mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-27 03:10:12 +00:00
![Linus Torvalds](/assets/img/avatar_default.png)
-----BEGIN PGP SIGNATURE-----
iHUEABYKAB0WIQRAhzRXHqcMeLMyaSiRxhvAZXjcogUCYCegywAKCRCRxhvAZXjc
ouJ6AQDlf+7jCQlQdeKKoN9QDFfMzG1ooemat36EpRRTONaGuAD8D9A4sUsG4+5f
4IU5Lj9oY4DEmF8HenbWK2ZHsesL2Qg=
=yPaw
-----END PGP SIGNATURE-----
Merge tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux
Pull idmapped mounts from Christian Brauner:
"This introduces idmapped mounts which has been in the making for some
time. Simply put, different mounts can expose the same file or
directory with different ownership. This initial implementation comes
with ports for fat, ext4 and with Christoph's port for xfs with more
filesystems being actively worked on by independent people and
maintainers.
Idmapping mounts handle a wide range of long standing use-cases. Here
are just a few:
- Idmapped mounts make it possible to easily share files between
multiple users or multiple machines especially in complex
scenarios. For example, idmapped mounts will be used in the
implementation of portable home directories in
systemd-homed.service(8) where they allow users to move their home
directory to an external storage device and use it on multiple
computers where they are assigned different uids and gids. This
effectively makes it possible to assign random uids and gids at
login time.
- It is possible to share files from the host with unprivileged
containers without having to change ownership permanently through
chown(2).
- It is possible to idmap a container's rootfs and without having to
mangle every file. For example, Chromebooks use it to share the
user's Download folder with their unprivileged containers in their
Linux subsystem.
- It is possible to share files between containers with
non-overlapping idmappings.
- Filesystem that lack a proper concept of ownership such as fat can
use idmapped mounts to implement discretionary access (DAC)
permission checking.
- They allow users to efficiently changing ownership on a per-mount
basis without having to (recursively) chown(2) all files. In
contrast to chown (2) changing ownership of large sets of files is
instantenous with idmapped mounts. This is especially useful when
ownership of a whole root filesystem of a virtual machine or
container is changed. With idmapped mounts a single syscall
mount_setattr syscall will be sufficient to change the ownership of
all files.
- Idmapped mounts always take the current ownership into account as
idmappings specify what a given uid or gid is supposed to be mapped
to. This contrasts with the chown(2) syscall which cannot by itself
take the current ownership of the files it changes into account. It
simply changes the ownership to the specified uid and gid. This is
especially problematic when recursively chown(2)ing a large set of
files which is commong with the aforementioned portable home
directory and container and vm scenario.
- Idmapped mounts allow to change ownership locally, restricting it
to specific mounts, and temporarily as the ownership changes only
apply as long as the mount exists.
Several userspace projects have either already put up patches and
pull-requests for this feature or will do so should you decide to pull
this:
- systemd: In a wide variety of scenarios but especially right away
in their implementation of portable home directories.
https://systemd.io/HOME_DIRECTORY/
- container runtimes: containerd, runC, LXD:To share data between
host and unprivileged containers, unprivileged and privileged
containers, etc. The pull request for idmapped mounts support in
containerd, the default Kubernetes runtime is already up for quite
a while now: https://github.com/containerd/containerd/pull/4734
- The virtio-fs developers and several users have expressed interest
in using this feature with virtual machines once virtio-fs is
ported.
- ChromeOS: Sharing host-directories with unprivileged containers.
I've tightly synced with all those projects and all of those listed
here have also expressed their need/desire for this feature on the
mailing list. For more info on how people use this there's a bunch of
talks about this too. Here's just two recent ones:
https://www.cncf.io/wp-content/uploads/2020/12/Rootless-Containers-in-Gitpod.pdf
https://fosdem.org/2021/schedule/event/containers_idmap/
This comes with an extensive xfstests suite covering both ext4 and
xfs:
https://git.kernel.org/brauner/xfstests-dev/h/idmapped_mounts
It covers truncation, creation, opening, xattrs, vfscaps, setid
execution, setgid inheritance and more both with idmapped and
non-idmapped mounts. It already helped to discover an unrelated xfs
setgid inheritance bug which has since been fixed in mainline. It will
be sent for inclusion with the xfstests project should you decide to
merge this.
In order to support per-mount idmappings vfsmounts are marked with
user namespaces. The idmapping of the user namespace will be used to
map the ids of vfs objects when they are accessed through that mount.
By default all vfsmounts are marked with the initial user namespace.
The initial user namespace is used to indicate that a mount is not
idmapped. All operations behave as before and this is verified in the
testsuite.
Based on prior discussions we want to attach the whole user namespace
and not just a dedicated idmapping struct. This allows us to reuse all
the helpers that already exist for dealing with idmappings instead of
introducing a whole new range of helpers. In addition, if we decide in
the future that we are confident enough to enable unprivileged users
to setup idmapped mounts the permission checking can take into account
whether the caller is privileged in the user namespace the mount is
currently marked with.
The user namespace the mount will be marked with can be specified by
passing a file descriptor refering to the user namespace as an
argument to the new mount_setattr() syscall together with the new
MOUNT_ATTR_IDMAP flag. The system call follows the openat2() pattern
of extensibility.
The following conditions must be met in order to create an idmapped
mount:
- The caller must currently have the CAP_SYS_ADMIN capability in the
user namespace the underlying filesystem has been mounted in.
- The underlying filesystem must support idmapped mounts.
- The mount must not already be idmapped. This also implies that the
idmapping of a mount cannot be altered once it has been idmapped.
- The mount must be a detached/anonymous mount, i.e. it must have
been created by calling open_tree() with the OPEN_TREE_CLONE flag
and it must not already have been visible in the filesystem.
The last two points guarantee easier semantics for userspace and the
kernel and make the implementation significantly simpler.
By default vfsmounts are marked with the initial user namespace and no
behavioral or performance changes are observed.
The manpage with a detailed description can be found here:
1d7b902e28
In order to support idmapped mounts, filesystems need to be changed
and mark themselves with the FS_ALLOW_IDMAP flag in fs_flags. The
patches to convert individual filesystem are not very large or
complicated overall as can be seen from the included fat, ext4, and
xfs ports. Patches for other filesystems are actively worked on and
will be sent out separately. The xfstestsuite can be used to verify
that port has been done correctly.
The mount_setattr() syscall is motivated independent of the idmapped
mounts patches and it's been around since July 2019. One of the most
valuable features of the new mount api is the ability to perform
mounts based on file descriptors only.
Together with the lookup restrictions available in the openat2()
RESOLVE_* flag namespace which we added in v5.6 this is the first time
we are close to hardened and race-free (e.g. symlinks) mounting and
path resolution.
While userspace has started porting to the new mount api to mount
proper filesystems and create new bind-mounts it is currently not
possible to change mount options of an already existing bind mount in
the new mount api since the mount_setattr() syscall is missing.
With the addition of the mount_setattr() syscall we remove this last
restriction and userspace can now fully port to the new mount api,
covering every use-case the old mount api could. We also add the
crucial ability to recursively change mount options for a whole mount
tree, both removing and adding mount options at the same time. This
syscall has been requested multiple times by various people and
projects.
There is a simple tool available at
https://github.com/brauner/mount-idmapped
that allows to create idmapped mounts so people can play with this
patch series. I'll add support for the regular mount binary should you
decide to pull this in the following weeks:
Here's an example to a simple idmapped mount of another user's home
directory:
u1001@f2-vm:/$ sudo ./mount --idmap both:1000:1001:1 /home/ubuntu/ /mnt
u1001@f2-vm:/$ ls -al /home/ubuntu/
total 28
drwxr-xr-x 2 ubuntu ubuntu 4096 Oct 28 22:07 .
drwxr-xr-x 4 root root 4096 Oct 28 04:00 ..
-rw------- 1 ubuntu ubuntu 3154 Oct 28 22:12 .bash_history
-rw-r--r-- 1 ubuntu ubuntu 220 Feb 25 2020 .bash_logout
-rw-r--r-- 1 ubuntu ubuntu 3771 Feb 25 2020 .bashrc
-rw-r--r-- 1 ubuntu ubuntu 807 Feb 25 2020 .profile
-rw-r--r-- 1 ubuntu ubuntu 0 Oct 16 16:11 .sudo_as_admin_successful
-rw------- 1 ubuntu ubuntu 1144 Oct 28 00:43 .viminfo
u1001@f2-vm:/$ ls -al /mnt/
total 28
drwxr-xr-x 2 u1001 u1001 4096 Oct 28 22:07 .
drwxr-xr-x 29 root root 4096 Oct 28 22:01 ..
