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, 60 insertions, 50 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 7cea503ae06d..ea751263fefa 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -641,28 +641,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 }
 
 /*
- * find the last mount at @dentry on vfsmount @mnt.
- * mount_lock must be held.
- */
-struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
-{
-	struct mount *p, *res = NULL;
-	p = __lookup_mnt(mnt, dentry);
-	if (!p)
-		goto out;
-	if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-		res = p;
-	hlist_for_each_entry_continue(p, mnt_hash) {
-		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
-			break;
-		if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-			res = p;
-	}
-out:
-	return res;
-}
-
-/*
  * lookup_mnt - Return the first child mount mounted at path
  *
  * "First" means first mounted chronologically.  If you create the
@@ -882,6 +860,13 @@ void mnt_set_mountpoint(struct mount *mnt,
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
+static void __attach_mnt(struct mount *mnt, struct mount *parent)
+{
+	hlist_add_head_rcu(&mnt->mnt_hash,
+			   m_hash(&parent->mnt, mnt->mnt_mountpoint));
+	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -890,28 +875,45 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	__attach_mnt(mnt, parent);
 }
 
-static void attach_shadowed(struct mount *mnt,
-			struct mount *parent,
-			struct mount *shadows)
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
-	if (shadows) {
-		hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
-		list_add(&mnt->mnt_child, &shadows->mnt_child);
-	} else {
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-	}
+	struct mountpoint *old_mp = mnt->mnt_mp;
+	struct dentry *old_mountpoint = mnt->mnt_mountpoint;
+	struct mount *old_parent = mnt->mnt_parent;
+
+	list_del_init(&mnt->mnt_child);
+	hlist_del_init(&mnt->mnt_mp_list);
+	hlist_del_init_rcu(&mnt->mnt_hash);
+
+	attach_mnt(mnt, parent, mp);
+
+	put_mountpoint(old_mp);
+
+	/*
+	 * Safely avoid even the suggestion this code might sleep or
+	 * lock the mount hash by taking advantage of the knowledge that
+	 * mnt_change_mountpoint will not release the final reference
+	 * to a mountpoint.
+	 *
+	 * During mounting, the mount passed in as the parent mount will
+	 * continue to use the old mountpoint and during unmounting, the
+	 * old mountpoint will continue to exist until namespace_unlock,
+	 * which happens well after mnt_change_mountpoint.
+	 */
+	spin_lock(&old_mountpoint->d_lock);
+	old_mountpoint->d_lockref.count--;
+	spin_unlock(&old_mountpoint->d_lock);
+
+	mnt_add_count(old_parent, -1);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt, struct mount *shadows)
+static void commit_tree(struct mount *mnt)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -929,7 +931,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 	n->mounts += n->pending_mounts;
 	n->pending_mounts = 0;
 
-	attach_shadowed(mnt, parent, shadows);
+	__attach_mnt(mnt, parent);
 	touch_mnt_namespace(n);
 }
 
@@ -1737,7 +1739,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
-			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1759,14 +1760,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			mnt_set_mountpoint(parent, p->mnt_mp, q);
-			if (!list_empty(&parent->mnt_mounts)) {
-				t = list_last_entry(&parent->mnt_mounts,
-					struct mount, mnt_child);
-				if (t->mnt_mp != p->mnt_mp)
-					t = NULL;
-			}
-			attach_shadowed(q, parent, t);
+			attach_mnt(q, parent, p->mnt_mp);
 			unlock_mount_hash();
 		}
 	}
@@ -1967,10 +1961,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 {
 	HLIST_HEAD(tree_list);
 	struct mnt_namespace *ns = dest_mnt->mnt_ns;
+	struct mountpoint *smp;
 	struct mount *child, *p;
 	struct hlist_node *n;
 	int err;
 
+	/* Preallocate a mountpoint in case the new mounts need
+	 * to be tucked under other mounts.
+	 */
+	smp = get_mountpoint(source_mnt->mnt.mnt_root);
+	if (IS_ERR(smp))
+		return PTR_ERR(smp);
+
 	/* Is there space to add these mounts to the mount namespace? */
 	if (!parent_path) {
 		err = count_mounts(ns, source_mnt);
@@ -1997,16 +1999,19 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt, NULL);
+		commit_tree(source_mnt);
 	}
 
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt_last(&child->mnt_parent->mnt,
-				      child->mnt_mountpoint);
-		commit_tree(child, q);
+		q = __lookup_mnt(&child->mnt_parent->mnt,
+				 child->mnt_mountpoint);
+		if (q)
+			mnt_change_mountpoint(child, smp, q);
+		commit_tree(child);
 	}
+	put_mountpoint(smp);
 	unlock_mount_hash();
 
 	return 0;
@@ -2021,6 +2026,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	ns->pending_mounts = 0;
+
+	read_seqlock_excl(&mount_lock);
+	put_mountpoint(smp);
+	read_sequnlock_excl(&mount_lock);
+
 	return err;
 }