/* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct flowi fl;
memset(&fl, 0, sizeof(fl));
switch (skb->protocol) {
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
break;
case htons(ETH_P_IPV6):
xfrm_decode_session(skb, &fl, AF_INET6);
memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
break;
default:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
/* override mark with tunnel output key */
fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
return vti_xmit(skb, dev, &fl);
}
int ip_xfrm_me_harder(struct sk_buff *skb)
{
struct flowi fl;
unsigned int hh_len;
struct dst_entry *dst;
if (IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
return 0;
if (xfrm_decode_session(skb, &fl, AF_INET) < 0)
return -1;
dst = skb->dst;
if (dst->xfrm)
dst = ((struct xfrm_dst *)dst)->route;
dst_hold(dst);
if (xfrm_lookup(&dst, &fl, skb->sk, 0) < 0)
return -1;
dst_release(skb->dst);
skb->dst = dst;
/* Change in oif may mean change in hh_len. */
hh_len = skb->dst->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
return -1;
return 0;
}
int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family)
{
struct flowi fl;
unsigned int hh_len;
struct dst_entry *dst;
int err;
err = xfrm_decode_session(skb, &fl, family);
if (err < 0)
return err;
dst = skb_dst(skb);
if (dst->xfrm)
dst = ((struct xfrm_dst *)dst)->route;
dst_hold(dst);
dst = xfrm_lookup(net, dst, &fl, skb->sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_dst_drop(skb);
skb_dst_set(skb, dst);
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
return -ENOMEM;
return 0;
}
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
struct net *net = dev_net(skb_dst(skb)->dev);
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4 = {};
__be32 saddr = iph->saddr;
__u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
unsigned int hh_len;
if (addr_type == RTN_UNSPEC)
addr_type = inet_addr_type(net, saddr);
if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
flags |= FLOWI_FLAG_ANYSRC;
else
saddr = 0;
/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
* packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
*/
fl4.daddr = iph->daddr;
fl4.saddr = saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
fl4.flowi4_mark = skb->mark;
fl4.flowi4_flags = flags;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return -1;
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
if (skb_dst(skb)->error)
return -1;
#ifdef CONFIG_XFRM
if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
struct dst_entry *dst = skb_dst(skb);
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
if (IS_ERR(dst))
return -1;
skb_dst_set(skb, dst);
}
#endif
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
0, GFP_ATOMIC))
return -1;
return 0;
}
int ip6_route_me_harder(struct sk_buff *skb)
{
struct ipv6hdr *iph = skb->nh.ipv6h;
struct dst_entry *dst;
struct flowi fl = {
.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.iif = ((struct inet6_skb_parm *)skb->cb)->iif,
.nl_u =
{ .ip6_u =
{ .daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = (* (__u32 *) iph)&IPV6_FLOWINFO_MASK, } },
};
dst = ip6_route_output(skb->sk, &fl);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, &fl, AF_INET6) == 0)
if (xfrm_lookup(&skb->dst, &fl, skb->sk, 0))
return -1;
#endif
if (dst->error) {
#ifdef CONFIG_IPV6_STATISTICS
struct inet6_dev *idev = ((struct rt6_info *)dst)->rt6i_idev;
IP6_INC_STATS(idev, IPSTATS_MIB_OUTNOROUTES);
#else
IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
#endif
LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
dst_release(dst);
return -EINVAL;
}
/* Drop old route. */
dst_release(skb->dst);
skb->dst = dst;
return 0;
}
int ip6_route_me_harder(struct sk_buff *skb)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct ipv6hdr *iph = ipv6_hdr(skb);
struct dst_entry *dst;
struct flowi fl = {
.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.mark = skb->mark,
.nl_u =
{ .ip6_u =
{ .daddr = iph->daddr,
.saddr = iph->saddr, } },
};
dst = ip6_route_output(net, skb->sk, &fl);
if (dst->error) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
dst_release(dst);
return -EINVAL;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, dst);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, &fl, AF_INET6) == 0) {
skb_dst_set(skb, NULL);
if (xfrm_lookup(net, &dst, &fl, skb->sk, 0))
return -1;
skb_dst_set(skb, dst);
}
#endif
return 0;
}
int ip_xfrm_me_harder(struct sk_buff **pskb)
{
struct flowi fl;
unsigned int hh_len;
struct dst_entry *dst;
if (IPCB(*pskb)->flags & IPSKB_XFRM_TRANSFORMED)
return 0;
if (xfrm_decode_session(*pskb, &fl, AF_INET) < 0)
return -1;
dst = (*pskb)->dst;
if (dst->xfrm)
dst = ((struct xfrm_dst *)dst)->route;
dst_hold(dst);
if (xfrm_lookup(&dst, &fl, (*pskb)->sk, 0) < 0)
return -1;
dst_release((*pskb)->dst);
(*pskb)->dst = dst;
/* Change in oif may mean change in hh_len. */
hh_len = (*pskb)->dst->dev->hard_header_len;
if (skb_headroom(*pskb) < hh_len) {
struct sk_buff *nskb;
nskb = skb_realloc_headroom(*pskb, hh_len);
if (!nskb)
return -1;
if ((*pskb)->sk)
skb_set_owner_w(nskb, (*pskb)->sk);
kfree_skb(*pskb);
*pskb = nskb;
}
return 0;
}
int ip6_route_me_harder(struct sk_buff *skb)
{
struct ipv6hdr *iph = skb->nh.ipv6h;
struct dst_entry *dst;
struct flowi fl = {
.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.nl_u =
{ .ip6_u =
{ .daddr = iph->daddr,
.saddr = iph->saddr,
}
},
};
dst = ip6_route_output(skb->sk, &fl);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, &fl, AF_INET6) == 0)
if (xfrm_lookup(&skb->dst, &fl, skb->sk, 0))
return -1;
#endif
if (dst->error) {
IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
dst_release(dst);
return -EINVAL;
}
/* Drop old route. */
dst_release(skb->dst);
skb->dst = dst;
return 0;
}
int ip6_route_me_harder(struct sk_buff *skb)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct ipv6hdr *iph = ipv6_hdr(skb);
struct dst_entry *dst;
struct flowi fl = {
.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.mark = skb->mark,
.fl6_dst = iph->daddr,
.fl6_src = iph->saddr,
};
dst = ip6_route_output(net, skb->sk, &fl);
if (dst->error) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
LIMIT_NETDEBUG(KERN_DEBUG "ip6_route_me_harder: No more route.\n");
dst_release(dst);
return -EINVAL;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, dst);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, &fl, AF_INET6) == 0) {
skb_dst_set(skb, NULL);
if (xfrm_lookup(net, &dst, &fl, skb->sk, 0))
return -1;
skb_dst_set(skb, dst);
}
#endif
return 0;
}
EXPORT_SYMBOL(ip6_route_me_harder);
/*
* Extra routing may needed on local out, as the QUEUE target never
* returns control to the table.
*/
struct ip6_rt_info {
struct in6_addr daddr;
struct in6_addr saddr;
u_int32_t mark;
};
static void nf_ip6_saveroute(const struct sk_buff *skb,
struct nf_queue_entry *entry)
{
struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->hook == NF_INET_LOCAL_OUT) {
struct ipv6hdr *iph = ipv6_hdr(skb);
rt_info->daddr = iph->daddr;
rt_info->saddr = iph->saddr;
rt_info->mark = skb->mark;
}
}
static int nf_ip6_reroute(struct sk_buff *skb,
const struct nf_queue_entry *entry)
{
struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->hook == NF_INET_LOCAL_OUT) {
struct ipv6hdr *iph = ipv6_hdr(skb);
if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
!ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
skb->mark != rt_info->mark)
return ip6_route_me_harder(skb);
}
return 0;
}
static int nf_ip6_route(struct dst_entry **dst, struct flowi *fl)
{
*dst = ip6_route_output(&init_net, NULL, fl);
return (*dst)->error;
}
int ip6_route_me_harder(struct sk_buff *skb)
{
struct net *net = dev_net(skb_dst(skb)->dev);
const struct ipv6hdr *iph = ipv6_hdr(skb);
unsigned int hh_len;
struct dst_entry *dst;
struct flowi6 fl6 = {
.flowi6_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
.flowi6_mark = skb->mark,
.daddr = iph->daddr,
.saddr = iph->saddr,
};
int err;
dst = ip6_route_output(net, skb->sk, &fl6);
err = dst->error;
if (err) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
net_dbg_ratelimited("ip6_route_me_harder: No more route\n");
dst_release(dst);
return err;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, dst);
#ifdef CONFIG_XFRM
if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi6_to_flowi(&fl6), AF_INET6) == 0) {
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), skb->sk, 0);
if (IS_ERR(dst))
return PTR_ERR(dst);
skb_dst_set(skb, dst);
}
#endif
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
0, GFP_ATOMIC))
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(ip6_route_me_harder);
/*
* Extra routing may needed on local out, as the QUEUE target never
* returns control to the table.
*/
struct ip6_rt_info {
struct in6_addr daddr;
struct in6_addr saddr;
u_int32_t mark;
};
static void nf_ip6_saveroute(const struct sk_buff *skb,
struct nf_queue_entry *entry)
{
struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->hook == NF_INET_LOCAL_OUT) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
rt_info->daddr = iph->daddr;
rt_info->saddr = iph->saddr;
rt_info->mark = skb->mark;
}
}
static int nf_ip6_reroute(struct sk_buff *skb,
const struct nf_queue_entry *entry)
{
struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry);
if (entry->hook == NF_INET_LOCAL_OUT) {
const struct ipv6hdr *iph = ipv6_hdr(skb);
if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
!ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
skb->mark != rt_info->mark)
return ip6_route_me_harder(skb);
}
return 0;
}
static int nf_ip6_route(struct net *net, struct dst_entry **dst,
struct flowi *fl, bool strict)
{
static const struct ipv6_pinfo fake_pinfo;
static const struct inet_sock fake_sk = {
/* makes ip6_route_output set RT6_LOOKUP_F_IFACE: */
.sk.sk_bound_dev_if = 1,
.pinet6 = (struct ipv6_pinfo *) &fake_pinfo,
};
const void *sk = strict ? &fake_sk : NULL;
struct dst_entry *result;
int err;
result = ip6_route_output(net, sk, &fl->u.ip6);
err = result->error;
if (err)
dst_release(result);
else
*dst = result;
return err;
}
__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
unsigned int dataoff, u_int8_t protocol)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
__sum16 csum = 0;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
break;
if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
skb->len - dataoff, protocol,
csum_sub(skb->csum,
skb_checksum(skb, 0,
dataoff, 0)))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
break;
}
/* fall through */
case CHECKSUM_NONE:
skb->csum = ~csum_unfold(
csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
skb->len - dataoff,
protocol,
csum_sub(0,
skb_checksum(skb, 0,
dataoff, 0))));
csum = __skb_checksum_complete(skb);
}
return csum;
}
EXPORT_SYMBOL(nf_ip6_checksum);
static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
unsigned int dataoff, unsigned int len,
u_int8_t protocol)
{
const struct ipv6hdr *ip6h = ipv6_hdr(skb);
__wsum hsum;
__sum16 csum = 0;
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
if (len == skb->len - dataoff)
return nf_ip6_checksum(skb, hook, dataoff, protocol);
/* fall through */
case CHECKSUM_NONE:
hsum = skb_checksum(skb, 0, dataoff, 0);
skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
&ip6h->daddr,
skb->len - dataoff,
protocol,
csum_sub(0, hsum)));
skb->ip_summed = CHECKSUM_NONE;
return __skb_checksum_complete_head(skb, dataoff + len);
}
return csum;
};
static const struct nf_ipv6_ops ipv6ops = {
.chk_addr = ipv6_chk_addr,
};
static const struct nf_afinfo nf_ip6_afinfo = {
.family = AF_INET6,
.checksum = nf_ip6_checksum,
.checksum_partial = nf_ip6_checksum_partial,
.route = nf_ip6_route,
.saveroute = nf_ip6_saveroute,
.reroute = nf_ip6_reroute,
.route_key_size = sizeof(struct ip6_rt_info),
};
int __init ipv6_netfilter_init(void)
{
RCU_INIT_POINTER(nf_ipv6_ops, &ipv6ops);
return nf_register_afinfo(&nf_ip6_afinfo);
}
/* This can be called from inet6_init() on errors, so it cannot
* be marked __exit. -DaveM
*/
void ipv6_netfilter_fini(void)
{
RCU_INIT_POINTER(nf_ipv6_ops, NULL);
nf_unregister_afinfo(&nf_ip6_afinfo);
}
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi fl = {};
struct dst_entry *odst;
unsigned int hh_len;
unsigned int type;
type = inet_addr_type(&init_net, iph->saddr);
if (addr_type == RTN_UNSPEC)
addr_type = type;
/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
* packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
*/
if (addr_type == RTN_LOCAL) {
fl.nl_u.ip4_u.daddr = iph->daddr;
if (type == RTN_LOCAL)
fl.nl_u.ip4_u.saddr = iph->saddr;
fl.nl_u.ip4_u.tos = RT_TOS(iph->tos);
fl.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
fl.mark = skb->mark;
if (ip_route_output_key(&init_net, &rt, &fl) != 0)
return -1;
/* Drop old route. */
dst_release(skb->dst);
skb->dst = &rt->u.dst;
} else {
/* non-local src, find valid iif to satisfy
* rp-filter when calling ip_route_input. */
fl.nl_u.ip4_u.daddr = iph->saddr;
if (ip_route_output_key(&init_net, &rt, &fl) != 0)
return -1;
odst = skb->dst;
if (ip_route_input(skb, iph->daddr, iph->saddr,
RT_TOS(iph->tos), rt->u.dst.dev) != 0) {
dst_release(&rt->u.dst);
return -1;
}
dst_release(&rt->u.dst);
dst_release(odst);
}
if (skb->dst->error)
return -1;
#ifdef CONFIG_XFRM
if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, &fl, AF_INET) == 0)
if (xfrm_lookup(&skb->dst, &fl, skb->sk, 0))
return -1;
#endif
/* Change in oif may mean change in hh_len. */
hh_len = skb->dst->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
return -1;
return 0;
}
/* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
{
struct net *net = dev_net(skb_dst(skb)->dev);
const struct iphdr *iph = ip_hdr(skb);
struct rtable *rt;
struct flowi4 fl4 = {};
unsigned long orefdst;
unsigned int hh_len;
unsigned int type;
type = inet_addr_type(net, iph->saddr);
if (skb->sk && inet_sk(skb->sk)->transparent)
type = RTN_LOCAL;
if (addr_type == RTN_UNSPEC)
addr_type = type;
/* some non-standard hacks like ipt_REJECT.c:send_reset() can cause
* packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook.
*/
if (addr_type == RTN_LOCAL) {
fl4.daddr = iph->daddr;
if (type == RTN_LOCAL)
fl4.saddr = iph->saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0;
fl4.flowi4_mark = skb->mark;
fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return -1;
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
/* non-local src, find valid iif to satisfy
* rp-filter when calling ip_route_input. */
fl4.daddr = iph->saddr;
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return -1;
orefdst = skb->_skb_refdst;
if (ip_route_input(skb, iph->daddr, iph->saddr,
RT_TOS(iph->tos), rt->dst.dev) != 0) {
dst_release(&rt->dst);
return -1;
}
dst_release(&rt->dst);
refdst_drop(orefdst);
}
if (skb_dst(skb)->error)
return -1;
#ifdef CONFIG_XFRM
if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
xfrm_decode_session(skb, flowi4_to_flowi(&fl4), AF_INET) == 0) {
struct dst_entry *dst = skb_dst(skb);
skb_dst_set(skb, NULL);
dst = xfrm_lookup(net, dst, flowi4_to_flowi(&fl4), skb->sk, 0);
if (IS_ERR(dst))
return -1;
skb_dst_set(skb, dst);
}
#endif
/* Change in oif may mean change in hh_len. */
hh_len = skb_dst(skb)->dev->hard_header_len;
if (skb_headroom(skb) < hh_len &&
pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
return -1;
return 0;
}
