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

#include <errno.h>
#include <stddef.h>
#include <stdint.h>

#include <netinet/ip.h>
#include <netinet/tcp.h>

#include <sys/socket.h>

#include <linux/virtio_net.h>

#include "util.h"
#include "ip.h"
#include "passt.h"
#include "siphash.h"
#include "inany.h"
#include "vhost_user.h"
#include "tcp.h"
#include "pcap.h"
#include "flow.h"
#include "tcp_conn.h"
#include "flow_table.h"
#include "tcp_vu.h"
#include "tap.h"
#include "tcp_internal.h"
#include "checksum.h"
#include "vu_common.h"
#include <time.h>

static struct iovec iov_vu[VIRTQUEUE_MAX_SIZE + 1];
static struct vu_virtq_element elem[VIRTQUEUE_MAX_SIZE];

/**
 * tcp_vu_l2_hdrlen() - return the size of the header in level 2 frame (TCP)
 * @v6:		Set for IPv6 packet
 *
 * Return: Return the size of the header
 */
static size_t tcp_vu_l2_hdrlen(bool v6)
{
	size_t l2_hdrlen;

	l2_hdrlen = sizeof(struct ethhdr) + sizeof(struct tcphdr);

	if (v6)
		l2_hdrlen += sizeof(struct ipv6hdr);
	else
		l2_hdrlen += sizeof(struct iphdr);

	return l2_hdrlen;
}

/**
 * tcp_vu_update_check() - Calculate TCP checksum
 * @tapside:	Address information for one side of the flow
 * @iov:	Pointer to the array of IO vectors
 * @iov_used:	Length of the array
 */
static void tcp_vu_update_check(const struct flowside *tapside,
			        struct iovec *iov, int iov_used)
{
	char *base = iov[0].iov_base;
	struct tcphdr *th;
	uint32_t psum;

	if (inany_v4(&tapside->oaddr)) {
		const struct in_addr *src4 = inany_v4(&tapside->oaddr);
		const struct in_addr *dst4 = inany_v4(&tapside->eaddr);
		const struct iphdr *iph = vu_ip(base);
		size_t l4len = ntohs(iph->tot_len) - sizeof(*th);

		th = vu_payloadv4(base);
		psum = proto_ipv4_header_psum(l4len, IPPROTO_TCP, *src4, *dst4);
	} else {
		const struct ipv6hdr *ip6h = vu_ip(base);
		size_t l4len = ntohs(ip6h->payload_len);

		th = vu_payloadv6(base);
		psum = proto_ipv6_header_psum(l4len, IPPROTO_TCP,
					      &ip6h->saddr, &ip6h->daddr);
	}
	tcp_update_csum(psum, th, iov, iov_used, (char *)(th + 1) - base);
}

/**
 * tcp_vu_send_flag() - Send segment with flags to vhost-user (no payload)
 * @c:		Execution context
 * @conn:	Connection pointer
 * @flags:	TCP flags: if not set, send segment only if ACK is due
 *
 * Return: negative error code on connection reset, 0 otherwise
 */
int tcp_vu_send_flag(const struct ctx *c, struct tcp_tap_conn *conn, int flags)
{
	struct vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	const struct flowside *tapside = TAPFLOW(conn);
	size_t l2len, optlen, hdrlen;
	struct ipv6hdr *ip6h = NULL;
	struct iphdr *ip4h = NULL;
	struct tcp_syn_opts *opts;
	struct tcphdr *th;
	struct ethhdr *eh;
	uint32_t seq;
	int elem_cnt;
	int nb_ack;
	int ret;

	hdrlen = tcp_vu_l2_hdrlen(CONN_V6(conn));

	vu_init_elem(elem, iov_vu, 2);

	elem_cnt = vu_collect_one_frame(vdev, vq, elem, 1,
					hdrlen + sizeof(struct tcp_syn_opts),
					0, NULL);
	if (elem_cnt < 1)
		return 0;

	vu_set_vnethdr(vdev, &iov_vu[0], 1, 0);

	eh = vu_eth(iov_vu[0].iov_base);

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

	if (CONN_V4(conn)) {
		eh->h_proto = htons(ETH_P_IP);

		ip4h = vu_ip(iov_vu[0].iov_base);
		*ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP);

		th = vu_payloadv4(iov_vu[0].iov_base);
	} else {
		eh->h_proto = htons(ETH_P_IPV6);

		ip6h = vu_ip(iov_vu[0].iov_base);
		*ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP);

		th = vu_payloadv6(iov_vu[0].iov_base);
	}

	memset(th, 0, sizeof(*th));
	th->doff = offsetof(struct tcp_flags_t, opts) / 4;
	th->ack = 1;

	seq = conn->seq_to_tap;
	opts = (struct tcp_syn_opts *)(th + 1);
	ret = tcp_prepare_flags(c, conn, flags, th, opts, &optlen);
	if (ret <= 0) {
		vu_queue_rewind(vq, 1);
		return ret;
	}

	l2len = hdrlen + optlen;
	elem[0].in_sg[0].iov_len = l2len +
				   sizeof(struct virtio_net_hdr_mrg_rxbuf);

	tcp_fill_headers(conn, NULL, ip4h, ip6h, th, iov_vu, 1,
			 (char *)opts - (char *)iov_vu[0].iov_base,
			 NULL, seq, true);

	if (*c->pcap) {
		tcp_vu_update_check(tapside, &elem[0].in_sg[0], 1);
		pcap_iov(&elem[0].in_sg[0], 1,
			 sizeof(struct virtio_net_hdr_mrg_rxbuf));
	}
	nb_ack = 1;

	if (flags & DUP_ACK) {
		elem_cnt = vu_collect_one_frame(vdev, vq, &elem[1], 1, l2len,
						0, NULL);
		if (elem_cnt == 1) {
			memcpy(elem[1].in_sg[0].iov_base,
			       elem[0].in_sg[0].iov_base, l2len);
			vu_set_vnethdr(vdev, &elem[1].in_sg[0], 1, 0);
			nb_ack++;

			if (*c->pcap)
				pcap_iov(&elem[1].in_sg[0], 1, 0);
		}
	}

	vu_flush(vdev, vq, elem, nb_ack);

	return 0;
}

/** tcp_vu_sock_recv() - Receive datastream from socket into vhost-user buffers
 * @c:		Execution context
 * @conn:	Connection pointer
 * @v6:		Set for IPv6 connections
 * @fillsize:	Number of bytes we can receive
 * @dlen:	Size of received data (output)
 *
 * Return: Number of iov entries used to store the data
 */
static ssize_t tcp_vu_sock_recv(const struct ctx *c,
				struct tcp_tap_conn *conn, bool v6,
				size_t fillsize, ssize_t *dlen)
{
	struct vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	struct msghdr mh_sock = { 0 };
	uint16_t mss = MSS_GET(conn);
	int s = conn->sock;
	size_t l2_hdrlen;
	int elem_cnt;
	ssize_t ret;

	*dlen = 0;

	l2_hdrlen = tcp_vu_l2_hdrlen(v6);

	vu_init_elem(elem, &iov_vu[1], VIRTQUEUE_MAX_SIZE);

	elem_cnt = vu_collect(vdev, vq, elem, VIRTQUEUE_MAX_SIZE, mss,
			      l2_hdrlen, fillsize);
	if (elem_cnt < 0) {
		tcp_rst(c, conn);
		return -ENOMEM;
	}

	mh_sock.msg_iov = iov_vu;
	mh_sock.msg_iovlen = elem_cnt + 1;

	do
		ret = recvmsg(s, &mh_sock, MSG_PEEK);
	while (ret < 0 && errno == EINTR);

	if (ret < 0) {
		vu_queue_rewind(vq, elem_cnt);
		if (errno != EAGAIN && errno != EWOULDBLOCK) {
			ret = -errno;
			tcp_rst(c, conn);
		}
		return ret;
	}
	if (!ret) {
		vu_queue_rewind(vq, elem_cnt);

		if ((conn->events & (SOCK_FIN_RCVD | TAP_FIN_SENT)) == SOCK_FIN_RCVD) {
			int retf = tcp_vu_send_flag(c, conn, FIN | ACK);
			if (retf) {
				tcp_rst(c, conn);
				return retf;
			}

			conn_event(c, conn, TAP_FIN_SENT);
		}
		return 0;
	}

	*dlen = ret;

	return elem_cnt;
}

/**
 * tcp_vu_prepare() - Prepare the packet header
 * @c:		Execution context
 * @conn:	Connection pointer
 * @iov:	Pointer to the array of IO vectors
 * @iov_cnt:	Number of entries in @iov
 * @check:	Checksum, if already known
 */
static void tcp_vu_prepare(const struct ctx *c, struct tcp_tap_conn *conn,
			   struct iovec *iov, size_t iov_cnt,
			   const uint16_t **check)
{
	const struct flowside *toside = TAPFLOW(conn);
	char *base = iov[0].iov_base;
	struct ipv6hdr *ip6h = NULL;
	struct iphdr *ip4h = NULL;
	struct tcphdr *th;
	struct ethhdr *eh;
	char *data;

	/* we guess the first iovec provided by the guest can embed
	 * all the headers needed by L2 frame
	 */

	eh = vu_eth(base);

	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)) {
		ASSERT(iov[0].iov_len >= sizeof(struct virtio_net_hdr_mrg_rxbuf) +
		       sizeof(struct ethhdr) + sizeof(struct iphdr) +
		       sizeof(struct tcphdr));

		eh->h_proto = htons(ETH_P_IP);

		ip4h = vu_ip(base);
		*ip4h = (struct iphdr)L2_BUF_IP4_INIT(IPPROTO_TCP);
		th = vu_payloadv4(base);
	} else {
		ASSERT(iov[0].iov_len >= sizeof(struct virtio_net_hdr_mrg_rxbuf) +
		       sizeof(struct ethhdr) + sizeof(struct ipv6hdr) +
		       sizeof(struct tcphdr));

		eh->h_proto = htons(ETH_P_IPV6);

		ip6h = vu_ip(base);
		*ip6h = (struct ipv6hdr)L2_BUF_IP6_INIT(IPPROTO_TCP);

		th = vu_payloadv6(base);
	}

	memset(th, 0, sizeof(*th));
	th->doff = offsetof(struct tcp_payload_t, data) / 4;
	th->ack = 1;
	data = (char *)(th + 1);

	tcp_fill_headers(conn, NULL, ip4h, ip6h, th, iov, iov_cnt, data - base,
			 *check, conn->seq_to_tap, true);
	if (ip4h)
		*check = &ip4h->check;
}

/**
 * tcp_vu_data_from_sock() - Handle new data from socket, queue to vhost-user,
 *			     in window
 * @c:		Execution context
 * @conn:	Connection pointer
 *
 * Return: Negative on connection reset, 0 otherwise
 */
int tcp_vu_data_from_sock(const struct ctx *c, struct tcp_tap_conn *conn)
{
	uint32_t wnd_scaled = conn->wnd_from_tap << conn->ws_from_tap;
	struct vu_dev *vdev = c->vdev;
	struct vu_virtq *vq = &vdev->vq[VHOST_USER_RX_QUEUE];
	const struct flowside *tapside = TAPFLOW(conn);
	uint16_t mss = MSS_GET(conn);
	size_t l2_hdrlen, fillsize;
	int i, iov_cnt, iov_used;
	uint32_t already_sent = 0;
	int v6 = CONN_V6(conn);
	const uint16_t *check;
	struct iovec *first;
	int frame_size;
	int num_buffers;
	ssize_t len;

	if (!vu_queue_enabled(vq) || !vu_queue_started(vq)) {
		flow_err(conn,
			 "Got packet, but RX virtqueue not usable yet");
		return 0;
	}

	already_sent = conn->seq_to_tap - conn->seq_ack_from_tap;

	if (SEQ_LT(already_sent, 0)) {
		/* RFC 761, section 2.1. */
		flow_trace(conn, "ACK sequence gap: ACK for %u, sent: %u",
			   conn->seq_ack_from_tap, conn->seq_to_tap);
		conn->seq_to_tap = conn->seq_ack_from_tap;
		already_sent = 0;
	}

	if (!wnd_scaled || already_sent >= wnd_scaled) {
		conn_flag(c, conn, STALLED);
		conn_flag(c, conn, ACK_FROM_TAP_DUE);
		return 0;
	}

	/* Set up buffer descriptors we'll fill completely and partially. */

	fillsize = wnd_scaled;

	if (peek_offset_cap)
		already_sent = 0;

	iov_vu[0].iov_base = tcp_buf_discard;
	iov_vu[0].iov_len = already_sent;
	fillsize -= already_sent;

	/* collect the buffers from vhost-user and fill them with the
	 * data from the socket
	 */
	iov_cnt = tcp_vu_sock_recv(c, conn, v6, fillsize, &len);
	if (iov_cnt <= 0)
		return iov_cnt;

	len -= already_sent;
	if (len <= 0) {
		conn_flag(c, conn, STALLED);
		vu_queue_rewind(vq, iov_cnt);
		return 0;
	}

	conn_flag(c, conn, ~STALLED);

	/* Likely, some new data was acked too. */
	tcp_update_seqack_wnd(c, conn, 0, NULL);

	/* initialize headers */
	l2_hdrlen = tcp_vu_l2_hdrlen(v6);
	iov_used = 0;
	num_buffers = 0;
	check = NULL;
	frame_size = 0;

	/* iov_vu is an array of buffers and the buffer size can be
	 * smaller than the frame size we want to use but with
	 * num_buffer we can merge several virtio iov buffers in one packet
	 * we need only to set the packet headers in the first iov and
	 * num_buffer to the number of iov entries
	 */
	for (i = 0; i < iov_cnt && len; i++) {

		if (frame_size == 0)
			first = &iov_vu[i + 1];

		if (iov_vu[i + 1].iov_len > (size_t)len)
			iov_vu[i + 1].iov_len = len;

		len -= iov_vu[i + 1].iov_len;
		iov_used++;

		frame_size += iov_vu[i + 1].iov_len;
		num_buffers++;

		if (frame_size >= mss || len == 0 ||
		    i + 1 == iov_cnt || !vu_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) {
			if (i + 1 == iov_cnt)
				check = NULL;

			/* restore first iovec base: point to vnet header */
			vu_set_vnethdr(vdev, first, num_buffers, l2_hdrlen);

			tcp_vu_prepare(c, conn, first, num_buffers, &check);
			if (*c->pcap)  {
				tcp_vu_update_check(tapside, first, num_buffers);
				pcap_iov(first, num_buffers,
					 sizeof(struct virtio_net_hdr_mrg_rxbuf));
			}

			conn->seq_to_tap += frame_size;

			frame_size = 0;
			num_buffers = 0;
		}
	}

	/* release unused buffers */
	vu_queue_rewind(vq, iov_cnt - iov_used);

	/* send packets */
	vu_flush(vdev, vq, elem, iov_used);

	conn_flag(c, conn, ACK_FROM_TAP_DUE);

	return 0;
}