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

Author: torvalds

fs/ceph/dir.c

@@ -1267,7 +1267,7 @@ __dentry_leases_walk(struct ceph_mds_client *mdsc,
 		if (!spin_trylock(&dentry->d_lock))
 			continue;
 
-		if (dentry->d_lockref.count < 0) {
+		if (__lockref_is_dead(&dentry->d_lockref)) {
 			list_del_init(&di->lease_list);
 			goto next;
 		}

fs/dcache.c

@@ -861,6 +861,32 @@ void dput(struct dentry *dentry)
 }
 EXPORT_SYMBOL(dput);
 
+static void __dput_to_list(struct dentry *dentry, struct list_head *list)
+__must_hold(&dentry->d_lock)
+{
+	if (dentry->d_flags & DCACHE_SHRINK_LIST) {
+		/* let the owner of the list it's on deal with it */
+		--dentry->d_lockref.count;
+	} else {
+		if (dentry->d_flags & DCACHE_LRU_LIST)
+			d_lru_del(dentry);
+		if (!--dentry->d_lockref.count)
+			d_shrink_add(dentry, list);
+	}
+}
+
+void dput_to_list(struct dentry *dentry, struct list_head *list)
+{
+	rcu_read_lock();
+	if (likely(fast_dput(dentry))) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+	if (!retain_dentry(dentry))
+		__dput_to_list(dentry, list);
+	spin_unlock(&dentry->d_lock);
+}
 
 /* This must be called with d_lock held */
 static inline void __dget_dlock(struct dentry *dentry)
@@ -1067,7 +1093,7 @@ static bool shrink_lock_dentry(struct dentry *dentry)
 	return false;
 }
 
-static void shrink_dentry_list(struct list_head *list)
+void shrink_dentry_list(struct list_head *list)
 {
 	while (!list_empty(list)) {
 		struct dentry *dentry, *parent;
@@ -1089,18 +1115,9 @@ static void shrink_dentry_list(struct list_head *list)
 		rcu_read_unlock();
 		d_shrink_del(dentry);
 		parent = dentry->d_parent;
+		if (parent != dentry)
+			__dput_to_list(parent, list);
 		__dentry_kill(dentry);
-		if (parent == dentry)
-			continue;
-		/*
-		 * We need to prune ancestors too. This is necessary to prevent
-		 * quadratic behavior of shrink_dcache_parent(), but is also
-		 * expected to be beneficial in reducing dentry cache
-		 * fragmentation.
-		 */
-		dentry = parent;
-		while (dentry && !lockref_put_or_lock(&dentry->d_lockref))
-			dentry = dentry_kill(dentry);
 	}
 }
 
@@ -1445,8 +1462,11 @@ int d_set_mounted(struct dentry *dentry)
 
 struct select_data {
 	struct dentry *start;
+	union {
+		long found;
+		struct dentry *victim;
+	};
 	struct list_head dispose;
-	int found;
 };
 
 static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
@@ -1478,6 +1498,37 @@ static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
 	return ret;
 }
 
+static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry)
+{
+	struct select_data *data = _data;
+	enum d_walk_ret ret = D_WALK_CONTINUE;
+
+	if (data->start == dentry)
+		goto out;
+
+	if (dentry->d_flags & DCACHE_SHRINK_LIST) {
+		if (!dentry->d_lockref.count) {
+			rcu_read_lock();
+			data->victim = dentry;
+			return D_WALK_QUIT;
+		}
+	} else {
+		if (dentry->d_flags & DCACHE_LRU_LIST)
+			d_lru_del(dentry);
+		if (!dentry->d_lockref.count)
+			d_shrink_add(dentry, &data->dispose);
+	}
+	/*
+	 * We can return to the caller if we have found some (this
+	 * ensures forward progress). We'll be coming back to find
+	 * the rest.
+	 */
+	if (!list_empty(&data->dispose))
+		ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY;
+out:
+	return ret;
+}
+
 /**
  * shrink_dcache_parent - prune dcache
  * @parent: parent of entries to prune
@@ -1487,12 +1538,9 @@ static enum d_walk_ret select_collect(void *_data, struct dentry *dentry)
 void shrink_dcache_parent(struct dentry *parent)
 {
 	for (;;) {
-		struct select_data data;
+		struct select_data data = {.start = parent};
 
 		INIT_LIST_HEAD(&data.dispose);
-		data.start = parent;
-		data.found = 0;
-
 		d_walk(parent, &data, select_collect);
 
 		if (!list_empty(&data.dispose)) {
@@ -1503,6 +1551,24 @@ void shrink_dcache_parent(struct dentry *parent)
 		cond_resched();
 		if (!data.found)
 			break;
+		data.victim = NULL;
+		d_walk(parent, &data, select_collect2);
+		if (data.victim) {
+			struct dentry *parent;
+			spin_lock(&data.victim->d_lock);
+			if (!shrink_lock_dentry(data.victim)) {
+				spin_unlock(&data.victim->d_lock);
+				rcu_read_unlock();
+			} else {
+				rcu_read_unlock();
+				parent = data.victim->d_parent;
+				if (parent != data.victim)
+					__dput_to_list(parent, &data.dispose);
+				__dentry_kill(data.victim);
+			}
+		}
+		if (!list_empty(&data.dispose))
+			shrink_dentry_list(&data.dispose);
 	}
 }
 EXPORT_SYMBOL(shrink_dcache_parent);

fs/fs_pin.c

@@ -19,20 +19,14 @@ void pin_remove(struct fs_pin *pin)
 	spin_unlock_irq(&pin->wait.lock);
 }
 
-void pin_insert_group(struct fs_pin *pin, struct vfsmount *m, struct hlist_head *p)
+void pin_insert(struct fs_pin *pin, struct vfsmount *m)
 {
 	spin_lock(&pin_lock);
-	if (p)
-		hlist_add_head(&pin->s_list, p);
+	hlist_add_head(&pin->s_list, &m->mnt_sb->s_pins);
 	hlist_add_head(&pin->m_list, &real_mount(m)->mnt_pins);
 	spin_unlock(&pin_lock);
 }
 
-void pin_insert(struct fs_pin *pin, struct vfsmount *m)
-{
-	pin_insert_group(pin, m, &m->mnt_sb->s_pins);
-}
-
 void pin_kill(struct fs_pin *p)
 {
 	wait_queue_entry_t wait;

fs/internal.h

@@ -157,6 +157,8 @@ extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc);
 extern struct dentry *d_alloc_cursor(struct dentry *);
 extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *);
 extern char *simple_dname(struct dentry *, char *, int);
+extern void dput_to_list(struct dentry *, struct list_head *);
+extern void shrink_dentry_list(struct list_head *);
 
 /*
  * read_write.c

fs/mount.h

@@ -58,7 +58,10 @@ struct mount {
 	struct mount *mnt_master;	/* slave is on master->mnt_slave_list */
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
-	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
+	union {
+		struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
+		struct hlist_node mnt_umount;
+	};
 	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
@@ -68,8 +71,7 @@ struct mount {
 	int mnt_group_id;		/* peer group identifier */
 	int mnt_expiry_mark;		/* true if marked for expiry */
 	struct hlist_head mnt_pins;
-	struct fs_pin mnt_umount;
-	struct dentry *mnt_ex_mountpoint;
+	struct hlist_head mnt_stuck_children;
 } __randomize_layout;
 
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */