mnt: Tuck mounts under others instead of creating shadow/side mounts.

commit 1064f874abc0d05eeed8993815f584d847b72486 upstream.

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.

Fixes: b90fa9ae8f51 ("[PATCH] shared mount handling: bind and rbind")
Tested-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 49 insertions, 12 deletions

diff --git a/fs/pnode.c b/fs/pnode.c
index 99899705b105..b9f2af59b9a6 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -324,6 +324,21 @@ out:
 	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
  */
@@ -344,9 +359,8 @@ static inline int do_refcount_check(struct mount *mnt, int count)
  */
 int propagate_mount_busy(struct mount *mnt, int refcnt)
 {
-	struct mount *m, *child;
+	struct mount *m, *child, *topper;
 	struct mount *parent = mnt->mnt_parent;
-	int ret = 0;
 
 	if (mnt == parent)
 		return do_refcount_check(mnt, refcnt);
@@ -361,12 +375,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
 
 	for (m = propagation_next(parent, parent); m;
 	     		m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
-		if (child && list_empty(&child->mnt_mounts) &&
-		    (ret = do_refcount_check(child, 1)))
-			break;
+		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 ret;
+	return 0;
 }
 
 /*
@@ -383,7 +409,7 @@ void propagate_mount_unlock(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
 		if (child)
 			child->mnt.mnt_flags &= ~MNT_LOCKED;
 	}
@@ -401,9 +427,11 @@ static void mark_umount_candidates(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		struct mount *child = __lookup_mnt_last(&m->mnt,
+		struct mount *child = __lookup_mnt(&m->mnt,
 						mnt->mnt_mountpoint);
-		if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) {
+		if (!child || (child->mnt.mnt_flags & MNT_UMOUNT))
+			continue;
+		if (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m)) {
 			SET_MNT_MARK(child);
 		}
 	}
@@ -422,8 +450,8 @@ static void __propagate_umount(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-
-		struct mount *child = __lookup_mnt_last(&m->mnt,
+		struct mount *topper;
+		struct mount *child = __lookup_mnt(&m->mnt,
 						mnt->mnt_mountpoint);
 		/*
 		 * umount the child only if the child has no children
@@ -432,6 +460,15 @@ static void __propagate_umount(struct mount *mnt)
 		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;