* 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 $
- *
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 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 <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
/*
This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c
#define HASH_SIZE 16
#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 void ipip6_fb_tunnel_init(struct net_device *dev);
+static void ipip6_tunnel_init(struct net_device *dev);
static void ipip6_tunnel_setup(struct net_device *dev);
-static struct net_device *ipip6_fb_tunnel_dev;
+static int sit_net_id;
+struct sit_net {
+ struct ip_tunnel *tunnels_r_l[HASH_SIZE];
+ struct ip_tunnel *tunnels_r[HASH_SIZE];
+ struct ip_tunnel *tunnels_l[HASH_SIZE];
+ struct ip_tunnel *tunnels_wc[1];
+ struct ip_tunnel **tunnels[4];
-static struct ip_tunnel *tunnels_r_l[HASH_SIZE];
-static struct ip_tunnel *tunnels_r[HASH_SIZE];
-static struct ip_tunnel *tunnels_l[HASH_SIZE];
-static struct ip_tunnel *tunnels_wc[1];
-static struct ip_tunnel **tunnels[4] = { tunnels_wc, tunnels_l, tunnels_r, tunnels_r_l };
+ struct net_device *fb_tunnel_dev;
+};
static DEFINE_RWLOCK(ipip6_lock);
-static struct ip_tunnel * ipip6_tunnel_lookup(__be32 remote, __be32 local)
+static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
+ __be32 remote, __be32 local)
{
unsigned h0 = HASH(remote);
unsigned h1 = HASH(local);
struct ip_tunnel *t;
+ struct sit_net *sitn = net_generic(net, sit_net_id);
- for (t = tunnels_r_l[h0^h1]; t; t = t->next) {
+ for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
}
- for (t = tunnels_r[h0]; t; t = t->next) {
+ for (t = sitn->tunnels_r[h0]; t; t = t->next) {
if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
}
- for (t = tunnels_l[h1]; t; t = t->next) {
+ for (t = sitn->tunnels_l[h1]; t; t = t->next) {
if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
return t;
}
- if ((t = tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP))
+ if ((t = sitn->tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP))
return t;
return NULL;
}
-static struct ip_tunnel ** ipip6_bucket(struct ip_tunnel *t)
+static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn,
+ 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;
prio |= 1;
h ^= HASH(local);
}
- return &tunnels[prio][h];
+ return &sitn->tunnels[prio][h];
}
-static void ipip6_tunnel_unlink(struct ip_tunnel *t)
+static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn,
+ struct ip_tunnel *t)
+{
+ return __ipip6_bucket(sitn, &t->parms);
+}
+
+static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
{
struct ip_tunnel **tp;
- for (tp = ipip6_bucket(t); *tp; tp = &(*tp)->next) {
+ for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) {
if (t == *tp) {
write_lock_bh(&ipip6_lock);
*tp = t->next;
}
}
-static void ipip6_tunnel_link(struct ip_tunnel *t)
+static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
{
- struct ip_tunnel **tp = ipip6_bucket(t);
+ struct ip_tunnel **tp = ipip6_bucket(sitn, t);
t->next = *tp;
write_lock_bh(&ipip6_lock);
write_unlock_bh(&ipip6_lock);
}
-static struct ip_tunnel * ipip6_tunnel_locate(struct ip_tunnel_parm *parms, int create)
+static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
+ struct ip_tunnel_parm *parms, int create)
{
__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];
+ struct sit_net *sitn = net_generic(net, sit_net_id);
- 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(sitn, 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;
+ dev_net_set(dev, net);
+
+ 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;
+ ipip6_tunnel_init(dev);
- 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);
+ ipip6_tunnel_link(sitn, 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->addr == addr)
+ break;
+ return p;
+
+}
+
+static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
+ struct ip_tunnel_prl __user *a)
+{
+ struct ip_tunnel_prl kprl, *kp;
+ struct ip_tunnel_prl_entry *prl;
+ unsigned int cmax, c = 0, ca, len;
+ int ret = 0;
+
+ if (copy_from_user(&kprl, a, sizeof(kprl)))
+ return -EFAULT;
+ cmax = kprl.datalen / sizeof(kprl);
+ if (cmax > 1 && kprl.addr != htonl(INADDR_ANY))
+ cmax = 1;
+
+ /* For simple GET or for root users,
+ * we try harder to allocate.
+ */
+ kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ?
+ kcalloc(cmax, sizeof(*kp), GFP_KERNEL) :
+ NULL;
+
+ read_lock(&ipip6_lock);
+
+ ca = t->prl_count < cmax ? t->prl_count : cmax;
+
+ if (!kp) {
+ /* We don't try hard to allocate much memory for
+ * non-root users.
+ * For root users, retry allocating enough memory for
+ * the answer.
+ */
+ kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC);
+ if (!kp) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ }
+
+ c = 0;
+ for (prl = t->prl; prl; prl = prl->next) {
+ if (c > cmax)
+ break;
+ if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr)
+ continue;
+ kp[c].addr = prl->addr;
+ kp[c].flags = prl->flags;
+ c++;
+ if (kprl.addr != htonl(INADDR_ANY))
+ break;
+ }
+out:
+ read_unlock(&ipip6_lock);
+
+ len = sizeof(*kp) * c;
+ ret = 0;
+ if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen))
+ ret = -EFAULT;
+
+ kfree(kp);
+
+ return ret;
+}
+
+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->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;
+ t->prl_count++;
+update:
+ p->addr = a->addr;
+ p->flags = a->flags;
+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)->addr == a->addr) {
+ x = *p;
+ *p = x->next;
+ kfree(x);
+ t->prl_count--;
+ goto out;
+ }
+ }
+ err = -ENXIO;
+ } else {
+ while (t->prl) {
+ x = t->prl;
+ t->prl = t->prl->next;
+ kfree(x);
+ t->prl_count--;
+ }
+ }
+out:
+ write_unlock(&ipip6_lock);
+ return 0;
+}
+
+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->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) &&
+ ipv6_chk_prefix(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) {
+ struct net *net = dev_net(dev);
+ struct sit_net *sitn = net_generic(net, sit_net_id);
+
+ if (dev == sitn->fb_tunnel_dev) {
write_lock_bh(&ipip6_lock);
- tunnels_wc[0] = NULL;
+ sitn->tunnels_wc[0] = NULL;
write_unlock_bh(&ipip6_lock);
dev_put(dev);
} else {
- ipip6_tunnel_unlink(netdev_priv(dev));
+ ipip6_tunnel_unlink(sitn, netdev_priv(dev));
+ ipip6_tunnel_del_prl(netdev_priv(dev), NULL);
dev_put(dev);
}
}
static int ipip6_err(struct sk_buff *skb, u32 info)
{
-#ifndef I_WISH_WORLD_WERE_PERFECT
-/* It is not :-( All the routers (except for Linux) return only
+/* 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.
*/
err = -ENOENT;
read_lock(&ipip6_lock);
- t = ipip6_tunnel_lookup(iph->daddr, iph->saddr);
+ t = ipip6_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr);
if (t == NULL || t->parms.iph.daddr == 0)
goto out;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
- if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+ if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
out:
read_unlock(&ipip6_lock);
return err;
-#else
- struct iphdr *iph = (struct iphdr*)dp;
- int hlen = iph->ihl<<2;
- struct ipv6hdr *iph6;
- 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;
- struct sk_buff *skb2;
- struct rt6_info *rt6i;
-
- if (len < hlen + sizeof(struct ipv6hdr))
- return;
- iph6 = (struct ipv6hdr*)(dp + hlen);
-
- switch (type) {
- default:
- return;
- case ICMP_PARAMETERPROB:
- 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 = icmp_hdr(skb)->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:
- /* Too complicated case ... */
- return;
- 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 = ICMPV6_DEST_UNREACH;
- rel_code = ICMPV6_ADDR_UNREACH;
- break;
- }
- break;
- case ICMP_TIME_EXCEEDED:
- if (code != ICMP_EXC_TTL)
- return;
- rel_type = ICMPV6_TIME_EXCEED;
- rel_code = ICMPV6_EXC_HOPLIMIT;
- break;
- }
-
- /* Prepare fake skb to feed it to icmpv6_send */
- skb2 = skb_clone(skb, GFP_ATOMIC);
- if (skb2 == NULL)
- return 0;
- dst_release(skb2->dst);
- skb2->dst = NULL;
- skb_pull(skb2, skb->data - (u8*)iph6);
- skb_reset_network_header(skb2);
-
- /* Try to guess incoming interface */
- rt6i = rt6_lookup(&iph6->saddr, NULL, NULL, 0);
- if (rt6i && rt6i->rt6i_dev) {
- skb2->dev = rt6i->rt6i_dev;
-
- rt6i = rt6_lookup(&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);
- if (rel_type == ICMPV6_TIME_EXCEED && t->parms.iph.ttl) {
- rel_type = ICMPV6_DEST_UNREACH;
- rel_code = ICMPV6_ADDR_UNREACH;
- }
- icmpv6_send(skb2, rel_type, rel_code, rel_info, skb2->dev);
- }
- }
- kfree_skb(skb2);
- return 0;
-#endif
}
static inline void ipip6_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
iph = ip_hdr(skb);
read_lock(&ipip6_lock);
- if ((tunnel = ipip6_tunnel_lookup(iph->saddr, iph->daddr)) != NULL) {
+ if ((tunnel = ipip6_tunnel_lookup(dev_net(skb->dev),
+ iph->saddr, iph->daddr)) != NULL) {
secpath_reset(skb);
