/**
* mipv6_mn_get_pref_ha - get preferred home agent for prefix
* @prefix: prefix
* @plen: prefix length
*
* Is this useful?
**/
struct in6_addr *mipv6_mn_get_prefha(struct in6_addr *prefix, int plen)
{
unsigned long flags;
struct mipv6_halist_entry *entry = NULL;
struct in6_addr *ha_addr;
struct prefha_iterator_args args;
DEBUG_FUNC();
ha_addr = kmalloc(sizeof(struct in6_addr), GFP_ATOMIC);
if (ha_addr == NULL) {
return NULL;
}
ipv6_addr_copy(&args.prefix, prefix);
args.plen = plen;
read_lock_irqsave(&home_agents->lock, flags);
/* search for HA in home subnet with highest preference */
if (entry == NULL) {
hashlist_iterate(home_agents->entries, &args, prefha_iterator);
entry = args.entry;
}
/* no suitable HA could be found */
if (entry == NULL) {
read_unlock_irqrestore(&home_agents->lock, flags);
kfree(ha_addr);
return NULL;
}
ipv6_addr_copy(ha_addr, &entry->global_addr);
read_unlock_irqrestore(&home_agents->lock, flags);
return ha_addr;
}
static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipv6hdr *ip6h;
int size = sizeof(struct ipv6hdr);
int err = -EINVAL;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
skb_push(skb, size);
memmove(skb->data, skb->nh.raw, size);
skb->nh.raw = skb->data;
skb->mac.raw = memmove(skb->data - skb->mac_len,
skb->mac.raw, skb->mac_len);
ip6h = skb->nh.ipv6h;
ip6h->payload_len = htons(skb->len - size);
ipv6_addr_copy(&ip6h->daddr, (struct in6_addr *) &x->sel.daddr.a6);
ipv6_addr_copy(&ip6h->saddr, (struct in6_addr *) &x->sel.saddr.a6);
err = 0;
out:
return err;
}
/* Add encapsulation header.
*
* The top IP header will be constructed per draft-nikander-esp-beet-mode-06.txt.
* The following fields in it shall be filled in by x->type->output:
* payload_len
*
* On exit, skb->h will be set to the start of the encapsulation header to be
* filled in by x->type->output and skb->nh will be set to the nextheader field
* of the extension header directly preceding the encapsulation header, or in
* its absence, that of the top IP header. The value of skb->data will always
* point to the top IP header.
*/
static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
{
struct ipv6hdr *iph, *top_iph;
u8 *prevhdr;
int hdr_len;
skb_push(skb, x->props.header_len);
iph = skb->nh.ipv6h;
hdr_len = ip6_find_1stfragopt(skb, &prevhdr);
skb->nh.raw = prevhdr - x->props.header_len;
skb->h.raw = skb->data + hdr_len;
memmove(skb->data, iph, hdr_len);
skb->nh.raw = skb->data;
top_iph = skb->nh.ipv6h;
skb->nh.raw = &top_iph->nexthdr;
skb->h.ipv6h = top_iph + 1;
ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
return 0;
}
struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
struct net_device *dev)
{
struct in6_rtmsg rtmsg;
memset(&rtmsg, 0, sizeof(struct in6_rtmsg));
rtmsg.rtmsg_type = RTMSG_NEWROUTE;
ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr);
rtmsg.rtmsg_metric = 1024;
rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP;
rtmsg.rtmsg_ifindex = dev->ifindex;
ip6_route_add(&rtmsg, NULL);
return rt6_get_dflt_router(gwaddr, dev);
}
/*
* Handle IPV6_RECVPATHMTU
*/
int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len,
int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
struct sockaddr_in6 *sin;
struct ip6_mtuinfo mtu_info;
int err;
int copied;
err = -EAGAIN;
skb = xchg(&np->rxpmtu, NULL);
if (skb == NULL)
goto out;
copied = skb->len;
if (copied > len) {
msg->msg_flags |= MSG_TRUNC;
copied = len;
}
err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied);
if (err)
goto out_free_skb;
sock_recv_timestamp(msg, sk, skb);
memcpy(&mtu_info, IP6CBMTU(skb), sizeof(mtu_info));
sin = (struct sockaddr_in6 *)msg->msg_name;
if (sin) {
sin->sin6_family = AF_INET6;
sin->sin6_flowinfo = 0;
sin->sin6_port = 0;
sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr);
*addr_len = sizeof(*sin);
}
put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
err = copied;
out_free_skb:
kfree_skb(skb);
out:
return err;
}
/**
* ip6_dst_lookup_flow - perform route lookup on flow with ipsec
* @sk: socket which provides route info
* @fl6: flow to lookup
* @final_dst: final destination address for ipsec lookup
* @can_sleep: we are in a sleepable context
*
* This function performs a route lookup on the given flow.
*
* It returns a valid dst pointer on success, or a pointer encoded
* error code.
*/
struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
const struct in6_addr *final_dst,
bool can_sleep)
{
struct dst_entry *dst = NULL;
int err;
err = ip6_dst_lookup_tail(sk, &dst, fl6);
if (err)
return ERR_PTR(err);
if (final_dst)
ipv6_addr_copy(&fl6->daddr, final_dst);
if (can_sleep)
fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
return xfrm_lookup(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0);
}
static int getaddr_iterator(void *data, void *args,
struct in6_addr *addr,
unsigned long *pref)
{
struct mipv6_halist_entry *entry =
(struct mipv6_halist_entry *)data;
struct getaddr_iterator_args *state =
(struct getaddr_iterator_args *)args;
if (entry->ifindex != state->dev->ifindex)
return ITERATOR_CONT;
if (ipv6_chk_addr(&entry->global_addr, state->dev)) {
ipv6_addr_copy(state->addr, &entry->global_addr);
return ITERATOR_STOP;
}
return ITERATOR_CONT;
}
/*
* Assign bond->master_ipv6 to the next IPv6 address in the list, or
* zero it out if there are none.
