static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
{
struct rtable *rt;
int flag = 0;
/*unsigned long now; */
struct net *net = dev_net(dev);
rt = ip_route_output(net, sip, tip, 0, 0);
if (IS_ERR(rt))
return 1;
if (rt->dst.dev != dev) {
NET_INC_STATS_BH(net, LINUX_MIB_ARPFILTER);
flag = 1;
}
ip_rt_put(rt);
return flag;
}
int ovs_tunnel_get_egress_info(struct dp_upcall_info *upcall,
struct net *net,
struct sk_buff *skb,
u8 ipproto,
__be16 tp_src,
__be16 tp_dst)
{
struct ip_tunnel_info *egress_tun_info = upcall->egress_tun_info;
struct ip_tunnel_info *tun_info = skb_tunnel_info(skb);
const struct ip_tunnel_key *tun_key;
u32 skb_mark = skb->mark;
struct rtable *rt;
struct flowi4 fl;
if (unlikely(!tun_info))
return -EINVAL;
if (ip_tunnel_info_af(tun_info) != AF_INET)
return -EINVAL;
tun_key = &tun_info->key;
/* Route lookup to get srouce IP address.
* The process may need to be changed if the corresponding process
* in vports ops changed.
*/
rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
/* Generate egress_tun_info based on tun_info,
* saddr, tp_src and tp_dst
*/
ip_tunnel_key_init(&egress_tun_info->key,
fl.saddr, tun_key->u.ipv4.dst,
tun_key->tos,
tun_key->ttl,
tp_src, tp_dst,
tun_key->tun_id,
tun_key->tun_flags);
egress_tun_info->options_len = tun_info->options_len;
egress_tun_info->mode = tun_info->mode;
upcall->egress_tun_opts = ip_tunnel_info_opts(tun_info);
return 0;
}
static int ip_tunnel_bind_dev(struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *iph;
int hlen = LL_MAX_HEADER;
int mtu = ETH_DATA_LEN;
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
iph = &tunnel->parms.iph;
/* Guess output device to choose reasonable mtu and needed_headroom */
if (iph->daddr) {
struct flowi4 fl4;
struct rtable *rt;
init_tunnel_flow(&fl4, iph->protocol, iph->daddr,
iph->saddr, tunnel->parms.o_key,
RT_TOS(iph->tos), tunnel->parms.link);
rt = ip_route_output_key(tunnel->net, &fl4);
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
tunnel_dst_set(tunnel, &rt->dst, fl4.saddr);
ip_rt_put(rt);
}
if (dev->type != ARPHRD_ETHER)
dev->flags |= IFF_POINTOPOINT;
}
if (!tdev && tunnel->parms.link)
tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
if (tdev) {
hlen = tdev->hard_header_len + tdev->needed_headroom;
mtu = tdev->mtu;
}
dev->needed_headroom = t_hlen + hlen;
mtu -= (dev->hard_header_len + t_hlen);
if (mtu < 68)
mtu = 68;
return mtu;
}
/* Before 2.6.11 we did implicit source NAT if required. Warn about change. */
static void warn_if_extra_mangle(__be32 dstip, __be32 srcip)
{
static int warned = 0;
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dstip } } };
struct rtable *rt;
if (ip_route_output_key(&rt, &fl) != 0)
return;
if (rt->rt_src != srcip && !warned) {
printk("NAT: no longer support implicit source local NAT\n");
printk("NAT: packet src %u.%u.%u.%u -> dst %u.%u.%u.%u\n",
NIPQUAD(srcip), NIPQUAD(dstip));
warned = 1;
}
ip_rt_put(rt);
}
static int arp_filter(__u32 sip, __u32 tip, struct net_device *dev)
{
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = sip,
.saddr = tip } } };
struct rtable *rt;
int flag = 0;
/*unsigned long now; */
if (ip_route_output_key(&rt, &fl) < 0)
return 1;
if (rt->u.dst.dev != dev) {
NET_INC_STATS_BH(LINUX_MIB_ARPFILTER);
flag = 1;
}
ip_rt_put(rt);
return flag;
}
static int ipip6_tunnel_init(struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel;
struct iphdr *iph;
tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
if (iph->daddr) {
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = iph->daddr,
.saddr = iph->saddr,
.tos = RT_TOS(iph->tos)
}
},
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6
};
struct rtable *rt;
if (!ip_route_output_key(&rt, &fl)) {
tdev = rt->u.dst.dev;
ip_rt_put(rt);
}
dev->flags |= IFF_POINTOPOINT;
}
if (!tdev && tunnel->parms.link)
tdev = __dev_get_by_index(tunnel->parms.link);
if (tdev) {
dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
dev->mtu = tdev->mtu - sizeof(struct iphdr);
if (dev->mtu < IPV6_MIN_MTU)
dev->mtu = IPV6_MIN_MTU;
}
dev->iflink = tunnel->parms.link;
return 0;
}
static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
{
struct neighbour *neigh;
struct atmarp_entry *entry;
int error;
struct clip_vcc *clip_vcc;
