linux/fs/pnode.c
Eric W. Biederman 1064f874ab mnt: Tuck mounts under others instead of creating shadow/side mounts.
Ever since mount propagation was introduced in cases where a mount in
propagated to parent mount mountpoint pair that is already in use the
code has placed the new mount behind the old mount in the mount hash
table.

This implementation detail is problematic as it allows creating
arbitrary length mount hash chains.

Furthermore it invalidates the constraint maintained elsewhere in the
mount code that a parent mount and a mountpoint pair will have exactly
one mount upon them.  Making it hard to deal with and to talk about
this special case in the mount code.

Modify mount propagation to notice when there is already a mount at
the parent mount and mountpoint where a new mount is propagating to
and place that preexisting mount on top of the new mount.

Modify unmount propagation to notice when a mount that is being
unmounted has another mount on top of it (and no other children), and
to replace the unmounted mount with the mount on top of it.

Move the MNT_UMUONT test from __lookup_mnt_last into
__propagate_umount as that is the only call of __lookup_mnt_last where
MNT_UMOUNT may be set on any mount visible in the mount hash table.

These modifications allow:
 - __lookup_mnt_last to be removed.
 - attach_shadows to be renamed __attach_mnt and its shadow
   handling to be removed.
 - commit_tree to be simplified
 - copy_tree to be simplified

The result is an easier to understand tree of mounts that does not
allow creation of arbitrary length hash chains in the mount hash table.

The result is also a very slight userspace visible difference in semantics.
The following two cases now behave identically, where before order
mattered:

case 1: (explicit user action)
	B is a slave of A
	mount something on A/a , it will propagate to B/a
	and than mount something on B/a

case 2: (tucked mount)
	B is a slave of A
	mount something on B/a
	and than mount something on A/a

Histroically umount A/a would fail in case 1 and succeed in case 2.
Now umount A/a succeeds in both configurations.

This very small change in semantics appears if anything to be a bug
fix to me and my survey of userspace leads me to believe that no programs
will notice or care of this subtle semantic change.

v2: Updated to mnt_change_mountpoint to not call dput or mntput
and instead to decrement the counts directly.  It is guaranteed
that there will be other references when mnt_change_mountpoint is
called so this is safe.

v3: Moved put_mountpoint under mount_lock in attach_recursive_mnt
    As the locking in fs/namespace.c changed between v2 and v3.

v4: Reworked the logic in propagate_mount_busy and __propagate_umount
    that detects when a mount completely covers another mount.

v5: Removed unnecessary tests whose result is alwasy true in
    find_topper and attach_recursive_mnt.

v6: Document the user space visible semantic difference.

Cc: stable@vger.kernel.org
Fixes: b90fa9ae8f ("[PATCH] shared mount handling: bind and rbind")
Tested-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
2017-02-04 00:01:06 +13:00

496 lines
12 KiB
C

/*
* linux/fs/pnode.c
*
* (C) Copyright IBM Corporation 2005.
* Released under GPL v2.
* Author : Ram Pai (linuxram@us.ibm.com)
*
*/
#include <linux/mnt_namespace.h>
#include <linux/mount.h>
#include <linux/fs.h>
#include <linux/nsproxy.h>
#include "internal.h"
#include "pnode.h"
/* return the next shared peer mount of @p */
static inline struct mount *next_peer(struct mount *p)
{
return list_entry(p->mnt_share.next, struct mount, mnt_share);
}
static inline struct mount *first_slave(struct mount *p)
{
return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
}
static inline struct mount *next_slave(struct mount *p)
{
return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
}
static struct mount *get_peer_under_root(struct mount *mnt,
struct mnt_namespace *ns,
const struct path *root)
{
struct mount *m = mnt;
do {
/* Check the namespace first for optimization */
if (m->mnt_ns == ns && is_path_reachable(m, m->mnt.mnt_root, root))
return m;
m = next_peer(m);
} while (m != mnt);
return NULL;
}
/*
* Get ID of closest dominating peer group having a representative
* under the given root.
*
* Caller must hold namespace_sem
*/
int get_dominating_id(struct mount *mnt, const struct path *root)
{
struct mount *m;
for (m = mnt->mnt_master; m != NULL; m = m->mnt_master) {
struct mount *d = get_peer_under_root(m, mnt->mnt_ns, root);
if (d)
return d->mnt_group_id;
}
return 0;
}
static int do_make_slave(struct mount *mnt)
{
struct mount *master, *slave_mnt;
if (list_empty(&mnt->mnt_share)) {
if (IS_MNT_SHARED(mnt)) {
mnt_release_group_id(mnt);
CLEAR_MNT_SHARED(mnt);
}
master = mnt->mnt_master;
if (!master) {
struct list_head *p = &mnt->mnt_slave_list;
while (!list_empty(p)) {
slave_mnt = list_first_entry(p,
struct mount, mnt_slave);
list_del_init(&slave_mnt->mnt_slave);
slave_mnt->mnt_master = NULL;
}
return 0;
}
} else {
struct mount *m;
/*
* slave 'mnt' to a peer mount that has the
* same root dentry. If none is available then
* slave it to anything that is available.
*/
for (m = master = next_peer(mnt); m != mnt; m = next_peer(m)) {
if (m->mnt.mnt_root == mnt->mnt.mnt_root) {
master = m;
break;
}
}
list_del_init(&mnt->mnt_share);
mnt->mnt_group_id = 0;
CLEAR_MNT_SHARED(mnt);
}
list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
slave_mnt->mnt_master = master;
list_move(&mnt->mnt_slave, &master->mnt_slave_list);
list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
INIT_LIST_HEAD(&mnt->mnt_slave_list);
mnt->mnt_master = master;
return 0;
}
/*
* vfsmount lock must be held for write
*/
void change_mnt_propagation(struct mount *mnt, int type)
{
if (type == MS_SHARED) {
set_mnt_shared(mnt);
return;
}
do_make_slave(mnt);
if (type != MS_SLAVE) {
list_del_init(&mnt->mnt_slave);
mnt->mnt_master = NULL;
if (type == MS_UNBINDABLE)
mnt->mnt.mnt_flags |= MNT_UNBINDABLE;
else
mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE;
}
}
/*
* get the next mount in the propagation tree.
* @m: the mount seen last
* @origin: the original mount from where the tree walk initiated
*
* Note that peer groups form contiguous segments of slave lists.
* We rely on that in get_source() to be able to find out if
* vfsmount found while iterating with propagation_next() is
* a peer of one we'd found earlier.
*/
static struct mount *propagation_next(struct mount *m,
struct mount *origin)
{
/* are there any slaves of this mount? */
if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
return first_slave(m);
while (1) {
struct mount *master = m->mnt_master;
if (master == origin->mnt_master) {
struct mount *next = next_peer(m);
return (next == origin) ? NULL : next;
} else if (m->mnt_slave.next != &master->mnt_slave_list)
return next_slave(m);
/* back at master */
m = master;
}
}
static struct mount *next_group(struct mount *m, struct mount *origin)
{
while (1) {
while (1) {
struct mount *next;
if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
return first_slave(m);
next = next_peer(m);
if (m->mnt_group_id == origin->mnt_group_id) {
if (next == origin)
return NULL;
} else if (m->mnt_slave.next != &next->mnt_slave)
break;
m = next;
}
/* m is the last peer */
while (1) {
struct mount *master = m->mnt_master;
if (m->mnt_slave.next != &master->mnt_slave_list)
return next_slave(m);
m = next_peer(master);
if (master->mnt_group_id == origin->mnt_group_id)
break;
if (master->mnt_slave.next == &m->mnt_slave)
break;
m = master;
}
if (m == origin)
return NULL;
}
}
/* all accesses are serialized by namespace_sem */
static struct user_namespace *user_ns;
static struct mount *last_dest, *first_source, *last_source, *dest_master;
static struct mountpoint *mp;
static struct hlist_head *list;
static inline bool peers(struct mount *m1, struct mount *m2)
{
return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id;
}
static int propagate_one(struct mount *m)
{
struct mount *child;
int type;
/* skip ones added by this propagate_mnt() */
if (IS_MNT_NEW(m))
return 0;
/* skip if mountpoint isn't covered by it */
if (!is_subdir(mp->m_dentry, m->mnt.mnt_root))
return 0;
if (peers(m, last_dest)) {
type = CL_MAKE_SHARED;
} else {
struct mount *n, *p;
bool done;
for (n = m; ; n = p) {
p = n->mnt_master;
if (p == dest_master || IS_MNT_MARKED(p))
break;
}
do {
struct mount *parent = last_source->mnt_parent;
if (last_source == first_source)
break;
done = parent->mnt_master == p;
if (done && peers(n, parent))
break;
last_source = last_source->mnt_master;
} while (!done);
type = CL_SLAVE;
/* beginning of peer group among the slaves? */
if (IS_MNT_SHARED(m))
type |= CL_MAKE_SHARED;
}
/* Notice when we are propagating across user namespaces */
if (m->mnt_ns->user_ns != user_ns)
type |= CL_UNPRIVILEGED;
child = copy_tree(last_source, last_source->mnt.mnt_root, type);
if (IS_ERR(child))
return PTR_ERR(child);
child->mnt.mnt_flags &= ~MNT_LOCKED;
mnt_set_mountpoint(m, mp, child);
last_dest = m;
last_source = child;
if (m->mnt_master != dest_master) {
read_seqlock_excl(&mount_lock);
SET_MNT_MARK(m->mnt_master);
read_sequnlock_excl(&mount_lock);
}
hlist_add_head(&child->mnt_hash, list);
return count_mounts(m->mnt_ns, child);
}
/*
* mount 'source_mnt' under the destination 'dest_mnt' at
* dentry 'dest_dentry'. And propagate that mount to
* all the peer and slave mounts of 'dest_mnt'.
* Link all the new mounts into a propagation tree headed at
* source_mnt. Also link all the new mounts using ->mnt_list
* headed at source_mnt's ->mnt_list
*
* @dest_mnt: destination mount.
* @dest_dentry: destination dentry.
* @source_mnt: source mount.
* @tree_list : list of heads of trees to be attached.
*/
int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
struct mount *source_mnt, struct hlist_head *tree_list)
{
struct mount *m, *n;
int ret = 0;
/*
* we don't want to bother passing tons of arguments to
* propagate_one(); everything is serialized by namespace_sem,
* so globals will do just fine.
*/
user_ns = current->nsproxy->mnt_ns->user_ns;
last_dest = dest_mnt;
first_source = source_mnt;
last_source = source_mnt;
mp = dest_mp;
list = tree_list;
dest_master = dest_mnt->mnt_master;
/* all peers of dest_mnt, except dest_mnt itself */
for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) {
ret = propagate_one(n);
if (ret)
goto out;
}
/* all slave groups */
for (m = next_group(dest_mnt, dest_mnt); m;
m = next_group(m, dest_mnt)) {
/* everything in that slave group */
n = m;
do {
ret = propagate_one(n);
if (ret)
goto out;
n = next_peer(n);
} while (n != m);
}
out:
read_seqlock_excl(&mount_lock);
hlist_for_each_entry(n, tree_list, mnt_hash) {
m = n->mnt_parent;
if (m->mnt_master != dest_mnt->mnt_master)
CLEAR_MNT_MARK(m->mnt_master);
}
read_sequnlock_excl(&mount_lock);
return ret;
}
static struct mount *find_topper(struct mount *mnt)
{
/* If there is exactly one mount covering mnt completely return it. */
struct mount *child;
if (!list_is_singular(&mnt->mnt_mounts))
return NULL;
child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);
if (child->mnt_mountpoint != mnt->mnt.mnt_root)
return NULL;
return child;
}
/*
* return true if the refcount is greater than count
*/
static inline int do_refcount_check(struct mount *mnt, int count)
{
return mnt_get_count(mnt) > count;
}
/*
* check if the mount 'mnt' can be unmounted successfully.
* @mnt: the mount to be checked for unmount
* NOTE: unmounting 'mnt' would naturally propagate to all
* other mounts its parent propagates to.
* Check if any of these mounts that **do not have submounts**
* have more references than 'refcnt'. If so return busy.
*
* vfsmount lock must be held for write
*/
int propagate_mount_busy(struct mount *mnt, int refcnt)
{
struct mount *m, *child, *topper;
struct mount *parent = mnt->mnt_parent;
if (mnt == parent)
return do_refcount_check(mnt, refcnt);
/*
* quickly check if the current mount can be unmounted.
* If not, we don't have to go checking for all other
* mounts
*/
if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt))
return 1;
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
int count = 1;
child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
if (!child)
continue;
/* Is there exactly one mount on the child that covers
* it completely whose reference should be ignored?
*/
topper = find_topper(child);
if (topper)
count += 1;
else if (!list_empty(&child->mnt_mounts))
continue;
if (do_refcount_check(child, count))
return 1;
}
return 0;
}
/*
* Clear MNT_LOCKED when it can be shown to be safe.
*
* mount_lock lock must be held for write
*/
void propagate_mount_unlock(struct mount *mnt)
{
struct mount *parent = mnt->mnt_parent;
struct mount *m, *child;
BUG_ON(parent == mnt);
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
if (child)
child->mnt.mnt_flags &= ~MNT_LOCKED;
}
}
/*
* Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
*/
static void mark_umount_candidates(struct mount *mnt)
{
struct mount *parent = mnt->mnt_parent;
struct mount *m;
BUG_ON(parent == mnt);
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
struct mount *child = __lookup_mnt(&m->mnt,
mnt->mnt_mountpoint);
if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
continue;
if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
SET_MNT_MARK(child);
}
}
}
/*
* NOTE: unmounting 'mnt' naturally propagates to all other mounts its
* parent propagates to.
*/
static void __propagate_umount(struct mount *mnt)
{
struct mount *parent = mnt->mnt_parent;
struct mount *m;
BUG_ON(parent == mnt);
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
struct mount *topper;
struct mount *child = __lookup_mnt(&m->mnt,
mnt->mnt_mountpoint);
/*
* umount the child only if the child has no children
* and the child is marked safe to unmount.
*/
if (!child || !IS_MNT_MARKED(child))
continue;
CLEAR_MNT_MARK(child);
/* If there is exactly one mount covering all of child
* replace child with that mount.
*/
topper = find_topper(child);
if (topper)
mnt_change_mountpoint(child->mnt_parent, child->mnt_mp,
topper);
if (list_empty(&child->mnt_mounts)) {
list_del_init(&child->mnt_child);
child->mnt.mnt_flags |= MNT_UMOUNT;
list_move_tail(&child->mnt_list, &mnt->mnt_list);
}
}
}
/*
* collect all mounts that receive propagation from the mount in @list,
* and return these additional mounts in the same list.
* @list: the list of mounts to be unmounted.
*
* vfsmount lock must be held for write
*/
int propagate_umount(struct list_head *list)
{
struct mount *mnt;
list_for_each_entry_reverse(mnt, list, mnt_list)
mark_umount_candidates(mnt);
list_for_each_entry(mnt, list, mnt_list)
__propagate_umount(mnt);
return 0;
}