linux/fs/overlayfs/dir.c
Linus Torvalds 7d6beb71da idmapped-mounts-v5.12
-----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
  ...
2021-02-23 13:39:45 -08:00

1305 lines
30 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
*
* Copyright (C) 2011 Novell Inc.
*/
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/xattr.h>
#include <linux/security.h>
#include <linux/cred.h>
#include <linux/module.h>
#include <linux/posix_acl.h>
#include <linux/posix_acl_xattr.h>
#include <linux/atomic.h>
#include <linux/ratelimit.h>
#include "overlayfs.h"
static unsigned short ovl_redirect_max = 256;
module_param_named(redirect_max, ovl_redirect_max, ushort, 0644);
MODULE_PARM_DESC(redirect_max,
"Maximum length of absolute redirect xattr value");
static int ovl_set_redirect(struct dentry *dentry, bool samedir);
int ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
{
int err;
dget(wdentry);
if (d_is_dir(wdentry))
err = ovl_do_rmdir(wdir, wdentry);
else
err = ovl_do_unlink(wdir, wdentry);
dput(wdentry);
if (err) {
pr_err("cleanup of '%pd2' failed (%i)\n",
wdentry, err);
}
return err;
}
struct dentry *ovl_lookup_temp(struct dentry *workdir)
{
struct dentry *temp;
char name[20];
static atomic_t temp_id = ATOMIC_INIT(0);
/* counter is allowed to wrap, since temp dentries are ephemeral */
snprintf(name, sizeof(name), "#%x", atomic_inc_return(&temp_id));
temp = lookup_one_len(name, workdir, strlen(name));
if (!IS_ERR(temp) && temp->d_inode) {
pr_err("workdir/%s already exists\n", name);
dput(temp);
temp = ERR_PTR(-EIO);
}
return temp;
}
/* caller holds i_mutex on workdir */
static struct dentry *ovl_whiteout(struct ovl_fs *ofs)
{
int err;
struct dentry *whiteout;
struct dentry *workdir = ofs->workdir;
struct inode *wdir = workdir->d_inode;
if (!ofs->whiteout) {
whiteout = ovl_lookup_temp(workdir);
if (IS_ERR(whiteout))
goto out;
err = ovl_do_whiteout(wdir, whiteout);
if (err) {
dput(whiteout);
whiteout = ERR_PTR(err);
goto out;
}
ofs->whiteout = whiteout;
}
if (ofs->share_whiteout) {
whiteout = ovl_lookup_temp(workdir);
if (IS_ERR(whiteout))
goto out;
err = ovl_do_link(ofs->whiteout, wdir, whiteout);
if (!err)
goto out;
if (err != -EMLINK) {
pr_warn("Failed to link whiteout - disabling whiteout inode sharing(nlink=%u, err=%i)\n",
ofs->whiteout->d_inode->i_nlink, err);
ofs->share_whiteout = false;
}
dput(whiteout);
}
whiteout = ofs->whiteout;
ofs->whiteout = NULL;
out:
return whiteout;
}
/* Caller must hold i_mutex on both workdir and dir */
int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
struct dentry *dentry)
{
struct inode *wdir = ofs->workdir->d_inode;
struct dentry *whiteout;
int err;
int flags = 0;
whiteout = ovl_whiteout(ofs);
err = PTR_ERR(whiteout);
if (IS_ERR(whiteout))
return err;
if (d_is_dir(dentry))
flags = RENAME_EXCHANGE;
err = ovl_do_rename(wdir, whiteout, dir, dentry, flags);
if (err)
goto kill_whiteout;
if (flags)
ovl_cleanup(wdir, dentry);
out:
dput(whiteout);
return err;
kill_whiteout:
ovl_cleanup(wdir, whiteout);
goto out;
}
static int ovl_mkdir_real(struct inode *dir, struct dentry **newdentry,
umode_t mode)
{
int err;
struct dentry *d, *dentry = *newdentry;
err = ovl_do_mkdir(dir, dentry, mode);
if (err)
return err;
if (likely(!d_unhashed(dentry)))
return 0;
/*
* vfs_mkdir() may succeed and leave the dentry passed
* to it unhashed and negative. If that happens, try to
* lookup a new hashed and positive dentry.
*/
d = lookup_one_len(dentry->d_name.name, dentry->d_parent,
dentry->d_name.len);
if (IS_ERR(d)) {
pr_warn("failed lookup after mkdir (%pd2, err=%i).\n",
dentry, err);
return PTR_ERR(d);
}
dput(dentry);
*newdentry = d;
return 0;
}
struct dentry *ovl_create_real(struct inode *dir, struct dentry *newdentry,
struct ovl_cattr *attr)
{
int err;
if (IS_ERR(newdentry))
return newdentry;
err = -ESTALE;
if (newdentry->d_inode)
goto out;
if (attr->hardlink) {
err = ovl_do_link(attr->hardlink, dir, newdentry);
} else {
switch (attr->mode & S_IFMT) {
case S_IFREG:
err = ovl_do_create(dir, newdentry, attr->mode);
break;
case S_IFDIR:
/* mkdir is special... */
err = ovl_mkdir_real(dir, &newdentry, attr->mode);
break;
case S_IFCHR:
case S_IFBLK:
case S_IFIFO:
case S_IFSOCK:
err = ovl_do_mknod(dir, newdentry, attr->mode,
attr->rdev);
break;
case S_IFLNK:
err = ovl_do_symlink(dir, newdentry, attr->link);
break;
default:
err = -EPERM;
}
}
if (!err && WARN_ON(!newdentry->d_inode)) {
/*
* Not quite sure if non-instantiated dentry is legal or not.
* VFS doesn't seem to care so check and warn here.
*/
err = -EIO;
}
out:
if (err) {
dput(newdentry);
return ERR_PTR(err);
}
return newdentry;
}
struct dentry *ovl_create_temp(struct dentry *workdir, struct ovl_cattr *attr)
{
return ovl_create_real(d_inode(workdir), ovl_lookup_temp(workdir),
attr);
}
static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper,
int xerr)
{
int err;
err = ovl_check_setxattr(dentry, upper, OVL_XATTR_OPAQUE, "y", 1, xerr);
if (!err)
ovl_dentry_set_opaque(dentry);
return err;
}
static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
{
/*
* Fail with -EIO when trying to create opaque dir and upper doesn't
* support xattrs. ovl_rename() calls ovl_set_opaque_xerr(-EXDEV) to
* return a specific error for noxattr case.
*/
return ovl_set_opaque_xerr(dentry, upperdentry, -EIO);
}
/*
* Common operations required to be done after creation of file on upper.
* If @hardlink is false, then @inode is a pre-allocated inode, we may or
* may not use to instantiate the new dentry.
*/
static int ovl_instantiate(struct dentry *dentry, struct inode *inode,
struct dentry *newdentry, bool hardlink)
{
struct ovl_inode_params oip = {
.upperdentry = newdentry,
.newinode = inode,
};
ovl_dir_modified(dentry->d_parent, false);
ovl_dentry_set_upper_alias(dentry);
ovl_dentry_update_reval(dentry, newdentry,
DCACHE_OP_REVALIDATE | DCACHE_OP_WEAK_REVALIDATE);
if (!hardlink) {
/*
* ovl_obtain_alias() can be called after ovl_create_real()
* and before we get here, so we may get an inode from cache
* with the same real upperdentry that is not the inode we
* pre-allocated. In this case we will use the cached inode
* to instantiate the new dentry.
*
* XXX: if we ever use ovl_obtain_alias() to decode directory
* file handles, need to use ovl_get_inode_locked() and
* d_instantiate_new() here to prevent from creating two
* hashed directory inode aliases.
