overly complex as it is.
The @userns_fd field lets user specify a user namespace whose idmapping
becomes the idmapping of the mount. This is implemented and explained in
detail in the next patch.
[1]: commit 2e4b7fcd9260 ("[PATCH] r/o bind mounts: honor mount writer counts at remount")
Link: https://lore.kernel.org/r/20210121131959.646623-35-christian.brauner@ubuntu.com
Cc: David Howells <dhowells@redhat.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:53 +00:00
|
|
|
#include <linux/types.h>
|
|
|
|
|
2018-11-01 23:07:23 +00:00
|
|
|
/*
|
|
|
|
* These are the fs-independent mount-flags: up to 32 flags are supported
|
|
|
|
*
|
|
|
|
* Usage of these is restricted within the kernel to core mount(2) code and
|
|
|
|
* callers of sys_mount() only. Filesystems should be using the SB_*
|
|
|
|
* equivalent instead.
|
|
|
|
*/
|
|
|
|
#define MS_RDONLY 1 /* Mount read-only */
|
|
|
|
#define MS_NOSUID 2 /* Ignore suid and sgid bits */
|
|
|
|
#define MS_NODEV 4 /* Disallow access to device special files */
|
|
|
|
#define MS_NOEXEC 8 /* Disallow program execution */
|
|
|
|
#define MS_SYNCHRONOUS 16 /* Writes are synced at once */
|
|
|
|
#define MS_REMOUNT 32 /* Alter flags of a mounted FS */
|
|
|
|
#define MS_MANDLOCK 64 /* Allow mandatory locks on an FS */
|
|
|
|
#define MS_DIRSYNC 128 /* Directory modifications are synchronous */
|
2020-08-27 17:09:46 +00:00
|
|
|
#define MS_NOSYMFOLLOW 256 /* Do not follow symlinks */
|
2018-11-01 23:07:23 +00:00
|
|
|
#define MS_NOATIME 1024 /* Do not update access times. */
|
|
|
|
#define MS_NODIRATIME 2048 /* Do not update directory access times */
|
|
|
|
#define MS_BIND 4096
|
|
|
|
#define MS_MOVE 8192
|
|
|
|
#define MS_REC 16384
|
|
|
|
#define MS_VERBOSE 32768 /* War is peace. Verbosity is silence.
|
|
|
|
MS_VERBOSE is deprecated. */
|
|
|
|
#define MS_SILENT 32768
|
|
|
|
#define MS_POSIXACL (1<<16) /* VFS does not apply the umask */
|
|
|
|
#define MS_UNBINDABLE (1<<17) /* change to unbindable */
|
|
|
|
#define MS_PRIVATE (1<<18) /* change to private */
|
|
|
|
#define MS_SLAVE (1<<19) /* change to slave */
|
|
|
|
#define MS_SHARED (1<<20) /* change to shared */
|
|
|
|
#define MS_RELATIME (1<<21) /* Update atime relative to mtime/ctime. */
|
|
|
|
#define MS_KERNMOUNT (1<<22) /* this is a kern_mount call */
|
|
|
|
#define MS_I_VERSION (1<<23) /* Update inode I_version field */
|
|
|
|
#define MS_STRICTATIME (1<<24) /* Always perform atime updates */
|
|
|
|
#define MS_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */
|
|
|
|
|
|
|
|
/* These sb flags are internal to the kernel */
|
|
|
|
#define MS_SUBMOUNT (1<<26)
|
|
|
|
#define MS_NOREMOTELOCK (1<<27)
|
|
|
|
#define MS_NOSEC (1<<28)
|
|
|
|
#define MS_BORN (1<<29)
|
|
|
|
#define MS_ACTIVE (1<<30)
|
|
|
|
#define MS_NOUSER (1<<31)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Superblock flags that can be altered by MS_REMOUNT
|
|
|
|
*/
|
|
|
|
#define MS_RMT_MASK (MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION|\
|
|
|
|
MS_LAZYTIME)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Old magic mount flag and mask
|
|
|
|
*/
|
|
|
|
#define MS_MGC_VAL 0xC0ED0000
|
|
|
|
#define MS_MGC_MSK 0xffff0000
|
|
|
|
|
2018-11-05 17:40:30 +00:00
|
|
|
/*
|
|
|
|
* open_tree() flags.
|
|
|
|
*/
|
|
|
|
#define OPEN_TREE_CLONE 1 /* Clone the target tree and attach the clone */
|
|
|
|
#define OPEN_TREE_CLOEXEC O_CLOEXEC /* Close the file on execve() */
|
|
|
|
|
2018-11-05 17:40:30 +00:00
|
|
|
/*
|
|
|
|
* move_mount() flags.
|
|
|
|
*/
|
|
|
|
#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */
|
|
|
|
#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */
|
|
|
|
#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
|
|
|
|
#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 */
|
2021-07-15 10:07:13 +00:00
|
|
|
#define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */
|
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 11:18:42 +00:00
|
|
|
#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */
|
|
|
|
#define MOVE_MOUNT__MASK 0x00000377
|
2018-11-05 17:40:30 +00:00
|
|
|
|
vfs: syscall: Add fsopen() to prepare for superblock creation
Provide an fsopen() system call that starts the process of preparing to
create a superblock that will then be mountable, using an fd as a context
handle. fsopen() is given the name of the filesystem that will be used:
int mfd = fsopen(const char *fsname, unsigned int flags);
where flags can be 0 or FSOPEN_CLOEXEC.
