af_unix: Introduce SO_PASSRIGHTS.

As long as recvmsg() or recvmmsg() is used with cmsg, it is not
possible to avoid receiving file descriptors via SCM_RIGHTS.

This behaviour has occasionally been flagged as problematic, as
it can be (ab)used to trigger DoS during close(), for example, by
passing a FUSE-controlled fd or a hung NFS fd.

For instance, as noted on the uAPI Group page [0], an untrusted peer
could send a file descriptor pointing to a hung NFS mount and then
close it.  Once the receiver calls recvmsg() with msg_control, the
descriptor is automatically installed, and then the responsibility
for the final close() now falls on the receiver, which may result
in blocking the process for a long time.

Regarding this, systemd calls cmsg_close_all() [1] after each
recvmsg() to close() unwanted file descriptors sent via SCM_RIGHTS.

However, this cannot work around the issue at all, because the final
fput() may still occur on the receiver's side once sendmsg() with
SCM_RIGHTS succeeds.  Also, even filtering by LSM at recvmsg() does
not work for the same reason.

Thus, we need a better way to refuse SCM_RIGHTS at sendmsg().

Let's introduce SO_PASSRIGHTS to disable SCM_RIGHTS.

Note that this option is enabled by default for backward
compatibility.

Link: https://uapi-group.org/kernel-features/#disabling-reception-of-scm_rights-for-af_unix-sockets #[0]
Link: https://github.com/systemd/systemd/blob/v257.5/src/basic/fd-util.c#L612-L628 #[1]
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/alpha/include/uapi/asm/socket.h

@@ -150,6 +150,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/mips/include/uapi/asm/socket.h

@@ -161,6 +161,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/parisc/include/uapi/asm/socket.h

@@ -142,6 +142,8 @@
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
 #define SO_DEVMEM_DONTNEED	0x4050
 
+#define SO_PASSRIGHTS		0x4051
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

arch/sparc/include/uapi/asm/socket.h

@@ -143,6 +143,8 @@
 
 #define SO_RCVPRIORITY           0x005b
 
+#define SO_PASSRIGHTS            0x005c
+
 #if !defined(__KERNEL__)
 
 

include/net/sock.h

@@ -341,6 +341,7 @@ struct sk_filter;
   *	@sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS
   *	@sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY
   *	@sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD
+  *	@sk_scm_rights: flagged by SO_PASSRIGHTS to recv SCM_RIGHTS
   *	@sk_scm_unused: unused flags for scm_recv()
   *	@ns_tracker: tracker for netns reference
   *	@sk_user_frags: xarray of pages the user is holding a reference on.
@@ -535,7 +536,8 @@ struct sock {
 			u8	sk_scm_credentials : 1,
 				sk_scm_security : 1,
 				sk_scm_pidfd : 1,
-				sk_scm_unused : 5;
+				sk_scm_rights : 1,
+				sk_scm_unused : 4;
 		};
 	};
 	u8			sk_clockid;

include/uapi/asm-generic/socket.h

@@ -145,6 +145,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))

net/core/sock.c

@@ -1571,6 +1571,13 @@ set_sndbuf:
 			ret = -EOPNOTSUPP;
 		break;
 
+	case SO_PASSRIGHTS:
+		if (sk_is_unix(sk))
+			sk->sk_scm_rights = valbool;
+		else
+			ret = -EOPNOTSUPP;
+		break;
+
 	case SO_INCOMING_CPU:
 		reuseport_update_incoming_cpu(sk, val);
 		break;
@@ -1879,6 +1886,13 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		v.val = sk->sk_scm_pidfd;
 		break;
 
+	case SO_PASSRIGHTS:
+		if (!sk_is_unix(sk))
+			return -EOPNOTSUPP;
+
+		v.val = sk->sk_scm_rights;
+		break;
+
 	case SO_PEERCRED:
 	{
 		struct ucred peercred;

net/unix/af_unix.c

@@ -1015,6 +1015,7 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 
 	sock_init_data(sock, sk);
 
+	sk->sk_scm_rights	= 1;
 	sk->sk_hash		= unix_unbound_hash(sk);
 	sk->sk_allocation	= GFP_KERNEL_ACCOUNT;
 	sk->sk_write_space	= unix_write_space;
@@ -2073,6 +2074,11 @@ restart_locked:
 		goto out_unlock;
 	}
 
+	if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+		err = -EPERM;
+		goto out_unlock;
+	}
+
 	if (sk->sk_type != SOCK_SEQPACKET) {
 		err = security_unix_may_send(sk->sk_socket, other->sk_socket);
 		if (err)
@@ -2174,9 +2180,13 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
 
 	if (sock_flag(other, SOCK_DEAD) ||
 	    (other->sk_shutdown & RCV_SHUTDOWN)) {
-		unix_state_unlock(other);
 		err = -EPIPE;
-		goto out;
+		goto out_unlock;
+	}
+
+	if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+		err = -EPERM;
+		goto out_unlock;
 	}
 
 	unix_maybe_add_creds(skb, sk, other);
@@ -2192,6 +2202,8 @@ static int queue_oob(struct sock *sk, struct msghdr *msg, struct sock *other,
 	other->sk_data_ready(other);
 
 	return 0;
+out_unlock:
+	unix_state_unlock(other);
 out:
 	consume_skb(skb);
 	return err;
@@ -2295,6 +2307,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 		    (other->sk_shutdown & RCV_SHUTDOWN))
 			goto out_pipe_unlock;
 
+		if (UNIXCB(skb).fp && !other->sk_scm_rights) {
+			unix_state_unlock(other);
+			err = -EPERM;
+			goto out_free;
+		}
+
 		unix_maybe_add_creds(skb, sk, other);
 		scm_stat_add(other, skb);
 		skb_queue_tail(&other->sk_receive_queue, skb);

tools/include/uapi/asm-generic/socket.h

@@ -145,6 +145,8 @@
 
 #define SO_RCVPRIORITY		82
 
+#define SO_PASSRIGHTS		83
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))