From d1f0467fd6f32aa4c03b392ed00742411a390656 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Tue, 16 Aug 2022 16:42:56 -0500 Subject: [PATCH] btrfs: check if root is readonly while setting security xattr commit b51111271b0352aa596c5ae8faf06939e91b3b68 upstream. For a filesystem which has btrfs read-only property set to true, all write operations including xattr should be denied. However, security xattr can still be changed even if btrfs ro property is true. This happens because xattr_permission() does not have any restrictions on security.*, system.* and in some cases trusted.* from VFS and the decision is left to the underlying filesystem. See comments in xattr_permission() for more details. This patch checks if the root is read-only before performing the set xattr operation. Testcase: DEV=/dev/vdb MNT=/mnt mkfs.btrfs -f $DEV mount $DEV $MNT echo "file one" > $MNT/f1 setfattr -n "security.one" -v 2 $MNT/f1 btrfs property set /mnt ro true setfattr -n "security.one" -v 1 $MNT/f1 umount $MNT CC: stable@vger.kernel.org # 4.9+ Reviewed-by: Qu Wenruo Reviewed-by: Filipe Manana Signed-off-by: Goldwyn Rodrigues Reviewed-by: David Sterba Signed-off-by: David Sterba Signed-off-by: Greg Kroah-Hartman --- fs/btrfs/xattr.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index fccbf5567e78..783214344ac1 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -375,6 +375,9 @@ static int btrfs_xattr_handler_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { + if (btrfs_root_readonly(BTRFS_I(inode)->root)) + return -EROFS; + name = xattr_full_name(handler, name); return __btrfs_getxattr(inode, name, buffer, size); }