static void ip_expire(unsigned long arg)
{
struct ipq *qp;
qp = (struct ipq *)arg;
/*
* Send an ICMP "Fragment Reassembly Timeout" message.
*/
ip_statistics.IpReasmTimeout++;
ip_statistics.IpReasmFails++;
/* This if is always true... shrug */
if(qp->fragments!=NULL)
icmp_send(qp->fragments->skb,ICMP_TIME_EXCEEDED,
ICMP_EXC_FRAGTIME, 0, qp->dev);
/*
* Nuke the fragment queue.
*/
ip_free(qp);
}
static inline int
ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct iphdr *iph = ip_hdr(skb);
int encap_limit = -1;
struct flowi fl;
__u8 dsfield;
__u32 mtu;
int err;
if ((t->parms.proto != IPPROTO_IPIP && t->parms.proto != 0) ||
!ip6_tnl_xmit_ctl(t))
return -1;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
memcpy(&fl, &t->fl, sizeof (fl));
fl.proto = IPPROTO_IPIP;
dsfield = ipv4_get_dsfield(iph);
if ((t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS))
fl.fl6_flowlabel |= htonl((__u32)iph->tos << IPV6_TCLASS_SHIFT)
& IPV6_TCLASS_MASK;
err = ip6_tnl_xmit2(skb, dev, dsfield, &fl, encap_limit, &mtu);
if (err != 0) {
/* XXX: send ICMP error even if DF is not set. */
if (err == -EMSGSIZE)
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
return -1;
}
return 0;
}
static bool ipv6_validate_packet_len(struct sk_buff *skb_in, struct sk_buff *skb_out)
{
struct ipv6hdr *ip6_hdr = ipv6_hdr(skb_out);
struct hdr_iterator iterator = HDR_ITERATOR_INIT(ip6_hdr);
unsigned int ipv6_mtu;
unsigned int ipv4_mtu;
if (skb_out->len <= skb_out->dev->mtu)
return true;
hdr_iterator_last(&iterator);
if (iterator.hdr_type == IPPROTO_ICMPV6) {
struct icmp6hdr *icmpv6_hdr = icmp6_hdr(skb_out);
if (is_icmp6_error(icmpv6_hdr->icmp6_type)) {
int new_packet_len = skb_out->dev->mtu;
int l3_payload_len = new_packet_len - (iterator.data - (void *) ip6_hdr);
skb_trim(skb_out, new_packet_len);
ip6_hdr->payload_len = cpu_to_be16(l3_payload_len);
icmpv6_hdr->icmp6_cksum = 0;
icmpv6_hdr->icmp6_cksum = csum_ipv6_magic(&ip6_hdr->saddr, &ip6_hdr->daddr,
l3_payload_len, IPPROTO_ICMPV6, csum_partial(icmpv6_hdr, l3_payload_len, 0));
return true;
}
}
ipv6_mtu = skb_out->dev->mtu;
ipv4_mtu = skb_in->dev->mtu;
log_debug("Packet is too large for the outgoing MTU and IPv6 routers don't do fragmentation. "
"Dropping...");
icmp_send(skb_in, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
cpu_to_be32(min_uint(ipv6_mtu, ipv4_mtu + 20)));
return false;
}
static int icmp_hnd_echo_request(const struct icmphdr *icmph,
const struct icmpbody_echo *echo_req,
struct sk_buff *skb) {
size_t len;
struct icmpbody_echo *echo_rep;
if (icmph->code != 0) {
skb_free(skb);
return 0; /* error: bad code */
}
len = ip_data_length(ip_hdr(skb));
if (sizeof *icmph + sizeof *echo_req > len) {
skb_free(skb);
return 0; /* error: invalid length */
}
len -= sizeof *icmph + sizeof *echo_req;
echo_rep = &icmp_hdr(skb)->body[0].echo;
return icmp_send(ICMP_ECHO_REPLY, 0, echo_rep,
sizeof *echo_rep + len, skb);
}
/**
* \ingroup tcpcmd
* \b PING-Befehl Sende "Ping" an angegebene Adresse
*/
int16_t command_ping (char *outbuffer)
{
uint32_t var = 0;
if (getLong(&var))
{
unsigned long dest_ip=0;
for (uint8_t i=0; i<4; ++i) {
dest_ip += (var<<(8*i));
if (!getLong(&var))
break;
}
//ARP Request senden
arp_request (dest_ip);
//ICMP-Nachricht Type=8 Code=0: Echo-Anfrage
//TODO: Sequenznummer, Identifier
icmp_send(dest_ip,0x08,0x00,1,1);
}
return 0;
}
int xfrm4_tunnel_check_size(struct sk_buff *skb)
{
int mtu, ret = 0;
struct dst_entry *dst;
struct iphdr *iph = skb->nh.iph;
if (IPCB(skb)->flags & IPSKB_XFRM_TUNNEL_SIZE)
goto out;
IPCB(skb)->flags |= IPSKB_XFRM_TUNNEL_SIZE;
if (!(iph->frag_off & htons(IP_DF)))
goto out;
dst = skb->dst;
mtu = dst_pmtu(dst) - dst->header_len - dst->trailer_len;
if (skb->len > mtu) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ret = -EMSGSIZE;
}
out:
return ret;
}
static int ipip6_rcv(struct sk_buff *skb)
{
struct iphdr *iph;
struct ip_tunnel *tunnel;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
iph = skb->nh.iph;
read_lock(&ipip6_lock);
if ((tunnel = ipip6_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) {
secpath_reset(skb);
skb->mac.raw = skb->nh.raw;
skb->nh.raw = skb->data;
memset(&(IPCB(skb)->opt), 0, sizeof(struct ip_options));
IPCB(skb)->flags = 0;
skb->protocol = htons(ETH_P_IPV6);
skb->pkt_type = PACKET_HOST;
tunnel->stat.rx_packets++;
tunnel->stat.rx_bytes += skb->len;
skb->dev = tunnel->dev;
dst_release(skb->dst);
skb->dst = NULL;
nf_reset(skb);
ipip6_ecn_decapsulate(iph, skb);
netif_rx(skb);
read_unlock(&ipip6_lock);
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PROT_UNREACH, 0);
kfree_skb(skb);
read_unlock(&ipip6_lock);
out:
return 0;
}
static int gre_rcv(struct sk_buff *skb)
{
struct tnl_ptk_info tpi;
bool csum_err = false;
#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
if (parse_gre_header(skb, &tpi, &csum_err) < 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;
}
int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi,
int encap_type)
{
int ret;
struct xfrm4_protocol *handler;
struct xfrm4_protocol __rcu **head = proto_handlers(nexthdr);
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = NULL;
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
if (!head)
goto out;
for_each_protocol_rcu(*head, handler)
if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL)
return ret;
out:
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
kfree_skb(skb);
return 0;
}
/*
* Pass or drop the packet.
* Called by ip_vs_in, when the virtual service is available but
* no destination is available for a new connection.
*/
int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb,
struct ip_vs_protocol *pp)
{
__be16 _ports[2], *pptr;
struct iphdr *iph = ip_hdr(skb);
pptr = skb_header_pointer(skb, iph->ihl*4,
sizeof(_ports), _ports);
if (pptr == NULL) {
ip_vs_service_put(svc);
return NF_DROP;
}
/* if it is fwmark-based service, the cache_bypass sysctl is up
and the destination is RTN_UNICAST (and not local), then create
a cache_bypass connection entry */
if (sysctl_ip_vs_cache_bypass && svc->fwmark
&& (inet_addr_type(iph->daddr) == RTN_UNICAST)) {
int ret, cs;
struct ip_vs_conn *cp;
ip_vs_service_put(svc);
/* create a new connection entry */
IP_VS_DBG(6, "ip_vs_leave: create a cache_bypass entry\n");
cp = ip_vs_conn_new(iph->protocol,
iph->saddr, pptr[0],
iph->daddr, pptr[1],
0, 0,
IP_VS_CONN_F_BYPASS,
NULL);
if (cp == NULL)
return NF_DROP;
/* statistics */
ip_vs_in_stats(cp, skb);
/* set state */
cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp);
/* transmit the first SYN packet */
ret = cp->packet_xmit(skb, cp, pp);
/* do not touch skb anymore */
atomic_inc(&cp->in_pkts);
ip_vs_conn_put(cp);
return ret;
}
/*
* When the virtual ftp service is presented, packets destined
* for other services on the VIP may get here (except services
* listed in the ipvs table), pass the packets, because it is
* not ipvs job to decide to drop the packets.
*/
if ((svc->port == FTPPORT) && (pptr[1] != FTPPORT)) {
ip_vs_service_put(svc);
return NF_ACCEPT;
}
ip_vs_service_put(svc);
/*
* Notify the client that the destination is unreachable, and
* release the socket buffer.
* Since it is in IP layer, the TCP socket is not actually
* created, the TCP RST packet cannot be sent, instead that
* ICMP_PORT_UNREACH is sent here no matter it is TCP/UDP. --WZ
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
return NF_DROP;
}
static unsigned int
fw_in(unsigned int hooknum,
struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
int ret = FW_BLOCK;
u_int16_t redirpt;
/* Assume worse case: any hook could change packet */
(*pskb)->nfcache |= NFC_UNKNOWN | NFC_ALTERED;
if ((*pskb)->ip_summed == CHECKSUM_HW)
if (skb_checksum_help(*pskb, (out == NULL)))
return NF_DROP;
switch (hooknum) {
case NF_IP_PRE_ROUTING:
if (fwops->fw_acct_in)
fwops->fw_acct_in(fwops, PF_INET,
(struct net_device *)in,
&redirpt, pskb);
if ((*pskb)->nh.iph->frag_off & htons(IP_MF|IP_OFFSET)) {
*pskb = ip_ct_gather_frags(*pskb);
if (!*pskb)
return NF_STOLEN;
}
ret = fwops->fw_input(fwops, PF_INET, (struct net_device *)in,
&redirpt, pskb);
break;
case NF_IP_FORWARD:
/* Connection will only be set if it was
demasqueraded: if so, skip forward chain. */
if ((*pskb)->nfct)
ret = FW_ACCEPT;
else ret = fwops->fw_forward(fwops, PF_INET,
(struct net_device *)out,
&redirpt, pskb);
break;
case NF_IP_POST_ROUTING:
ret = fwops->fw_output(fwops, PF_INET,
(struct net_device *)out,
&redirpt, pskb);
if (ret == FW_ACCEPT || ret == FW_SKIP) {
if (fwops->fw_acct_out)
fwops->fw_acct_out(fwops, PF_INET,
(struct net_device *)out,
&redirpt,
pskb);
/* ip_conntrack_confirm return NF_DROP or NF_ACCEPT */
if (ip_conntrack_confirm(*pskb) == NF_DROP)
ret = FW_BLOCK;
}
break;
}
switch (ret) {
case FW_REJECT: {
/* Alexey says:
*
* Generally, routing is THE FIRST thing to make, when
* packet enters IP stack. Before packet is routed you
* cannot call any service routines from IP stack. */
struct iphdr *iph = (*pskb)->nh.iph;
if ((*pskb)->dst != NULL
|| ip_route_input(*pskb, iph->daddr, iph->saddr, iph->tos,
(struct net_device *)in) == 0)
icmp_send(*pskb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH,
0);
return NF_DROP;
}
case FW_ACCEPT:
case FW_SKIP:
if (hooknum == NF_IP_PRE_ROUTING) {
check_for_demasq(pskb);
check_for_redirect(*pskb);
} else if (hooknum == NF_IP_POST_ROUTING) {
check_for_unredirect(*pskb);
/* Handle ICMP errors from client here */
if ((*pskb)->nh.iph->protocol == IPPROTO_ICMP
&& (*pskb)->nfct)
check_for_masq_error(pskb);
}
return NF_ACCEPT;
case FW_MASQUERADE:
if (hooknum == NF_IP_FORWARD) {
#ifdef CONFIG_IP_VS
/* check if it is for ip_vs */
if (check_for_ip_vs_out(pskb, okfn) == NF_STOLEN)
return NF_STOLEN;
#endif
return do_masquerade(pskb, out);
}
else return NF_ACCEPT;
case FW_REDIRECT:
if (hooknum == NF_IP_PRE_ROUTING)
return do_redirect(*pskb, in, redirpt);
else return NF_ACCEPT;
default:
/* FW_BLOCK */
return NF_DROP;
}
}
int icmp_error(struct iphdr * __ip, int __type,
int __code, struct ifnet * __if)
{
// uint8_t icmp_buf[sizeof(struct icmp) + IP_MAXOPTLEN + 8];
struct icmp * icp;
int len;
/* TODO:
if (type != ICMP_REDIRECT)
icmpstat.icps_error++; */
/* Don't send error if not the first fragment
Ref.: TCP/IP Illustrated Volume 2, pg. 325 */
icp = (struct icmp *)__ip->opt;
if (__ip->ip_off & ~(IP_MF | IP_DF)) {
DCC_LOG1(LOG_WARNING, "not first fragment!; ip_off = %04x",
__ip->ip_off);
return -1;
}
len = MIN((__ip->hlen << 2) + 8 , ntohs(__ip->tot_len));
memcpy((void *)&(icp->icmp_ip), __ip, len);
/*
if ((ip->proto == IPPROTO_ICMP) && (type != ICMP_REDIRECT) &&
(totlen >= iplen + ICMP_MINLEN) ) {
TODO:
icmpstat.icps_oldicmp++;
return -1;
} */
/* Don't send error in response to a multicast or broadcast packet */
if (in_broadcast(__ip->daddr, __if) || IN_MULTICAST(__ip->daddr)) {
DCC_LOG(LOG_INFO, "broadcast/multicast!");
return -1;
}
if ((unsigned int)__type > ICMP_MAXTYPE) {
DCC_LOG(LOG_PANIC, "icmp_error");
return -1;
}
/* TODO:
icmpstat.icps_outhist[type]++; */
icp->icmp_type = __type;
icp->icmp_void = 0;
if (__type == ICMP_PARAMETERPROB) {
icp->icmp_pptr = __code;
__code = 0;
} else {
if ((__type == ICMP_DEST_UNREACH) &&
(__code == ICMP_FRAG_NEEDED) && (__if)) {
icp->icmp_nextmtu = htons(__if->if_mtu);
}
}
icp->icmp_code = __code;
return icmp_send(__ip, icp, len);
}
/*
* Oops, a fragment queue timed out. Kill it and send an ICMP reply.