*/
inode = ovl_get_inode(dentry->d_sb, &oip);
if (IS_ERR(inode))
return PTR_ERR(inode);
if (inode == oip.newinode)
ovl_set_flag(OVL_UPPERDATA, inode);
} else {
WARN_ON(ovl_inode_real(inode) != d_inode(newdentry));
dput(newdentry);
inc_nlink(inode);
}
d_instantiate(dentry, inode);
if (inode != oip.newinode) {
pr_warn_ratelimited("newly created inode found in cache (%pd2)\n",
dentry);
}
/* Force lookup of new upper hardlink to find its lower */
if (hardlink)
d_drop(dentry);
return 0;
}
static bool ovl_type_merge(struct dentry *dentry)
{
return OVL_TYPE_MERGE(ovl_path_type(dentry));
}
static bool ovl_type_origin(struct dentry *dentry)
{
return OVL_TYPE_ORIGIN(ovl_path_type(dentry));
}
static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
struct ovl_cattr *attr)
{
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *newdentry;
int err;
if (!attr->hardlink && !IS_POSIXACL(udir))
attr->mode &= ~current_umask();
inode_lock_nested(udir, I_MUTEX_PARENT);
newdentry = ovl_create_real(udir,
lookup_one_len(dentry->d_name.name,
upperdir,
dentry->d_name.len),
attr);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_unlock;
if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry)) {
/* Setting opaque here is just an optimization, allow to fail */
ovl_set_opaque(dentry, newdentry);
}
err = ovl_instantiate(dentry, inode, newdentry, !!attr->hardlink);
if (err)
goto out_cleanup;
out_unlock:
inode_unlock(udir);
return err;
out_cleanup:
ovl_cleanup(udir, newdentry);
dput(newdentry);
goto out_unlock;
}
static struct dentry *ovl_clear_empty(struct dentry *dentry,
struct list_head *list)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct path upperpath;
struct dentry *upper;
struct dentry *opaquedir;
struct kstat stat;
int err;
if (WARN_ON(!workdir))
return ERR_PTR(-EROFS);
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
ovl_path_upper(dentry, &upperpath);
err = vfs_getattr(&upperpath, &stat,
STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
if (err)
goto out_unlock;
err = -ESTALE;
if (!S_ISDIR(stat.mode))
goto out_unlock;
upper = upperpath.dentry;
if (upper->d_parent->d_inode != udir)
goto out_unlock;
opaquedir = ovl_create_temp(workdir, OVL_CATTR(stat.mode));
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out_unlock;
err = ovl_copy_xattr(dentry->d_sb, upper, opaquedir);
if (err)
goto out_cleanup;
err = ovl_set_opaque(dentry, opaquedir);
if (err)
goto out_cleanup;
inode_lock(opaquedir->d_inode);
err = ovl_set_attr(opaquedir, &stat);
inode_unlock(opaquedir->d_inode);
if (err)
goto out_cleanup;
err = ovl_do_rename(wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
if (err)
goto out_cleanup;
ovl_cleanup_whiteouts(upper, list);
ovl_cleanup(wdir, upper);
unlock_rename(workdir, upperdir);
/* dentry's upper doesn't match now, get rid of it */
d_drop(dentry);
return opaquedir;
out_cleanup:
ovl_cleanup(wdir, opaquedir);
dput(opaquedir);
out_unlock:
unlock_rename(workdir, upperdir);
out:
return ERR_PTR(err);
}
static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name,
const struct posix_acl *acl)
{
void *buffer;
size_t size;
int err;
if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !acl)
return 0;
size = posix_acl_xattr_size(acl->a_count);
buffer = kmalloc(size, GFP_KERNEL);
if (!buffer)
return -ENOMEM;
err = posix_acl_to_xattr(&init_user_ns, acl, buffer, size);
if (err < 0)
goto out_free;
err = vfs_setxattr(&init_user_ns, upperdentry, name, buffer, size, XATTR_CREATE);
out_free:
kfree(buffer);
return err;
}
static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
struct ovl_cattr *cattr)
{
struct dentry *workdir = ovl_workdir(dentry);
struct inode *wdir = workdir->d_inode;
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *udir = upperdir->d_inode;
struct dentry *upper;
struct dentry *newdentry;
int err;
struct posix_acl *acl, *default_acl;
bool hardlink = !!cattr->hardlink;
if (WARN_ON(!workdir))
return -EROFS;
if (!hardlink) {
err = posix_acl_create(dentry->d_parent->d_inode,
&cattr->mode, &default_acl, &acl);
if (err)