-rw------- 1 u1001 u1001 3154 Oct 28 22:12 .bash_history
-rw-r--r-- 1 u1001 u1001 220 Feb 25 2020 .bash_logout
-rw-r--r-- 1 u1001 u1001 3771 Feb 25 2020 .bashrc
-rw-r--r-- 1 u1001 u1001 807 Feb 25 2020 .profile
-rw-r--r-- 1 u1001 u1001 0 Oct 16 16:11 .sudo_as_admin_successful
-rw------- 1 u1001 u1001 1144 Oct 28 00:43 .viminfo
u1001@f2-vm:/$ touch /mnt/my-file
u1001@f2-vm:/$ setfacl -m u:1001:rwx /mnt/my-file
u1001@f2-vm:/$ sudo setcap -n 1001 cap_net_raw+ep /mnt/my-file
u1001@f2-vm:/$ ls -al /mnt/my-file
-rw-rwxr--+ 1 u1001 u1001 0 Oct 28 22:14 /mnt/my-file
u1001@f2-vm:/$ ls -al /home/ubuntu/my-file
-rw-rwxr--+ 1 ubuntu ubuntu 0 Oct 28 22:14 /home/ubuntu/my-file
u1001@f2-vm:/$ getfacl /mnt/my-file
getfacl: Removing leading '/' from absolute path names
# file: mnt/my-file
# owner: u1001
# group: u1001
user::rw-
user:u1001:rwx
group::rw-
mask::rwx
other::r--
u1001@f2-vm:/$ getfacl /home/ubuntu/my-file
getfacl: Removing leading '/' from absolute path names
# file: home/ubuntu/my-file
# owner: ubuntu
# group: ubuntu
user::rw-
user:ubuntu:rwx
group::rw-
mask::rwx
other::r--"
* tag 'idmapped-mounts-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/brauner/linux: (41 commits)
xfs: remove the possibly unused mp variable in xfs_file_compat_ioctl
xfs: support idmapped mounts
ext4: support idmapped mounts
fat: handle idmapped mounts
tests: add mount_setattr() selftests
fs: introduce MOUNT_ATTR_IDMAP
fs: add mount_setattr()
fs: add attr_flags_to_mnt_flags helper
fs: split out functions to hold writers
namespace: only take read lock in do_reconfigure_mnt()
mount: make {lock,unlock}_mount_hash() static
namespace: take lock_mount_hash() directly when changing flags
nfs: do not export idmapped mounts
overlayfs: do not mount on top of idmapped mounts
ecryptfs: do not mount on top of idmapped mounts
ima: handle idmapped mounts
apparmor: handle idmapped mounts
fs: make helpers idmap mount aware
exec: handle idmapped mounts
would_dump: handle idmapped mounts
...
724 lines
16 KiB
C
724 lines
16 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* Copyright (C) 2017 Red Hat, Inc.
|
|
*/
|
|
|
|
#include <linux/cred.h>
|
|
#include <linux/file.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/xattr.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/splice.h>
|
|
#include <linux/security.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/fs.h>
|
|
#include "overlayfs.h"
|
|
|
|
struct ovl_aio_req {
|
|
struct kiocb iocb;
|
|
struct kiocb *orig_iocb;
|
|
struct fd fd;
|
|
};
|
|
|
|
static struct kmem_cache *ovl_aio_request_cachep;
|
|
|
|
static char ovl_whatisit(struct inode *inode, struct inode *realinode)
|
|
{
|
|
if (realinode != ovl_inode_upper(inode))
|
|
return 'l';
|
|
if (ovl_has_upperdata(inode))
|
|
return 'u';
|
|
else
|
|
return 'm';
|
|
}
|
|
|
|
/* No atime modificaton nor notify on underlying */
|
|
#define OVL_OPEN_FLAGS (O_NOATIME | FMODE_NONOTIFY)
|
|
|
|
static struct file *ovl_open_realfile(const struct file *file,
|
|
struct inode *realinode)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
struct file *realfile;
|
|
const struct cred *old_cred;
|
|
int flags = file->f_flags | OVL_OPEN_FLAGS;
|
|
int acc_mode = ACC_MODE(flags);
|
|
int err;
|
|
|
|
if (flags & O_APPEND)
|
|
acc_mode |= MAY_APPEND;
|
|
|
|
old_cred = ovl_override_creds(inode->i_sb);
|
|
err = inode_permission(&init_user_ns, realinode, MAY_OPEN | acc_mode);
|
|
if (err) {
|
|
realfile = ERR_PTR(err);
|
|
} else {
|
|
if (!inode_owner_or_capable(&init_user_ns, realinode))
|
|
flags &= ~O_NOATIME;
|
|
|
|
realfile = open_with_fake_path(&file->f_path, flags, realinode,
|
|
current_cred());
|
|
}
|
|
revert_creds(old_cred);
|
|
|
|
pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n",
|
|
file, file, ovl_whatisit(inode, realinode), file->f_flags,
|
|
realfile, IS_ERR(realfile) ? 0 : realfile->f_flags);
|
|
|
|
return realfile;
|
|
}
|
|
|
|
#define OVL_SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT)
|
|
|
|
static int ovl_change_flags(struct file *file, unsigned int flags)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
int err;
|
|
|
|
flags &= OVL_SETFL_MASK;
|
|
|
|
if (((flags ^ file->f_flags) & O_APPEND) && IS_APPEND(inode))
|
|
return -EPERM;
|
|
|
|
if (flags & O_DIRECT) {
|
|
if (!file->f_mapping->a_ops ||
|
|
!file->f_mapping->a_ops->direct_IO)
|
|
return -EINVAL;
|
|
}
|
|
|
|
if (file->f_op->check_flags) {
|
|
err = file->f_op->check_flags(flags);
|
|
if (err)
|
|
return err;
|
|
}
|
|
|
|
spin_lock(&file->f_lock);
|
|
file->f_flags = (file->f_flags & ~OVL_SETFL_MASK) | flags;
|
|
spin_unlock(&file->f_lock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int ovl_real_fdget_meta(const struct file *file, struct fd *real,
|
|
bool allow_meta)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
struct inode *realinode;
|
|
|
|
real->flags = 0;
|
|
real->file = file->private_data;
|
|
|
|
if (allow_meta)
|
|
realinode = ovl_inode_real(inode);
|
|
else
|
|
realinode = ovl_inode_realdata(inode);
|
|
|
|
/* Has it been copied up since we'd opened it? */
|
|
if (unlikely(file_inode(real->file) != realinode)) {
|
|
real->flags = FDPUT_FPUT;
|
|
real->file = ovl_open_realfile(file, realinode);
|
|
|
|
return PTR_ERR_OR_ZERO(real->file);
|
|
}
|
|
|
|
/* Did the flags change since open? */
|
|
if (unlikely((file->f_flags ^ real->file->f_flags) & ~OVL_OPEN_FLAGS))
|
|
return ovl_change_flags(real->file, file->f_flags);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int ovl_real_fdget(const struct file *file, struct fd *real)
|
|
{
|
|
if (d_is_dir(file_dentry(file))) {
|
|
real->flags = 0;
|
|
real->file = ovl_dir_real_file(file, false);
|
|
|
|
return PTR_ERR_OR_ZERO(real->file);
|
|
}
|
|
|
|
return ovl_real_fdget_meta(file, real, false);
|
|
}
|
|
|
|
static int ovl_open(struct inode *inode, struct file *file)
|
|
{
|
|
struct file *realfile;
|
|
int err;
|
|
|
|
err = ovl_maybe_copy_up(file_dentry(file), file->f_flags);
|
|
if (err)
|
|
return err;
|
|
|
|
/* No longer need these flags, so don't pass them on to underlying fs */
|
|
file->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
|
|
|
|
realfile = ovl_open_realfile(file, ovl_inode_realdata(inode));
|
|
if (IS_ERR(realfile))
|
|
return PTR_ERR(realfile);
|
|
|
|
file->private_data = realfile;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static int ovl_release(struct inode *inode, struct file *file)
|
|
{
|
|
fput(file->private_data);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static loff_t ovl_llseek(struct file *file, loff_t offset, int whence)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
struct fd real;
|
|
const struct cred *old_cred;
|
|
loff_t ret;
|
|
|
|
/*
|
|
* The two special cases below do not need to involve real fs,
|
|
* so we can optimizing concurrent callers.
|
|
*/
|
|
if (offset == 0) {
|
|
if (whence == SEEK_CUR)
|
|
return file->f_pos;
|
|
|
|
if (whence == SEEK_SET)
|
|
return vfs_setpos(file, 0, 0);
|
|
}
|
|
|
|
ret = ovl_real_fdget(file, &real);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/*
|
|
* Overlay file f_pos is the master copy that is preserved
|
|
* through copy up and modified on read/write, but only real
|
|
* fs knows how to SEEK_HOLE/SEEK_DATA and real fs may impose
|
|
* limitations that are more strict than ->s_maxbytes for specific
|
|
* files, so we use the real file to perform seeks.
