silently ignore ownership changes unless unix extensions are enabled or we're faking uid changes

CIFS currently allows you to change the ownership of a file, but unless
unix extensions are enabled this change is not passed off to the server.

Have CIFS silently ignore ownership changes that can't be persistently
stored on the server unless the "setuids" option is explicitly
specified.

We could return an error here (-EOPNOTSUPP or something), but this is
how most disk-based windows filesystems on behave on Linux (e.g.  VFAT,
NTFS, etc). With cifsacl support and proper Windows to Unix idmapping
support, we may be able to do this more properly in the future.

Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Steve French <sfrench@us.ibm.com>

1 files changed, 20 insertions, 7 deletions

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index ae6b725..fe752fd 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1546,13 +1546,26 @@ int cifs_setattr(struct dentry *direntry, struct iattr *attrs)
 		} else
 			goto cifs_setattr_exit;
 	}
-	if (attrs->ia_valid & ATTR_UID) {
-		cFYI(1, ("UID changed to %d", attrs->ia_uid));
-		uid = attrs->ia_uid;
-	}
-	if (attrs->ia_valid & ATTR_GID) {
-		cFYI(1, ("GID changed to %d", attrs->ia_gid));
-		gid = attrs->ia_gid;
+
+	/*
+	 * Without unix extensions we can't send ownership changes to the
+	 * server, so silently ignore them. This is consistent with how
+	 * local DOS/Windows filesystems behave (VFAT, NTFS, etc). With
+	 * CIFSACL support + proper Windows to Unix idmapping, we may be
+	 * able to support this in the future.
+	 */
+	if (!pTcon->unix_ext &&
+	    !(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) {
+		attrs->ia_valid &= ~(ATTR_UID | ATTR_GID);
+	} else {
+		if (attrs->ia_valid & ATTR_UID) {
+			cFYI(1, ("UID changed to %d", attrs->ia_uid));
+			uid = attrs->ia_uid;
+		}
+		if (attrs->ia_valid & ATTR_GID) {
+			cFYI(1, ("GID changed to %d", attrs->ia_gid));
+			gid = attrs->ia_gid;
+		}
 	}
 
 	time_buf.Attributes = 0;