For example:
sfd = fsopen("ext4", FSOPEN_CLOEXEC);
fsconfig(sfd, FSCONFIG_SET_PATH, "source", "/dev/sda1", AT_FDCWD);
fsconfig(sfd, FSCONFIG_SET_FLAG, "noatime", NULL, 0);
fsconfig(sfd, FSCONFIG_SET_FLAG, "acl", NULL, 0);
fsconfig(sfd, FSCONFIG_SET_FLAG, "user_xattr", NULL, 0);
fsconfig(sfd, FSCONFIG_SET_STRING, "sb", "1", 0);
fsconfig(sfd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
fsinfo(sfd, NULL, ...); // query new superblock attributes
mfd = fsmount(sfd, FSMOUNT_CLOEXEC, MS_RELATIME);
move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH);
sfd = fsopen("afs", -1);
fsconfig(fd, FSCONFIG_SET_STRING, "source",
"#grand.central.org:root.cell", 0);
fsconfig(fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0);
mfd = fsmount(sfd, 0, MS_NODEV);
move_mount(mfd, "", sfd, AT_FDCWD, "/mnt", MOVE_MOUNT_F_EMPTY_PATH);
If an error is reported at any step, an error message may be available to be
read() back (ENODATA will be reported if there isn't an error available) in
the form:
"e <subsys>:<problem>"
"e SELinux:Mount on mountpoint not permitted"
Once fsmount() has been called, further fsconfig() calls will incur EBUSY,
even if the fsmount() fails. read() is still possible to retrieve error
information.
The fsopen() syscall creates a mount context and hangs it of the fd that it
returns.
Netlink is not used because it is optional and would make the core VFS
dependent on the networking layer and also potentially add network
namespace issues.
Note that, for the moment, the caller must have SYS_CAP_ADMIN to use
fsopen().
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:33:31 +00:00
|
|
|
/*
|
|
|
|
* fsopen() flags.
|
|
|
|
*/
|
|
|
|
#define FSOPEN_CLOEXEC 0x00000001
|
|
|
|
|
vfs: syscall: Add fspick() to select a superblock for reconfiguration
Provide an fspick() system call that can be used to pick an existing
mountpoint into an fs_context which can thereafter be used to reconfigure a
superblock (equivalent of the superblock side of -o remount).
This looks like:
int fd = fspick(AT_FDCWD, "/mnt",
FSPICK_CLOEXEC | FSPICK_NO_AUTOMOUNT);
fsconfig(fd, FSCONFIG_SET_FLAG, "intr", NULL, 0);
fsconfig(fd, FSCONFIG_SET_FLAG, "noac", NULL, 0);
fsconfig(fd, FSCONFIG_CMD_RECONFIGURE, NULL, NULL, 0);
At the point of fspick being called, the file descriptor referring to the
filesystem context is in exactly the same state as the one that was created
by fsopen() after fsmount() has been successfully called.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:36:23 +00:00
|
|
|
/*
|
|
|
|
* fspick() flags.
|
|
|
|
*/
|
|
|
|
#define FSPICK_CLOEXEC 0x00000001
|
|
|
|
#define FSPICK_SYMLINK_NOFOLLOW 0x00000002
|
|
|
|
#define FSPICK_NO_AUTOMOUNT 0x00000004
|
|
|
|
#define FSPICK_EMPTY_PATH 0x00000008
|
|
|
|
|
vfs: syscall: Add fsconfig() for configuring and managing a context
Add a syscall for configuring a filesystem creation context and triggering
actions upon it, to be used in conjunction with fsopen, fspick and fsmount.
long fsconfig(int fs_fd, unsigned int cmd, const char *key,
const void *value, int aux);
Where fs_fd indicates the context, cmd indicates the action to take, key
indicates the parameter name for parameter-setting actions and, if needed,
value points to a buffer containing the value and aux can give more
information for the value.
The following command IDs are proposed:
(*) FSCONFIG_SET_FLAG: No value is specified. The parameter must be
boolean in nature. The key may be prefixed with "no" to invert the
setting. value must be NULL and aux must be 0.
(*) FSCONFIG_SET_STRING: A string value is specified. The parameter can
be expecting boolean, integer, string or take a path. A conversion to
an appropriate type will be attempted (which may include looking up as
a path). value points to a NUL-terminated string and aux must be 0.
(*) FSCONFIG_SET_BINARY: A binary blob is specified. value points to
the blob and aux indicates its size. The parameter must be expecting
a blob.
(*) FSCONFIG_SET_PATH: A non-empty path is specified. The parameter must
be expecting a path object. value points to a NUL-terminated string
that is the path and aux is a file descriptor at which to start a
relative lookup or AT_FDCWD.
(*) FSCONFIG_SET_PATH_EMPTY: As fsconfig_set_path, but with AT_EMPTY_PATH
implied.
(*) FSCONFIG_SET_FD: An open file descriptor is specified. value must
be NULL and aux indicates the file descriptor.
(*) FSCONFIG_CMD_CREATE: Trigger superblock creation.
(*) FSCONFIG_CMD_RECONFIGURE: Trigger superblock reconfiguration.
For the "set" command IDs, the idea is that the file_system_type will point
to a list of parameters and the types of value that those parameters expect
to take. The core code can then do the parse and argument conversion and
then give the LSM and FS a cooked option or array of options to use.
Source specification is also done the same way same way, using special keys
"source", "source1", "source2", etc..
[!] Note that, for the moment, the key and value are just glued back
together and handed to the filesystem. Every filesystem that uses options
uses match_token() and co. to do this, and this will need to be changed -
but not all at once.