|
|
*/
|
|
ovl_inode_lock(inode);
|
|
real.file->f_pos = file->f_pos;
|
|
|
|
old_cred = ovl_override_creds(inode->i_sb);
|
|
ret = vfs_llseek(real.file, offset, whence);
|
|
revert_creds(old_cred);
|
|
|
|
file->f_pos = real.file->f_pos;
|
|
ovl_inode_unlock(inode);
|
|
|
|
fdput(real);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static void ovl_file_accessed(struct file *file)
|
|
{
|
|
struct inode *inode, *upperinode;
|
|
|
|
if (file->f_flags & O_NOATIME)
|
|
return;
|
|
|
|
inode = file_inode(file);
|
|
upperinode = ovl_inode_upper(inode);
|
|
|
|
if (!upperinode)
|
|
return;
|
|
|
|
if ((!timespec64_equal(&inode->i_mtime, &upperinode->i_mtime) ||
|
|
!timespec64_equal(&inode->i_ctime, &upperinode->i_ctime))) {
|
|
inode->i_mtime = upperinode->i_mtime;
|
|
inode->i_ctime = upperinode->i_ctime;
|
|
}
|
|
|
|
touch_atime(&file->f_path);
|
|
}
|
|
|
|
static rwf_t ovl_iocb_to_rwf(int ifl)
|
|
{
|
|
rwf_t flags = 0;
|
|
|
|
if (ifl & IOCB_NOWAIT)
|
|
flags |= RWF_NOWAIT;
|
|
if (ifl & IOCB_HIPRI)
|
|
flags |= RWF_HIPRI;
|
|
if (ifl & IOCB_DSYNC)
|
|
flags |= RWF_DSYNC;
|
|
if (ifl & IOCB_SYNC)
|
|
flags |= RWF_SYNC;
|
|
|
|
return flags;
|
|
}
|
|
|
|
static void ovl_aio_cleanup_handler(struct ovl_aio_req *aio_req)
|
|
{
|
|
struct kiocb *iocb = &aio_req->iocb;
|
|
struct kiocb *orig_iocb = aio_req->orig_iocb;
|
|
|
|
if (iocb->ki_flags & IOCB_WRITE) {
|
|
struct inode *inode = file_inode(orig_iocb->ki_filp);
|
|
|
|
/* Actually acquired in ovl_write_iter() */
|
|
__sb_writers_acquired(file_inode(iocb->ki_filp)->i_sb,
|
|
SB_FREEZE_WRITE);
|
|
file_end_write(iocb->ki_filp);
|
|
ovl_copyattr(ovl_inode_real(inode), inode);
|
|
}
|
|
|
|
orig_iocb->ki_pos = iocb->ki_pos;
|
|
fdput(aio_req->fd);
|
|
kmem_cache_free(ovl_aio_request_cachep, aio_req);
|
|
}
|
|
|
|
static void ovl_aio_rw_complete(struct kiocb *iocb, long res, long res2)
|
|
{
|
|
struct ovl_aio_req *aio_req = container_of(iocb,
|
|
struct ovl_aio_req, iocb);
|
|
struct kiocb *orig_iocb = aio_req->orig_iocb;
|
|
|
|
ovl_aio_cleanup_handler(aio_req);
|
|
orig_iocb->ki_complete(orig_iocb, res, res2);
|
|
}
|
|
|
|
static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter)
|
|
{
|
|
struct file *file = iocb->ki_filp;
|
|
struct fd real;
|
|
const struct cred *old_cred;
|
|
ssize_t ret;
|
|
|
|
if (!iov_iter_count(iter))
|
|
return 0;
|
|
|
|
ret = ovl_real_fdget(file, &real);
|
|
if (ret)
|
|
return ret;
|
|
|
|
old_cred = ovl_override_creds(file_inode(file)->i_sb);
|
|
if (is_sync_kiocb(iocb)) {
|
|
ret = vfs_iter_read(real.file, iter, &iocb->ki_pos,
|
|
ovl_iocb_to_rwf(iocb->ki_flags));
|
|
} else {
|
|
struct ovl_aio_req *aio_req;
|
|
|
|
ret = -ENOMEM;
|
|
aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
|
|
if (!aio_req)
|
|
goto out;
|
|
|
|
aio_req->fd = real;
|
|
real.flags = 0;
|
|
aio_req->orig_iocb = iocb;
|
|
kiocb_clone(&aio_req->iocb, iocb, real.file);
|
|
aio_req->iocb.ki_complete = ovl_aio_rw_complete;
|
|
ret = vfs_iocb_iter_read(real.file, &aio_req->iocb, iter);
|
|
if (ret != -EIOCBQUEUED)
|
|
ovl_aio_cleanup_handler(aio_req);
|
|
}
|
|
out:
|
|
revert_creds(old_cred);
|
|