return err;
}
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out;
upper = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_unlock;
err = -ESTALE;
if (d_is_negative(upper) || !IS_WHITEOUT(d_inode(upper)))
goto out_dput;
newdentry = ovl_create_temp(workdir, cattr);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_dput;
/*
* mode could have been mutilated due to umask (e.g. sgid directory)
*/
if (!hardlink &&
!S_ISLNK(cattr->mode) &&
newdentry->d_inode->i_mode != cattr->mode) {
struct iattr attr = {
.ia_valid = ATTR_MODE,
.ia_mode = cattr->mode,
};
inode_lock(newdentry->d_inode);
err = notify_change(&init_user_ns, newdentry, &attr, NULL);
inode_unlock(newdentry->d_inode);
if (err)
goto out_cleanup;
}
if (!hardlink) {
err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_ACCESS,
acl);
if (err)
goto out_cleanup;
err = ovl_set_upper_acl(newdentry, XATTR_NAME_POSIX_ACL_DEFAULT,
default_acl);
if (err)
goto out_cleanup;
}
if (!hardlink && S_ISDIR(cattr->mode)) {
err = ovl_set_opaque(dentry, newdentry);
if (err)
goto out_cleanup;
err = ovl_do_rename(wdir, newdentry, udir, upper,
RENAME_EXCHANGE);
if (err)
goto out_cleanup;
ovl_cleanup(wdir, upper);
} else {
err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
if (err)
goto out_cleanup;
}
err = ovl_instantiate(dentry, inode, newdentry, hardlink);
if (err)
goto out_cleanup;
out_dput:
dput(upper);
out_unlock:
unlock_rename(workdir, upperdir);
out:
if (!hardlink) {
posix_acl_release(acl);
posix_acl_release(default_acl);
}
return err;
out_cleanup:
ovl_cleanup(wdir, newdentry);
dput(newdentry);
goto out_dput;
}
static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
struct ovl_cattr *attr, bool origin)
{
int err;
const struct cred *old_cred;
struct cred *override_cred;
struct dentry *parent = dentry->d_parent;
err = ovl_copy_up(parent);
if (err)
return err;
old_cred = ovl_override_creds(dentry->d_sb);
/*
* When linking a file with copy up origin into a new parent, mark the
* new parent dir "impure".
*/
if (origin) {
err = ovl_set_impure(parent, ovl_dentry_upper(parent));
if (err)
goto out_revert_creds;
}
err = -ENOMEM;
override_cred = prepare_creds();
if (override_cred) {
override_cred->fsuid = inode->i_uid;
override_cred->fsgid = inode->i_gid;
if (!attr->hardlink) {
err = security_dentry_create_files_as(dentry,
attr->mode, &dentry->d_name, old_cred,
override_cred);
if (err) {
put_cred(override_cred);
goto out_revert_creds;
}
}
put_cred(override_creds(override_cred));
put_cred(override_cred);
if (!ovl_dentry_is_whiteout(dentry))
err = ovl_create_upper(dentry, inode, attr);
else
err = ovl_create_over_whiteout(dentry, inode, attr);
}
out_revert_creds:
revert_creds(old_cred);
return err;
}
static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
const char *link)
{
int err;
struct inode *inode;
struct ovl_cattr attr = {
.rdev = rdev,
.link = link,
};
err = ovl_want_write(dentry);
if (err)
goto out;
/* Preallocate inode to be used by ovl_get_inode() */
err = -ENOMEM;
inode = ovl_new_inode(dentry->d_sb, mode, rdev);
if (!inode)
goto out_drop_write;
spin_lock(&inode->i_lock);
inode->i_state |= I_CREATING;
spin_unlock(&inode->i_lock);
inode_init_owner(&init_user_ns, inode, dentry->d_parent->d_inode, mode);
attr.mode = inode->i_mode;
err = ovl_create_or_link(dentry, inode, &attr, false);
/* Did we end up using the preallocated inode? */
if (inode != d_inode(dentry))
iput(inode);
out_drop_write:
ovl_drop_write(dentry);
out:
return err;
}
static int ovl_create(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, bool excl)
{
return ovl_create_object(dentry, (mode & 07777) | S_IFREG, 0, NULL);
}
static int ovl_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode)
{
return ovl_create_object(dentry, (mode & 07777) | S_IFDIR, 0, NULL);
}
static int ovl_mknod(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, umode_t mode, dev_t rdev)
{
/* Don't allow creation of "whiteout" on overlay */
if (S_ISCHR(mode) && rdev == WHITEOUT_DEV)
return -EPERM;
return ovl_create_object(dentry, mode, rdev, NULL);
