8f502d5b9e
Pull usernamespace mount fixes from Eric Biederman: "Way back in October Andrey Vagin reported that umount(MNT_DETACH) could be used to defeat MNT_LOCKED. As I worked to fix this I discovered that combined with mount propagation and an appropriate selection of shared subtrees a reference to a directory on an unmounted filesystem is not necessary. That MNT_DETACH is allowed in user namespace in a form that can break MNT_LOCKED comes from my early misunderstanding what MNT_DETACH does. To avoid breaking existing userspace the conflict between MNT_DETACH and MNT_LOCKED is fixed by leaving mounts that are locked to their parents in the mount hash table until the last reference goes away. While investigating this issue I also found an issue with __detach_mounts. The code was unnecessarily and incorrectly triggering mount propagation. Resulting in too many mounts going away when a directory is deleted, and too many cpu cycles are burned while doing that. Looking some more I realized that __detach_mounts by only keeping mounts connected that were MNT_LOCKED it had the potential to still leak information so I tweaked the code to keep everything locked together that possibly could be. This code was almost ready last cycle but Al invented fs_pin which slightly simplifies this code but required rewrites and retesting, and I have not been in top form for a while so it took me a while to get all of that done. Similiarly this pull request is late because I have been feeling absolutely miserable all week. The issue of being able to escape a bind mount has not yet been addressed, as the fixes are not yet mature" * 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: mnt: Update detach_mounts to leave mounts connected mnt: Fix the error check in __detach_mounts mnt: Honor MNT_LOCKED when detaching mounts fs_pin: Allow for the possibility that m_list or s_list go unused. mnt: Factor umount_mnt from umount_tree mnt: Factor out unhash_mnt from detach_mnt and umount_tree mnt: Fail collect_mounts when applied to unmounted mounts mnt: Don't propagate unmounts to locked mounts mnt: On an unmount propagate clearing of MNT_LOCKED mnt: Delay removal from the mount hash. mnt: Add MNT_UMOUNT flag mnt: In umount_tree reuse mnt_list instead of mnt_hash mnt: Don't propagate umounts in __detach_mounts mnt: Improve the umount_tree flags mnt: Use hlist_move_list in namespace_unlock
99 lines
3 KiB
C
99 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);
|
|
|
|
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 */
|