Example usage:
fd = fsopen("ext4", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_path, "source", "/dev/sda1", AT_FDCWD);
fsconfig(fd, fsconfig_set_path_empty, "journal_path", "", journal_fd);
fsconfig(fd, fsconfig_set_fd, "journal_fd", "", journal_fd);
fsconfig(fd, fsconfig_set_flag, "user_xattr", NULL, 0);
fsconfig(fd, fsconfig_set_flag, "noacl", NULL, 0);
fsconfig(fd, fsconfig_set_string, "sb", "1", 0);
fsconfig(fd, fsconfig_set_string, "errors", "continue", 0);
fsconfig(fd, fsconfig_set_string, "data", "journal", 0);
fsconfig(fd, fsconfig_set_string, "context", "unconfined_u:...", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("ext4", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "/dev/sda1", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("afs", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "#grand.central.org:root.cell", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("jffs2", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "mtd0", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:36:09 +00:00
|
|
|
/*
|
|
|
|
* The type of fsconfig() call made.
|
|
|
|
*/
|
|
|
|
enum fsconfig_command {
|
|
|
|
FSCONFIG_SET_FLAG = 0, /* Set parameter, supplying no value */
|
|
|
|
FSCONFIG_SET_STRING = 1, /* Set parameter, supplying a string value */
|
|
|
|
FSCONFIG_SET_BINARY = 2, /* Set parameter, supplying a binary blob value */
|
|
|
|
FSCONFIG_SET_PATH = 3, /* Set parameter, supplying an object by path */
|
|
|
|
FSCONFIG_SET_PATH_EMPTY = 4, /* Set parameter, supplying an object by (empty) path */
|
|
|
|
FSCONFIG_SET_FD = 5, /* Set parameter, supplying an object by fd */
|
fs: add FSCONFIG_CMD_CREATE_EXCL
Summary
=======
This introduces FSCONFIG_CMD_CREATE_EXCL which will allows userspace to
implement something like mount -t ext4 --exclusive /dev/sda /B which
fails if a superblock for the requested filesystem does already exist:
Before this patch
-----------------
$ sudo ./move-mount -f xfs -o source=/dev/sda4 /A
Requesting filesystem type xfs
Mount options requested: source=/dev/sda4
Attaching mount at /A
Moving single attached mount
Setting key(source) with val(/dev/sda4)
$ sudo ./move-mount -f xfs -o source=/dev/sda4 /B
Requesting filesystem type xfs
Mount options requested: source=/dev/sda4
Attaching mount at /B
Moving single attached mount
Setting key(source) with val(/dev/sda4)
After this patch with --exclusive as a switch for FSCONFIG_CMD_CREATE_EXCL
--------------------------------------------------------------------------
$ sudo ./move-mount -f xfs --exclusive -o source=/dev/sda4 /A
Requesting filesystem type xfs
Request exclusive superblock creation
Mount options requested: source=/dev/sda4
Attaching mount at /A
Moving single attached mount
Setting key(source) with val(/dev/sda4)
$ sudo ./move-mount -f xfs --exclusive -o source=/dev/sda4 /B
Requesting filesystem type xfs
Request exclusive superblock creation
Mount options requested: source=/dev/sda4
Attaching mount at /B
Moving single attached mount
Setting key(source) with val(/dev/sda4)
Device or resource busy | move-mount.c: 300: do_fsconfig: i xfs: reusing existing filesystem not allowed
Details
=======
As mentioned on the list (cf. [1]-[3]) mount requests like
mount -t ext4 /dev/sda /A are ambigous for userspace. Either a new
superblock has been created and mounted or an existing superblock has
been reused and a bind-mount has been created.
This becomes clear in the following example where two processes create
the same mount for the same block device:
P1 P2
fd_fs = fsopen("ext4"); fd_fs = fsopen("ext4");
fsconfig(fd_fs, FSCONFIG_SET_STRING, "source", "/dev/sda"); fsconfig(fd_fs, FSCONFIG_SET_STRING, "source", "/dev/sda");
fsconfig(fd_fs, FSCONFIG_SET_STRING, "dax", "always"); fsconfig(fd_fs, FSCONFIG_SET_STRING, "resuid", "1000");
// wins and creates superblock
fsconfig(fd_fs, FSCONFIG_CMD_CREATE, ...)
// finds compatible superblock of P1
// spins until P1 sets SB_BORN and grabs a reference
fsconfig(fd_fs, FSCONFIG_CMD_CREATE, ...)
fd_mnt1 = fsmount(fd_fs); fd_mnt2 = fsmount(fd_fs);
move_mount(fd_mnt1, "/A") move_mount(fd_mnt2, "/B")
Not just does P2 get a bind-mount but the mount options that P2
requestes are silently ignored. The VFS itself doesn't, can't and
shouldn't enforce filesystem specific mount option compatibility. It
only enforces incompatibility for read-only <-> read-write transitions:
mount -t ext4 /dev/sda /A
mount -t ext4 -o ro /dev/sda /B
The read-only request will fail with EBUSY as the VFS can't just
silently transition a superblock from read-write to read-only or vica
versa without risking security issues.
To userspace this silent superblock reuse can become a security issue in
because there is currently no straightforward way for userspace to know
that they did indeed manage to create a new superblock and didn't just
reuse an existing one.
This adds a new FSCONFIG_CMD_CREATE_EXCL command to fsconfig() that
returns EBUSY if an existing superblock would be reused. Userspace that
needs to be sure that it did create a new superblock with the requested
mount options can request superblock creation using this command. If the
command succeeds they can be sure that they did create a new superblock
with the requested mount options.
This requires the new mount api. With the old mount api it would be
necessary to plumb this through every legacy filesystem's
file_system_type->mount() method. If they want this feature they are
most welcome to switch to the new mount api.
Following is an analysis of the effect of FSCONFIG_CMD_CREATE_EXCL on
each high-level superblock creation helper:
(1) get_tree_nodev()
Always allocate new superblock. Hence, FSCONFIG_CMD_CREATE and
FSCONFIG_CMD_CREATE_EXCL are equivalent.
The binderfs or overlayfs filesystems are examples.
(4) get_tree_keyed()
Finds an existing superblock based on sb->s_fs_info. Hence,
FSCONFIG_CMD_CREATE would reuse an existing superblock whereas
FSCONFIG_CMD_CREATE_EXCL would reject it with EBUSY.
The mqueue or nfsd filesystems are examples.
(2) get_tree_bdev()
This effectively works like get_tree_keyed().
The ext4 or xfs filesystems are examples.
(3) get_tree_single()
Only one superblock of this filesystem type can ever exist.
Hence, FSCONFIG_CMD_CREATE would reuse an existing superblock
whereas FSCONFIG_CMD_CREATE_EXCL would reject it with EBUSY.
