C++ skb_rtable函数代码示例

int arp_find(unsigned char *haddr, struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	__be32 paddr;
	struct neighbour *n;

	if (!skb_dst(skb)) {
		pr_debug("arp_find is called with dst==NULL\n");
		kfree_skb(skb);
		return 1;
	}

	paddr = rt_nexthop(skb_rtable(skb), ip_hdr(skb)->daddr);
	if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr,
			       paddr, dev))
		return 0;

	n = __neigh_lookup(&arp_tbl, &paddr, dev, 1);

	if (n) {
		n->used = jiffies;
		if (n->nud_state & NUD_VALID || neigh_event_send(n, skb) == 0) {
			neigh_ha_snapshot(haddr, n, dev);
			neigh_release(n);
			return 0;
		}
		neigh_release(n);
	} else
		kfree_skb(skb);
	return 1;
}

/*
 *		Add an ip header to a skbuff and send it out.
 *
 */
int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
{
	struct inet_sock *inet = inet_sk(sk);
	struct rtable *rt = skb_rtable(skb);
	struct iphdr *iph;

	/* Build the IP header. */
	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->opt.optlen : 0));
	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	iph->version  = 4;
	iph->ihl      = 5;
	iph->tos      = inet->tos;
	if (ip_dont_fragment(sk, &rt->dst))
		iph->frag_off = htons(IP_DF);
	else
		iph->frag_off = 0;
	iph->ttl      = ip_select_ttl(inet, &rt->dst);
	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
	iph->saddr    = saddr;
	iph->protocol = sk->sk_protocol;
	ip_select_ident(skb, &rt->dst, sk);

	if (opt && opt->opt.optlen) {
		iph->ihl += opt->opt.optlen>>2;
		ip_options_build(skb, &opt->opt, daddr, rt, 0);
	}

static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb,
				    u8 proto, void *data, __sum16 *check,
				    int datalen, int oldlen)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct rtable *rt = skb_rtable(skb);

	if (skb->ip_summed != CHECKSUM_PARTIAL) {
		if (!(rt->rt_flags & RTCF_LOCAL) &&
		    (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) {
			skb->ip_summed = CHECKSUM_PARTIAL;
			skb->csum_start = skb_headroom(skb) +
					  skb_network_offset(skb) +
					  ip_hdrlen(skb);
			skb->csum_offset = (void *)check - data;
			*check = ~csum_tcpudp_magic(iph->saddr, iph->daddr,
						    datalen, proto, 0);
		} else {
			*check = 0;
			*check = csum_tcpudp_magic(iph->saddr, iph->daddr,
						   datalen, proto,
						   csum_partial(data, datalen,
								0));
			if (proto == IPPROTO_UDP && !*check)
				*check = CSUM_MANGLED_0;
		}
	} else
		inet_proto_csum_replace2(check, skb,
					 htons(oldlen), htons(datalen), true);
}

static int gre_rcv(struct sk_buff *skb)
{
	struct tnl_ptk_info tpi;
	bool csum_err = false;
	int hdr_len;

#ifdef CONFIG_NET_IPGRE_BROADCAST
	if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
		/* Looped back packet, drop it! */
		if (rt_is_output_route(skb_rtable(skb)))
			goto drop;
	}
#endif

	hdr_len = parse_gre_header(skb, &tpi, &csum_err);
	if (hdr_len < 0)
		goto drop;
	if (iptunnel_pull_header(skb, hdr_len, tpi.proto, false) < 0)
		goto drop;

	if (ipgre_rcv(skb, &tpi) == PACKET_RCVD)
		return 0;

	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
	kfree_skb(skb);
	return 0;
}

static unsigned int
tarpit_tg4(struct sk_buff *skb, const struct xt_action_param *par)
{
	const struct iphdr *iph = ip_hdr(skb);
	const struct rtable *rt = skb_rtable(skb);
	const struct xt_tarpit_tginfo *info = par->targinfo;

	/* Do we have an input route cache entry? (Not in PREROUTING.) */
	if (rt == NULL)
		return NF_DROP;

	/* No replies to physical multicast/broadcast */
	/* skb != PACKET_OTHERHOST handled by ip_rcv() */
	if (skb->pkt_type != PACKET_HOST)
		return NF_DROP;

	/* Now check at the protocol level */
	if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
		return NF_DROP;

	/*
	 * Our naive response construction does not deal with IP
	 * options, and probably should not try.
	 */
	if (ip_hdrlen(skb) != sizeof(struct iphdr))
		return NF_DROP;

	/* We are not interested in fragments */
	if (iph->frag_off & htons(IP_OFFSET))
		return NF_DROP;
	tarpit_tcp4(par_net(par), skb, par->state->hook, info->variant);
	return NF_DROP;
}

static int ip_rcv_finish(struct sk_buff *skb)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct rtable *rt;

	if (sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
		const struct net_protocol *ipprot;
		int protocol = iph->protocol;

		ipprot = rcu_dereference(inet_protos[protocol]);
		if (ipprot && ipprot->early_demux) {
			ipprot->early_demux(skb);
			/* must reload iph, skb->head might have changed */
			iph = ip_hdr(skb);
		}
	}

	/*
	 *	Initialise the virtual path cache for the packet. It describes
	 *	how the packet travels inside Linux networking.
	 */
	if (!skb_dst(skb)) {
		int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
					       iph->tos, skb->dev);
		if (unlikely(err)) {
			if (err == -EXDEV)
				NET_INC_STATS_BH(dev_net(skb->dev),
						 LINUX_MIB_IPRPFILTER);
			goto drop;
		}
	}

#ifdef CONFIG_IP_ROUTE_CLASSID
	if (unlikely(skb_dst(skb)->tclassid)) {
		struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
		u32 idx = skb_dst(skb)->tclassid;
		st[idx&0xFF].o_packets++;
		st[idx&0xFF].o_bytes += skb->len;
		st[(idx>>16)&0xFF].i_packets++;
		st[(idx>>16)&0xFF].i_bytes += skb->len;
	}
#endif

	if (iph->ihl > 5 && ip_rcv_options(skb))
		goto drop;

	rt = skb_rtable(skb);
	if (rt->rt_type == RTN_MULTICAST) {
		IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INMCAST,
				skb->len);
	} else if (rt->rt_type == RTN_BROADCAST)
		IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INBCAST,
				skb->len);

	return dst_input(skb);

drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}

static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu)
{
	struct sock *sk = skb->sk;
	struct rtable *ort = skb_rtable(skb);

	if (!skb->dev && sk && sk_fullsock(sk))
		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
}

static netdev_tx_t ipddp_xmit(struct sk_buff *skb, struct net_device *dev)
{
	__be32 paddr = skb_rtable(skb)->rt_gateway;
        struct ddpehdr *ddp;
        struct ipddp_route *rt;
        struct atalk_addr *our_addr;

	spin_lock(&ipddp_route_lock);

        for(rt = ipddp_route_list; rt != NULL; rt = rt->next)
        {
                if(rt->ip == paddr)
                        break;
        }
        if(rt == NULL) {
		spin_unlock(&ipddp_route_lock);
                return NETDEV_TX_OK;
	}

        our_addr = atalk_find_dev_addr(rt->dev);

	if(ipddp_mode == IPDDP_DECAP)
		skb_pull(skb, 35-(sizeof(struct ddpehdr)+1));

	
	ddp = (struct ddpehdr *)skb->data;
        ddp->deh_len_hops = htons(skb->len + (1<<10));
        ddp->deh_sum = 0;

        if(rt->dev->type == ARPHRD_LOCALTLK)
        {
                ddp->deh_dnet  = 0;   
                ddp->deh_snet  = 0;
        }
        else
        {
                ddp->deh_dnet  = rt->at.s_net;   
                ddp->deh_snet  = our_addr->s_net;
        }
        ddp->deh_dnode = rt->at.s_node;
        ddp->deh_snode = our_addr->s_node;
        ddp->deh_dport = 72;
        ddp->deh_sport = 72;

        *((__u8 *)(ddp+1)) = 22;        	

        skb->protocol = htons(ETH_P_ATALK);     

	dev->stats.tx_packets++;
	dev->stats.tx_bytes += skb->len;

	aarp_send_ddp(rt->dev, skb, &rt->at, NULL);

	spin_unlock(&ipddp_route_lock);

        return NETDEV_TX_OK;
}

/*
 * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
 */
static void ip_expire(unsigned long arg)
{
	struct ipq *qp;
	struct net *net;

	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
	net = container_of(qp->q.net, struct net, ipv4.frags);

	spin_lock(&qp->q.lock);

	if (qp->q.flags & INET_FRAG_COMPLETE)
		goto out;

	ipq_kill(qp);
	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);

	if (!(qp->q.flags & INET_FRAG_EVICTED)) {
		struct sk_buff *head = qp->q.fragments;
		const struct iphdr *iph;
		int err;

		IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);

		if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
			goto out;

		rcu_read_lock();
		head->dev = dev_get_by_index_rcu(net, qp->iif);
		if (!head->dev)
			goto out_rcu_unlock;

		/* skb has no dst, perform route lookup again */
		iph = ip_hdr(head);
		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
					   iph->tos, head->dev);
		if (err)
			goto out_rcu_unlock;

		/* Only an end host needs to send an ICMP
		 * "Fragment Reassembly Timeout" message, per RFC792.
		 */
		if (qp->user == IP_DEFRAG_AF_PACKET ||
		    ((qp->user >= IP_DEFRAG_CONNTRACK_IN) &&
		     (qp->user <= __IP_DEFRAG_CONNTRACK_IN_END) &&
		     (skb_rtable(head)->rt_type != RTN_LOCAL)))
			goto out_rcu_unlock;

		/* Send an ICMP "Fragment Reassembly Timeout" message. */
		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
out_rcu_unlock:
		rcu_read_unlock();
	}
out:
	spin_unlock(&qp->q.lock);
	ipq_put(qp);
}

/*
 * Oops, a fragment queue timed out.  Kill it and send an ICMP reply.
 */
static void ip_expire(unsigned long arg)
{
	struct ipq *qp;
	struct net *net;

	qp = container_of((struct inet_frag_queue *) arg, struct ipq, q);
	net = container_of(qp->q.net, struct net, ipv4.frags);

	spin_lock(&qp->q.lock);

	if (qp->q.last_in & INET_FRAG_COMPLETE)
		goto out;

	ipq_kill(qp);

	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);
	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);

	if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) {
		struct sk_buff *head = qp->q.fragments;

		rcu_read_lock();
		head->dev = dev_get_by_index_rcu(net, qp->iif);
		if (!head->dev)
			goto out_rcu_unlock;

		/*
		 * Only search router table for the head fragment,
		 * when defraging timeout at PRE_ROUTING HOOK.
		 */
		if (qp->user == IP_DEFRAG_CONNTRACK_IN && !skb_dst(head)) {
			const struct iphdr *iph = ip_hdr(head);
			int err = ip_route_input(head, iph->daddr, iph->saddr,
						 iph->tos, head->dev);
			if (unlikely(err))
				goto out_rcu_unlock;

			/*
			 * Only an end host needs to send an ICMP
			 * "Fragment Reassembly Timeout" message, per RFC792.
			 */
			if (skb_rtable(head)->rt_type != RTN_LOCAL)
				goto out_rcu_unlock;

		}

		/* Send an ICMP "Fragment Reassembly Timeout" message. */
		icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
out_rcu_unlock:
		rcu_read_unlock();
	}
out:
	spin_unlock(&qp->q.lock);
	ipq_put(qp);
}

int ip_rcv_finish(struct sk_buff *skb)
{
    const struct iphdr *iph = ip_hdr(skb);
    struct rtable *rt;

    /*
     *	Initialise the virtual path cache for the packet. It describes
     *	how the packet travels inside Linux networking.
     */
    if (skb_dst(skb) == NULL) {
        int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
                                       iph->tos, skb->dev);
        if (unlikely(err)) {
            if (err == -EHOSTUNREACH)
                IP_INC_STATS_BH(dev_net(skb->dev),
                                IPSTATS_MIB_INADDRERRORS);
            else if (err == -ENETUNREACH)
                IP_INC_STATS_BH(dev_net(skb->dev),
                                IPSTATS_MIB_INNOROUTES);
            else if (err == -EXDEV)
                NET_INC_STATS_BH(dev_net(skb->dev),
                                 LINUX_MIB_IPRPFILTER);
            goto drop;
        }
    }

#ifdef CONFIG_IP_ROUTE_CLASSID
    if (unlikely(skb_dst(skb)->tclassid)) {
        struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct);
        u32 idx = skb_dst(skb)->tclassid;
        st[idx&0xFF].o_packets++;
        st[idx&0xFF].o_bytes += skb->len;
        st[(idx>>16)&0xFF].i_packets++;
        st[(idx>>16)&0xFF].i_bytes += skb->len;
    }
#endif

    if (iph->ihl > 5 && ip_rcv_options(skb))
        goto drop;

    rt = skb_rtable(skb);
    if (rt->rt_type == RTN_MULTICAST) {
        IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INMCAST,
                           skb->len);
    } else if (rt->rt_type == RTN_BROADCAST)
        IP_UPD_PO_STATS_BH(dev_net(rt->dst.dev), IPSTATS_MIB_INBCAST,
                           skb->len);

    return dst_input(skb);

