1 files changed, 269 insertions, 261 deletions

diff --git a/fs/dcache.c b/fs/dcache.c
index 06f65857a85..3ffef7f4e5c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -106,8 +106,7 @@ static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
 					unsigned int hash)
 {
 	hash += (unsigned long) parent / L1_CACHE_BYTES;
-	hash = hash + (hash >> d_hash_shift);
-	return dentry_hashtable + (hash & d_hash_mask);
+	return dentry_hashtable + hash_32(hash, d_hash_shift);
 }
 
 /* Statistics gathering. */
@@ -236,18 +235,49 @@ static inline int dentry_cmp(const struct dentry *dentry, const unsigned char *c
 	return dentry_string_cmp(cs, ct, tcount);
 }
 
+struct external_name {
+	union {
+		atomic_t count;
+		struct rcu_head head;
+	} u;
+	unsigned char name[];
+};
+
+static inline struct external_name *external_name(struct dentry *dentry)
+{
+	return container_of(dentry->d_name.name, struct external_name, name[0]);
+}
+
 static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
 
 	WARN_ON(!hlist_unhashed(&dentry->d_alias));
-	if (dname_external(dentry))
-		kfree(dentry->d_name.name);
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
+static void __d_free_external(struct rcu_head *head)
+{
+	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
+	WARN_ON(!hlist_unhashed(&dentry->d_alias));
+	kfree(external_name(dentry));
+	kmem_cache_free(dentry_cache, dentry); 
+}
+
+static inline int dname_external(const struct dentry *dentry)
+{
+	return dentry->d_name.name != dentry->d_iname;
+}
+
 static void dentry_free(struct dentry *dentry)
 {
+	if (unlikely(dname_external(dentry))) {
+		struct external_name *p = external_name(dentry);
+		if (likely(atomic_dec_and_test(&p->u.count))) {
+			call_rcu(&dentry->d_u.d_rcu, __d_free_external);
+			return;
+		}
+	}
 	/* if dentry was never visible to RCU, immediate free is OK */
 	if (!(dentry->d_flags & DCACHE_RCUACCESS))
 		__d_free(&dentry->d_u.d_rcu);
@@ -457,7 +487,7 @@ static void __dentry_kill(struct dentry *dentry)
 	 * inform the fs via d_prune that this dentry is about to be
 	 * unhashed and destroyed.
 	 */
-	if ((dentry->d_flags & DCACHE_OP_PRUNE) && !d_unhashed(dentry))
+	if (dentry->d_flags & DCACHE_OP_PRUNE)
 		dentry->d_op->d_prune(dentry);
 
 	if (dentry->d_flags & DCACHE_LRU_LIST) {
@@ -620,62 +650,6 @@ kill_it:
 }
 EXPORT_SYMBOL(dput);
 
-/**
- * d_invalidate - invalidate a dentry
- * @dentry: dentry to invalidate
- *
- * Try to invalidate the dentry if it turns out to be
- * possible. If there are other dentries that can be
- * reached through this one we can't delete it and we
- * return -EBUSY. On success we return 0.
- *
- * no dcache lock.
- */
- 
-int d_invalidate(struct dentry * dentry)
-{
-	/*
-	 * If it's already been dropped, return OK.
-	 */
-	spin_lock(&dentry->d_lock);
-	if (d_unhashed(dentry)) {
-		spin_unlock(&dentry->d_lock);
-		return 0;
-	}
-	/*
-	 * Check whether to do a partial shrink_dcache
-	 * to get rid of unused child entries.
-	 */
-	if (!list_empty(&dentry->d_subdirs)) {
-		spin_unlock(&dentry->d_lock);
-		shrink_dcache_parent(dentry);
-		spin_lock(&dentry->d_lock);
-	}
-
-	/*
-	 * Somebody else still using it?
-	 *
-	 * If it's a directory, we can't drop it
-	 * for fear of somebody re-populating it
-	 * with children (even though dropping it
-	 * would make it unreachable from the root,
-	 * we might still populate it if it was a
-	 * working directory or similar).
-	 * We also need to leave mountpoints alone,
-	 * directory or not.
-	 */
-	if (dentry->d_lockref.count > 1 && dentry->d_inode) {
-		if (S_ISDIR(dentry->d_inode->i_mode) || d_mountpoint(dentry)) {
-			spin_unlock(&dentry->d_lock);
-			return -EBUSY;
-		}
-	}
-
-	__d_drop(dentry);
-	spin_unlock(&dentry->d_lock);
-	return 0;
-}
-EXPORT_SYMBOL(d_invalidate);
 
 /* This must be called with d_lock held */
 static inline void __dget_dlock(struct dentry *dentry)
@@ -731,20 +705,18 @@ EXPORT_SYMBOL(dget_parent);
 /**
  * d_find_alias - grab a hashed alias of inode
  * @inode: inode in question
- * @want_discon:  flag, used by d_splice_alias, to request
- *          that only a DISCONNECTED alias be returned.
  *
  * If inode has a hashed alias, or is a directory and has any alias,
  * acquire the reference to alias and return it. Otherwise return NULL.
  * Notice that if inode is a directory there can be only one alias and
  * it can be unhashed only if it has no children, or if it is the root
- * of a filesystem.
+ * of a filesystem, or if the directory was renamed and d_revalidate
+ * was the first vfs operation to notice.
  *
  * If the inode has an IS_ROOT, DCACHE_DISCONNECTED alias, then prefer
- * any other hashed alias over that one unless @want_discon is set,
- * in which case only return an IS_ROOT, DCACHE_DISCONNECTED alias.
+ * any other hashed alias over that one.
  */
-static struct dentry *__d_find_alias(struct inode *inode, int want_discon)
+static struct dentry *__d_find_alias(struct inode *inode)
 {
 	struct dentry *alias, *discon_alias;
 
@@ -756,7 +728,7 @@ again:
 			if (IS_ROOT(alias) &&
 			    (alias->d_flags & DCACHE_DISCONNECTED)) {
 				discon_alias = alias;
-			} else if (!want_discon) {
+			} else {
 				__dget_dlock(alias);
 				spin_unlock(&alias->d_lock);
 				return alias;
@@ -768,12 +740,9 @@ again:
 		alias = discon_alias;
 		spin_lock(&alias->d_lock);
 		if (S_ISDIR(inode->i_mode) || !d_unhashed(alias)) {
-			if (IS_ROOT(alias) &&
-			    (alias->d_flags & DCACHE_DISCONNECTED)) {
-				__dget_dlock(alias);
-				spin_unlock(&alias->d_lock);
-				return alias;
-			}
+			__dget_dlock(alias);
+			spin_unlock(&alias->d_lock);
+			return alias;
 		}
 		spin_unlock(&alias->d_lock);
 		goto again;
@@ -787,7 +756,7 @@ struct dentry *d_find_alias(struct inode *inode)
 