ovl_file_accessed(file);
|
|
|
|
fdput(real);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter)
|
|
{
|
|
struct file *file = iocb->ki_filp;
|
|
struct inode *inode = file_inode(file);
|
|
struct fd real;
|
|
const struct cred *old_cred;
|
|
ssize_t ret;
|
|
int ifl = iocb->ki_flags;
|
|
|
|
if (!iov_iter_count(iter))
|
|
return 0;
|
|
|
|
inode_lock(inode);
|
|
/* Update mode */
|
|
ovl_copyattr(ovl_inode_real(inode), inode);
|
|
ret = file_remove_privs(file);
|
|
if (ret)
|
|
goto out_unlock;
|
|
|
|
ret = ovl_real_fdget(file, &real);
|
|
if (ret)
|
|
goto out_unlock;
|
|
|
|
if (!ovl_should_sync(OVL_FS(inode->i_sb)))
|
|
ifl &= ~(IOCB_DSYNC | IOCB_SYNC);
|
|
|
|
old_cred = ovl_override_creds(file_inode(file)->i_sb);
|
|
if (is_sync_kiocb(iocb)) {
|
|
file_start_write(real.file);
|
|
ret = vfs_iter_write(real.file, iter, &iocb->ki_pos,
|
|
ovl_iocb_to_rwf(ifl));
|
|
file_end_write(real.file);
|
|
/* Update size */
|
|
ovl_copyattr(ovl_inode_real(inode), inode);
|
|
} else {
|
|
struct ovl_aio_req *aio_req;
|
|
|
|
ret = -ENOMEM;
|
|
aio_req = kmem_cache_zalloc(ovl_aio_request_cachep, GFP_KERNEL);
|
|
if (!aio_req)
|
|
goto out;
|
|
|
|
file_start_write(real.file);
|
|
/* Pacify lockdep, same trick as done in aio_write() */
|
|
__sb_writers_release(file_inode(real.file)->i_sb,
|
|
SB_FREEZE_WRITE);
|
|
aio_req->fd = real;
|
|
real.flags = 0;
|
|
aio_req->orig_iocb = iocb;
|
|
kiocb_clone(&aio_req->iocb, iocb, real.file);
|
|
aio_req->iocb.ki_flags = ifl;
|
|
aio_req->iocb.ki_complete = ovl_aio_rw_complete;
|
|
ret = vfs_iocb_iter_write(real.file, &aio_req->iocb, iter);
|
|
if (ret != -EIOCBQUEUED)
|
|
ovl_aio_cleanup_handler(aio_req);
|
|
}
|
|
out:
|
|
revert_creds(old_cred);
|
|
fdput(real);
|
|
|
|
out_unlock:
|
|
inode_unlock(inode);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync)
|
|
{
|
|
struct fd real;
|
|
const struct cred *old_cred;
|
|
int ret;
|
|
|
|
ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb));
|
|
if (ret <= 0)
|
|
return ret;
|
|
|
|
ret = ovl_real_fdget_meta(file, &real, !datasync);
|
|
if (ret)
|
|
return ret;
|
|
|
|
/* Don't sync lower file for fear of receiving EROFS error */
|
|
if (file_inode(real.file) == ovl_inode_upper(file_inode(file))) {
|
|
old_cred = ovl_override_creds(file_inode(file)->i_sb);
|
|
ret = vfs_fsync_range(real.file, start, end, datasync);
|
|
revert_creds(old_cred);
|
|
}
|
|
|
|
fdput(real);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int ovl_mmap(struct file *file, struct vm_area_struct *vma)
|
|
{
|
|
struct file *realfile = file->private_data;
|
|
const struct cred *old_cred;
|
|
int ret;
|
|
|
|
if (!realfile->f_op->mmap)
|
|
return -ENODEV;
|
|
|
|
if (WARN_ON(file != vma->vm_file))
|
|
return -EIO;
|
|
|
|
vma->vm_file = get_file(realfile);
|
|
|
|
old_cred = ovl_override_creds(file_inode(file)->i_sb);
|
|
ret = call_mmap(vma->vm_file, vma);
|
|
revert_creds(old_cred);
|
|
|
|
if (ret) {
|
|
/* Drop reference count from new vm_file value */
|
|
fput(realfile);
|
|
} else {
|
|
/* Drop reference count from previous vm_file value */
|
|
fput(file);
|
|
}
|
|
|
|
