// SPDX-License-Identifier: GPL-2.0-or-later
/* udp_vu.c - UDP L2 vhost-user management functions
 *
 * Copyright Red Hat
 * Author: Laurent Vivier <lvivier@redhat.com>
 */

#include <unistd.h>
#include <assert.h>
#include <net/ethernet.h>
#include <net/if.h>
#include <netinet/in.h>
#include <netinet/ip.h>
#include <netinet/udp.h>
#include <stdint.h>
#include <stddef.h>
#include <sys/uio.h>
#include <linux/virtio_net.h>

#include "checksum.h"
#include "util.h"
#include "ip.h"
#include "siphash.h"
#include "inany.h"
#include "passt.h"
#include "pcap.h"
#include "log.h"
#include "vhost_user.h"
#include "udp_internal.h"
#include "flow.h"
#include "flow_table.h"
#include "udp_flow.h"
#include "udp_vu.h"
#include "vu_common.h"

static struct iovec     iov_vu		[VIRTQUEUE_MAX_SIZE];
static struct vu_virtq_element	elem		[VIRTQUEUE_MAX_SIZE];

/**
 * udp_vu_hdrlen() - Sum size of all headers, from UDP to virtio-net
 * @v6:		Set for IPv6 packet
 *
 * Return: total size of virtio-net, Ethernet, IP, and UDP headers
 */
static size_t udp_vu_hdrlen(bool v6)
{
	size_t hdrlen;

	hdrlen = VNET_HLEN + sizeof(struct ethhdr) + sizeof(struct udphdr);

	if (v6)
		hdrlen += sizeof(struct ipv6hdr);
	else
		hdrlen += sizeof(struct iphdr);

	return hdrlen;
}

/**
 * udp_vu_sock_recv() - Receive datagrams from socket into vhost-user buffers
 * @data:	IO vector tail for the frame (modified on output)
 * @s:		Socket to receive from
 * @v6:		Set for IPv6 connections
 *
 * Return: size of received data, -1 on error
 */
static ssize_t udp_vu_sock_recv(struct iov_tail *data, int s, bool v6)
{
	struct iovec msg_iov[data->cnt];
	struct msghdr msg = { 0 };
	struct iov_tail payload;
	size_t hdrlen;
	ssize_t dlen;

	/* compute L2 header length */
	hdrlen = udp_vu_hdrlen(v6);

	/* reserve space for the headers */
	ASSERT(iov_tail_size(data) >= MAX(hdrlen, ETH_ZLEN + VNET_HLEN));

	payload = *data;
	iov_drop_header(&payload, hdrlen);

	msg.msg_iov = msg_iov;
	msg.msg_iovlen = iov_tail_clone(msg.msg_iov, payload.cnt, &payload);

	/* read data from the socket */
	dlen = recvmsg(s, &msg, 0);
	if (dlen < 0)
		return -1;

	iov_tail_truncate(data, MAX(dlen + hdrlen, ETH_ZLEN + VNET_HLEN));
	iov_tail_zero_end(data, dlen + hdrlen);
	iov_tail_truncate(data, dlen + hdrlen);

	return dlen;
}

/**
 * udp_vu_prepare() - Prepare the packet header
 * @c:		Execution context
 * @data:	IO vector tail for the frame
 * @toside:	Address information for one side of the flow
 *
 * Return: Layer-4 length
 */
static size_t udp_vu_prepare(const struct ctx *c, const struct iov_tail *data,
			     const struct flowside *toside)
{
	struct iov_tail current = *data;
	struct ethhdr *eh, eh_storage;
	struct udphdr *uh, uh_storage;
	size_t l4len;

	/* ethernet header */
	eh = IOV_REMOVE_HEADER(&current, eh_storage);

	memcpy(eh->h_dest, c->guest_mac, sizeof(eh->h_dest));
	memcpy(eh->h_source, c->our_tap_mac, sizeof(eh->h_source));

