15 files changed, 1905 insertions, 409 deletions

diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index e6a5f4912b6d..6ea1e64d1464 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -190,6 +190,20 @@ Mount options:
     Redirects are not created and not followed (equivalent to "redirect_dir=off"
     if "redirect_always_follow" feature is not enabled).
 
+When the NFS export feature is enabled, every copied up directory is
+indexed by the file handle of the lower inode and a file handle of the
+upper directory is stored in a "trusted.overlay.upper" extended attribute
+on the index entry.  On lookup of a merged directory, if the upper
+directory does not match the file handle stores in the index, that is an
+indication that multiple upper directories may be redirected to the same
+lower directory.  In that case, lookup returns an error and warns about
+a possible inconsistency.
+
+Because lower layer redirects cannot be verified with the index, enabling
+NFS export support on an overlay filesystem with no upper layer requires
+turning off redirect follow (e.g. "redirect_dir=nofollow").
+
+
 Non-directories
 ---------------
 
@@ -281,9 +295,9 @@ filesystem, so both st_dev and st_ino of the file may change.
 
 Any open files referring to this inode will access the old data.
 
-If a file with multiple hard links is copied up, then this will
-"break" the link.  Changes will not be propagated to other names
-referring to the same inode.
+Unless "inode index" feature is enabled, if a file with multiple hard
+links is copied up, then this will "break" the link.  Changes will not be
+propagated to other names referring to the same inode.
 
 Unless "redirect_dir" feature is enabled, rename(2) on a lower or merged
 directory will fail with EXDEV.
@@ -299,6 +313,92 @@ filesystem are not allowed.  If the underlying filesystem is changed,
 the behavior of the overlay is undefined, though it will not result in
 a crash or deadlock.
 
+When the overlay NFS export feature is enabled, overlay filesystems
+behavior on offline changes of the underlying lower layer is different
+than the behavior when NFS export is disabled.
+
+On every copy_up, an NFS file handle of the lower inode, along with the
+UUID of the lower filesystem, are encoded and stored in an extended
+attribute "trusted.overlay.origin" on the upper inode.
+
+When the NFS export feature is enabled, a lookup of a merged directory,
+that found a lower directory at the lookup path or at the path pointed
+to by the "trusted.overlay.redirect" extended attribute, will verify
+that the found lower directory file handle and lower filesystem UUID
+match the origin file handle that was stored at copy_up time.  If a
+found lower directory does not match the stored origin, that directory
+will not be merged with the upper directory.
+
+
+
+NFS export
+----------
+
+When the underlying filesystems supports NFS export and the "nfs_export"
+feature is enabled, an overlay filesystem may be exported to NFS.
+
+With the "nfs_export" feature, on copy_up of any lower object, an index
+entry is created under the index directory.  The index entry name is the
+hexadecimal representation of the copy up origin file handle.  For a
+non-directory object, the index entry is a hard link to the upper inode.
+For a directory object, the index entry has an extended attribute
+"trusted.overlay.upper" with an encoded file handle of the upper
+directory inode.
+
+When encoding a file handle from an overlay filesystem object, the
+following rules apply:
+
+1. For a non-upper object, encode a lower file handle from lower inode
+2. For an indexed object, encode a lower file handle from copy_up origin
+3. For a pure-upper object and for an existing non-indexed upper object,
+   encode an upper file handle from upper inode
+
+The encoded overlay file handle includes:
+ - Header including path type information (e.g. lower/upper)
+ - UUID of the underlying filesystem
+ - Underlying filesystem encoding of underlying inode
+
+This encoding format is identical to the encoding format file handles that
+are stored in extended attribute "trusted.overlay.origin".
+
+When decoding an overlay file handle, the following steps are followed:
+
+1. Find underlying layer by UUID and path type information.
+2. Decode the underlying filesystem file handle to underlying dentry.
+3. For a lower file handle, lookup the handle in index directory by name.
+4. If a whiteout is found in index, return ESTALE. This represents an
+   overlay object that was deleted after its file handle was encoded.
+5. For a non-directory, instantiate a disconnected overlay dentry from the
+   decoded underlying dentry, the path type and index inode, if found.
+6. For a directory, use the connected underlying decoded dentry, path type
+   and index, to lookup a connected overlay dentry.
+
+Decoding a non-directory file handle may return a disconnected dentry.
+copy_up of that disconnected dentry will create an upper index entry with
+no upper alias.
+
+When overlay filesystem has multiple lower layers, a middle layer
+directory may have a "redirect" to lower directory.  Because middle layer
+"redirects" are not indexed, a lower file handle that was encoded from the
+"redirect" origin directory, cannot be used to find the middle or upper
+layer directory.  Similarly, a lower file handle that was encoded from a
+descendant of the "redirect" origin directory, cannot be used to
+reconstruct a connected overlay path.  To mitigate the cases of
+directories that cannot be decoded from a lower file handle, these
+directories are copied up on encode and encoded as an upper file handle.
+On an overlay filesystem with no upper layer this mitigation cannot be
+used NFS export in this setup requires turning off redirect follow (e.g.
+"redirect_dir=nofollow").
+
+The overlay filesystem does not support non-directory connectable file
+handles, so exporting with the 'subtree_check' exportfs configuration will
+cause failures to lookup files over NFS.
+
+When the NFS export feature is enabled, all directory index entries are
+verified on mount time to check that upper file handles are not stale.
+This verification may cause significant overhead in some cases.
+
+
 Testsuite
 ---------
 