drop:
    kfree_skb(skb);
    return NET_RX_DROP;
}

/* The packet is locally destined, which requires a real
 * dst_entry, so detach the fake one.  On the way up, the
 * packet would pass through PRE_ROUTING again (which already
 * took place when the packet entered the bridge), but we
 * register an IPv4 PRE_ROUTING 'sabotage' hook that will
 * prevent this from happening. */
static unsigned int br_nf_local_in(unsigned int hook, struct sk_buff *skb,
				   const struct net_device *in,
				   const struct net_device *out,
				   int (*okfn)(struct sk_buff *))
{
	struct rtable *rt = skb_rtable(skb);

	if (rt && rt == bridge_parent_rtable(in))
		skb_dst_drop(skb);

	return NF_ACCEPT;
}

unsigned int
nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum,
		       const struct nf_nat_range2 *range,
		       const struct net_device *out)
{
	struct nf_conn *ct;
	struct nf_conn_nat *nat;
	enum ip_conntrack_info ctinfo;
	struct nf_nat_range2 newrange;
	const struct rtable *rt;
	__be32 newsrc, nh;

	WARN_ON(hooknum != NF_INET_POST_ROUTING);

	ct = nf_ct_get(skb, &ctinfo);

	WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
			 ctinfo == IP_CT_RELATED_REPLY)));

	/* Source address is 0.0.0.0 - locally generated packet that is
	 * probably not supposed to be masqueraded.
	 */
	if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
		return NF_ACCEPT;

	rt = skb_rtable(skb);
	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
	newsrc = inet_select_addr(out, nh, RT_SCOPE_UNIVERSE);
	if (!newsrc) {
		pr_info("%s ate my IP address\n", out->name);
		return NF_DROP;
	}

	nat = nf_ct_nat_ext_add(ct);
	if (nat)
		nat->masq_index = out->ifindex;

	/* Transfer from original range. */
	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
	newrange.flags       = range->flags | NF_NAT_RANGE_MAP_IPS;
	newrange.min_addr.ip = newsrc;
	newrange.max_addr.ip = newsrc;
	newrange.min_proto   = range->min_proto;
	newrange.max_proto   = range->max_proto;

	/* Hand modified range to generic setup. */
	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
}

/**
 * ipv4_pktinfo_prepare - transfer some info from rtable to skb
 * @sk: socket
 * @skb: buffer
 *
 * To support IP_CMSG_PKTINFO option, we store rt_iif and specific
 * destination in skb->cb[] before dst drop.
 * This way, receiver doesn't make cache line misses to read rtable.
 */
void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
{
	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
	bool prepare = (inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO) ||
		       ipv6_sk_rxinfo(sk);

	if (prepare && skb_rtable(skb)) {
		pktinfo->ipi_ifindex = inet_iif(skb);
		pktinfo->ipi_spec_dst.s_addr = fib_compute_spec_dst(skb);
	} else {
		pktinfo->ipi_ifindex = 0;
		pktinfo->ipi_spec_dst.s_addr = 0;
	}
	skb_dst_drop(skb);
}

static unsigned int
masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
{
	struct nf_conn *ct;
	struct nf_conn_nat *nat;
	enum ip_conntrack_info ctinfo;
	struct nf_nat_range newrange;
	const struct nf_nat_ipv4_multi_range_compat *mr;
	const struct rtable *rt;
	__be32 newsrc, nh;

	NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);

	ct = nf_ct_get(skb, &ctinfo);
	nat = nfct_nat(ct);

	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
			    ctinfo == IP_CT_RELATED_REPLY));

	/* Source address is 0.0.0.0 - locally generated packet that is
	 * probably not supposed to be masqueraded.
	 */
	if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == 0)
		return NF_ACCEPT;

	mr = par->targinfo;
	rt = skb_rtable(skb);
	nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
	newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE);
	if (!newsrc) {
		pr_info("%s ate my IP address\n", par->out->name);
		return NF_DROP;
	}

	nat->masq_index = par->out->ifindex;

	/* Transfer from original range. */
	memset(&newrange.min_addr, 0, sizeof(newrange.min_addr));
	memset(&newrange.max_addr, 0, sizeof(newrange.max_addr));
	newrange.flags       = mr->range[0].flags | NF_NAT_RANGE_MAP_IPS;
	newrange.min_addr.ip = newsrc;
	newrange.max_addr.ip = newsrc;
	newrange.min_proto   = mr->range[0].min;
	newrange.max_proto   = mr->range[0].max;

	/* Hand modified range to generic setup. */
	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
}