 	if (!hlist_empty(&inode->i_dentry)) {
 		spin_lock(&inode->i_lock);
-		de = __d_find_alias(inode, 0);
+		de = __d_find_alias(inode);
 		spin_unlock(&inode->i_lock);
 	}
 	return de;
@@ -806,20 +775,13 @@ restart:
 	hlist_for_each_entry(dentry, &inode->i_dentry, d_alias) {
 		spin_lock(&dentry->d_lock);
 		if (!dentry->d_lockref.count) {
-			/*
-			 * inform the fs via d_prune that this dentry
-			 * is about to be unhashed and destroyed.
-			 */
-			if ((dentry->d_flags & DCACHE_OP_PRUNE) &&
-			    !d_unhashed(dentry))
-				dentry->d_op->d_prune(dentry);
-
-			__dget_dlock(dentry);
-			__d_drop(dentry);
-			spin_unlock(&dentry->d_lock);
-			spin_unlock(&inode->i_lock);
-			dput(dentry);
-			goto restart;
+			struct dentry *parent = lock_parent(dentry);
+			if (likely(!dentry->d_lockref.count)) {
+				__dentry_kill(dentry);
+				goto restart;
+			}
+			if (parent)
+				spin_unlock(&parent->d_lock);
 		}
 		spin_unlock(&dentry->d_lock);
 	}
@@ -1200,7 +1162,7 @@ EXPORT_SYMBOL(have_submounts);
  * reachable (e.g. NFS can unhash a directory dentry and then the complete
  * subtree can become unreachable).
  *
- * Only one of check_submounts_and_drop() and d_set_mounted() must succeed.  For
+ * Only one of d_invalidate() and d_set_mounted() must succeed.  For
  * this reason take rename_lock and d_lock on dentry and ancestors.
  */
 int d_set_mounted(struct dentry *dentry)
@@ -1209,7 +1171,7 @@ int d_set_mounted(struct dentry *dentry)
 	int ret = -ENOENT;
 	write_seqlock(&rename_lock);
 	for (p = dentry->d_parent; !IS_ROOT(p); p = p->d_parent) {
-		/* Need exclusion wrt. check_submounts_and_drop() */
+		/* Need exclusion wrt. d_invalidate() */
 		spin_lock(&p->d_lock);
 		if (unlikely(d_unhashed(p))) {
 			spin_unlock(&p->d_lock);
@@ -1353,70 +1315,84 @@ void shrink_dcache_for_umount(struct super_block *sb)
 	}
 }
 
-static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry)
+struct detach_data {
+	struct select_data select;
+	struct dentry *mountpoint;
+};
+static enum d_walk_ret detach_and_collect(void *_data, struct dentry *dentry)
 {
-	struct select_data *data = _data;
+	struct detach_data *data = _data;
 
 	if (d_mountpoint(dentry)) {
-		data->found = -EBUSY;
+		__dget_dlock(dentry);
+		data->mountpoint = dentry;
 		return D_WALK_QUIT;
 	}
 
-	return select_collect(_data, dentry);
+	return select_collect(&data->select, dentry);
 }
 
 static void check_and_drop(void *_data)
 {
-	struct select_data *data = _data;
+	struct detach_data *data = _data;
 
-	if (d_mountpoint(data->start))
-		data->found = -EBUSY;
-	if (!data->found)
-		__d_drop(data->start);
+	if (!data->mountpoint && !data->select.found)
+		__d_drop(data->select.start);
 }
 
 /**
- * check_submounts_and_drop - prune dcache, check for submounts and drop
+ * d_invalidate - detach submounts, prune dcache, and drop
+ * @dentry: dentry to invalidate (aka detach, prune and drop)
  *
- * All done as a single atomic operation relative to has_unlinked_ancestor().
- * Returns 0 if successfully unhashed @parent.  If there were submounts then
- * return -EBUSY.
+ * no dcache lock.
  *
- * @dentry: dentry to prune and drop
+ * The final d_drop is done as an atomic operation relative to
+ * rename_lock ensuring there are no races with d_set_mounted.  This
+ * ensures there are no unhashed dentries on the path to a mountpoint.
  */
-int check_submounts_and_drop(struct dentry *dentry)
+void d_invalidate(struct dentry *dentry)
 {
-	int ret = 0;
+	/*
+	 * If it's already been dropped, return OK.
+	 */
+	spin_lock(&dentry->d_lock);
+	if (d_unhashed(dentry)) {
+		spin_unlock(&dentry->d_lock);
+		return;
+	}
+	spin_unlock(&dentry->d_lock);
 
 	/* Negative dentries can be dropped without further checks */
 	if (!dentry->d_inode) {
 		d_drop(dentry);
-		goto out;
+		return;
 	}
 
 	for (;;) {
-		struct select_data data;
+		struct detach_data data;
 
