/*
* Linux NET3: IP/IP protocol decoder.
*
- * Version: $Id: ipip.c,v 1.50 2001/10/02 02:22:36 davem Exp $
- *
* Authors:
* Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95
*
Made the tunnels use dev->name not tunnel: when error reporting.
Added tx_dropped stat
- -Alan Cox (Alan.Cox@linux.org) 21 March 95
+ -Alan Cox (alan@lxorguk.ukuu.org.uk) 21 March 95
Reworked:
Changed to tunnel to destination gateway in addition to the
#define HASH_SIZE 16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
-static int ipip_net_id;
+static int ipip_net_id __read_mostly;
struct ipip_net {
struct ip_tunnel *tunnels_r_l[HASH_SIZE];
struct ip_tunnel *tunnels_r[HASH_SIZE];
struct net_device *fb_tunnel_dev;
};
-static int ipip_fb_tunnel_init(struct net_device *dev);
-static int ipip_tunnel_init(struct net_device *dev);
+static void ipip_fb_tunnel_init(struct net_device *dev);
+static void ipip_tunnel_init(struct net_device *dev);
static void ipip_tunnel_setup(struct net_device *dev);
-static DEFINE_RWLOCK(ipip_lock);
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipip_lock);
+
+#define for_each_ip_tunnel_rcu(start) \
+ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
static struct ip_tunnel * ipip_tunnel_lookup(struct net *net,
__be32 remote, __be32 local)
struct ip_tunnel *t;
struct ipip_net *ipn = net_generic(net, ipip_net_id);
- for (t = ipn->tunnels_r_l[h0^h1]; t; t = t->next) {
+ for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1])
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
- }
- for (t = ipn->tunnels_r[h0]; t; t = t->next) {
+
+ for_each_ip_tunnel_rcu(ipn->tunnels_r[h0])
if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP))
return t;
- }
- for (t = ipn->tunnels_l[h1]; t; t = t->next) {
+
+ for_each_ip_tunnel_rcu(ipn->tunnels_l[h1])
if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP))
return t;
- }
- if ((t = ipn->tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP))
+
+ t = rcu_dereference(ipn->tunnels_wc[0]);
+ if (t && (t->dev->flags&IFF_UP))
return t;
return NULL;
}
for (tp = ipip_bucket(ipn, t); *tp; tp = &(*tp)->next) {
if (t == *tp) {
- write_lock_bh(&ipip_lock);
+ spin_lock_bh(&ipip_lock);
*tp = t->next;
- write_unlock_bh(&ipip_lock);
+ spin_unlock_bh(&ipip_lock);
break;
}
}
{
struct ip_tunnel **tp = ipip_bucket(ipn, t);
+ spin_lock_bh(&ipip_lock);
t->next = *tp;
- write_lock_bh(&ipip_lock);
- *tp = t;
- write_unlock_bh(&ipip_lock);
+ rcu_assign_pointer(*tp, t);
+ spin_unlock_bh(&ipip_lock);
}
static struct ip_tunnel * ipip_tunnel_locate(struct net *net,
}
nt = netdev_priv(dev);
- dev->init = ipip_tunnel_init;
nt->parms = *parms;
+ ipip_tunnel_init(dev);
+
if (register_netdevice(dev) < 0)
goto failed_free;
struct ipip_net *ipn = net_generic(net, ipip_net_id);
if (dev == ipn->fb_tunnel_dev) {
- write_lock_bh(&ipip_lock);
+ spin_lock_bh(&ipip_lock);
ipn->tunnels_wc[0] = NULL;
- write_unlock_bh(&ipip_lock);
+ spin_unlock_bh(&ipip_lock);
} else
ipip_tunnel_unlink(ipn, netdev_priv(dev));
dev_put(dev);
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
*/
- struct iphdr *iph = (struct iphdr*)skb->data;
+ struct iphdr *iph = (struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
err = -ENOENT;
- read_lock(&ipip_lock);
+ rcu_read_lock();
t = ipip_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;
t->err_time = jiffies;
out:
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
return err;
}
struct ip_tunnel *tunnel;
const struct iphdr *iph = ip_hdr(skb);
- read_lock(&ipip_lock);
+ rcu_read_lock();
if ((tunnel = ipip_tunnel_lookup(dev_net(skb->dev),
iph->saddr, iph->daddr)) != NULL) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
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;
+ skb_dst_drop(skb);
nf_reset(skb);
ipip_ecn_decapsulate(iph, skb);
netif_rx(skb);
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
return 0;
}
- read_unlock(&ipip_lock);
+ rcu_read_unlock();
return -1;
}
* and that skb is filled properly by that function.
*/
-static int ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- struct net_device_stats *stats = &tunnel->dev->stats;
+ struct net_device_stats *stats = &dev->stats;
+ struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
struct iphdr *tiph = &tunnel->parms.iph;
u8 tos = tunnel->parms.iph.tos;
__be16 df = tiph->frag_off;
__be32 dst = tiph->daddr;
int mtu;
- if (tunnel->recursion++) {
- stats->collisions++;
- goto tx_error;
- }
-
if (skb->protocol != htons(ETH_P_IP))
goto tx_error;
if (!dst) {
/* NBMA tunnel */
- if ((rt = skb->rtable) == NULL) {
+ if ((rt = skb_rtable(skb)) == NULL) {
stats->tx_fifo_errors++;
goto tx_error;
}
goto tx_error;
}
- if (tiph->frag_off)
+ df |= old_iph->frag_off & htons(IP_DF);
+
+ if (df) {
mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
- else
- mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
- if (mtu < 68) {
- stats->collisions++;
- ip_rt_put(rt);
- goto tx_error;
- }
- if (skb->dst)
- skb->dst->ops->update_pmtu(skb->dst, mtu);
+ if (mtu < 68) {
+ stats->collisions++;
+ ip_rt_put(rt);
+ goto tx_error;
+ }
- df |= (old_iph->frag_off&htons(IP_DF));
+ if (skb_dst(skb))
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
- if ((old_iph->frag_off&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 ((old_iph->frag_off & 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) {
+ if (time_before(jiffies,
+ tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
- stats->tx_dropped++;
+ txq->tx_dropped++;
dev_kfree_skb(skb);
- tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
- dst_release(skb->dst);
- skb->dst = &rt->u.dst;
+ skb_dst_drop(skb);
+ skb_dst_set(skb, &rt->u.dst);
/*
* Push down and install the IPIP header.
nf_reset(skb);
IPTUNNEL_XMIT();
- tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
stats->tx_errors++;
dev_kfree_skb(skb);
- tunnel->recursion--;
- return 0;
+ return NETDEV_TX_OK;
}
static void ipip_tunnel_bind_dev(struct net_device *dev)
return 0;
}
+static const struct net_device_ops ipip_netdev_ops = {
+ .ndo_uninit = ipip_tunnel_uninit,
+ .ndo_start_xmit = ipip_tunnel_xmit,
+ .ndo_do_ioctl = ipip_tunnel_ioctl,
+ .ndo_change_mtu = ipip_tunnel_change_mtu,
+
+};
+
static void ipip_tunnel_setup(struct net_device *dev)
{
- dev->uninit = ipip_tunnel_uninit;
- dev->hard_start_xmit = ipip_tunnel_xmit;
- dev->do_ioctl = ipip_tunnel_ioctl;
- dev->change_mtu = ipip_tunnel_change_mtu;
+ dev->netdev_ops = &ipip_netdev_ops;
dev->destructor = free_netdev;
dev->type = ARPHRD_TUNNEL;
dev->iflink = 0;
dev->addr_len = 4;
dev->features |= NETIF_F_NETNS_LOCAL;
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
}
-static int ipip_tunnel_init(struct net_device *dev)
+static void ipip_tunnel_init(struct net_device *dev)
{
- struct ip_tunnel *tunnel;
-
- tunnel = netdev_priv(dev);
+ struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
ipip_tunnel_bind_dev(dev);
-
- return 0;
}
-static int ipip_fb_tunnel_init(struct net_device *dev)
+static void ipip_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
dev_hold(dev);
ipn->tunnels_wc[0] = tunnel;
- return 0;
}
static struct xfrm_tunnel ipip_handler = {
.priority = 1,
};
-static char banner[] __initdata =
+static const char banner[] __initconst =
KERN_INFO "IPv4 over IPv4 tunneling driver\n";
-static void ipip_destroy_tunnels(struct ipip_net *ipn)
+static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
{
int prio;
for (prio = 1; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
- while ((t = ipn->tunnels[prio][h]) != NULL)
- unregister_netdevice(t->dev);
+ struct ip_tunnel *t = ipn->tunnels[prio][h];
+
+ while (t != NULL) {
+ unregister_netdevice_queue(t->dev, head);
+ t = t->next;
+ }
}
}
}
static int ipip_init_net(struct net *net)
{
+ struct ipip_net *ipn = net_generic(net, ipip_net_id);
int err;
- struct ipip_net *ipn;
-
- err = -ENOMEM;
- ipn = kzalloc(sizeof(struct ipip_net), GFP_KERNEL);
- if (ipn == NULL)
- goto err_alloc;
-
- err = net_assign_generic(net, ipip_net_id, ipn);
- if (err < 0)
- goto err_assign;
ipn->tunnels[0] = ipn->tunnels_wc;
ipn->tunnels[1] = ipn->tunnels_l;
err = -ENOMEM;
goto err_alloc_dev;
}
-
- ipn->fb_tunnel_dev->init = ipip_fb_tunnel_init;
dev_net_set(ipn->fb_tunnel_dev, net);
+ ipip_fb_tunnel_init(ipn->fb_tunnel_dev);
+
if ((err = register_netdev(ipn->fb_tunnel_dev)))
goto err_reg_dev;
free_netdev(ipn->fb_tunnel_dev);
err_alloc_dev:
/* nothing */
-err_assign:
- kfree(ipn);
-err_alloc:
return err;
}
static void ipip_exit_net(struct net *net)
{
- struct ipip_net *ipn;
+ struct ipip_net *ipn = net_generic(net, ipip_net_id);
+ LIST_HEAD(list);
- ipn = net_generic(net, ipip_net_id);
rtnl_lock();
- ipip_destroy_tunnels(ipn);
- unregister_netdevice(ipn->fb_tunnel_dev);
+ ipip_destroy_tunnels(ipn, &list);
+ unregister_netdevice_queue(ipn->fb_tunnel_dev, &list);
+ unregister_netdevice_many(&list);
rtnl_unlock();
- kfree(ipn);
}
static struct pernet_operations ipip_net_ops = {
.init = ipip_init_net,
.exit = ipip_exit_net,
+ .id = &ipip_net_id,
+ .size = sizeof(struct ipip_net),
};
static int __init ipip_init(void)
return -EAGAIN;
}
- err = register_pernet_gen_device(&ipip_net_id, &ipip_net_ops);
+ err = register_pernet_device(&ipip_net_ops);
if (err)
xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET))
printk(KERN_INFO "ipip close: can't deregister tunnel\n");
- unregister_pernet_gen_device(ipip_net_id, &ipip_net_ops);
+ unregister_pernet_device(&ipip_net_ops);
}
module_init(ipip_init);