The securityfs or configfs filesystems are examples.
Note that some single-instance filesystems never destroy the
superblock once it has been created during the first mount. For
example, if securityfs has been mounted at least onces then the
created superblock will never be destroyed again as long as there is
still an LSM making use it. Consequently, even if securityfs is
unmounted and the superblock seemingly destroyed it really isn't
which means that FSCONFIG_CMD_CREATE_EXCL will continue rejecting
reusing an existing superblock.
This is acceptable thugh since special purpose filesystems such as
this shouldn't have a need to use FSCONFIG_CMD_CREATE_EXCL anyway
and if they do it's probably to make sure that mount options aren't
ignored.
Following is an analysis of the effect of FSCONFIG_CMD_CREATE_EXCL on
filesystems that make use of the low-level sget_fc() helper directly.
They're all effectively variants on get_tree_keyed(), get_tree_bdev(),
or get_tree_nodev():
(5) mtd_get_sb()
Similar logic to get_tree_keyed().
(6) afs_get_tree()
Similar logic to get_tree_keyed().
(7) ceph_get_tree()
Similar logic to get_tree_keyed().
Already explicitly allows forcing the allocation of a new superblock
via CEPH_OPT_NOSHARE. This turns it into get_tree_nodev().
(8) fuse_get_tree_submount()
Similar logic to get_tree_nodev().
(9) fuse_get_tree()
Forces reuse of existing FUSE superblock.
Forces reuse of existing superblock if passed in file refers to an
existing FUSE connection.
If FSCONFIG_CMD_CREATE_EXCL is specified together with an fd
referring to an existing FUSE connections this would cause the
superblock reusal to fail. If reusing is the intent then
FSCONFIG_CMD_CREATE_EXCL shouldn't be specified.
(10) fuse_get_tree()
-> get_tree_nodev()
Same logic as in get_tree_nodev().
(11) fuse_get_tree()
-> get_tree_bdev()
Same logic as in get_tree_bdev().
(12) virtio_fs_get_tree()
Same logic as get_tree_keyed().
(13) gfs2_meta_get_tree()
Forces reuse of existing gfs2 superblock.
Mounting gfs2meta enforces that a gf2s superblock must already
exist. If not, it will error out. Consequently, mounting gfs2meta
with FSCONFIG_CMD_CREATE_EXCL would always fail. If reusing is the
intent then FSCONFIG_CMD_CREATE_EXCL shouldn't be specified.
(14) kernfs_get_tree()
Similar logic to get_tree_keyed().
(15) nfs_get_tree_common()
Similar logic to get_tree_keyed().
Already explicitly allows forcing the allocation of a new superblock
via NFS_MOUNT_UNSHARED. This effectively turns it into
get_tree_nodev().
Link: [1] https://lore.kernel.org/linux-block/20230704-fasching-wertarbeit-7c6ffb01c83d@brauner
Link: [2] https://lore.kernel.org/linux-block/20230705-pumpwerk-vielversprechend-a4b1fd947b65@brauner
Link: [3] https://lore.kernel.org/linux-fsdevel/20230725-einnahmen-warnschilder-17779aec0a97@brauner
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Aleksa Sarai <cyphar@cyphar.com>
Message-Id: <20230802-vfs-super-exclusive-v2-4-95dc4e41b870@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
2023-08-02 11:57:06 +00:00
|
|
|
FSCONFIG_CMD_CREATE = 6, /* Create new or reuse existing superblock */
|
vfs: syscall: Add fsconfig() for configuring and managing a context
Add a syscall for configuring a filesystem creation context and triggering
actions upon it, to be used in conjunction with fsopen, fspick and fsmount.
long fsconfig(int fs_fd, unsigned int cmd, const char *key,
const void *value, int aux);
Where fs_fd indicates the context, cmd indicates the action to take, key
indicates the parameter name for parameter-setting actions and, if needed,
value points to a buffer containing the value and aux can give more
information for the value.
The following command IDs are proposed:
(*) FSCONFIG_SET_FLAG: No value is specified. The parameter must be
boolean in nature. The key may be prefixed with "no" to invert the
setting. value must be NULL and aux must be 0.
(*) FSCONFIG_SET_STRING: A string value is specified. The parameter can
be expecting boolean, integer, string or take a path. A conversion to
an appropriate type will be attempted (which may include looking up as
a path). value points to a NUL-terminated string and aux must be 0.
(*) FSCONFIG_SET_BINARY: A binary blob is specified. value points to
the blob and aux indicates its size. The parameter must be expecting
a blob.
(*) FSCONFIG_SET_PATH: A non-empty path is specified. The parameter must
be expecting a path object. value points to a NUL-terminated string
that is the path and aux is a file descriptor at which to start a
relative lookup or AT_FDCWD.
(*) FSCONFIG_SET_PATH_EMPTY: As fsconfig_set_path, but with AT_EMPTY_PATH
implied.
(*) FSCONFIG_SET_FD: An open file descriptor is specified. value must
be NULL and aux indicates the file descriptor.
(*) FSCONFIG_CMD_CREATE: Trigger superblock creation.
(*) FSCONFIG_CMD_RECONFIGURE: Trigger superblock reconfiguration.
For the "set" command IDs, the idea is that the file_system_type will point
to a list of parameters and the types of value that those parameters expect
to take. The core code can then do the parse and argument conversion and
then give the LSM and FS a cooked option or array of options to use.
Source specification is also done the same way same way, using special keys
"source", "source1", "source2", etc..
[!] Note that, for the moment, the key and value are just glued back
together and handed to the filesystem. Every filesystem that uses options
uses match_token() and co. to do this, and this will need to be changed -
but not all at once.
Example usage:
fd = fsopen("ext4", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_path, "source", "/dev/sda1", AT_FDCWD);
fsconfig(fd, fsconfig_set_path_empty, "journal_path", "", journal_fd);
fsconfig(fd, fsconfig_set_fd, "journal_fd", "", journal_fd);
fsconfig(fd, fsconfig_set_flag, "user_xattr", NULL, 0);
fsconfig(fd, fsconfig_set_flag, "noacl", NULL, 0);
fsconfig(fd, fsconfig_set_string, "sb", "1", 0);
fsconfig(fd, fsconfig_set_string, "errors", "continue", 0);
fsconfig(fd, fsconfig_set_string, "data", "journal", 0);
fsconfig(fd, fsconfig_set_string, "context", "unconfined_u:...", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("ext4", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "/dev/sda1", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("afs", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "#grand.central.org:root.cell", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("jffs2", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "mtd0", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:36:09 +00:00
|
|
|
FSCONFIG_CMD_RECONFIGURE = 7, /* Invoke superblock reconfiguration */
|
fs: add FSCONFIG_CMD_CREATE_EXCL
Summary
=======
This introduces FSCONFIG_CMD_CREATE_EXCL which will allows userspace to
implement something like mount -t ext4 --exclusive /dev/sda /B which
fails if a superblock for the requested filesystem does already exist:
Before this patch
-----------------
$ sudo ./move-mount -f xfs -o source=/dev/sda4 /A
Requesting filesystem type xfs
Mount options requested: source=/dev/sda4
Attaching mount at /A
Moving single attached mount
Setting key(source) with val(/dev/sda4)
$ sudo ./move-mount -f xfs -o source=/dev/sda4 /B
Requesting filesystem type xfs
Mount options requested: source=/dev/sda4
Attaching mount at /B
Moving single attached mount
Setting key(source) with val(/dev/sda4)
After this patch with --exclusive as a switch for FSCONFIG_CMD_CREATE_EXCL
--------------------------------------------------------------------------
$ sudo ./move-mount -f xfs --exclusive -o source=/dev/sda4 /A
Requesting filesystem type xfs
Request exclusive superblock creation
Mount options requested: source=/dev/sda4
Attaching mount at /A
Moving single attached mount
Setting key(source) with val(/dev/sda4)
$ sudo ./move-mount -f xfs --exclusive -o source=/dev/sda4 /B
Requesting filesystem type xfs
Request exclusive superblock creation
Mount options requested: source=/dev/sda4
Attaching mount at /B
Moving single attached mount
Setting key(source) with val(/dev/sda4)
Device or resource busy | move-mount.c: 300: do_fsconfig: i xfs: reusing existing filesystem not allowed
Details
=======
As mentioned on the list (cf. [1]-[3]) mount requests like
mount -t ext4 /dev/sda /A are ambigous for userspace. Either a new
superblock has been created and mounted or an existing superblock has
been reused and a bind-mount has been created.
This becomes clear in the following example where two processes create
the same mount for the same block device:
P1 P2
fd_fs = fsopen("ext4"); fd_fs = fsopen("ext4");
fsconfig(fd_fs, FSCONFIG_SET_STRING, "source", "/dev/sda"); fsconfig(fd_fs, FSCONFIG_SET_STRING, "source", "/dev/sda");
fsconfig(fd_fs, FSCONFIG_SET_STRING, "dax", "always"); fsconfig(fd_fs, FSCONFIG_SET_STRING, "resuid", "1000");
// wins and creates superblock
fsconfig(fd_fs, FSCONFIG_CMD_CREATE, ...)
// finds compatible superblock of P1
// spins until P1 sets SB_BORN and grabs a reference
fsconfig(fd_fs, FSCONFIG_CMD_CREATE, ...)
fd_mnt1 = fsmount(fd_fs); fd_mnt2 = fsmount(fd_fs);
move_mount(fd_mnt1, "/A") move_mount(fd_mnt2, "/B")
Not just does P2 get a bind-mount but the mount options that P2
requestes are silently ignored. The VFS itself doesn't, can't and
shouldn't enforce filesystem specific mount option compatibility. It
only enforces incompatibility for read-only <-> read-write transitions:
mount -t ext4 /dev/sda /A
mount -t ext4 -o ro /dev/sda /B
The read-only request will fail with EBUSY as the VFS can't just
silently transition a superblock from read-write to read-only or vica
versa without risking security issues.
To userspace this silent superblock reuse can become a security issue in
because there is currently no straightforward way for userspace to know
that they did indeed manage to create a new superblock and didn't just
reuse an existing one.
This adds a new FSCONFIG_CMD_CREATE_EXCL command to fsconfig() that
returns EBUSY if an existing superblock would be reused. Userspace that
needs to be sure that it did create a new superblock with the requested
mount options can request superblock creation using this command. If the
command succeeds they can be sure that they did create a new superblock
with the requested mount options.
This requires the new mount api. With the old mount api it would be
necessary to plumb this through every legacy filesystem's
file_system_type->mount() method. If they want this feature they are
most welcome to switch to the new mount api.
Following is an analysis of the effect of FSCONFIG_CMD_CREATE_EXCL on
each high-level superblock creation helper:
(1) get_tree_nodev()
Always allocate new superblock. Hence, FSCONFIG_CMD_CREATE and
FSCONFIG_CMD_CREATE_EXCL are equivalent.
The binderfs or overlayfs filesystems are examples.
(4) get_tree_keyed()
Finds an existing superblock based on sb->s_fs_info. Hence,
FSCONFIG_CMD_CREATE would reuse an existing superblock whereas
FSCONFIG_CMD_CREATE_EXCL would reject it with EBUSY.
The mqueue or nfsd filesystems are examples.
(2) get_tree_bdev()
This effectively works like get_tree_keyed().
The ext4 or xfs filesystems are examples.
(3) get_tree_single()
Only one superblock of this filesystem type can ever exist.
Hence, FSCONFIG_CMD_CREATE would reuse an existing superblock
whereas FSCONFIG_CMD_CREATE_EXCL would reject it with EBUSY.
The securityfs or configfs filesystems are examples.
Note that some single-instance filesystems never destroy the
superblock once it has been created during the first mount. For
example, if securityfs has been mounted at least onces then the
created superblock will never be destroyed again as long as there is
still an LSM making use it. Consequently, even if securityfs is
unmounted and the superblock seemingly destroyed it really isn't
which means that FSCONFIG_CMD_CREATE_EXCL will continue rejecting
reusing an existing superblock.
This is acceptable thugh since special purpose filesystems such as
this shouldn't have a need to use FSCONFIG_CMD_CREATE_EXCL anyway
and if they do it's probably to make sure that mount options aren't
ignored.
Following is an analysis of the effect of FSCONFIG_CMD_CREATE_EXCL on
filesystems that make use of the low-level sget_fc() helper directly.
They're all effectively variants on get_tree_keyed(), get_tree_bdev(),
or get_tree_nodev():
(5) mtd_get_sb()
Similar logic to get_tree_keyed().
(6) afs_get_tree()
Similar logic to get_tree_keyed().
(7) ceph_get_tree()
Similar logic to get_tree_keyed().
Already explicitly allows forcing the allocation of a new superblock
via CEPH_OPT_NOSHARE. This turns it into get_tree_nodev().
(8) fuse_get_tree_submount()
Similar logic to get_tree_nodev().
(9) fuse_get_tree()
Forces reuse of existing FUSE superblock.
Forces reuse of existing superblock if passed in file refers to an
existing FUSE connection.
If FSCONFIG_CMD_CREATE_EXCL is specified together with an fd
referring to an existing FUSE connections this would cause the
superblock reusal to fail. If reusing is the intent then
FSCONFIG_CMD_CREATE_EXCL shouldn't be specified.
(10) fuse_get_tree()
-> get_tree_nodev()
Same logic as in get_tree_nodev().
(11) fuse_get_tree()
-> get_tree_bdev()
Same logic as in get_tree_bdev().
(12) virtio_fs_get_tree()
Same logic as get_tree_keyed().
(13) gfs2_meta_get_tree()
Forces reuse of existing gfs2 superblock.
Mounting gfs2meta enforces that a gf2s superblock must already
exist. If not, it will error out. Consequently, mounting gfs2meta
with FSCONFIG_CMD_CREATE_EXCL would always fail. If reusing is the
intent then FSCONFIG_CMD_CREATE_EXCL shouldn't be specified.
(14) kernfs_get_tree()
Similar logic to get_tree_keyed().
(15) nfs_get_tree_common()
Similar logic to get_tree_keyed().
Already explicitly allows forcing the allocation of a new superblock
via NFS_MOUNT_UNSHARED. This effectively turns it into
get_tree_nodev().
Link: [1] https://lore.kernel.org/linux-block/20230704-fasching-wertarbeit-7c6ffb01c83d@brauner
Link: [2] https://lore.kernel.org/linux-block/20230705-pumpwerk-vielversprechend-a4b1fd947b65@brauner
Link: [3] https://lore.kernel.org/linux-fsdevel/20230725-einnahmen-warnschilder-17779aec0a97@brauner
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Aleksa Sarai <cyphar@cyphar.com>
Message-Id: <20230802-vfs-super-exclusive-v2-4-95dc4e41b870@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
2023-08-02 11:57:06 +00:00
|
|
|
FSCONFIG_CMD_CREATE_EXCL = 8, /* Create new superblock, fail if reusing existing superblock */
|
vfs: syscall: Add fsconfig() for configuring and managing a context
Add a syscall for configuring a filesystem creation context and triggering
actions upon it, to be used in conjunction with fsopen, fspick and fsmount.
long fsconfig(int fs_fd, unsigned int cmd, const char *key,
const void *value, int aux);
Where fs_fd indicates the context, cmd indicates the action to take, key
indicates the parameter name for parameter-setting actions and, if needed,
value points to a buffer containing the value and aux can give more
information for the value.
The following command IDs are proposed:
(*) FSCONFIG_SET_FLAG: No value is specified. The parameter must be
boolean in nature. The key may be prefixed with "no" to invert the
setting. value must be NULL and aux must be 0.
(*) FSCONFIG_SET_STRING: A string value is specified. The parameter can
be expecting boolean, integer, string or take a path. A conversion to
an appropriate type will be attempted (which may include looking up as
a path). value points to a NUL-terminated string and aux must be 0.
(*) FSCONFIG_SET_BINARY: A binary blob is specified. value points to
the blob and aux indicates its size. The parameter must be expecting
a blob.
(*) FSCONFIG_SET_PATH: A non-empty path is specified. The parameter must
be expecting a path object. value points to a NUL-terminated string
that is the path and aux is a file descriptor at which to start a
relative lookup or AT_FDCWD.
(*) FSCONFIG_SET_PATH_EMPTY: As fsconfig_set_path, but with AT_EMPTY_PATH
implied.
(*) FSCONFIG_SET_FD: An open file descriptor is specified. value must
be NULL and aux indicates the file descriptor.
(*) FSCONFIG_CMD_CREATE: Trigger superblock creation.
(*) FSCONFIG_CMD_RECONFIGURE: Trigger superblock reconfiguration.
For the "set" command IDs, the idea is that the file_system_type will point
to a list of parameters and the types of value that those parameters expect
to take. The core code can then do the parse and argument conversion and
then give the LSM and FS a cooked option or array of options to use.
Source specification is also done the same way same way, using special keys
"source", "source1", "source2", etc..
[!] Note that, for the moment, the key and value are just glued back
together and handed to the filesystem. Every filesystem that uses options
uses match_token() and co. to do this, and this will need to be changed -
but not all at once.