-		INIT_LIST_HEAD(&data.dispose);
-		data.start = dentry;
-		data.found = 0;
+		data.mountpoint = NULL;
+		INIT_LIST_HEAD(&data.select.dispose);
+		data.select.start = dentry;
+		data.select.found = 0;
+
+		d_walk(dentry, &data, detach_and_collect, check_and_drop);
 
-		d_walk(dentry, &data, check_and_collect, check_and_drop);
-		ret = data.found;
+		if (data.select.found)
+			shrink_dentry_list(&data.select.dispose);
 
-		if (!list_empty(&data.dispose))
-			shrink_dentry_list(&data.dispose);
+		if (data.mountpoint) {
+			detach_mounts(data.mountpoint);
+			dput(data.mountpoint);
+		}
 
-		if (ret <= 0)
+		if (!data.mountpoint && !data.select.found)
 			break;
 
 		cond_resched();
 	}
-
-out:
-	return ret;
 }
-EXPORT_SYMBOL(check_submounts_and_drop);
+EXPORT_SYMBOL(d_invalidate);
 
 /**
  * __d_alloc	-	allocate a dcache entry
@@ -1445,11 +1421,14 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	 */
 	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
 	if (name->len > DNAME_INLINE_LEN-1) {
-		dname = kmalloc(name->len + 1, GFP_KERNEL);
-		if (!dname) {
+		size_t size = offsetof(struct external_name, name[1]);
+		struct external_name *p = kmalloc(size + name->len, GFP_KERNEL);
+		if (!p) {
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
 		}
+		atomic_set(&p->u.count, 1);
+		dname = p->name;
 	} else  {
 		dname = dentry->d_iname;
 	}	
@@ -1781,25 +1760,7 @@ struct dentry *d_find_any_alias(struct inode *inode)
 }
 EXPORT_SYMBOL(d_find_any_alias);
 
-/**
- * d_obtain_alias - find or allocate a dentry for a given inode
- * @inode: inode to allocate the dentry for
- *
- * Obtain a dentry for an inode resulting from NFS filehandle conversion or
- * similar open by handle operations.  The returned dentry may be anonymous,
- * or may have a full name (if the inode was already in the cache).
- *
- * When called on a directory inode, we must ensure that the inode only ever
- * has one dentry.  If a dentry is found, that is returned instead of
- * allocating a new one.
- *
- * On successful return, the reference to the inode has been transferred
- * to the dentry.  In case of an error the reference on the inode is released.
- * To make it easier to use in export operations a %NULL or IS_ERR inode may
- * be passed in and will be the error will be propagate to the return value,
- * with a %NULL @inode replaced by ERR_PTR(-ESTALE).
- */
-struct dentry *d_obtain_alias(struct inode *inode)
+static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
 {
 	static const struct qstr anonstring = QSTR_INIT("/", 1);
 	struct dentry *tmp;
@@ -1830,7 +1791,10 @@ struct dentry *d_obtain_alias(struct inode *inode)
 	}
 
 	/* attach a disconnected dentry */
-	add_flags = d_flags_for_inode(inode) | DCACHE_DISCONNECTED;
+	add_flags = d_flags_for_inode(inode);
+
+	if (disconnected)
+		add_flags |= DCACHE_DISCONNECTED;
 
 	spin_lock(&tmp->d_lock);
 	tmp->d_inode = inode;
@@ -1851,59 +1815,51 @@ struct dentry *d_obtain_alias(struct inode *inode)
 	iput(inode);
 	return res;
 }
-EXPORT_SYMBOL(d_obtain_alias);
 