}
static int ovl_symlink(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *dentry, const char *link)
{
return ovl_create_object(dentry, S_IFLNK, 0, link);
}
static int ovl_set_link_redirect(struct dentry *dentry)
{
const struct cred *old_cred;
int err;
old_cred = ovl_override_creds(dentry->d_sb);
err = ovl_set_redirect(dentry, false);
revert_creds(old_cred);
return err;
}
static int ovl_link(struct dentry *old, struct inode *newdir,
struct dentry *new)
{
int err;
struct inode *inode;
err = ovl_want_write(old);
if (err)
goto out;
err = ovl_copy_up(old);
if (err)
goto out_drop_write;
err = ovl_copy_up(new->d_parent);
if (err)
goto out_drop_write;
if (ovl_is_metacopy_dentry(old)) {
err = ovl_set_link_redirect(old);
if (err)
goto out_drop_write;
}
err = ovl_nlink_start(old);
if (err)
goto out_drop_write;
inode = d_inode(old);
ihold(inode);
err = ovl_create_or_link(new, inode,
&(struct ovl_cattr) {.hardlink = ovl_dentry_upper(old)},
ovl_type_origin(old));
if (err)
iput(inode);
ovl_nlink_end(old);
out_drop_write:
ovl_drop_write(old);
out:
return err;
}
static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper)
{
return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper);
}
static int ovl_remove_and_whiteout(struct dentry *dentry,
struct list_head *list)
{
struct ovl_fs *ofs = OVL_FS(dentry->d_sb);
struct dentry *workdir = ovl_workdir(dentry);
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct dentry *upper;
struct dentry *opaquedir = NULL;
int err;
if (WARN_ON(!workdir))
return -EROFS;
if (!list_empty(list)) {
opaquedir = ovl_clear_empty(dentry, list);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out;
}
err = ovl_lock_rename_workdir(workdir, upperdir);
if (err)
goto out_dput;
upper = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_unlock;
err = -ESTALE;
if ((opaquedir && upper != opaquedir) ||
(!opaquedir && ovl_dentry_upper(dentry) &&
!ovl_matches_upper(dentry, upper))) {
goto out_dput_upper;
}
err = ovl_cleanup_and_whiteout(ofs, d_inode(upperdir), upper);
if (err)
goto out_d_drop;
ovl_dir_modified(dentry->d_parent, true);
out_d_drop:
d_drop(dentry);
out_dput_upper:
dput(upper);
out_unlock:
unlock_rename(workdir, upperdir);
out_dput:
dput(opaquedir);
out:
return err;
}
static int ovl_remove_upper(struct dentry *dentry, bool is_dir,
struct list_head *list)
{
struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
struct inode *dir = upperdir->d_inode;
struct dentry *upper;
struct dentry *opaquedir = NULL;
int err;
if (!list_empty(list)) {
opaquedir = ovl_clear_empty(dentry, list);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir))
goto out;
}
inode_lock_nested(dir, I_MUTEX_PARENT);
upper = lookup_one_len(dentry->d_name.name, upperdir,
dentry->d_name.len);
err = PTR_ERR(upper);
if (IS_ERR(upper))
goto out_unlock;
err = -ESTALE;
if ((opaquedir && upper != opaquedir) ||
(!opaquedir && !ovl_matches_upper(dentry, upper)))
goto out_dput_upper;
if (is_dir)
err = vfs_rmdir(&init_user_ns, dir, upper);
else
err = vfs_unlink(&init_user_ns, dir, upper, NULL);
ovl_dir_modified(dentry->d_parent, ovl_type_origin(dentry));
/*
* Keeping this dentry hashed would mean having to release
* upperpath/lowerpath, which could only be done if we are the
* sole user of this dentry. Too tricky... Just unhash for
* now.
*/
if (!err)
d_drop(dentry);
out_dput_upper:
dput(upper);
out_unlock:
inode_unlock(dir);
dput(opaquedir);
out:
return err;
}
static bool ovl_pure_upper(struct dentry *dentry)
{
return !ovl_dentry_lower(dentry) &&
!ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry));
}
static void ovl_drop_nlink(struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
struct dentry *alias;
/* Try to find another, hashed alias */
spin_lock(&inode->i_lock);
hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
if (alias != dentry && !d_unhashed(alias))
break;
}
spin_unlock(&inode->i_lock);
/*
* Changes to underlying layers may cause i_nlink to lose sync with
* reality. In this case prevent the link count from going to zero
* prematurely.
