sunrpc: fix client side handling of tls alerts

A security exploit was discovered in NFS over TLS in tls_alert_recv
due to its assumption that there is valid data in the msghdr's
iterator's kvec.

Instead, this patch proposes the rework how control messages are
setup and used by sock_recvmsg().

If no control message structure is setup, kTLS layer will read and
process TLS data record types. As soon as it encounters a TLS control
message, it would return an error. At that point, NFS can setup a kvec
backed control buffer and read in the control message such as a TLS
alert. Scott found that a msg iterator can advance the kvec pointer
as a part of the copy process thus we need to revert the iterator
before calling into the tls_alert_recv.

Fixes: dea034b ("SUNRPC: Capture CMSG metadata on client-side receive")
Suggested-by: Trond Myklebust <[email protected]>
Suggested-by: Scott Mayhew <[email protected]>
Signed-off-by: Olga Kornievskaia <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Trond Myklebust <[email protected]>

Author: Olga Kornievskaia

net/sunrpc/xprtsock.c

@@ -358,7 +358,7 @@ xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp)
 
 static int
 xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
-		     struct cmsghdr *cmsg, int ret)
+		     unsigned int *msg_flags, struct cmsghdr *cmsg, int ret)
 {
 	u8 content_type = tls_get_record_type(sock->sk, cmsg);
 	u8 level, description;
@@ -371,7 +371,7 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 		 * record, even though there might be more frames
 		 * waiting to be decrypted.
 		 */
-		msg->msg_flags &= ~MSG_EOR;
+		*msg_flags &= ~MSG_EOR;
 		break;
 	case TLS_RECORD_TYPE_ALERT:
 		tls_alert_recv(sock->sk, msg, &level, &description);
@@ -386,19 +386,33 @@ xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg,
 }
 
 static int
-xs_sock_recv_cmsg(struct socket *sock, struct msghdr *msg, int flags)
+xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags)
 {
 	union {
 		struct cmsghdr	cmsg;
 		u8		buf[CMSG_SPACE(sizeof(u8))];
 	} u;
+	u8 alert[2];
+	struct kvec alert_kvec = {
+		.iov_base = alert,
+		.iov_len = sizeof(alert),
+	};
+	struct msghdr msg = {
+		.msg_flags = *msg_flags,
+		.msg_control = &u,
+		.msg_controllen = sizeof(u),
+	};
 	int ret;
 
-	msg->msg_control = &u;
-	msg->msg_controllen = sizeof(u);
-	ret = sock_recvmsg(sock, msg, flags);
-	if (msg->msg_controllen != sizeof(u))
-		ret = xs_sock_process_cmsg(sock, msg, &u.cmsg, ret);
+	iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1,
+		      alert_kvec.iov_len);
+	ret = sock_recvmsg(sock, &msg, flags);
+	if (ret > 0 &&
+	    tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) {
+		iov_iter_revert(&msg.msg_iter, ret);
+		ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg,
+					   -EAGAIN);
+	}
 	return ret;
 }
 
@@ -408,7 +422,13 @@ xs_sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags, size_t seek)
 	ssize_t ret;
 	if (seek != 0)
 		iov_iter_advance(&msg->msg_iter, seek);
-	ret = xs_sock_recv_cmsg(sock, msg, flags);
+	ret = sock_recvmsg(sock, msg, flags);
+	/* Handle TLS inband control message lazily */
+	if (msg->msg_flags & MSG_CTRUNC) {
+		msg->msg_flags &= ~(MSG_CTRUNC | MSG_EOR);
+		if (ret == 0 || ret == -EIO)
+			ret = xs_sock_recv_cmsg(sock, &msg->msg_flags, flags);
+	}
 	return ret > 0 ? ret + seek : ret;
 }
 
@@ -434,7 +454,7 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags,
 		size_t count)
 {
 	iov_iter_discard(&msg->msg_iter, ITER_DEST, count);
-	return xs_sock_recv_cmsg(sock, msg, flags);
+	return xs_sock_recvmsg(sock, msg, flags, 0);
 }
 
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE