int ip6_forward(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr = ipv6_hdr(skb);
struct inet6_skb_parm *opt = IP6CB(skb);
struct net *net = dev_net(dst->dev);
if (net->ipv6.devconf_all->forwarding == 0)
goto error;
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
skb_forward_csum(skb);
/*
* We DO NOT make any processing on
* RA packets, pushing them to user level AS IS
* without ane WARRANTY that application will be able
* to interpret them. The reason is that we
* cannot make anything clever here.
*
* We are not end-node, so that if packet contains
* AH/ESP, we cannot make anything.
* Defragmentation also would be mistake, RA packets
* cannot be fragmented, because there is no warranty
* that different fragments will go along one path. --ANK
*/
if (opt->ra) {
u8 *ptr = skb_network_header(skb) + opt->ra;
if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
return 0;
}
/*
* check and decrement ttl
*/
if (hdr->hop_limit <= 1) {
/* Force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
0, skb->dev);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);
kfree_skb(skb);
return -ETIMEDOUT;
}
/* XXX: idev->cnf.proxy_ndp? */
if (net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &hdr->daddr, skb->dev, 0)) {
int proxied = ip6_forward_proxy_check(skb);
if (proxied > 0)
return ip6_input(skb);
else if (proxied < 0) {
IP6_INC_STATS(net, ip6_dst_idev(dst),
IPSTATS_MIB_INDISCARDS);
goto drop;
}
}
if (!xfrm6_route_forward(skb)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
goto drop;
}
dst = skb_dst(skb);
/* IPv6 specs say nothing about it, but it is clear that we cannot
send redirects to source routed frames.
We don't send redirects to frames decapsulated from IPsec.
*/
if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 &&
!skb_sec_path(skb)) {
struct in6_addr *target = NULL;
struct rt6_info *rt;
struct neighbour *n = dst->neighbour;
/*
* incoming and outgoing devices are the same
* send a redirect.
*/
rt = (struct rt6_info *) dst;
if ((rt->rt6i_flags & RTF_GATEWAY))
target = (struct in6_addr*)&n->primary_key;
else
target = &hdr->daddr;
/* Limit redirects both by destination (here)
and by source (inside ndisc_send_redirect)
*/
if (xrlim_allow(dst, 1*HZ))
ndisc_send_redirect(skb, n, target);
} else {
int addrtype = ipv6_addr_type(&hdr->saddr);
/* This check is security critical. */
if (addrtype == IPV6_ADDR_ANY ||
addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
goto error;
if (addrtype & IPV6_ADDR_LINKLOCAL) {
icmpv6_send(skb, ICMPV6_DEST_UNREACH,
ICMPV6_NOT_NEIGHBOUR, 0, skb->dev);
goto error;
}
}
if (skb->len > dst_mtu(dst) && !skb_is_gso(skb)) {
/* Again, force OUTPUT device used as source address */
skb->dev = dst->dev;
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_INTOOBIGERRORS);
IP6_INC_STATS_BH(net,
ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
if (skb_cow(skb, dst->dev->hard_header_len)) {
IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
goto drop;
}
hdr = ipv6_hdr(skb);
/* Mangling hops number delayed to point after skb COW */
hdr->hop_limit--;
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS);
return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dst->dev,
ip6_forward_finish);
error:
IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS);
drop:
kfree_skb(skb);
return -EINVAL;
}
static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
struct ipv6_txoptions *opt;
struct inet_sock *newinet;
struct dccp6_sock *newdp6;
struct sock *newsk;
struct ipv6_txoptions *opt;
if (skb->protocol == htons(ETH_P_IP)) {
/*
* v6 mapped
*/
newsk = dccp_v4_request_recv_sock(sk, skb, req, dst);
if (newsk == NULL)
return NULL;
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr);
ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
newnp->rcv_saddr = newnp->saddr;
inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
newsk->sk_backlog_rcv = dccp_v4_do_rcv;
newnp->pktoptions = NULL;
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks count
* here, dccp_create_openreq_child now does this for us, see the comment in
* that function for the gory details. -acme
*/
/* It is tricky place. Until this moment IPv4 tcp
worked with IPv6 icsk.icsk_af_ops.
Sync it now.
*/
dccp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);
return newsk;
}
opt = np->opt;
if (sk_acceptq_is_full(sk))
goto out_overflow;
if (dst == NULL) {
struct in6_addr *final_p, final;
struct flowi6 fl6;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = ireq6->rmt_addr;
final_p = fl6_update_dst(&fl6, opt, &final);
fl6.saddr = ireq6->loc_addr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = inet_rsk(req)->rmt_port;
fl6.fl6_sport = inet_rsk(req)->loc_port;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, final_p, false);
if (IS_ERR(dst))
goto out;
}
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
goto out_nonewsk;
/*
* No need to charge this sock to the relevant IPv6 refcnt debug socks
* count here, dccp_create_openreq_child now does this for us, see the
* comment in that function for the gory details. -acme
*/
__ip6_dst_store(newsk, dst, NULL, NULL);
newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM |
NETIF_F_TSO);
newdp6 = (struct dccp6_sock *)newsk;
newinet = inet_sk(newsk);
newinet->pinet6 = &newdp6->inet6;
newnp = inet6_sk(newsk);
memcpy(newnp, np, sizeof(struct ipv6_pinfo));
newnp->daddr = ireq6->rmt_addr;
newnp->saddr = ireq6->loc_addr;
newnp->rcv_saddr = ireq6->loc_addr;
newsk->sk_bound_dev_if = ireq6->iif;
/* Now IPv6 options...
First: no IPv4 options.
*/
newinet->inet_opt = NULL;
/* Clone RX bits */
newnp->rxopt.all = np->rxopt.all;
/* Clone pktoptions received with SYN */
newnp->pktoptions = NULL;
if (ireq6->pktopts != NULL) {
newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC);
kfree_skb(ireq6->pktopts);
ireq6->pktopts = NULL;
if (newnp->pktoptions)
skb_set_owner_r(newnp->pktoptions, newsk);
}
newnp->opt = NULL;
newnp->mcast_oif = inet6_iif(skb);
newnp->mcast_hops = ipv6_hdr(skb)->hop_limit;
/*
* Clone native IPv6 options from listening socket (if any)
*
* Yes, keeping reference count would be much more clever, but we make
* one more one thing there: reattach optmem to newsk.
*/
opt = rcu_dereference(np->opt);
if (opt) {
opt = ipv6_dup_options(newsk, opt);
RCU_INIT_POINTER(newnp->opt, opt);
}
inet_csk(newsk)->icsk_ext_hdr_len = 0;
if (opt)
inet_csk(newsk)->icsk_ext_hdr_len = opt->opt_nflen +
opt->opt_flen;
dccp_sync_mss(newsk, dst_mtu(dst));
newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
if (__inet_inherit_port(sk, newsk) < 0) {
sock_put(newsk);
goto out;
}
__inet6_hash(newsk, NULL);
return newsk;
out_overflow:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
out_nonewsk:
dst_release(dst);
out:
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
if (opt != NULL && opt != np->opt)
sock_kfree_s(sk, opt, opt->tot_len);
return NULL;
}
static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct net_device_stats *stats = &tunnel->dev->stats;
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
int mtu;
struct in6_addr *addr6;
int addr_type;
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
/* ISATAP (RFC4214) - must come before 6to4 */
if (dev->priv_flags & IFF_ISATAP) {
struct neighbour *neigh = NULL;
if (skb_dst(skb))
neigh = skb_dst(skb)->neighbour;
if (neigh == NULL) {
if (net_ratelimit())
printk(KERN_DEBUG "sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (struct in6_addr*)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if ((addr_type & IPV6_ADDR_UNICAST) &&
ipv6_addr_is_isatap(addr6))
dst = addr6->s6_addr32[3];
else
goto tx_error;
}
if (!dst)
dst = try_6to4(&iph6->daddr);
if (!dst) {
struct neighbour *neigh = NULL;
if (skb_dst(skb))
neigh = skb_dst(skb)->neighbour;
if (neigh == NULL) {
if (net_ratelimit())
printk(KERN_DEBUG "sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (struct in6_addr*)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
goto tx_error_icmp;
dst = addr6->s6_addr32[3];
}
{
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = dst,
.saddr = tiph->saddr,
.tos = RT_TOS(tos) } },
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6 };
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
stats->tx_carrier_errors++;
goto tx_error_icmp;
}
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
stats->tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
stats->collisions++;
goto tx_error;
}
if (tiph->frag_off)
mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
else
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (mtu < 68) {
stats->collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (tunnel->parms.iph.daddr && skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
stats->tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
iph6 = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags = 0;
skb_dst_drop(skb);
skb_dst_set(skb, &rt->u.dst);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
if (mtu > IPV6_MIN_MTU)
iph->frag_off = tiph->frag_off;
else
iph->frag_off = 0;
iph->protocol = IPPROTO_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
nf_reset(skb);
IPTUNNEL_XMIT();
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
struct ipv6_txoptions *opt, int tclass)
{
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;
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;
}
consume_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)
hlimit = np->hop_limit;
if (hlimit < 0)
hlimit = ip6_dst_hoplimit(dst);
ip6_flow_hdr(hdr, tclass, fl6->flowlabel);
hdr->payload_len = htons(seg_len);
hdr->nexthdr = proto;
hdr->hop_limit = hlimit;
hdr->saddr = fl6->saddr;
hdr->daddr = *first_hop;
skb->protocol = htons(ETH_P_IPV6);
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);
}
skb->dev = dst->dev;
ipv6_local_error(sk, EMSGSIZE, fl6, mtu);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
static unsigned int
echo_tg6(struct sk_buff **poldskb, const struct xt_action_param *par)
{
const struct sk_buff *oldskb = *poldskb;
const struct udphdr *oldudp;
const struct ipv6hdr *oldip;
struct udphdr *newudp, oldudp_buf;
struct ipv6hdr *newip;
struct sk_buff *newskb;
unsigned int data_len;
void *payload;
struct flowi6 fl;
struct dst_entry *dst = NULL;
struct net *net = dev_net((par->in != NULL) ? par->in : par->out);
/* This allows us to do the copy operation in fewer lines of code. */
if (skb_linearize(*poldskb) < 0)
return NF_DROP;
oldip = ipv6_hdr(oldskb);
oldudp = skb_header_pointer(oldskb, par->thoff,
sizeof(*oldudp), &oldudp_buf);
if (oldudp == NULL)
return NF_DROP;
if (ntohs(oldudp->len) <= sizeof(*oldudp))
return NF_DROP;
newskb = alloc_skb(LL_MAX_HEADER + sizeof(*newip) +
ntohs(oldudp->len), GFP_ATOMIC);
if (newskb == NULL)
return NF_DROP;
skb_reserve(newskb, LL_MAX_HEADER);
newskb->protocol = oldskb->protocol;
skb_reset_network_header(newskb);
newip = (void *)skb_put(newskb, sizeof(*newip));
newip->version = oldip->version;
newip->priority = oldip->priority;
memcpy(newip->flow_lbl, oldip->flow_lbl, sizeof(newip->flow_lbl));
newip->nexthdr = par->target->proto;
newip->saddr = oldip->daddr;
newip->daddr = oldip->saddr;
skb_reset_transport_header(newskb);
newudp = (void *)skb_put(newskb, sizeof(*newudp));
newudp->source = oldudp->dest;
newudp->dest = oldudp->source;
newudp->len = oldudp->len;
data_len = htons(oldudp->len) - sizeof(*oldudp);
payload = skb_header_pointer(oldskb, par->thoff +
sizeof(*oldudp), data_len, NULL);
memcpy(skb_put(newskb, data_len), payload, data_len);
#if 0
/*
* Since no fields are modified (we just swapped things around),
* this works too in our specific echo case.
*/
newudp->check = oldudp->check;
#else
newudp->check = 0;
newudp->check = csum_ipv6_magic(&newip->saddr, &newip->daddr,
ntohs(newudp->len), IPPROTO_UDP,
csum_partial(newudp, ntohs(newudp->len), 0));
#endif
memset(&fl, 0, sizeof(fl));
fl.flowi6_proto = newip->nexthdr;
memcpy(&fl.saddr, &newip->saddr, sizeof(fl.saddr));
memcpy(&fl.daddr, &newip->daddr, sizeof(fl.daddr));
fl.fl6_sport = newudp->source;
fl.fl6_dport = newudp->dest;
security_skb_classify_flow((struct sk_buff *)oldskb, flowi6_to_flowi(&fl));
dst = ip6_route_output(net, NULL, &fl);
if (dst == NULL || dst->error != 0) {
dst_release(dst);
goto free_nskb;
}
skb_dst_set(newskb, dst);
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)
newip->hop_limit = ip6_dst_hoplimit(skb_dst(newskb));
#else
newip->hop_limit = dst_metric(skb_dst(newskb), RTAX_HOPLIMIT);
#endif
newskb->ip_summed = CHECKSUM_NONE;
/* "Never happens" (?) */
if (newskb->len > dst_mtu(skb_dst(newskb)))
goto free_nskb;
nf_ct_attach(newskb, *poldskb);
ip6_local_out(newskb);
return NF_DROP;
free_nskb:
kfree_skb(newskb);
return NF_DROP;
}
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;
}
static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
int type, int code, int offset, __u32 info)
{
struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
struct ipv6_pinfo *np;
struct sock *sk;
int err;
struct tcp_sock *tp;
__u32 seq;
sk = inet6_lookup(&tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr,
th->source, skb->dev->ifindex);
if (sk == NULL) {
ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == TCP_CLOSE)
goto out;
tp = tcp_sk(sk);
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
goto out;
/* icmp should have updated the destination cache entry */
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi fl;
/* BUGGG_FUTURE: Again, it is not clear how
to handle rthdr case. Ignore this complexity
for now.
*/
memset(&fl, 0, sizeof(fl));
fl.proto = IPPROTO_TCP;
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;
security_skb_classify_flow(skb, &fl);
if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
sk->sk_err_soft = -err;
goto out;
}
if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
sk->sk_err_soft = -err;
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
tcp_sync_mss(sk, dst_mtu(dst));
tcp_simple_retransmit(sk);
} /* else let the usual retransmit timer handle it */
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
struct request_sock *req, **prev;
case TCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
&hdr->saddr, inet6_iif(skb));
if (!req)
goto out;
/* ICMPs are not backlogged, hence we cannot get
* an established socket here.
*/
BUG_TRAP(req->sk == NULL);
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case TCP_SYN_SENT:
case TCP_SYN_RECV: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
sk->sk_err = err;
sk->sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */
tcp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static int do_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 (ip6_mroute_opt(optname))
return ip6_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
switch (optname) {
case IPV6_ADDRFORM:
if (sk->sk_protocol != IPPROTO_UDP &&
sk->sk_protocol != IPPROTO_UDPLITE &&
sk->sk_protocol != IPPROTO_TCP)
return -ENOPROTOOPT;
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;
if (gsf.gf_group.ss_family != AF_INET6)
return -EADDRNOTAVAIL;
lock_sock(sk);
err = ip6_mc_msfget(sk, &gsf,
(struct group_filter __user *)optval, optlen);
release_sock(sk);
return err;
}
case IPV6_2292PKTOPTIONS:
{
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 ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
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);
}
if (np->rxopt.bits.rxoinfo) {
struct in6_pktinfo src_info;
src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
np->sticky_pktinfo.ipi6_ifindex;
np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
}
if (np->rxopt.bits.rxohlim) {
int hlim = np->mcast_hops;
put_cmsg(&msg, SOL_IPV6, IPV6_2292HOPLIMIT, sizeof(hlim), &hlim);
}
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IPV6_MTU:
{
struct dst_entry *dst;
val = 0;
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = dst_mtu(dst);
rcu_read_unlock();
if (!val)
return -ENOTCONN;
break;
}
case IPV6_V6ONLY:
val = np->ipv6only;
break;
case IPV6_RECVPKTINFO:
val = np->rxopt.bits.rxinfo;
break;
case IPV6_2292PKTINFO:
val = np->rxopt.bits.rxoinfo;
break;
case IPV6_RECVHOPLIMIT:
val = np->rxopt.bits.rxhlim;
break;
case IPV6_2292HOPLIMIT:
val = np->rxopt.bits.rxohlim;
break;
case IPV6_RECVRTHDR:
val = np->rxopt.bits.srcrt;
break;
case IPV6_2292RTHDR:
val = np->rxopt.bits.osrcrt;
break;
case IPV6_HOPOPTS:
case IPV6_RTHDRDSTOPTS:
case IPV6_RTHDR:
case IPV6_DSTOPTS:
{
lock_sock(sk);
len = ipv6_getsockopt_sticky(sk, np->opt,
optname, optval, len);
release_sock(sk);
/* check if ipv6_getsockopt_sticky() returns err code */
if (len < 0)
return len;
return put_user(len, optlen);
}
case IPV6_RECVHOPOPTS:
val = np->rxopt.bits.hopopts;
break;
case IPV6_2292HOPOPTS:
val = np->rxopt.bits.ohopopts;
break;
case IPV6_RECVDSTOPTS:
val = np->rxopt.bits.dstopts;
break;
case IPV6_2292DSTOPTS:
val = np->rxopt.bits.odstopts;
break;
case IPV6_TCLASS:
val = np->tclass;
break;
case IPV6_RECVTCLASS:
val = np->rxopt.bits.rxtclass;
break;
case IPV6_FLOWINFO:
val = np->rxopt.bits.rxflow;
break;
case IPV6_RECVPATHMTU:
val = np->rxopt.bits.rxpmtu;
break;
case IPV6_PATHMTU:
{
struct dst_entry *dst;
struct ip6_mtuinfo mtuinfo;
if (len < sizeof(mtuinfo))
return -EINVAL;
len = sizeof(mtuinfo);
memset(&mtuinfo, 0, sizeof(mtuinfo));
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
mtuinfo.ip6m_mtu = dst_mtu(dst);
rcu_read_unlock();
if (!mtuinfo.ip6m_mtu)
return -ENOTCONN;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &mtuinfo, len))
return -EFAULT;
return 0;
break;
}
case IPV6_TRANSPARENT:
val = inet_sk(sk)->transparent;
break;
case IPV6_RECVORIGDSTADDR:
val = np->rxopt.bits.rxorigdstaddr;
break;
case IPV6_UNICAST_HOPS:
case IPV6_MULTICAST_HOPS:
{
struct dst_entry *dst;
if (optname == IPV6_UNICAST_HOPS)
val = np->hop_limit;
else
val = np->mcast_hops;
if (val < 0) {
rcu_read_lock();
dst = __sk_dst_get(sk);
if (dst)
val = ip6_dst_hoplimit(dst);
rcu_read_unlock();
}
if (val < 0)
val = sock_net(sk)->ipv6.devconf_all->hop_limit;
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;
case IPV6_ADDR_PREFERENCES:
val = 0;
if (np->srcprefs & IPV6_PREFER_SRC_TMP)
val |= IPV6_PREFER_SRC_TMP;
else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC)
val |= IPV6_PREFER_SRC_PUBLIC;
else {
/* XXX: should we return system default? */
val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT;
}
if (np->srcprefs & IPV6_PREFER_SRC_COA)
val |= IPV6_PREFER_SRC_COA;
else
val |= IPV6_PREFER_SRC_HOME;
break;
case IPV6_MINHOPCOUNT:
val = np->min_hopcount;
break;
case IPV6_DONTFRAG:
val = np->dontfrag;
break;
default:
return -ENOPROTOOPT;
}
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;
}
static int ip6_tnl_xmit2(struct sk_buff *skb,
struct net_device *dev,
__u8 dsfield,
struct flowi *fl,
int encap_limit,
__u32 *pmtu)
{
struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ipv6_tel_txoption opt;
struct dst_entry *dst;
struct net_device *tdev;
int mtu;
unsigned int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err = -1;
int pkt_len;
if ((dst = ip6_tnl_dst_check(t)) != NULL)
dst_hold(dst);
else {
dst = ip6_route_output(net, NULL, fl);
if (dst->error || xfrm_lookup(net, &dst, fl, NULL, 0) < 0)
goto tx_err_link_failure;
}
tdev = dst->dev;
if (tdev == dev) {
stats->collisions++;
if (net_ratelimit())
printk(KERN_WARNING
"%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst) - sizeof (*ipv6h);
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
}
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
if (skb->len > mtu) {
*pmtu = mtu;
err = -EMSGSIZE;
goto tx_err_dst_release;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom += LL_RESERVED_SPACE(tdev);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb;
if (!(new_skb = skb_realloc_headroom(skb, max_headroom)))
goto tx_err_dst_release;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
skb_dst_drop(skb);
skb_dst_set(skb, dst_clone(dst));
skb->transport_header = skb->network_header;
proto = fl->proto;
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
*(__be32*)ipv6h = fl->fl6_flowlabel | htonl(0x60000000);
dsfield = INET_ECN_encapsulate(0, dsfield);
ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
ipv6h->hop_limit = t->parms.hop_limit;
ipv6h->nexthdr = proto;
ipv6_addr_copy(&ipv6h->saddr, &fl->fl6_src);
ipv6_addr_copy(&ipv6h->daddr, &fl->fl6_dst);
nf_reset(skb);
pkt_len = skb->len;
err = ip6_local_out(skb);
if (net_xmit_eval(err) == 0) {
stats->tx_bytes += pkt_len;
stats->tx_packets++;
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
}
ip6_tnl_dst_store(t, dst);
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
return err;
}
static int ax8netfilter_do_ip_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct inet_sock *inet = inet_sk(sk);
int val;
int len;
if (level != SOL_IP)
return -EOPNOTSUPP;
if (ip_mroute_opt(optname))
return ip_mroute_getsockopt(sk, optname, optval, optlen);
if (get_user(len, optlen))
return -EFAULT;
if (len < 0)
return -EINVAL;
lock_sock(sk);
switch (optname) {
case IP_OPTIONS:
{
unsigned char optbuf[sizeof(struct ip_options)+40];
struct ip_options * opt = (struct ip_options *)optbuf;
opt->optlen = 0;
if (inet->opt)
memcpy(optbuf, inet->opt,
sizeof(struct ip_options)+
inet->opt->optlen);
release_sock(sk);
if (opt->optlen == 0)
return put_user(0, optlen);
ax8netfilter_ip_options_undo(opt);
len = min_t(unsigned int, len, opt->optlen);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, opt->__data, len))
return -EFAULT;
return 0;
}
case IP_PKTINFO:
val = (inet->cmsg_flags & IP_CMSG_PKTINFO) != 0;
break;
case IP_RECVTTL:
val = (inet->cmsg_flags & IP_CMSG_TTL) != 0;
break;
case IP_RECVTOS:
val = (inet->cmsg_flags & IP_CMSG_TOS) != 0;
break;
case IP_RECVOPTS:
val = (inet->cmsg_flags & IP_CMSG_RECVOPTS) != 0;
break;
case IP_RETOPTS:
val = (inet->cmsg_flags & IP_CMSG_RETOPTS) != 0;
break;
case IP_PASSSEC:
val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0;
break;
case IP_RECVORIGDSTADDR:
val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0;
break;
case IP_TOS:
val = inet->tos;
break;
case IP_TTL:
val = (inet->uc_ttl == -1 ?
*ax8netfilter_sysctl_ip_default_ttl :
inet->uc_ttl);
break;
case IP_HDRINCL:
val = inet->hdrincl;
break;
case IP_MTU_DISCOVER:
val = inet->pmtudisc;
break;
case IP_MTU:
{
struct dst_entry *dst;
val = 0;
dst = sk_dst_get(sk);
if (dst) {
val = dst_mtu(dst);
dst_release(dst);
}
if (!val) {
release_sock(sk);
return -ENOTCONN;
}
break;
}
case IP_RECVERR:
val = inet->recverr;
break;
case IP_MULTICAST_TTL:
val = inet->mc_ttl;
break;
case IP_MULTICAST_LOOP:
val = inet->mc_loop;
break;
case IP_MULTICAST_IF:
{
struct in_addr addr;
len = min_t(unsigned int, len, sizeof(struct in_addr));
addr.s_addr = inet->mc_addr;
release_sock(sk);
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &addr, len))
return -EFAULT;
return 0;
}
case IP_MSFILTER:
{
struct ip_msfilter msf;
int err;
if (len < IP_MSFILTER_SIZE(0)) {
release_sock(sk);
return -EINVAL;
}
if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) {
release_sock(sk);
return -EFAULT;
}
err = ax8netfilter_ip_mc_msfget(sk, &msf,
(struct ip_msfilter __user *)optval, optlen);
release_sock(sk);
return err;
}
case MCAST_MSFILTER:
{
struct group_filter gsf;
int err;
if (len < GROUP_FILTER_SIZE(0)) {
release_sock(sk);
return -EINVAL;
}
if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) {
release_sock(sk);
return -EFAULT;
}
err = ax8netfilter_ip_mc_gsfget(sk, &gsf,
(struct group_filter __user *)optval, optlen);
release_sock(sk);
return err;
}
case IP_PKTOPTIONS:
{
struct msghdr msg;
release_sock(sk);
if (sk->sk_type != SOCK_STREAM)
return -ENOPROTOOPT;
msg.msg_control = optval;
msg.msg_controllen = len;
msg.msg_flags = 0;
if (inet->cmsg_flags & IP_CMSG_PKTINFO) {
struct in_pktinfo info;
info.ipi_addr.s_addr = inet->rcv_saddr;
info.ipi_spec_dst.s_addr = inet->rcv_saddr;
info.ipi_ifindex = inet->mc_index;
put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
}
if (inet->cmsg_flags & IP_CMSG_TTL) {
int hlim = inet->mc_ttl;
put_cmsg(&msg, SOL_IP, IP_TTL, sizeof(hlim), &hlim);
}
len -= msg.msg_controllen;
return put_user(len, optlen);
}
case IP_FREEBIND:
val = inet->freebind;
break;
case IP_TRANSPARENT:
val = inet->transparent;
break;
default:
release_sock(sk);
return -ENOPROTOOPT;
}
release_sock(sk);
if (len < sizeof(int) && len > 0 && val>=0 && val<=255) {
unsigned char ucval = (unsigned char)val;
len = 1;
if (put_user(len, optlen))
return -EFAULT;
if (copy_to_user(optval, &ucval, 1))
return -EFAULT;
} else {
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;
}
static int
ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
int rel_msg = 0;
u8 rel_type = type;
u8 rel_code = code;
__u32 rel_info = ntohl(info);
int err;
struct sk_buff *skb2;
struct iphdr *eiph;
struct flowi fl;
struct rtable *rt;
err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code,
&rel_msg, &rel_info, offset);
if (err < 0)
return err;
if (rel_msg == 0)
return 0;
switch (rel_type) {
case ICMPV6_DEST_UNREACH:
if (rel_code != ICMPV6_ADDR_UNREACH)
return 0;
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
break;
case ICMPV6_PKT_TOOBIG:
if (rel_code != 0)
return 0;
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_FRAG_NEEDED;
break;
default:
return 0;
}
if (!pskb_may_pull(skb, offset + sizeof(struct iphdr)))
return 0;
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return 0;
skb_dst_drop(skb2);
skb_pull(skb2, offset);
skb_reset_network_header(skb2);
eiph = ip_hdr(skb2);
/* Try to guess incoming interface */
memset(&fl, 0, sizeof(fl));
fl.fl4_dst = eiph->saddr;
fl.fl4_tos = RT_TOS(eiph->tos);
fl.proto = IPPROTO_IPIP;
if (ip_route_output_key(dev_net(skb->dev), &rt, &fl))
goto out;
skb2->dev = rt->u.dst.dev;
/* route "incoming" packet */
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
rt = NULL;
fl.fl4_dst = eiph->daddr;
fl.fl4_src = eiph->saddr;
fl.fl4_tos = eiph->tos;
if (ip_route_output_key(dev_net(skb->dev), &rt, &fl) ||
rt->u.dst.dev->type != ARPHRD_TUNNEL) {
ip_rt_put(rt);
goto out;
}
skb_dst_set(skb2, (struct dst_entry *)rt);
} else {
ip_rt_put(rt);
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
skb2->dev) ||
skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
goto out;
}
/* change mtu on this route */
if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) {
if (rel_info > dst_mtu(skb_dst(skb2)))
goto out;
skb_dst(skb2)->ops->update_pmtu(skb_dst(skb2), rel_info);
}
icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
out:
kfree_skb(skb2);
return 0;
}
static int
tcpmss_mangle_packet(struct sk_buff *skb,
const struct xt_action_param *par,
unsigned int in_mtu,
unsigned int tcphoff,
unsigned int minlen)
{
const struct xt_tcpmss_info *info = par->targinfo;
struct tcphdr *tcph;
int len, tcp_hdrlen;
unsigned int i;
__be16 oldval;
u16 newmss;
u8 *opt;
/* This is a fragment, no TCP header is available */
if (par->fragoff != 0)
return 0;
if (!skb_make_writable(skb, skb->len))
return -1;
len = skb->len - tcphoff;
if (len < (int)sizeof(struct tcphdr))
return -1;
tcph = (struct tcphdr *)(skb_network_header(skb) + tcphoff);
tcp_hdrlen = tcph->doff * 4;
if (len < tcp_hdrlen)
return -1;
if (info->mss == XT_TCPMSS_CLAMP_PMTU) {
if (dst_mtu(skb_dst(skb)) <= minlen) {
net_err_ratelimited("unknown or invalid path-MTU (%u)\n",
dst_mtu(skb_dst(skb)));
return -1;
}
if (in_mtu <= minlen) {
net_err_ratelimited("unknown or invalid path-MTU (%u)\n",
in_mtu);
return -1;
}
newmss = min(dst_mtu(skb_dst(skb)), in_mtu) - minlen;
} else
newmss = info->mss;
opt = (u_int8_t *)tcph;
for (i = sizeof(struct tcphdr); i <= tcp_hdrlen - TCPOLEN_MSS; i += optlen(opt, i)) {
if (opt[i] == TCPOPT_MSS && opt[i+1] == TCPOLEN_MSS) {
u_int16_t oldmss;
oldmss = (opt[i+2] << 8) | opt[i+3];
/* Never increase MSS, even when setting it, as
* doing so results in problems for hosts that rely
* on MSS being set correctly.
*/
if (oldmss <= newmss)
return 0;
opt[i+2] = (newmss & 0xff00) >> 8;
opt[i+3] = newmss & 0x00ff;
inet_proto_csum_replace2(&tcph->check, skb,
htons(oldmss), htons(newmss),
0);
return 0;
}
}
static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset);
struct dccp_sock *dp;
struct ipv6_pinfo *np;
struct sock *sk;
int err;
__u64 seq;
struct net *net = dev_net(skb->dev);
if (skb->len < offset + sizeof(*dh) ||
skb->len < offset + __dccp_basic_hdr_len(dh)) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
sk = inet6_lookup(net, &dccp_hashinfo,
&hdr->daddr, dh->dccph_dport,
&hdr->saddr, dh->dccph_sport, inet6_iif(skb));
if (sk == NULL) {
ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return;
}
if (sk->sk_state == DCCP_TIME_WAIT) {
inet_twsk_put(inet_twsk(sk));
return;
}
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS);
if (sk->sk_state == DCCP_CLOSED)
goto out;
dp = dccp_sk(sk);
seq = dccp_hdr_seq(dh);
if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) &&
!between48(seq, dp->dccps_awl, dp->dccps_awh)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
struct dst_entry *dst = NULL;
if (sock_owned_by_user(sk))
goto out;
if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED))
goto out;
/* icmp should have updated the destination cache entry */
dst = __sk_dst_check(sk, np->dst_cookie);
if (dst == NULL) {
struct inet_sock *inet = inet_sk(sk);
struct flowi6 fl6;
/* BUGGG_FUTURE: Again, it is not clear how
to handle rthdr case. Ignore this complexity
for now.
*/
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_DCCP;
fl6.daddr = np->daddr;
fl6.saddr = np->saddr;
fl6.flowi6_oif = sk->sk_bound_dev_if;
fl6.fl6_dport = inet->inet_dport;
fl6.fl6_sport = inet->inet_sport;
security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
dst = ip6_dst_lookup_flow(sk, &fl6, NULL, false);
if (IS_ERR(dst)) {
sk->sk_err_soft = -PTR_ERR(dst);
goto out;
}
} else
dst_hold(dst);
if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
dccp_sync_mss(sk, dst_mtu(dst));
} /* else let the usual retransmit timer handle it */
dst_release(dst);
goto out;
}
icmpv6_err_convert(type, code, &err);
/* Might be for an request_sock */
switch (sk->sk_state) {
struct request_sock *req, **prev;
case DCCP_LISTEN:
if (sock_owned_by_user(sk))
goto out;
req = inet6_csk_search_req(sk, &prev, dh->dccph_dport,
&hdr->daddr, &hdr->saddr,
inet6_iif(skb));
if (req == NULL)
goto out;
/*
* ICMPs are not backlogged, hence we cannot get an established
* socket here.
*/
WARN_ON(req->sk != NULL);
if (!between48(seq, dccp_rsk(req)->dreq_iss,
dccp_rsk(req)->dreq_gss)) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
inet_csk_reqsk_queue_drop(sk, req, prev);
goto out;
case DCCP_REQUESTING:
case DCCP_RESPOND: /* Cannot happen.
It can, it SYNs are crossed. --ANK */
if (!sock_owned_by_user(sk)) {
DCCP_INC_STATS_BH(DCCP_MIB_ATTEMPTFAILS);
sk->sk_err = err;
/*
* Wake people up to see the error
* (see connect in sock.c)
*/
sk->sk_error_report(sk);
dccp_done(sk);
} else
sk->sk_err_soft = err;
goto out;
}
if (!sock_owned_by_user(sk) && np->recverr) {
sk->sk_err = err;
sk->sk_error_report(sk);
} else
sk->sk_err_soft = err;
out:
bh_unlock_sock(sk);
sock_put(sk);
}
/*
* IP Tunneling transmitter
*
* This function encapsulates the packet in a new IP packet, its
* destination will be set to cp->daddr. Most code of this function
* is taken from ipip.c.
*
* It is used in VS/TUN cluster. The load balancer selects a real
* server from a cluster based on a scheduling algorithm,
* encapsulates the request packet and forwards it to the selected
* server. For example, all real servers are configured with
* "ifconfig tunl0 <Virtual IP Address> up". When the server receives
* the encapsulated packet, it will decapsulate the packet, processe
* the request and return the response packets directly to the client
* without passing the load balancer. This can greatly increase the
* scalability of virtual server.
*
* Used for ANY protocol
*/
int
ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
__be32 saddr; /* Source for tunnel */
struct net_device *tdev; /* Device to other host */
struct iphdr *old_iph = ip_hdr(skb);
u8 tos = old_iph->tos;
__be16 df = old_iph->frag_off;
struct iphdr *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(skb, cp->dest, cp->daddr.ip,
RT_TOS(tos), IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL,
&saddr)))
goto tx_error_icmp;
if (rt->rt_flags & RTCF_LOCAL) {
ip_rt_put(rt);
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
tdev = rt->dst.dev;
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
IP_VS_DBG_RL("%s(): mtu less than 68\n", __func__);
goto tx_error_put;
}
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
df |= (old_iph->frag_off & htons(IP_DF));
if ((old_iph->frag_off & htons(IP_DF) &&
mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(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 iphdr);
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) {
ip_rt_put(rt);
kfree_skb(skb);
IP_VS_ERR_RL("%s(): no memory\n", __func__);
return NF_STOLEN;
}
kfree_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
skb->transport_header = skb->network_header;
/* fix old IP header checksum */
ip_send_check(old_iph);
skb_push(skb, sizeof(struct iphdr));
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 = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = cp->daddr.ip;
iph->saddr = saddr;
iph->ttl = old_iph->ttl;
ip_select_ident(iph, &rt->dst, NULL);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
ret = IP_VS_XMIT_TUNNEL(skb, cp);
if (ret == NF_ACCEPT)
ip_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:
ip_rt_put(rt);
goto tx_error;
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
const struct iphdr *oiph;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _otcph, *tcph;
/* IP header checks: fragment. */
if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, ip_hdrlen(oldskb),
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP))
return;
oiph = ip_hdr(oldskb);
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
return;
skb_reserve(nskb, LL_MAX_HEADER);
skb_reset_network_header(nskb);
niph = (struct iphdr *)skb_put(nskb, sizeof(struct iphdr));
niph->version = 4;
niph->ihl = sizeof(struct iphdr) / 4;
niph->tos = 0;
niph->id = 0;
niph->frag_off = htons(IP_DF);
niph->protocol = IPPROTO_TCP;
niph->check = 0;
niph->saddr = oiph->daddr;
niph->daddr = oiph->saddr;
tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
memset(tcph, 0, sizeof(*tcph));
tcph->source = oth->dest;
tcph->dest = oth->source;
tcph->doff = sizeof(struct tcphdr) / 4;
if (oth->ack)
tcph->seq = oth->ack_seq;
else {
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
oldskb->len - ip_hdrlen(oldskb) -
(oth->doff << 2));
tcph->ack = 1;
}
tcph->rst = 1;
tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), niph->saddr,
niph->daddr, 0);
nskb->ip_summed = CHECKSUM_PARTIAL;
nskb->csum_start = (unsigned char *)tcph - nskb->head;
nskb->csum_offset = offsetof(struct tcphdr, check);
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
nskb->protocol = htons(ETH_P_IP);
if (ip_route_me_harder(nskb, RTN_UNSPEC))
goto free_nskb;
niph->ttl = ip4_dst_hoplimit(skb_dst(nskb));
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
ip_local_out(nskb);
return;
free_nskb:
kfree_skb(nskb);
}
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, (IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL))))
