C++ RT_TOS函数代码示例

/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
	struct net *net = dev_net(skb_dst(skb)->dev);
	const struct iphdr *iph = ip_hdr(skb);
	struct rtable *rt;
	struct flowi4 fl4 = {};
	__be32 saddr = iph->saddr;
	__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
	unsigned int hh_len;

	if (addr_type == RTN_UNSPEC)
		addr_type = inet_addr_type(net, saddr);
	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
		flags |= FLOWI_FLAG_ANYSRC;
	else
		saddr = 0;

	/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
	 * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
	 */
	fl4.daddr = iph->daddr;
	fl4.saddr = saddr;
	fl4.flowi4_tos = RT_TOS(iph->tos);
	fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
	fl4.flowi4_mark = skb->mark;
	fl4.flowi4_flags = flags;
	rt = ip_route_output_key(net, &fl4);
	if (IS_ERR(rt))
		return -1;

	/* Drop old route. */
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);

	if (skb_dst(skb)->error)
		return -1;

#ifdef CONFIG_XFRM
	if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
	    xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
		struct dst_entry *dst = skb_dst(skb);
		skb_dst_set(skb, NULL);
		dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
		if (IS_ERR(dst))
			return -1;
		skb_dst_set(skb, dst);
	}
#endif

	/* Change in oif may mean change in hh_len. */
	hh_len = skb_dst(skb)->dev->hard_header_len;
	if (skb_headroom(skb) < hh_len &&
	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
				0, GFP_ATOMIC))
		return -1;

	return 0;
}

/*
 *      Direct Routing transmitter
 *      Used for ANY protocol
 */
int
ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
	      struct ip_vs_protocol *pp)
{
	struct rtable *rt;			/* Route to the other host */
	struct iphdr  *iph = ip_hdr(skb);
	int    mtu;

	EnterFunction(10);

	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
				      RT_TOS(iph->tos), 1|2)))
		goto tx_error_icmp;
	if (rt->rt_flags & RTCF_LOCAL) {
		ip_rt_put(rt);
		IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
	}

	/* MTU checking */
	mtu = dst_mtu(&rt->dst);
	if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) {
		icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
		ip_rt_put(rt);
		IP_VS_DBG_RL("%s(): frag needed\n", __func__);
		goto tx_error;
	}

	/*
	 * Call ip_send_check because we are not sure it is called
	 * after ip_defrag. Is copy-on-write needed?
	 */
	if (unlikely((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)) {
		ip_rt_put(rt);
		return NF_STOLEN;
	}
	ip_send_check(ip_hdr(skb));

	/* drop old route */
	skb_dst_drop(skb);
	skb_dst_set(skb, &rt->dst);

	/* Another hack: avoid icmp_send in ip_fragment */
	skb->local_df = 1;

	IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 0);

	LeaveFunction(10);
	return NF_STOLEN;

  tx_error_icmp:
	dst_link_failure(skb);
  tx_error:
	kfree_skb(skb);
	LeaveFunction(10);
	return NF_STOLEN;
}

/* Try to route the packet according to the routing keys specified in
 * route_info. Keys are :
 *  - ifindex : 
 *      0 if no oif preferred, 
 *      otherwise set to the index of the desired oif
 *  - route_info->gw :
 *      0 if no gateway specified,
 *      otherwise set to the next host to which the pkt must be routed
 * If success, skb->dev is the output device to which the packet must 
 * be sent and skb->dst is not NULL
 *
 * RETURN: -1 if an error occured
 *          1 if the packet was succesfully routed to the 
 *            destination desired
 *          0 if the kernel routing table could not route the packet
 *            according to the keys specified
 */
static int route(struct sk_buff *skb,
		 unsigned int ifindex,
		 const struct ipt_route_target_info *route_info)
{
	int err;
	struct rtable *rt;
	struct iphdr *iph = ip_hdr(skb);
	struct flowi fl = {
		.oif = ifindex,
		.nl_u = {
			.ip4_u = {
				.daddr = iph->daddr,
				.saddr = 0,
				.tos = RT_TOS(iph->tos),
				.scope = RT_SCOPE_UNIVERSE,
			}
		} 
	};
	
	/* The destination address may be overloaded by the target */
	if (route_info->gw)
		fl.fl4_dst = route_info->gw;
	
	/* Trying to route the packet using the standard routing table. */
	if ((err = ip_route_output_key(&init_net,&rt, &fl))) {
		if (net_ratelimit()) 
			pr_debug("ipt_ROUTE: couldn't route pkt (err: %i)",err);
		return -1;
	}
	
	/* Drop old route. */
	skb_dst_drop(skb);

	/* Success if no oif specified or if the oif correspond to the 
	 * one desired */
	if (!ifindex || rt->dst.dev->ifindex == ifindex) {
		skb_dst_set(skb, &rt->dst);
		skb->dev = skb_dst(skb)->dev;
		skb->protocol = htons(ETH_P_IP);
		return 1;
	}
	
	/* The interface selected by the routing table is not the one
	 * specified by the user. This may happen because the dst address
	 * is one of our own addresses.
	 */
	if (net_ratelimit()) 
		pr_debug("ipt_ROUTE: failed to route as desired gw, oif=%i (got oif=%i)\n", 
		//pr_debug("ipt_ROUTE: failed to route as desired gw=%u.%u.%u.%u oif=%i (got oif=%i)\n", 
		       ifindex, rt->dst.dev->ifindex);
		       //NIPQUAD(route_info->gw), ifindex, rt->dst.dev->ifindex);
	
	return 0;
}

static int vxlan_tnl_send(struct vport *vport, struct sk_buff *skb)
{
	struct net *net = ovs_dp_get_net(vport->dp);
	struct vxlan_port *vxlan_port = vxlan_vport(vport);
	__be16 dst_port = inet_sk(vxlan_port->vs->sock->sk)->inet_sport;
	struct ovs_key_ipv4_tunnel *tun_key;
	struct rtable *rt;
	struct flowi4 fl;
	__be16 src_port;
	__be16 df;
	int err;

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

	tun_key = &OVS_CB(skb)->egress_tun_info->tunnel;
	/* Route lookup */
	memset(&fl, 0, sizeof(fl));
	fl.daddr = tun_key->ipv4_dst;
	fl.saddr = tun_key->ipv4_src;
	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
	fl.flowi4_mark = skb->mark;
	fl.flowi4_proto = IPPROTO_UDP;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt)) {
		err = PTR_ERR(rt);
		goto error;
	}

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

	skb->ignore_df = 1;

	src_port = udp_flow_src_port(net, skb, 0, 0, true);

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

static inline struct rtable *route_mirror(struct sk_buff *skb, int local)
{
        struct iphdr *iph = skb->nh.iph;
	struct dst_entry *odst;
	struct rt_key key = {};
	struct rtable *rt;

	if (local) {
		key.dst = iph->saddr;
		key.src = iph->daddr;
		key.tos = RT_TOS(iph->tos);

		if (ip_route_output_key(&rt, &key) != 0)
			return NULL;
	} else {
		/* non-local src, find valid iif to satisfy
		 * rp-filter when calling ip_route_input. */
		key.dst = iph->daddr;
		if (ip_route_output_key(&rt, &key) != 0)
			return NULL;

		odst = skb->dst;
		if (ip_route_input(skb, iph->saddr, iph->daddr,
		                   RT_TOS(iph->tos), rt->u.dst.dev) != 0) {
			dst_release(&rt->u.dst);
			return NULL;
		}
		dst_release(&rt->u.dst);
		rt = (struct rtable *)skb->dst;
		skb->dst = odst;
	}

	if (rt->u.dst.error) {
		dst_release(&rt->u.dst);
		rt = NULL;
	}

	return rt;
}

static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
					   struct net_device *vrf_dev)
{
	struct iphdr *ip4h = ip_hdr(skb);
	int ret = NET_XMIT_DROP;
	struct flowi4 fl4 = {
		/* needed to match OIF rule */
		.flowi4_oif = vrf_dev->ifindex,
		.flowi4_iif = LOOPBACK_IFINDEX,
		.flowi4_tos = RT_TOS(ip4h->tos),
		.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_L3MDEV_SRC |
				FLOWI_FLAG_SKIP_NH_OIF,
		.daddr = ip4h->daddr,
	};

	if (vrf_send_v4_prep(skb, &fl4, vrf_dev))
		goto err;

	if (!ip4h->saddr) {
		ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
					       RT_SCOPE_LINK);
	}

	ret = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
	if (unlikely(net_xmit_eval(ret)))
		vrf_dev->stats.tx_errors++;
	else
		ret = NET_XMIT_SUCCESS;

out:
	return ret;
err:
	vrf_tx_error(vrf_dev, skb);
	goto out;
}

static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
{
	/* strip the ethernet header added for pass through VRF device */
	__skb_pull(skb, skb_network_offset(skb));

	switch (skb->protocol) {
	case htons(ETH_P_IP):
		return vrf_process_v4_outbound(skb, dev);
	case htons(ETH_P_IPV6):
		return vrf_process_v6_outbound(skb, dev);
	default:
		vrf_tx_error(dev, skb);
		return NET_XMIT_DROP;
	}
}

int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
			       struct net *net,
			       const struct ovs_tunnel_info *tun_info,
			       u8 ipproto,
			       u32 skb_mark,
			       __be16 tp_src,
			       __be16 tp_dst)
{
	const struct ovs_key_ipv4_tunnel *tun_key;
	struct rtable *rt;
	struct flowi4 fl;

	if (unlikely(!tun_info))
		return -EINVAL;

	tun_key = &tun_info->tunnel;

	/* Route lookup to get srouce IP address.
	 * The process may need to be changed if the corresponding process
	 * in vports ops changed.
	 */
	memset(&fl, 0, sizeof(fl));
	fl.daddr = tun_key->ipv4_dst;
	fl.saddr = tun_key->ipv4_src;
	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
	fl.flowi4_mark = skb_mark;
	fl.flowi4_proto = ipproto;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt))
		return PTR_ERR(rt);

	ip_rt_put(rt);

	/* Generate egress_tun_info based on tun_info,
	 * saddr, tp_src and tp_dst
	 */
	__ovs_flow_tun_info_init(egress_tun_info,
				 fl.saddr, tun_key->ipv4_dst,
				 tun_key->ipv4_tos,
				 tun_key->ipv4_ttl,
				 tp_src, tp_dst,
				 tun_key->tun_id,
				 tun_key->tun_flags,
				 tun_info->options,
				 tun_info->options_len);

	return 0;
}

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

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

	/* Route lookup */
	memset(&fl, 0, sizeof(fl));
	fl.fl4_dst = OVS_CB(skb)->tun_key->ipv4_dst;
	fl.fl4_src = OVS_CB(skb)->tun_key->ipv4_src;
	fl.fl4_tos = RT_TOS(OVS_CB(skb)->tun_key->ipv4_tos);
	fl.mark = skb->mark;
	fl.proto = IPPROTO_UDP;

	err = ip_route_output_key(net, &rt, &fl);
	if (err)
		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->vs, rt, skb,
			     fl.fl4_src, 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 struct rtable *gre_get_rt(struct sk_buff *skb,
				 struct net_device *dev,
				 struct flowi4 *fl,
				 const struct ip_tunnel_key *key)
{
	struct net *net = dev_net(dev);

	memset(fl, 0, sizeof(*fl));
	fl->daddr = key->u.ipv4.dst;
	fl->saddr = key->u.ipv4.src;
	fl->flowi4_tos = RT_TOS(key->tos);
	fl->flowi4_mark = skb->mark;
	fl->flowi4_proto = IPPROTO_GRE;

	return ip_route_output_key(net, fl);
}

static int ip_tunnel_bind_dev(struct net_device *dev)
{
	struct net_device *tdev = NULL;
	struct ip_tunnel *tunnel = netdev_priv(dev);
	const struct iphdr *iph;
	int hlen = LL_MAX_HEADER;
	int mtu = ETH_DATA_LEN;
	int t_hlen = tunnel->hlen + sizeof(struct iphdr);

	iph = &tunnel->parms.iph;

	/* Guess output device to choose reasonable mtu and needed_headroom */
	if (iph->daddr) {
		struct flowi4 fl4;
		struct rtable *rt;

		rt = ip_route_output_tunnel(dev_net(dev), &fl4,
					    tunnel->parms.iph.protocol,
					    iph->daddr, iph->saddr,
					    tunnel->parms.o_key,
					    RT_TOS(iph->tos),
					    tunnel->parms.link);
		if (!IS_ERR(rt)) {
			tdev = rt->dst.dev;
			ip_rt_put(rt);
		}
		if (dev->type != ARPHRD_ETHER)
			dev->flags |= IFF_POINTOPOINT;
	}

	if (!tdev && tunnel->parms.link)
		tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);

	if (tdev) {
		hlen = tdev->hard_header_len + tdev->needed_headroom;
		mtu = tdev->mtu;
	}
	dev->iflink = tunnel->parms.link;

	dev->needed_headroom = t_hlen + hlen;
	mtu -= (dev->hard_header_len + t_hlen);

	if (mtu < 68)
		mtu = 68;

	return mtu;
}

static struct rtable *ovs_tunnel_route_lookup(struct net *net,
					      const struct ip_tunnel_key *key,
					      u32 mark,
					      struct flowi4 *fl,
					      u8 protocol)
{
	struct rtable *rt;

