* Linux INET6 implementation
*
* Authors:
- * Pedro Roque <roque@di.fc.ul.pt>
+ * Pedro Roque <roque@di.fc.ul.pt>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
*
* $Id: sit.c,v 1.53 2001/09/25 05:09:53 davem Exp $
* Changes:
* Roger Venning <r.venning@telstra.com>: 6to4 support
* Nate Thompson <nate@thebog.net>: 6to4 support
+ * Fred L. Templin <fltemplin@acm.org>: isatap support
*/
#include <linux/module.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
-#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
*/
#define HASH_SIZE 16
-#define HASH(addr) ((addr^(addr>>4))&0xF)
+#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
static int ipip6_fb_tunnel_init(struct net_device *dev);
static int ipip6_tunnel_init(struct net_device *dev);
static DEFINE_RWLOCK(ipip6_lock);
-static struct ip_tunnel * ipip6_tunnel_lookup(u32 remote, u32 local)
+static struct ip_tunnel * ipip6_tunnel_lookup(__be32 remote, __be32 local)
{
unsigned h0 = HASH(remote);
unsigned h1 = HASH(local);
return NULL;
}
-static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t)
+static struct ip_tunnel **__ipip6_bucket(struct ip_tunnel_parm *parms)
{
- u32 remote = t->parms.iph.daddr;
- u32 local = t->parms.iph.saddr;
+ __be32 remote = parms->iph.daddr;
+ __be32 local = parms->iph.saddr;
unsigned h = 0;
int prio = 0;
return &tunnels[prio][h];
}
+static inline struct ip_tunnel **ipip6_bucket(struct ip_tunnel *t)
+{
+ return __ipip6_bucket(&t->parms);
+}
+
static void ipip6_tunnel_unlink(struct ip_tunnel *t)
{
struct ip_tunnel **tp;
static struct ip_tunnel * ipip6_tunnel_locate(struct ip_tunnel_parm *parms, int create)
{
- u32 remote = parms->iph.daddr;
- u32 local = parms->iph.saddr;
+ __be32 remote = parms->iph.daddr;
+ __be32 local = parms->iph.saddr;
struct ip_tunnel *t, **tp, *nt;
struct net_device *dev;
- unsigned h = 0;
- int prio = 0;
char name[IFNAMSIZ];
- if (remote) {
- prio |= 2;
- h ^= HASH(remote);
- }
- if (local) {
- prio |= 1;
- h ^= HASH(local);
- }
- for (tp = &tunnels[prio][h]; (t = *tp) != NULL; tp = &t->next) {
+ for (tp = __ipip6_bucket(parms); (t = *tp) != NULL; tp = &t->next) {
if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr)
return t;
}
int i;
for (i=1; i<100; i++) {
sprintf(name, "sit%d", i);
- if (__dev_get_by_name(name) == NULL)
+ if (__dev_get_by_name(&init_net, name) == NULL)
break;
}
if (i==100)
dev->init = ipip6_tunnel_init;
nt->parms = *parms;
+ if (parms->i_flags & SIT_ISATAP)
+ dev->priv_flags |= IFF_ISATAP;
+
if (register_netdevice(dev) < 0) {
free_netdev(dev);
goto failed;
}
-static void ipip6_err(struct sk_buff *skb, u32 info)
+static int ipip6_err(struct sk_buff *skb, u32 info)
{
#ifndef I_WISH_WORLD_WERE_PERFECT
ICMP in the real Internet is absolutely infeasible.
*/
struct iphdr *iph = (struct iphdr*)skb->data;
- int type = skb->h.icmph->type;
- int code = skb->h.icmph->code;
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
+ int err;
switch (type) {
default:
case ICMP_PARAMETERPROB:
- return;
+ return 0;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
- return;
+ return 0;
case ICMP_FRAG_NEEDED:
/* Soft state for pmtu is maintained by IP core. */
- return;
+ return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
- return;
+ return 0;
break;
}
+ err = -ENOENT;
+
read_lock(&ipip6_lock);
t = ipip6_tunnel_lookup(iph->daddr, iph->saddr);
if (t == NULL || t->parms.iph.daddr == 0)
goto out;
+
+ err = 0;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
t->err_time = jiffies;
out:
read_unlock(&ipip6_lock);
- return;
+ return err;
#else
struct iphdr *iph = (struct iphdr*)dp;
int hlen = iph->ihl<<2;
struct ipv6hdr *iph6;
- int type = skb->h.icmph->type;
- int code = skb->h.icmph->code;
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
int rel_type = 0;
int rel_code = 0;
int rel_info = 0;
default:
return;
case ICMP_PARAMETERPROB:
- if (skb->h.icmph->un.gateway < hlen)
+ if (icmp_hdr(skb)->un.gateway < hlen)
return;
/* So... This guy found something strange INSIDE encapsulated
packet. Well, he is fool, but what can we do ?
*/
rel_type = ICMPV6_PARAMPROB;
- rel_info = skb->h.icmph->un.gateway - hlen;
+ rel_info = icmp_hdr(skb)->un.gateway - hlen;
break;
case ICMP_DEST_UNREACH:
/* Prepare fake skb to feed it to icmpv6_send */
skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2 == NULL)
- return;
+ return 0;
dst_release(skb2->dst);
skb2->dst = NULL;
skb_pull(skb2, skb->data - (u8*)iph6);
- skb2->nh.raw = skb2->data;
+ skb_reset_network_header(skb2);
/* Try to guess incoming interface */
rt6i = rt6_lookup(&iph6->saddr, NULL, NULL, 0);
}
}
kfree_skb(skb2);
- return;
+ return 0;
#endif
}
static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
{
if (INET_ECN_is_ce(iph->tos))
- IP6_ECN_set_ce(skb->nh.ipv6h);
+ IP6_ECN_set_ce(ipv6_hdr(skb));
+}
+
+/* ISATAP (RFC4214) - check source address */
+static int
+isatap_srcok(struct sk_buff *skb, struct iphdr *iph, struct net_device *dev)
+{
+ struct neighbour *neigh;
+ struct dst_entry *dst;
+ struct rt6_info *rt;
+ struct flowi fl;
+ struct in6_addr *addr6;
+ struct in6_addr rtr;
+ struct ipv6hdr *iph6;
+ int ok = 0;
+
+ /* from onlink default router */
+ ipv6_addr_set(&rtr, htonl(0xFE800000), 0, 0, 0);
+ ipv6_isatap_eui64(rtr.s6_addr + 8, iph->saddr);
+ if ((rt = rt6_get_dflt_router(&rtr, dev))) {
+ dst_release(&rt->u.dst);
+ return 1;
+ }
+
+ iph6 = ipv6_hdr(skb);
+ memset(&fl, 0, sizeof(fl));
+ fl.proto = iph6->nexthdr;
+ ipv6_addr_copy(&fl.fl6_dst, &iph6->saddr);
+ fl.oif = dev->ifindex;
+ security_skb_classify_flow(skb, &fl);
+
+ dst = ip6_route_output(NULL, &fl);
+ if (!dst->error && (dst->dev == dev) && (neigh = dst->neighbour)) {
+
+ addr6 = (struct in6_addr*)&neigh->primary_key;
+
+ /* from correct previous hop */
+ if (ipv6_addr_is_isatap(addr6) &&
+ (addr6->s6_addr32[3] == iph->saddr))
+ ok = 1;
+ }
+ dst_release(dst);
+ return ok;
}
static int ipip6_rcv(struct sk_buff *skb)
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
- iph = skb->nh.iph;
+ iph = ip_hdr(skb);
read_lock(&ipip6_lock);
if ((tunnel = ipip6_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) {
secpath_reset(skb);
- skb->mac.raw = skb->nh.raw;
- skb->nh.raw = skb->data;
+ skb->mac_header = skb->network_header;
+ skb_reset_network_header(skb);
IPCB(skb)->flags = 0;
skb->protocol = htons(ETH_P_IPV6);
skb->pkt_type = PACKET_HOST;
+
+ if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
+ !isatap_srcok(skb, iph, tunnel->dev)) {
+ tunnel->stat.rx_errors++;
+ read_unlock(&ipip6_lock);
+ kfree_skb(skb);
+ return 0;
+ }
tunnel->stat.rx_packets++;
tunnel->stat.rx_bytes += skb->len;
skb->dev = tunnel->dev;
/* Returns the embedded IPv4 address if the IPv6 address
comes from 6to4 (RFC 3056) addr space */
-static inline u32 try_6to4(struct in6_addr *v6dst)
+static inline __be32 try_6to4(struct in6_addr *v6dst)
{
- u32 dst = 0;
+ __be32 dst = 0;
if (v6dst->s6_addr16[0] == htons(0x2002)) {
- /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
+ /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
memcpy(&dst, &v6dst->s6_addr16[1], 4);
}
return dst;
struct ip_tunnel *tunnel = netdev_priv(dev);
struct net_device_stats *stats = &tunnel->stat;
struct iphdr *tiph = &tunnel->parms.iph;
- struct ipv6hdr *iph6 = skb->nh.ipv6h;
+ 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 */
- int max_headroom; /* The extra header space needed */
- u32 dst = tiph->daddr;
+ unsigned int max_headroom; /* The extra header space needed */
+ __be32 dst = tiph->daddr;
int mtu;
- struct in6_addr *addr6;
+ struct in6_addr *addr6;
int addr_type;
if (tunnel->recursion++) {
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)
+ 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_UNICAST) &&
+ ipv6_addr_is_isatap(addr6))
+ dst = addr6->s6_addr32[3];
+ else
+ goto tx_error;
+ }
+
if (!dst)
dst = try_6to4(&iph6->daddr);
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
- addr6 = &skb->nh.ipv6h->daddr;
+ addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
.tos = RT_TOS(tos) } },
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6 };
- if (ip_route_output_key(&rt, &fl)) {
+ if (ip_route_output_key(&init_net, &rt, &fl)) {
tunnel->stat.tx_carrier_errors++;
goto tx_error_icmp;
}
*/
max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
- if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
+ 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++;
+ stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
- iph6 = skb->nh.ipv6h;
+ iph6 = ipv6_hdr(skb);
}
- skb->h.raw = skb->nh.raw;
- skb->nh.raw = skb_push(skb, sizeof(struct iphdr));
+ 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);
* Push down and install the IPIP header.
*/
- iph = skb->nh.iph;
+ iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
if (mtu > IPV6_MIN_MTU)
return 0;
}
+static void ipip6_tunnel_bind_dev(struct net_device *dev)
+{
+ struct net_device *tdev = NULL;
+ struct ip_tunnel *tunnel;
+ struct iphdr *iph;
+
+ tunnel = netdev_priv(dev);
+ iph = &tunnel->parms.iph;
+
+ 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(&init_net, &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(&init_net, 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;
+}
+
static int
ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
{
if (cmd == SIOCCHGTUNNEL) {
t->parms.iph.ttl = p.iph.ttl;
t->parms.iph.tos = p.iph.tos;
+ if (t->parms.link != p.link) {
+ t->parms.link = p.link;
+ ipip6_tunnel_bind_dev(dev);
+ netdev_state_change(dev);
+ }
}
if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
err = -EFAULT;
goto done;
dev = t->dev;
}
- err = unregister_netdevice(dev);
+ unregister_netdevice(dev);
+ err = 0;
break;
default:
static void ipip6_tunnel_setup(struct net_device *dev)
{
- SET_MODULE_OWNER(dev);
dev->uninit = ipip6_tunnel_uninit;
dev->destructor = free_netdev;
dev->hard_start_xmit = ipip6_tunnel_xmit;
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;
+ ipip6_tunnel_bind_dev(dev);
return 0;
}
return 0;
}
-static struct net_protocol sit_protocol = {
+static struct xfrm_tunnel sit_handler = {
.handler = ipip6_rcv,
.err_handler = ipip6_err,
+ .priority = 1,
};
static void __exit sit_destroy_tunnels(void)
}
}
-void __exit sit_cleanup(void)
+static void __exit sit_cleanup(void)
{
- inet_del_protocol(&sit_protocol, IPPROTO_IPV6);
+ xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
rtnl_lock();
sit_destroy_tunnels();
rtnl_unlock();
}
-int __init sit_init(void)
+static int __init sit_init(void)
{
int err;
printk(KERN_INFO "IPv6 over IPv4 tunneling driver\n");
- if (inet_add_protocol(&sit_protocol, IPPROTO_IPV6) < 0) {
+ if (xfrm4_tunnel_register(&sit_handler, AF_INET6) < 0) {
printk(KERN_INFO "sit init: Can't add protocol\n");
return -EAGAIN;
}
- ipip6_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
+ ipip6_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
ipip6_tunnel_setup);
if (!ipip6_fb_tunnel_dev) {
err = -ENOMEM;
err2:
free_netdev(ipip6_fb_tunnel_dev);
err1:
- inet_del_protocol(&sit_protocol, IPPROTO_IPV6);
+ xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
goto out;
}