net: af_unix: useful handling of LSM denials on SCM_RIGHTS

Right now if some LSM such as Smack denies an AF_UNIX socket peer to
receive an SCM_RIGHTS fd, the SCM_RIGHTS fd array will be cut short at
that point, and MSG_CTRUNC is set on return of recvmsg(). This is
highly problematic behaviour, because it leaves the receiver
wondering what happened. As per man page MSG_CTRUNC is supposed to
indicate that the control buffer was sized too short, but suddenly
a permission error might result in the exact same flag being set.
Moreover, the receiver has no chance to determine how many fds got
originally sent and how many were suppressed.[1]

Add a SO_RIGHTS_NOTRUNC option to UNIX sockets to enable more useful
handling of LSM denials when receiving SCM_RIGHTS messages: instead of
truncating the message at the first blocked fd, keep every fd slot
and store the LSM errno in the blocked slot. The socket option is
inherited by the child accept() socket if set on the listen() socket.

[1]: https://github.com/uapi-group/kernel-features#useful-handling-of-lsm-denials-on-scm_rights

Reviewed-by: Christian Brauner (Amutable) <brauner@kernel.org>
Signed-off-by: Jori Koolstra <jkoolstra@xs4all.nl>
Link: https://patch.msgid.link/20260813162818.149248-4-jkoolstra@xs4all.nl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 46 insertions, 8 deletions

diff --git a/net/compat.c b/net/compat.c
index d68cf9c3aad5..6bdf4a2c9077 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -286,7 +286,7 @@ static int scm_max_fds_compat(struct msghdr *msg)
 	return (msg->msg_controllen - sizeof(struct compat_cmsghdr)) / sizeof(int);
 }
 
-void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
+void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm, bool notrunc)
 {
 	struct compat_cmsghdr __user *cm =
 		(struct compat_cmsghdr __user *)msg->msg_control_user;
@@ -296,7 +296,7 @@ void scm_detach_fds_compat(struct msghdr *msg, struct scm_cookie *scm)
 	int err = 0, i;
 
 	for (i = 0; i < fdmax; i++) {
-		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags, notrunc);
 		if (err < 0)
 			break;
 	}
diff --git a/net/core/scm.c b/net/core/scm.c
index a73b1eb30fd2..f0d44ecdb11f 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -351,7 +351,31 @@ static int scm_max_fds(struct msghdr *msg)
 	return (msg->msg_controllen - sizeof(struct cmsghdr)) / sizeof(int);
 }
 
-void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
+int scm_recv_one_fd(struct file *f, int __user *ufd, unsigned int flags,
+		    bool notrunc)
+{
+	int error;
+
+	if (!ufd)
+		return -EFAULT;
+
+	error = security_file_receive(f);
+	if (error)
+		return notrunc ? put_user(error, ufd) : error;
+
+	FD_PREPARE(fdf, flags, get_file(f));
+	if (fdf.err)
+		return fdf.err;
+
+	error = put_user(fd_prepare_fd(fdf), ufd);
+	if (error)
+		return error;
+
+	__receive_sock(fd_prepare_file(fdf));
+	return fd_publish(fdf);
+}
+
+void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm, bool notrunc)
 {
 	struct cmsghdr __user *cm =
 		(__force struct cmsghdr __user *)msg->msg_control_user;
@@ -365,12 +389,12 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 		return;
 
 	if (msg->msg_flags & MSG_CMSG_COMPAT) {
-		scm_detach_fds_compat(msg, scm);
+		scm_detach_fds_compat(msg, scm, notrunc);
 		return;
 	}
 
 	for (i = 0; i < fdmax; i++) {
-		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags);
+		err = scm_recv_one_fd(scm->fp->fp[i], cmsg_data + i, o_flags, notrunc);
 		if (err < 0)
 			break;
 	}
@@ -542,8 +566,12 @@ void scm_recv_unix(struct socket *sock, struct msghdr *msg,
 	if (!__scm_recv_common(sock->sk, msg, scm, flags))
 		return;
 
-	if (scm->fp)
-		scm_detach_fds(msg, scm);
+	if (scm->fp) {
+		struct unix_sock *u;
+
+		u = unix_sk(sock->sk);
+		scm_detach_fds(msg, scm, READ_ONCE(u->scm_rights_notrunc));
+	}
 
 	if (sock->sk->sk_scm_pidfd)
 		scm_pidfd_recv(msg, scm);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 51cbf920130d..5c0549e6784f 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -922,6 +922,7 @@ static bool unix_custom_sockopt(int optname)
 {
 	switch (optname) {
 	case SO_INQ:
+	case SO_RIGHTS_NOTRUNC:
 		return true;
 	default:
 		return false;
@@ -957,6 +958,14 @@ static int unix_setsockopt(struct socket *sock, int level, int optname,
 
 		WRITE_ONCE(u->recvmsg_inq, val);
 		break;
+
+	case SO_RIGHTS_NOTRUNC:
+		if (val > 1 || val < 0)
+			return -EINVAL;
+
+		WRITE_ONCE(u->scm_rights_notrunc, val);
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
@@ -1746,9 +1755,10 @@ restart:
 	init_peercred(newsk, &peercred);
 
 	newu = unix_sk(newsk);
+	otheru = unix_sk(other);
 	newu->listener = other;
+	newu->scm_rights_notrunc = READ_ONCE(otheru->scm_rights_notrunc);
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
-	otheru = unix_sk(other);
 
 	/* copy address information from listening to new sock
 	 *