![Andy Lutomirski](/assets/img/avatar_default.png)
If a process gets access to a mount from a different user namespace, that process should not be able to take advantage of setuid files or selinux entrypoints from that filesystem. Prevent this by treating mounts from other mount namespaces and those not owned by current_user_ns() or an ancestor as nosuid. This will make it safer to allow more complex filesystems to be mounted in non-root user namespaces. This does not remove the need for MNT_LOCK_NOSUID. The setuid, setgid, and file capability bits can no longer be abused if code in a user namespace were to clear nosuid on an untrusted filesystem, but this patch, by itself, is insufficient to protect the system from abuse of files that, when execed, would increase MAC privilege. As a more concrete explanation, any task that can manipulate a vfsmount associated with a given user namespace already has capabilities in that namespace and all of its descendents. If they can cause a malicious setuid, setgid, or file-caps executable to appear in that mount, then that executable will only allow them to elevate privileges in exactly the set of namespaces in which they are already privileges. On the other hand, if they can cause a malicious executable to appear with a dangerous MAC label, running it could change the caller's security context in a way that should not have been possible, even inside the namespace in which the task is confined. As a hardening measure, this would have made CVE-2014-5207 much more difficult to exploit. Signed-off-by: Andy Lutomirski <luto@amacapital.net> Signed-off-by: Seth Forshee <seth.forshee@canonical.com> Acked-by: James Morris <james.l.morris@oracle.com> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
100 lines
3 KiB
C
100 lines
3 KiB
C
/*
|
|
*
|
|
* Definitions for mount interface. This describes the in the kernel build
|
|
* linkedlist with mounted filesystems.
|
|
*
|
|
* Author: Marco van Wieringen <mvw@planets.elm.net>
|
|
*
|
|
*/
|
|
#ifndef _LINUX_MOUNT_H
|
|
#define _LINUX_MOUNT_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/list.h>
|
|
#include <linux/nodemask.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/seqlock.h>
|
|
#include <linux/atomic.h>
|
|
|
|
struct super_block;
|
|
struct vfsmount;
|
|
struct dentry;
|
|
struct mnt_namespace;
|
|
|
|
#define MNT_NOSUID 0x01
|
|
#define MNT_NODEV 0x02
|
|
#define MNT_NOEXEC 0x04
|
|
#define MNT_NOATIME 0x08
|
|
#define MNT_NODIRATIME 0x10
|
|
#define MNT_RELATIME 0x20
|
|
#define MNT_READONLY 0x40 /* does the user want this to be r/o? */
|
|
|
|
#define MNT_SHRINKABLE 0x100
|
|
#define MNT_WRITE_HOLD 0x200
|
|
|
|
#define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */
|
|
#define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */
|
|
/*
|
|
* MNT_SHARED_MASK is the set of flags that should be cleared when a
|
|
* mount becomes shared. Currently, this is only the flag that says a
|
|
* mount cannot be bind mounted, since this is how we create a mount
|
|
* that shares events with another mount. If you add a new MNT_*
|
|
* flag, consider how it interacts with shared mounts.
|
|
*/
|
|
#define MNT_SHARED_MASK (MNT_UNBINDABLE)
|
|
#define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \
|
|
| MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \
|
|
| MNT_READONLY)
|
|
#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
|
|
|
|
#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
|
|
MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED)
|
|
|
|
#define MNT_INTERNAL 0x4000
|
|
|
|
#define MNT_LOCK_ATIME 0x040000
|
|
#define MNT_LOCK_NOEXEC 0x080000
|
|
#define MNT_LOCK_NOSUID 0x100000
|
|
#define MNT_LOCK_NODEV 0x200000
|
|
#define MNT_LOCK_READONLY 0x400000
|
|
#define MNT_LOCKED 0x800000
|
|
#define MNT_DOOMED 0x1000000
|
|
#define MNT_SYNC_UMOUNT 0x2000000
|
|
#define MNT_MARKED 0x4000000
|
|
#define MNT_UMOUNT 0x8000000
|
|
|
|
struct vfsmount {
|
|
struct dentry *mnt_root; /* root of the mounted tree */
|
|
struct super_block *mnt_sb; /* pointer to superblock */
|
|
int mnt_flags;
|
|
};
|
|
|
|
struct file; /* forward dec */
|
|
struct path;
|
|
|
|
extern int mnt_want_write(struct vfsmount *mnt);
|
|
extern int mnt_want_write_file(struct file *file);
|
|
extern int mnt_clone_write(struct vfsmount *mnt);
|
|
extern void mnt_drop_write(struct vfsmount *mnt);
|
|
extern void mnt_drop_write_file(struct file *file);
|
|
extern void mntput(struct vfsmount *mnt);
|
|
extern struct vfsmount *mntget(struct vfsmount *mnt);
|
|
extern struct vfsmount *mnt_clone_internal(struct path *path);
|
|
extern int __mnt_is_readonly(struct vfsmount *mnt);
|
|
extern bool mnt_may_suid(struct vfsmount *mnt);
|
|
|
|
struct path;
|
|
extern struct vfsmount *clone_private_mount(struct path *path);
|
|
|
|
struct file_system_type;
|
|
extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
|
|
int flags, const char *name,
|
|
void *data);
|
|
|
|
extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
|
|
extern void mark_mounts_for_expiry(struct list_head *mounts);
|
|
|
|
extern dev_t name_to_dev_t(const char *name);
|
|
|
|
#endif /* _LINUX_MOUNT_H */
|