	memset(fl, 0, sizeof(*fl));
	fl->daddr = key->u.ipv4.dst;
	fl->saddr = key->u.ipv4.src;
	fl->flowi4_tos = RT_TOS(key->tos);
	fl->flowi4_mark = mark;
	fl->flowi4_proto = protocol;

	rt = ip_route_output_key(net, fl);
	return rt;
}

static int gre_tnl_send(struct vport *vport, struct sk_buff *skb)
{
	struct net *net = ovs_dp_get_net(vport->dp);
	struct ovs_key_ipv4_tunnel *tun_key;
	struct flowi4 fl;
	struct rtable *rt;
	int min_headroom;
	int tunnel_hlen;
	__be16 df;
	int err;

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

	tun_key = OVS_CB(skb)->egress_tun_key;
	/* Route lookup */
	memset(&fl, 0, sizeof(fl));
	fl.daddr = tun_key->ipv4_dst;
	fl.saddr = tun_key->ipv4_src;
	fl.flowi4_tos = RT_TOS(tun_key->ipv4_tos);
	fl.flowi4_mark = skb->mark;
	fl.flowi4_proto = IPPROTO_GRE;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt))
		return PTR_ERR(rt);

	tunnel_hlen = ip_gre_calc_hlen(tun_key->tun_flags);

	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
			+ tunnel_hlen + sizeof(struct iphdr)
			+ (vlan_tx_tag_present(skb) ? VLAN_HLEN : 0);
	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
		int head_delta = SKB_DATA_ALIGN(min_headroom -
						skb_headroom(skb) +
						16);
		err = pskb_expand_head(skb, max_t(int, head_delta, 0),
					0, GFP_ATOMIC);
		if (unlikely(err))
			goto err_free_rt;
	}

static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct ip_tunnel_info *tun_info;
	struct net *net = dev_net(dev);
	const struct ip_tunnel_key *key;
	struct flowi4 fl;
	struct rtable *rt;
	int min_headroom;
	int tunnel_hlen;
	__be16 df, flags;
	int err;

	tun_info = skb_tunnel_info(skb, AF_INET);
	if (unlikely(!tun_info || tun_info->mode != IP_TUNNEL_INFO_TX))
		goto err_free_skb;

	key = &tun_info->key;
	memset(&fl, 0, sizeof(fl));
	fl.daddr = key->ipv4_dst;
	fl.saddr = key->ipv4_src;
	fl.flowi4_tos = RT_TOS(key->ipv4_tos);
	fl.flowi4_mark = skb->mark;
	fl.flowi4_proto = IPPROTO_GRE;

	rt = ip_route_output_key(net, &fl);
	if (IS_ERR(rt))
		goto err_free_skb;

	tunnel_hlen = ip_gre_calc_hlen(key->tun_flags);

	min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len
			+ tunnel_hlen + sizeof(struct iphdr);
	if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) {
		int head_delta = SKB_DATA_ALIGN(min_headroom -
						skb_headroom(skb) +
						16);
		err = pskb_expand_head(skb, max_t(int, head_delta, 0),
				       0, GFP_ATOMIC);
		if (unlikely(err))
			goto err_free_rt;
	}

static int route_mirror(struct sk_buff *skb)
{
        struct iphdr *iph = skb->nh.iph;
	struct rtable *rt;

	/* Backwards */
	if (ip_route_output(&rt, iph->saddr, iph->daddr,
			    RT_TOS(iph->tos) | RTO_CONN,
			    0)) {
		return 0;
	}

	/* check if the interface we are leaving by is the same as the
           one we arrived on */
	if (skb->dev == rt->u.dst.dev) {
		/* Drop old route. */
		dst_release(skb->dst);
		skb->dst = &rt->u.dst;
		return 1;
	}
	return 0;
}

/* With a chainsaw... */
static int route_me_harder(struct sk_buff *skb)
{
    struct iphdr *iph = skb->nh.iph;
    struct rtable *rt;

    struct rt_key key = {
	dst:iph->daddr, src:iph->saddr,
	oif:skb->sk ? skb->sk->bound_dev_if : 0,
	tos:RT_TOS(iph->tos) | RTO_CONN,
#ifdef CONFIG_IP_ROUTE_FWMARK
	fwmark:skb->nfmark
#endif
    };

    if (ip_route_output_key(&rt, &key) != 0)
	return -EINVAL;

    /* Drop old route. */
    dst_release(skb->dst);
    skb->dst = &rt->u.dst;
    return 0;
}