scm: add SO_PASSPIDFD and SCM_PIDFD

Implement SCM_PIDFD, a new type of CMSG type analogical to SCM_CREDENTIALS,
but it contains pidfd instead of plain pid, which allows programmers not
to care about PID reuse problem.

We mask SO_PASSPIDFD feature if CONFIG_UNIX is not builtin because
it depends on a pidfd_prepare() API which is not exported to the kernel
modules.

Idea comes from UAPI kernel group:
https://uapi-group.org/kernel-features/

Big thanks to Christian Brauner and Lennart Poettering for productive
discussions about this.

Cc: "David S. Miller" <[e-mail]>
Cc: Eric Dumazet <[e-mail]>
Cc: Jakub Kicinski <[e-mail]>
Cc: Paolo Abeni <[e-mail]>
Cc: Leon Romanovsky <[e-mail]>
Cc: David Ahern <[e-mail]>
Cc: Arnd Bergmann <[e-mail]>
Cc: Kees Cook <[e-mail]>
Cc: Christian Brauner <[e-mail]>
Cc: Kuniyuki Iwashima <[e-mail]>
Cc: Lennart Poettering <[e-mail]>
Cc: Luca Boccassi <[e-mail]>
Cc: [e-mail]
Cc: [e-mail]
Cc: [e-mail]
Tested-by: Luca Boccassi <[e-mail]>
Reviewed-by: Kuniyuki Iwashima <[e-mail]>
Reviewed-by: Christian Brauner <[e-mail]>
Signed-off-by: Alexander Mikhalitsyn <[e-mail]>
Reviewed-by: Eric Dumazet <[e-mail]>
Signed-off-by: David S. Miller <[e-mail]>

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

···
 
 #define SO_RCVMARK		75
 
+#define SO_PASSPIDFD		76
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

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

···
 
 #define SO_RCVMARK		75
 
+#define SO_PASSPIDFD		76
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

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

···
 
 #define SO_RCVMARK		0x4049
 
+#define SO_PASSPIDFD		0x404A
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64

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

···
 
 #define SO_RCVMARK               0x0054
 
+#define SO_PASSPIDFD             0x0055
+
 #if !defined(__KERNEL__)
 
 

include/linux/net.h

···
 #define SOCK_PASSSEC		4
 #define SOCK_SUPPORT_ZC		5
 #define SOCK_CUSTOM_SOCKOPT	6
+#define SOCK_PASSPIDFD		7
 
 #ifndef ARCH_HAS_SOCKET_TYPES
 /**

include/linux/socket.h

···
 #define	SCM_RIGHTS	0x01		/* rw: access rights (array of int) */
 #define SCM_CREDENTIALS 0x02		/* rw: struct ucred		*/
 #define SCM_SECURITY	0x03		/* rw: security label		*/
+#define SCM_PIDFD	0x04		/* ro: pidfd (int)		*/
 
 struct ucred {
 	__u32	pid;

include/net/scm.h

···
 }
 #endif /* CONFIG_SECURITY_NETWORK */
 
+static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm)
+{
+	struct file *pidfd_file = NULL;
+	int pidfd;
+
+	/*
+	 * put_cmsg() doesn't return an error if CMSG is truncated,
+	 * that's why we need to opencode these checks here.
+	 */
+	if ((msg->msg_controllen <= sizeof(struct cmsghdr)) ||
+	    (msg->msg_controllen - sizeof(struct cmsghdr)) < sizeof(int)) {
+		msg->msg_flags |= MSG_CTRUNC;
+		return;
+	}
+
+	WARN_ON_ONCE(!scm->pid);
+	pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file);
+
+	if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) {
+		if (pidfd_file) {
+			put_unused_fd(pidfd);
+			fput(pidfd_file);
+		}
+
+		return;
+	}
+
+	if (pidfd_file)
+		fd_install(pidfd, pidfd_file);
+}
+
 static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg,
 				struct scm_cookie *scm, int flags)
 {
 	if (!msg->msg_control) {
-		if (test_bit(SOCK_PASSCRED, &sock->flags) || scm->fp ||
-		    scm_has_secdata(sock))
+		if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+		    test_bit(SOCK_PASSPIDFD, &sock->flags) ||
+		    scm->fp || scm_has_secdata(sock))
 			msg->msg_flags |= MSG_CTRUNC;
 		scm_destroy(scm);
 		return;
···
 		};
 		put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds);
 	}
+
+	if (test_bit(SOCK_PASSPIDFD, &sock->flags))
+		scm_pidfd_recv(msg, scm);
 
