* Changes:
* Roger Venning <r.venning@telstra.com>: 6to4 support
* Nate Thompson <nate@thebog.net>: 6to4 support
+ * Fred Templin <fred.l.templin@boeing.com>: 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>
return NULL;
}
-static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t)
+static struct ip_tunnel **__ipip6_bucket(struct ip_tunnel_parm *parms)
{
- __be32 remote = t->parms.iph.daddr;
- __be32 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;
__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;
}
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
- else {
- int i;
- for (i=1; i<100; i++) {
- sprintf(name, "sit%d", i);
- if (__dev_get_by_name(name) == NULL)
- break;
- }
- if (i==100)
- goto failed;
- }
+ else
+ sprintf(name, "sit%%d");
dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup);
if (dev == NULL)
return NULL;
+ if (strchr(name, '%')) {
+ if (dev_alloc_name(dev, name) < 0)
+ goto failed_free;
+ }
+
nt = netdev_priv(dev);
dev->init = ipip6_tunnel_init;
nt->parms = *parms;
- if (register_netdevice(dev) < 0) {
- free_netdev(dev);
- goto failed;
- }
+ if (parms->i_flags & SIT_ISATAP)
+ dev->priv_flags |= IFF_ISATAP;
+
+ if (register_netdevice(dev) < 0)
+ goto failed_free;
dev_hold(dev);
ipip6_tunnel_link(nt);
return nt;
+failed_free:
+ free_netdev(dev);
failed:
return NULL;
}
+static struct ip_tunnel_prl_entry *
+__ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr)
+{
+ struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *)NULL;
+
+ for (p = t->prl; p; p = p->next)
+ if (p->entry.addr == addr)
+ break;
+ return p;
+
+}
+
+static int
+ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
+{
+ struct ip_tunnel_prl_entry *p;
+ int err = 0;
+
+ if (a->addr == htonl(INADDR_ANY))
+ return -EINVAL;
+
+ write_lock(&ipip6_lock);
+
+ for (p = t->prl; p; p = p->next) {
+ if (p->entry.addr == a->addr) {
+ if (chg)
+ goto update;
+ err = -EEXIST;
+ goto out;
+ }
+ }
+
+ if (chg) {
+ err = -ENXIO;
+ goto out;
+ }
+
+ p = kzalloc(sizeof(struct ip_tunnel_prl_entry), GFP_KERNEL);
+ if (!p) {
+ err = -ENOBUFS;
+ goto out;
+ }
+
+ p->next = t->prl;
+ t->prl = p;
+update:
+ p->entry = *a;
+out:
+ write_unlock(&ipip6_lock);
+ return err;
+}
+
+static int
+ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a)
+{
+ struct ip_tunnel_prl_entry *x, **p;
+ int err = 0;
+
+ write_lock(&ipip6_lock);
+
+ if (a && a->addr != htonl(INADDR_ANY)) {
+ for (p = &t->prl; *p; p = &(*p)->next) {
+ if ((*p)->entry.addr == a->addr) {
+ x = *p;
+ *p = x->next;
+ kfree(x);
+ goto out;
+ }
+ }
+ err = -ENXIO;
+ } else {
+ while (t->prl) {
+ x = t->prl;
+ t->prl = t->prl->next;
+ kfree(x);
+ }
+ }
+out:
+ write_unlock(&ipip6_lock);
+ return 0;
+}
+
+/* copied directly from anycast.c */
+static int
+ipip6_onlink(struct in6_addr *addr, struct net_device *dev)
+{
+ struct inet6_dev *idev;
+ struct inet6_ifaddr *ifa;
+ int onlink;
+
+ onlink = 0;
+ rcu_read_lock();
+ idev = __in6_dev_get(dev);
+ if (idev) {
+ read_lock_bh(&idev->lock);
+ for (ifa=idev->addr_list; ifa; ifa=ifa->if_next) {
+ onlink = ipv6_prefix_equal(addr, &ifa->addr,
+ ifa->prefix_len);
+ if (onlink)
+ break;
+ }
+ read_unlock_bh(&idev->lock);
+ }
+ rcu_read_unlock();
+ return onlink;
+}
+
+static int
+isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
+{
+ struct ip_tunnel_prl_entry *p;
+ int ok = 1;
+
+ read_lock(&ipip6_lock);
+ p = __ipip6_tunnel_locate_prl(t, iph->saddr);
+ if (p) {
+ if (p->entry.flags & PRL_DEFAULT)
+ skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT;
+ else
+ skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT;
+ } else {
+ struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr;
+ if (ipv6_addr_is_isatap(addr6) &&
+ (addr6->s6_addr32[3] == iph->saddr) &&
+ ipip6_onlink(addr6, t->dev))
+ skb->ndisc_nodetype = NDISC_NODETYPE_HOST;
+ else
+ ok = 0;
+ }
+ read_unlock(&ipip6_lock);
+ return ok;
+}
+
static void ipip6_tunnel_uninit(struct net_device *dev)
{
if (dev == ipip6_fb_tunnel_dev) {
dev_put(dev);
} else {
ipip6_tunnel_unlink(netdev_priv(dev));
+ ipip6_tunnel_del_prl(netdev_priv(dev), 0);
dev_put(dev);
}
}
-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);
+ rt6i = rt6_lookup(&init_net, &iph6->saddr, NULL, NULL, 0);
if (rt6i && rt6i->rt6i_dev) {
skb2->dev = rt6i->rt6i_dev;
- rt6i = rt6_lookup(&iph6->daddr, &iph6->saddr, NULL, 0);
+ rt6i = rt6_lookup(&init_net, &iph6->daddr, &iph6->saddr, NULL, 0);
if (rt6i && rt6i->rt6i_dev && rt6i->rt6i_dev->type == ARPHRD_SIT) {
struct ip_tunnel *t = netdev_priv(rt6i->rt6i_dev);
}
}
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));
}
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_chksrc(skb, iph, tunnel)) {
+ 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;
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 */
+ unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
int mtu;
struct in6_addr *addr6;
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);
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)
{
int err = 0;
struct ip_tunnel_parm p;
+ struct ip_tunnel_prl prl;
struct ip_tunnel *t;
switch (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;
err = 0;
break;
+ case SIOCADDPRL:
+ case SIOCDELPRL:
+ case SIOCCHGPRL:
+ err = -EPERM;
+ if (!capable(CAP_NET_ADMIN))
+ goto done;
+ err = -EINVAL;
+ if (dev == ipip6_fb_tunnel_dev)
+ goto done;
+ err = -EFAULT;
+ if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl)))
+ goto done;
+ err = -ENOENT;
+ if (!(t = netdev_priv(dev)))
+ goto done;
+
+ if (cmd == SIOCDELPRL)
+ err = ipip6_tunnel_del_prl(t, &prl);
+ else
+ err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
+ netdev_state_change(dev);
+ break;
+
default:
err = -EINVAL;
}
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)
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();
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;
}
err2:
free_netdev(ipip6_fb_tunnel_dev);
err1:
- inet_del_protocol(&sit_protocol, IPPROTO_IPV6);
+ xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
goto out;
}