@@ -120,13 +120,26 @@ xattr_permission(struct user_namespace *mnt_userns, struct inode *inode,
}
/*
- * In the user.* namespace, only regular files and directories can have
- * extended attributes. For sticky directories, only the owner and
- * privileged users can write attributes.
+ * In the user.* namespace, for symlinks and special files, only
+ * the owner and priviliged users can read/write attributes.
+ * For sticky directories, only the owner and privileged users can
+ * write attributes.
*/
if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN)) {
- if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
- return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
+ if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) {
+ if (!inode_owner_or_capable(mnt_userns, inode)) {
+ return (mask & MAY_WRITE) ? -EPERM : -ENODATA;
+ }
+ /*
+ * This is special file and file mode bits represent
+ * permission to access device and not
+ * necessarily permission to read/write xattrs.
+ * Hence do not call inode_permission() and return
+ * success.
+ */
+ if (!S_ISLNK(inode->i_mode))
+ return 0;
+ }
if (S_ISDIR(inode->i_mode) && (inode->i_mode & S_ISVTX) &&
(mask & MAY_WRITE) &&
!inode_owner_or_capable(mnt_userns, inode))
Currently user.* xattr are not allowed on symlink and special files. man xattr and recent discussion suggested that primary reason for this restriction is how file permissions for symlinks and special files are little different from regular files and directories. For symlinks, they are world readable/writable and if user xattr were to be permitted, it will allow unpriviliged users to dump a huge amount of user.* xattrs on symlinks without any control. (I think quota control still works with symlinks, just that quota is not typically deployed). For special files, permissions typically control capability to read/write from devices (and not necessarily from filesystem). So if a user can write to device (/dev/null), does not necessarily mean it should be allowed to write large number of user.* xattrs on the filesystem device node is residing in. This patch proposes to relax the restrictions a bit and allow file owner or privileged user (CAP_FOWNER), to be able to read/write user.* xattrs on symlink and special files. Note, for special files, file mode bits represent permission to access device and not necessarily permission to read/write xattrs. Hence, inode_permission() is not called on special files and just being owner (or CAP_FOWNER) is enough to read/write user extended xattrs on special files. LSM will still get a chance to allow/deny this operation as xattr related security hooks are still called. (security_inode_setxattr(), security_inode_getxattr(), security_inode_removexattr(), security_inode_listxattr()) virtiofs daemon has a need to store user.* xatrrs on all the files (including symlinks and special files), and currently that fails. This patch should help. Link: https://lore.kernel.org/linux-fsdevel/20210625191229.1752531-1-vgoyal@redhat.com/ Signed-off-by: Vivek Goyal <vgoyal@redhat.com> --- fs/xattr.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-)