*/
static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr)
{
struct inet6_dev *idev;
if (!dev)
return;
idev = in6_dev_get(dev);
if (!idev)
return;
read_lock_bh(&idev->lock);
if (!list_empty(&idev->addr_list)) {
struct inet6_ifaddr *ifa
= list_first_entry(&idev->addr_list,
struct inet6_ifaddr, if_list);
ipv6_addr_copy(addr, &ifa->addr);
} else
static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
const struct in6_addr *addr)
{
const struct nf_afinfo *afinfo;
struct flowi6 flow;
struct rt6_info *rt;
u32 ret;
int route_err;
memset(&flow, 0, sizeof(flow));
ipv6_addr_copy(&flow.daddr, addr);
if (dev)
flow.flowi6_oif = dev->ifindex;
rcu_read_lock();
afinfo = nf_get_afinfo(NFPROTO_IPV6);
if (afinfo != NULL)
route_err = afinfo->route(net, (struct dst_entry **)&rt,
flowi6_to_flowi(&flow), !!dev);
else
route_err = 1;
rcu_read_unlock();
if (route_err)
return XT_ADDRTYPE_UNREACHABLE;
if (rt->rt6i_flags & RTF_REJECT)
ret = XT_ADDRTYPE_UNREACHABLE;
else
ret = 0;
if (rt->rt6i_flags & RTF_LOCAL)
ret |= XT_ADDRTYPE_LOCAL;
if (rt->rt6i_flags & RTF_ANYCAST)
ret |= XT_ADDRTYPE_ANYCAST;
dst_release(&rt->dst);
return ret;
}
static int select_source_address(struct in6_addr *src, const struct in6_addr *dst)
{
int err = 0;
int family = AF_INET;
struct idxmap *idxmap[16] = { 0 };
struct in6_addr lpback = IN6ADDR_LOOPBACK_INIT;
HIP_DEBUG_IN6ADDR("dst", dst);
/* Required for loopback connections */
if (!ipv6_addr_cmp(dst, &lpback)) {
ipv6_addr_copy(src, dst);
goto out_err;
}
HIP_IFEL(hip_iproute_get(&hipfw_nl_route, src, dst, NULL, NULL, family, idxmap), -1, "Finding ip route failed\n");
HIP_DEBUG_IN6ADDR("src", src);
out_err:
return err;
}
int ip6_rt_addr_add(struct in6_addr *addr, struct net_device *dev)
{
struct rt6_info *rt;
rt = dst_alloc(&ip6_dst_ops);
if (rt == NULL)
return -ENOMEM;
rt->u.dst.flags = DST_HOST;
rt->u.dst.input = ip6_input;
rt->u.dst.output = ip6_output;
rt->rt6i_dev = dev_get_by_name("lo");
if (rt->rt6i_dev == NULL) {
if (net_ratelimit())
printk(KERN_WARNING
"ip6_rt_addr_addr(): cannot find loopback device.\n");
dst_free((struct dst_entry *) rt);
return -ENODEV;
}
rt->u.dst.pmtu = ipv6_get_mtu(rt->rt6i_dev);
rt->u.dst.advmss = max_t(unsigned int, rt->u.dst.pmtu - 60, ip6_rt_min_advmss);
if (rt->u.dst.advmss > 65535-20)
rt->u.dst.advmss = 65535;
rt->rt6i_hoplimit = ipv6_get_hoplimit(rt->rt6i_dev);
rt->u.dst.obsolete = -1;
rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
if (rt->rt6i_nexthop == NULL) {
dst_free((struct dst_entry *) rt);
return -ENOMEM;
}
ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
rt->rt6i_dst.plen = 128;
rt6_ins(rt, NULL);
return 0;
}
int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr)
{
struct inet6_dev *idev;
int err = -EADDRNOTAVAIL;
read_lock(&addrconf_lock);
if ((idev = __in6_dev_get(dev)) != NULL) {
struct inet6_ifaddr *ifp;
read_lock_bh(&idev->lock);
for (ifp=idev->addr_list; ifp; ifp=ifp->if_next) {
if (ifp->scope == IFA_LINK && !(ifp->flags&IFA_F_TENTATIVE)) {
ipv6_addr_copy(addr, &ifp->addr);
err = 0;
break;
}
}
read_unlock_bh(&idev->lock);
}
read_unlock(&addrconf_lock);
return err;
}
void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct sock_exterr_skb *serr;
struct ipv6hdr *iph;
struct sk_buff *skb;
if (!np->recverr)
return;
skb = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
if (!skb)
return;
skb->protocol = htons(ETH_P_IPV6);
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
ipv6_addr_copy(&iph->daddr, &fl6->daddr);
serr = SKB_EXT_ERR(skb);
serr->ee.ee_errno = err;
serr->ee.ee_origin = SO_EE_ORIGIN_LOCAL;
serr->ee.ee_type = 0;
serr->ee.ee_code = 0;
serr->ee.ee_pad = 0;
serr->ee.ee_info = info;
serr->ee.ee_data = 0;
serr->addr_offset = (u8 *)&iph->daddr - skb_network_header(skb);
serr->port = fl6->fl6_dport;
__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
skb_reset_transport_header(skb);
if (sock_queue_err_skb(sk, skb))
kfree_skb(skb);
}
int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet6_skb_parm *opt = IP6CB(skb);
unsigned char *nh = skb_network_header(skb);
if (np->rxopt.bits.rxinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = opt->iif;
ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr);
put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxhlim) {