	/* initialize header */
	if (inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr)) {
		struct iphdr *iph, iph_storage;

		eh->h_proto = htons(ETH_P_IP);

		iph = IOV_REMOVE_HEADER(&current, iph_storage);
		*iph = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_UDP);

		uh = IOV_REMOVE_HEADER(&current, uh_storage);
		l4len = udp_update_hdr4(iph, uh, &current, toside, true);

		current = *data;
		IOV_PUT_HEADER(&current, eh);
		IOV_PUT_HEADER(&current, iph);
		IOV_PUT_HEADER(&current, uh);
	} else {
		struct ipv6hdr *ip6h, ip6h_storage;

		eh->h_proto = htons(ETH_P_IPV6);

		ip6h = IOV_REMOVE_HEADER(&current, ip6h_storage);
		*ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_UDP);

		uh = IOV_REMOVE_HEADER(&current, uh_storage);
		l4len = udp_update_hdr6(ip6h, uh, &current, toside, true);

		current = *data;
		IOV_PUT_HEADER(&current, eh);
		IOV_PUT_HEADER(&current, ip6h);
		IOV_PUT_HEADER(&current, uh);
	}

	return l4len;
}

/**
 * udp_vu_csum() - Calculate and set checksum for a UDP packet
 * @toside:	Address information for one side of the flow
 * @data:	IO vector tail for the frame
 */
static void udp_vu_csum(const struct flowside *toside,
			const struct iov_tail *data)
{
	const struct in_addr *src4 = inany_v4(&toside->oaddr);
	const struct in_addr *dst4 = inany_v4(&toside->eaddr);
	struct iov_tail payload = *data;
	struct udphdr *uh, uh_storage;
	bool ipv4 = src4 && dst4;
	int hdrlen = sizeof(struct ethhdr) +
		     (ipv4 ? sizeof(struct iphdr) : sizeof(struct ipv6hdr));

	iov_drop_header(&payload, hdrlen);
	uh = IOV_REMOVE_HEADER(&payload, uh_storage);

	if (ipv4)
		csum_udp4(uh, *src4, *dst4, &payload);
	else
		csum_udp6(uh, &toside->oaddr.a6, &toside->eaddr.a6, &payload);
}

/**
 * udp_vu_sock_to_tap() - Forward datagrams from socket to tap
 * @c:		Execution context
 * @s:		Socket to read data from
 * @n:		Maximum number of datagrams to forward
 * @tosidx:	Flow & side to forward data from @s to
 */
void udp_vu_sock_to_tap(const struct ctx *c, int s, int n, flow_sidx_t tosidx)
{
	const struct flowside *toside = flowside_at_sidx(tosidx);
	bool v6 = !(inany_v4(&toside->eaddr) && inany_v4(&toside->oaddr));
	struct vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	struct iov_tail data;
	int i;

	ASSERT(!c->no_udp);

	if (!vu_queue_enabled(vq) || !vu_queue_started(vq)) {
		struct msghdr msg = { 0 };

		debug("Got UDP packet, but RX virtqueue not usable yet");

		for (i = 0; i < n; i++) {
			if (recvmsg(s, &msg, MSG_DONTWAIT) < 0)
				debug_perror("Failed to discard datagram");
		}

		return;
	}

	for (i = 0; i < n; i++) {
		int elem_cnt, elem_used;
		ssize_t dlen;

		vu_init_elem(elem, iov_vu, ARRAY_SIZE(elem), 1);

		elem_cnt = vu_collect(vdev, vq, elem, ARRAY_SIZE(elem),
				      IP_MAX_MTU + ETH_HLEN + VNET_HLEN, NULL);
		if (elem_cnt == 0)
			break;

		data = IOV_TAIL(iov_vu, elem_cnt, 0);

		dlen = udp_vu_sock_recv(&data, s, v6);
		if (dlen < 0) {
			vu_queue_rewind(vq, elem_cnt);
			continue;
		}
		elem_used = data.cnt;

		/* release unused buffers */
		vu_queue_rewind(vq, elem_cnt - elem_used);

		if (data.cnt > 0) {
			vu_set_vnethdr(vdev, &data, elem_used);
			udp_vu_prepare(c, &data, toside);
			if (*c->pcap) {
				udp_vu_csum(toside, &data);
				pcap_iov(data.iov, data.cnt, 0);
			}
			vu_flush(vdev, vq, elem, elem_used);
		}
	}
}