*/
static void ip_expire(struct timer_list *t)
{
struct inet_frag_queue *frag = from_timer(frag, t, timer);
struct ipq *qp;
struct net *net;
qp = container_of(frag, struct ipq, q);
net = container_of(qp->q.net, struct net, ipv4.frags);
rcu_read_lock();
spin_lock(&qp->q.lock);
if (qp->q.flags & INET_FRAG_COMPLETE)
goto out;
ipq_kill(qp);
__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
if (!inet_frag_evicting(&qp->q)) {
struct sk_buff *clone, *head = qp->q.fragments;
const struct iphdr *iph;
int err;
__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments)
goto out;
head->dev = dev_get_by_index_rcu(net, qp->iif);
if (!head->dev)
goto out;
/* 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;
/* Only an end host needs to send an ICMP
* "Fragment Reassembly Timeout" message, per RFC792.
*/
if (frag_expire_skip_icmp(qp->user) &&
(skb_rtable(head)->rt_type != RTN_LOCAL))
goto out;
clone = skb_clone(head, GFP_ATOMIC);
/* Send an ICMP "Fragment Reassembly Timeout" message. */
if (clone) {
spin_unlock(&qp->q.lock);
icmp_send(clone, ICMP_TIME_EXCEEDED,
ICMP_EXC_FRAGTIME, 0);
consume_skb(clone);
goto out_rcu_unlock;
}
}
out:
spin_unlock(&qp->q.lock);
out_rcu_unlock:
rcu_read_unlock();
ipq_put(qp);
}
/*
* NAT transmitter (only for outside-to-inside nat forwarding)
* Not used for related ICMP
*/
int
ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
int mtu;
struct iphdr *iph = ip_hdr(skb);
int local;
EnterFunction(10);
/* check if it is a connection of no-client-port */
if (unlikely(cp->flags & IP_VS_CONN_F_NO_CPORT)) {
__be16 _pt, *p;
p = skb_header_pointer(skb, iph->ihl*4, sizeof(_pt), &_pt);
if (p == NULL)
goto tx_error;
ip_vs_conn_fill_cport(cp, *p);
IP_VS_DBG(10, "filled cport=%d\n", ntohs(*p));
}
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(iph->tos),
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG_RL_PKT(10, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): "
"stopping DNAT to local address");
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(rt->rt_dst) &&
rt_is_input_route(skb_rtable(skb))) {
IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
"stopping DNAT to loopback address");
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
!skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): frag needed for");
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct iphdr)))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
/* mangle the packet */
if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
goto tx_error_put;
ip_hdr(skb)->daddr = cp->daddr.ip;
ip_send_check(ip_hdr(skb));
if (!local) {
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
ip_rt_put(rt);
/*
* Some IPv4 replies get local address from routes,
* not from iph, so while we DNAT after routing
* we need this second input/output route.
*/
if (!__ip_vs_reroute_locally(skb))
goto tx_error;
}
IP_VS_DBG_PKT(10, AF_INET, pp, skb, 0, "After DNAT");
/* FIXME: when application helper enlarges the packet and the length
is larger than the MTU of outgoing device, there will be still
MTU problem. */
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb->ip_summed = CHECKSUM_NONE;
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
iph = skb->nh.iph;
if (iph->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
iph = skb->nh.iph;
rt = (struct rtable*)skb->dst;
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = skb->nh.iph;
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr)
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_IP_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
void ipip_err(struct sk_buff *skb, unsigned char *dp, int len)
{
#ifndef I_WISH_WORLD_WERE_PERFECT
/* It is not :-( All the routers (except for Linux) return only
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
*/
struct iphdr *iph = (struct iphdr*)dp;
int type = skb->h.icmph->type;
int code = skb->h.icmph->code;
struct ip_tunnel *t;
if (len < sizeof(struct iphdr))
return;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
case ICMP_FRAG_NEEDED:
/* Soft state for pmtu is maintained by IP core. */
return;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe they are just ether pollution. --ANK
*/
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return;
break;
}
t = ipip_tunnel_lookup(iph->daddr, iph->saddr);
if (t == NULL || t->parms.iph.daddr == 0)
return;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
return;
if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
return;
#else
struct iphdr *iph = (struct iphdr*)dp;
int hlen = iph->ihl<<2;
struct iphdr *eiph;
int type = skb->h.icmph->type;
int code = skb->h.icmph->code;
int rel_type = 0;
int rel_code = 0;
int rel_info = 0;
struct sk_buff *skb2;
struct rtable *rt;
if (len < hlen + sizeof(struct iphdr))
return;
eiph = (struct iphdr*)(dp + hlen);
switch (type) {
default:
return;
case ICMP_PARAMETERPROB:
if (skb->h.icmph->un.gateway < hlen)
return;
/* So... This guy found something strange INSIDE encapsulated
packet. Well, he is fool, but what can we do ?
*/
rel_type = ICMP_PARAMETERPROB;
rel_info = skb->h.icmph->un.gateway - hlen;
break;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
case ICMP_FRAG_NEEDED:
/* And it is the only really necessary thing :-) */
rel_info = ntohs(skb->h.icmph->un.frag.mtu);
if (rel_info < hlen+68)
return;
rel_info -= hlen;
/* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
if (rel_info > ntohs(eiph->tot_len))
return;
break;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe, it is just ether pollution. --ANK
*/
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return;
break;
}
/* Prepare fake skb to feed it to icmp_send */
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 == NULL)
return;
dst_release(skb2->dst);
skb2->dst = NULL;
skb_pull(skb2, skb->data - (u8*)eiph);
skb2->nh.raw = skb2->data;
/* Try to guess incoming interface */
if (ip_route_output(&rt, eiph->saddr, 0, RT_TOS(eiph->tos), 0)) {
kfree_skb(skb2);
return;
}
skb2->dev = rt->u.dst.dev;
/* route "incoming" packet */
if (rt->rt_flags&RTCF_LOCAL) {
ip_rt_put(rt);
rt = NULL;
if (ip_route_output(&rt, eiph->daddr, eiph->saddr, eiph->tos, 0) ||
rt->u.dst.dev->type != ARPHRD_IPGRE) {
ip_rt_put(rt);
kfree_skb(skb2);
return;
}
} else {
ip_rt_put(rt);
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
skb2->dst->dev->type != ARPHRD_IPGRE) {
kfree_skb(skb2);
return;
}
}
/* change mtu on this route */
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
if (rel_info > skb2->dst->pmtu) {
kfree_skb(skb2);
return;
}
skb2->dst->pmtu = rel_info;
rel_info = htonl(rel_info);
} else if (type == ICMP_TIME_EXCEEDED) {
struct ip_tunnel *t = (struct ip_tunnel*)skb2->dev->priv;
if (t->parms.iph.ttl) {
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
}
}
icmp_send(skb2, rel_type, rel_code, rel_info);
kfree_skb(skb2);
return;
#endif
}
static inline void send_unreach(struct sk_buff *skb_in, int code)
{
icmp_send(skb_in, ICMP_DEST_UNREACH, code, 0);
}
static int ipgre_rcv(struct sk_buff *skb)
{
struct iphdr *iph;
u8 *h;
__be16 flags;
__sum16 csum = 0;
__be32 key = 0;
u32 seqno = 0;
struct ip_tunnel *tunnel;
int offset = 4;
__be16 gre_proto;
unsigned int len;
if (!pskb_may_pull(skb, 16))
goto drop_nolock;
iph = ip_hdr(skb);
h = skb->data;
flags = *(__be16*)h;
if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
/* - Version must be 0.
- We do not support routing headers.
*/
if (flags&(GRE_VERSION|GRE_ROUTING))
goto drop_nolock;
if (flags&GRE_CSUM) {
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
if (!csum)
break;
/* fall through */
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
}
offset += 4;
}
if (flags&GRE_KEY) {
key = *(__be32*)(h + offset);
offset += 4;
}
if (flags&GRE_SEQ) {
seqno = ntohl(*(__be32*)(h + offset));
offset += 4;
}
}
gre_proto = *(__be16 *)(h + 2);
read_lock(&ipgre_lock);
if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
struct net_device_stats *stats = &tunnel->dev->stats;
secpath_reset(skb);
skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
skb->protocol = htons(ETH_P_IP);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
skb->mac_header = skb->network_header;
__pskb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
if (skb_rtable(skb)->fl.iif == 0)
goto drop;
stats->multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
stats->rx_crc_errors++;
stats->rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&GRE_SEQ) {
if (!(flags&GRE_SEQ) ||
(tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
stats->rx_fifo_errors++;
stats->rx_errors++;
goto drop;
}
tunnel->i_seqno = seqno + 1;
}
len = skb->len;
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
stats->rx_length_errors++;
stats->rx_errors++;
goto drop;
}
iph = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
stats->rx_packets++;
stats->rx_bytes += len;
skb->dev = tunnel->dev;
skb_dst_drop(skb);
nf_reset(skb);
skb_reset_network_header(skb);
ipgre_ecn_decapsulate(iph, skb);
netif_rx(skb);
read_unlock(&ipgre_lock);
return(0);
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
read_unlock(&ipgre_lock);
drop_nolock:
kfree_skb(skb);
return(0);
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph;
struct rtable *rt;
struct ip_options * opt = &(IPCB(skb)->opt);
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb_rtable(skb);
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
ip_decrease_ttl(iph);
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
int ip_forward(struct sk_buff *skb)
{
struct net_device *dev2; /* Output device */
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
unsigned short mtu;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb->ip_summed = CHECKSUM_NONE;
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
iph = skb->nh.iph;
rt = (struct rtable*)skb->dst;
if (iph->ttl <= 1)
goto too_many_hops;
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
/*
* Having picked a route we can now send the frame out
* after asking the firewall permission to do so.
*/
skb->priority = rt_tos2priority(iph->tos);
dev2 = rt->u.dst.dev;
mtu = rt->u.dst.pmtu;
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr)
ip_rt_send_redirect(skb);
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, dev2->hard_header_len))
goto drop;
iph = skb->nh.iph;
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now may allocate a new buffer, and copy the datagram into it.
* If the indicated interface is up and running, kick it.
*/
if (skb->len > mtu && (ntohs(iph->frag_off) & IP_DF))
goto frag_needed;
#ifdef CONFIG_IP_ROUTE_NAT
if (rt->rt_flags & RTCF_NAT) {
if (ip_do_nat(skb)) {
kfree_skb(skb);
return NET_RX_BAD;
}
}
#endif
return NF_HOOK(PF_INET, NF_IP_FORWARD, skb, skb->dev, dev2,
ip_forward_finish);
frag_needed:
IP_INC_STATS_BH(IpFragFails);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
goto drop;
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb_rtable(skb);
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
/* We are about to mangle packet. Copy it! */
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
/*
* It is hooked at the NF_IP_FORWARD chain, used only for VS/NAT.
* Check if outgoing packet belongs to the established ip_vs_conn,
* rewrite addresses of the packet and send it on its way...
*/
static unsigned int
ip_vs_out(unsigned int hooknum, struct sk_buff **pskb,
const struct net_device *in, const struct net_device *out,
int (*okfn)(struct sk_buff *))
{
struct sk_buff *skb = *pskb;
struct iphdr *iph;
struct ip_vs_protocol *pp;
struct ip_vs_conn *cp;
int ihl;
EnterFunction(11);
if (skb->ipvs_property)
return NF_ACCEPT;
iph = ip_hdr(skb);
if (unlikely(iph->protocol == IPPROTO_ICMP)) {
int related, verdict = ip_vs_out_icmp(pskb, &related);
if (related)
return verdict;
skb = *pskb;
iph = ip_hdr(skb);
}
pp = ip_vs_proto_get(iph->protocol);
if (unlikely(!pp))
return NF_ACCEPT;
/* reassemble IP fragments */
if (unlikely(iph->frag_off & htons(IP_MF|IP_OFFSET) &&
!pp->dont_defrag)) {
skb = ip_vs_gather_frags(skb, IP_DEFRAG_VS_OUT);
if (!skb)
return NF_STOLEN;
iph = ip_hdr(skb);
*pskb = skb;
}
ihl = iph->ihl << 2;
/*
* Check if the packet belongs to an existing entry
*/
cp = pp->conn_out_get(skb, pp, iph, ihl, 0);
if (unlikely(!cp)) {
if (sysctl_ip_vs_nat_icmp_send &&
(pp->protocol == IPPROTO_TCP ||
pp->protocol == IPPROTO_UDP)) {
__be16 _ports[2], *pptr;
pptr = skb_header_pointer(skb, ihl,
sizeof(_ports), _ports);
if (pptr == NULL)
return NF_ACCEPT; /* Not for me */
if (ip_vs_lookup_real_service(iph->protocol,
iph->saddr, pptr[0])) {
/*
* Notify the real server: there is no
* existing entry if it is not RST
* packet or not TCP packet.
*/
if (iph->protocol != IPPROTO_TCP
|| !is_tcp_reset(skb)) {
icmp_send(skb,ICMP_DEST_UNREACH,
ICMP_PORT_UNREACH, 0);
return NF_DROP;
}
}
}
IP_VS_DBG_PKT(12, pp, skb, 0,
"packet continues traversal as normal");
return NF_ACCEPT;
}
IP_VS_DBG_PKT(11, pp, skb, 0, "Outgoing packet");
if (!ip_vs_make_skb_writable(pskb, ihl))
goto drop;
/* mangle the packet */
if (pp->snat_handler && !pp->snat_handler(pskb, pp, cp))
goto drop;
skb = *pskb;
ip_hdr(skb)->saddr = cp->vaddr;
ip_send_check(ip_hdr(skb));
/* For policy routing, packets originating from this
* machine itself may be routed differently to packets
* passing through. We want this packet to be routed as
* if it came from this machine itself. So re-compute
* the routing information.
*/
if (ip_route_me_harder(pskb, RTN_LOCAL) != 0)
goto drop;
skb = *pskb;
IP_VS_DBG_PKT(10, pp, skb, 0, "After SNAT");
ip_vs_out_stats(cp, skb);
ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp);
ip_vs_conn_put(cp);
skb->ipvs_property = 1;
LeaveFunction(11);
return NF_ACCEPT;
drop:
ip_vs_conn_put(cp);
kfree_skb(*pskb);
return NF_STOLEN;
}
int ip_options_compile(struct net *net,
struct ip_options * opt, struct sk_buff * skb)
{
int l;
unsigned char * iph;
unsigned char * optptr;
int optlen;
unsigned char * pp_ptr = NULL;
struct rtable *rt = NULL;
if (skb != NULL) {
rt = skb_rtable(skb);
optptr = (unsigned char *)&(ip_hdr(skb)[1]);
} else
optptr = opt->__data;
iph = optptr - sizeof(struct iphdr);
for (l = opt->optlen; l > 0; ) {
switch (*optptr) {
case IPOPT_END:
for (optptr++, l--; l>0; optptr++, l--) {
if (*optptr != IPOPT_END) {
*optptr = IPOPT_END;
opt->is_changed = 1;
}
}
goto eol;
case IPOPT_NOOP:
l--;
optptr++;
continue;
}
optlen = optptr[1];
if (optlen<2 || optlen>l) {
pp_ptr = optptr;
goto error;
}
switch (*optptr) {
case IPOPT_SSRR:
case IPOPT_LSRR:
if (optlen < 3) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 4) {
pp_ptr = optptr + 2;
goto error;
}
/* NB: cf RFC-1812 5.2.4.1 */
if (opt->srr) {
pp_ptr = optptr;
goto error;
}
if (!skb) {
if (optptr[2] != 4 || optlen < 7 || ((optlen-3) & 3)) {
pp_ptr = optptr + 1;
goto error;
}
memcpy(&opt->faddr, &optptr[3], 4);
if (optlen > 7)
memmove(&optptr[3], &optptr[7], optlen-7);
}
opt->is_strictroute = (optptr[0] == IPOPT_SSRR);
opt->srr = optptr - iph;
break;
case IPOPT_RR:
if (opt->rr) {
pp_ptr = optptr;
goto error;
}
if (optlen < 3) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 4) {
pp_ptr = optptr + 2;
goto error;
}
if (optptr[2] <= optlen) {
if (optptr[2]+3 > optlen) {
pp_ptr = optptr + 2;
goto error;
}
if (rt) {
memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
opt->is_changed = 1;
}
optptr[2] += 4;
opt->rr_needaddr = 1;
}
opt->rr = optptr - iph;
break;
case IPOPT_TIMESTAMP:
if (opt->ts) {
pp_ptr = optptr;
goto error;
}
if (optlen < 4) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] < 5) {
pp_ptr = optptr + 2;
goto error;
}
if (optptr[2] <= optlen) {
__be32 *timeptr = NULL;
if (optptr[2]+3 > optptr[1]) {
pp_ptr = optptr + 2;
goto error;
}
switch (optptr[3]&0xF) {
case IPOPT_TS_TSONLY:
opt->ts = optptr - iph;
if (skb)
timeptr = (__be32*)&optptr[optptr[2]-1];
opt->ts_needtime = 1;
optptr[2] += 4;
break;
case IPOPT_TS_TSANDADDR:
if (optptr[2]+7 > optptr[1]) {
pp_ptr = optptr + 2;
goto error;
}
opt->ts = optptr - iph;
if (rt) {
memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
timeptr = (__be32*)&optptr[optptr[2]+3];
}
opt->ts_needaddr = 1;
opt->ts_needtime = 1;
optptr[2] += 8;
break;
case IPOPT_TS_PRESPEC:
if (optptr[2]+7 > optptr[1]) {
pp_ptr = optptr + 2;
goto error;
}
opt->ts = optptr - iph;
{
__be32 addr;
memcpy(&addr, &optptr[optptr[2]-1], 4);
if (inet_addr_type(net, addr) == RTN_UNICAST)
break;
if (skb)
timeptr = (__be32*)&optptr[optptr[2]+3];
}
opt->ts_needtime = 1;
optptr[2] += 8;
break;
default:
if (!skb && !capable(CAP_NET_RAW)) {
pp_ptr = optptr + 3;
goto error;
}
break;
}
if (timeptr) {
struct timespec tv;
__be32 midtime;
getnstimeofday(&tv);
midtime = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC);
memcpy(timeptr, &midtime, sizeof(__be32));
opt->is_changed = 1;
}
} else {
unsigned overflow = optptr[3]>>4;
if (overflow == 15) {
pp_ptr = optptr + 3;
goto error;
}
opt->ts = optptr - iph;
if (skb) {
optptr[3] = (optptr[3]&0xF)|((overflow+1)<<4);
opt->is_changed = 1;
}
}
break;
case IPOPT_RA:
if (optlen < 4) {
pp_ptr = optptr + 1;
goto error;
}
if (optptr[2] == 0 && optptr[3] == 0)
opt->router_alert = optptr - iph;
break;
case IPOPT_CIPSO:
if ((!skb && !capable(CAP_NET_RAW)) || opt->cipso) {
pp_ptr = optptr;
goto error;
}
opt->cipso = optptr - iph;
if (cipso_v4_validate(skb, &optptr)) {
pp_ptr = optptr;
goto error;
}
break;
case IPOPT_SEC:
case IPOPT_SID:
default:
if (!skb && !capable(CAP_NET_RAW)) {
pp_ptr = optptr;
goto error;
}
break;
}
l -= optlen;
optptr += optlen;
}
eol:
if (!pp_ptr)
return 0;
error:
if (skb) {
icmp_send(skb, ICMP_PARAMETERPROB, 0, htonl((pp_ptr-iph)<<24));
}
return -EINVAL;
}
/* Get route to destination or remote server */
static int
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, int rt_mode, __be32 *ret_saddr)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct netns_ipvs *ipvs = net_ipvs(net);
struct ip_vs_dest_dst *dest_dst;
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
struct iphdr *iph;
__be16 df;
int mtu;
int local, noref = 1;
if (dest) {
dest_dst = __ip_vs_dst_check(dest);
if (likely(dest_dst))
rt = (struct rtable *) dest_dst->dst_cache;
else {
dest_dst = ip_vs_dest_dst_alloc();
spin_lock_bh(&dest->dst_lock);
if (!dest_dst) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
goto err_unreach;
}
rt = do_output_route4(net, dest->addr.ip, rt_mode,
&dest_dst->dst_saddr.ip);
if (!rt) {
__ip_vs_dst_set(dest, NULL, NULL, 0);
spin_unlock_bh(&dest->dst_lock);
ip_vs_dest_dst_free(dest_dst);
goto err_unreach;
}
__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
spin_unlock_bh(&dest->dst_lock);
IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
&dest->addr.ip, &dest_dst->dst_saddr.ip,
atomic_read(&rt->dst.__refcnt));
}
daddr = dest->addr.ip;
if (ret_saddr)
*ret_saddr = dest_dst->dst_saddr.ip;
} else {
__be32 saddr = htonl(INADDR_ANY);
noref = 0;
/* For such unconfigured boxes avoid many route lookups
* for performance reasons because we do not remember saddr
*/
rt_mode &= ~IP_VS_RT_MODE_CONNECT;
rt = do_output_route4(net, daddr, rt_mode, &saddr);
if (!rt)
goto err_unreach;
if (ret_saddr)
*ret_saddr = saddr;
}
local = (rt->rt_flags & RTCF_LOCAL) ? 1 : 0;
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
(rt->rt_flags & RTCF_LOCAL) ?
"local":"non-local", &daddr);
goto err_put;
}
iph = ip_hdr(skb);
if (likely(!local)) {
if (unlikely(ipv4_is_loopback(iph->saddr))) {
IP_VS_DBG_RL("Stopping traffic from loopback address "
"%pI4 to non-local address, dest: %pI4\n",
&iph->saddr, &daddr);
goto err_put;
}
} else {
ort = skb_rtable(skb);
if (!(rt_mode & IP_VS_RT_MODE_RDR) &&
!(ort->rt_flags & RTCF_LOCAL)) {
IP_VS_DBG_RL("Redirect from non-local address %pI4 to "
"local requires NAT method, dest: %pI4\n",
&iph->daddr, &daddr);
goto err_put;
}
/* skb to local stack, preserve old route */
if (!noref)
ip_rt_put(rt);
return local;
}
if (likely(!(rt_mode & IP_VS_RT_MODE_TUNNEL))) {
mtu = dst_mtu(&rt->dst);
df = iph->frag_off & htons(IP_DF);
} else {
struct sock *sk = skb->sk;
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto err_put;
}
ort = skb_rtable(skb);
if (!skb->dev && sk && sk->sk_state != TCP_TIME_WAIT)
ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
/* MTU check allowed? */
df = sysctl_pmtu_disc(ipvs) ? iph->frag_off & htons(IP_DF) : 0;
}
/* MTU checking */
if (unlikely(df && skb->len > mtu && !skb_is_gso(skb))) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG(1, "frag needed for %pI4\n", &iph->saddr);
goto err_put;
}
skb_dst_drop(skb);
if (noref) {
if (!local)
skb_dst_set_noref_force(skb, &rt->dst);
else
skb_dst_set(skb, dst_clone(&rt->dst));
} else
skb_dst_set(skb, &rt->dst);
return local;
err_put:
if (!noref)
ip_rt_put(rt);
return -1;
err_unreach:
dst_link_failure(skb);
return -1;
}
static int ipip_tunnel_xmit(struct sk_buff *skb, struct device *dev)
{
struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv;
struct net_device_stats *stats = &tunnel->stat;
struct iphdr *tiph = &tunnel->parms.iph;
u8 tos = tunnel->parms.iph.tos;
u16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct device *tdev; /* Device to other host */
struct iphdr *old_iph = skb->nh.iph;
struct iphdr *iph; /* Our new IP header */
int max_headroom; /* The extra header space needed */
u32 dst = tiph->daddr;
int mtu;
if (tunnel->recursion++) {
tunnel->stat.collisions++;
goto tx_error;
}
if (skb->protocol != __constant_htons(ETH_P_IP))
goto tx_error;
if (tos&1)
tos = old_iph->tos;
if (!dst) {
/* NBMA tunnel */
if ((rt = (struct rtable*)skb->dst) == NULL) {
tunnel->stat.tx_fifo_errors++;
goto tx_error;
}
if ((dst = rt->rt_gateway) == 0)
goto tx_error_icmp;
}
if (ip_route_output(&rt, dst, tiph->saddr, RT_TOS(tos), tunnel->parms.link)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
tunnel->stat.collisions++;
goto tx_error;
}
mtu = rt->u.dst.pmtu - sizeof(struct iphdr);
if (mtu < 68) {
tunnel->stat.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (skb->dst && mtu < skb->dst->pmtu)
skb->dst->pmtu = mtu;
df |= (old_iph->frag_off&__constant_htons(IP_DF));
if ((old_iph->frag_off&__constant_htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
skb->h.raw = skb->nh.raw;
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = (((tdev->hard_header_len+15)&~15)+sizeof(struct iphdr));
if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
}
skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/*
* Push down and install the IPIP header.
*/
iph = skb->nh.iph;
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = old_iph->ttl;
iph->tot_len = htons(skb->len);
iph->id = htons(ip_id_count++);
ip_send_check(iph);
stats->tx_bytes += skb->len;
stats->tx_packets++;
ip_send(skb);
tunnel->recursion--;
return 0;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
void * arp_queue_caretaker(void * router){
struct sr_instance * sr = router;
while(TRUE)
{
// walk the packet queue, send and clear any that are sendable
rmutex_lock(&sr->arp_queue_lock);
for(int i = 0; i < OUTSTANDING_ARP_LIMIT; i++)
{
if (sr->pq[i].payload)
{
addr_mac_t result;
if (arp_table_get_entry(sr,sr->pq[i].ip,&result))
{
Debug("found destination in arp cache, sending packet\n");
memcpy(sr->pq[i].payload,&result,ETHER_ADDR_LEN);
sr_send_packet(sr,sr->pq[i].payload,sr->pq[i].payload_len,sr->pq[i].iface);
free(sr->pq[i].payload);
sr->pq[i].payload = NULL;
continue;
}
// last chance failed, drop this packet
else if (sr->pq[i].expiry < time(NULL))
{
// grab the pointer so we can send the icmp error,
// but free up the outgoing IP packet cache entry
uint8_t * buf = sr->pq[i].payload;
sr->pq[i].payload = NULL;
Debug("sending icmp host unreach on arp timeout\n");
// send ICMP HOST UNREACH back to sender to inform
// them that we cannot route this packet
uint32_t dst = ((struct ip *)(buf + sizeof(struct sr_ethernet_hdr)))->ip_src.s_addr;
icmp_send(sr,dst,0,buf + sizeof(struct sr_ethernet_hdr),sr->pq[i].payload_len - sizeof(struct sr_ethernet_hdr),ICMP_TYPE_DEST_UNREACH,ICMP_CODE_HOST_UNREACH,0,0);
free(buf);
}
}
}
// walk the pending arp request queue, sending or deleting entries
// as necessary
for(int i = 0; i < OUTSTANDING_ARP_LIMIT; i++)
{
// clear entries that responses have been found for
addr_mac_t ret;
if (sr->aq[i].ip && arp_table_get_entry(sr,sr->aq[i].ip,&ret))
{
sr->aq[i].ip = 0;
continue;
}
if (sr->aq[i].ip != 0 && sr->aq[i].expiry < time(NULL))
{
if(sr->aq[i].req_remaining-- < 1)
{
// done trying this one, fail
sr->aq[i].ip = 0;
continue;
}
// reset the time remaining
sr->aq[i].expiry = time(NULL) + ARP_TIMEOUT;
// send an ARP request for this packet
int len = sizeof(struct sr_ethernet_hdr) + sizeof(struct sr_arphdr);
uint8_t * buf = malloc(len);
memset(buf,0,len);
Debug("crafting arp packet from %s\n",sr->aq[i].iface);
addr_mac_t saddr = sr_get_interface(sr,sr->aq[i].iface)->addr;
uint32_t src_ip = sr_get_interface(sr,sr->aq[i].iface)->ip;
struct sr_ethernet_hdr * eh = (struct sr_ethernet_hdr *)buf;
struct sr_arphdr * ah = (struct sr_arphdr *) (buf + sizeof(struct sr_ethernet_hdr));
// set ethernet fields
eh->ether_shost = saddr;
memset(&eh->ether_dhost,0xFF,ETHER_ADDR_LEN);
eh->ether_type = htons(ETHERTYPE_ARP);
// set arp fields
ah->ar_hrd = htons(ARPHDR_ETHER);
ah->ar_pro = htons(ETHERTYPE_IP);
ah->ar_hln = 6;
ah->ar_pln = 4;
ah->ar_op = htons(ARP_REQUEST);
ah->ar_sha = saddr;
ah->ar_sip = src_ip;
ah->ar_tip = sr->aq[i].ip;
memset(&ah->ar_tha,0,ETHER_ADDR_LEN);
Debug("sr_send_packet sending arp request out interface %s with length %d\n",sr->aq[i].iface,len);
sr_send_packet(sr,buf,len,sr->aq[i].iface);
free(buf);
}
}
rmutex_unlock(&sr->arp_queue_lock);
sleep(1);
}
return NULL;
}
/*
* ICMP packet transmitter
* called by the ip_vs_in_icmp
*/
int
ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset)
{
struct rtable *rt; /* Route to the other host */
int mtu;
int rc;
int local;
EnterFunction(10);
/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
forwarded directly here, because there is no need to
translate address/port back */
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
if (cp->packet_xmit)
rc = cp->packet_xmit(skb, cp, pp);
else
rc = NF_ACCEPT;
/* do not touch skb anymore */
atomic_inc_unchecked(&cp->in_pkts);
goto out;
}
/*
* mangle and send the packet here (only for VS/NAT)
*/
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(ip_hdr(skb)->tos),
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
* Avoid duplicate tuple in reply direction for NAT traffic
* to local address when connection is sync-ed
*/
#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
if (cp->flags & IP_VS_CONN_F_SYNC && local) {
enum ip_conntrack_info ctinfo;
struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
if (ct && !nf_ct_is_untracked(ct)) {
IP_VS_DBG(10, "%s(): "
"stopping DNAT to local address %pI4\n",
__func__, &cp->daddr.ip);
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(rt->rt_dst) &&
rt_is_input_route(skb_rtable(skb))) {
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI4\n",
__func__, &cp->daddr.ip);
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) &&
!skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, offset))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
ip_vs_nat_icmp(skb, pp, cp, 0);
if (!local) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
ip_rt_put(rt);
/*
* Some IPv4 replies get local address from routes,
* not from iph, so while we DNAT after routing
* we need this second input/output route.
