[PATCH v2 2/6] nfsd: allow filesystems to opt out of subtree checking

[trondmy@gmail.com]

From: Jeff Layton <jeff.layton@primarydata.com>

When we start allowing NFS to be reexported, then we have some problems
when it comes to subtree checking. In principle, we could allow it, but
it would mean encoding parent info in the filehandles and there may not
be enough space for that in a NFSv3 filehandle.

To enforce this at export upcall time, we add a new export_ops flag
that declares the filesystem ineligible for subtree checking.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 Documentation/filesystems/nfs/exporting.rst | 12 ++++++++++++
 fs/nfs/export.c                             |  2 +-
 fs/nfsd/export.c                            |  6 ++++++
 include/linux/exportfs.h                    |  1 +
 4 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/nfs/exporting.rst b/Documentation/filesystems/nfs/exporting.rst
index cbe542ad5233..960be64446cb 100644
--- a/Documentation/filesystems/nfs/exporting.rst
+++ b/Documentation/filesystems/nfs/exporting.rst
@@ -190,3 +190,15 @@ following flags are defined:
     this on filesystems that have an expensive ->getattr inode operation,
     or when atomicity between pre and post operation attribute collection
     is impossible to guarantee.
+
+  EXPORT_OP_NOSUBTREECHK - disallow subtree checking on this fs
+    Many NFS operations deal with filehandles, which the server must then
+    vet to ensure that they live inside of an exported tree. When the
+    export consists of an entire filesystem, this is trivial. nfsd can just
+    ensure that the filehandle live on the filesystem. When only part of a
+    filesystem is exported however, then nfsd must walk the ancestors of the
+    inode to ensure that it's within an exported subtree. This is an
+    expensive operation and not all filesystems can support it properly.
+    This flag exempts the filesystem from subtree checking and causes
+    exportfs to get back an error if it tries to enable subtree checking
+    on it.
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
index 8f4c528865c5..b9ba306bf912 100644
--- a/fs/nfs/export.c
+++ b/fs/nfs/export.c
@@ -171,5 +171,5 @@ const struct export_operations nfs_export_ops = {
 	.encode_fh = nfs_encode_fh,
 	.fh_to_dentry = nfs_fh_to_dentry,
 	.get_parent = nfs_get_parent,
-	.flags = EXPORT_OP_NOWCC,
+	.flags = EXPORT_OP_NOWCC|EXPORT_OP_NOSUBTREECHK,
 };
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 21e404e7cb68..81e7bb12aca6 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -408,6 +408,12 @@ static int check_export(struct inode *inode, int *flags, unsigned char *uuid)
 		return -EINVAL;
 	}
 
+	if (inode->i_sb->s_export_op->flags & EXPORT_OP_NOSUBTREECHK &&
+	    !(*flags & NFSEXP_NOSUBTREECHECK)) {
+		dprintk("%s: %s does not support subtree checking!\n",
+			__func__, inode->i_sb->s_type->name);
+		return -EINVAL;
+	}
 	return 0;
 
 }
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index e7de0103a32e..2fcbab0f6b61 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -214,6 +214,7 @@ struct export_operations {
 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
 			     int nr_iomaps, struct iattr *iattr);
 #define	EXPORT_OP_NOWCC		(0x1)	/* Don't collect wcc data for NFSv3 replies */
+#define	EXPORT_OP_NOSUBTREECHK	(0x2)	/* Subtree checking is not supported! */
 	unsigned long	flags;
 };
 
-- 
2.28.0