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip, .tos = 1}} };
struct rtable *rt;
if (vcc->push != clip_push) {
printk(KERN_WARNING "clip_setentry: non-CLIP VCC\n");
return -EBADF;
}
clip_vcc = CLIP_VCC(vcc);
if (!ip) {
if (!clip_vcc->entry) {
printk(KERN_ERR "hiding hidden ATMARP entry\n");
return 0;
}
DPRINTK("setentry: remove\n");
unlink_clip_vcc(clip_vcc);
return 0;
}
error = ip_route_output_key(&rt, &fl);
if (error)
return error;
neigh = __neigh_lookup(&clip_tbl, &ip, rt->u.dst.dev, 1);
ip_rt_put(rt);
if (!neigh)
return -ENOMEM;
entry = NEIGH2ENTRY(neigh);
if (entry != clip_vcc->entry) {
if (!clip_vcc->entry)
DPRINTK("setentry: add\n");
else {
DPRINTK("setentry: update\n");
unlink_clip_vcc(clip_vcc);
}
link_vcc(clip_vcc, entry);
}
error = neigh_update(neigh, llc_oui, NUD_PERMANENT,
NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN);
neigh_release(neigh);
return error;
}
int arp_req_delete(struct arpreq *r, struct net_device * dev)
{
int err;
u32 ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
struct neighbour *neigh;
if (r->arp_flags & ATF_PUBL) {
u32 mask =
((struct sockaddr_in *)&r->arp_netmask)->sin_addr.s_addr;
if (mask == 0xFFFFFFFF)
return pneigh_delete(&arp_tbl, &ip, dev);
if (mask == 0) {
if (dev == NULL) {
ipv4_devconf.proxy_arp = 0;
return 0;
}
if (__in_dev_get(dev)) {
__in_dev_get(dev)->cnf.proxy_arp = 0;
return 0;
}
return -ENXIO;
}
return -EINVAL;
}
if (dev == NULL) {
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip,
.tos = RTO_ONLINK } } };
struct rtable * rt;
if ((err = ip_route_output_key(&rt, &fl)) != 0)
return err;
dev = rt->u.dst.dev;
ip_rt_put(rt);
if (!dev)
return -EINVAL;
}
err = -ENXIO;
neigh = neigh_lookup(&arp_tbl, &ip, dev);
if (neigh) {
if (neigh->nud_state&~NUD_NOARP)
err = neigh_update(neigh, NULL, NUD_FAILED, 1, 0);
neigh_release(neigh);
}
return err;
}
static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
{
struct neighbour *neigh;
struct atmarp_entry *entry;
int error;
struct clip_vcc *clip_vcc;
struct rtable *rt;
if (vcc->push != clip_push) {
pr_warning("non-CLIP VCC\n");
return -EBADF;
}
clip_vcc = CLIP_VCC(vcc);
if (!ip) {
if (!clip_vcc->entry) {
pr_err("hiding hidden ATMARP entry\n");
return 0;
}
pr_debug("remove\n");
unlink_clip_vcc(clip_vcc);
return 0;
}
rt = ip_route_output(&init_net, ip, 0, 1, 0);
if (IS_ERR(rt))
return PTR_ERR(rt);
neigh = __neigh_lookup(&arp_tbl, &ip, rt->dst.dev, 1);
ip_rt_put(rt);
if (!neigh)
return -ENOMEM;
entry = neighbour_priv(neigh);
if (entry != clip_vcc->entry) {
if (!clip_vcc->entry)
pr_debug("add\n");
else {
pr_debug("update\n");
unlink_clip_vcc(clip_vcc);
}
link_vcc(clip_vcc, entry);
}
error = neigh_update(neigh, llc_oui, NUD_PERMANENT,
NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN);
neigh_release(neigh);
return error;
}
int ovs_tunnel_get_egress_info(struct ovs_tunnel_info *egress_tun_info,
struct net *net,
const struct ovs_tunnel_info *tun_info,
u8 ipproto,
u32 skb_mark,
__be16 tp_src,
__be16 tp_dst)
{
const struct ovs_key_ipv4_tunnel *tun_key;
struct rtable *rt;
struct flowi4 fl;
if (unlikely(!tun_info))
return -EINVAL;
tun_key = &tun_info->tunnel;
/* Route lookup to get srouce IP address.
* The process may need to be changed if the corresponding process
* in vports ops changed.
*/
rt = ovs_tunnel_route_lookup(net, tun_key, skb_mark, &fl, ipproto);
if (IS_ERR(rt))
return PTR_ERR(rt);
ip_rt_put(rt);
/* Generate egress_tun_info based on tun_info,
* saddr, tp_src and tp_dst
*/
__ovs_flow_tun_info_init(egress_tun_info,
fl.saddr, tun_key->ipv4_dst,
tun_key->ipv4_tos,
tun_key->ipv4_ttl,
tp_src, tp_dst,
tun_key->tun_id,
tun_key->tun_flags,
tun_info->options,
tun_info->options_len);
return 0;
}
static int arp_req_delete(struct net *net, struct arpreq *r,
struct net_device *dev)
{
__be32 ip;
if (r->arp_flags & ATF_PUBL)
return arp_req_delete_public(net, r, dev);
ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
if (dev == NULL) {
struct rtable *rt = ip_route_output(net, ip, 0, RTO_ONLINK, 0);
if (IS_ERR(rt))
return PTR_ERR(rt);
dev = rt->dst.dev;
ip_rt_put(rt);
if (!dev)
return -EINVAL;
}
return arp_invalidate(dev, ip);
}
/*
This will route a SYN-ACK, i.e., the response to a request to open a
new connection.
*/
struct dst_entry *serval_ipv4_req_route(struct sock *sk,
struct request_sock *rsk,
int protocol,
u32 saddr,
u32 daddr)
{
struct rtable *rt;
struct ip_options *opt = NULL; /* inet_rsk(req)->opt; */
struct flowi fl;
serval_flow_init_output(&fl, sk->sk_bound_dev_if, sk->sk_mark,
RT_CONN_FLAGS(sk), 0, protocol,
#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,28))
inet_sk_flowi_flags(sk),
#else
0,
#endif
daddr, saddr, 0, 0);
serval_security_req_classify_flow(rsk, &fl);
rt = serval_ip_route_output_flow(sock_net(sk), &fl, sk, 0);
if (!rt)
goto no_route;
if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
goto route_err;
return route_dst(rt);
route_err:
ip_rt_put(rt);
no_route:
#if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,25))
IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
#else
IP_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
#endif
return NULL;
}
static struct in_device * ip_mc_find_dev(struct ip_mreqn *imr)
{
struct rtable *rt;
struct device *dev = NULL;
if (imr->imr_address.s_addr) {
dev = ip_dev_find(imr->imr_address.s_addr);
if (!dev)
return NULL;
}
if (!dev && !ip_route_output(&rt, imr->imr_multiaddr.s_addr, 0, 0, 0)) {
dev = rt->u.dst.dev;
ip_rt_put(rt);
}
if (dev) {
imr->imr_ifindex = dev->ifindex;
return dev->ip_ptr;
}
return NULL;
}
static int ipgre_open(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
if (ipv4_is_multicast(t->parms.iph.daddr)) {
struct flowi fl = { .oif = t->parms.link,
.nl_u = { .ip4_u =
{ .daddr = t->parms.iph.daddr,
.saddr = t->parms.iph.saddr,
.tos = RT_TOS(t->parms.iph.tos) } },
.proto = IPPROTO_GRE };
struct rtable *rt;
if (ip_route_output_key(dev_net(dev), &rt, &fl))
return -EADDRNOTAVAIL;
dev = rt->u.dst.dev;
ip_rt_put(rt);
if (__in_dev_get_rtnl(dev) == NULL)
return -EADDRNOTAVAIL;
t->mlink = dev->ifindex;
ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr);
}
static int vrf_send_v4_prep(struct sk_buff *skb, struct flowi4 *fl4,
struct net_device *vrf_dev)
{
struct rtable *rt;
int err = 1;
rt = ip_route_output_flow(dev_net(vrf_dev), fl4, NULL);
if (IS_ERR(rt))
goto out;
/* TO-DO: what about broadcast ? */
if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
ip_rt_put(rt);
goto out;
}
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
err = 0;
out:
return err;
}
static int arp_req_delete(struct net *net, struct arpreq *r,
struct net_device * dev)
{
int err;
__be32 ip;
struct neighbour *neigh;
if (r->arp_flags & ATF_PUBL)
return arp_req_delete_public(net, r, dev);
ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
if (dev == NULL) {
struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip,
.tos = RTO_ONLINK
}
}
};
struct rtable * rt;
if ((err = ip_route_output_key(net, &rt, &fl)) != 0)
return err;
dev = rt->u.dst.dev;
ip_rt_put(rt);
if (!dev)
return -EINVAL;
}
err = -ENXIO;
neigh = neigh_lookup(&arp_tbl, &ip, dev);
if (neigh) {
if (neigh->nud_state&~NUD_NOARP)
err = neigh_update(neigh, NULL, NUD_FAILED,
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_ADMIN);
neigh_release(neigh);
}
return err;
}
/*
* 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)
{
struct rtable *rt; /* Route to the other host */
int mtu;
int rc;
int local;
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_unchecked(&cp->in_pkts);
goto out;
}
/*
* mangle and send the packet here (only for VS/NAT)
*/
if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
RT_TOS(ip_hdr(skb)->tos),
IP_VS_RT_MODE_LOCAL |
IP_VS_RT_MODE_NON_LOCAL |
IP_VS_RT_MODE_RDR)))
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(rt->rt_dst) &&
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;
}
int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
__be16 orig_sport, orig_dport;
__be32 daddr, nexthop;
struct flowi4 *fl4;
struct rtable *rt;
int err;
struct ip_options_rcu *inet_opt;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
inet_opt = rcu_dereference_protected(inet->inet_opt,
sock_owned_by_user(sk));
if (inet_opt != NULL && inet_opt->opt.srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet_opt->opt.faddr;
}
orig_sport = inet->inet_sport;
orig_dport = usin->sin_port;
fl4 = &inet->cork.fl.u.ip4;
rt = ip_route_connect(fl4, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
orig_sport, orig_dport, sk);
if (IS_ERR(rt))
return PTR_ERR(rt);
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet_opt == NULL || !inet_opt->opt.srr)
daddr = fl4->daddr;
if (inet->inet_saddr == 0)
inet->inet_saddr = fl4->saddr;
sk_rcv_saddr_set(sk, inet->inet_saddr);
inet->inet_dport = usin->sin_port;
sk_daddr_set(sk, daddr);
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet_opt)
inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
inet->inet_sport, inet->inet_dport, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
goto failure;
}
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->dst);
dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
inet->inet_dport);
inet->inet_id = dp->dccps_iss ^ jiffies;
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
/*
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
goto out;
}
static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv;
struct net_device_stats *stats = &tunnel->stat;
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = skb->nh.ipv6h;
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 */
int max_headroom; /* The extra header space needed */
u32 dst = tiph->daddr;
int mtu;
struct in6_addr *addr6;
int addr_type;
if (tunnel->recursion++) {
tunnel->stat.collisions++;
goto tx_error;
}
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
if (!dst)
dst = try_6to4(&iph6->daddr);
if (!dst) {
struct neighbour *neigh = NULL;
if (skb->dst)
neigh = skb->dst->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 = &skb->nh.ipv6h->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
};
if (ip_route_output_key(&rt, &fl)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
}
if (rt->rt_type != RTN_UNICAST) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
tunnel->stat.collisions++;
goto tx_error;
}
if (tiph->frag_off)
mtu = dst_pmtu(&rt->u.dst) - sizeof(struct iphdr);
else
mtu = skb->dst ? dst_pmtu(skb->dst) : dev->mtu;
if (mtu < 68) {
tunnel->stat.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->dst->ops->update_pmtu(skb->dst, 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 (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
skb->h.raw = skb->nh.raw;
/*
* 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);
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
iph6 = skb->nh.ipv6h;
}
skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/*
* Push down and install the IPIP header.
*/
iph = skb->nh.iph;
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
if (mtu > IPV6_MIN_MTU)
iph->frag_off = htons(IP_DF);
else
iph->frag_off = 0;
iph->protocol = IPPROTO_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ip6_get_dsfield(iph6));
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
#ifdef CONFIG_NETFILTER
nf_conntrack_put(skb->nfct);
skb->nfct = NULL;
#ifdef CONFIG_NETFILTER_DEBUG
skb->nf_debug = 0;
#endif
#endif
IPTUNNEL_XMIT();
tunnel->recursion--;
return 0;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, const u8 protocol)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
struct flowi4 fl4;
u8 tos, ttl;
__be16 df;
struct rtable *rt; /* Route to the other host */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst;
int err;
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, inner_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb),
&ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
addr6 = (const 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)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
}
#endif
else
goto tx_error;
}
tos = tnl_params->tos;
if (tos & 0x1) {
tos &= ~0x1;
if (skb->protocol == htons(ETH_P_IP))
tos = inner_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph);
}
rt = ip_route_output_tunnel(tunnel->net, &fl4,
protocol,
dst, tnl_params->saddr,
tunnel->parms.o_key,
RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (rt->dst.dev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->net != dev_net(dev))
skb_scrub_packet(skb);
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;
}
tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
ttl = tnl_params->ttl;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
ttl = inner_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
ttl = ((const struct ipv6hdr *)inner_iph)->hop_limit;
#endif
else
ttl = ip4_dst_hoplimit(&rt->dst);
}
df = tnl_params->frag_off;
if (skb->protocol == htons(ETH_P_IP))
df |= (inner_iph->frag_off&htons(IP_DF));
max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
+ rt->dst.header_len;
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
if (skb_cow_head(skb, dev->needed_headroom)) {
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return;
}
err = iptunnel_xmit(dev_net(dev), rt, skb,
fl4.saddr, fl4.daddr, protocol,
tos, ttl, df);
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
return;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
}
static int ipip_tunnel_xmit(struct sk_buff *skb, struct device *dev)
{
struct ip_tunnel *tunnel = (struct ip_tunnel*)dev->priv;
struct net_device_stats *stats = &tunnel->stat;
struct iphdr *tiph = &tunnel->parms.iph;
u8 tos = tunnel->parms.iph.tos;
u16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct device *tdev; /* Device to other host */
struct iphdr *old_iph = skb->nh.iph;
struct iphdr *iph; /* Our new IP header */
int max_headroom; /* The extra header space needed */
u32 dst = tiph->daddr;
int mtu;
if (tunnel->recursion++) {
tunnel->stat.collisions++;
goto tx_error;
}
if (skb->protocol != __constant_htons(ETH_P_IP))
goto tx_error;
if (tos&1)
tos = old_iph->tos;
if (!dst) {
/* NBMA tunnel */
if ((rt = (struct rtable*)skb->dst) == NULL) {
tunnel->stat.tx_fifo_errors++;
goto tx_error;
}
if ((dst = rt->rt_gateway) == 0)
goto tx_error_icmp;
}
if (ip_route_output(&rt, dst, tiph->saddr, RT_TOS(tos), tunnel->parms.link)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
tunnel->stat.collisions++;
goto tx_error;
}
mtu = rt->u.dst.pmtu - sizeof(struct iphdr);
if (mtu < 68) {
tunnel->stat.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (skb->dst && mtu < skb->dst->pmtu)
skb->dst->pmtu = mtu;
df |= (old_iph->frag_off&__constant_htons(IP_DF));
if ((old_iph->frag_off&__constant_htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
goto tx_error;
}
if (tunnel->err_count > 0) {
if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
skb->h.raw = skb->nh.raw;
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = (((tdev->hard_header_len+15)&~15)+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);
stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
}
skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
dst_release(skb->dst);
skb->dst = &rt->u.dst;
/*
* Push down and install the IPIP header.
*/
iph = skb->nh.iph;
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
iph->frag_off = df;
iph->protocol = IPPROTO_IPIP;
iph->tos = tos;
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = old_iph->ttl;
iph->tot_len = htons(skb->len);
iph->id = htons(ip_id_count++);
ip_send_check(iph);
stats->tx_bytes += skb->len;
stats->tx_packets++;
ip_send(skb);
tunnel->recursion--;
return 0;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
/*
* 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 */
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)))
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 = rt->rt_dst;
iph->saddr = rt->rt_src;
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;
}
static int pptp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
{
struct sock *sk = (struct sock *) chan->private;
struct pppox_sock *po = pppox_sk(sk);
struct pptp_opt *opt=&po->proto.pptp;
struct pptp_gre_header *hdr;
unsigned int header_len=sizeof(*hdr);
int len=skb?skb->len:0;
int err=0;
int window;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
int max_headroom; /* The extra header space needed */
INC_TX_PACKETS;
spin_lock_bh(&opt->xmit_lock);
window=WRAPPED(opt->ack_recv,opt->seq_sent)?(__u32)0xffffffff-opt->seq_sent+opt->ack_recv:opt->seq_sent-opt->ack_recv;
if (!skb){
if (opt->ack_sent == opt->seq_recv) goto exit;
}else if (window>opt->window){
__set_bit(PPTP_FLAG_PAUSE,(unsigned long*)&opt->flags);
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
mod_timer(&opt->ack_timeout_timer,opt->stat->rtt/100*HZ/10000);
#else
schedule_delayed_work(&opt->ack_timeout_work,opt->stat->rtt/100*HZ/10000);
#endif
goto exit;
}
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
{
struct rt_key key = {
.dst=opt->dst_addr.sin_addr.s_addr,
.src=opt->src_addr.sin_addr.s_addr,
.tos=RT_TOS(0),
};
if ((err=ip_route_output_key(&rt, &key))) {
goto tx_error;
}
}
#else
{
struct flowi fl = { .oif = 0,
.nl_u = { .ip4_u =
{ .daddr = opt->dst_addr.sin_addr.s_addr,
.saddr = opt->src_addr.sin_addr.s_addr,
.tos = RT_TOS(0) } },
.proto = IPPROTO_GRE };
if ((err=ip_route_output_key(&rt, &fl))) {
goto tx_error;
}
}
#endif
tdev = rt->u.dst.dev;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
max_headroom = ((tdev->hard_header_len+15)&~15) + sizeof(*iph)+sizeof(*hdr)+2;
#else
max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(*iph)+sizeof(*hdr)+2;
#endif
if (!skb){
skb=dev_alloc_skb(max_headroom);
if (!skb) {
ip_rt_put(rt);
goto tx_error;
}
skb_reserve(skb,max_headroom-skb_headroom(skb));
}else 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);
goto tx_error;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
kfree_skb(skb);
skb = new_skb;
}
if (skb->len){
int islcp;
unsigned char *data=skb->data;
islcp=((data[0] << 8) + data[1])== PPP_LCP && 1 <= data[2] && data[2] <= 7;
/* compress protocol field */
if ((opt->ppp_flags & SC_COMP_PROT) && data[0]==0 && !islcp)
skb_pull(skb,1);
/*
* Put in the address/control bytes if necessary
*/
if ((opt->ppp_flags & SC_COMP_AC) == 0 || islcp) {
data=skb_push(skb,2);
data[0]=0xff;
data[1]=0x03;
}
}
len=skb->len;
if (len==0) header_len-=sizeof(hdr->seq);
if (opt->ack_sent == opt->seq_recv) header_len-=sizeof(hdr->ack);
// Push down and install GRE header
skb_push(skb,header_len);
hdr=(struct pptp_gre_header *)(skb->data);
hdr->flags = PPTP_GRE_FLAG_K;
hdr->ver = PPTP_GRE_VER;
hdr->protocol = htons(PPTP_GRE_PROTO);
hdr->call_id = htons(opt->dst_addr.call_id);
if (!len){
hdr->payload_len = 0;
hdr->ver |= PPTP_GRE_FLAG_A;
/* ack is in odd place because S == 0 */
hdr->seq = htonl(opt->seq_recv);
opt->ack_sent = opt->seq_recv;
opt->stat->tx_acks++;
}else {
hdr->flags |= PPTP_GRE_FLAG_S;
hdr->seq = htonl(opt->seq_sent++);
if (log_level>=3 && opt->seq_sent<=log_packets)
printk(KERN_INFO"PPTP[%i]: send packet: seq=%i",opt->src_addr.call_id,opt->seq_sent);
if (opt->ack_sent != opt->seq_recv) {
/* send ack with this message */
hdr->ver |= PPTP_GRE_FLAG_A;
hdr->ack = htonl(opt->seq_recv);
opt->ack_sent = opt->seq_recv;
if (log_level>=3 && opt->seq_sent<=log_packets)
printk(" ack=%i",opt->seq_recv);
}
hdr->payload_len = htons(len);
if (log_level>=3 && opt->seq_sent<=log_packets)
printk("\n");
}
/*
* Push down and install the IP header.
*/
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,22)
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(*iph));
skb_reset_network_header(skb);
#else
skb->h.raw = skb->nh.raw;
skb->nh.raw = skb_push(skb, sizeof(*iph));
#endif
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,16)
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
#endif
#if LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,22)
iph = ip_hdr(skb);
#else
iph = skb->nh.iph;
#endif
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = 0;//df;
iph->protocol = IPPROTO_GRE;
iph->tos = 0;
iph->daddr = rt->rt_dst;
iph->saddr = rt->rt_src;
#if LINUX_VERSION_CODE < KERNEL_VERSION(2,6,0)
iph->ttl = sysctl_ip_default_ttl;
#else
iph->ttl = dst_metric(&rt->u.dst, RTAX_HOPLIMIT);
#endif
iph->tot_len = htons(skb->len);
dst_release(skb->dst);
skb->dst = &rt->u.dst;
nf_reset(skb);
skb->ip_summed = CHECKSUM_NONE;
ip_select_ident(iph, &rt->u.dst, NULL);
ip_send_check(iph);
err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev, dst_output);
wake_up(&opt->wait);
if (err == NET_XMIT_SUCCESS || err == NET_XMIT_CN) {
opt->stat->tx_sent++;
if (!opt->stat->pt_seq){
opt->stat->pt_seq = opt->seq_sent;
do_gettimeofday(&opt->stat->pt_time);
}
}else{
INC_TX_ERRORS;
opt->stat->tx_failed++;
}
spin_unlock_bh(&opt->xmit_lock);
return 1;
tx_error:
INC_TX_ERRORS;
opt->stat->tx_failed++;
if (!len) kfree_skb(skb);
spin_unlock_bh(&opt->xmit_lock);
return 1;
exit:
spin_unlock_bh(&opt->xmit_lock);
return 0;
}
/* This requires some explaining. If DNAT has taken place,
* we will need to fix up the destination Ethernet address.
* This is also true when SNAT takes place (for the reply direction).
*
* There are two cases to consider:
* 1. The packet was DNAT'ed to a device in the same bridge
* port group as it was received on. We can still bridge
* the packet.
* 2. The packet was DNAT'ed to a different device, either
* a non-bridged device or another bridge port group.
* The packet will need to be routed.
*
* The correct way of distinguishing between these two cases is to
* call ip_route_input() and to look at skb->dst->dev, which is
* changed to the destination device if ip_route_input() succeeds.
*
* Let's first consider the case that ip_route_input() succeeds:
*
* If the output device equals the logical bridge device the packet
* came in on, we can consider this bridging. The corresponding MAC
* address will be obtained in br_nf_pre_routing_finish_bridge.
* Otherwise, the packet is considered to be routed and we just
* change the destination MAC address so that the packet will
* later be passed up to the IP stack to be routed. For a redirected
* packet, ip_route_input() will give back the localhost as output device,
* which differs from the bridge device.
*
* Let's now consider the case that ip_route_input() fails:
*
* This can be because the destination address is martian, in which case
* the packet will be dropped.
