static void xfrm4_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (dst->xfrm && dst->xfrm->props.family == AF_INET && likely(xdst->u.rt.peer))
inet_putpeer(xdst->u.rt.peer);
xfrm_dst_destroy(xdst);
}
static __inline__ void ip4_frag_free(struct inet_frag_queue *q)
{
struct ipq *qp;
qp = container_of(q, struct ipq, q);
if (qp->peer)
inet_putpeer(qp->peer);
}
static void xfrm4_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (likely(xdst->u.rt.idev))
in_dev_put(xdst->u.rt.idev);
if (likely(xdst->u.rt.peer))
inet_putpeer(xdst->u.rt.peer);
xfrm_dst_destroy(xdst);
}
static void xfrm4_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
dst_destroy_metrics_generic(dst);
if (likely(xdst->u.rt.peer))
inet_putpeer(xdst->u.rt.peer);
xfrm_dst_destroy(xdst);
}
static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
if (likely(xdst->u.rt6.rt6i_peer))
inet_putpeer(xdst->u.rt6.rt6i_peer);
xfrm_dst_destroy(xdst);
}
static void xfrm6_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
if (likely(xdst->u.rt6.rt6i_idev))
in6_dev_put(xdst->u.rt6.rt6i_idev);
dst_destroy_metrics_generic(dst);
if (rt6_has_peer(&xdst->u.rt6)) {
struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6);
inet_putpeer(peer);
}
xfrm_dst_destroy(xdst);
}
int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
u32 mtu;
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
if (skb->pkt_type != PACKET_HOST)
goto drop;
if (unlikely(skb->sk))
goto drop;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
skb_forward_csum(skb);
/*
* We DO NOT make any processing on
* RA packets, pushing them to user level AS IS
* without ane WARRANTY that application will be able
* to interpret them. The reason is that we
* cannot make anything clever here.
*
* We are not end-node, so that if packet contains
* AH/ESP, we cannot make anything.
* Defragmentation also would be mistake, RA packets
* cannot be fragmented, because there is no warranty
* that different fragments will go along one path. --ANK
*/
if (unlikely(opt->flags & IP6SKB_ROUTERALERT)) {
if (ip6_call_ra_chain(skb, ntohs(opt->ra)))
return 0;
}
/*
* check and decrement ttl
*/
if (hdr->hop_limit <= 1) {
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INHDRERRORS);
kfree_skb(skb);
return -ETIMEDOUT;
}
/* XXX: idev->cnf.proxy_ndp? */
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
if (proxied > 0)
return ip6_input(skb);
else if (proxied < 0) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
}
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
dst = skb_dst(skb);
/* IPv6 specs say nothing about it, but it is clear that we cannot
send redirects to source routed frames.
We don't send redirects to frames decapsulated from IPsec.
*/
if (skb->dev == dst->dev && opt->srcrt == 0 && !skb_sec_path(skb)) {
struct in6_addr *target = NULL;
struct inet_peer *peer;
struct rt6_info *rt;
/*
* incoming and outgoing devices are the same
* send a redirect.
*/
rt = (struct rt6_info *) dst;
if (rt->rt6i_flags & RTF_GATEWAY)
target = &rt->rt6i_gateway;
else
target = &hdr->daddr;
peer = inet_getpeer_v6(net->ipv6.peers, &hdr->daddr, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (inet_peer_xrlim_allow(peer, 1*HZ))
ndisc_send_redirect(skb, target);
if (peer)
inet_putpeer(peer);
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
/* This check is security critical. */
if (addrtype == IPV6_ADDR_ANY ||
addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
goto error;
if (addrtype & IPV6_ADDR_LINKLOCAL) {
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
ICMPV6_NOT_NEIGHBOUR, 0);
goto error;
}
}
mtu = ip6_dst_mtu_forward(dst);
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (ip6_pkt_too_big(skb, mtu)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_INTOOBIGERRORS);
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (skb_cow(skb, dst->dev->hard_header_len)) {
IP6_INC_STATS_BH(net, ip6_dst_idev(dst),
IPSTATS_MIB_OUTDISCARDS);
goto drop;
}
hdr = ipv6_hdr(skb);
/* Mangling hops number delayed to point after skb COW */
hdr->hop_limit--;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len);
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
net, NULL, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
drop:
kfree_skb(skb);
return -EINVAL;
}
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr)
{
struct flowi4 fl4 = {
.daddr = daddr->a4,
.flowi4_tos = tos,
};
struct rtable *rt;
if (saddr)
fl4.saddr = saddr->a4;
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt))
return &rt->dst;
return ERR_CAST(rt);
}
static int xfrm4_get_saddr(struct net *net,
xfrm_address_t *saddr, xfrm_address_t *daddr)
{
struct dst_entry *dst;
struct rtable *rt;
dst = xfrm4_dst_lookup(net, 0, NULL, daddr);
if (IS_ERR(dst))
return -EHOSTUNREACH;
rt = (struct rtable *)dst;
saddr->a4 = rt->rt_src;
dst_release(dst);
return 0;
}
static int xfrm4_get_tos(const struct flowi *fl)
{
return IPTOS_RT_MASK & fl->u.ip4.flowi4_tos; /* Strip ECN bits */
}
static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst,
int nfheader_len)
{
return 0;
}
static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
const struct flowi *fl)
{
struct rtable *rt = (struct rtable *)xdst->route;
const struct flowi4 *fl4 = &fl->u.ip4;
rt->rt_key_dst = fl4->daddr;
rt->rt_key_src = fl4->saddr;
rt->rt_tos = fl4->flowi4_tos;
rt->rt_iif = fl4->flowi4_iif;
rt->rt_oif = fl4->flowi4_oif;
rt->rt_mark = fl4->flowi4_mark;
xdst->u.dst.dev = dev;
dev_hold(dev);
xdst->u.rt.peer = rt->peer;
if (rt->peer)
atomic_inc(&rt->peer->refcnt);
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
xdst->u.rt.rt_src = rt->rt_src;
xdst->u.rt.rt_dst = rt->rt_dst;
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_spec_dst = rt->rt_spec_dst;
return 0;
}
static void
_decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
{
struct iphdr *iph = ip_hdr(skb);
u8 *xprth = skb_network_header(skb) + iph->ihl * 4;
struct flowi4 *fl4 = &fl->u.ip4;
memset(fl4, 0, sizeof(struct flowi4));
fl4->flowi4_mark = skb->mark;
if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) {
switch (iph->protocol) {
case IPPROTO_UDP:
case IPPROTO_UDPLITE:
case IPPROTO_TCP:
case IPPROTO_SCTP:
case IPPROTO_DCCP:
if (xprth + 4 < skb->data ||
pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ports = (__be16 *)xprth;
fl4->fl4_sport = ports[!!reverse];
fl4->fl4_dport = ports[!reverse];
}
break;
case IPPROTO_ICMP:
if (pskb_may_pull(skb, xprth + 2 - skb->data)) {
u8 *icmp = xprth;
fl4->fl4_icmp_type = icmp[0];
fl4->fl4_icmp_code = icmp[1];
}
break;
case IPPROTO_ESP:
if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be32 *ehdr = (__be32 *)xprth;
fl4->fl4_ipsec_spi = ehdr[0];
}
break;
case IPPROTO_AH:
if (pskb_may_pull(skb, xprth + 8 - skb->data)) {
__be32 *ah_hdr = (__be32*)xprth;
fl4->fl4_ipsec_spi = ah_hdr[1];
}
break;
case IPPROTO_COMP:
if (pskb_may_pull(skb, xprth + 4 - skb->data)) {
__be16 *ipcomp_hdr = (__be16 *)xprth;
fl4->fl4_ipsec_spi = htonl(ntohs(ipcomp_hdr[1]));
}
break;
case IPPROTO_GRE:
if (pskb_may_pull(skb, xprth + 12 - skb->data)) {
__be16 *greflags = (__be16 *)xprth;
__be32 *gre_hdr = (__be32 *)xprth;
if (greflags[0] & GRE_KEY) {
if (greflags[0] & GRE_CSUM)
gre_hdr++;
fl4->fl4_gre_key = gre_hdr[1];
}
}
break;
default:
fl4->fl4_ipsec_spi = 0;
break;
}
}
fl4->flowi4_proto = iph->protocol;
fl4->daddr = reverse ? iph->saddr : iph->daddr;
fl4->saddr = reverse ? iph->daddr : iph->saddr;
fl4->flowi4_tos = iph->tos;
}
static inline int xfrm4_garbage_collect(struct dst_ops *ops)
{
struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
xfrm4_policy_afinfo.garbage_collect(net);
return (dst_entries_get_slow(ops) > ops->gc_thresh * 2);
}
static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
struct dst_entry *path = xdst->route;
path->ops->update_pmtu(path, mtu);
}
static void xfrm4_dst_destroy(struct dst_entry *dst)
{
struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
dst_destroy_metrics_generic(dst);
if (likely(xdst->u.rt.peer))
inet_putpeer(xdst->u.rt.peer);
xfrm_dst_destroy(xdst);
}
static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int unregister)
{
if (!unregister)
return;
xfrm_dst_ifdown(dst, dev);
}
static struct dst_ops xfrm4_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.gc = xfrm4_garbage_collect,
.update_pmtu = xfrm4_update_pmtu,
.cow_metrics = dst_cow_metrics_generic,
.destroy = xfrm4_dst_destroy,
.ifdown = xfrm4_dst_ifdown,
.local_out = __ip_local_out,
.gc_thresh = 1024,
};
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.family = AF_INET,
.dst_ops = &xfrm4_dst_ops,
.dst_lookup = xfrm4_dst_lookup,
.get_saddr = xfrm4_get_saddr,
.decode_session = _decode_session4,
.get_tos = xfrm4_get_tos,
.init_path = xfrm4_init_path,
.fill_dst = xfrm4_fill_dst,
.blackhole_route = ipv4_blackhole_route,
};
#ifdef CONFIG_SYSCTL
static struct ctl_table xfrm4_policy_table[] = {
{
.procname = "xfrm4_gc_thresh",
.data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