ovl_file_accessed(file);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
|
|
{
|
|
struct inode *inode = file_inode(file);
|
|
struct fd real;
|
|
const struct cred *old_cred;
|
|
int ret;
|
|
|
|
ret = ovl_real_fdget(file, &real);
|
|
if (ret)
|
|
return ret;
|
|
|
|
old_cred = ovl_override_creds(file_inode(file)->i_sb);
|
|
ret = vfs_fallocate(real.file, mode, offset, len);
|
|
revert_creds(old_cred);
|
|
|
|
/* Update size */
|
|
ovl_copyattr(ovl_inode_real(inode), inode);
|
|
|
|
fdput(real);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice)
|
|
{
|
|
struct fd real;
|
|
const struct cred *old_cred;
|
|
int ret;
|
|
|
|
ret = ovl_real_fdget(file, &real);
|
|
if (ret)
|
|
return ret;
|
|
|
|
old_cred = ovl_override_creds(file_inode(file)->i_sb);
|
|
ret = vfs_fadvise(real.file, offset, len, advice);
|
|
revert_creds(old_cred);
|
|
|
|
fdput(real);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static long ovl_real_ioctl(struct file *file, unsigned int cmd,
|
|
unsigned long arg)
|
|
{
|
|
struct fd real;
|
|
long ret;
|
|
|
|
ret = ovl_real_fdget(file, &real);
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = security_file_ioctl(real.file, cmd, arg);
|
|
if (!ret) {
|
|
/*
|
|
* Don't override creds, since we currently can't safely check
|
|
* permissions before doing so.
|
|
*/
|
|
ret = vfs_ioctl(real.file, cmd, arg);
|
|
}
|
|
|
|
fdput(real);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static long ovl_ioctl_set_flags(struct file *file, unsigned int cmd,
|
|
unsigned long arg)
|
|
{
|
|
long ret;
|
|
struct inode *inode = file_inode(file);
|
|
|
|
if (!inode_owner_or_capable(&init_user_ns, inode))
|
|
return -EACCES;
|
|
|
|
ret = mnt_want_write_file(file);
|
|
if (ret)
|
|
return ret;
|
|
|
|
inode_lock(inode);
|
|
|
|
/*
|
|
* Prevent copy up if immutable and has no CAP_LINUX_IMMUTABLE
|
|
* capability.
|
|
*/
|
|
ret = -EPERM;
|
|
if (!ovl_has_upperdata(inode) && IS_IMMUTABLE(inode) &&
|
|
!capable(CAP_LINUX_IMMUTABLE))
|
|
goto unlock;
|
|
|
|
ret = ovl_maybe_copy_up(file_dentry(file), O_WRONLY);
|
|
if (ret)
|
|
goto unlock;
|
|
|
|
ret = ovl_real_ioctl(file, cmd, arg);
|
|
|
|
ovl_copyflags(ovl_inode_real(inode), inode);
|
|
unlock:
|
|
inode_unlock(inode);
|
|
|
|
mnt_drop_write_file(file);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
long ovl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
|
|
{
|
|
long ret;
|
|
|
|
switch (cmd) {
|
|
case FS_IOC_GETFLAGS:
|
|
case FS_IOC_FSGETXATTR:
|
|
ret = ovl_real_ioctl(file, cmd, arg);
|
|
break;
|
|
|
|
case FS_IOC_FSSETXATTR:
|
|
case FS_IOC_SETFLAGS:
|
|
ret = ovl_ioctl_set_flags(file, cmd, arg);
|
|
break;
|
|
|
|
default:
|
|
ret = -ENOTTY;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
long ovl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
|
|
{
|
|
switch (cmd) {
|
|
case FS_IOC32_GETFLAGS:
|
|
cmd = FS_IOC_GETFLAGS;
|
|
break;
|
|
|
|
case FS_IOC32_SETFLAGS:
|
|
cmd = FS_IOC_SETFLAGS;
|
|
break;
|
|
|
|
default:
|
|
return -ENOIOCTLCMD;
|
|
}
|
|
|
|
return ovl_ioctl(file, cmd, arg);
|
|
}
|
|
#endif
|
|
|
|
enum ovl_copyop {
|
|
OVL_COPY,
|
|
OVL_CLONE,
|
|
OVL_DEDUPE,
|
|
};
|