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;
}
//-----------------------------------------------------------------------------
static int _gtpusp_ksocket_process_gtp(const unsigned char * const rx_buf_pP, const int lenP, unsigned char* tx_buf_pP)
//-----------------------------------------------------------------------------
{
gtpv1u_msg_t gtpv1u_msg;
uint8_t msg_type;
struct iphdr *iph_p = NULL;
struct iphdr *new_iph_p= NULL;
struct sk_buff *skb_p = NULL;
const unsigned char * rx_buf_p = rx_buf_pP;
int err = 0;
struct rtable *rt = NULL;
struct flowi fl = {
.u = {
.ip4 = {
.daddr = 0,
.flowi4_tos = 0,
.flowi4_scope = RT_SCOPE_UNIVERSE,
}
}
};
msg_type = rx_buf_pP[1];
switch(msg_type) {
case GTP_ECHO_REQ:
PR_INFO(MODULE_NAME": TODO GTP ECHO_REQ, SEND TO GTPV1U TASK USER SPACE\n");
//TODO;
return 0;
break;
case GTP_ERROR_INDICATION:
PR_INFO(MODULE_NAME":TODO GTP ERROR INDICATION, SEND TO GTPV1U TASK USER SPACE\n");
//TODO;
return 0;
break;
case GTP_ECHO_RSP:
PR_INFO(MODULE_NAME":GTP ECHO_RSP, SEND TO GTPV1U TASK USER SPACE\n");
return 0;
break;
case GTP_GPDU: {
gtpv1u_msg.version = ((*rx_buf_p) & 0xE0) >> 5;
gtpv1u_msg.protocol_type = ((*rx_buf_p) & 0x10) >> 4;
gtpv1u_msg.ext_hdr_flag = ((*rx_buf_p) & 0x04) >> 2;
gtpv1u_msg.seq_num_flag = ((*rx_buf_p) & 0x02) >> 1;
gtpv1u_msg.npdu_num_flag = ((*rx_buf_p) & 0x01);
rx_buf_p++;
gtpv1u_msg.msg_type = *(rx_buf_p);
rx_buf_p++;
rx_buf_p += 2;
gtpv1u_msg.teid = ntohl(*((u_int32_t *)rx_buf_p));
rx_buf_p += 4;
if(gtpv1u_msg.ext_hdr_flag || gtpv1u_msg.seq_num_flag || gtpv1u_msg.npdu_num_flag) {
gtpv1u_msg.seq_num = ntohs(*(((u_int16_t *)rx_buf_p)));
rx_buf_p += 2;
gtpv1u_msg.npdu_num = *(rx_buf_p++);
gtpv1u_msg.next_ext_hdr_type = *(rx_buf_p++);
}
gtpv1u_msg.msg_buf_offset = (u_int32_t)(rx_buf_p - rx_buf_pP);
gtpv1u_msg.msg_buf_len = lenP - gtpv1u_msg.msg_buf_offset;
gtpv1u_msg.msg_len = lenP;
iph_p = (struct iphdr*)(&rx_buf_pP[gtpv1u_msg.msg_buf_offset]);
fl.u.ip4.daddr = iph_p->daddr;
fl.u.ip4.flowi4_tos = RT_TOS(iph_p->tos);
rt = ip_route_output_key(&init_net, &fl.u.ip4);
if (rt == NULL) {
PR_INFO("GTPURH: Failed to route packet to dst 0x%x. Error: (%d)\n", fl.u.ip4.daddr, err);
return NF_DROP;
}
if (rt->dst.dev == NULL) {
pr_info("GTPURH: dst dev NULL\n");
return 0;
}
skb_p = alloc_skb(LL_MAX_HEADER + ntohs(iph_p->tot_len), GFP_ATOMIC);
if (skb_p == NULL) {
return 0;
}
skb_p->priority = rt_tos2priority(iph_p->tos);
skb_p->pkt_type = PACKET_OTHERHOST;
skb_dst_set(skb_p, dst_clone(&rt->dst));
skb_p->dev = skb_dst(skb_p)->dev;
skb_reserve(skb_p, LL_MAX_HEADER + ntohs(iph_p->tot_len));
skb_p->protocol = htons(ETH_P_IP);
new_iph_p = (void *)skb_push(skb_p, ntohs(iph_p->tot_len) - (iph_p->ihl << 2));
skb_reset_transport_header(skb_p);
new_iph_p = (void *)skb_push(skb_p, iph_p->ihl << 2);
memcpy(new_iph_p, iph_p, ntohs(iph_p->tot_len));
skb_reset_network_header(skb_p);
skb_reset_inner_network_header(skb_p);
skb_reset_inner_transport_header(skb_p);
skb_p->mark = gtpv1u_msg.teid;
new_iph_p->ttl = ip4_dst_hoplimit(skb_dst(skb_p));
skb_p->ip_summed = CHECKSUM_NONE;
if (skb_p->len > dst_mtu(skb_dst(skb_p))) {
PR_INFO("GTPURH: bad length\n");
goto free_skb;
}
ip_local_out(skb_p);
return 0;
free_skb:
pr_info("GTPURH: Dropped skb\n");
kfree_skb(skb_p);
return 0;
}
break;
default:
PR_INFO(MODULE_NAME":ERROR GTPU msg type %u\n", msg_type);
return 0;
}
}
static unsigned int
echo_tg4(struct sk_buff **poldskb, const struct xt_action_param *par)
{
const struct sk_buff *oldskb = *poldskb;
const struct udphdr *oldudp;
const struct iphdr *oldip;
struct udphdr *newudp, oldudp_buf;
struct iphdr *newip;
struct sk_buff *newskb;
unsigned int data_len;
void *payload;
/* This allows us to do the copy operation in fewer lines of code. */
if (skb_linearize(*poldskb) < 0)
return NF_DROP;
oldip = ip_hdr(oldskb);
oldudp = skb_header_pointer(oldskb, par->thoff,
sizeof(*oldudp), &oldudp_buf);
if (oldudp == NULL)
return NF_DROP;
if (ntohs(oldudp->len) <= sizeof(*oldudp))
return NF_DROP;
newskb = alloc_skb(LL_MAX_HEADER + sizeof(*newip) +
ntohs(oldudp->len), GFP_ATOMIC);
if (newskb == NULL)
return NF_DROP;
skb_reserve(newskb, LL_MAX_HEADER);
newskb->protocol = oldskb->protocol;
skb_reset_network_header(newskb);
newip = (void *)skb_put(newskb, sizeof(*newip));
newip->version = oldip->version;
newip->ihl = sizeof(*newip) / 4;
newip->tos = oldip->tos;
newip->id = 0;
newip->frag_off = htons(IP_DF);
newip->protocol = oldip->protocol;
newip->check = 0;
newip->saddr = oldip->daddr;
newip->daddr = oldip->saddr;
skb_reset_transport_header(newskb);
newudp = (void *)skb_put(newskb, sizeof(*newudp));
newudp->source = oldudp->dest;
newudp->dest = oldudp->source;
newudp->len = oldudp->len;
data_len = htons(oldudp->len) - sizeof(*oldudp);
payload = skb_header_pointer(oldskb, par->thoff +
sizeof(*oldudp), data_len, NULL);
memcpy(skb_put(newskb, data_len), payload, data_len);
#if 0
/*
* Since no fields are modified (we just swapped things around),
* this works too in our specific echo case.
*/
newudp->check = oldudp->check;
#else
newudp->check = 0;
newudp->check = csum_tcpudp_magic(newip->saddr, newip->daddr,
ntohs(newudp->len), IPPROTO_UDP,
csum_partial(newudp, ntohs(newudp->len), 0));
#endif
/* ip_route_me_harder expects the skb's dst to be set */
skb_dst_set(newskb, dst_clone(skb_dst(oldskb)));
if (ip_route_me_harder(&newskb, RTN_UNSPEC) != 0)
goto free_nskb;
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2, 6, 38)
newip->ttl = ip4_dst_hoplimit(skb_dst(newskb));
#else
newip->ttl = dst_metric(skb_dst(newskb), RTAX_HOPLIMIT);
#endif
newskb->ip_summed = CHECKSUM_NONE;
/* "Never happens" (?) */
if (newskb->len > dst_mtu(skb_dst(newskb)))
goto free_nskb;
nf_ct_attach(newskb, *poldskb);
ip_local_out(newskb);
return NF_DROP;
free_nskb:
kfree_skb(newskb);
return NF_DROP;
}
int
ip_vs_dr_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;
EnterFunction(10);
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, (IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL))))
goto tx_error_icmp;
if (__ip_vs_is_local_route6(rt)) {
dst_release(&rt->dst);
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 1);
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if (skb->len > mtu) {
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);
dst_release(&rt->dst);
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error;
}
/*
* Call ip_send_check because we are not sure it is called
* after ip_defrag. Is copy-on-write needed?
*/
skb = skb_share_check(skb, GFP_ATOMIC);
if (unlikely(skb == NULL)) {
dst_release(&rt->dst);
return NF_STOLEN;
}
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT(NFPROTO_IPV6, skb, cp, 0);
LeaveFunction(10);
return NF_STOLEN;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
kfree_skb(skb);
LeaveFunction(10);
return NF_STOLEN;
}
int ip_forward(struct sk_buff *skb)
{
struct iphdr *iph; /* Our header */
struct rtable *rt; /* Route we use */
struct ip_options * opt = &(IPCB(skb)->opt);
if (skb_warn_if_lro(skb))
goto drop;
if (!xfrm4_policy_check(NULL, XFRM_POLICY_FWD, skb))
goto drop;
if (IPCB(skb)->opt.router_alert && ip_call_ra_chain(skb))
return NET_RX_SUCCESS;
if (skb->pkt_type != PACKET_HOST)
goto drop;
skb_forward_csum(skb);
/*
* According to the RFC, we must first decrease the TTL field. If
* that reaches zero, we must reply an ICMP control message telling
* that the packet's lifetime expired.
