NFS: only invalidate dentrys that are clearly invalid.

Since commit bafc9b754f75 ("vfs: More precise tests in d_invalidate")
in v3.18, a return of '0' from ->d_revalidate() will cause the dentry
to be invalidated even if it has filesystems mounted on or it or on a
descendant.  The mounted filesystem is unmounted.

This means we need to be careful not to return 0 unless the directory
referred to truly is invalid.  So -ESTALE or -ENOENT should invalidate
the directory.  Other errors such a -EPERM or -ERESTARTSYS should be
returned from ->d_revalidate() so they are propagated to the caller.

A particular problem can be demonstrated by:

1/ mount an NFS filesystem using NFSv3 on /mnt
2/ mount any other filesystem on /mnt/foo
3/ ls /mnt/foo
4/ turn off network, or otherwise make the server unable to respond
5/ ls /mnt/foo &
6/ cat /proc/$!/stack # note that nfs_lookup_revalidate is in the call stack
7/ kill -9 $! # this results in -ERESTARTSYS being returned
8/ observe that /mnt/foo has been unmounted.

This patch changes nfs_lookup_revalidate() to only treat
  -ESTALE from nfs_lookup_verify_inode() and
  -ESTALE or -ENOENT from ->lookup()
as indicating an invalid inode.  Other errors are returned.

Also nfs_check_inode_attributes() is changed to return -ESTALE rather
than -EIO.  This is consistent with the error returned in similar
circumstances from nfs_update_inode().

As this bug allows any user to unmount a filesystem mounted on an NFS
filesystem, this fix is suitable for stable kernels.

Fixes: bafc9b754f75 ("vfs: More precise tests in d_invalidate")
Cc: stable@vger.kernel.org (v3.18+)
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

2 files changed, 10 insertions, 6 deletions

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index ab69ebb48350..98b18aaf45c9 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1115,11 +1115,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	/* Force a full look up iff the parent directory has changed */
 	if (!nfs_is_exclusive_create(dir, flags) &&
 	    nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
-
-		if (nfs_lookup_verify_inode(inode, flags)) {
+		error = nfs_lookup_verify_inode(inode, flags);
+		if (error) {
 			if (flags & LOOKUP_RCU)
 				return -ECHILD;
-			goto out_zap_parent;
+			if (error == -ESTALE)
+				goto out_zap_parent;
+			goto out_error;
 		}
 		nfs_advise_use_readdirplus(dir);
 		goto out_valid;
@@ -1144,8 +1146,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
 	trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
-	if (error)
+	if (error == -ESTALE || error == -ENOENT)
 		goto out_bad;
+	if (error)
+		goto out_error;
 	if (nfs_compare_fh(NFS_FH(inode), fhandle))
 		goto out_bad;
 	if ((error = nfs_refresh_inode(inode, fattr)) != 0)
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 1de93ba78dc9..8c465d3c7e05 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1315,9 +1315,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 		return 0;
 	/* Has the inode gone and changed behind our back? */
 	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
-		return -EIO;
+		return -ESTALE;
 	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
-		return -EIO;
+		return -ESTALE;
 
 	if (!nfs_file_has_buffered_writers(nfsi)) {
 		/* Verify a few of the more important attributes */