 	scm_destroy_cred(scm);
 

include/uapi/asm-generic/socket.h

···
 
 #define SO_RCVMARK		75
 
+#define SO_PASSPIDFD		76
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))

net/core/sock.c

···
 			clear_bit(SOCK_PASSCRED, &sock->flags);
 		break;
 
+	case SO_PASSPIDFD:
+		if (valbool)
+			set_bit(SOCK_PASSPIDFD, &sock->flags);
+		else
+			clear_bit(SOCK_PASSPIDFD, &sock->flags);
+		break;
+
 	case SO_TIMESTAMP_OLD:
 	case SO_TIMESTAMP_NEW:
 	case SO_TIMESTAMPNS_OLD:
···
 
 	case SO_PASSCRED:
 		v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);
+		break;
+
+	case SO_PASSPIDFD:
+		v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags);
 		break;
 
 	case SO_PEERCRED:

net/mptcp/sockopt.c

···
 	case SO_BROADCAST:
 	case SO_BSDCOMPAT:
 	case SO_PASSCRED:
+	case SO_PASSPIDFD:
 	case SO_PASSSEC:
 	case SO_RXQ_OVFL:
 	case SO_WIFI_STATUS:

net/unix/af_unix.c

···
 		if (err)
 			goto out;
 
-		if (test_bit(SOCK_PASSCRED, &sock->flags) &&
+		if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+		     test_bit(SOCK_PASSPIDFD, &sock->flags)) &&
 		    !unix_sk(sk)->addr) {
 			err = unix_autobind(sk);
 			if (err)
···
 	if (err)
 		goto out;
 
-	if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
···
 {
 	if (test_bit(SOCK_PASSCRED, &old->flags))
 		set_bit(SOCK_PASSCRED, &new->flags);
+	if (test_bit(SOCK_PASSPIDFD, &old->flags))
+		set_bit(SOCK_PASSPIDFD, &new->flags);
 	if (test_bit(SOCK_PASSSEC, &old->flags))
 		set_bit(SOCK_PASSSEC, &new->flags);
 }
···
 				  const struct sock *other)
 {
 	return test_bit(SOCK_PASSCRED, &sock->flags) ||
+	       test_bit(SOCK_PASSPIDFD, &sock->flags) ||
 	       !other->sk_socket ||
-	       test_bit(SOCK_PASSCRED, &other->sk_socket->flags);
+	       test_bit(SOCK_PASSCRED, &other->sk_socket->flags) ||
+	       test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags);
 }
 
 /*
···
 			goto out;
 	}
 
-	if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) {
+	if ((test_bit(SOCK_PASSCRED, &sock->flags) ||
+	     test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) {
 		err = unix_autobind(sk);
 		if (err)
 			goto out;
···
 			/* Never glue messages from different writers */
 			if (!unix_skb_scm_eq(skb, &scm))
 				break;
-		} else if (test_bit(SOCK_PASSCRED, &sock->flags)) {
+		} else if (test_bit(SOCK_PASSCRED, &sock->flags) ||
+			   test_bit(SOCK_PASSPIDFD, &sock->flags)) {
 			/* Copy credentials */
 			scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid);
 			unix_set_secdata(&scm, skb);

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

···
 
 #define SO_RCVMARK		75
 
+#define SO_PASSPIDFD		76
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))