 /**
- * d_splice_alias - splice a disconnected dentry into the tree if one exists
- * @inode:  the inode which may have a disconnected dentry
- * @dentry: a negative dentry which we want to point to the inode.
- *
- * If inode is a directory and has a 'disconnected' dentry (i.e. IS_ROOT and
- * DCACHE_DISCONNECTED), then d_move that in place of the given dentry
- * and return it, else simply d_add the inode to the dentry and return NULL.
+ * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode
+ * @inode: inode to allocate the dentry for
  *
- * This is needed in the lookup routine of any filesystem that is exportable
- * (via knfsd) so that we can build dcache paths to directories effectively.
+ * Obtain a dentry for an inode resulting from NFS filehandle conversion or
+ * similar open by handle operations.  The returned dentry may be anonymous,
+ * or may have a full name (if the inode was already in the cache).
  *
- * If a dentry was found and moved, then it is returned.  Otherwise NULL
- * is returned.  This matches the expected return value of ->lookup.
+ * When called on a directory inode, we must ensure that the inode only ever
+ * has one dentry.  If a dentry is found, that is returned instead of
+ * allocating a new one.
  *
- * Cluster filesystems may call this function with a negative, hashed dentry.
- * In that case, we know that the inode will be a regular file, and also this
- * will only occur during atomic_open. So we need to check for the dentry
- * being already hashed only in the final case.
+ * On successful return, the reference to the inode has been transferred
+ * to the dentry.  In case of an error the reference on the inode is released.
+ * To make it easier to use in export operations a %NULL or IS_ERR inode may
+ * be passed in and the error will be propagated to the return value,
+ * with a %NULL @inode replaced by ERR_PTR(-ESTALE).
  */
-struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
+struct dentry *d_obtain_alias(struct inode *inode)
 {
-	struct dentry *new = NULL;
-
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
+	return __d_obtain_alias(inode, 1);
+}
+EXPORT_SYMBOL(d_obtain_alias);
 
-	if (inode && S_ISDIR(inode->i_mode)) {
-		spin_lock(&inode->i_lock);
-		new = __d_find_alias(inode, 1);
-		if (new) {
-			BUG_ON(!(new->d_flags & DCACHE_DISCONNECTED));
-			spin_unlock(&inode->i_lock);
-			security_d_instantiate(new, inode);
-			d_move(new, dentry);
-			iput(inode);
-		} else {
-			/* already taking inode->i_lock, so d_add() by hand */
-			__d_instantiate(dentry, inode);
-			spin_unlock(&inode->i_lock);
-			security_d_instantiate(dentry, inode);
-			d_rehash(dentry);
-		}
-	} else {
-		d_instantiate(dentry, inode);
-		if (d_unhashed(dentry))
-			d_rehash(dentry);
-	}
-	return new;
+/**
+ * d_obtain_root - find or allocate a dentry for a given inode
+ * @inode: inode to allocate the dentry for
+ *
+ * Obtain an IS_ROOT dentry for the root of a filesystem.
+ *
+ * We must ensure that directory inodes only ever have one dentry.  If a
+ * dentry is found, that is returned instead of allocating a new one.
+ *
+ * On successful return, the reference to the inode has been transferred
+ * to the dentry.  In case of an error the reference on the inode is
+ * released.  A %NULL or IS_ERR inode may be passed in and will be the
+ * error will be propagate to the return value, with a %NULL @inode
+ * replaced by ERR_PTR(-ESTALE).
+ */
+struct dentry *d_obtain_root(struct inode *inode)
+{
+	return __d_obtain_alias(inode, 0);
 }
-EXPORT_SYMBOL(d_splice_alias);
+EXPORT_SYMBOL(d_obtain_root);
 
 /**
  * d_add_ci - lookup or allocate new dentry with case-exact name
@@ -2142,10 +2098,10 @@ struct dentry *d_lookup(const struct dentry *parent, const struct qstr *name)
 	struct dentry *dentry;
 	unsigned seq;
 
-        do {
-                seq = read_seqbegin(&rename_lock);
-                dentry = __d_lookup(parent, name);
-                if (dentry)
+	do {
+		seq = read_seqbegin(&rename_lock);
+		dentry = __d_lookup(parent, name);
+		if (dentry)
 			break;
 	} while (read_seqretry(&rename_lock, seq));
 	return dentry;
@@ -2402,10 +2358,10 @@ void dentry_update_name_case(struct dentry *dentry, struct qstr *name)
 }
 EXPORT_SYMBOL(dentry_update_name_case);
 
-static void switch_names(struct dentry *dentry, struct dentry *target)
+static void swap_names(struct dentry *dentry, struct dentry *target)
 {
-	if (dname_external(target)) {
-		if (dname_external(dentry)) {
+	if (unlikely(dname_external(target))) {
+		if (unlikely(dname_external(dentry))) {
 			/*
 			 * Both external: swap the pointers
 			 */
@@ -2421,7 +2377,7 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
 			target->d_name.name = target->d_iname;
 		}
 	} else {
-		if (dname_external(dentry)) {
+		if (unlikely(dname_external(dentry))) {
 			/*
 			 * dentry:external, target:internal.  Give dentry's
 			 * storage to target and make dentry internal
@@ -2442,7 +2398,25 @@ static void switch_names(struct dentry *dentry, struct dentry *target)
 			}
 		}
 	}
-	swap(dentry->d_name.len, target->d_name.len);
+	swap(dentry->d_name.hash_len, target->d_name.hash_len);
+}
+
+static void copy_name(struct dentry *dentry, struct dentry *target)
+{
+	struct external_name *old_name = NULL;
+	if (unlikely(dname_external(dentry)))
+		old_name = external_name(dentry);
+	if (unlikely(dname_external(target))) {
+		atomic_inc(&external_name(target)->u.count);
+		dentry->d_name = target->d_name;
+	} else {
+		memcpy(dentry->d_iname, target->d_name.name,
+				target->d_name.len + 1);
+		dentry->d_name.name = dentry->d_iname;
+		dentry->d_name.hash_len = target->d_name.hash_len;
+	}
+	if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
+		kfree_rcu(old_name, u.head);
 }
 
 static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
@@ -2472,25 +2446,29 @@ static void dentry_lock_for_move(struct dentry *dentry, struct dentry *target)
 	}
 }
 
-static void dentry_unlock_parents_for_move(struct dentry *dentry,
-					struct dentry *target)
+static void dentry_unlock_for_move(struct dentry *dentry, struct dentry *target)
 {
 	if (target->d_parent != dentry->d_parent)
 		spin_unlock(&dentry->d_parent->d_lock);
 	if (target->d_parent != target)
 		spin_unlock(&target->d_parent->d_lock);
+	spin_unlock(&target->d_lock);
+	spin_unlock(&dentry->d_lock);
 }
 
 /*
  * When switching names, the actual string doesn't strictly have to
  * be preserved in the target - because we're dropping the target
  * anyway. As such, we can just do a simple memcpy() to copy over
- * the new name before we switch.
- *
- * Note that we have to be a lot more careful about getting the hash
- * switched - we have to switch the hash value properly even if it
- * then no longer matches the actual (corrupted) string of the target.
- * The hash value has to match the hash queue that the dentry is on..
+ * the new name before we switch, unless we are going to rehash
+ * it.  Note that if we *do* unhash the target, we are not allowed
+ * to rehash it without giving it a new name/hash key - whether
+ * we swap or overwrite the names here, resulting name won't match
+ * the reality in filesystem; it's only there for d_path() purposes.
+ * Note that all of this is happening under rename_lock, so the
+ * any hash lookup seeing it in the middle of manipulations will
+ * be discarded anyway.  So we do not care what happens to the hash
+ * key in that case.
  */
 /*
  * __d_move - move a dentry
@@ -2536,36 +2514,33 @@ static void __d_move(struct dentry *dentry, struct dentry *target,
 			   d_hash(dentry->d_parent, dentry->d_name.hash));
 	}
 
-	list_del(&dentry->d_u.d_child);
-	list_del(&target->d_u.d_child);
-
 	/* Switch the names.. */
-	switch_names(dentry, target);
-	swap(dentry->d_name.hash, target->d_name.hash);
+	if (exchange)
+		swap_names(dentry, target);
+	else
+		copy_name(dentry, target);
 
-	/* ... and switch the parents */
+	/* ... and switch them in the tree */
 	if (IS_ROOT(dentry)) {
+		/* splicing a tree */
 		dentry->d_parent = target->d_parent;
 		target->d_parent = target;
-		INIT_LIST_HEAD(&target->d_u.d_child);
+		list_del_init(&target->d_u.d_child);
+		list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
 	} else {
+		/* swapping two dentries */
 		swap(dentry->d_parent, target->d_parent);
-
-		/* And add them back to the (new) parent lists */
-		list_add(&target->d_u.d_child, &target->d_parent->d_subdirs);
+		list_move(&target->d_u.d_child, &target->d_parent->d_subdirs);
+		list_move(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
+		if (exchange)
+			fsnotify_d_move(target);
+		fsnotify_d_move(dentry);
 	}
 
-	list_add(&dentry->d_u.d_child, &dentry->d_parent->d_subdirs);
-
 	write_seqcount_end(&target->d_seq);
 	write_seqcount_end(&dentry->d_seq);
 
-	dentry_unlock_parents_for_move(dentry, target);
-	if (exchange)
-		fsnotify_d_move(target);
-	spin_unlock(&target->d_lock);
-	fsnotify_d_move(dentry);
-	spin_unlock(&dentry->d_lock);
+	dentry_unlock_for_move(dentry, target);
 }
 
 /*
@@ -2650,10 +2625,8 @@ static struct dentry *__d_unalias(struct inode *inode,
 		goto out_err;
 	m2 = &alias->d_parent->d_inode->i_mutex;
 out_unalias:
-	if (likely(!d_mountpoint(alias))) {
-		__d_move(alias, dentry, false);
-		ret = alias;
-	}
+	__d_move(alias, dentry, false);
+	ret = alias;
 out_err:
 	spin_unlock(&inode->i_lock);
 	if (m2)
@@ -2663,38 +2636,73 @@ out_err:
 	return ret;
 }
 
-/*
- * Prepare an anonymous dentry for life in the superblock's dentry tree as a
- * named dentry in place of the dentry to be replaced.
- * returns with anon->d_lock held!
+/**
+ * d_splice_alias - splice a disconnected dentry into the tree if one exists
+ * @inode:  the inode which may have a disconnected dentry
+ * @dentry: a negative dentry which we want to point to the inode.
+ *
+ * If inode is a directory and has an IS_ROOT alias, then d_move that in
+ * place of the given dentry and return it, else simply d_add the inode
+ * to the dentry and return NULL.
+ *
+ * If a non-IS_ROOT directory is found, the filesystem is corrupt, and
+ * we should error out: directories can't have multiple aliases.
+ *
+ * This is needed in the lookup routine of any filesystem that is exportable
+ * (via knfsd) so that we can build dcache paths to directories effectively.
+ *
+ * If a dentry was found and moved, then it is returned.  Otherwise NULL
+ * is returned.  This matches the expected return value of ->lookup.
+ *
+ * Cluster filesystems may call this function with a negative, hashed dentry.
+ * In that case, we know that the inode will be a regular file, and also this
+ * will only occur during atomic_open. So we need to check for the dentry
+ * being already hashed only in the final case.
  */
-static void __d_materialise_dentry(struct dentry *dentry, struct dentry *anon)
+struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 {
-	struct dentry *dparent;
-
-	dentry_lock_for_move(anon, dentry);
-
-	write_seqcount_begin(&dentry->d_seq);
-	write_seqcount_begin_nested(&anon->d_seq, DENTRY_D_LOCK_NESTED);
-
-	dparent = dentry->d_parent;
-
-	switch_names(dentry, anon);
-	swap(dentry->d_name.hash, anon->d_name.hash);
-
-	dentry->d_parent = dentry;
-	list_del_init(&dentry->d_u.d_child);
-	anon->d_parent = dparent;
-	list_move(&anon->d_u.d_child, &dparent->d_subdirs);
-
-	write_seqcount_end(&dentry->d_seq);
-	write_seqcount_end(&anon->d_seq);
+	struct dentry *new = NULL;
 
-	dentry_unlock_parents_for_move(anon, dentry);
-	spin_unlock(&dentry->d_lock);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
 
-	/* anon->d_lock still locked, returns locked */
+	if (inode && S_ISDIR(inode->i_mode)) {
+		spin_lock(&inode->i_lock);
+		new = __d_find_any_alias(inode);
+		if (new) {
+			if (!IS_ROOT(new)) {
+				spin_unlock(&inode->i_lock);
+				dput(new);
+				iput(inode);
+				return ERR_PTR(-EIO);
+			}
+			if (d_ancestor(new, dentry)) {
+				spin_unlock(&inode->i_lock);
+				dput(new);
+				iput(inode);
+				return ERR_PTR(-EIO);
+			}
+			write_seqlock(&rename_lock);
+			__d_move(new, dentry, false);
+			write_sequnlock(&rename_lock);
+			spin_unlock(&inode->i_lock);
+			security_d_instantiate(new, inode);
+			iput(inode);
+		} else {
+			/* already taking inode->i_lock, so d_add() by hand */
+			__d_instantiate(dentry, inode);
+			spin_unlock(&inode->i_lock);
+			security_d_instantiate(dentry, inode);
+			d_rehash(dentry);
+		}
+	} else {
+		d_instantiate(dentry, inode);
+		if (d_unhashed(dentry))
+			d_rehash(dentry);
+	}
+	return new;
 }
+EXPORT_SYMBOL(d_splice_alias);
 
 /**
  * d_materialise_unique - introduce an inode into the tree
@@ -2724,7 +2732,7 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 		struct dentry *alias;
 
 		/* Does an aliased dentry already exist? */
-		alias = __d_find_alias(inode, 0);
+		alias = __d_find_alias(inode);
 		if (alias) {
 			actual = alias;
 			write_seqlock(&rename_lock);
@@ -2736,9 +2744,8 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 			} else if (IS_ROOT(alias)) {
 				/* Is this an anonymous mountpoint that we
 				 * could splice into our tree? */
-				__d_materialise_dentry(dentry, alias);
+				__d_move(alias, dentry, false);
 				write_sequnlock(&rename_lock);
-				__d_drop(alias);
 				goto found;
 			} else {
 				/* Nope, but we must(!) avoid directory
@@ -2764,13 +2771,9 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 	actual = __d_instantiate_unique(dentry, inode);
 	if (!actual)
 		actual = dentry;
-	else
-		BUG_ON(!d_unhashed(actual));
 
-	spin_lock(&actual->d_lock);
+	d_rehash(actual);
 found:
-	_d_rehash(actual);
-	spin_unlock(&actual->d_lock);
 	spin_unlock(&inode->i_lock);
 out_nolock:
 	if (actual == dentry) {
@@ -2807,6 +2810,9 @@ static int prepend(char **buffer, int *buflen, const char *str, int namelen)
  * the beginning of the name. The sequence number check at the caller will
  * retry it again when a d_move() does happen. So any garbage in the buffer
  * due to mismatched pointer and length will be discarded.
+ *
+ * Data dependency barrier is needed to make sure that we see that terminating
+ * NUL.  Alpha strikes again, film at 11...
  */
 static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 {
@@ -2814,6 +2820,8 @@ static int prepend_name(char **buffer, int *buflen, struct qstr *name)
 	u32 dlen = ACCESS_ONCE(name->len);
 	char *p;
 
+	smp_read_barrier_depends();
+
 	*buflen -= dlen + 1;
 	if (*buflen < 0)
 		return -ENAMETOOLONG;