2019-06-04 17:11:33 +09:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0-only */
|
2016-12-16 19:02:56 +09:00
|
|
|
/*
|
|
|
|
*
|
|
|
|
* Copyright (C) 2011 Novell Inc.
|
|
|
|
* Copyright (C) 2016 Red Hat, Inc.
|
|
|
|
*/
|
|
|
|
|
|
|
|
struct ovl_config {
|
|
|
|
char *lowerdir;
|
|
|
|
char *upperdir;
|
|
|
|
char *workdir;
|
|
|
|
bool default_permissions;
|
2016-12-16 19:02:56 +09:00
|
|
|
bool redirect_dir;
|
2017-12-11 19:28:10 +09:00
|
|
|
bool redirect_follow;
|
|
|
|
const char *redirect_mode;
|
2017-06-21 21:28:36 +09:00
|
|
|
bool index;
|
2018-01-19 18:26:53 +09:00
|
|
|
bool nfs_export;
|
2018-03-29 15:08:18 +09:00
|
|
|
int xino;
|
2018-05-12 00:49:27 +09:00
|
|
|
bool metacopy;
|
FROMLIST: overlayfs: override_creds=off option bypass creator_cred
By default, all access to the upper, lower and work directories is the
recorded mounter's MAC and DAC credentials. The incoming accesses are
checked against the caller's credentials.
If the principles of least privilege are applied, the mounter's
credentials might not overlap the credentials of the caller's when
accessing the overlayfs filesystem. For example, a file that a lower
DAC privileged caller can execute, is MAC denied to the generally
higher DAC privileged mounter, to prevent an attack vector.
We add the option to turn off override_creds in the mount options; all
subsequent operations after mount on the filesystem will be only the
caller's credentials. The module boolean parameter and mount option
override_creds is also added as a presence check for this "feature",
existence of /sys/module/overlay/parameters/override_creds.
It was not always this way. Circa 4.6 there was no recorded mounter's
credentials, instead privileged access to upper or work directories
were temporarily increased to perform the operations. The MAC
(selinux) policies were caller's in all cases. override_creds=off
partially returns us to this older access model minus the insecure
temporary credential increases. This is to permit use in a system
with non-overlapping security models for each executable including
the agent that mounts the overlayfs filesystem. In Android
this is the case since init, which performs the mount operations,
has a minimal MAC set of privileges to reduce any attack surface,
and services that use the content have a different set of MAC
privileges (eg: read, for vendor labelled configuration, execute for
vendor libraries and modules). The caveats are not a problem in
the Android usage model, however they should be fixed for
completeness and for general use in time.
Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: linux-unionfs@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: kernel-team@android.com
(cherry picked from https://lore.kernel.org/lkml/20191104215253.141818-5-salyzyn@android.com/)
Signed-off-by: Mark Salyzyn <salyzyn@google.com>
Bug: 133515582
Bug: 136124883
Bug: 129319403
Change-Id: I6a82338fcb8b30b8e6f5d4c26b473730bdfd4488
2018-06-15 03:15:22 +09:00
|
|
|
bool override_creds;
|
2016-12-16 19:02:56 +09:00
|
|
|
};
|
|
|
|
|
2018-03-29 02:22:41 +09:00
|
|
|
struct ovl_sb {
|
|
|
|
struct super_block *sb;
|
|
|
|
dev_t pseudo_dev;
|
2019-11-15 05:28:41 +09:00
|
|
|
/* Unusable (conflicting) uuid */
|
|
|
|
bool bad_uuid;
|
2018-03-29 02:22:41 +09:00
|
|
|
};
|
|
|
|
|
2017-07-24 15:57:54 +09:00
|
|
|
struct ovl_layer {
|
2023-06-13 17:13:37 +09:00
|
|
|
/* ovl_free_fs() relies on @mnt being the first member! */
|
2017-07-24 15:57:54 +09:00
|
|
|
struct vfsmount *mnt;
|
ovl: detect overlapping layers
Overlapping overlay layers are not supported and can cause unexpected
behavior, but overlayfs does not currently check or warn about these
configurations.
User is not supposed to specify the same directory for upper and
lower dirs or for different lower layers and user is not supposed to
specify directories that are descendants of each other for overlay
layers, but that is exactly what this zysbot repro did:
https://syzkaller.appspot.com/x/repro.syz?x=12c7a94f400000
Moving layer root directories into other layers while overlayfs
is mounted could also result in unexpected behavior.
This commit places "traps" in the overlay inode hash table.
Those traps are dummy overlay inodes that are hashed by the layers
root inodes.
On mount, the hash table trap entries are used to verify that overlay
layers are not overlapping. While at it, we also verify that overlay
layers are not overlapping with directories "in-use" by other overlay
instances as upperdir/workdir.
On lookup, the trap entries are used to verify that overlay layers
root inodes have not been moved into other layers after mount.
Some examples:
$ ./run --ov --samefs -s
...
( mkdir -p base/upper/0/u base/upper/0/w base/lower lower upper mnt
mount -o bind base/lower lower
mount -o bind base/upper upper
mount -t overlay none mnt ...
-o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w)
$ umount mnt
$ mount -t overlay none mnt ...
-o lowerdir=base,upperdir=upper/0/u,workdir=upper/0/w
[ 94.434900] overlayfs: overlapping upperdir path
mount: mount overlay on mnt failed: Too many levels of symbolic links
$ mount -t overlay none mnt ...
-o lowerdir=upper/0/u,upperdir=upper/0/u,workdir=upper/0/w
[ 151.350132] overlayfs: conflicting lowerdir path
mount: none is already mounted or mnt busy
$ mount -t overlay none mnt ...
-o lowerdir=lower:lower/a,upperdir=upper/0/u,workdir=upper/0/w
[ 201.205045] overlayfs: overlapping lowerdir path
mount: mount overlay on mnt failed: Too many levels of symbolic links
$ mount -t overlay none mnt ...
-o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w
$ mv base/upper/0/ base/lower/
$ find mnt/0
mnt/0
mnt/0/w
find: 'mnt/0/w/work': Too many levels of symbolic links
find: 'mnt/0/u': Too many levels of symbolic links
Reported-by: syzbot+9c69c282adc4edd2b540@syzkaller.appspotmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-04-18 23:42:08 +09:00
|
|
|
/* Trap in ovl inode cache */
|
|
|
|
struct inode *trap;
|
2018-03-29 02:22:41 +09:00
|
|
|
struct ovl_sb *fs;
|
|
|
|
/* Index of this layer in fs root (upper idx == 0) */
|
2017-11-09 02:23:36 +09:00
|
|
|
int idx;
|
2018-03-29 02:22:41 +09:00
|
|
|
/* One fsid per unique underlying sb (upper fsid == 0) */
|
|
|
|
int fsid;
|
2017-07-24 15:57:54 +09:00
|
|
|
};
|
|
|
|
|
2023-06-13 17:13:37 +09:00
|
|
|
/*
|
|
|
|
* ovl_free_fs() relies on @mnt being the first member when unmounting
|
|
|
|
* the private mounts created for each layer. Let's check both the
|
|
|
|
* offset and type.
|
|
|
|
*/
|
|
|
|
static_assert(offsetof(struct ovl_layer, mnt) == 0);
|
|
|
|
static_assert(__same_type(typeof_member(struct ovl_layer, mnt), struct vfsmount *));
|
|
|
|
|
2017-07-24 15:57:54 +09:00
|
|
|
struct ovl_path {
|
|
|
|
struct ovl_layer *layer;
|
|
|
|
struct dentry *dentry;
|
|
|
|
};
|
|
|
|
|
2016-12-16 19:02:56 +09:00
|
|
|
/* private information held for overlayfs's superblock */
|
|
|
|
struct ovl_fs {
|
|
|
|
struct vfsmount *upper_mnt;
|
2018-03-29 02:22:41 +09:00
|
|
|
unsigned int numlower;
|
|
|
|
/* Number of unique lower sb that differ from upper sb */
|
|
|
|
unsigned int numlowerfs;
|
2017-07-24 15:57:54 +09:00
|
|
|
struct ovl_layer *lower_layers;
|
2018-03-29 02:22:41 +09:00
|
|
|
struct ovl_sb *lower_fs;
|
2017-06-21 21:28:33 +09:00
|
|
|
/* workbasedir is the path at workdir= mount option */
|
|
|
|
struct dentry *workbasedir;
|
|
|
|
/* workdir is the 'work' directory under workbasedir */
|
2016-12-16 19:02:56 +09:00
|
|
|
struct dentry *workdir;
|
2017-06-21 21:28:36 +09:00
|
|
|
/* index directory listing overlay inodes by origin file handle */
|
|
|
|
struct dentry *indexdir;
|
2016-12-16 19:02:56 +09:00
|
|
|
long namelen;
|
2016-12-16 19:02:56 +09:00
|
|
|
/* pathnames of lower and upper dirs, for show_options */
|
|
|
|
struct ovl_config config;
|
|
|
|
/* creds of process who forced instantiation of super block */
|
|
|
|
const struct cred *creator_cred;
|
2017-01-17 13:34:53 +09:00
|
|
|
bool tmpfile;
|
2017-05-17 06:12:40 +09:00
|
|
|
bool noxattr;
|
2017-09-29 16:21:21 +09:00
|
|
|
/* Did we take the inuse lock? */
|
|
|
|
bool upperdir_locked;
|
|
|
|
bool workdir_locked;
|
ovl: detect overlapping layers
Overlapping overlay layers are not supported and can cause unexpected
behavior, but overlayfs does not currently check or warn about these
configurations.
User is not supposed to specify the same directory for upper and
lower dirs or for different lower layers and user is not supposed to
specify directories that are descendants of each other for overlay
layers, but that is exactly what this zysbot repro did:
https://syzkaller.appspot.com/x/repro.syz?x=12c7a94f400000
Moving layer root directories into other layers while overlayfs
is mounted could also result in unexpected behavior.
This commit places "traps" in the overlay inode hash table.
Those traps are dummy overlay inodes that are hashed by the layers
root inodes.
On mount, the hash table trap entries are used to verify that overlay
layers are not overlapping. While at it, we also verify that overlay
layers are not overlapping with directories "in-use" by other overlay
instances as upperdir/workdir.
On lookup, the trap entries are used to verify that overlay layers
root inodes have not been moved into other layers after mount.
Some examples:
$ ./run --ov --samefs -s
...
( mkdir -p base/upper/0/u base/upper/0/w base/lower lower upper mnt
mount -o bind base/lower lower
mount -o bind base/upper upper
mount -t overlay none mnt ...
-o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w)
$ umount mnt
$ mount -t overlay none mnt ...
-o lowerdir=base,upperdir=upper/0/u,workdir=upper/0/w
[ 94.434900] overlayfs: overlapping upperdir path
mount: mount overlay on mnt failed: Too many levels of symbolic links
$ mount -t overlay none mnt ...
-o lowerdir=upper/0/u,upperdir=upper/0/u,workdir=upper/0/w
[ 151.350132] overlayfs: conflicting lowerdir path
mount: none is already mounted or mnt busy
$ mount -t overlay none mnt ...
-o lowerdir=lower:lower/a,upperdir=upper/0/u,workdir=upper/0/w
[ 201.205045] overlayfs: overlapping lowerdir path
mount: mount overlay on mnt failed: Too many levels of symbolic links
$ mount -t overlay none mnt ...
-o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w
$ mv base/upper/0/ base/lower/
$ find mnt/0
mnt/0
mnt/0/w
find: 'mnt/0/w/work': Too many levels of symbolic links
find: 'mnt/0/u': Too many levels of symbolic links
Reported-by: syzbot+9c69c282adc4edd2b540@syzkaller.appspotmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-04-18 23:42:08 +09:00
|
|
|
/* Traps in ovl inode cache */
|
|
|
|
struct inode *upperdir_trap;
|
2019-07-12 21:24:34 +09:00
|
|
|
struct inode *workbasedir_trap;
|
ovl: detect overlapping layers
Overlapping overlay layers are not supported and can cause unexpected
behavior, but overlayfs does not currently check or warn about these
configurations.
User is not supposed to specify the same directory for upper and
lower dirs or for different lower layers and user is not supposed to
specify directories that are descendants of each other for overlay
layers, but that is exactly what this zysbot repro did:
https://syzkaller.appspot.com/x/repro.syz?x=12c7a94f400000
Moving layer root directories into other layers while overlayfs
is mounted could also result in unexpected behavior.
This commit places "traps" in the overlay inode hash table.
Those traps are dummy overlay inodes that are hashed by the layers
root inodes.
On mount, the hash table trap entries are used to verify that overlay
layers are not overlapping. While at it, we also verify that overlay
layers are not overlapping with directories "in-use" by other overlay
instances as upperdir/workdir.
On lookup, the trap entries are used to verify that overlay layers
root inodes have not been moved into other layers after mount.
Some examples:
$ ./run --ov --samefs -s
...
( mkdir -p base/upper/0/u base/upper/0/w base/lower lower upper mnt
mount -o bind base/lower lower
mount -o bind base/upper upper
mount -t overlay none mnt ...
-o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w)
$ umount mnt
$ mount -t overlay none mnt ...
-o lowerdir=base,upperdir=upper/0/u,workdir=upper/0/w
[ 94.434900] overlayfs: overlapping upperdir path
mount: mount overlay on mnt failed: Too many levels of symbolic links
$ mount -t overlay none mnt ...
-o lowerdir=upper/0/u,upperdir=upper/0/u,workdir=upper/0/w
[ 151.350132] overlayfs: conflicting lowerdir path
mount: none is already mounted or mnt busy
$ mount -t overlay none mnt ...
-o lowerdir=lower:lower/a,upperdir=upper/0/u,workdir=upper/0/w
[ 201.205045] overlayfs: overlapping lowerdir path
mount: mount overlay on mnt failed: Too many levels of symbolic links
$ mount -t overlay none mnt ...
-o lowerdir=lower,upperdir=upper/0/u,workdir=upper/0/w
$ mv base/upper/0/ base/lower/
$ find mnt/0
mnt/0
mnt/0/w
find: 'mnt/0/w/work': Too many levels of symbolic links
find: 'mnt/0/u': Too many levels of symbolic links
Reported-by: syzbot+9c69c282adc4edd2b540@syzkaller.appspotmail.com
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
2019-04-18 23:42:08 +09:00
|
|
|
struct inode *workdir_trap;
|
|
|
|
struct inode *indexdir_trap;
|
2017-11-07 20:55:04 +09:00
|
|
|
/* Inode numbers in all layers do not use the high xino_bits */
|
|
|
|
unsigned int xino_bits;
|
2016-12-16 19:02:56 +09:00
|
|
|
};
|
|
|
|
|
|
|
|
/* private information held for every overlayfs dentry */
|
|
|
|
struct ovl_entry {
|
|
|
|
union {
|
2017-07-05 05:03:18 +09:00
|
|
|
struct {
|
2018-01-15 02:25:31 +09:00
|
|
|
unsigned long flags;
|
2017-07-05 05:03:18 +09:00
|
|
|
};
|
2016-12-16 19:02:56 +09:00
|
|
|
struct rcu_head rcu;
|
|
|
|
};
|
|
|
|
unsigned numlower;
|
2017-07-24 15:57:54 +09:00
|
|
|
struct ovl_path lowerstack[];
|
2016-12-16 19:02:56 +09:00
|
|
|
};
|
|
|
|
|
|
|
|
struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
|
|
|
|
|
2018-01-15 02:25:31 +09:00
|
|
|
static inline struct ovl_entry *OVL_E(struct dentry *dentry)
|
|
|
|
{
|
|
|
|
return (struct ovl_entry *) dentry->d_fsdata;
|
|
|
|
}
|
|
|
|
|
2017-06-12 15:54:40 +09:00
|
|
|
struct ovl_inode {
|
2018-05-12 00:49:30 +09:00
|
|
|
union {
|
|
|
|
struct ovl_dir_cache *cache; /* directory */
|
|
|
|
struct inode *lowerdata; /* regular file */
|
|
|
|
};
|
2017-07-05 05:03:16 +09:00
|
|
|
const char *redirect;
|
2017-07-05 05:03:16 +09:00
|
|
|
u64 version;
|
2017-07-05 05:03:16 +09:00
|
|
|
unsigned long flags;
|
2017-06-12 15:54:40 +09:00
|
|
|
struct inode vfs_inode;
|
2017-07-05 05:03:16 +09:00
|
|
|
struct dentry *__upperdentry;
|
2017-07-05 05:03:16 +09:00
|
|
|
struct inode *lower;
|
2017-06-21 21:28:51 +09:00
|
|
|
|
|
|
|
/* synchronize copy up and more */
|
|
|
|
struct mutex lock;
|
2017-06-12 15:54:40 +09:00
|
|
|
};
|
|
|
|
|
|
|
|
static inline struct ovl_inode *OVL_I(struct inode *inode)
|
|
|
|
{
|
|
|
|
return container_of(inode, struct ovl_inode, vfs_inode);
|
|
|
|
}
|
2017-07-05 05:03:16 +09:00
|
|
|
|
|
|
|
static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
|
|
|
|
{
|
2017-10-24 19:22:48 +09:00
|
|
|
return READ_ONCE(oi->__upperdentry);
|
2017-07-05 05:03:16 +09:00
|
|
|
}
|