|
|
|
static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in,
|
|
struct file *file_out, loff_t pos_out,
|
|
loff_t len, unsigned int flags, enum ovl_copyop op)
|
|
{
|
|
struct inode *inode_out = file_inode(file_out);
|
|
struct fd real_in, real_out;
|
|
const struct cred *old_cred;
|
|
loff_t ret;
|
|
|
|
ret = ovl_real_fdget(file_out, &real_out);
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = ovl_real_fdget(file_in, &real_in);
|
|
if (ret) {
|
|
fdput(real_out);
|
|
return ret;
|
|
}
|
|
|
|
old_cred = ovl_override_creds(file_inode(file_out)->i_sb);
|
|
switch (op) {
|
|
case OVL_COPY:
|
|
ret = vfs_copy_file_range(real_in.file, pos_in,
|
|
real_out.file, pos_out, len, flags);
|
|
break;
|
|
|
|
case OVL_CLONE:
|
|
ret = vfs_clone_file_range(real_in.file, pos_in,
|
|
real_out.file, pos_out, len, flags);
|
|
break;
|
|
|
|
case OVL_DEDUPE:
|
|
ret = vfs_dedupe_file_range_one(real_in.file, pos_in,
|
|
real_out.file, pos_out, len,
|
|
flags);
|
|
break;
|
|
}
|
|
revert_creds(old_cred);
|
|
|
|
/* Update size */
|
|
ovl_copyattr(ovl_inode_real(inode_out), inode_out);
|
|
|
|
fdput(real_in);
|
|
fdput(real_out);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in,
|
|
struct file *file_out, loff_t pos_out,
|
|
size_t len, unsigned int flags)
|
|
{
|
|
return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, flags,
|
|
OVL_COPY);
|
|
}
|
|
|
|
static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in,
|
|
struct file *file_out, loff_t pos_out,
|
|
loff_t len, unsigned int remap_flags)
|
|
{
|
|
enum ovl_copyop op;
|
|
|
|
if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY))
|
|
return -EINVAL;
|
|
|
|
if (remap_flags & REMAP_FILE_DEDUP)
|
|
op = OVL_DEDUPE;
|
|
else
|
|
op = OVL_CLONE;
|
|
|
|
/*
|
|
* Don't copy up because of a dedupe request, this wouldn't make sense
|
|
* most of the time (data would be duplicated instead of deduplicated).
|
|
*/
|
|
if (op == OVL_DEDUPE &&
|
|
(!ovl_inode_upper(file_inode(file_in)) ||
|
|
!ovl_inode_upper(file_inode(file_out))))
|
|
return -EPERM;
|
|
|
|
return ovl_copyfile(file_in, pos_in, file_out, pos_out, len,
|
|
remap_flags, op);
|
|
}
|
|
|
|
const struct file_operations ovl_file_operations = {
|
|
.open = ovl_open,
|
|
.release = ovl_release,
|
|
.llseek = ovl_llseek,
|
|
.read_iter = ovl_read_iter,
|
|
.write_iter = ovl_write_iter,
|
|
.fsync = ovl_fsync,
|
|
.mmap = ovl_mmap,
|
|
.fallocate = ovl_fallocate,
|
|
.fadvise = ovl_fadvise,
|
|
.unlocked_ioctl = ovl_ioctl,
|
|
#ifdef CONFIG_COMPAT
|
|
.compat_ioctl = ovl_compat_ioctl,
|
|
#endif
|
|
.splice_read = generic_file_splice_read,
|
|
.splice_write = iter_file_splice_write,
|
|
|
|
.copy_file_range = ovl_copy_file_range,
|
|
.remap_file_range = ovl_remap_file_range,
|
|
};
|
|
|
|
int __init ovl_aio_request_cache_init(void)
|
|
{
|
|
ovl_aio_request_cachep = kmem_cache_create("ovl_aio_req",
|
|
sizeof(struct ovl_aio_req),
|
|
0, SLAB_HWCACHE_ALIGN, NULL);
|
|
if (!ovl_aio_request_cachep)
|
|
return -ENOMEM;
|
|
|
|
return 0;
|
|
}
|
|
|
|
void ovl_aio_request_cache_destroy(void)
|
|
{
|
|
kmem_cache_destroy(ovl_aio_request_cachep);
|
|
}
|