- skb->mac.raw = skb->nh.raw;
+ 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;
- tunnel->stat.rx_packets++;
- tunnel->stat.rx_bytes += skb->len;
+
+ if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
+ !isatap_chksrc(skb, iph, tunnel)) {
+ tunnel->dev->stats.rx_errors++;
+ read_unlock(&ipip6_lock);
+ kfree_skb(skb);
+ return 0;
+ }
+ tunnel->dev->stats.rx_packets++;
+ tunnel->dev->stats.rx_bytes += skb->len;
skb->dev = tunnel->dev;
dst_release(skb->dst);
skb->dst = NULL;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
- kfree_skb(skb);
read_unlock(&ipip6_lock);
out:
+ kfree_skb(skb);
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 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 */
- 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;
int addr_type;
if (tunnel->recursion++) {
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
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);
.tos = RT_TOS(tos) } },
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6 };
- if (ip_route_output_key(&rt, &fl)) {
- tunnel->stat.tx_carrier_errors++;
+ 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);
- tunnel->stat.tx_carrier_errors++;
+ stats->tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->u.dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
if (mtu < 68) {
- tunnel->stat.collisions++;
+ stats->collisions++;
ip_rt_put(rt);
goto tx_error;
}
}
if (tunnel->err_count > 0) {
- if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
+ if (time_before(jiffies,
+ tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
*/
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);
iph6 = ipv6_hdr(skb);
}
- skb->h.raw = skb->nh.raw;
+ 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));
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(dev_net(dev), &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(dev_net(dev), 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;
+ struct net *net = dev_net(dev);
+ struct sit_net *sitn = net_generic(net, sit_net_id);
switch (cmd) {
case SIOCGETTUNNEL:
t = NULL;
- if (dev == ipip6_fb_tunnel_dev) {
+ if (dev == sitn->fb_tunnel_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
err = -EFAULT;
break;
}
- t = ipip6_tunnel_locate(&p, 0);
+ t = ipip6_tunnel_locate(net, &p, 0);
}
if (t == NULL)
t = netdev_priv(dev);
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
- t = ipip6_tunnel_locate(&p, cmd == SIOCADDTUNNEL);
+ t = ipip6_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
- if (dev != ipip6_fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
+ if (dev != sitn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
t = netdev_priv(dev);
- ipip6_tunnel_unlink(t);
+ ipip6_tunnel_unlink(sitn, t);
t->parms.iph.saddr = p.iph.saddr;
t->parms.iph.daddr = p.iph.daddr;
memcpy(dev->dev_addr, &p.iph.saddr, 4);
memcpy(dev->broadcast, &p.iph.daddr, 4);
- ipip6_tunnel_link(t);
+ ipip6_tunnel_link(sitn, t);
netdev_state_change(dev);
}
}
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;
if (!capable(CAP_NET_ADMIN))
goto done;
- if (dev == ipip6_fb_tunnel_dev) {
+ if (dev == sitn->fb_tunnel_dev) {
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
goto done;
err = -ENOENT;
- if ((t = ipip6_tunnel_locate(&p, 0)) == NULL)
+ if ((t = ipip6_tunnel_locate(net, &p, 0)) == NULL)
goto done;
err = -EPERM;
- if (t == netdev_priv(ipip6_fb_tunnel_dev))
+ if (t == netdev_priv(sitn->fb_tunnel_dev))
goto done;
dev = t->dev;
}
err = 0;
break;
+ case SIOCGETPRL:
+ err = -EINVAL;
+ if (dev == sitn->fb_tunnel_dev)
+ goto done;
+ err = -ENOENT;
+ if (!(t = netdev_priv(dev)))
+ goto done;
+ err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data);
+ break;
+
+ case SIOCADDPRL:
+ case SIOCDELPRL:
+ case SIOCCHGPRL:
+ err = -EPERM;
+ if (!capable(CAP_NET_ADMIN))
+ goto done;
+ err = -EINVAL;
+ if (dev == sitn->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;
+
+ switch (cmd) {
+ case SIOCDELPRL:
+ err = ipip6_tunnel_del_prl(t, &prl);
+ break;
+ case SIOCADDPRL:
+ case SIOCCHGPRL:
+ err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
+ break;
+ }
+ netdev_state_change(dev);
+ break;
+
default:
err = -EINVAL;
}
return err;
}
-static struct net_device_stats *ipip6_tunnel_get_stats(struct net_device *dev)
-{
- return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
-}
-
static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr))
return 0;
}
+static const struct net_device_ops ipip6_netdev_ops = {
+ .ndo_uninit = ipip6_tunnel_uninit,
+ .ndo_start_xmit = ipip6_tunnel_xmit,
+ .ndo_do_ioctl = ipip6_tunnel_ioctl,
+ .ndo_change_mtu = ipip6_tunnel_change_mtu,
+};
+
static void ipip6_tunnel_setup(struct net_device *dev)
{
- SET_MODULE_OWNER(dev);
- dev->uninit = ipip6_tunnel_uninit;
+ dev->netdev_ops = &ipip6_netdev_ops;
dev->destructor = free_netdev;
- dev->hard_start_xmit = ipip6_tunnel_xmit;
- dev->get_stats = ipip6_tunnel_get_stats;
- dev->do_ioctl = ipip6_tunnel_ioctl;
- dev->change_mtu = ipip6_tunnel_change_mtu;
dev->type = ARPHRD_SIT;
dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
+ dev->features |= NETIF_F_NETNS_LOCAL;
}
-static int ipip6_tunnel_init(struct net_device *dev)
+static void 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;
+ struct ip_tunnel *tunnel = netdev_priv(dev);
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;
+ ipip6_tunnel_bind_dev(dev);
}
-static int __init ipip6_fb_tunnel_init(struct net_device *dev)
+static void ipip6_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
+ struct net *net = dev_net(dev);
+ struct sit_net *sitn = net_generic(net, sit_net_id);
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
iph->ttl = 64;
dev_hold(dev);
- tunnels_wc[0] = tunnel;
- return 0;
+ sitn->tunnels_wc[0] = tunnel;
}
static struct xfrm_tunnel sit_handler = {
.priority = 1,
};
-static void __exit sit_destroy_tunnels(void)
+static void sit_destroy_tunnels(struct sit_net *sitn)
{
int prio;
int h;
for (h = 0; h < HASH_SIZE; h++) {
struct ip_tunnel *t;
- while ((t = tunnels[prio][h]) != NULL)
+ while ((t = sitn->tunnels[prio][h]) != NULL)
unregister_netdevice(t->dev);
}
}
}
-static void __exit sit_cleanup(void)
+static int sit_init_net(struct net *net)
{
- xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
+ int err;
+ struct sit_net *sitn;
+
+ err = -ENOMEM;
+ sitn = kzalloc(sizeof(struct sit_net), GFP_KERNEL);
+ if (sitn == NULL)
+ goto err_alloc;
+
+ err = net_assign_generic(net, sit_net_id, sitn);
+ if (err < 0)
+ goto err_assign;
+
+ sitn->tunnels[0] = sitn->tunnels_wc;
+ sitn->tunnels[1] = sitn->tunnels_l;
+ sitn->tunnels[2] = sitn->tunnels_r;
+ sitn->tunnels[3] = sitn->tunnels_r_l;
+
+ sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
+ ipip6_tunnel_setup);
+ if (!sitn->fb_tunnel_dev) {
+ err = -ENOMEM;
+ goto err_alloc_dev;
+ }
+ dev_net_set(sitn->fb_tunnel_dev, net);
+
+ ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+
+ if ((err = register_netdev(sitn->fb_tunnel_dev)))
+ goto err_reg_dev;
+
+ return 0;
+
+err_reg_dev:
+ dev_put(sitn->fb_tunnel_dev);
+ free_netdev(sitn->fb_tunnel_dev);
+err_alloc_dev:
+ /* nothing */
+err_assign:
+ kfree(sitn);
+err_alloc:
+ return err;
+}
+
+static void sit_exit_net(struct net *net)
+{
+ struct sit_net *sitn;
+ sitn = net_generic(net, sit_net_id);
rtnl_lock();
- sit_destroy_tunnels();
- unregister_netdevice(ipip6_fb_tunnel_dev);
+ sit_destroy_tunnels(sitn);
+ unregister_netdevice(sitn->fb_tunnel_dev);
rtnl_unlock();
+ kfree(sitn);
+}
+
+static struct pernet_operations sit_net_ops = {
+ .init = sit_init_net,
+ .exit = sit_exit_net,
+};
+
+static void __exit sit_cleanup(void)
+{
+ xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
+
+ unregister_pernet_gen_device(sit_net_id, &sit_net_ops);
}
static int __init sit_init(void)
return -EAGAIN;
}
- ipip6_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
- ipip6_tunnel_setup);
- if (!ipip6_fb_tunnel_dev) {
- err = -ENOMEM;
- goto err1;
- }
-
- ipip6_fb_tunnel_dev->init = ipip6_fb_tunnel_init;
+ err = register_pernet_gen_device(&sit_net_id, &sit_net_ops);
+ if (err < 0)
+ xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
- if ((err = register_netdev(ipip6_fb_tunnel_dev)))
- goto err2;
-
- out:
return err;
- err2:
- free_netdev(ipip6_fb_tunnel_dev);
- err1:
- xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
- goto out;
}
module_init(sit_init);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff