/*
 * Copyright (c) 2011 Nicira, Inc.
 * Copyright (c) 2012 Cisco Systems, Inc.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/version.h>
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,26)

#include <linux/in.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <linux/rculist.h>
#include <linux/udp.h>

#include <net/icmp.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/ip_tunnels.h>
#include <net/udp.h>
#include <net/rtnetlink.h>
#include <net/route.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/vxlan.h>

#include "datapath.h"
#include "vport.h"

#define OVS_VXLAN_RCV_PRIORITY		8

/**
 * struct vxlan_port - Keeps track of open UDP ports
 * @vh: vxlan_handler created for the port.
 * @name: vport name.
 */
struct vxlan_port {
	struct vxlan_handler *vh;
	char name[IFNAMSIZ];
};

static inline struct vxlan_port *vxlan_vport(const struct vport *vport)
{
	return vport_priv(vport);
}

/* Called with rcu_read_lock and BH disabled. */
static int vxlan_rcv(struct vxlan_handler *vh, struct sk_buff *skb, __be32 vx_vni)
{
	struct vport *vport = vh->data;
	struct iphdr *iph;
	struct ovs_key_ipv4_tunnel tun_key;
	__be64 key;

	/* Save outer tunnel values */
	iph = ip_hdr(skb);
	key = cpu_to_be64(ntohl(vx_vni) >> 8);
	ovs_flow_tun_key_init(&tun_key, iph, key, TUNNEL_KEY);

	ovs_vport_receive(vport, skb, &tun_key);
	return PACKET_RCVD;
}

static int vxlan_get_options(const struct vport *vport, struct sk_buff *skb)
{
	struct vxlan_port *vxlan_port = vxlan_vport(vport);
	__be16 dst_port = inet_sport(vxlan_port->vh->vs->sock->sk);

	if (nla_put_u16(skb, OVS_TUNNEL_ATTR_DST_PORT, ntohs(dst_port)))
		return -EMSGSIZE;
	return 0;
}

static void vxlan_tnl_destroy(struct vport *vport)
{
	struct vxlan_port *vxlan_port = vxlan_vport(vport);

	vxlan_handler_put(vxlan_port->vh);

	ovs_vport_deferred_free(vport);
}

static struct vport *vxlan_tnl_create(const struct vport_parms *parms)
{
	struct net *net = ovs_dp_get_net(parms->dp);
	struct nlattr *options = parms->options;
	struct vxlan_port *vxlan_port;
	struct vxlan_handler *vh;
	struct vport *vport;
	struct nlattr *a;
	u16 dst_port;
	int err;

	if (!options) {
		err = -EINVAL;
		goto error;
	}
	a = nla_find_nested(options, OVS_TUNNEL_ATTR_DST_PORT);
	if (a && nla_len(a) == sizeof(u16)) {
		dst_port = nla_get_u16(a);
	} else {
		/* Require destination port from userspace. */
		err = -EINVAL;
		goto error;
	}

	vport = ovs_vport_alloc(sizeof(struct vxlan_port),
				&ovs_vxlan_vport_ops, parms);
	if (IS_ERR(vport))
		return vport;

	vxlan_port = vxlan_vport(vport);
	strncpy(vxlan_port->name, parms->name, IFNAMSIZ);

	vh = vxlan_handler_add(net, htons(dst_port), vxlan_rcv,
			       vport, OVS_VXLAN_RCV_PRIORITY, true);
	if (IS_ERR(vh)) {
		ovs_vport_free(vport);
		return (void *)vh;
	}
	vxlan_port->vh = vh;

	return vport;

error:
	return ERR_PTR(err);
}

static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
	struct vxlan_port *vxlan_port = vxlan_vport(vport);
	__be16 dst_port = inet_sport(vxlan_port->vh->vs->sock->sk);
	struct net *net = ovs_dp_get_net(vport->dp);
	struct rtable *rt;
	__be16 src_port;
	__be32 saddr;
	__be16 df;
	int port_min;
	int port_max;
	int err;

	if (unlikely(!OVS_CB(skb)->tun_key)) {
		err = -EINVAL;
		goto error;
	}

	forward_ip_summed(skb, true);

	/* Route lookup */
	saddr = OVS_CB(skb)->tun_key->ipv4_src;
	rt = find_route(ovs_dp_get_net(vport->dp),
			&saddr,
			OVS_CB(skb)->tun_key->ipv4_dst,
			IPPROTO_UDP,
			OVS_CB(skb)->tun_key->ipv4_tos,
			skb_get_mark(skb));
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		goto error;
	}

	df = OVS_CB(skb)->tun_key->tun_flags & TUNNEL_DONT_FRAGMENT ?
		htons(IP_DF) : 0;

	skb->local_df = 1;

	inet_get_local_port_range(&port_min, &port_max);
	src_port = vxlan_src_port(port_min, port_max, skb);

	err = vxlan_xmit_skb(net, vxlan_port->vh, rt, skb,
			     saddr, OVS_CB(skb)->tun_key->ipv4_dst,
			     OVS_CB(skb)->tun_key->ipv4_tos,
			     OVS_CB(skb)->tun_key->ipv4_ttl, df,
			     src_port, dst_port,
			     htonl(be64_to_cpu(OVS_CB(skb)->tun_key->tun_id) << 8));
	if (err < 0)
		ip_rt_put(rt);
error:
	return err;
}

static const char *vxlan_get_name(const struct vport *vport)
{
	struct vxlan_port *vxlan_port = vxlan_vport(vport);
	return vxlan_port->name;
}

const struct vport_ops ovs_vxlan_vport_ops = {
	.type		= OVS_VPORT_TYPE_VXLAN,
	.create		= vxlan_tnl_create,
	.destroy	= vxlan_tnl_destroy,
	.get_name	= vxlan_get_name,
	.get_options	= vxlan_get_options,
	.send		= vxlan_tnl_send,
};
#else
#warning VXLAN tunneling will not be available on kernels before 2.6.26
#endif /* Linux kernel < 2.6.26 */