int hlim = ipv6_hdr(skb)->hop_limit;
put_cmsg(msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
}
if (np->rxopt.bits.rxtclass) {
int tclass = (ntohl(*(__be32 *)ipv6_hdr(skb)) >> 20) & 0xff;
put_cmsg(msg, SOL_IPV6, IPV6_TCLASS, sizeof(tclass), &tclass);
}
static int
__xfrm4_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int nx,
struct flowi *fl, struct dst_entry **dst_p)
{
struct dst_entry *dst, *dst_prev;
struct rtable *rt0 = (struct rtable*)(*dst_p);
struct rtable *rt = rt0;
struct flowi fl_tunnel = {
.nl_u = {
.ip4_u = {
.saddr = fl->fl4_src,
.daddr = fl->fl4_dst,
.tos = fl->fl4_tos
}
}
};
int i;
int err;
int header_len = 0;
int trailer_len = 0;
dst = dst_prev = NULL;
dst_hold(&rt->u.dst);
for (i = 0; i < nx; i++) {
struct dst_entry *dst1 = dst_alloc(&xfrm4_dst_ops);
struct xfrm_dst *xdst;
if (unlikely(dst1 == NULL)) {
err = -ENOBUFS;
dst_release(&rt->u.dst);
goto error;
}
if (!dst)
dst = dst1;
else {
dst_prev->child = dst1;
dst1->flags |= DST_NOHASH;
dst_clone(dst1);
}
xdst = (struct xfrm_dst *)dst1;
xdst->route = &rt->u.dst;
xdst->genid = xfrm[i]->genid;
dst1->next = dst_prev;
dst_prev = dst1;
header_len += xfrm[i]->props.header_len;
trailer_len += xfrm[i]->props.trailer_len;
if (xfrm[i]->props.mode == XFRM_MODE_TUNNEL) {
unsigned short encap_family = xfrm[i]->props.family;
switch(encap_family) {
case AF_INET:
fl_tunnel.fl4_dst = xfrm[i]->id.daddr.a4;
fl_tunnel.fl4_src = xfrm[i]->props.saddr.a4;
break;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
case AF_INET6:
ipv6_addr_copy(&fl_tunnel.fl6_dst, (struct in6_addr*)&xfrm[i]->id.daddr.a6);
ipv6_addr_copy(&fl_tunnel.fl6_src, (struct in6_addr*)&xfrm[i]->props.saddr.a6);
break;
#endif
default:
BUG_ON(1);
}
err = xfrm_dst_lookup((struct xfrm_dst **)&rt,
&fl_tunnel, encap_family);
if (err)
goto error;
} else
dst_hold(&rt->u.dst);
}
dst_prev->child = &rt->u.dst;
dst->path = &rt->u.dst;
*dst_p = dst;
dst = dst_prev;
dst_prev = *dst_p;
i = 0;
for (; dst_prev != &rt->u.dst; dst_prev = dst_prev->child) {
struct xfrm_dst *x = (struct xfrm_dst*)dst_prev;
struct xfrm_state_afinfo *afinfo;
x->u.rt.fl = *fl;
dst_prev->xfrm = xfrm[i++];
dst_prev->dev = rt->u.dst.dev;
if (rt->u.dst.dev)
dev_hold(rt->u.dst.dev);
dst_prev->obsolete = -1;
dst_prev->flags |= DST_HOST;
dst_prev->lastuse = jiffies;
dst_prev->header_len = header_len;
dst_prev->nfheader_len = 0;
dst_prev->trailer_len = trailer_len;
memcpy(&dst_prev->metrics, &x->route->metrics, sizeof(dst_prev->metrics));
/* Copy neighbout for reachability confirmation */
dst_prev->neighbour = neigh_clone(rt->u.dst.neighbour);
dst_prev->input = rt->u.dst.input;
/* XXX: When IPv6 module can be unloaded, we should manage reference
* to xfrm6_output in afinfo->output. Miyazawa
* */
afinfo = xfrm_state_get_afinfo(dst_prev->xfrm->props.family);
if (!afinfo) {
dst = *dst_p;
err = -EAFNOSUPPORT;
goto error;
}
dst_prev->output = afinfo->output;
xfrm_state_put_afinfo(afinfo);
if (dst_prev->xfrm->props.family == AF_INET && rt->peer)
atomic_inc(&rt->peer->refcnt);
x->u.rt.peer = rt->peer;
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
x->u.rt.rt_flags = rt0->rt_flags&(RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL);
x->u.rt.rt_type = rt->rt_type;
x->u.rt.rt_src = rt0->rt_src;
x->u.rt.rt_dst = rt0->rt_dst;
x->u.rt.rt_gateway = rt->rt_gateway;
x->u.rt.rt_spec_dst = rt0->rt_spec_dst;
x->u.rt.idev = rt0->idev;
in_dev_hold(rt0->idev);
header_len -= x->u.dst.xfrm->props.header_len;
trailer_len -= x->u.dst.xfrm->props.trailer_len;
}
xfrm_init_pmtu(dst);
return 0;
error:
if (dst)
dst_free(dst);
return err;
}
int ipv6_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct ipv6_pinfo *np = inet6_sk(sk);
int len;
int val;
if (level == SOL_IP && sk->sk_type != SOCK_RAW)
return udp_prot.getsockopt(sk, level, optname, optval, optlen);
if(level!=SOL_IPV6)
return -ENOPROTOOPT;
if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
case IPV6_ADDRFORM:
if (sk->sk_protocol != IPPROTO_UDP &&
sk->sk_protocol != IPPROTO_TCP)
return -EINVAL;
if (sk->sk_state != TCP_ESTABLISHED)
return -ENOTCONN;
val = sk->sk_family;
break;
case MCAST_MSFILTER:
{
struct group_filter gsf;
int err;
if (len < GROUP_FILTER_SIZE(0))
return -EINVAL;
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0)))
return -EFAULT;
lock_sock(sk);
err = ip6_mc_msfget(sk, &gsf,
(struct group_filter __user *)optval, optlen);
release_sock(sk);
return err;
}
case IPV6_PKTOPTIONS:
{
struct msghdr msg;
struct sk_buff *skb;
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = optval;
msg.msg_controllen = len;
msg.msg_flags = 0;
lock_sock(sk);
skb = np->pktoptions;
if (skb)
atomic_inc(&skb->users);
release_sock(sk);
if (skb) {
int err = datagram_recv_ctl(sk, &msg, skb);
kfree_skb(skb);
if (err)
return err;
} else {
if (np->rxopt.bits.rxinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif;
ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr);
put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxhlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_HOPLIMIT, sizeof(hlim), &hlim);
}
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IPV6_MTU:
{
struct dst_entry *dst;
val = 0;
lock_sock(sk);
dst = sk_dst_get(sk);
if (dst) {
val = dst_mtu(dst);
dst_release(dst);
}
release_sock(sk);
if (!val)
return -ENOTCONN;
break;
}
case IPV6_V6ONLY:
val = np->ipv6only;
break;
case IPV6_PKTINFO:
val = np->rxopt.bits.rxinfo;
break;
case IPV6_HOPLIMIT:
val = np->rxopt.bits.rxhlim;
break;
case IPV6_RTHDR:
val = np->rxopt.bits.srcrt;
break;
case IPV6_HOPOPTS:
val = np->rxopt.bits.hopopts;
break;
case IPV6_DSTOPTS:
val = np->rxopt.bits.dstopts;
break;
case IPV6_FLOWINFO:
val = np->rxopt.bits.rxflow;
break;
case IPV6_UNICAST_HOPS:
val = np->hop_limit;
break;
case IPV6_MULTICAST_HOPS:
val = np->mcast_hops;
break;
case IPV6_MULTICAST_LOOP:
val = np->mc_loop;
break;
case IPV6_MULTICAST_IF:
val = np->mcast_oif;
break;
case IPV6_MTU_DISCOVER:
val = np->pmtudisc;
break;
case IPV6_RECVERR:
val = np->recverr;
break;
case IPV6_FLOWINFO_SEND:
val = np->sndflow;
break;
default:
#ifdef CONFIG_NETFILTER
lock_sock(sk);
val = nf_getsockopt(sk, PF_INET6, optname, optval,
&len);
release_sock(sk);
if (val >= 0)
val = put_user(len, optlen);
return val;
#else
return -EINVAL;
#endif
}
len = min_t(unsigned int, sizeof(int), len);
if(put_user(len, optlen))
return -EFAULT;
if(copy_to_user(optval,&val,len))
return -EFAULT;
return 0;
}
int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *daddr, *final_p = NULL, final;
struct dst_entry *dst;
struct flowi fl;
struct ip6_flowlabel *flowlabel = NULL;
int addr_type;
int err;
if (usin->sin6_family == AF_INET) {
if (__ipv6_only_sock(sk))
return -EAFNOSUPPORT;
err = ip4_datagram_connect(sk, uaddr, addr_len);
goto ipv4_connected;
}
if (addr_len < SIN6_LEN_RFC2133)
return -EINVAL;
if (usin->sin6_family != AF_INET6)
return -EAFNOSUPPORT;
memset(&fl, 0, sizeof(fl));
if (np->sndflow) {
fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
if (flowlabel == NULL)
return -EINVAL;
ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
}
}
addr_type = ipv6_addr_type(&usin->sin6_addr);
if (addr_type == IPV6_ADDR_ANY) {
/*
* connect to self
*/
usin->sin6_addr.s6_addr[15] = 0x01;
}
daddr = &usin->sin6_addr;
if (addr_type == IPV6_ADDR_MAPPED) {
struct sockaddr_in sin;
if (__ipv6_only_sock(sk)) {
err = -ENETUNREACH;
goto out;
}
sin.sin_family = AF_INET;
sin.sin_addr.s_addr = daddr->s6_addr32[3];
sin.sin_port = usin->sin6_port;
err = ip4_datagram_connect(sk,
(struct sockaddr*) &sin,
sizeof(sin));
ipv4_connected:
if (err)
goto out;
ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr);
if (ipv6_addr_any(&np->saddr)) {
ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000ffff),
inet->saddr);
}
if (ipv6_addr_any(&np->rcv_saddr)) {
ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000ffff),
inet->rcv_saddr);
}
goto out;
}
if (addr_type&IPV6_ADDR_LINKLOCAL) {
if (addr_len >= sizeof(struct sockaddr_in6) &&
usin->sin6_scope_id) {
if (sk->sk_bound_dev_if &&
sk->sk_bound_dev_if != usin->sin6_scope_id) {
err = -EINVAL;
goto out;
}
sk->sk_bound_dev_if = usin->sin6_scope_id;
}
if (!sk->sk_bound_dev_if && (addr_type & IPV6_ADDR_MULTICAST))
sk->sk_bound_dev_if = np->mcast_oif;
/* Connect to link-local address requires an interface */
if (!sk->sk_bound_dev_if) {
err = -EINVAL;
goto out;
}
}
ipv6_addr_copy(&np->daddr, daddr);
np->flow_label = fl.fl6_flowlabel;
inet->dport = usin->sin6_port;
/*
* Check for a route to destination an obtain the
* destination cache for it.
*/
fl.proto = sk->sk_protocol;
ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
ipv6_addr_copy(&fl.fl6_src, &np->saddr);
fl.oif = sk->sk_bound_dev_if;
fl.fl_ip_dport = inet->dport;
fl.fl_ip_sport = inet->sport;
if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST))
fl.oif = np->mcast_oif;
security_sk_classify_flow(sk, &fl);
if (flowlabel) {
if (flowlabel->opt && flowlabel->opt->srcrt) {
struct rt0_hdr *rt0 = (struct rt0_hdr *) flowlabel->opt->srcrt;
ipv6_addr_copy(&final, &fl.fl6_dst);
ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
final_p = &final;
}
} else if (np->opt && np->opt->srcrt) {
/* 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);
}
struct sk_buff *ndisc_build_skb(struct net_device *dev,
const struct in6_addr *daddr,
const struct in6_addr *saddr,
struct icmp6hdr *icmp6h,
const struct in6_addr *target,
int llinfo)
{
struct net *net = dev_net(dev);
struct sock *sk = net->ipv6.ndisc_sk;
struct sk_buff *skb;
struct icmp6hdr *hdr;
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
int len;
u8 *opt;
if (!dev->addr_len)
llinfo = 0;
len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0);
if (llinfo)
len += ndisc_opt_addr_space(dev);
skb = alloc_skb((MAX_HEADER + sizeof(struct ipv6hdr) +
len + hlen + tlen), GFP_ATOMIC);
if (!skb) {
ND_PRINTK0(KERN_ERR
"ICMPv6 ND: %s() failed to allocate an skb.\n",
__func__);
return NULL;
}
skb_reserve(skb, hlen);
ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len);
skb->transport_header = skb->tail;
skb_put(skb, len);
hdr = (struct icmp6hdr *)skb_transport_header(skb);
memcpy(hdr, icmp6h, sizeof(*hdr));
opt = skb_transport_header(skb) + sizeof(struct icmp6hdr);
if (target) {
ipv6_addr_copy((struct in6_addr *)opt, target);
opt += sizeof(*target);
}
if (llinfo)
ndisc_fill_addr_option(opt, llinfo, dev->dev_addr,
dev->addr_len, dev->type);
hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len,
IPPROTO_ICMPV6,
csum_partial(hdr,
len, 0));
/* Manually assign socket ownership as we avoid calling
* sock_alloc_send_pskb() to bypass wmem buffer limits
*/
skb_set_owner_w(skb, sk);
return skb;
}
int
ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
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, sizeof(struct ipv6hdr),
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_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, 1|2|4)))
goto tx_error_icmp;
local = __ip_vs_is_local_route6(rt);
/*
* 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_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to local address");
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && skb->dev && !(skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LOOPBACK) {
IP_VS_DBG_RL_PKT(1, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): "
"stopping DNAT to loopback address");
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu && !skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP_VS_DBG_RL_PKT(0, AF_INET6, pp, skb, 0,
"ip_vs_nat_xmit_v6(): frag needed for");
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct ipv6hdr)))
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;
ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6);
if (!local || !skb->dev) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
/* destined to loopback, do we need to change route? */
dst_release(&rt->dst);
}
IP_VS_DBG_PKT(10, AF_INET6, 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_IPV6, skb, cp, local);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
LeaveFunction(10);
kfree_skb(skb);
return NF_STOLEN;
tx_error_put:
dst_release(&rt->dst);
goto tx_error;
}
static int ip6mr_cache_report(struct sk_buff *pkt, mifi_t mifi, int assert)
{
struct sk_buff *skb;
struct mrt6msg *msg;
int ret;
#ifdef CONFIG_IPV6_PIMSM_V2
if (assert == MRT6MSG_WHOLEPKT)
skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt)
+sizeof(*msg));
else
#endif
skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC);
if (!skb)
return -ENOBUFS;
/* I suppose that internal messages
* do not require checksums */
skb->ip_summed = CHECKSUM_UNNECESSARY;
#ifdef CONFIG_IPV6_PIMSM_V2
if (assert == MRT6MSG_WHOLEPKT) {
/* Ugly, but we have no choice with this interface.
Duplicate old header, fix length etc.
And all this only to mangle msg->im6_msgtype and
to set msg->im6_mbz to "mbz" :-)
*/
skb_push(skb, -skb_network_offset(pkt));
skb_push(skb, sizeof(*msg));
skb_reset_transport_header(skb);
msg = (struct mrt6msg *)skb_transport_header(skb);
msg->im6_mbz = 0;
msg->im6_msgtype = MRT6MSG_WHOLEPKT;
msg->im6_mif = reg_vif_num;
msg->im6_pad = 0;
ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else
#endif
{
/*
* Copy the IP header
*/
skb_put(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr));
/*
* Add our header
*/
skb_put(skb, sizeof(*msg));
skb_reset_transport_header(skb);
msg = (struct mrt6msg *)skb_transport_header(skb);
msg->im6_mbz = 0;
msg->im6_msgtype = assert;
msg->im6_mif = mifi;
msg->im6_pad = 0;
ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
skb->dst = dst_clone(pkt->dst);
skb->ip_summed = CHECKSUM_UNNECESSARY;
skb_pull(skb, sizeof(struct ipv6hdr));
}
if (mroute6_socket == NULL) {
kfree_skb(skb);
return -EINVAL;
}
/*
* Deliver to user space multicast routing algorithms
*/
if ((ret = sock_queue_rcv_skb(mroute6_socket, skb)) < 0) {
if (net_ratelimit())
printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n");
kfree_skb(skb);
}
return ret;
}
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
struct ipv6_txoptions *opt, int ipfragok)
{
struct ipv6_pinfo *np = sk ? inet6_sk(sk) : NULL;
struct in6_addr *first_hop = &fl->fl6_dst;
struct dst_entry *dst = skb->dst;
struct ipv6hdr *hdr;
u8 proto = fl->proto;
int seg_len = skb->len;
int hlimit;
u32 mtu;
if (opt) {
int head_room;
/* First: exthdrs may take lots of space (~8K for now)
MAX_HEADER is not enough.