Example usage:
fd = fsopen("ext4", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_path, "source", "/dev/sda1", AT_FDCWD);
fsconfig(fd, fsconfig_set_path_empty, "journal_path", "", journal_fd);
fsconfig(fd, fsconfig_set_fd, "journal_fd", "", journal_fd);
fsconfig(fd, fsconfig_set_flag, "user_xattr", NULL, 0);
fsconfig(fd, fsconfig_set_flag, "noacl", NULL, 0);
fsconfig(fd, fsconfig_set_string, "sb", "1", 0);
fsconfig(fd, fsconfig_set_string, "errors", "continue", 0);
fsconfig(fd, fsconfig_set_string, "data", "journal", 0);
fsconfig(fd, fsconfig_set_string, "context", "unconfined_u:...", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("ext4", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "/dev/sda1", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("afs", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "#grand.central.org:root.cell", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
or:
fd = fsopen("jffs2", FSOPEN_CLOEXEC);
fsconfig(fd, fsconfig_set_string, "source", "mtd0", 0);
fsconfig(fd, fsconfig_cmd_create, NULL, NULL, 0);
mfd = fsmount(fd, FSMOUNT_CLOEXEC, MS_NOEXEC);
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-api@vger.kernel.org
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2018-11-01 23:36:09 +00:00
|
|
|
};
|
|
|
|
|
2018-11-01 23:36:14 +00:00
|
|
|
/*
|
|
|
|
* fsmount() flags.
|
|
|
|
*/
|
|
|
|
#define FSMOUNT_CLOEXEC 0x00000001
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Mount attributes.
|
|
|
|
*/
|
|
|
|
#define MOUNT_ATTR_RDONLY 0x00000001 /* Mount read-only */
|
|
|
|
#define MOUNT_ATTR_NOSUID 0x00000002 /* Ignore suid and sgid bits */
|
|
|
|
#define MOUNT_ATTR_NODEV 0x00000004 /* Disallow access to device special files */
|
|
|
|
#define MOUNT_ATTR_NOEXEC 0x00000008 /* Disallow program execution */
|
|
|
|
#define MOUNT_ATTR__ATIME 0x00000070 /* Setting on how atime should be updated */
|
|
|
|
#define MOUNT_ATTR_RELATIME 0x00000000 /* - Update atime relative to mtime/ctime. */
|
|
|
|
#define MOUNT_ATTR_NOATIME 0x00000010 /* - Do not update access times. */
|
|
|
|
#define MOUNT_ATTR_STRICTATIME 0x00000020 /* - Always perform atime updates */
|
|
|
|
#define MOUNT_ATTR_NODIRATIME 0x00000080 /* Do not update directory access times */
|
2021-01-21 13:19:54 +00:00
|
|
|
#define MOUNT_ATTR_IDMAP 0x00100000 /* Idmap mount to @userns_fd in struct mount_attr. */
|
2021-06-01 09:33:59 +00:00
|
|
|
#define MOUNT_ATTR_NOSYMFOLLOW 0x00200000 /* Do not follow symlinks */
|
2018-11-01 23:36:14 +00:00
|
|
|
|
fs: add mount_setattr()
This implements the missing mount_setattr() syscall. While the new mount
api allows to change the properties of a superblock there is currently
no way to change the properties of a mount or a mount tree using file
descriptors which the new mount api is based on. In addition the old
mount api has the restriction that mount options cannot be applied
recursively. This hasn't changed since changing mount options on a
per-mount basis was implemented in [1] and has been a frequent request
not just for convenience but also for security reasons. The legacy
mount syscall is unable to accommodate this behavior without introducing
a whole new set of flags because MS_REC | MS_REMOUNT | MS_BIND |
MS_RDONLY | MS_NOEXEC | [...] only apply the mount option to the topmost
mount. Changing MS_REC to apply to the whole mount tree would mean
introducing a significant uapi change and would likely cause significant
regressions.
The new mount_setattr() syscall allows to recursively clear and set
mount options in one shot. Multiple calls to change mount options
requesting the same changes are idempotent:
int mount_setattr(int dfd, const char *path, unsigned flags,
struct mount_attr *uattr, size_t usize);
Flags to modify path resolution behavior are specified in the @flags
argument. Currently, AT_EMPTY_PATH, AT_RECURSIVE, AT_SYMLINK_NOFOLLOW,
and AT_NO_AUTOMOUNT are supported. If useful, additional lookup flags to
restrict path resolution as introduced with openat2() might be supported
in the future.
The mount_setattr() syscall can be expected to grow over time and is
designed with extensibility in mind. It follows the extensible syscall
pattern we have used with other syscalls such as openat2(), clone3(),
sched_{set,get}attr(), and others.
The set of mount options is passed in the uapi struct mount_attr which
currently has the following layout:
struct mount_attr {
__u64 attr_set;
__u64 attr_clr;
__u64 propagation;
__u64 userns_fd;
};
The @attr_set and @attr_clr members are used to clear and set mount
options. This way a user can e.g. request that a set of flags is to be
raised such as turning mounts readonly by raising MOUNT_ATTR_RDONLY in
@attr_set while at the same time requesting that another set of flags is
to be lowered such as removing noexec from a mount tree by specifying
MOUNT_ATTR_NOEXEC in @attr_clr.
Note, since the MOUNT_ATTR_<atime> values are an enum starting from 0,
not a bitmap, users wanting to transition to a different atime setting
cannot simply specify the atime setting in @attr_set, but must also
specify MOUNT_ATTR__ATIME in the @attr_clr field. So we ensure that
MOUNT_ATTR__ATIME can't be partially set in @attr_clr and that @attr_set
can't have any atime bits set if MOUNT_ATTR__ATIME isn't set in
@attr_clr.
The @propagation field lets callers specify the propagation type of a
mount tree. Propagation is a single property that has four different
settings and as such is not really a flag argument but an enum.
Specifically, it would be unclear what setting and clearing propagation
settings in combination would amount to. The legacy mount() syscall thus
forbids the combination of multiple propagation settings too. The goal
is to keep the semantics of mount propagation somewhat simple as they
are overly complex as it is.
The @userns_fd field lets user specify a user namespace whose idmapping
becomes the idmapping of the mount. This is implemented and explained in
detail in the next patch.
[1]: commit 2e4b7fcd9260 ("[PATCH] r/o bind mounts: honor mount writer counts at remount")
Link: https://lore.kernel.org/r/20210121131959.646623-35-christian.brauner@ubuntu.com
Cc: David Howells <dhowells@redhat.com>
Cc: Aleksa Sarai <cyphar@cyphar.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2021-01-21 13:19:53 +00:00
|
|
|
/*
|
|
|
|
* mount_setattr()
|
|
|
|
*/
|
|
|
|
struct mount_attr {
|
|
|
|
__u64 attr_set;
|
|
|
|
__u64 attr_clr;
|
|
|
|
__u64 propagation;
|
|
|
|
__u64 userns_fd;
|
|
|
|
};
|
|
|
|
|
|
|
|
/* List of all mount_attr versions. */
|
|
|
|
#define MOUNT_ATTR_SIZE_VER0 32 /* sizeof first published struct */
|
|
|
|
|
2023-10-25 14:02:02 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Structure for getting mount/superblock/filesystem info with statmount(2).
|
|
|
|
*
|
|
|
|
* The interface is similar to statx(2): individual fields or groups can be
|
|
|
|
* selected with the @mask argument of statmount(). Kernel will set the @mask
|
|
|
|
* field according to the supported fields.
|
|
|
|
*
|
|
|
|
* If string fields are selected, then the caller needs to pass a buffer that
|
|
|
|
* has space after the fixed part of the structure. Nul terminated strings are
|
|
|
|
* copied there and offsets relative to @str are stored in the relevant fields.
|
|
|
|
* If the buffer is too small, then EOVERFLOW is returned. The actually used
|
|
|
|
* size is returned in @size.
|
|
|
|
*/
|
|
|
|
struct statmount {
|
|
|
|
__u32 size; /* Total size, including strings */
|
|
|
|
__u32 __spare1;
|
|
|
|
__u64 mask; /* What results were written */
|
|
|
|
__u32 sb_dev_major; /* Device ID */
|
|
|
|
__u32 sb_dev_minor;
|
|
|
|
__u64 sb_magic; /* ..._SUPER_MAGIC */
|
|
|
|
__u32 sb_flags; /* SB_{RDONLY,SYNCHRONOUS,DIRSYNC,LAZYTIME} */
|
|
|
|
__u32 fs_type; /* [str] Filesystem type */
|
|
|
|
__u64 mnt_id; /* Unique ID of mount */
|
|
|
|
__u64 mnt_parent_id; /* Unique ID of parent (for root == mnt_id) */
|
|
|
|
__u32 mnt_id_old; /* Reused IDs used in proc/.../mountinfo */
|
|
|
|
__u32 mnt_parent_id_old;
|
|
|
|
__u64 mnt_attr; /* MOUNT_ATTR_... */
|
|
|
|
__u64 mnt_propagation; /* MS_{SHARED,SLAVE,PRIVATE,UNBINDABLE} */
|
|
|
|
__u64 mnt_peer_group; /* ID of shared peer group */
|
|
|
|
__u64 mnt_master; /* Mount receives propagation from this ID */
|
|
|
|
__u64 propagate_from; /* Propagation from in current namespace */
|
|
|
|
__u32 mnt_root; /* [str] Root of mount relative to root of fs */
|
|
|
|
__u32 mnt_point; /* [str] Mountpoint relative to current root */
|
|
|
|
__u64 __spare2[50];
|
|
|
|
char str[]; /* Variable size part containing strings */
|
|
|
|
};
|
|
|
|
|
2023-10-25 14:02:03 +00:00
|
|
|
/*
|
|
|
|
* Structure for passing mount ID and miscellaneous parameters to statmount(2)
|
|
|
|
* and listmount(2).
|
|
|
|
*
|
|
|
|
* For statmount(2) @param represents the request mask.
|
|
|
|
* For listmount(2) @param represents the last listed mount id (or zero).
|
|
|
|
*/
|
2023-10-25 14:02:02 +00:00
|
|
|
struct mnt_id_req {
|
2023-11-29 11:27:15 +00:00
|
|
|
__u32 size;
|
|
|
|
__u32 spare;
|
2023-10-25 14:02:02 +00:00
|
|
|
__u64 mnt_id;
|
2023-10-25 14:02:03 +00:00
|
|
|
__u64 param;
|
2023-10-25 14:02:02 +00:00
|
|
|
};
|
|
|
|
|
2023-11-29 11:27:15 +00:00
|
|
|
/* List of all mnt_id_req versions. */
|
|
|
|
#define MNT_ID_REQ_SIZE_VER0 24 /* sizeof first published struct */
|
|
|
|
|
2023-10-25 14:02:02 +00:00
|
|
|
/*
|
|
|
|
* @mask bits for statmount(2)
|
|
|
|
*/
|
|
|
|
#define STATMOUNT_SB_BASIC 0x00000001U /* Want/got sb_... */
|
|
|
|
#define STATMOUNT_MNT_BASIC 0x00000002U /* Want/got mnt_... */
|
|
|
|
#define STATMOUNT_PROPAGATE_FROM 0x00000004U /* Want/got propagate_from */
|
|
|
|
#define STATMOUNT_MNT_ROOT 0x00000008U /* Want/got mnt_root */
|
|
|
|
#define STATMOUNT_MNT_POINT 0x00000010U /* Want/got mnt_point */
|
|
|
|
#define STATMOUNT_FS_TYPE 0x00000020U /* Want/got fs_type */
|
|
|
|
|
2023-10-25 14:02:03 +00:00
|
|
|
/*
|
|
|
|
* Special @mnt_id values that can be passed to listmount
|
|
|
|
*/
|
|
|
|
#define LSMT_ROOT 0xffffffffffffffff /* root mount */
|
|
|
|
|
2018-11-01 23:07:23 +00:00
|
|
|
#endif /* _UAPI_LINUX_MOUNT_H */
|