*/
if (!__ip_vs_reroute_locally(skb))
goto tx_error;
}
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
rc = NF_STOLEN;
goto out;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev_kfree_skb(skb);
rc = NF_STOLEN;
out:
LeaveFunction(10);
return rc;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
static unsigned int ipt_route_target(struct sk_buff **pskb,
const struct net_device *in,
const struct net_device *out,
unsigned int hooknum,
const void *targinfo,
void *userinfo)
{
const struct ipt_route_target_info *route_info = targinfo;
struct sk_buff *skb = *pskb;
unsigned int res;
if (skb->nfct == &route_tee_track.ct_general) {
/* Loopback - a packet we already routed, is to be
* routed another time. Avoid that, now.
*/
if (net_ratelimit())
DEBUGP(KERN_DEBUG "ipt_ROUTE: loopback - DROP!\n");
return NF_DROP;
}
/* If we are at PREROUTING or INPUT hook
* the TTL isn't decreased by the IP stack
*/
if (hooknum == NF_IP_PRE_ROUTING ||
hooknum == NF_IP_LOCAL_IN) {
struct iphdr *iph = skb->nh.iph;
if (iph->ttl <= 1) {
struct rtable *rt;
struct flowi fl = {
.oif = 0,
.nl_u = {
.ip4_u = {
.daddr = iph->daddr,
.saddr = iph->saddr,
.tos = RT_TOS(iph->tos),
.scope = ((iph->tos & RTO_ONLINK) ?
RT_SCOPE_LINK :
RT_SCOPE_UNIVERSE)
}
}
};
if (ip_route_output_key(&rt, &fl)) {
return NF_DROP;
}
if (skb->dev == rt->u.dst.dev) {
/* Drop old route. */
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/* this will traverse normal stack, and
* thus call conntrack on the icmp packet */
icmp_send(skb, ICMP_TIME_EXCEEDED,
ICMP_EXC_TTL, 0);
}
return NF_DROP;
}
/*
* If we are at INPUT the checksum must be recalculated since
* the length could change as the result of a defragmentation.
*/
if(hooknum == NF_IP_LOCAL_IN) {
iph->ttl = iph->ttl - 1;
iph->check = 0;
iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
} else {
ip_decrease_ttl(iph);
}
}
if ((route_info->flags & IPT_ROUTE_TEE)) {
/*
* Copy the *pskb, and route the copy. Will later return
* IPT_CONTINUE for the original skb, which should continue
* on its way as if nothing happened. The copy should be
* independantly delivered to the ROUTE --gw.
*/
skb = skb_copy(*pskb, GFP_ATOMIC);
if (!skb) {
if (net_ratelimit())
DEBUGP(KERN_DEBUG "ipt_ROUTE: copy failed!\n");
return IPT_CONTINUE;
}
}
/* Tell conntrack to forget this packet since it may get confused
* when a packet is leaving with dst address == our address.
* Good idea ? Dunno. Need advice.
*
* NEW: mark the skb with our &route_tee_track, so we avoid looping
* on any already routed packet.
*/
if (!(route_info->flags & IPT_ROUTE_CONTINUE)) {
nf_conntrack_put(skb->nfct);
skb->nfct = &route_tee_track.ct_general;
skb->nfctinfo = IP_CT_NEW;
nf_conntrack_get(skb->nfct);
skb->nfcache = 0;
#ifdef CONFIG_NETFILTER_DEBUG
skb->nf_debug = 0;
#endif
}
if (route_info->oif[0] != '\0') {
res = route_oif(route_info, skb);
} else if (route_info->iif[0] != '\0') {
res = route_iif(route_info, skb);
} else if (route_info->gw) {
res = route_gw(route_info, skb);
} else {
if (net_ratelimit())
DEBUGP(KERN_DEBUG "ipt_ROUTE: no parameter !\n");
res = IPT_CONTINUE;
}
if ((route_info->flags & IPT_ROUTE_TEE))
res = IPT_CONTINUE;
return res;
}
/*
* IP Tunneling transmitter
*
* This function encapsulates the packet in a new IP packet, its
* destination will be set to cp->daddr. Most code of this function
* is taken from ipip.c.
*
* It is used in VS/TUN cluster. The load balancer selects a real
* server from a cluster based on a scheduling algorithm,
* encapsulates the request packet and forwards it to the selected
* server. For example, all real servers are configured with
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
* the encapsulated packet, it will decapsulate the packet, processe
* the request and return the response packets directly to the client
* without passing the load balancer. This can greatly increase the
* scalability of virtual server.
*
* Used for ANY protocol
*/
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df = old_iph->frag_off;
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int mtu;
int ret;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
df |= (old_iph->frag_off & htons(IP_DF));
if ((old_iph->frag_off & htons(IP_DF) &&
mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom
|| skb_cloned(skb) || skb_shared(skb)) {
struct sk_buff *new_skb =
skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
kfree_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
skb->transport_header = skb->network_header;
/* fix old IP header checksum */
ip_send_check(old_iph);
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
iph->ttl = old_iph->ttl;
ip_select_ident(iph, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip_local_out(skb);
else if (ret == NF_DROP)
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
static int ip_local_deliver_finish(struct sk_buff *skb)
{
struct net *net = dev_net(skb->dev);
__skb_pull(skb, ip_hdrlen(skb));
/* Point into the IP datagram, just past the header. */
skb_reset_transport_header(skb);
rcu_read_lock();
{
int protocol = ip_hdr(skb)->protocol;
int hash, raw;
const struct net_protocol *ipprot;
resubmit:
raw = raw_local_deliver(skb, protocol);
hash = protocol & (MAX_INET_PROTOS - 1);
ipprot = rcu_dereference(inet_protos[hash]);
if (ipprot != NULL) {
int ret;
if (!net_eq(net, &init_net) && !ipprot->netns_ok) {
if (net_ratelimit())
printk("%s: proto %d isn't netns-ready\n",
__func__, protocol);
kfree_skb(skb);
goto out;
}
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
goto out;
}
nf_reset(skb);
}
ret = ipprot->handler(skb);
if (ret < 0) {
protocol = -ret;
goto resubmit;
}
IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
} else {
if (!raw) {
if (xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
IP_INC_STATS_BH(net, IPSTATS_MIB_INUNKNOWNPROTOS);
icmp_send(skb, ICMP_DEST_UNREACH,
ICMP_PROT_UNREACH, 0);
}
} else
IP_INC_STATS_BH(net, IPSTATS_MIB_INDELIVERS);
kfree_skb(skb);
}
}
out:
rcu_read_unlock();
return 0;
}