*/
head_room = opt->opt_nflen + opt->opt_flen;
seg_len += head_room;
head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
if (skb_headroom(skb) < head_room) {
struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
kfree_skb(skb);
skb = skb2;
if (skb == NULL) {
IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
return -ENOBUFS;
}
if (sk)
skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
}
hdr = skb->nh.ipv6h = (struct ipv6hdr*)skb_push(skb, sizeof(struct ipv6hdr));
/*
* Fill in the IPv6 header
*/
*(u32*)hdr = htonl(0x60000000) | fl->fl6_flowlabel;
hlimit = -1;
if (np)
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = dst_metric(dst, RTAX_HOPLIMIT);
if (hlimit < 0)
hlimit = ipv6_get_hoplimit(dst->dev);
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
ipv6_addr_copy(&hdr->daddr, first_hop);
mtu = dst_mtu(dst);
if ((skb->len <= mtu) || ipfragok) {
IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, ip6_maybe_reroute);
}
if (net_ratelimit())
printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
int ip6_push_pending_frames(struct sock *sk)
{
struct sk_buff *skb, *tmp_skb;
struct sk_buff **tail_skb;
struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct ipv6hdr *hdr;
struct ipv6_txoptions *opt = np->cork.opt;
struct rt6_info *rt = np->cork.rt;
struct flowi *fl = &inet->cork.fl;
unsigned char proto = fl->proto;
int err = 0;
if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
goto out;
tail_skb = &(skb_shinfo(skb)->frag_list);
/* move skb->data to ip header from ext header */
if (skb->data < skb->nh.raw)
__skb_pull(skb, skb->nh.raw - skb->data);
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
__skb_pull(tmp_skb, skb->h.raw - skb->nh.raw);
*tail_skb = tmp_skb;
tail_skb = &(tmp_skb->next);
skb->len += tmp_skb->len;
skb->data_len += tmp_skb->len;
skb->truesize += tmp_skb->truesize;
__sock_put(tmp_skb->sk);
tmp_skb->destructor = NULL;
tmp_skb->sk = NULL;
}
ipv6_addr_copy(final_dst, &fl->fl6_dst);
__skb_pull(skb, skb->h.raw - skb->nh.raw);
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
skb->nh.ipv6h = hdr = (struct ipv6hdr*) skb_push(skb, sizeof(struct ipv6hdr));
*(u32*)hdr = fl->fl6_flowlabel | htonl(0x60000000);
if (skb->len <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN)
hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
else
hdr->payload_len = 0;
hdr->hop_limit = np->cork.hop_limit;
hdr->nexthdr = proto;
ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
ipv6_addr_copy(&hdr->daddr, final_dst);
skb->dst = dst_clone(&rt->u.dst);
IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, skb->dst->dev, dst_output);
if (err) {
if (err > 0)
err = np->recverr ? net_xmit_errno(err) : 0;
if (err)
goto error;
}
out:
inet->cork.flags &= ~IPCORK_OPT;
if (np->cork.opt) {
kfree(np->cork.opt);
np->cork.opt = NULL;
}
if (np->cork.rt) {
dst_release(&np->cork.rt->u.dst);
np->cork.rt = NULL;
inet->cork.flags &= ~IPCORK_ALLFRAG;
}
memset(&inet->cork.fl, 0, sizeof(inet->cork.fl));
return err;
error:
goto out;
}
int ip6_push_pending_frames(struct sock *sk)
{
struct sk_buff *skb, *tmp_skb;
struct sk_buff **tail_skb;
struct in6_addr final_dst_buf, *final_dst = &final_dst_buf;
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
struct ipv6hdr *hdr;
struct ipv6_txoptions *opt = np->cork.opt;
struct rt6_info *rt = (struct rt6_info *)inet->cork.base.dst;
struct flowi6 *fl6 = &inet->cork.fl.u.ip6;
unsigned char proto = fl6->flowi6_proto;
int err = 0;
if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
goto out;
tail_skb = &(skb_shinfo(skb)->frag_list);
/* move skb->data to ip header from ext header */
if (skb->data < skb_network_header(skb))
__skb_pull(skb, skb_network_offset(skb));
while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
__skb_pull(tmp_skb, skb_network_header_len(skb));
*tail_skb = tmp_skb;
tail_skb = &(tmp_skb->next);
skb->len += tmp_skb->len;
skb->data_len += tmp_skb->len;
skb->truesize += tmp_skb->truesize;
tmp_skb->destructor = NULL;
tmp_skb->sk = NULL;
}
/* Allow local fragmentation. */
if (np->pmtudisc < IPV6_PMTUDISC_DO)
skb->local_df = 1;
ipv6_addr_copy(final_dst, &fl6->daddr);
__skb_pull(skb, skb_network_header_len(skb));
if (opt && opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt && opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &final_dst);
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
*(__be32*)hdr = fl6->flowlabel |
htonl(0x60000000 | ((int)np->cork.tclass << 20));
hdr->hop_limit = np->cork.hop_limit;
hdr->nexthdr = proto;
ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
ipv6_addr_copy(&hdr->daddr, final_dst);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
skb_dst_set(skb, dst_clone(&rt->dst));
IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
if (proto == IPPROTO_ICMPV6) {
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
ICMP6MSGOUT_INC_STATS_BH(net, idev, icmp6_hdr(skb)->icmp6_type);
ICMP6_INC_STATS_BH(net, idev, ICMP6_MIB_OUTMSGS);
}
err = ip6_local_out(skb);
if (err) {
if (err > 0)
err = net_xmit_errno(err);
if (err)
goto error;
}
out:
ip6_cork_release(inet, np);
return err;
error:
IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
goto out;
}
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct ipv6_txoptions *opt)
{
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl6->daddr;
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr;
u8 proto = fl6->flowi6_proto;
int seg_len = skb->len;
int hlimit = -1;
int tclass = 0;
u32 mtu;
if (opt) {
unsigned int head_room;
/* First: exthdrs may take lots of space (~8K for now)
MAX_HEADER is not enough.
*/
head_room = opt->opt_nflen + opt->opt_flen;
seg_len += head_room;
head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);
if (skb_headroom(skb) < head_room) {
struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
if (skb2 == NULL) {
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUTDISCARDS);
kfree_skb(skb);
return -ENOBUFS;
}
kfree_skb(skb);
skb = skb2;
skb_set_owner_w(skb, sk);
}
if (opt->opt_flen)
ipv6_push_frag_opts(skb, opt, &proto);
if (opt->opt_nflen)
ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
/*
* Fill in the IPv6 header
*/
if (np) {
tclass = np->tclass;
hlimit = np->hop_limit;
}
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl6->flowlabel;
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
ipv6_addr_copy(&hdr->daddr, first_hop);
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
mtu = dst_mtu(dst);
if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_OUT, skb->len);
return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL,
dst->dev, dst_output);
}
if (net_ratelimit())
printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh)
{
int err;
struct rtmsg *r;
struct rt6_info *rt;
struct net_device *dev = NULL;
int addr_type;
if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128)
return -EINVAL;
#ifndef CONFIG_IPV6_SUBTREES
if (rtmsg->rtmsg_src_len)
return -EINVAL;
#endif
if (rtmsg->rtmsg_metric == 0)
rtmsg->rtmsg_metric = IP6_RT_PRIO_USER;
rt = dst_alloc(&ip6_dst_ops);
if (rt == NULL)
return -ENOMEM;
rt->u.dst.obsolete = -1;
rt->rt6i_expires = rtmsg->rtmsg_info;
if (nlh && (r = NLMSG_DATA(nlh))) {
rt->rt6i_protocol = r->rtm_protocol;
} else {
rt->rt6i_protocol = RTPROT_BOOT;
}
addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst);
if (addr_type & IPV6_ADDR_MULTICAST)
rt->u.dst.input = ip6_mc_input;
else
rt->u.dst.input = ip6_forward;
rt->u.dst.output = ip6_output;
if (rtmsg->rtmsg_ifindex) {
dev = dev_get_by_index(rtmsg->rtmsg_ifindex);
err = -ENODEV;
if (dev == NULL)
goto out;
}
ipv6_addr_prefix(&rt->rt6i_dst.addr,
&rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len);
rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len;
if (rt->rt6i_dst.plen == 128)
rt->u.dst.flags = DST_HOST;
#ifdef CONFIG_IPV6_SUBTREES
ipv6_addr_prefix(&rt->rt6i_src.addr,
&rtmsg->rtmsg_src, rtmsg->rtmsg_src_len);
rt->rt6i_src.plen = rtmsg->rtmsg_src_len;
#endif
rt->rt6i_metric = rtmsg->rtmsg_metric;
/* We cannot add true routes via loopback here,
they would result in kernel looping; promote them to reject routes
*/
if ((rtmsg->rtmsg_flags&RTF_REJECT) ||
(dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
if (dev)
dev_put(dev);
dev = &loopback_dev;
dev_hold(dev);
rt->u.dst.output = ip6_pkt_discard;
rt->u.dst.input = ip6_pkt_discard;
rt->u.dst.error = -ENETUNREACH;
rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
goto install_route;
}
if (rtmsg->rtmsg_flags & RTF_GATEWAY) {
struct in6_addr *gw_addr;
int gwa_type;
gw_addr = &rtmsg->rtmsg_gateway;
ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway);
gwa_type = ipv6_addr_type(gw_addr);
if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
struct rt6_info *grt;
/* IPv6 strictly inhibits using not link-local
addresses as nexthop address.
Otherwise, router will not able to send redirects.
It is very good, but in some (rare!) curcumstances
(SIT, PtP, NBMA NOARP links) it is handy to allow
some exceptions. --ANK
*/
err = -EINVAL;
if (!(gwa_type&IPV6_ADDR_UNICAST))
goto out;
grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1);
err = -EHOSTUNREACH;
if (grt == NULL)
goto out;
if (dev) {
if (dev != grt->rt6i_dev) {
dst_release(&grt->u.dst);
goto out;
}
} else {
dev = grt->rt6i_dev;
dev_hold(dev);
}
if (!(grt->rt6i_flags&RTF_GATEWAY))
err = 0;
dst_release(&grt->u.dst);
if (err)
goto out;
}
err = -EINVAL;
if (dev == NULL || (dev->flags&IFF_LOOPBACK))
goto out;
}
err = -ENODEV;
if (dev == NULL)
goto out;
if (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) {
rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
if (IS_ERR(rt->rt6i_nexthop)) {
err = PTR_ERR(rt->rt6i_nexthop);
rt->rt6i_nexthop = NULL;
goto out;
}
}
if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr))
rt->rt6i_hoplimit = IPV6_DEFAULT_MCASTHOPS;
else
rt->rt6i_hoplimit = ipv6_get_hoplimit(dev);
rt->rt6i_flags = rtmsg->rtmsg_flags;
install_route:
rt->u.dst.pmtu = ipv6_get_mtu(dev);
rt->u.dst.advmss = max_t(unsigned int, rt->u.dst.pmtu - 60, ip6_rt_min_advmss);
/* Maximal non-jumbo IPv6 payload is 65535 and corresponding
MSS is 65535 - tcp_header_size. 65535 is also valid and
means: "any MSS, rely only on pmtu discovery"
*/
if (rt->u.dst.advmss > 65535-20)
rt->u.dst.advmss = 65535;
rt->u.dst.dev = dev;
return rt6_ins(rt, nlh);
out:
if (dev)
dev_put(dev);
dst_free((struct dst_entry *) rt);
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);
}
/*
* Handle redirects
*/
void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr,
struct neighbour *neigh, int on_link)
{
struct rt6_info *rt, *nrt;
/* Locate old route to this destination. */
rt = rt6_lookup(dest, NULL, neigh->dev->ifindex, 1);
if (rt == NULL)
return;
if (neigh->dev != rt->rt6i_dev)
goto out;
/* Redirect received -> path was valid.
Look, redirects are sent only in response to data packets,
so that this nexthop apparently is reachable. --ANK
*/
dst_confirm(&rt->u.dst);
/* Duplicate redirect: silently ignore. */
if (neigh == rt->u.dst.neighbour)
goto out;
/* Current route is on-link; redirect is always invalid.
Seems, previous statement is not true. It could
be node, which looks for us as on-link (f.e. proxy ndisc)
But then router serving it might decide, that we should
know truth 8)8) --ANK (980726).
*/
if (!(rt->rt6i_flags&RTF_GATEWAY))
goto out;
/*
* RFC 1970 specifies that redirects should only be
* accepted if they come from the nexthop to the target.
