/* Route IPv6 packet 'skbp', using the route key selectors in
'route_selector' and the interface number 'ifnum_in'. */
Boolean
ssh_interceptor_reroute_skb_ipv6(SshInterceptor interceptor,
struct sk_buff *skbp,
SshUInt16 route_selector,
SshUInt32 ifnum_in)
{
/* we do not need a socket, only fake flow */
struct flowi rt_key;
struct dst_entry *dst;
struct ipv6hdr *iph6;
iph6 = (struct ipv6hdr *) SSH_SKB_GET_NETHDR(skbp);
if (iph6 == NULL)
{
SSH_DEBUG(SSH_D_ERROR, ("Could not access IPv6 header"));
return FALSE;
}
memset(&rt_key, 0, sizeof(rt_key));
rt_key.fl6_dst = iph6->daddr;
if (route_selector & SSH_INTERCEPTOR_ROUTE_KEY_SRC)
rt_key.fl6_src = iph6->saddr;
if (route_selector & SSH_INTERCEPTOR_ROUTE_KEY_OUT_IFNUM)
{
rt_key.oif = (skbp->dev ? skbp->dev->ifindex : 0);
SSH_LINUX_ASSERT_IFNUM(rt_key.oif);
}
#ifdef LINUX_IP6_ROUTE_OUTPUT_KEY_HAS_NET_ARGUMENT
dst = ip6_route_output(&init_net, NULL, &rt_key);
#else /* LINUX_IP6_ROUTE_OUTPUT_KEY_HAS_NET_ARGUMENT */
dst = ip6_route_output(NULL, &rt_key);
#endif /* LINUX_IP6_ROUTE_OUTPUT_KEY_HAS_NET_ARGUMENT */
if (dst == NULL || dst->error != 0)
{
SSH_DEBUG(SSH_D_FAIL,
("ip6_route_output failed."));
SSH_DEBUG_HEXDUMP(SSH_D_NICETOKNOW,
("dst "),
(unsigned char *) &iph6->daddr, sizeof(iph6->daddr));
SSH_DEBUG_HEXDUMP(SSH_D_NICETOKNOW,
("src "),
(unsigned char *) &iph6->saddr, sizeof(iph6->saddr));
SSH_DEBUG(SSH_D_NICETOKNOW,
("oif %d[%s]",
(skbp->dev ? skbp->dev->ifindex : -1),
(skbp->dev ? skbp->dev->name : "none")));
return FALSE;
}
if (SSH_SKB_DST(skbp))
dst_release(SSH_SKB_DST(skbp));
SSH_SKB_DST_SET(skbp, dst_clone(dst));
return TRUE;
}
static int ip6_dst_lookup_tail(struct sock *sk,
struct dst_entry **dst, struct flowi *fl)
{
int err;
if (*dst == NULL)
*dst = ip6_route_output(sk, fl);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl->fl6_src)) {
err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src);
if (err)
goto out_err_release;
}
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
* has a neighbour entry that is in the INCOMPLETE
* state and the src address from the flow is
* marked as OPTIMISTIC, we release the found
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
if (!((*dst)->neighbour->nud_state & NUD_VALID)) {
struct inet6_ifaddr *ifp;
struct flowi fl_gw;
int redirect;
ifp = ipv6_get_ifaddr(&fl->fl6_src, (*dst)->dev, 1);
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
if (ifp)
in6_ifa_put(ifp);
if (redirect) {
/*
* We need to get the dst entry for the
* default router instead
*/
dst_release(*dst);
memcpy(&fl_gw, fl, sizeof(struct flowi));
memset(&fl_gw.fl6_dst, 0, sizeof(struct in6_addr));
*dst = ip6_route_output(sk, &fl_gw);
if ((err = (*dst)->error))
goto out_err_release;
}
}
#endif
return 0;
out_err_release:
dst_release(*dst);
*dst = NULL;
return err;
}
int ip6_route_me_harder(struct sk_buff *skb)
{
struct ipv6hdr *iph = skb->nh.ipv6h;
struct dst_entry *dst;
struct flowi fl;
fl.proto = iph->nexthdr;
fl.fl6_dst = &iph->daddr;
fl.fl6_src = &iph->saddr;
fl.oif = skb->sk ? skb->sk->bound_dev_if : 0;
fl.fl6_flowlabel = 0;
fl.uli_u.ports.dport = 0;
fl.uli_u.ports.sport = 0;
dst = ip6_route_output(skb->sk, &fl);
if (dst->error) {
if (net_ratelimit())
printk(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;
}
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
struct in6_addr *ret_saddr, int do_xfrm)
{
struct dst_entry *dst;
struct flowi6 fl6 = {
.daddr = *daddr,
};
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error)
goto out_err;
if (!ret_saddr)
return dst;
if (ipv6_addr_any(&fl6.saddr) &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6.daddr, 0, &fl6.saddr) < 0)
goto out_err;
if (do_xfrm) {
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst)) {
dst = NULL;
goto out_err;
}
}
*ret_saddr = fl6.saddr;
return dst;
out_err:
dst_release(dst);
IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr);
return NULL;
}
static bool
tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = pick_net(skb);
struct dst_entry *dst;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
if (info->priv) {
if (info->priv->oif == -1)
return false;
fl6.flowi6_oif = info->priv->oif;
}
fl6.daddr = info->gw.in6;
fl6.flowlabel = ((iph->flow_lbl[0] & 0xF) << 16) |
(iph->flow_lbl[1] << 8) | iph->flow_lbl[2];
dst = ip6_route_output(net, NULL, &fl6);
if (dst == NULL)
return false;
skb_dst_drop(skb);
skb_dst_set(skb, dst);
skb->dev = dst->dev;
skb->protocol = htons(ETH_P_IPV6);
return true;
}
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, } },
.proto = iph->nexthdr,
};
dst = ip6_route_output(skb->sk, &fl);
if (dst->error) {
IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
LIMIT_NETDEBUG(
printk(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;
}
static bool nf_dup_ipv6_route(struct net *net, struct sk_buff *skb,
const struct in6_addr *gw, int oif)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct dst_entry *dst;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
if (oif != -1)
fl6.flowi6_oif = oif;
fl6.daddr = *gw;
fl6.flowlabel = (__force __be32)(((iph->flow_lbl[0] & 0xF) << 16) |
(iph->flow_lbl[1] << 8) | iph->flow_lbl[2]);
fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
dst_release(dst);
return false;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
skb->dev = dst->dev;
skb->protocol = htons(ETH_P_IPV6);
return true;
}
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->bound_dev_if : 0,
.nl_u =
{ .ip6_u =
{ .daddr = iph->daddr,
.saddr = iph->saddr, } },
.proto = iph->nexthdr,
};
dst = ip6_route_output(skb->sk, &fl);
if (dst->error) {
if (net_ratelimit())
printk(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;
}
static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
struct rt6_info *rt = (struct rt6_info *)orig_dst;
struct ila_lwt *ilwt = ila_lwt_lwtunnel(orig_dst->lwtstate);
struct dst_entry *dst;
int err = -EINVAL;
if (skb->protocol != htons(ETH_P_IPV6))
goto drop;
ila_update_ipv6_locator(skb, ila_params_lwtunnel(orig_dst->lwtstate),
true);
if (rt->rt6i_flags & (RTF_GATEWAY | RTF_CACHE)) {
/* Already have a next hop address in route, no need for
* dest cache route.
*/
return orig_dst->lwtstate->orig_output(net, sk, skb);
}
dst = dst_cache_get(&ilwt->dst_cache);
if (unlikely(!dst)) {
struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct flowi6 fl6;
/* Lookup a route for the new destination. Take into
* account that the base route may already have a gateway.
*/
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_oif = orig_dst->dev->ifindex;
fl6.flowi6_iif = LOOPBACK_IFINDEX;
fl6.daddr = *rt6_nexthop((struct rt6_info *)orig_dst,
&ip6h->daddr);
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
err = -EHOSTUNREACH;
dst_release(dst);
goto drop;
}
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto drop;
}
if (ilwt->connected)
dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
}
skb_dst_set(skb, dst);
return dst_output(net, sk, skb);
drop:
kfree_skb(skb);
return err;
}
int xfrm6_dst_lookup(struct xfrm_dst **dst, struct flowi *fl)
{
int err = 0;
*dst = (struct xfrm_dst*)ip6_route_output(NULL, fl);
if (!*dst)
err = -ENETUNREACH;
return err;
}
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
struct flowi6 fl6 = {
/* needed to match OIF rule */
.flowi6_oif = dev->ifindex,
.flowi6_iif = LOOPBACK_IFINDEX,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
};
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or the VRF device again this is locally
* originated traffic destined to a local address. Short circuit
* to Rx path
*/
if (dst->dev == dev)
return vrf_local_xmit(skb, dev, dst);
skb_dst_set(skb, dst);
/* strip the ethernet header added for pass through VRF device */
__skb_pull(skb, skb_network_offset(skb));
ret = vrf_ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
return ret;
err:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
#else
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
static int xfrm6_dst_lookup(struct xfrm_dst **xdst, struct flowi *fl)
{
struct dst_entry *dst = ip6_route_output(NULL, fl);
int err = dst->error;
if (!err)
*xdst = (struct xfrm_dst *) dst;
else
dst_release(dst);
return err;
}
static void
synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb,
struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo,
struct ipv6hdr *niph, struct tcphdr *nth,
unsigned int tcp_hdr_size)
{
struct net *net = nf_ct_net((struct nf_conn *)nfct);
struct dst_entry *dst;
struct flowi6 fl6;
nth->check = ~tcp_v6_check(tcp_hdr_size, &niph->saddr, &niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)nth - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.saddr = niph->saddr;
fl6.daddr = niph->daddr;
fl6.fl6_sport = nth->source;
fl6.fl6_dport = nth->dest;
security_skb_classify_flow((struct sk_buff *)skb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst == NULL || dst->error) {
dst_release(dst);
goto free_nskb;
}
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst))
goto free_nskb;
skb_dst_set(nskb, dst);
if (nfct) {
nskb->nfct = nfct;
nskb->nfctinfo = ctinfo;
nf_conntrack_get(nfct);
}
ip6_local_out(nskb);
return;
free_nskb:
kfree_skb(nskb);
}
int nat64_send_packet_ipv6(struct sk_buff *skb)
{
// Function based on Ecdysis's nat64_output_ipv4
struct ipv6hdr *iph = ipv6_hdr(skb);
struct flowi fl;
struct dst_entry *dst;
//union nat64_l4header_t {
// struct udphdr * uh;
// struct tcphdr * th;
// struct icmp6hdr * icmph;
//} l4header;
//int i = 0;
skb->protocol = htons(ETH_P_IPV6);
memset(&fl, 0, sizeof(fl));
fl.u.ip6.saddr = iph->saddr;
fl.u.ip6.daddr = iph->daddr;
fl.u.ip6.flowlabel = 0;
fl.flowi_proto= skb->protocol;
dst = ip6_route_output(&init_net, NULL, &fl.u.ip6);
if (!dst) {
pr_warning("error: ip6_route_output failed.");
return -EINVAL;
}
skb->dev = dst->dev;
skb_dst_set(skb, dst);
/*
* Makes sure the net_device can actually send packets.
*/
netif_start_queue(skb->dev);
if(ip6_local_out(skb)) {
pr_warning("nf_NAT64: ip6_local_out failed");
return -EINVAL;
}
return 0;
}
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
struct flowi6 fl6 = {
/* needed to match OIF rule */
.flowi6_oif = dev->ifindex,
.flowi6_iif = LOOPBACK_IFINDEX,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
.flowi6_flags = FLOWI_FLAG_L3MDEV_SRC | FLOWI_FLAG_SKIP_NH_OIF,
};
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
skb_dst_drop(skb);
skb_dst_set(skb, dst);
ret = ip6_local_out(net, skb->sk, skb);
if (unlikely(net_xmit_eval(ret)))
dev->stats.tx_errors++;
else
ret = NET_XMIT_SUCCESS;
return ret;
err:
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
#else
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
struct net_device *dev)
{
vrf_tx_error(dev, skb);
return NET_XMIT_DROP;
}
static struct dst_entry *route_packet_ipv6(struct sk_buff *skb)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
struct flowi fl;
struct dst_entry *dst;
memset(&fl, 0, sizeof(fl));
fl.u.ip6.saddr = iph->saddr;
fl.u.ip6.daddr = iph->daddr;
fl.u.ip6.flowlabel = 0;
fl.flowi_proto= skb->protocol;
dst = ip6_route_output(&init_net, NULL, &fl.u.ip6);
if (!dst) {
log_err(ERR_ROUTE_FAILED, "ip6_route_output() returned NULL. Cannot route packet.");
return NULL;
}
return dst;
}
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;
}
static struct dst_entry *xfrm6_dst_lookup(int tos, xfrm_address_t *saddr,
xfrm_address_t *daddr)
{
struct flowi fl = {};
struct dst_entry *dst;
int err;
memcpy(&fl.fl6_dst, daddr, sizeof(fl.fl6_dst));
if (saddr)
memcpy(&fl.fl6_src, saddr, sizeof(fl.fl6_src));
dst = ip6_route_output(&init_net, NULL, &fl);
err = dst->error;
if (dst->error) {
dst_release(dst);
dst = ERR_PTR(err);
}
return dst;
}
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;
}
static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos,
const xfrm_address_t *saddr,
const xfrm_address_t *daddr)
{
struct flowi6 fl6;
struct dst_entry *dst;
int err;
memset(&fl6, 0, sizeof(fl6));
memcpy(&fl6.daddr, daddr, sizeof(fl6.daddr));
if (saddr)
memcpy(&fl6.saddr, saddr, sizeof(fl6.saddr));
dst = ip6_route_output(net, NULL, &fl6);
err = dst->error;
if (dst->error) {
dst_release(dst);
dst = ERR_PTR(err);
}
return dst;
}
int nat64_send_packet_ipv6(struct sk_buff *skb)
{
// Function based on Ecdysis's nat64_output_ipv4
struct ipv6hdr *iph = ipv6_hdr(skb);
struct flowi fl;
struct dst_entry *dst;
skb->protocol = htons(ETH_P_IPV6);
memset(&fl, 0, sizeof(fl));
if(!&(fl.fl6_src)) {
return -EINVAL;
}
fl.fl6_src = iph->saddr;
fl.fl6_dst = iph->daddr;
fl.fl6_flowlabel = 0;
fl.proto = skb->protocol;
dst = ip6_route_output(&init_net, NULL, &fl);
if (!dst) {
pr_warning("error: ip6_route_output failed");
return -EINVAL;
}
skb->dev = dst->dev;
skb_dst_set(skb, dst);
if(ip6_local_out(skb)) {
pr_warning("nf_NAT64: ip6_local_out failed.");
return -EINVAL;
}
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;
}
static int ip6_dst_lookup_tail(struct sock *sk,
struct dst_entry **dst, struct flowi *fl)
{
int err;
if (*dst == NULL)
*dst = ip6_route_output(sk, fl);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl->fl6_src)) {
err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src);
if (err)
goto out_err_release;
}
return 0;
out_err_release:
dst_release(*dst);
*dst = NULL;
return err;
}
/* Reroute packet to local IPv4 stack after DNAT */
static int
__ip_vs_reroute_locally(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->dst.dev;
struct net *net = dev_net(dev);
struct iphdr *iph = ip_hdr(skb);
if (rt_is_input_route(rt)) {
unsigned long orefdst = skb->_skb_refdst;
if (ip_route_input(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev))
return 0;
refdst_drop(orefdst);
} else {
struct flowi4 fl4 = {
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowi4_tos = RT_TOS(iph->tos),
.flowi4_mark = skb->mark,
};
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return 0;
if (!(rt->rt_flags & RTCF_LOCAL)) {
ip_rt_put(rt);
return 0;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
}
return 1;
}
#ifdef CONFIG_IP_VS_IPV6
static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
{
return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK;
}
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
struct in6_addr *ret_saddr, int do_xfrm)
{
struct dst_entry *dst;
struct flowi6 fl6 = {
.daddr = *daddr,
};
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error)
goto out_err;
if (!ret_saddr)
return dst;
if (ipv6_addr_any(&fl6.saddr) &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6.daddr, 0, &fl6.saddr) < 0)
goto out_err;
if (do_xfrm) {
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst)) {
dst = NULL;
goto out_err;
}
}
ipv6_addr_copy(ret_saddr, &fl6.saddr);
return dst;
out_err:
dst_release(dst);
IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr);
return NULL;
}
/*
* Get route to destination or remote server
* rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest,
* &4=Allow redirect from remote daddr to local
*/
static struct rt6_info *
__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rt6_info *rt; /* Route to the other host */
struct rt6_info *ort; /* Original route */
struct dst_entry *dst;
int local;
if (dest) {
spin_lock(&dest->dst_lock);
rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0);
if (!rt) {
u32 cookie;
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest->dst_saddr,
do_xfrm);
if (!dst) {
spin_unlock(&dest->dst_lock);
return NULL;
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
__ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest->dst_saddr,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
ipv6_addr_copy(ret_saddr, &dest->dst_saddr);
spin_unlock(&dest->dst_lock);
} else {
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst)
return NULL;
rt = (struct rt6_info *) dst;
}
local = __ip_vs_is_local_route6(rt);
if (!((local ? 1 : 2) & rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
local ? "local":"non-local", daddr);
dst_release(&rt->dst);
return NULL;
}
if (local && !(rt_mode & 4) &&
!((ort = (struct rt6_info *) skb_dst(skb)) &&
__ip_vs_is_local_route6(ort))) {
IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
"requires NAT method, dest: %pI6\n",
&ipv6_hdr(skb)->daddr, daddr);
dst_release(&rt->dst);
return NULL;
}
if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
IPV6_ADDR_LOOPBACK)) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
"to non-local address, dest: %pI6\n",
&ipv6_hdr(skb)->saddr, daddr);
dst_release(&rt->dst);
return NULL;
}
return rt;
}
#endif
/*
* Release dest->dst_cache before a dest is removed
*/
void
ip_vs_dst_reset(struct ip_vs_dest *dest)
{
struct dst_entry *old_dst;
old_dst = dest->dst_cache;
dest->dst_cache = NULL;
dst_release(old_dst);
}
#define IP_VS_XMIT_TUNNEL(skb, cp) \
({ \
int __ret = NF_ACCEPT; \
\
(skb)->ipvs_property = 1; \
if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \
__ret = ip_vs_confirm_conntrack(skb, cp); \
if (__ret == NF_ACCEPT) { \
nf_reset(skb); \
skb_forward_csum(skb); \
} \
__ret; \
})
#define IP_VS_XMIT_NAT(pf, skb, cp, local) \
do { \
(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); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
#define IP_VS_XMIT(pf, skb, cp, local) \
do { \
(skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
ip_vs_notrack(skb); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
/*
* NULL transmitter (do nothing except return NF_ACCEPT)
*/
int
ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
/* we do not touch skb and do not need pskb ptr */
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
static int ip6_dst_lookup_tail(struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
struct net *net = sock_net(sk);
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
#endif
int err;
if (*dst == NULL)
*dst = ip6_route_output(net, sk, fl6);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl6->saddr)) {
struct rt6_info *rt = (struct rt6_info *) *dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
goto out_err_release;
}
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
* has a neighbour entry that is in the INCOMPLETE
* state and the src address from the flow is
* marked as OPTIMISTIC, we release the found
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
rcu_read_lock();
n = dst_get_neighbour(*dst);
if (n && !(n->nud_state & NUD_VALID)) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
int redirect;
rcu_read_unlock();
ifp = ipv6_get_ifaddr(net, &fl6->saddr,
(*dst)->dev, 1);
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
if (ifp)
in6_ifa_put(ifp);
if (redirect) {
/*
* We need to get the dst entry for the
* default router instead
*/
dst_release(*dst);
memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
*dst = ip6_route_output(net, sk, &fl_gw6);
if ((err = (*dst)->error))
goto out_err_release;
}
} else {
rcu_read_unlock();
}
#endif
return 0;
out_err_release:
if (err == -ENETUNREACH)
IP6_INC_STATS_BH(net, NULL, IPSTATS_MIB_OUTNOROUTES);
dst_release(*dst);
*dst = NULL;
return err;
}
/* Send RST reply */
static void send_reset(struct net *net, struct sk_buff *oldskb)
{
struct sk_buff *nskb;
struct tcphdr otcph, *tcph;
unsigned int otcplen, hh_len;
int tcphoff, needs_ack;
const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
struct ipv6hdr *ip6h;
#define DEFAULT_TOS_VALUE 0x0U
const __u8 tclass = DEFAULT_TOS_VALUE;
struct dst_entry *dst = NULL;
u8 proto;
struct flowi fl;
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
(!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
pr_debug("addr is not unicast.\n");
return;
}
proto = oip6h->nexthdr;
tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto);
if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
pr_debug("Cannot get TCP header.\n");
return;
}
otcplen = oldskb->len - tcphoff;
/* IP header checks: fragment, too short. */
if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
pr_debug("proto(%d) != IPPROTO_TCP, "
"or too short. otcplen = %d\n",
proto, otcplen);
return;
}
if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
BUG();
/* No RST for RST. */
if (otcph.rst) {
pr_debug("RST is set\n");
return;
}
/* Check checksum. */
if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP,
skb_checksum(oldskb, tcphoff, otcplen, 0))) {
pr_debug("TCP checksum is invalid\n");
return;
}
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_TCP;
ipv6_addr_copy(&fl.fl6_src, &oip6h->daddr);
ipv6_addr_copy(&fl.fl6_dst, &oip6h->saddr);
fl.fl_ip_sport = otcph.dest;
fl.fl_ip_dport = otcph.source;
security_skb_classify_flow(oldskb, &fl);
dst = ip6_route_output(net, NULL, &fl);
if (dst == NULL || dst->error) {
dst_release(dst);
return;
}
if (xfrm_lookup(net, &dst, &fl, NULL, 0))
return;
hh_len = (dst->dev->hard_header_len + 15)&~15;
nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+ sizeof(struct tcphdr) + dst->trailer_len,
GFP_ATOMIC);
if (!nskb) {
if (net_ratelimit())
pr_debug("cannot alloc skb\n");
dst_release(dst);
return;
}
skb_dst_set(nskb, dst);
skb_reserve(nskb, hh_len + dst->header_len);
skb_put(nskb, sizeof(struct ipv6hdr));
skb_reset_network_header(nskb);
ip6h = ipv6_hdr(nskb);
*(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20));
ip6h->hop_limit = dst_metric(dst, RTAX_HOPLIMIT);
ip6h->nexthdr = IPPROTO_TCP;
ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr);
ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr);
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
/* Truncate to length (no data) */
tcph->doff = sizeof(struct tcphdr)/4;
tcph->source = otcph.dest;
tcph->dest = otcph.source;
if (otcph.ack) {
needs_ack = 0;
tcph->seq = otcph.ack_seq;
tcph->ack_seq = 0;
} else {
needs_ack = 1;
tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
+ otcplen - (otcph.doff<<2));
tcph->seq = 0;
}
/* Reset flags */
((u_int8_t *)tcph)[13] = 0;
tcph->rst = 1;
tcph->ack = needs_ack;
tcph->window = 0;
tcph->urg_ptr = 0;
tcph->check = 0;
/* Adjust TCP checksum */
tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
&ipv6_hdr(nskb)->daddr,
sizeof(struct tcphdr), IPPROTO_TCP,
csum_partial(tcph,
sizeof(struct tcphdr), 0));
nf_ct_attach(nskb, oldskb);
ip6_local_out(nskb);
}
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;
}
static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
struct dst_entry **dst, struct flowi6 *fl6)
{
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
struct neighbour *n;
struct rt6_info *rt;
#endif
int err;
int flags = 0;
/* The correct way to handle this would be to do
* ip6_route_get_saddr, and then ip6_route_output; however,
* the route-specific preferred source forces the
* ip6_route_output call _before_ ip6_route_get_saddr.
*
* In source specific routing (no src=any default route),
* ip6_route_output will fail given src=any saddr, though, so
* that's why we try it again later.
*/
if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) {
struct rt6_info *rt;
bool had_dst = *dst != NULL;
if (!had_dst)
*dst = ip6_route_output(net, sk, fl6);
rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)
goto out_err_release;
/* If we had an erroneous initial result, pretend it
* never existed and let the SA-enabled version take
* over.
*/
if (!had_dst && (*dst)->error) {
dst_release(*dst);
*dst = NULL;
}
if (fl6->flowi6_oif)
flags |= RT6_LOOKUP_F_IFACE;
}
if (!*dst)
*dst = ip6_route_output_flags(net, sk, fl6, flags);
err = (*dst)->error;
if (err)
goto out_err_release;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* Here if the dst entry we've looked up
* has a neighbour entry that is in the INCOMPLETE
* state and the src address from the flow is
* marked as OPTIMISTIC, we release the found
* dst entry and replace it instead with the
* dst entry of the nexthop router
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
n = __ipv6_neigh_lookup_noref(rt->dst.dev,
rt6_nexthop(rt, &fl6->daddr));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
if (err) {
struct inet6_ifaddr *ifp;
struct flowi6 fl_gw6;
int redirect;
ifp = ipv6_get_ifaddr(net, &fl6->saddr,
(*dst)->dev, 1);
redirect = (ifp && ifp->flags & IFA_F_OPTIMISTIC);
if (ifp)
in6_ifa_put(ifp);
if (redirect) {
/*
* We need to get the dst entry for the
* default router instead
*/
dst_release(*dst);
memcpy(&fl_gw6, fl6, sizeof(struct flowi6));
memset(&fl_gw6.daddr, 0, sizeof(struct in6_addr));
*dst = ip6_route_output(net, sk, &fl_gw6);
err = (*dst)->error;
if (err)
goto out_err_release;
}
}
#endif
return 0;
out_err_release:
if (err == -ENETUNREACH)
IP6_INC_STATS(net, NULL, IPSTATS_MIB_OUTNOROUTES);
dst_release(*dst);
*dst = NULL;
return err;
}
int ip6_dst_lookup(struct sock *sk, struct dst_entry **dst, struct flowi *fl)
{
int err = 0;
*dst = NULL;
if (sk) {
struct ipv6_pinfo *np = inet6_sk(sk);
*dst = sk_dst_check(sk, np->dst_cookie);
if (*dst) {
struct rt6_info *rt = (struct rt6_info*)*dst;
/* Yes, checking route validity in not connected
case is not very simple. Take into account,
that we do not support routing by source, TOS,
and MSG_DONTROUTE --ANK (980726)
1. If route was host route, check that
cached destination is current.
If it is network route, we still may
check its validity using saved pointer
to the last used address: daddr_cache.
We do not want to save whole address now,
(because main consumer of this service
is tcp, which has not this problem),
so that the last trick works only on connected
sockets.
2. oif also should be the same.
*/
if (((rt->rt6i_dst.plen != 128 ||
!ipv6_addr_equal(&fl->fl6_dst, &rt->rt6i_dst.addr))
&& (np->daddr_cache == NULL ||
!ipv6_addr_equal(&fl->fl6_dst, np->daddr_cache)))
|| (fl->oif && fl->oif != (*dst)->dev->ifindex)) {
dst_release(*dst);
*dst = NULL;
}
}
}
if (*dst == NULL)
*dst = ip6_route_output(sk, fl);
if ((err = (*dst)->error))
goto out_err_release;
if (ipv6_addr_any(&fl->fl6_src)) {
err = ipv6_get_saddr(*dst, &fl->fl6_dst, &fl->fl6_src);
if (err) {
#if IP6_DEBUG >= 2
printk(KERN_DEBUG "ip6_dst_lookup: "
"no available source address\n");
#endif
goto out_err_release;
}
}
return 0;
out_err_release:
dst_release(*dst);
*dst = NULL;
return err;
}
int ip6_build_xmit(struct sock *sk, inet_getfrag_t getfrag, const void *data,
struct flowi *fl, unsigned length,
struct ipv6_txoptions *opt, int hlimit, int flags)
{
struct ipv6_pinfo *np = &sk->net_pinfo.af_inet6;
struct in6_addr *final_dst = NULL;
struct dst_entry *dst;
int err = 0;
unsigned int pktlength, jumbolen, mtu;
struct in6_addr saddr;
if (opt && opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
final_dst = fl->fl6_dst;
fl->fl6_dst = rt0->addr;
}
if (!fl->oif && ipv6_addr_is_multicast(fl->nl_u.ip6_u.daddr))
fl->oif = np->mcast_oif;
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst) {
struct rt6_info *rt = (struct rt6_info*)dst;
/* Yes, checking route validity in not connected
case is not very simple. Take into account,
that we do not support routing by source, TOS,
and MSG_DONTROUTE --ANK (980726)
1. If route was host route, check that
cached destination is current.
If it is network route, we still may
check its validity using saved pointer
to the last used address: daddr_cache.
We do not want to save whole address now,
(because main consumer of this service
is tcp, which has not this problem),
so that the last trick works only on connected
sockets.
2. oif also should be the same.
*/
if (((rt->rt6i_dst.plen != 128 ||
ipv6_addr_cmp(fl->fl6_dst, &rt->rt6i_dst.addr))
&& (np->daddr_cache == NULL ||
ipv6_addr_cmp(fl->fl6_dst, np->daddr_cache)))
|| (fl->oif && fl->oif != dst->dev->ifindex)) {
dst = NULL;
} else
dst_hold(dst);
}
if (dst == NULL)
dst = ip6_route_output(sk, fl);
if (dst->error) {
IP6_INC_STATS(Ip6OutNoRoutes);
dst_release(dst);
return -ENETUNREACH;
}
if (fl->fl6_src == NULL) {
err = ipv6_get_saddr(dst, fl->fl6_dst, &saddr);
if (err) {
#if IP6_DEBUG >= 2
printk(KERN_DEBUG "ip6_build_xmit: "
"no available source address\n");
#endif
goto out;
}
fl->fl6_src = &saddr;
}
pktlength = length;
if (hlimit < 0) {
if (ipv6_addr_is_multicast(fl->fl6_dst))
hlimit = np->mcast_hops;
else
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = ((struct rt6_info*)dst)->rt6i_hoplimit;
}
jumbolen = 0;
if (!sk->protinfo.af_inet.hdrincl) {
pktlength += sizeof(struct ipv6hdr);
if (opt)
pktlength += opt->opt_flen + opt->opt_nflen;
if (pktlength > 0xFFFF + sizeof(struct ipv6hdr)) {
/* Jumbo datagram.
It is assumed, that in the case of hdrincl
jumbo option is supplied by user.
*/
pktlength += 8;
jumbolen = pktlength - sizeof(struct ipv6hdr);
}
}
mtu = dst->pmtu;
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
else if (np->pmtudisc == IPV6_PMTUDISC_DONT)
mtu = IPV6_MIN_MTU;
}
/* Critical arithmetic overflow check.
FIXME: may gcc optimize it out? --ANK (980726)
*/
if (pktlength < length) {
ipv6_local_error(sk, EMSGSIZE, fl, mtu);
err = -EMSGSIZE;
goto out;
}
if (flags&MSG_CONFIRM)
dst_confirm(dst);
if (pktlength <= mtu) {
struct sk_buff *skb;
struct ipv6hdr *hdr;
struct net_device *dev = dst->dev;
err = 0;
if (flags&MSG_PROBE)
goto out;
skb = sock_alloc_send_skb(sk, pktlength + 15 +
dev->hard_header_len,
flags & MSG_DONTWAIT, &err);
if (skb == NULL) {
IP6_INC_STATS(Ip6OutDiscards);
goto out;
}
skb->dst = dst_clone(dst);
skb_reserve(skb, (dev->hard_header_len + 15) & ~15);
hdr = (struct ipv6hdr *) skb->tail;
skb->nh.ipv6h = hdr;
if (!sk->protinfo.af_inet.hdrincl) {
ip6_bld_1(sk, skb, fl, hlimit,
jumbolen ? sizeof(struct ipv6hdr) : pktlength);
if (opt || jumbolen) {
u8 *prev_hdr = &hdr->nexthdr;
prev_hdr = ipv6_build_nfrag_opts(skb, prev_hdr, opt, final_dst, jumbolen);
if (opt && opt->opt_flen)
ipv6_build_frag_opts(skb, prev_hdr, opt);
}
}
skb_put(skb, length);
err = getfrag(data, &hdr->saddr,
((char *) hdr) + (pktlength - length),
0, length);
if (!err) {
IP6_INC_STATS(Ip6OutRequests);
err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, ip6_maybe_reroute);
} else {
err = -EFAULT;
kfree_skb(skb);
}
} else {
if (sk->protinfo.af_inet.hdrincl || jumbolen ||
np->pmtudisc == IPV6_PMTUDISC_DO) {
ipv6_local_error(sk, EMSGSIZE, fl, mtu);
err = -EMSGSIZE;
goto out;
}
err = ip6_frag_xmit(sk, getfrag, data, dst, fl, opt, final_dst, hlimit,
flags, length, mtu);
}
/*
* cleanup
*/
out:
ip6_dst_store(sk, dst, fl->nl_u.ip6_u.daddr == &np->daddr ? &np->daddr : NULL);
if (err > 0)
err = np->recverr ? net_xmit_errno(err) : 0;
return err;
}