/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
struct ip_vs_conn *cp, int local)
{
int ret = NF_STOLEN;
skb->ipvs_property = 1;
if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
ip_vs_notrack(skb);
else
ip_vs_update_conntrack(skb, cp, 1);
/* Remove the early_demux association unless it's bound for the
* exact same port and address on this host after translation.
*/
if (!local || cp->vport != cp->dport ||
!ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr))
ip_vs_drop_early_demux_sk(skb);
if (!local) {
skb_forward_csum(skb);
if (!skb->sk)
skb_sender_cpu_clear(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
NULL, skb_dst(skb)->dev, dst_output_sk);
} else
ret = NF_ACCEPT;
return ret;
}
/* return NF_ACCEPT to allow forwarding or other NF_xxx on error */
static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
struct ip_vs_conn *cp)
{
int ret = NF_ACCEPT;
skb->ipvs_property = 1;
if (unlikely(cp->flags & IP_VS_CONN_F_NFCT))
ret = ip_vs_confirm_conntrack(skb);
if (ret == NF_ACCEPT) {
nf_reset(skb);
skb_forward_csum(skb);
}
return ret;
}
/* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
struct ip_vs_conn *cp, int local)
{
int ret = NF_STOLEN;
skb->ipvs_property = 1;
if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
ip_vs_notrack(skb);
if (!local) {
skb_forward_csum(skb);
NF_HOOK(pf, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
dst_output);
} else
ret = NF_ACCEPT;
return ret;
}
static void __vnsw_forward(const struct vnsw_if *to, struct sk_buff *skb)
{
struct net_device *indev;
if (skb_warn_if_lro(skb)) {
kfree_skb(skb);
return;
}
indev = skb->dev;
skb->dev = to->dev;
skb_forward_csum(skb);
NF_HOOK(NFPROTO_BRIDGE, NF_BR_FORWARD, skb, indev, skb->dev,
vnsw_forward_finish);
}
static int mpls_xmit(struct sk_buff *skb)
{
struct mpls_iptunnel_encap *tun_encap_info;
struct mpls_shim_hdr *hdr;
struct net_device *out_dev;
unsigned int hh_len;
unsigned int new_header_size;
unsigned int mtu;
struct dst_entry *dst = skb_dst(skb);
struct rtable *rt = NULL;
struct rt6_info *rt6 = NULL;
int err = 0;
bool bos;
int i;
unsigned int ttl;
/* Obtain the ttl */
if (dst->ops->family == AF_INET) {
ttl = ip_hdr(skb)->ttl;
rt = (struct rtable *)dst;
} else if (dst->ops->family == AF_INET6) {
ttl = ipv6_hdr(skb)->hop_limit;
rt6 = (struct rt6_info *)dst;
} else {
goto drop;
}
skb_orphan(skb);
/* Find the output device */
out_dev = dst->dev;
if (!mpls_output_possible(out_dev) ||
!dst->lwtstate || skb_warn_if_lro(skb))
goto drop;
skb_forward_csum(skb);
tun_encap_info = mpls_lwtunnel_encap(dst->lwtstate);
/* Verify the destination can hold the packet */
new_header_size = mpls_encap_size(tun_encap_info);
mtu = mpls_dev_mtu(out_dev);
if (mpls_pkt_too_big(skb, mtu - new_header_size))
goto drop;
hh_len = LL_RESERVED_SPACE(out_dev);
if (!out_dev->header_ops)
hh_len = 0;
/* Ensure there is enough space for the headers in the skb */
if (skb_cow(skb, hh_len + new_header_size))
goto drop;
skb_set_inner_protocol(skb, skb->protocol);
skb_reset_inner_network_header(skb);
skb_push(skb, new_header_size);
skb_reset_network_header(skb);
skb->dev = out_dev;
skb->protocol = htons(ETH_P_MPLS_UC);
/* Push the new labels */
hdr = mpls_hdr(skb);
bos = true;
for (i = tun_encap_info->labels - 1; i >= 0; i--) {
hdr[i] = mpls_entry_encode(tun_encap_info->label[i],
ttl, 0, bos);
bos = false;
}
if (rt)
err = neigh_xmit(NEIGH_ARP_TABLE, out_dev, &rt->rt_gateway,
skb);
else if (rt6)
err = neigh_xmit(NEIGH_ND_TABLE, out_dev, &rt6->rt6i_gateway,
skb);
if (err)
net_dbg_ratelimited("%s: packet transmission failed: %d\n",
__func__, err);
return LWTUNNEL_XMIT_DONE;
drop:
kfree_skb(skb);
return -EINVAL;
}
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);
struct neighbour *n;
u32 mtu;
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
if (skb->pkt_type != PACKET_HOST)
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 (opt->ra) {
u8 *ptr = skb_network_header(skb) + opt->ra;
if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
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(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
}
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS(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.