* Due to the way default routers are chosen, this notion
* is a bit fuzzy and one might need to check all default
* routers.
*/
if (ipv6_addr_cmp(saddr, &rt->rt6i_gateway)) {
if (rt->rt6i_flags & RTF_DEFAULT) {
struct rt6_info *rt1;
read_lock(&rt6_lock);
for (rt1 = ip6_routing_table.leaf; rt1; rt1 = rt1->u.next) {
if (!ipv6_addr_cmp(saddr, &rt1->rt6i_gateway)) {
dst_hold(&rt1->u.dst);
dst_release(&rt->u.dst);
read_unlock(&rt6_lock);
rt = rt1;
goto source_ok;
}
}
read_unlock(&rt6_lock);
}
if (net_ratelimit())
printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop "
"for redirect target\n");
goto out;
}
source_ok:
/*
* We have finally decided to accept it.
*/
nrt = ip6_rt_copy(rt);
if (nrt == NULL)
goto out;
nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
if (on_link)
nrt->rt6i_flags &= ~RTF_GATEWAY;
ipv6_addr_copy(&nrt->rt6i_dst.addr, dest);
nrt->rt6i_dst.plen = 128;
nrt->u.dst.flags |= DST_HOST;
ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
nrt->rt6i_nexthop = neigh_clone(neigh);
/* Reset pmtu, it may be better */
nrt->u.dst.pmtu = ipv6_get_mtu(neigh->dev);
nrt->u.dst.advmss = max_t(unsigned int, nrt->u.dst.pmtu - 60, ip6_rt_min_advmss);
if (rt->u.dst.advmss > 65535-20)
rt->u.dst.advmss = 65535;
nrt->rt6i_hoplimit = ipv6_get_hoplimit(neigh->dev);
if (rt6_ins(nrt, NULL))
goto out;
if (rt->rt6i_flags&RTF_CACHE) {
ip6_del_rt(rt, NULL);
return;
}
out:
dst_release(&rt->u.dst);
return;
}
int
ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rt6_info *rt; /* Route to the other host */
struct in6_addr saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct ipv6hdr *old_iph = ipv6_hdr(skb);
struct ipv6hdr *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_v6(skb, cp->dest, &cp->daddr.in6,
&saddr, 1, 1|2)))
goto tx_error_icmp;
if (__ip_vs_is_local_route6(rt)) {
dst_release(&rt->dst);
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct ipv6hdr);
if (mtu < IPV6_MIN_MTU) {
IP_VS_DBG_RL("%s(): mtu less than %d\n", __func__,
IPV6_MIN_MTU);
goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) &&
!skb_is_gso(skb)) {
if (!skb->dev) {
struct net *net = dev_net(skb_dst(skb)->dev);
skb->dev = net->loopback_dev;
}
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, 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 ipv6hdr);
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) {
dst_release(&rt->dst);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
kfree_skb(skb);
skb = new_skb;
old_iph = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct ipv6hdr));
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 = ipv6_hdr(skb);
iph->version = 6;
iph->nexthdr = IPPROTO_IPV6;
iph->payload_len = old_iph->payload_len;
be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
iph->priority = old_iph->priority;
memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
ipv6_addr_copy(&iph->daddr, &cp->daddr.in6);
ipv6_addr_copy(&iph->saddr, &saddr);
iph->hop_limit = old_iph->hop_limit;
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip6_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:
dst_release(&rt->dst);
goto tx_error;
}
void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
struct net_device *dev, u32 pmtu)
{
struct rt6_info *rt, *nrt;
if (pmtu < IPV6_MIN_MTU) {
if (net_ratelimit())
printk(KERN_DEBUG "rt6_pmtu_discovery: invalid MTU value %d\n",
pmtu);
/* According to RFC1981, the PMTU is set to the IPv6 minimum
link MTU if the node receives a Packet Too Big message
reporting next-hop MTU that is less than the IPv6 minimum MTU.
*/
pmtu = IPV6_MIN_MTU;
}
rt = rt6_lookup(daddr, saddr, dev->ifindex, 0);
if (rt == NULL)
return;
if (pmtu >= rt->u.dst.pmtu)
goto out;
/* New mtu received -> path was valid.
They are sent only in response to data packets,
so that this nexthop apparently is reachable. --ANK
*/
dst_confirm(&rt->u.dst);
/* Host route. If it is static, it would be better
not to override it, but add new one, so that
when cache entry will expire old pmtu
would return automatically.
*/
if (rt->rt6i_flags & RTF_CACHE) {
rt->u.dst.pmtu = pmtu;
dst_set_expires(&rt->u.dst, ip6_rt_mtu_expires);
rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
goto out;
}
/* Network route.
Two cases are possible:
1. It is connected route. Action: COW
2. It is gatewayed route or NONEXTHOP route. Action: clone it.
*/
if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) {
nrt = rt6_cow(rt, daddr, saddr);
if (!nrt->u.dst.error) {
nrt->u.dst.pmtu = pmtu;
/* According to RFC 1981, detecting PMTU increase shouldn't be
happened within 5 mins, the recommended timer is 10 mins.
Here this route expiration time is set to ip6_rt_mtu_expires
which is 10 mins. After 10 mins the decreased pmtu is expired
and detecting PMTU increase will be automatically happened.
*/
dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires);
nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;
dst_release(&nrt->u.dst);
}
} else {
nrt = ip6_rt_copy(rt);
if (nrt == NULL)
goto out;
ipv6_addr_copy(&nrt->rt6i_dst.addr, daddr);
nrt->rt6i_dst.plen = 128;
nrt->u.dst.flags |= DST_HOST;
nrt->rt6i_nexthop = neigh_clone(rt->rt6i_nexthop);
dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires);
nrt->rt6i_flags |= RTF_DYNAMIC|RTF_CACHE|RTF_EXPIRES;
nrt->u.dst.pmtu = pmtu;
rt6_ins(nrt, NULL);
}
out:
dst_release(&rt->u.dst);
}