*/
if (inode->i_nlink > !!alias)
drop_nlink(inode);
}
static int ovl_do_remove(struct dentry *dentry, bool is_dir)
{
int err;
const struct cred *old_cred;
struct dentry *upperdentry;
bool lower_positive = ovl_lower_positive(dentry);
LIST_HEAD(list);
/* No need to clean pure upper removed by vfs_rmdir() */
if (is_dir && (lower_positive || !ovl_pure_upper(dentry))) {
err = ovl_check_empty_dir(dentry, &list);
if (err)
goto out;
}
err = ovl_want_write(dentry);
if (err)
goto out;
err = ovl_copy_up(dentry->d_parent);
if (err)
goto out_drop_write;
err = ovl_nlink_start(dentry);
if (err)
goto out_drop_write;
old_cred = ovl_override_creds(dentry->d_sb);
if (!lower_positive)
err = ovl_remove_upper(dentry, is_dir, &list);
else
err = ovl_remove_and_whiteout(dentry, &list);
revert_creds(old_cred);
if (!err) {
if (is_dir)
clear_nlink(dentry->d_inode);
else
ovl_drop_nlink(dentry);
}
ovl_nlink_end(dentry);
/*
* Copy ctime
*
* Note: we fail to update ctime if there was no copy-up, only a
* whiteout
*/
upperdentry = ovl_dentry_upper(dentry);
if (upperdentry)
ovl_copyattr(d_inode(upperdentry), d_inode(dentry));
out_drop_write:
ovl_drop_write(dentry);
out:
ovl_cache_free(&list);
return err;
}
static int ovl_unlink(struct inode *dir, struct dentry *dentry)
{
return ovl_do_remove(dentry, false);
}
static int ovl_rmdir(struct inode *dir, struct dentry *dentry)
{
return ovl_do_remove(dentry, true);
}
static bool ovl_type_merge_or_lower(struct dentry *dentry)
{
enum ovl_path_type type = ovl_path_type(dentry);
return OVL_TYPE_MERGE(type) || !OVL_TYPE_UPPER(type);
}
static bool ovl_can_move(struct dentry *dentry)
{
return ovl_redirect_dir(dentry->d_sb) ||
!d_is_dir(dentry) || !ovl_type_merge_or_lower(dentry);
}
static char *ovl_get_redirect(struct dentry *dentry, bool abs_redirect)
{
char *buf, *ret;
struct dentry *d, *tmp;
int buflen = ovl_redirect_max + 1;
if (!abs_redirect) {
ret = kstrndup(dentry->d_name.name, dentry->d_name.len,
GFP_KERNEL);
goto out;
}
buf = ret = kmalloc(buflen, GFP_KERNEL);
if (!buf)
goto out;
buflen--;
buf[buflen] = '\0';
for (d = dget(dentry); !IS_ROOT(d);) {
const char *name;
int thislen;
spin_lock(&d->d_lock);
name = ovl_dentry_get_redirect(d);
if (name) {
thislen = strlen(name);
} else {
name = d->d_name.name;
thislen = d->d_name.len;
}
/* If path is too long, fall back to userspace move */
if (thislen + (name[0] != '/') > buflen) {
ret = ERR_PTR(-EXDEV);
spin_unlock(&d->d_lock);
goto out_put;
}
buflen -= thislen;
memcpy(&buf[buflen], name, thislen);
spin_unlock(&d->d_lock);
tmp = dget_parent(d);
dput(d);
d = tmp;
/* Absolute redirect: finished */
if (buf[buflen] == '/')
break;
buflen--;
buf[buflen] = '/';
}
ret = kstrdup(&buf[buflen], GFP_KERNEL);
out_put:
dput(d);
kfree(buf);
out:
return ret ? ret : ERR_PTR(-ENOMEM);
}
static bool ovl_need_absolute_redirect(struct dentry *dentry, bool samedir)
{
struct dentry *lowerdentry;
if (!samedir)
return true;
if (d_is_dir(dentry))
return false;
/*
* For non-dir hardlinked files, we need absolute redirects
* in general as two upper hardlinks could be in different
* dirs. We could put a relative redirect now and convert
* it to absolute redirect later. But when nlink > 1 and
* indexing is on, that means relative redirect needs to be
* converted to absolute during copy up of another lower
* hardllink as well.