diff --git a/fs/dcache.c b/fs/dcache.c
index cca2b377ff0a..7c38f39958bc 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1698,9 +1698,15 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name)
 }
 EXPORT_SYMBOL(d_alloc);
 
+struct dentry *d_alloc_anon(struct super_block *sb)
+{
+	return __d_alloc(sb, NULL);
+}
+EXPORT_SYMBOL(d_alloc_anon);
+
 struct dentry *d_alloc_cursor(struct dentry * parent)
 {
-	struct dentry *dentry = __d_alloc(parent->d_sb, NULL);
+	struct dentry *dentry = d_alloc_anon(parent->d_sb);
 	if (dentry) {
 		dentry->d_flags |= DCACHE_RCUACCESS | DCACHE_DENTRY_CURSOR;
 		dentry->d_parent = dget(parent);
@@ -1886,7 +1892,7 @@ struct dentry *d_make_root(struct inode *root_inode)
 	struct dentry *res = NULL;
 
 	if (root_inode) {
-		res = __d_alloc(root_inode->i_sb, NULL);
+		res = d_alloc_anon(root_inode->i_sb);
 		if (res)
 			d_instantiate(res, root_inode);
 		else
@@ -1925,33 +1931,19 @@ struct dentry *d_find_any_alias(struct inode *inode)
 }
 EXPORT_SYMBOL(d_find_any_alias);
 
-static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
+static struct dentry *__d_instantiate_anon(struct dentry *dentry,
+					   struct inode *inode,
+					   bool disconnected)
 {
-	struct dentry *tmp;
 	struct dentry *res;
 	unsigned add_flags;
 
-	if (!inode)
-		return ERR_PTR(-ESTALE);
-	if (IS_ERR(inode))
-		return ERR_CAST(inode);
-
-	res = d_find_any_alias(inode);
-	if (res)
-		goto out_iput;
-
-	tmp = __d_alloc(inode->i_sb, NULL);
-	if (!tmp) {
-		res = ERR_PTR(-ENOMEM);
-		goto out_iput;
-	}
-
-	security_d_instantiate(tmp, inode);
+	security_d_instantiate(dentry, inode);
 	spin_lock(&inode->i_lock);
 	res = __d_find_any_alias(inode);
 	if (res) {
 		spin_unlock(&inode->i_lock);
-		dput(tmp);
+		dput(dentry);
 		goto out_iput;
 	}
 
@@ -1961,24 +1953,57 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
 	if (disconnected)
 		add_flags |= DCACHE_DISCONNECTED;
 
-	spin_lock(&tmp->d_lock);
-	__d_set_inode_and_type(tmp, inode, add_flags);
-	hlist_add_head(&tmp->d_u.d_alias, &inode->i_dentry);
+	spin_lock(&dentry->d_lock);
+	__d_set_inode_and_type(dentry, inode, add_flags);
+	hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
 	if (!disconnected) {
-		hlist_bl_lock(&tmp->d_sb->s_roots);
-		hlist_bl_add_head(&tmp->d_hash, &tmp->d_sb->s_roots);
-		hlist_bl_unlock(&tmp->d_sb->s_roots);
+		hlist_bl_lock(&dentry->d_sb->s_roots);
+		hlist_bl_add_head(&dentry->d_hash, &dentry->d_sb->s_roots);
+		hlist_bl_unlock(&dentry->d_sb->s_roots);
 	}
-	spin_unlock(&tmp->d_lock);
+	spin_unlock(&dentry->d_lock);
 	spin_unlock(&inode->i_lock);
 