*/
if (ip_hdr(skb)->ttl <= 1)
goto too_many_hops;
if (!xfrm4_route_forward(skb))
goto drop;
rt = skb->rtable;
if (opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto sr_failed;
if (unlikely(skb->len > dst_mtu(&rt->u.dst) && !skb_is_gso(skb) &&
(ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) {
IP_INC_STATS(dev_net(rt->u.dst.dev), IPSTATS_MIB_FRAGFAILS);
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(dst_mtu(&rt->u.dst)));
goto drop;
}
/* We are about to mangle packet. Copy it! */
#if 0
if( (LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len) > skb_headroom(skb))
{
printk("=========%s(%d),dst.dev(%s),reserved(%d),header_len(%d),hard_header_len(%d),needed_headroom(%d)\n",__FUNCTION__,__LINE__,rt->u.dst.dev->name,LL_RESERVED_SPACE(rt->u.dst.dev),
rt->u.dst.header_len,rt->u.dst.dev->hard_header_len,rt->u.dst.dev->needed_headroom);
printk("======%s(%d),skb->headroom(%d)\n",__FUNCTION__,__LINE__,skb_headroom(skb));
}
#endif
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+rt->u.dst.header_len))
goto drop;
iph = ip_hdr(skb);
/* Decrease ttl after skb cow done */
ip_decrease_ttl(iph);
/*
* We now generate an ICMP HOST REDIRECT giving the route
* we calculated.
*/
if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb))
ip_rt_send_redirect(skb);
skb->priority = rt_tos2priority(iph->tos);
return NF_HOOK(PF_INET, NF_INET_FORWARD, skb, skb->dev, rt->u.dst.dev,
ip_forward_finish);
sr_failed:
/*
* Strict routing permits no gatewaying
*/
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_SR_FAILED, 0);
goto drop;
too_many_hops:
/* Tell the sender its packet died... */
IP_INC_STATS_BH(dev_net(skb->dst->dev), IPSTATS_MIB_INHDRERRORS);
icmp_send(skb, ICMP_TIME_EXCEEDED, ICMP_EXC_TTL, 0);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
/*
* ICMP packet transmitter
* called by the ip_vs_in_icmp
*/
int
ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset, unsigned int hooknum)
{
struct rtable *rt; /* Route to the other host */
int mtu;
int rc;
int local;
int rt_mode;
EnterFunction(10);
/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
forwarded directly here, because there is no need to
translate address/port back */
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
if (cp->packet_xmit)
rc = cp->packet_xmit(skb, cp, pp);
else
rc = NF_ACCEPT;
/* do not touch skb anymore */
atomic_inc(&cp->in_pkts);
goto out;
}
/*
* mangle and send the packet here (only for VS/NAT)
*/
/* LOCALNODE from FORWARD hook is not supported */
rt_mode = (hooknum != NF_INET_FORWARD) ?
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(ip_hdr(skb)->tos),
rt_mode, NULL)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
* 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(10, "%s(): "
"stopping DNAT to local address %pI4\n",
__func__, &cp->daddr.ip);
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(cp->daddr.ip) &&
rt_is_input_route(skb_rtable(skb))) {
IP_VS_DBG(1, "%s(): "
"stopping DNAT to loopback %pI4\n",
__func__, &cp->daddr.ip);
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) &&
!skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, offset))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
ip_vs_nat_icmp(skb, pp, cp, 0);
if (!local) {
/* drop the old route when skb is not shared */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
ip_rt_put(rt);
/*
* Some IPv4 replies get local address from routes,
* not from iph, so while we DNAT after routing
* we need this second input/output route.
*/
if (!__ip_vs_reroute_locally(skb))
goto tx_error;
}
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV4, skb, cp, local);
rc = NF_STOLEN;
goto out;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev_kfree_skb(skb);
rc = NF_STOLEN;
out:
LeaveFunction(10);
return rc;
tx_error_put:
ip_rt_put(rt);
goto tx_error;
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct iphdr *iph = oldskb->nh.iph;
struct tcphdr _otcph, *oth, *tcph;
__be16 tmp_port;
__be32 tmp_addr;
int needs_ack;
unsigned int addr_type;
/* IP header checks: fragment. */
if (oldskb->nh.iph->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, oldskb->nh.iph->ihl * 4,
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
/* Check checksum */
if (nf_ip_checksum(oldskb, hook, iph->ihl * 4, IPPROTO_TCP))
return;
/* We need a linear, writeable skb. We also need to expand
headroom in case hh_len of incoming interface < hh_len of
outgoing interface */
nskb = skb_copy_expand(oldskb, LL_MAX_HEADER, skb_tailroom(oldskb),
GFP_ATOMIC);
if (!nskb)
return;
/* This packet will not be the same as the other: clear nf fields */
nf_reset(nskb);
nskb->mark = 0;
skb_init_secmark(nskb);
tcph = (struct tcphdr *)((u_int32_t*)nskb->nh.iph + nskb->nh.iph->ihl);
/* Swap source and dest */
tmp_addr = nskb->nh.iph->saddr;
nskb->nh.iph->saddr = nskb->nh.iph->daddr;
nskb->nh.iph->daddr = tmp_addr;
tmp_port = tcph->source;
tcph->source = tcph->dest;
tcph->dest = tmp_port;
/* Truncate to length (no data) */
tcph->doff = sizeof(struct tcphdr)/4;
skb_trim(nskb, nskb->nh.iph->ihl*4 + sizeof(struct tcphdr));
nskb->nh.iph->tot_len = htons(nskb->len);
if (tcph->ack) {
needs_ack = 0;
tcph->seq = oth->ack_seq;
tcph->ack_seq = 0;
} else {
needs_ack = 1;
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin
+ oldskb->len - oldskb->nh.iph->ihl*4
- (oth->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;
/* Adjust TCP checksum */
tcph->check = 0;
tcph->check = tcp_v4_check(tcph, sizeof(struct tcphdr),
nskb->nh.iph->saddr,
nskb->nh.iph->daddr,
csum_partial((char *)tcph,
sizeof(struct tcphdr), 0));
/* Set DF, id = 0 */
nskb->nh.iph->frag_off = htons(IP_DF);
nskb->nh.iph->id = 0;
addr_type = RTN_UNSPEC;
if (hook != NF_IP_FORWARD
#ifdef CONFIG_BRIDGE_NETFILTER
|| (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED)
#endif
)
addr_type = RTN_LOCAL;
if (ip_route_me_harder(&nskb, addr_type))
goto free_nskb;
nskb->ip_summed = CHECKSUM_NONE;
/* Adjust IP TTL */
nskb->nh.iph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT);
/* Adjust IP checksum */
nskb->nh.iph->check = 0;
nskb->nh.iph->check = ip_fast_csum((unsigned char *)nskb->nh.iph,
nskb->nh.iph->ihl);
/* "Never happens" */
if (nskb->len > dst_mtu(nskb->dst))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, nskb, NULL, nskb->dst->dev,
dst_output);
return;
free_nskb:
kfree_skb(nskb);
}
int
ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp, int offset, unsigned int hooknum)
{
struct rt6_info *rt; /* Route to the other host */
int mtu;
int rc;
int local;
int rt_mode;
EnterFunction(10);
/* The ICMP packet for VS/TUN, VS/DR and LOCALNODE will be
forwarded directly here, because there is no need to
translate address/port back */
if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
if (cp->packet_xmit)
rc = cp->packet_xmit(skb, cp, pp);
else
rc = NF_ACCEPT;
/* do not touch skb anymore */
atomic_inc(&cp->in_pkts);
goto out;
}
/*
* mangle and send the packet here (only for VS/NAT)
*/
/* LOCALNODE from FORWARD hook is not supported */
rt_mode = (hooknum != NF_INET_FORWARD) ?