* If IP forwarding is disabled, ip_route_input() will fail, while
* ip_route_output_key() can return success. The source
* address for ip_route_output_key() is set to zero, so ip_route_output_key()
* thinks we're handling a locally generated packet and won't care
* if IP forwarding is enabled. If the output device equals the logical bridge
* device, we proceed as if ip_route_input() succeeded. If it differs from the
* logical bridge port or if ip_route_output_key() fails we drop the packet.
*/
static int br_nf_pre_routing_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct iphdr *iph = ip_hdr(skb);
struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
struct rtable *rt;
int err;
nf_bridge->frag_max_size = IPCB(skb)->frag_max_size;
if (nf_bridge->pkt_otherhost) {
skb->pkt_type = PACKET_OTHERHOST;
nf_bridge->pkt_otherhost = false;
}
nf_bridge->in_prerouting = 0;
if (br_nf_ipv4_daddr_was_changed(skb, nf_bridge)) {
if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
/* If err equals -EHOSTUNREACH the error is due to a
* martian destination or due to the fact that
* forwarding is disabled. For most martian packets,
* ip_route_output_key() will fail. It won't fail for 2 types of
* martian destinations: loopback destinations and destination
* 0.0.0.0. In both cases the packet will be dropped because the
* destination is the loopback device and not the bridge. */
if (err != -EHOSTUNREACH || !in_dev || IN_DEV_FORWARD(in_dev))
goto free_skb;
rt = ip_route_output(net, iph->daddr, 0,
RT_TOS(iph->tos), 0);
if (!IS_ERR(rt)) {
/* - Bridged-and-DNAT'ed traffic doesn't
* require ip_forwarding. */
if (rt->dst.dev == dev) {
skb_dst_set(skb, &rt->dst);
goto bridged_dnat;
}
ip_rt_put(rt);
}
free_skb:
kfree_skb(skb);
return 0;
} else {
if (skb_dst(skb)->dev == dev) {
bridged_dnat:
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
br_nf_hook_thresh(NF_BR_PRE_ROUTING,
net, sk, skb, skb->dev,
NULL,
br_nf_pre_routing_finish_bridge);
return 0;
}
ether_addr_copy(eth_hdr(skb)->h_dest, dev->dev_addr);
skb->pkt_type = PACKET_HOST;
}
} else {
rt = bridge_parent_rtable(nf_bridge->physindev);
if (!rt) {
kfree_skb(skb);
return 0;
}
skb_dst_set_noref(skb, &rt->dst);
}
skb->dev = nf_bridge->physindev;
nf_bridge_update_protocol(skb);
nf_bridge_push_encap_header(skb);
br_nf_hook_thresh(NF_BR_PRE_ROUTING, net, sk, skb, skb->dev, NULL,
br_handle_frame_finish);
return 0;
}
static int ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct net_device_stats *stats = &tunnel->stat;
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;
if (tunnel->recursion++) {
tunnel->stat.collisions++;
goto tx_error;
}
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
if (extract_ipv4_endpoint(&iph6->daddr, &dst) < 0)
goto tx_error_icmp;
{
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(&rt, &fl)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
tunnel->stat.collisions++;
goto tx_error;
}
if (tiph->frag_off)
mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
else
mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
if (mtu < 68) {
tunnel->stat.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->dst->ops->update_pmtu(skb->dst, 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 (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);
tunnel->recursion--;
return 0;
}
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;
dst_release(skb->dst);
skb->dst = &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 = htons(IP_DF);
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();
tunnel->recursion--;
return 0;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
}
/* Reroute packet to local IPv4 stack after DNAT */
static int
__ip_vs_reroute_locally(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = rt->dst.dev;
struct net *net = dev_net(dev);
struct iphdr *iph = ip_hdr(skb);
if (rt_is_input_route(rt)) {
unsigned long orefdst = skb->_skb_refdst;
if (ip_route_input(skb, iph->daddr, iph->saddr,
iph->tos, skb->dev))
return 0;
refdst_drop(orefdst);
} else {
struct flowi4 fl4 = {
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowi4_tos = RT_TOS(iph->tos),
.flowi4_mark = skb->mark,
};
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return 0;
if (!(rt->rt_flags & RTCF_LOCAL)) {
ip_rt_put(rt);
return 0;
}
/* Drop old route. */
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
}
return 1;
}
#ifdef CONFIG_IP_VS_IPV6
static inline int __ip_vs_is_local_route6(struct rt6_info *rt)
{
return rt->rt6i_dev && rt->rt6i_dev->flags & IFF_LOOPBACK;
}
static struct dst_entry *
__ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
struct in6_addr *ret_saddr, int do_xfrm)
{
struct dst_entry *dst;
struct flowi6 fl6 = {
.daddr = *daddr,
};
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error)
goto out_err;
if (!ret_saddr)
return dst;
if (ipv6_addr_any(&fl6.saddr) &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6.daddr, 0, &fl6.saddr) < 0)
goto out_err;
if (do_xfrm) {
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst)) {
dst = NULL;
goto out_err;
}
}
ipv6_addr_copy(ret_saddr, &fl6.saddr);
return dst;
out_err:
dst_release(dst);
IP_VS_DBG_RL("ip6_route_output error, dest: %pI6\n", daddr);
return NULL;
}
/*
* Get route to destination or remote server
* rt_mode: flags, &1=Allow local dest, &2=Allow non-local dest,
* &4=Allow redirect from remote daddr to local
*/
static struct rt6_info *
__ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
struct in6_addr *daddr, struct in6_addr *ret_saddr,
int do_xfrm, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rt6_info *rt; /* Route to the other host */
struct rt6_info *ort; /* Original route */
struct dst_entry *dst;
int local;
if (dest) {
spin_lock(&dest->dst_lock);
rt = (struct rt6_info *)__ip_vs_dst_check(dest, 0);
if (!rt) {
u32 cookie;
dst = __ip_vs_route_output_v6(net, &dest->addr.in6,
&dest->dst_saddr,
do_xfrm);
if (!dst) {
spin_unlock(&dest->dst_lock);
return NULL;
}
rt = (struct rt6_info *) dst;
cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0;
__ip_vs_dst_set(dest, 0, dst_clone(&rt->dst), cookie);
IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
&dest->addr.in6, &dest->dst_saddr,
atomic_read(&rt->dst.__refcnt));
}
if (ret_saddr)
ipv6_addr_copy(ret_saddr, &dest->dst_saddr);
spin_unlock(&dest->dst_lock);
} else {
dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
if (!dst)
return NULL;
rt = (struct rt6_info *) dst;
}
local = __ip_vs_is_local_route6(rt);
if (!((local ? 1 : 2) & rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI6\n",
local ? "local":"non-local", daddr);
dst_release(&rt->dst);
return NULL;
}
if (local && !(rt_mode & 4) &&
!((ort = (struct rt6_info *) skb_dst(skb)) &&
__ip_vs_is_local_route6(ort))) {
IP_VS_DBG_RL("Redirect from non-local address %pI6 to local "
"requires NAT method, dest: %pI6\n",
&ipv6_hdr(skb)->daddr, daddr);
dst_release(&rt->dst);
return NULL;
}
if (unlikely(!local && (!skb->dev || skb->dev->flags & IFF_LOOPBACK) &&
ipv6_addr_type(&ipv6_hdr(skb)->saddr) &
IPV6_ADDR_LOOPBACK)) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI6 "
"to non-local address, dest: %pI6\n",
&ipv6_hdr(skb)->saddr, daddr);
dst_release(&rt->dst);
return NULL;
}
return rt;
}
#endif
/*
* Release dest->dst_cache before a dest is removed
*/
void
ip_vs_dst_reset(struct ip_vs_dest *dest)
{
struct dst_entry *old_dst;
old_dst = dest->dst_cache;
dest->dst_cache = NULL;
dst_release(old_dst);
}
#define IP_VS_XMIT_TUNNEL(skb, cp) \
({ \
int __ret = NF_ACCEPT; \
\
(skb)->ipvs_property = 1; \
if (unlikely((cp)->flags & IP_VS_CONN_F_NFCT)) \
__ret = ip_vs_confirm_conntrack(skb, cp); \
if (__ret == NF_ACCEPT) { \
nf_reset(skb); \
skb_forward_csum(skb); \
} \
__ret; \
})
#define IP_VS_XMIT_NAT(pf, skb, cp, local) \
do { \
(skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
ip_vs_notrack(skb); \
else \
ip_vs_update_conntrack(skb, cp, 1); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
#define IP_VS_XMIT(pf, skb, cp, local) \
do { \
(skb)->ipvs_property = 1; \
if (likely(!((cp)->flags & IP_VS_CONN_F_NFCT))) \
ip_vs_notrack(skb); \
if (local) \
return NF_ACCEPT; \
skb_forward_csum(skb); \
NF_HOOK(pf, NF_INET_LOCAL_OUT, (skb), NULL, \
skb_dst(skb)->dev, dst_output); \
} while (0)
/*
* NULL transmitter (do nothing except return NF_ACCEPT)
*/
int
ip_vs_null_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
struct ip_vs_protocol *pp)
{
/* we do not touch skb and do not need pskb ptr */
IP_VS_XMIT(NFPROTO_IPV4, skb, cp, 1);
}
/*
* 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)))
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(rt->rt_dst) &&
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 dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
struct rtable *rt;
__be32 daddr, nexthop;
int tmp;
int err;
dp->dccps_role = DCCP_ROLE_CLIENT;
if (addr_len < sizeof(struct sockaddr_in))
return -EINVAL;
if (usin->sin_family != AF_INET)
return -EAFNOSUPPORT;
nexthop = daddr = usin->sin_addr.s_addr;
if (inet->opt != NULL && inet->opt->srr) {
if (daddr == 0)
return -EINVAL;
nexthop = inet->opt->faddr;
}
tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr,
RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
IPPROTO_DCCP,
inet->inet_sport, usin->sin_port, sk, 1);
if (tmp < 0)
return tmp;
if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
ip_rt_put(rt);
return -ENETUNREACH;
}
if (inet->opt == NULL || !inet->opt->srr)
daddr = rt->rt_dst;
if (inet->inet_saddr == 0)
inet->inet_saddr = rt->rt_src;
inet->inet_rcv_saddr = inet->inet_saddr;
inet->inet_dport = usin->sin_port;
inet->inet_daddr = daddr;
inet_csk(sk)->icsk_ext_hdr_len = 0;
if (inet->opt != NULL)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
/*
* Socket identity is still unknown (sport may be zero).
* However we set state to DCCP_REQUESTING and not releasing socket
* lock select source port, enter ourselves into the hash tables and
* complete initialization after this.
*/
dccp_set_state(sk, DCCP_REQUESTING);
err = inet_hash_connect(&dccp_death_row, sk);
if (err != 0)
goto failure;
err = ip_route_newports(&rt, IPPROTO_DCCP, inet->inet_sport,
inet->inet_dport, sk);
if (err != 0)
goto failure;
/* OK, now commit destination to socket. */
sk_setup_caps(sk, &rt->u.dst);
dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr,
inet->inet_daddr,
inet->inet_sport,
inet->inet_dport);
inet->inet_id = dp->dccps_iss ^ jiffies;
err = dccp_connect(sk);
rt = NULL;
if (err != 0)
goto failure;
out:
return err;
failure:
/*
* This unhashes the socket and releases the local port, if necessary.
*/
dccp_set_state(sk, DCCP_CLOSED);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
goto out;
}
/* Get route to destination or remote server */
static struct rtable *
__ip_vs_get_out_rt(struct sk_buff *skb, struct ip_vs_dest *dest,
__be32 daddr, u32 rtos, int rt_mode)
{
struct net *net = dev_net(skb_dst(skb)->dev);
struct rtable *rt; /* Route to the other host */
struct rtable *ort; /* Original route */
int local;
if (dest) {
spin_lock(&dest->dst_lock);
if (!(rt = (struct rtable *)
__ip_vs_dst_check(dest, rtos))) {
rt = ip_route_output(net, dest->addr.ip, 0, rtos, 0);
if (IS_ERR(rt)) {
spin_unlock(&dest->dst_lock);
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&dest->addr.ip);
return NULL;
}
__ip_vs_dst_set(dest, rtos, dst_clone(&rt->dst), 0);
IP_VS_DBG(10, "new dst %pI4, refcnt=%d, rtos=%X\n",
&dest->addr.ip,
atomic_read(&rt->dst.__refcnt), rtos);
}
spin_unlock(&dest->dst_lock);
} else {
rt = ip_route_output(net, daddr, 0, rtos, 0);
if (IS_ERR(rt)) {
IP_VS_DBG_RL("ip_route_output error, dest: %pI4\n",
&daddr);
return NULL;
}
}
local = rt->rt_flags & RTCF_LOCAL;
if (!((local ? IP_VS_RT_MODE_LOCAL : IP_VS_RT_MODE_NON_LOCAL) &
rt_mode)) {
IP_VS_DBG_RL("Stopping traffic to %s address, dest: %pI4\n",
(rt->rt_flags & RTCF_LOCAL) ?
"local":"non-local", &rt->rt_dst);
ip_rt_put(rt);
return NULL;
}
if (local && !(rt_mode & IP_VS_RT_MODE_RDR) &&
!((ort = skb_rtable(skb)) && ort->rt_flags & RTCF_LOCAL)) {
IP_VS_DBG_RL("Redirect from non-local address %pI4 to local "
"requires NAT method, dest: %pI4\n",
&ip_hdr(skb)->daddr, &rt->rt_dst);
ip_rt_put(rt);
return NULL;
}
if (unlikely(!local && ipv4_is_loopback(ip_hdr(skb)->saddr))) {
IP_VS_DBG_RL("Stopping traffic from loopback address %pI4 "
"to non-local address, dest: %pI4\n",
&ip_hdr(skb)->saddr, &rt->rt_dst);
ip_rt_put(rt);
return NULL;
}
return rt;
}
void ipip_err(struct sk_buff *skb, unsigned char *dp, int len)
{
#ifndef I_WISH_WORLD_WERE_PERFECT
/* It is not :-( All the routers (except for Linux) return only
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
*/
struct iphdr *iph = (struct iphdr*)dp;
int type = skb->h.icmph->type;
int code = skb->h.icmph->code;
struct ip_tunnel *t;
if (len < sizeof(struct iphdr))
return;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
case ICMP_FRAG_NEEDED:
/* Soft state for pmtu is maintained by IP core. */
return;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe they are just ether pollution. --ANK
*/
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return;
break;
}
t = ipip_tunnel_lookup(iph->daddr, iph->saddr);
if (t == NULL || t->parms.iph.daddr == 0)
return;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
return;
if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
return;
#else
struct iphdr *iph = (struct iphdr*)dp;
int hlen = iph->ihl<<2;
struct iphdr *eiph;
int type = skb->h.icmph->type;
int code = skb->h.icmph->code;
int rel_type = 0;
int rel_code = 0;
int rel_info = 0;
struct sk_buff *skb2;
struct rtable *rt;
if (len < hlen + sizeof(struct iphdr))
return;
eiph = (struct iphdr*)(dp + hlen);
switch (type) {
default:
return;
case ICMP_PARAMETERPROB:
if (skb->h.icmph->un.gateway < hlen)
return;
/* So... This guy found something strange INSIDE encapsulated
packet. Well, he is fool, but what can we do ?
*/
rel_type = ICMP_PARAMETERPROB;
rel_info = skb->h.icmph->un.gateway - hlen;
break;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
case ICMP_FRAG_NEEDED:
/* And it is the only really necessary thing :-) */
rel_info = ntohs(skb->h.icmph->un.frag.mtu);
if (rel_info < hlen+68)
return;
rel_info -= hlen;
/* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
if (rel_info > ntohs(eiph->tot_len))
return;
break;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe, it is just ether pollution. --ANK
*/
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return;
break;
}
/* Prepare fake skb to feed it to icmp_send */
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 == NULL)
return;
dst_release(skb2->dst);
skb2->dst = NULL;
skb_pull(skb2, skb->data - (u8*)eiph);
skb2->nh.raw = skb2->data;
/* Try to guess incoming interface */
if (ip_route_output(&rt, eiph->saddr, 0, RT_TOS(eiph->tos), 0)) {
kfree_skb(skb2);
return;
}
skb2->dev = rt->u.dst.dev;
/* route "incoming" packet */
if (rt->rt_flags&RTCF_LOCAL) {
ip_rt_put(rt);
rt = NULL;
if (ip_route_output(&rt, eiph->daddr, eiph->saddr, eiph->tos, 0) ||
rt->u.dst.dev->type != ARPHRD_IPGRE) {
ip_rt_put(rt);
kfree_skb(skb2);
return;
}
} else {
ip_rt_put(rt);
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
skb2->dst->dev->type != ARPHRD_IPGRE) {
kfree_skb(skb2);
return;
}
}
/* change mtu on this route */
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
if (rel_info > skb2->dst->pmtu) {
kfree_skb(skb2);
return;
}
skb2->dst->pmtu = rel_info;
rel_info = htonl(rel_info);
} else if (type == ICMP_TIME_EXCEEDED) {
struct ip_tunnel *t = (struct ip_tunnel*)skb2->dev->priv;
if (t->parms.iph.ttl) {
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
}
}
icmp_send(skb2, rel_type, rel_code, rel_info);
kfree_skb(skb2);
return;
#endif
}