-	return tmp;
+	return dentry;
 
  out_iput:
 	iput(inode);
 	return res;
 }
 
+struct dentry *d_instantiate_anon(struct dentry *dentry, struct inode *inode)
+{
+	return __d_instantiate_anon(dentry, inode, true);
+}
+EXPORT_SYMBOL(d_instantiate_anon);
+
+static struct dentry *__d_obtain_alias(struct inode *inode, bool disconnected)
+{
+	struct dentry *tmp;
+	struct dentry *res;
+
+	if (!inode)
+		return ERR_PTR(-ESTALE);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	res = d_find_any_alias(inode);
+	if (res)
+		goto out_iput;
+
+	tmp = d_alloc_anon(inode->i_sb);
+	if (!tmp) {
+		res = ERR_PTR(-ENOMEM);
+		goto out_iput;
+	}
+
+	return __d_instantiate_anon(tmp, inode, disconnected);
+
+out_iput:
+	iput(inode);
+	return res;
+}
+
 /**
  * d_obtain_alias - find or allocate a DISCONNECTED dentry for a given inode
  * @inode: inode to allocate the dentry for
@@ -1999,7 +2024,7 @@ static struct dentry *__d_obtain_alias(struct inode *inode, int disconnected)
  */
 struct dentry *d_obtain_alias(struct inode *inode)
 {
-	return __d_obtain_alias(inode, 1);
+	return __d_obtain_alias(inode, true);
 }
 EXPORT_SYMBOL(d_obtain_alias);
 
@@ -2020,7 +2045,7 @@ EXPORT_SYMBOL(d_obtain_alias);
  */
 struct dentry *d_obtain_root(struct inode *inode)
 {
-	return __d_obtain_alias(inode, 0);
+	return __d_obtain_alias(inode, false);
 }
 EXPORT_SYMBOL(d_obtain_root);
 
@@ -3527,6 +3552,7 @@ bool is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
 
 	return result;
 }
+EXPORT_SYMBOL(is_subdir);
 
 static enum d_walk_ret d_genocide_kill(void *data, struct dentry *dentry)
 {
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index 5ac415466861..406e72de88f6 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -47,9 +47,28 @@ config OVERLAY_FS_INDEX
 	  The inodes index feature prevents breaking of lower hardlinks on copy
 	  up.
 
-	  Note, that the inodes index feature is read-only backward compatible.
-	  That is, mounting an overlay which has an index dir on a kernel that
-	  doesn't support this feature read-only, will not have any negative
-	  outcomes.  However, mounting the same overlay with an old kernel
-	  read-write and then mounting it again with a new kernel, will have
-	  unexpected results.
+	  Note, that the inodes index feature is not backward compatible.
+	  That is, mounting an overlay which has an inodes index on a kernel
+	  that doesn't support this feature will have unexpected results.
+
+config OVERLAY_FS_NFS_EXPORT
+	bool "Overlayfs: turn on NFS export feature by default"
+	depends on OVERLAY_FS
+	depends on OVERLAY_FS_INDEX
+	help
+	  If this config option is enabled then overlay filesystems will use
+	  the inodes index dir to decode overlay NFS file handles by default.
+	  In this case, it is still possible to turn off NFS export support
+	  globally with the "nfs_export=off" module option or on a filesystem
+	  instance basis with the "nfs_export=off" mount option.
+
+	  The NFS export feature creates an index on copy up of every file and
+	  directory.  This full index is used to detect overlay filesystems
+	  inconsistencies on lookup, like redirect from multiple upper dirs to
+	  the same lower dir.  The full index may incur some overhead on mount
+	  time, especially when verifying that directory file handles are not
+	  stale.
+
+	  Note, that the NFS export feature is not backward compatible.
+	  That is, mounting an overlay which has a full index on a kernel
+	  that doesn't support this feature will have unexpected results.
diff --git a/fs/overlayfs/Makefile b/fs/overlayfs/Makefile
index 99373bbc1478..30802347a020 100644
--- a/fs/overlayfs/Makefile
+++ b/fs/overlayfs/Makefile
@@ -4,4 +4,5 @@
 
