Merge branch 'work.dcache2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull dcache and mountpoint updates from Al Viro:
 "Saner handling of refcounts to mountpoints.

  Transfer the counting reference from struct mount ->mnt_mountpoint
  over to struct mountpoint ->m_dentry. That allows us to get rid of the
  convoluted games with ordering of mount shutdowns.

  The cost is in teaching shrink_dcache_{parent,for_umount} to cope with
  mixed-filesystem shrink lists, which we'll also need for the Slab
  Movable Objects patchset"

* 'work.dcache2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  switch the remnants of releasing the mountpoint away from fs_pin
  get rid of detach_mnt()
  make struct mountpoint bear the dentry reference to mountpoint, not struct mount
  Teach shrink_dcache_parent() to cope with mixed-filesystem shrink lists
  fs/namespace.c: shift put_mountpoint() to callers of unhash_mnt()
  __detach_mounts(): lookup_mountpoint() can't return ERR_PTR() anymore
  nfs: dget_parent() never returns NULL
  ceph: don't open-code the check for dead lockref

1 files changed, 77 insertions, 82 deletions

diff --git a/fs/namespace.c b/fs/namespace.c
index f0d664adb9ba..6464ea4acba9 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -70,6 +70,8 @@ static struct hlist_head *mount_hashtable __read_mostly;
 static struct hlist_head *mountpoint_hashtable __read_mostly;
 static struct kmem_cache *mnt_cache __read_mostly;
 static DECLARE_RWSEM(namespace_sem);
+static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
+static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */
 
 /* /sys/fs */
 struct kobject *fs_kobj;
@@ -170,14 +172,6 @@ unsigned int mnt_get_count(struct mount *mnt)
 #endif
 }
 
-static void drop_mountpoint(struct fs_pin *p)
-{
-	struct mount *m = container_of(p, struct mount, mnt_umount);
-	dput(m->mnt_ex_mountpoint);
-	pin_remove(p);
-	mntput(&m->mnt);
-}
-
 static struct mount *alloc_vfsmnt(const char *name)
 {
 	struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL);
@@ -215,7 +209,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
 		INIT_LIST_HEAD(&mnt->mnt_umounting);
-		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
+		INIT_HLIST_HEAD(&mnt->mnt_stuck_children);
 	}
 	return mnt;
 
@@ -740,7 +734,7 @@ mountpoint:
 
 	/* Add the new mountpoint to the hash table */
 	read_seqlock_excl(&mount_lock);
-	new->m_dentry = dentry;
+	new->m_dentry = dget(dentry);
 	new->m_count = 1;
 	hlist_add_head(&new->m_hash, mp_hash(dentry));
 	INIT_HLIST_HEAD(&new->m_list);
@@ -753,7 +747,11 @@ done:
 	return mp;
 }
 
-static void put_mountpoint(struct mountpoint *mp)
+/*
+ * vfsmount lock must be held.  Additionally, the caller is responsible
+ * for serializing calls for given disposal list.
+ */
+static void __put_mountpoint(struct mountpoint *mp, struct list_head *list)
 {
 	if (!--mp->m_count) {
 		struct dentry *dentry = mp->m_dentry;
@@ -761,11 +759,18 @@ static void put_mountpoint(struct mountpoint *mp)
 		spin_lock(&dentry->d_lock);
 		dentry->d_flags &= ~DCACHE_MOUNTED;
 		spin_unlock(&dentry->d_lock);
+		dput_to_list(dentry, list);
 		hlist_del(&mp->m_hash);
 		kfree(mp);
 	}
 }
 
+/* called with namespace_lock and vfsmount lock */
+static void put_mountpoint(struct mountpoint *mp)
+{
+	__put_mountpoint(mp, &ex_mountpoints);
+}
+
 static inline int check_mnt(struct mount *mnt)
 {
 	return mnt->mnt_ns == current->nsproxy->mnt_ns;
@@ -796,25 +801,17 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns)
 /*
  * vfsmount lock must be held for write
  */
-static void unhash_mnt(struct mount *mnt)
+static struct mountpoint *unhash_mnt(struct mount *mnt)
 {
+	struct mountpoint *mp;
 	mnt->mnt_parent = mnt;
 	mnt->mnt_mountpoint = mnt->mnt.mnt_root;
 	list_del_init(&mnt->mnt_child);
 	hlist_del_init_rcu(&mnt->mnt_hash);
 	hlist_del_init(&mnt->mnt_mp_list);
-	put_mountpoint(mnt->mnt_mp);
+	mp = mnt->mnt_mp;
 	mnt->mnt_mp = NULL;
-}
-
-/*
- * vfsmount lock must be held for write
- */
-static void detach_mnt(struct mount *mnt, struct path *old_path)
-{
-	old_path->dentry = mnt->mnt_mountpoint;
-	old_path->mnt = &mnt->mnt_parent->mnt;
-	unhash_mnt(mnt);
+	return mp;
 }
 
 /*
@@ -822,9 +819,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path)
  */
 static void umount_mnt(struct mount *mnt)
 {
-	/* old mountpoint will be dropped when we can do that */
-	mnt->mnt_ex_mountpoint = mnt->mnt_mountpoint;
-	unhash_mnt(mnt);
+	put_mountpoint(unhash_mnt(mnt));
 }
 
 /*
@@ -836,7 +831,7 @@ void mnt_set_mountpoint(struct mount *mnt,
 {
 	mp->m_count++;
 	mnt_add_count(mnt, 1);	/* essentially, that's mntget */
-	child_mnt->mnt_mountpoint = dget(mp->m_dentry);
+	child_mnt->mnt_mountpoint = mp->m_dentry;
 	child_mnt->mnt_parent = mnt;
 	child_mnt->mnt_mp = mp;
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
@@ -863,7 +858,6 @@ static void attach_mnt(struct mount *mnt,
 void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
 	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);
@@ -873,22 +867,6 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m
 	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);
 }
 
@@ -1103,19 +1081,22 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 
 static void cleanup_mnt(struct mount *mnt)
 {
+	struct hlist_node *p;
+	struct mount *m;
 	/*
-	 * This probably indicates that somebody messed
-	 * up a mnt_want/drop_write() pair.  If this
-	 * happens, the filesystem was probably unable
-	 * to make r/w->r/o transitions.
-	 */
-	/*
+	 * The warning here probably indicates that somebody messed
+	 * up a mnt_want/drop_write() pair.  If this happens, the
+	 * filesystem was probably unable to make r/w->r/o transitions.
 	 * The locking used to deal with mnt_count decrement provides barriers,
 	 * so mnt_get_writers() below is safe.
 	 */
 	WARN_ON(mnt_get_writers(mnt));
 	if (unlikely(mnt->mnt_pins.first))
 		mnt_pin_kill(mnt);
+	hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) {
+		hlist_del(&m->mnt_umount);
+		mntput(&m->mnt);
+	}
 	fsnotify_vfsmount_delete(&mnt->mnt);
 	dput(mnt->mnt.mnt_root);
 	deactivate_super(mnt->mnt.mnt_sb);
@@ -1141,6 +1122,8 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput);
 
 static void mntput_no_expire(struct mount *mnt)
 {
+	LIST_HEAD(list);
+
 	rcu_read_lock();
 	if (likely(READ_ONCE(mnt->mnt_ns))) {
 		/*
@@ -1181,10 +1164,12 @@ static void mntput_no_expire(struct mount *mnt)
 	if (unlikely(!list_empty(&mnt->mnt_mounts))) {
 		struct mount *p, *tmp;
 		list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts,  mnt_child) {
-			umount_mnt(p);
+			__put_mountpoint(unhash_mnt(p), &list);
+			hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children);
 		}
 	}
 	unlock_mount_hash();
+	shrink_dentry_list(&list);
 
 	if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) {
 		struct task_struct *task = current;
@@ -1370,22 +1355,29 @@ int may_umount(struct vfsmount *mnt)
 
 EXPORT_SYMBOL(may_umount);
 
-static HLIST_HEAD(unmounted);	/* protected by namespace_sem */
-
 static void namespace_unlock(void)
 {
 	struct hlist_head head;
+	struct hlist_node *p;
+	struct mount *m;
+	LIST_HEAD(list);
 
 	hlist_move_list(&unmounted, &head);
+	list_splice_init(&ex_mountpoints, &list);
 
 	up_write(&namespace_sem);
 
+	shrink_dentry_list(&list);
+
 	if (likely(hlist_empty(&head)))
 		return;
 
 	synchronize_rcu_expedited();
 
-	group_pin_kill(&head);
+	hlist_for_each_entry_safe(m, p, &head, mnt_umount) {
+		hlist_del(&m->mnt_umount);
+		mntput(&m->mnt);
+	}
 }
 
 static inline void namespace_lock(void)
@@ -1472,8 +1464,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 
 		disconnect = disconnect_mount(p, how);
 
-		pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt,
-				 disconnect ? &unmounted : NULL);
 		if (mnt_has_parent(p)) {
 			mnt_add_count(p->mnt_parent, -1);
 			if (!disconnect) {
@@ -1481,6 +1471,7 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
 				list_add_tail(&p->mnt_child, &p->mnt_parent->mnt_mounts);
 			} else {
 				umount_mnt(p);
+				hlist_add_head(&p->mnt_umount, &unmounted);
 			}
 		}
 		change_mnt_propagation(p, MS_PRIVATE);
@@ -1626,15 +1617,15 @@ void __detach_mounts(struct dentry *dentry)
 	namespace_lock();
 	lock_mount_hash();
 	mp = lookup_mountpoint(dentry);
-	if (IS_ERR_OR_NULL(mp))
+	if (!mp)
 		goto out_unlock;
 
 	event++;
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
-			hlist_add_head(&mnt->mnt_umount.s_list, &unmounted);
 			umount_mnt(mnt);
+			hlist_add_head(&mnt->mnt_umount, &unmounted);
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
@@ -2046,7 +2037,7 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt)
 static int attach_recursive_mnt(struct mount *source_mnt,
 			struct mount *dest_mnt,
 			struct mountpoint *dest_mp,
-			struct path *parent_path)
+			bool moving)
 {
 	struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns;
 	HLIST_HEAD(tree_list);
@@ -2064,7 +2055,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		return PTR_ERR(smp);
 
 	/* Is there space to add these mounts to the mount namespace? */
-	if (!parent_path) {
+	if (!moving) {
 		err = count_mounts(ns, source_mnt);
 		if (err)
 			goto out;
@@ -2083,8 +2074,8 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	} else {
 		lock_mount_hash();
 	}
-	if (parent_path) {
-		detach_mnt(source_mnt, parent_path);
+	if (moving) {
+		unhash_mnt(source_mnt);
 		attach_mnt(source_mnt, dest_mnt, dest_mp);
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
@@ -2182,7 +2173,7 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp)
 	      d_is_dir(mnt->mnt.mnt_root))
 		return -ENOTDIR;
 
-	return attach_recursive_mnt(mnt, p, mp, NULL);
+	return attach_recursive_mnt(mnt, p, mp, false);
 }
 
 /*
@@ -2575,11 +2566,11 @@ out:
 
 static int do_move_mount(struct path *old_path, struct path *new_path)
 {
-	struct path parent_path = {.mnt = NULL, .dentry = NULL};
 	struct mnt_namespace *ns;
 	struct mount *p;
 	struct mount *old;
-	struct mountpoint *mp;
+	struct mount *parent;
+	struct mountpoint *mp, *old_mp;
 	int err;
 	bool attached;
 
@@ -2589,7 +2580,9 @@ static int do_move_mount(struct path *old_path, struct path *new_path)
 
 	old = real_mount(old_path->mnt);
 	p = real_mount(new_path->mnt);
+	parent = old->mnt_parent;
 	attached = mnt_has_parent(old);
+	old_mp = old->mnt_mp;
 	ns = old->mnt_ns;
 
 	err = -EINVAL;
@@ -2617,7 +2610,7 @@ static int do_move_mount(struct path *old_path, struct path *new_path)
 	/*
 	 * Don't move a mount residing in a shared parent.
 	 */
-	if (attached && IS_MNT_SHARED(old->mnt_parent))
+	if (attached && IS_MNT_SHARED(parent))
 		goto out;
 	/*
 	 * Don't move a mount tree containing unbindable mounts to a destination
@@ -2633,18 +2626,21 @@ static int do_move_mount(struct path *old_path, struct path *new_path)
 			goto out;
 
 	err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp,
-				   attached ? &parent_path : NULL);
+				   attached);
 	if (err)
 		goto out;
 
 	/* if the mount is moved, it should no longer be expire
 	 * automatically */
 	list_del_init(&old->mnt_expire);
+	if (attached)
+		put_mountpoint(old_mp);
 out:
 	unlock_mount(mp);
 	if (!err) {
-		path_put(&parent_path);
-		if (!attached)
+		if (attached)
+			mntput_no_expire(parent);
+		else
 			free_mnt_ns(ns);
 	}
 	return err;
@@ -3589,8 +3585,8 @@ EXPORT_SYMBOL(path_is_under);
 SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 		const char __user *, put_old)
 {
-	struct path new, old, parent_path, root_parent, root;
-	struct mount *new_mnt, *root_mnt, *old_mnt;
+	struct path new, old, root;
+	struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent;
 	struct mountpoint *old_mp, *root_mp;
 	int error;
 
@@ -3619,9 +3615,11 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	new_mnt = real_mount(new.mnt);
 	root_mnt = real_mount(root.mnt);
 	old_mnt = real_mount(old.mnt);
+	ex_parent = new_mnt->mnt_parent;
+	root_parent = root_mnt->mnt_parent;
 	if (IS_MNT_SHARED(old_mnt) ||
-		IS_MNT_SHARED(new_mnt->mnt_parent) ||
-		IS_MNT_SHARED(root_mnt->mnt_parent))
+		IS_MNT_SHARED(ex_parent) ||
+		IS_MNT_SHARED(root_parent))
 		goto out4;
 	if (!check_mnt(root_mnt) || !check_mnt(new_mnt))
 		goto out4;
@@ -3638,7 +3636,6 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 		goto out4; /* not a mountpoint */
 	if (!mnt_has_parent(root_mnt))
 		goto out4; /* not attached */
-	root_mp = root_mnt->mnt_mp;
 	if (new.mnt->mnt_root != new.dentry)
 		goto out4; /* not a mountpoint */
 	if (!mnt_has_parent(new_mnt))
@@ -3649,10 +3646,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* make certain new is below the root */
 	if (!is_path_reachable(new_mnt, new.dentry, &root))
 		goto out4;
-	root_mp->m_count++; /* pin it so it won't go away */
 	lock_mount_hash();
-	detach_mnt(new_mnt, &parent_path);
-	detach_mnt(root_mnt, &root_parent);
+	umount_mnt(new_mnt);
+	root_mp = unhash_mnt(root_mnt);  /* we'll need its mountpoint */
 	if (root_mnt->mnt.mnt_flags & MNT_LOCKED) {
 		new_mnt->mnt.mnt_flags |= MNT_LOCKED;
 		root_mnt->mnt.mnt_flags &= ~MNT_LOCKED;
@@ -3660,7 +3656,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	/* mount old root on put_old */
 	attach_mnt(root_mnt, old_mnt, old_mp);
 	/* mount new_root on / */
-	attach_mnt(new_mnt, real_mount(root_parent.mnt), root_mp);
+	attach_mnt(new_mnt, root_parent, root_mp);
+	mnt_add_count(root_parent, -1);
 	touch_mnt_namespace(current->nsproxy->mnt_ns);
 	/* A moved mount should not expire automatically */
 	list_del_init(&new_mnt->mnt_expire);
@@ -3670,10 +3667,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root,
 	error = 0;
 out4:
 	unlock_mount(old_mp);
-	if (!error) {
-		path_put(&root_parent);
-		path_put(&parent_path);
-	}
+	if (!error)
+		mntput_no_expire(ex_parent);
 out3:
 	path_put(&root);
 out2: