[patch 4/7] vfs: mountinfo: add mount peer group ID

Add a unique ID to each peer group using the IDR infrastructure.  The
identifiers are reused after the peer group dissolves.

The IDR structures are protected by holding namepspace_sem for write
while allocating or deallocating IDs.

IDs are allocated when a previously unshared vfsmount becomes the
first member of a peer group.  When a new member is added to an
existing group, the ID is copied from one of the old members.

IDs are freed when the last member of a peer group is unshared.

Setting the MNT_SHARED flag on members of a subtree is done as a
separate step, after all the IDs have been allocated.  This way an
allocation failure can be cleaned up easilty, without affecting the
propagation state.

Based on design sketch by Al Viro.

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

3 files changed, 95 insertions, 4 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index 8ca6317cb40..cefa1d9939b 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -41,6 +41,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
 
 static int event;
 static DEFINE_IDA(mnt_id_ida);
+static DEFINE_IDA(mnt_group_ida);
 
 static struct list_head *mount_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
@@ -83,6 +84,28 @@ static void mnt_free_id(struct vfsmount *mnt)
 	spin_unlock(&vfsmount_lock);
 }
 
+/*
+ * Allocate a new peer group ID
+ *
+ * mnt_group_ida is protected by namespace_sem
+ */
+static int mnt_alloc_group_id(struct vfsmount *mnt)
+{
+	if (!ida_pre_get(&mnt_group_ida, GFP_KERNEL))
+		return -ENOMEM;
+
+	return ida_get_new_above(&mnt_group_ida, 1, &mnt->mnt_group_id);
+}
+
+/*
+ * Release a peer group ID
+ */
+void mnt_release_group_id(struct vfsmount *mnt)
+{
+	ida_remove(&mnt_group_ida, mnt->mnt_group_id);
+	mnt->mnt_group_id = 0;
+}
+
 struct vfsmount *alloc_vfsmnt(const char *name)
 {
 	struct vfsmount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
@@ -533,6 +556,17 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 	struct vfsmount *mnt = alloc_vfsmnt(old->mnt_devname);
 
 	if (mnt) {
+		if (flag & (CL_SLAVE | CL_PRIVATE))
+			mnt->mnt_group_id = 0; /* not a peer of original */
+		else
+			mnt->mnt_group_id = old->mnt_group_id;
+
+		if ((flag & CL_MAKE_SHARED) && !mnt->mnt_group_id) {
+			int err = mnt_alloc_group_id(mnt);
+			if (err)
+				goto out_free;
+		}
+
 		mnt->mnt_flags = old->mnt_flags;
 		atomic_inc(&sb->s_active);
 		mnt->mnt_sb = sb;
@@ -562,6 +596,10 @@ static struct vfsmount *clone_mnt(struct vfsmount *old, struct dentry *root,
 		}
 	}
 	return mnt;
+
+ out_free:
+	free_vfsmnt(mnt);
+	return NULL;
 }
 
 static inline void __mntput(struct vfsmount *mnt)
@@ -1142,6 +1180,33 @@ void drop_collected_mounts(struct vfsmount *mnt)
 	release_mounts(&umount_list);
 }
 
+static void cleanup_group_ids(struct vfsmount *mnt, struct vfsmount *end)
+{
+	struct vfsmount *p;
+
+	for (p = mnt; p != end; p = next_mnt(p, mnt)) {
+		if (p->mnt_group_id && !IS_MNT_SHARED(p))
+			mnt_release_group_id(p);
+	}
+}
+
+static int invent_group_ids(struct vfsmount *mnt, bool recurse)
+{
+	struct vfsmount *p;
+
+	for (p = mnt; p; p = recurse ? next_mnt(p, mnt) : NULL) {
+		if (!p->mnt_group_id && !IS_MNT_SHARED(p)) {
+			int err = mnt_alloc_group_id(p);
+			if (err) {
+				cleanup_group_ids(mnt, p);
+				return err;
+			}
+		}
+	}
+
+	return 0;
+}
+
 /*
  *  @source_mnt : mount tree to be attached
  *  @nd         : place the mount tree @source_mnt is attached
@@ -1212,9 +1277,16 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
 	struct vfsmount *dest_mnt = path->mnt;
 	struct dentry *dest_dentry = path->dentry;
 	struct vfsmount *child, *p;
+	int err;
 
-	if (propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list))
-		return -EINVAL;
+	if (IS_MNT_SHARED(dest_mnt)) {
+		err = invent_group_ids(source_mnt, true);
+		if (err)
+			goto out;
+	}
+	err = propagate_mnt(dest_mnt, dest_dentry, source_mnt, &tree_list);
+	if (err)
+		goto out_cleanup_ids;
 
 	if (IS_MNT_SHARED(dest_mnt)) {
 		for (p = source_mnt; p; p = next_mnt(p, source_mnt))
@@ -1237,6 +1309,12 @@ static int attach_recursive_mnt(struct vfsmount *source_mnt,
 	}
 	spin_unlock(&vfsmount_lock);
 	return 0;
+
+ out_cleanup_ids:
+	if (IS_MNT_SHARED(dest_mnt))
+		cleanup_group_ids(source_mnt, NULL);
+ out:
+	return err;
 }
 
 static int graft_tree(struct vfsmount *mnt, struct path *path)
@@ -1277,6 +1355,7 @@ static noinline int do_change_type(struct nameidata *nd, int flag)
 	struct vfsmount *m, *mnt = nd->path.mnt;
 	int recurse = flag & MS_REC;
 	int type = flag & ~MS_REC;
+	int err = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1285,12 +1364,20 @@ static noinline int do_change_type(struct nameidata *nd, int flag)
 		return -EINVAL;
 
 	down_write(&namespace_sem);
+	if (type == MS_SHARED) {
+		err = invent_group_ids(mnt, recurse);
+		if (err)
+			goto out_unlock;
+	}
+
 	spin_lock(&vfsmount_lock);
 	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
 		change_mnt_propagation(m, type);
 	spin_unlock(&vfsmount_lock);
+
+ out_unlock:
 	up_write(&namespace_sem);
-	return 0;
+	return err;
 }
 
 /*
diff --git a/fs/pnode.c b/fs/pnode.c
index f968e35d978..d18d66491a0 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -46,7 +46,11 @@ static int do_make_slave(struct vfsmount *mnt)
 		if (peer_mnt == mnt)
 			peer_mnt = NULL;
 	}
+	if (IS_MNT_SHARED(mnt) && list_empty(&mnt->mnt_share))
+		mnt_release_group_id(mnt);
+
 	list_del_init(&mnt->mnt_share);
+	mnt->mnt_group_id = 0;
 
 	if (peer_mnt)
 		master = peer_mnt;
@@ -68,7 +72,6 @@ static int do_make_slave(struct vfsmount *mnt)
 	}
 	mnt->mnt_master = master;
 	CLEAR_MNT_SHARED(mnt);
-	INIT_LIST_HEAD(&mnt->mnt_slave_list);
 	return 0;
 }
 
diff --git a/include/linux/mount.h b/include/linux/mount.h
index f0dfb17ffcc..b4836d58f42 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -57,6 +57,7 @@ struct vfsmount {
 	struct vfsmount *mnt_master;	/* slave is on master->mnt_slave_list */
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	int mnt_id;			/* mount identifier */
+	int mnt_group_id;		/* peer group identifier */
 	/*
 	 * We put mnt_count & mnt_expiry_mark at the end of struct vfsmount
 	 * to let these frequently modified fields in a separate cache line