 obj-$(CONFIG_OVERLAY_FS) += overlay.o
 
-overlay-objs := super.o namei.o util.o inode.o dir.o readdir.o copy_up.o
+overlay-objs := super.o namei.o util.o inode.o dir.o readdir.o copy_up.o \
+		export.o
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index eb3b8d39fb61..d855f508fa20 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -232,13 +232,13 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 	return err;
 }
 
-struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper)
+struct ovl_fh *ovl_encode_fh(struct dentry *real, bool is_upper)
 {
 	struct ovl_fh *fh;
 	int fh_type, fh_len, dwords;
 	void *buf;
 	int buflen = MAX_HANDLE_SZ;
-	uuid_t *uuid = &lower->d_sb->s_uuid;
+	uuid_t *uuid = &real->d_sb->s_uuid;
 
 	buf = kmalloc(buflen, GFP_KERNEL);
 	if (!buf)
@@ -250,7 +250,7 @@ struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper)
 	 * the price or reconnecting the dentry.
 	 */
 	dwords = buflen >> 2;
-	fh_type = exportfs_encode_fh(lower, buf, &dwords, 0);
+	fh_type = exportfs_encode_fh(real, buf, &dwords, 0);
 	buflen = (dwords << 2);
 
 	fh = ERR_PTR(-EIO);
@@ -288,8 +288,8 @@ out:
 	return fh;
 }
 
-static int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
-			  struct dentry *upper)
+int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
+		   struct dentry *upper)
 {
 	const struct ovl_fh *fh = NULL;
 	int err;
@@ -315,6 +315,94 @@ static int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
 	return err;
 }
 
+/* Store file handle of @upper dir in @index dir entry */
+static int ovl_set_upper_fh(struct dentry *upper, struct dentry *index)
+{
+	const struct ovl_fh *fh;
+	int err;
+
+	fh = ovl_encode_fh(upper, true);
+	if (IS_ERR(fh))
+		return PTR_ERR(fh);
+
+	err = ovl_do_setxattr(index, OVL_XATTR_UPPER, fh, fh->len, 0);
+
+	kfree(fh);
+	return err;
+}
+
+/*
+ * Create and install index entry.
+ *
+ * Caller must hold i_mutex on indexdir.
+ */
+static int ovl_create_index(struct dentry *dentry, struct dentry *origin,
+			    struct dentry *upper)
+{
+	struct dentry *indexdir = ovl_indexdir(dentry->d_sb);
+	struct inode *dir = d_inode(indexdir);
+	struct dentry *index = NULL;
+	struct dentry *temp = NULL;
+	struct qstr name = { };
+	int err;
+
+	/*
+	 * For now this is only used for creating index entry for directories,
+	 * because non-dir are copied up directly to index and then hardlinked
+	 * to upper dir.
+	 *
+	 * TODO: implement create index for non-dir, so we can call it when
+	 * encoding file handle for non-dir in case index does not exist.
+	 */
+	if (WARN_ON(!d_is_dir(dentry)))
+		return -EIO;
+
+	/* Directory not expected to be indexed before copy up */
+	if (WARN_ON(ovl_test_flag(OVL_INDEX, d_inode(dentry))))
+		return -EIO;
+
+	err = ovl_get_index_name(origin, &name);
+	if (err)
+		return err;
+
+	temp = ovl_lookup_temp(indexdir);
+	if (IS_ERR(temp))
+		goto temp_err;
+
+	err = ovl_do_mkdir(dir, temp, S_IFDIR, true);
+	if (err)
+		goto out;
+
+	err = ovl_set_upper_fh(upper, temp);
+	if (err)
+		goto out_cleanup;
+
+	index = lookup_one_len(name.name, indexdir, name.len);
+	if (IS_ERR(index)) {
+		err = PTR_ERR(index);
+	} else {
+		err = ovl_do_rename(dir, temp, dir, index, 0);
+		dput(index);
+	}
+
+	if (err)
+		goto out_cleanup;
+
+out:
+	dput(temp);
+	kfree(name.name);
+	return err;
+
+temp_err:
+	err = PTR_ERR(temp);
+	temp = NULL;
+	goto out;
+
+out_cleanup:
+	ovl_cleanup(dir, temp);
+	goto out;
+}
+
 struct ovl_copy_up_ctx {
 	struct dentry *parent;
 	struct dentry *dentry;
@@ -327,6 +415,7 @@ struct ovl_copy_up_ctx {
 	struct dentry *workdir;
 	bool tmpfile;
 	bool origin;
+	bool indexed;
 };
 
 static int ovl_link_up(struct ovl_copy_up_ctx *c)
@@ -361,7 +450,10 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
 		}
 	}
 	inode_unlock(udir);
-	ovl_set_nlink_upper(c->dentry);
+	if (err)
+		return err;
+
+	err = ovl_set_nlink_upper(c->dentry);
 
 	return err;
 }
@@ -498,6 +590,12 @@ static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c)
 	if (err)
 		goto out_cleanup;
 
+	if (S_ISDIR(c->stat.mode) && c->indexed) {
+		err = ovl_create_index(c->dentry, c->lowerpath.dentry, temp);
+		if (err)
+			goto out_cleanup;
+	}
+
 	if (c->tmpfile) {
 		inode_lock_nested(udir, I_MUTEX_PARENT);
 		err = ovl_install_temp(c, temp, &newdentry);
@@ -536,20 +634,33 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 {
 	int err;
 	struct ovl_fs *ofs = c->dentry->d_sb->s_fs_info;
-	bool indexed = false;
+	bool to_index = false;
 
-	if (ovl_indexdir(c->dentry->d_sb) && !S_ISDIR(c->stat.mode) &&
-	    c->stat.nlink > 1)
-		indexed = true;
+	/*
+	 * Indexed non-dir is copied up directly to the index entry and then
+	 * hardlinked to upper dir. Indexed dir is copied up to indexdir,
+	 * then index entry is created and then copied up dir installed.
+	 * Copying dir up to indexdir instead of workdir simplifies locking.
+	 */
+	if (ovl_need_index(c->dentry)) {
+		c->indexed = true;
+		if (S_ISDIR(c->stat.mode))
+			c->workdir = ovl_indexdir(c->dentry->d_sb);
+		else
+			to_index = true;
+	}
 
-	if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || indexed)
+	if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || to_index)
 		c->origin = true;
 
-	if (indexed) {
+	if (to_index) {
 		c->destdir = ovl_indexdir(c->dentry->d_sb);
 		err = ovl_get_index_name(c->lowerpath.dentry, &c->destname);
 		if (err)
 			return err;
+	} else if (WARN_ON(!c->parent)) {
+		/* Disconnected dentry must be copied up to index dir */
+		return -EIO;
 	} else {
 		/*
 		 * Mark parent "impure" because it may now contain non-pure
@@ -572,11 +683,17 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 		}
 	}
 
-	if (indexed) {
-		if (!err)
-			ovl_set_flag(OVL_INDEX, d_inode(c->dentry));
-		kfree(c->destname.name);
-	} else if (!err) {
+
+	if (err)
+		goto out;
+
+	if (c->indexed)
+		ovl_set_flag(OVL_INDEX, d_inode(c->dentry));
+
+	if (to_index) {
+		/* Initialize nlink for copy up of disconnected dentry */
+		err = ovl_set_nlink_upper(c->dentry);
+	} else {
 		struct inode *udir = d_inode(c->destdir);
 
 		/* Restore timestamps on parent (best effort) */
@@ -587,6 +704,9 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 		ovl_dentry_set_upper_alias(c->dentry);
 	}
 
+out:
+	if (to_index)
+		kfree(c->destname.name);
 	return err;
 }
 
@@ -611,14 +731,17 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	if (err)
 		return err;
 
-	ovl_path_upper(parent, &parentpath);
-	ctx.destdir = parentpath.dentry;
-	ctx.destname = dentry->d_name;
+	if (parent) {
+		ovl_path_upper(parent, &parentpath);
+		ctx.destdir = parentpath.dentry;
+		ctx.destname = dentry->d_name;
 
-	err = vfs_getattr(&parentpath, &ctx.pstat,
-			  STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT);
-	if (err)
-		return err;
+		err = vfs_getattr(&parentpath, &ctx.pstat,
+				  STATX_ATIME | STATX_MTIME,
+				  AT_STATX_SYNC_AS_STAT);
+		if (err)
+			return err;
+	}
 
 	/* maybe truncate regular file. this has no effect on dirs */
 	if (flags & O_TRUNC)
@@ -639,7 +762,7 @@ static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
 	} else {
 		if (!ovl_dentry_upper(dentry))
 			err = ovl_do_copy_up(&ctx);
-		if (!err && !ovl_dentry_has_upper_alias(dentry))
+		if (!err && parent && !ovl_dentry_has_upper_alias(dentry))
 			err = ovl_link_up(&ctx);
 		ovl_copy_up_end(dentry);
 	}
@@ -652,10 +775,19 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
 {
 	int err = 0;
 	const struct cred *old_cred = ovl_override_creds(dentry->d_sb);
+	bool disconnected = (dentry->d_flags & DCACHE_DISCONNECTED);
+
+	/*
+	 * With NFS export, copy up can get called for a disconnected non-dir.
+	 * In this case, we will copy up lower inode to index dir without
+	 * linking it to upper dir.
+	 */
+	if (WARN_ON(disconnected && d_is_dir(dentry)))
+		return -EIO;
 
 	while (!err) {
 		struct dentry *next;
-		struct dentry *parent;
+		struct dentry *parent = NULL;
 
 		/*
 		 * Check if copy-up has happened as well as for upper alias (in
@@ -671,12 +803,12 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
 		 *      with rename.
 		 */
 		if (ovl_dentry_upper(dentry) &&
-		    ovl_dentry_has_upper_alias(dentry))
+		    (ovl_dentry_has_upper_alias(dentry) || disconnected))
 			break;
 
 		next = dget(dentry);
 		/* find the topmost dentry not yet copied up */
-		for (;;) {
+		for (; !disconnected;) {
 			parent = dget_parent(next);
 
 			if (ovl_dentry_upper(parent))
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index f9788bc116a8..839709c7803a 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -63,8 +63,7 @@ struct dentry *ovl_lookup_temp(struct dentry *workdir)
 }
 
 /* caller holds i_mutex on workdir */
-static struct dentry *ovl_whiteout(struct dentry *workdir,
-				   struct dentry *dentry)
+static struct dentry *ovl_whiteout(struct dentry *workdir)
 {
 	int err;
 	struct dentry *whiteout;
@@ -83,6 +82,38 @@ static struct dentry *ovl_whiteout(struct dentry *workdir,
 	return whiteout;
 }
 
+/* Caller must hold i_mutex on both workdir and dir */
+int ovl_cleanup_and_whiteout(struct dentry *workdir, struct inode *dir,
+			     struct dentry *dentry)
+{
+	struct inode *wdir = workdir->d_inode;
+	struct dentry *whiteout;
+	int err;
+	int flags = 0;
+
+	whiteout = ovl_whiteout(workdir);
+	err = PTR_ERR(whiteout);
+	if (IS_ERR(whiteout))
+		return err;
+
+	if (d_is_dir(dentry))
+		flags = RENAME_EXCHANGE;
+
+	err = ovl_do_rename(wdir, whiteout, dir, dentry, flags);
+	if (err)
+		goto kill_whiteout;
+	if (flags)
+		ovl_cleanup(wdir, dentry);
+
+out:
+	dput(whiteout);
+	return err;
+
+kill_whiteout:
+	ovl_cleanup(wdir, whiteout);
+	goto out;
+}
+
 int ovl_create_real(struct inode *dir, struct dentry *newdentry,
 		    struct cattr *attr, struct dentry *hardlink, bool debug)
 {
@@ -181,11 +212,6 @@ static bool ovl_type_origin(struct dentry *dentry)
 	return OVL_TYPE_ORIGIN(ovl_path_type(dentry));
 }
 
-static bool ovl_may_have_whiteouts(struct dentry *dentry)
-{
-	return ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry));
-}
-
 static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 			    struct cattr *attr, struct dentry *hardlink)
 {
@@ -301,37 +327,6 @@ out:
 	return ERR_PTR(err);
 }
 
-static struct dentry *ovl_check_empty_and_clear(struct dentry *dentry)
-{
-	int err;
-	struct dentry *ret = NULL;
-	LIST_HEAD(list);
-
-	err = ovl_check_empty_dir(dentry, &list);
-	if (err) {
-		ret = ERR_PTR(err);
-		goto out_free;
-	}
-
-	/*
-	 * When removing an empty opaque directory, then it makes no sense to
-	 * replace it with an exact replica of itself.
-	 *
-	 * If upperdentry has whiteouts, clear them.
-	 *
-	 * Can race with copy-up, since we don't hold the upperdir mutex.
-	 * Doesn't matter, since copy-up can't create a non-empty directory
-	 * from an empty one.
-	 */
-	if (!list_empty(&list))
-		ret = ovl_clear_empty(dentry, &list);
-
-out_free:
-	ovl_cache_free(&list);
-
-	return ret;
-}
-
 static int ovl_set_upper_acl(struct dentry *upperdentry, const char *name,
 			     const struct posix_acl *acl)
 {
@@ -623,23 +618,20 @@ static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper)
 	return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper);
 }
 
-static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
+static int ovl_remove_and_whiteout(struct dentry *dentry,
+				   struct list_head *list)
 {
 	struct dentry *workdir = ovl_workdir(dentry);
-	struct inode *wdir = workdir->d_inode;
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
-	struct inode *udir = upperdir->d_inode;
-	struct dentry *whiteout;
 	struct dentry *upper;
 	struct dentry *opaquedir = NULL;
 	int err;
-	int flags = 0;
 
 	if (WARN_ON(!workdir))
 		return -EROFS;
 
-	if (is_dir) {
-		opaquedir = ovl_check_empty_and_clear(dentry);
+	if (!list_empty(list)) {
+		opaquedir = ovl_clear_empty(dentry, list);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir))
 			goto out;
@@ -662,24 +654,13 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 		goto out_dput_upper;
 	}
 
-	whiteout = ovl_whiteout(workdir, dentry);
-	err = PTR_ERR(whiteout);
-	if (IS_ERR(whiteout))
-		goto out_dput_upper;
-
-	if (d_is_dir(upper))
-		flags = RENAME_EXCHANGE;
-
-	err = ovl_do_rename(wdir, whiteout, udir, upper, flags);
+	err = ovl_cleanup_and_whiteout(workdir, d_inode(upperdir), upper);
 	if (err)
-		goto kill_whiteout;
-	if (flags)
-		ovl_cleanup(wdir, upper);
+		goto out_d_drop;
 
 	ovl_dentry_version_inc(dentry->d_parent, true);
 out_d_drop:
 	d_drop(dentry);
-	dput(whiteout);
 out_dput_upper:
 	dput(upper);
 out_unlock:
@@ -688,13 +669,10 @@ out_dput:
 	dput(opaquedir);
 out:
 	return err;
-
-kill_whiteout:
-	ovl_cleanup(wdir, whiteout);
-	goto out_d_drop;
 }
 
-static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
+static int ovl_remove_upper(struct dentry *dentry, bool is_dir,
+			    struct list_head *list)
 {
 	struct dentry *upperdir = ovl_dentry_upper(dentry->d_parent);
 	struct inode *dir = upperdir->d_inode;
@@ -702,10 +680,8 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 	struct dentry *opaquedir = NULL;
 	int err;
 
-	/* Redirect/origin dir can be !ovl_lower_positive && not clean */
-	if (is_dir && (ovl_dentry_get_redirect(dentry) ||
-		       ovl_may_have_whiteouts(dentry))) {
-		opaquedir = ovl_check_empty_and_clear(dentry);
+	if (!list_empty(list)) {
+		opaquedir = ovl_clear_empty(dentry, list);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir))
 			goto out;
@@ -746,11 +722,26 @@ out:
 	return err;
 }
 
+static bool ovl_pure_upper(struct dentry *dentry)
+{
+	return !ovl_dentry_lower(dentry) &&
+	       !ovl_test_flag(OVL_WHITEOUTS, d_inode(dentry));
+}
+
 static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 {
 	int err;
 	bool locked = false;
 	const struct cred *old_cred;
+	bool lower_positive = ovl_lower_positive(dentry);
+	LIST_HEAD(list);
+
+	/* No need to clean pure upper removed by vfs_rmdir() */
+	if (is_dir && (lower_positive || !ovl_pure_upper(dentry))) {
+		err = ovl_check_empty_dir(dentry, &list);
+		if (err)
+			goto out;
+	}
 
 	err = ovl_want_write(dentry);
 	if (err)
@@ -765,10 +756,10 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 		goto out_drop_write;
 
 	old_cred = ovl_override_creds(dentry->d_sb);
-	if (!ovl_lower_positive(dentry))
-		err = ovl_remove_upper(dentry, is_dir);
+	if (!lower_positive)
+		err = ovl_remove_upper(dentry, is_dir, &list);
 	else
-		err = ovl_remove_and_whiteout(dentry, is_dir);
+		err = ovl_remove_and_whiteout(dentry, &list);
 	revert_creds(old_cred);
 	if (!err) {
 		if (is_dir)
@@ -780,6 +771,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 out_drop_write:
 	ovl_drop_write(dentry);
 out:
+	ovl_cache_free(&list);
 	return err;
 }
 
@@ -915,6 +907,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 	bool samedir = olddir == newdir;
 	struct dentry *opaquedir = NULL;
 	const struct cred *old_cred = NULL;
+	LIST_HEAD(list);
 
 	err = -EINVAL;
 	if (flags & ~(RENAME_EXCHANGE | RENAME_NOREPLACE))
@@ -929,6 +922,27 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 	if (!overwrite && !ovl_can_move(new))
 		goto out;
 
+	if (overwrite && new_is_dir && !ovl_pure_upper(new)) {
+		err = ovl_check_empty_dir(new, &list);
+		if (err)
+			goto out;
+	}
+
+	if (overwrite) {
+		if (ovl_lower_positive(old)) {
+			if (!ovl_dentry_is_whiteout(new)) {
+				/* Whiteout source */
+				flags |= RENAME_WHITEOUT;
+			} else {
+				/* Switch whiteouts */
+				flags |= RENAME_EXCHANGE;
+			}
+		} else if (is_dir && ovl_dentry_is_whiteout(new)) {
+			flags |= RENAME_EXCHANGE;
+			cleanup_whiteout = true;
+		}
+	}
+
 	err = ovl_want_write(old);
 	if (err)
 		goto out;
@@ -952,9 +966,8 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 
 	old_cred = ovl_override_creds(old->d_sb);
 
-	if (overwrite && new_is_dir && (ovl_type_merge_or_lower(new) ||
-					ovl_may_have_whiteouts(new))) {
-		opaquedir = ovl_check_empty_and_clear(new);
+	if (!list_empty(&list)) {
+		opaquedir = ovl_clear_empty(new, &list);
 		err = PTR_ERR(opaquedir);
 		if (IS_ERR(opaquedir)) {
 			opaquedir = NULL;
@@ -962,21 +975,6 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 		}
 	}
 
-	if (overwrite) {
-		if (ovl_lower_positive(old)) {
-			if (!ovl_dentry_is_whiteout(new)) {
-				/* Whiteout source */
-				flags |= RENAME_WHITEOUT;
-			} else {
-				/* Switch whiteouts */
-				flags |= RENAME_EXCHANGE;
-			}
-		} else if (is_dir && ovl_dentry_is_whiteout(new)) {
-			flags |= RENAME_EXCHANGE;
-			cleanup_whiteout = true;
-		}
-	}
-
 	old_upperdir = ovl_dentry_upper(old->d_parent);
 	new_upperdir = ovl_dentry_upper(new->d_parent);
 
@@ -1094,6 +1092,7 @@ out_drop_write:
 	ovl_drop_write(old);
 out:
 	dput(opaquedir);
+	ovl_cache_free(&list);
 	return err;
 }
 
diff --git a/fs/overlayfs/export.c b/fs/overlayfs/export.c
new file mode 100644
index 000000000000..bb94ce9da5c8
--- /dev/null
+++ b/fs/overlayfs/export.c
@@ -0,0 +1,715 @@
+/*
+ * Overlayfs NFS export support.
+ *
+ * Amir Goldstein <amir73il@gmail.com>
+ *
+ * Copyright (C) 2017-2018 CTERA Networks. All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/fs.h>
+#include <linux/cred.h>
+#include <linux/mount.h>
+#include <linux/namei.h>