*
* So without optimizing too much, just check if lower is
* a hard link or not. If lower is hard link, put absolute
* redirect.
*/
lowerdentry = ovl_dentry_lower(dentry);
return (d_inode(lowerdentry)->i_nlink > 1);
}
static int ovl_set_redirect(struct dentry *dentry, bool samedir)
{
int err;
const char *redirect = ovl_dentry_get_redirect(dentry);
bool absolute_redirect = ovl_need_absolute_redirect(dentry, samedir);
if (redirect && (!absolute_redirect || redirect[0] == '/'))
return 0;
redirect = ovl_get_redirect(dentry, absolute_redirect);
if (IS_ERR(redirect))
return PTR_ERR(redirect);
err = ovl_check_setxattr(dentry, ovl_dentry_upper(dentry),
OVL_XATTR_REDIRECT,
redirect, strlen(redirect), -EXDEV);
if (!err) {
spin_lock(&dentry->d_lock);
ovl_dentry_set_redirect(dentry, redirect);
spin_unlock(&dentry->d_lock);
} else {
kfree(redirect);
pr_warn_ratelimited("failed to set redirect (%i)\n",
err);
/* Fall back to userspace copy-up */
err = -EXDEV;
}
return err;
}
static int ovl_rename(struct user_namespace *mnt_userns, struct inode *olddir,
struct dentry *old, struct inode *newdir,
struct dentry *new, unsigned int flags)
{
int err;
struct dentry *old_upperdir;
struct dentry *new_upperdir;
struct dentry *olddentry;
struct dentry *newdentry;
struct dentry *trap;
bool old_opaque;
bool new_opaque;
bool cleanup_whiteout = false;
bool update_nlink = false;
bool overwrite = !(flags & RENAME_EXCHANGE);
bool is_dir = d_is_dir(old);
bool new_is_dir = d_is_dir(new);
bool samedir = olddir == newdir;
struct dentry *opaquedir = NULL;
const struct cred *old_cred = NULL;
LIST_HEAD(list);
err = -EINVAL;
if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE))
goto out;
flags &= ~RENAME_NOREPLACE;
/* Don't copy up directory trees */
err = -EXDEV;
if (!ovl_can_move(old))
goto out;
if (!overwrite && !ovl_can_move(new))
goto out;
if (overwrite && new_is_dir && !ovl_pure_upper(new)) {
err = ovl_check_empty_dir(new, &list);
if (err)
goto out;
}
if (overwrite) {
if (ovl_lower_positive(old)) {
if (!ovl_dentry_is_whiteout(new)) {
/* Whiteout source */
flags |= RENAME_WHITEOUT;
} else {
/* Switch whiteouts */
flags |= RENAME_EXCHANGE;
}
} else if (is_dir && ovl_dentry_is_whiteout(new)) {
flags |= RENAME_EXCHANGE;
cleanup_whiteout = true;
}
}
err = ovl_want_write(old);
if (err)
goto out;
err = ovl_copy_up(old);
if (err)
goto out_drop_write;
err = ovl_copy_up(new->d_parent);
if (err)
goto out_drop_write;
if (!overwrite) {
err = ovl_copy_up(new);
if (err)
goto out_drop_write;
} else if (d_inode(new)) {
err = ovl_nlink_start(new);
if (err)
goto out_drop_write;
update_nlink = true;
}
old_cred = ovl_override_creds(old->d_sb);
if (!list_empty(&list)) {
opaquedir = ovl_clear_empty(new, &list);
err = PTR_ERR(opaquedir);
if (IS_ERR(opaquedir)) {
opaquedir = NULL;
goto out_revert_creds;
}
}
old_upperdir = ovl_dentry_upper(old->d_parent);
new_upperdir = ovl_dentry_upper(new->d_parent);
if (!samedir) {
/*
* When moving a merge dir or non-dir with copy up origin into
* a new parent, we are marking the new parent dir "impure".
* When ovl_iterate() iterates an "impure" upper dir, it will
* lookup the origin inodes of the entries to fill d_ino.
*/
if (ovl_type_origin(old)) {
err = ovl_set_impure(new->d_parent, new_upperdir);
if (err)
goto out_revert_creds;
}
if (!overwrite && ovl_type_origin(new)) {
err = ovl_set_impure(old->d_parent, old_upperdir);
if (err)
goto out_revert_creds;
}
}
trap = lock_rename(new_upperdir, old_upperdir);
olddentry = lookup_one_len(old->d_name.name, old_upperdir,
old->d_name.len);
err = PTR_ERR(olddentry);
if (IS_ERR(olddentry))
goto out_unlock;
err = -ESTALE;
if (!ovl_matches_upper(old, olddentry))
goto out_dput_old;
newdentry = lookup_one_len(new->d_name.name, new_upperdir,
new->d_name.len);
err = PTR_ERR(newdentry);
if (IS_ERR(newdentry))
goto out_dput_old;
old_opaque = ovl_dentry_is_opaque(old);
new_opaque = ovl_dentry_is_opaque(new);
err = -ESTALE;
if (d_inode(new) && ovl_dentry_upper(new)) {
if (opaquedir) {
if (newdentry != opaquedir)
goto out_dput;
} else {
if (!ovl_matches_upper(new, newdentry))
goto out_dput;
}
} else {
if (!d_is_negative(newdentry) &&
(!new_opaque || !ovl_is_whiteout(newdentry)))
goto out_dput;
}
if (olddentry == trap)
goto out_dput;
if (newdentry == trap)
goto out_dput;
if (olddentry->d_inode == newdentry->d_inode)
goto out_dput;
err = 0;
if (ovl_type_merge_or_lower(old))
err = ovl_set_redirect(old, samedir);
else if (is_dir && !old_opaque && ovl_type_merge(new->d_parent))
err = ovl_set_opaque_xerr(old, olddentry, -EXDEV);
if (err)
goto out_dput;
if (!overwrite && ovl_type_merge_or_lower(new))
err = ovl_set_redirect(new, samedir);
else if (!overwrite && new_is_dir && !new_opaque &&
ovl_type_merge(old->d_parent))
err = ovl_set_opaque_xerr(new, newdentry, -EXDEV);
if (err)
goto out_dput;
err = ovl_do_rename(old_upperdir->d_inode, olddentry,
new_upperdir->d_inode, newdentry, flags);
if (err)
goto out_dput;
if (cleanup_whiteout)
ovl_cleanup(old_upperdir->d_inode, newdentry);
if (overwrite && d_inode(new)) {
if (new_is_dir)
clear_nlink(d_inode(new));
else
ovl_drop_nlink(new);
}
ovl_dir_modified(old->d_parent, ovl_type_origin(old) ||
(!overwrite && ovl_type_origin(new)));
ovl_dir_modified(new->d_parent, ovl_type_origin(old) ||
(d_inode(new) && ovl_type_origin(new)));
/* copy ctime: */
ovl_copyattr(d_inode(olddentry), d_inode(old));
if (d_inode(new) && ovl_dentry_upper(new))
ovl_copyattr(d_inode(newdentry), d_inode(new));
out_dput:
dput(newdentry);
out_dput_old:
dput(olddentry);
out_unlock:
unlock_rename(new_upperdir, old_upperdir);
out_revert_creds:
revert_creds(old_cred);
if (update_nlink)
ovl_nlink_end(new);
out_drop_write:
ovl_drop_write(old);
out:
dput(opaquedir);
ovl_cache_free(&list);
return err;
}
const struct inode_operations ovl_dir_inode_operations = {
.lookup = ovl_lookup,
.mkdir = ovl_mkdir,
.symlink = ovl_symlink,
.unlink = ovl_unlink,
.rmdir = ovl_rmdir,
.rename = ovl_rename,
.link = ovl_link,
.setattr = ovl_setattr,
.create = ovl_create,
.mknod = ovl_mknod,
.permission = ovl_permission,
.getattr = ovl_getattr,
.listxattr = ovl_listxattr,
.get_acl = ovl_get_acl,
.update_time = ovl_update_time,
};