*/
n = dst_get_neighbour(dst);
if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) {
struct in6_addr *target = NULL;
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 = (struct in6_addr*)&n->primary_key;
else
target = &hdr->daddr;
if (!rt->rt6i_peer)
rt6_bind_peer(rt, 1);
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
ndisc_send_redirect(skb, n, target);
} 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 = dst_mtu(dst);
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb->len > mtu && !skb_is_gso(skb)) {
/* 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(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);
return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, 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;
}
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;
}
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;
}
static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct net *net = dev_net(dev);
struct mpls_shim_hdr *hdr;
struct mpls_route *rt;
struct mpls_entry_decoded dec;
struct net_device *out_dev;
struct mpls_dev *mdev;
unsigned int hh_len;
unsigned int new_header_size;
unsigned int mtu;
int err;
/* Careful this entire function runs inside of an rcu critical section */
mdev = mpls_dev_get(dev);
if (!mdev || !mdev->input_enabled)
goto drop;
if (skb->pkt_type != PACKET_HOST)
goto drop;
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
goto drop;
if (!pskb_may_pull(skb, sizeof(*hdr)))
goto drop;
/* Read and decode the label */
hdr = mpls_hdr(skb);
dec = mpls_entry_decode(hdr);
/* Pop the label */
skb_pull(skb, sizeof(*hdr));
skb_reset_network_header(skb);
skb_orphan(skb);
rt = mpls_route_input_rcu(net, dec.label);
if (!rt)
goto drop;
/* Find the output device */
out_dev = rcu_dereference(rt->rt_dev);
if (!mpls_output_possible(out_dev))
goto drop;
if (skb_warn_if_lro(skb))
goto drop;
skb_forward_csum(skb);
/* Verify ttl is valid */
if (dec.ttl <= 1)
goto drop;
dec.ttl -= 1;
/* Verify the destination can hold the packet */
new_header_size = mpls_rt_header_size(rt);
mtu = mpls_dev_mtu(out_dev);
if (mpls_pkt_too_big(skb, mtu - new_header_size))
goto drop;
hh_len = LL_RESERVED_SPACE(out_dev);
if (!out_dev->header_ops)
hh_len = 0;
/* Ensure there is enough space for the headers in the skb */
if (skb_cow(skb, hh_len + new_header_size))
goto drop;
skb->dev = out_dev;
skb->protocol = htons(ETH_P_MPLS_UC);
if (unlikely(!new_header_size && dec.bos)) {
/* Penultimate hop popping */
if (!mpls_egress(rt, skb, dec))
goto drop;
} else {
bool bos;
int i;
skb_push(skb, new_header_size);
skb_reset_network_header(skb);
/* Push the new labels */
hdr = mpls_hdr(skb);
bos = dec.bos;
for (i = rt->rt_labels - 1; i >= 0; i--) {
hdr[i] = mpls_entry_encode(rt->rt_label[i], dec.ttl, 0, bos);
bos = false;
}
}
err = neigh_xmit(rt->rt_via_table, out_dev, rt->rt_via, skb);
if (err)
net_dbg_ratelimited("%s: packet transmission failed: %d\n",
__func__, err);
return 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);
#ifdef CONFIG_NETFILTER_TABLE_INDEX
int verdict;
#endif
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);
#ifdef CONFIG_AS_FASTPATH
/* ToS in route table is not actually that is in packet */
_route_add_hook(rt, iph->tos);
#endif
/* 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);
#ifdef CONFIG_NETFILTER_TABLE_INDEX
verdict = match_netfilter_table_index(
NFPROTO_IPV4, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
p_netfilter_table_index);
if (-1 == verdict) /* not found, go along the old path */
return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
else{
if (verdict == NF_ACCEPT || verdict == NF_STOP)
return ip_forward_finish(skb);
else
goto drop;
/* We only recorded 3 kinds of results,
* NF_ACCEPT, NF_STOP, NF DROP.
* NF_DROP will be processed.
* we don't accelorate NF_QUEUE
*/
}
#endif /* end CONFIG_NETFILTER_TABLE_INDEX */
return NF_HOOK(NFPROTO_IPV4, 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;
}