IP_VS_RT_MODE_LOCAL | IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR : IP_VS_RT_MODE_NON_LOCAL;
if (!(rt = __ip_vs_get_out_rt_v6(skb, cp->dest, &cp->daddr.in6, NULL,
0, rt_mode)))
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(10, "%s(): "
"stopping DNAT to local address %pI6\n",
__func__, &cp->daddr.in6);
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(1, "%s(): "
"stopping DNAT to loopback %pI6\n",
__func__, &cp->daddr.in6);
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("%s(): frag needed\n", __func__);
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, offset))
goto tx_error_put;
if (skb_cow(skb, rt->dst.dev->hard_header_len))
goto tx_error_put;
ip_vs_nat_icmp_v6(skb, pp, cp, 0);
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);
}
/* Another hack: avoid icmp_send in ip_fragment */
skb->local_df = 1;
IP_VS_XMIT_NAT(NFPROTO_IPV6, skb, cp, local);
rc = NF_STOLEN;
goto out;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev_kfree_skb(skb);
rc = NF_STOLEN;
out:
LeaveFunction(10);
return rc;
tx_error_put:
dst_release(&rt->dst);
goto tx_error;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi6 *fl6,
struct rt6_info *rt, unsigned int flags, int dontfrag)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_cork *cork;
struct sk_buff *skb, *skb_prev = NULL;
unsigned int maxfraglen, fragheaderlen, mtu;
int exthdrlen;
int dst_exthdrlen;
int hh_len;
int copy;
int err;
int offset = 0;
__u8 tx_flags = 0;
if (flags&MSG_PROBE)
return 0;
cork = &inet->cork.base;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (WARN_ON(np->cork.opt))
return -EINVAL;
np->cork.opt = kzalloc(opt->tot_len, sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
np->cork.opt->tot_len = opt->tot_len;
np->cork.opt->opt_flen = opt->opt_flen;
np->cork.opt->opt_nflen = opt->opt_nflen;
np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
sk->sk_allocation);
if (opt->dst0opt && !np->cork.opt->dst0opt)
return -ENOBUFS;
np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
sk->sk_allocation);
if (opt->dst1opt && !np->cork.opt->dst1opt)
return -ENOBUFS;
np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
sk->sk_allocation);
if (opt->hopopt && !np->cork.opt->hopopt)
return -ENOBUFS;
np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
sk->sk_allocation);
if (opt->srcrt && !np->cork.opt->srcrt)
return -ENOBUFS;
/* need source address above miyazawa*/
}
dst_hold(&rt->dst);
cork->dst = &rt->dst;
inet->cork.fl.u.ip6 = *fl6;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
if (rt->dst.flags & DST_XFRM_TUNNEL)
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(&rt->dst);
else
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->dst.dev->mtu : dst_mtu(rt->dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
cork->fragsize = mtu;
if (dst_allfrag(rt->dst.path))
cork->flags |= IPCORK_ALLFRAG;
cork->length = 0;
exthdrlen = (opt ? opt->opt_flen : 0);
length += exthdrlen;
transhdrlen += exthdrlen;
dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len;
} else {
rt = (struct rt6_info *)cork->dst;
fl6 = &inet->cork.fl.u.ip6;
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
mtu = cork->fragsize;
}
hh_len = LL_RESERVED_SPACE(rt->dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (cork->length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/* For UDP, check if TX timestamp is enabled */
if (sk->sk_type == SOCK_DGRAM)
sock_tx_timestamp(sk, &tx_flags);
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
if ((length > mtu) && dontfrag && (sk->sk_protocol == IPPROTO_UDP ||
sk->sk_protocol == IPPROTO_RAW)) {
ipv6_local_rxpmtu(sk, fl6, mtu-exthdrlen);
return -EMSGSIZE;
}
skb = skb_peek_tail(&sk->sk_write_queue);
cork->length += length;
if (((length > mtu) ||
(skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length,
hh_len, fragheaderlen,
transhdrlen, mtu, flags, rt);
if (err)
goto error;
return 0;
}
if (!skb)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
alloc_new_skb:
/* There's no room in the current skb */
if (skb)
fraggap = skb->len - maxfraglen;
else
fraggap = 0;
/* update mtu and maxfraglen if necessary */
if (skb == NULL || skb_prev == NULL)
ip6_append_data_mtu(&mtu, &maxfraglen,
fragheaderlen, skb, rt,
np->pmtudisc ==
IPV6_PMTUDISC_PROBE);
skb_prev = skb;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
if ((flags & MSG_MORE) &&
!(rt->dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
alloclen += dst_exthdrlen;
if (datalen != length + fraggap) {
/*
* this is not the last fragment, the trailer
* space is regarded as data space.
*/
datalen += rt->dst.trailer_len;
}
alloclen += rt->dst.trailer_len;
fraglen = datalen + fragheaderlen;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
else {
/* Only the initial fragment
* is time stamped.
*/
tx_flags = 0;
}
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->protocol = htons(ETH_P_IPV6);
skb->ip_summed = CHECKSUM_NONE;
skb->csum = 0;
/* reserve for fragmentation and ipsec header */
skb_reserve(skb, hh_len + sizeof(struct frag_hdr) +
dst_exthdrlen);
if (sk->sk_type == SOCK_DGRAM)
skb_shinfo(skb)->tx_flags = tx_flags;
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
dst_exthdrlen = 0;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
struct page_frag *pfrag = sk_page_frag(sk);
err = -ENOMEM;
if (!sk_page_frag_refill(sk, pfrag))
goto error;
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
err = -EMSGSIZE;
if (i == MAX_SKB_FRAGS)
goto error;
__skb_fill_page_desc(skb, i, pfrag->page,
pfrag->offset, 0);
skb_shinfo(skb)->nr_frags = ++i;
get_page(pfrag->page);
}
copy = min_t(int, copy, pfrag->size - pfrag->offset);
if (getfrag(from,
page_address(pfrag->page) + pfrag->offset,
offset, copy, skb->len, skb) < 0)
goto error_efault;
pfrag->offset += copy;
skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
}
return 0;
error_efault:
err = -EFAULT;
error:
cork->length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
/*
* NAT transmitter (only for outside-to-inside nat forwarding)
* Not used for related ICMP
*/
int
ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
struct rtable *rt; /* Route to the other host */
int mtu;
struct iphdr *iph = ip_hdr(skb);
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, iph->ihl*4, 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(skb, cp->dest, cp->daddr.ip,
RT_TOS(iph->tos),
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR, NULL)))
goto tx_error_icmp;
local = rt->rt_flags & RTCF_LOCAL;
/*
* 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_INET, pp, skb, 0,
"ip_vs_nat_xmit(): "
"stopping DNAT to local address");
goto tx_error_put;
}
}
#endif
/* From world but DNAT to loopback address? */
if (local && ipv4_is_loopback(cp->daddr.ip) &&
rt_is_input_route(skb_rtable(skb))) {
IP_VS_DBG_RL_PKT(1, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): "
"stopping DNAT to loopback address");
goto tx_error_put;
}
/* MTU checking */
mtu = dst_mtu(&rt->dst);
if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) &&
!skb_is_gso(skb)) {
icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu));
IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0,
"ip_vs_nat_xmit(): frag needed for");
goto tx_error_put;
}
/* copy-on-write the packet before mangling it */
if (!skb_make_writable(skb, sizeof(struct iphdr)))
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_put;
ip_hdr(skb)->daddr = cp->daddr.ip;
ip_send_check(ip_hdr(skb));
if (!local) {
/* drop old route */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
} else {
ip_rt_put(rt);
/*
* Some IPv4 replies get local address from routes,
* not from iph, so while we DNAT after routing
* we need this second input/output route.
*/
if (!__ip_vs_reroute_locally(skb))
goto tx_error;
}
IP_VS_DBG_PKT(10, AF_INET, 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_IPV4, skb, cp, local);
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:
ip_rt_put(rt);
goto tx_error;
}
int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
struct ipv6_txoptions *opt, int ipfragok)
{
struct net *net = sock_net(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct in6_addr *first_hop = &fl->fl6_dst;
struct dst_entry *dst = skb_dst(skb);
struct ipv6hdr *hdr;
u8 proto = fl->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;
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);
}
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
hdr = ipv6_hdr(skb);
/* Allow local fragmentation. */
if (ipfragok)
skb->local_df = 1;
/*
* 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)) | fl->fl6_flowlabel;
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);
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(PF_INET6, 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, skb->dev);
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
kfree_skb(skb);
return -EMSGSIZE;
}
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, (IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR))))
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;
}
int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
int offset, int len, int odd, struct sk_buff *skb),
void *from, int length, int transhdrlen,
int hlimit, int tclass, struct ipv6_txoptions *opt, struct flowi *fl,
struct rt6_info *rt, unsigned int flags)
{
struct inet_sock *inet = inet_sk(sk);
struct ipv6_pinfo *np = inet6_sk(sk);
struct sk_buff *skb;
unsigned int maxfraglen, fragheaderlen;
int exthdrlen;
int hh_len;
int mtu;
int copy;
int err;
int offset = 0;
int csummode = CHECKSUM_NONE;
if (flags&MSG_PROBE)
return 0;
if (skb_queue_empty(&sk->sk_write_queue)) {
/*
* setup for corking
*/
if (opt) {
if (WARN_ON(np->cork.opt))
return -EINVAL;
np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
if (unlikely(np->cork.opt == NULL))
return -ENOBUFS;
np->cork.opt->tot_len = opt->tot_len;
np->cork.opt->opt_flen = opt->opt_flen;
np->cork.opt->opt_nflen = opt->opt_nflen;
np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
sk->sk_allocation);
if (opt->dst0opt && !np->cork.opt->dst0opt)
return -ENOBUFS;
np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
sk->sk_allocation);
if (opt->dst1opt && !np->cork.opt->dst1opt)
return -ENOBUFS;
np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
sk->sk_allocation);
if (opt->hopopt && !np->cork.opt->hopopt)
return -ENOBUFS;
np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
sk->sk_allocation);
if (opt->srcrt && !np->cork.opt->srcrt)
return -ENOBUFS;
/* need source address above miyazawa*/
}
dst_hold(&rt->u.dst);
inet->cork.dst = &rt->u.dst;
inet->cork.fl = *fl;
np->cork.hop_limit = hlimit;
np->cork.tclass = tclass;
mtu = np->pmtudisc == IPV6_PMTUDISC_PROBE ?
rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path);
if (np->frag_size < mtu) {
if (np->frag_size)
mtu = np->frag_size;
}
inet->cork.fragsize = mtu;
if (dst_allfrag(rt->u.dst.path))
inet->cork.flags |= IPCORK_ALLFRAG;
inet->cork.length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
exthdrlen = rt->u.dst.header_len + (opt ? opt->opt_flen : 0) -
rt->rt6i_nfheader_len;
length += exthdrlen;
transhdrlen += exthdrlen;
} else {
rt = (struct rt6_info *)inet->cork.dst;
fl = &inet->cork.fl;
opt = np->cork.opt;
transhdrlen = 0;
exthdrlen = 0;
mtu = inet->cork.fragsize;
}
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
(opt ? opt->opt_nflen : 0);
maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen - sizeof(struct frag_hdr);
if (mtu <= sizeof(struct ipv6hdr) + IPV6_MAXPLEN) {
if (inet->cork.length + length > sizeof(struct ipv6hdr) + IPV6_MAXPLEN - fragheaderlen) {
ipv6_local_error(sk, EMSGSIZE, fl, mtu-exthdrlen);
return -EMSGSIZE;
}
}
/*
* Let's try using as much space as possible.
* Use MTU if total length of the message fits into the MTU.
* Otherwise, we need to reserve fragment header and
* fragment alignment (= 8-15 octects, in total).
*
* Note that we may need to "move" the data from the tail of
* of the buffer to the new fragment when we split
* the message.
*
* FIXME: It may be fragmented into multiple chunks
* at once if non-fragmentable extension headers
* are too large.
* --yoshfuji
*/
inet->cork.length += length;
if (((length > mtu) && (sk->sk_protocol == IPPROTO_UDP)) &&
(rt->u.dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len,
fragheaderlen, transhdrlen, mtu,
flags);
if (err)
goto error;
return 0;
}
if ((skb = skb_peek_tail(&sk->sk_write_queue)) == NULL)
goto alloc_new_skb;
while (length > 0) {
/* Check if the remaining data fits into current packet. */
copy = (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len;
if (copy < length)
copy = maxfraglen - skb->len;
if (copy <= 0) {
char *data;
unsigned int datalen;
unsigned int fraglen;
unsigned int fraggap;
unsigned int alloclen;
struct sk_buff *skb_prev;
alloc_new_skb:
skb_prev = skb;
/* There's no room in the current skb */
if (skb_prev)
fraggap = skb_prev->len - maxfraglen;
else
fraggap = 0;
/*
* If remaining data exceeds the mtu,
* we know we need more fragment(s).
*/
datalen = length + fraggap;
if (datalen > (inet->cork.length <= mtu && !(inet->cork.flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
datalen = maxfraglen - fragheaderlen;
fraglen = datalen + fragheaderlen;
if ((flags & MSG_MORE) &&
!(rt->u.dst.dev->features&NETIF_F_SG))
alloclen = mtu;
else
alloclen = datalen + fragheaderlen;
/*
* The last fragment gets additional space at tail.
* Note: we overallocate on fragments with MSG_MODE
* because we have no idea if we're the last one.
*/
if (datalen == length + fraggap)
alloclen += rt->u.dst.trailer_len;
/*
* We just reserve space for fragment header.
* Note: this may be overallocation if the message
* (without MSG_MORE) fits into the MTU.
*/
alloclen += sizeof(struct frag_hdr);
if (transhdrlen) {
skb = sock_alloc_send_skb(sk,
alloclen + hh_len,
(flags & MSG_DONTWAIT), &err);
} else {
skb = NULL;
if (atomic_read(&sk->sk_wmem_alloc) <=
2 * sk->sk_sndbuf)
skb = sock_wmalloc(sk,
alloclen + hh_len, 1,
sk->sk_allocation);
if (unlikely(skb == NULL))
err = -ENOBUFS;
}
if (skb == NULL)
goto error;
/*
* Fill in the control structures
*/
skb->ip_summed = csummode;
skb->csum = 0;
/* reserve for fragmentation */
skb_reserve(skb, hh_len+sizeof(struct frag_hdr));
/*
* Find where to start putting bytes
*/
data = skb_put(skb, fraglen);
skb_set_network_header(skb, exthdrlen);
data += fragheaderlen;
skb->transport_header = (skb->network_header +
fragheaderlen);
if (fraggap) {
skb->csum = skb_copy_and_csum_bits(
skb_prev, maxfraglen,
data + transhdrlen, fraggap, 0);
skb_prev->csum = csum_sub(skb_prev->csum,
skb->csum);
data += fraggap;
pskb_trim_unique(skb_prev, maxfraglen);
}
copy = datalen - transhdrlen - fraggap;
if (copy < 0) {
err = -EINVAL;
kfree_skb(skb);
goto error;
} else if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) {
err = -EFAULT;
kfree_skb(skb);
goto error;
}
offset += copy;
length -= datalen - fraggap;
transhdrlen = 0;
exthdrlen = 0;
csummode = CHECKSUM_NONE;
/*
* Put the packet on the pending queue
*/
__skb_queue_tail(&sk->sk_write_queue, skb);
continue;
}
if (copy > length)
copy = length;
if (!(rt->u.dst.dev->features&NETIF_F_SG)) {
unsigned int off;
off = skb->len;
if (getfrag(from, skb_put(skb, copy),
offset, copy, off, skb) < 0) {
__skb_trim(skb, off);
err = -EFAULT;
goto error;
}
} else {
int i = skb_shinfo(skb)->nr_frags;
skb_frag_t *frag = &skb_shinfo(skb)->frags[i-1];
struct page *page = sk->sk_sndmsg_page;
int off = sk->sk_sndmsg_off;
unsigned int left;
if (page && (left = PAGE_SIZE - off) > 0) {
if (copy >= left)
copy = left;
if (page != frag->page) {
if (i == MAX_SKB_FRAGS) {
err = -EMSGSIZE;
goto error;
}
get_page(page);
skb_fill_page_desc(skb, i, page, sk->sk_sndmsg_off, 0);
frag = &skb_shinfo(skb)->frags[i];
}
} else if(i < MAX_SKB_FRAGS) {
if (copy > PAGE_SIZE)
copy = PAGE_SIZE;
page = alloc_pages(sk->sk_allocation, 0);
if (page == NULL) {
err = -ENOMEM;
goto error;
}
sk->sk_sndmsg_page = page;
sk->sk_sndmsg_off = 0;
skb_fill_page_desc(skb, i, page, 0, 0);
frag = &skb_shinfo(skb)->frags[i];
} else {
err = -EMSGSIZE;
goto error;
}
if (getfrag(from, page_address(frag->page)+frag->page_offset+frag->size, offset, copy, skb->len, skb) < 0) {
err = -EFAULT;
goto error;
}
sk->sk_sndmsg_off += copy;
frag->size += copy;
skb->len += copy;
skb->data_len += copy;
skb->truesize += copy;
atomic_add(copy, &sk->sk_wmem_alloc);
}
offset += copy;
length -= copy;
}
return 0;
error:
inet->cork.length -= length;
IP6_INC_STATS(sock_net(sk), rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS);
return err;
}
/* Send RST reply */
static void send_reset(struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct iphdr *iph = oldskb->nh.iph;
struct tcphdr _otcph, *oth, *tcph;
struct rtable *rt;
u_int16_t tmp_port;
u_int32_t tmp_addr;
unsigned int tcplen;
int needs_ack;
int hh_len;
/* IP header checks: fragment. */
if (oldskb->nh.iph->frag_off & htons(IP_OFFSET))
return;
oth = skb_header_pointer(oldskb, oldskb->nh.iph->ihl * 4,
sizeof(_otcph), &_otcph);
if (oth == NULL)
return;
/* No RST for RST. */
if (oth->rst)
return;
/* Check checksum */
tcplen = oldskb->len - iph->ihl * 4;
if (((hook != NF_IP_LOCAL_IN && oldskb->ip_summed != CHECKSUM_HW) ||
(hook == NF_IP_LOCAL_IN &&
oldskb->ip_summed != CHECKSUM_UNNECESSARY)) &&
csum_tcpudp_magic(iph->saddr, iph->daddr, tcplen, IPPROTO_TCP,
oldskb->ip_summed == CHECKSUM_HW ? oldskb->csum :
skb_checksum(oldskb, iph->ihl * 4, tcplen, 0)))
return;
if ((rt = route_reverse(oldskb, oth, hook)) == NULL)
return;
hh_len = LL_RESERVED_SPACE(rt->u.dst.dev);
/* We need a linear, writeable skb. We also need to expand
headroom in case hh_len of incoming interface < hh_len of
outgoing interface */
nskb = skb_copy_expand(oldskb, hh_len, skb_tailroom(oldskb),
GFP_ATOMIC);
if (!nskb) {
dst_release(&rt->u.dst);
return;
}
dst_release(nskb->dst);
nskb->dst = &rt->u.dst;
/* This packet will not be the same as the other: clear nf fields */
nf_reset(nskb);
nskb->nfmark = 0;
#ifdef CONFIG_BRIDGE_NETFILTER
nf_bridge_put(nskb->nf_bridge);
nskb->nf_bridge = NULL;
#endif
tcph = (struct tcphdr *)((u_int32_t*)nskb->nh.iph + nskb->nh.iph->ihl);
/* Swap source and dest */
tmp_addr = nskb->nh.iph->saddr;
nskb->nh.iph->saddr = nskb->nh.iph->daddr;
nskb->nh.iph->daddr = tmp_addr;
tmp_port = tcph->source;
tcph->source = tcph->dest;
tcph->dest = tmp_port;
/* Truncate to length (no data) */
tcph->doff = sizeof(struct tcphdr)/4;
skb_trim(nskb, nskb->nh.iph->ihl*4 + sizeof(struct tcphdr));
nskb->nh.iph->tot_len = htons(nskb->len);
if (tcph->ack) {
needs_ack = 0;
tcph->seq = oth->ack_seq;
tcph->ack_seq = 0;
} else {
needs_ack = 1;
tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin
+ oldskb->len - oldskb->nh.iph->ihl*4
- (oth->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;
/* Adjust TCP checksum */
tcph->check = 0;
tcph->check = tcp_v4_check(tcph, sizeof(struct tcphdr),
nskb->nh.iph->saddr,
nskb->nh.iph->daddr,
csum_partial((char *)tcph,
sizeof(struct tcphdr), 0));
/* Adjust IP TTL, DF */
nskb->nh.iph->ttl = dst_metric(nskb->dst, RTAX_HOPLIMIT);
/* Set DF, id = 0 */
nskb->nh.iph->frag_off = htons(IP_DF);
nskb->nh.iph->id = 0;
/* Adjust IP checksum */
nskb->nh.iph->check = 0;
nskb->nh.iph->check = ip_fast_csum((unsigned char *)nskb->nh.iph,
nskb->nh.iph->ihl);
/* "Never happens" */
if (nskb->len > dst_mtu(nskb->dst))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, nskb, NULL, nskb->dst->dev,
dst_output);
return;
free_nskb:
kfree_skb(nskb);
}
