1 files changed, 212 insertions, 57 deletions

diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index dbd19a78ca73..2362a3397e91 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -77,8 +77,17 @@ struct sit_net {
 	struct net_device *fb_tunnel_dev;
 };
 
-static DEFINE_RWLOCK(ipip6_lock);
+/*
+ * Locking : hash tables are protected by RCU and a spinlock
+ */
+static DEFINE_SPINLOCK(ipip6_lock);
 
+#define for_each_ip_tunnel_rcu(start) \
+	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
+
+/*
+ * Must be invoked with rcu_read_lock
+ */
 static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
 		struct net_device *dev, __be32 remote, __be32 local)
 {
@@ -87,26 +96,26 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
 	struct ip_tunnel *t;
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
-	for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) {
+	for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) {
 		if (local == t->parms.iph.saddr &&
 		    remote == t->parms.iph.daddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	for (t = sitn->tunnels_r[h0]; t; t = t->next) {
+	for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) {
 		if (remote == t->parms.iph.daddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	for (t = sitn->tunnels_l[h1]; t; t = t->next) {
+	for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) {
 		if (local == t->parms.iph.saddr &&
 		    (!dev || !t->parms.link || dev->iflink == t->parms.link) &&
 		    (t->dev->flags & IFF_UP))
 			return t;
 	}
-	t = sitn->tunnels_wc[0];
+	t = rcu_dereference(sitn->tunnels_wc[0]);
 	if ((t != NULL) && (t->dev->flags & IFF_UP))
 		return t;
 	return NULL;
@@ -143,9 +152,9 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
 
 	for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) {
 		if (t == *tp) {
-			write_lock_bh(&ipip6_lock);
+			spin_lock_bh(&ipip6_lock);
 			*tp = t->next;
-			write_unlock_bh(&ipip6_lock);
+			spin_unlock_bh(&ipip6_lock);
 			break;
 		}
 	}
@@ -155,10 +164,27 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
 {
 	struct ip_tunnel **tp = ipip6_bucket(sitn, t);
 
+	spin_lock_bh(&ipip6_lock);
 	t->next = *tp;
-	write_lock_bh(&ipip6_lock);
-	*tp = t;
-	write_unlock_bh(&ipip6_lock);
+	rcu_assign_pointer(*tp, t);
+	spin_unlock_bh(&ipip6_lock);
+}
+
+static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
+{
+#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel *t = netdev_priv(dev);
+
+	if (t->dev == sitn->fb_tunnel_dev) {
+		ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
+		t->ip6rd.relay_prefix = 0;
+		t->ip6rd.prefixlen = 16;
+		t->ip6rd.relay_prefixlen = 0;
+	} else {
+		struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev);
+		memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd));
+	}
+#endif
 }
 
 static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
@@ -204,6 +230,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
 
 	nt->parms = *parms;
 	ipip6_tunnel_init(dev);
+	ipip6_tunnel_clone_6rd(dev, sitn);
 
 	if (parms->i_flags & SIT_ISATAP)
 		dev->priv_flags |= IFF_ISATAP;
@@ -222,15 +249,22 @@ failed:
 	return NULL;
 }
 
+static DEFINE_SPINLOCK(ipip6_prl_lock);
+
+#define for_each_prl_rcu(start)			\
+	for (prl = rcu_dereference(start);	\
+	     prl;				\
+	     prl = rcu_dereference(prl->next))
+
 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;
+	struct ip_tunnel_prl_entry *prl;
 
-	for (p = t->prl; p; p = p->next)
-		if (p->addr == addr)
+	for_each_prl_rcu(t->prl)
+		if (prl->addr == addr)
 			break;
-	return p;
+	return prl;
 
 }
 
@@ -255,7 +289,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 		kcalloc(cmax, sizeof(*kp), GFP_KERNEL) :
 		NULL;
 
-	read_lock(&ipip6_lock);
+	rcu_read_lock();
 
 	ca = t->prl_count < cmax ? t->prl_count : cmax;
 
@@ -273,7 +307,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 	}
 
 	c = 0;
-	for (prl = t->prl; prl; prl = prl->next) {
+	for_each_prl_rcu(t->prl) {
 		if (c >= cmax)
 			break;
 		if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr)
@@ -285,7 +319,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
 			break;
 	}
 out:
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 
 	len = sizeof(*kp) * c;
 	ret = 0;
@@ -306,12 +340,14 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
 	if (a->addr == htonl(INADDR_ANY))
 		return -EINVAL;
 
-	write_lock(&ipip6_lock);
+	spin_lock(&ipip6_prl_lock);
 
 	for (p = t->prl; p; p = p->next) {
 		if (p->addr == a->addr) {
-			if (chg)
-				goto update;
+			if (chg) {
+				p->flags = a->flags;
+				goto out;
+			}
 			err = -EEXIST;
 			goto out;
 		}
@@ -328,46 +364,63 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
 		goto out;
 	}
 
+	INIT_RCU_HEAD(&p->rcu_head);
 	p->next = t->prl;
-	t->prl = p;
-	t->prl_count++;
-update:
 	p->addr = a->addr;
 	p->flags = a->flags;
+	t->prl_count++;
+	rcu_assign_pointer(t->prl, p);
 out:
-	write_unlock(&ipip6_lock);
+	spin_unlock(&ipip6_prl_lock);
 	return err;
 }
 
+static void prl_entry_destroy_rcu(struct rcu_head *head)
+{
+	kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head));
+}
+
+static void prl_list_destroy_rcu(struct rcu_head *head)
+{
+	struct ip_tunnel_prl_entry *p, *n;
+
+	p = container_of(head, struct ip_tunnel_prl_entry, rcu_head);
+	do {
+		n = p->next;
+		kfree(p);
+		p = n;
+	} while (p);
+}
+
 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);
+	spin_lock(&ipip6_prl_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);
+				call_rcu(&x->rcu_head, prl_entry_destroy_rcu);
 				t->prl_count--;
 				goto out;
 			}
 		}
 		err = -ENXIO;
 	} else {
-		while (t->prl) {
+		if (t->prl) {
+			t->prl_count = 0;
 			x = t->prl;
-			t->prl = t->prl->next;
-			kfree(x);
-			t->prl_count--;
+			call_rcu(&x->rcu_head, prl_list_destroy_rcu);
+			t->prl = NULL;
 		}
 	}
 out:
-	write_unlock(&ipip6_lock);
+	spin_unlock(&ipip6_prl_lock);
 	return err;
 }
 
@@ -377,7 +430,7 @@ 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);
+	rcu_read_lock();
 	p = __ipip6_tunnel_locate_prl(t, iph->saddr);
 	if (p) {
 		if (p->flags & PRL_DEFAULT)
@@ -393,7 +446,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t)
 		else
 			ok = 0;
 	}
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 	return ok;
 }
 
@@ -403,9 +456,9 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
 	struct sit_net *sitn = net_generic(net, sit_net_id);
 
 	if (dev == sitn->fb_tunnel_dev) {
-		write_lock_bh(&ipip6_lock);
+		spin_lock_bh(&ipip6_lock);
 		sitn->tunnels_wc[0] = NULL;
-		write_unlock_bh(&ipip6_lock);
+		spin_unlock_bh(&ipip6_lock);
 		dev_put(dev);
 	} else {
 		ipip6_tunnel_unlink(sitn, netdev_priv(dev));
@@ -458,7 +511,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 
 	err = -ENOENT;
 
-	read_lock(&ipip6_lock);
+	rcu_read_lock();
 	t = ipip6_tunnel_lookup(dev_net(skb->dev),
 				skb->dev,
 				iph->daddr,
@@ -476,7 +529,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info)
 		t->err_count = 1;
 	t->err_time = jiffies;
 out:
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 	return err;
 }
 
@@ -496,7 +549,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 
 	iph = ip_hdr(skb);
 
-	read_lock(&ipip6_lock);
+	rcu_read_lock();
 	tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
 				     iph->saddr, iph->daddr);
 	if (tunnel != NULL) {
@@ -510,7 +563,7 @@ static int ipip6_rcv(struct sk_buff *skb)
 		if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
 		    !isatap_chksrc(skb, iph, tunnel)) {
 			tunnel->dev->stats.rx_errors++;
-			read_unlock(&ipip6_lock);
+			rcu_read_unlock();
 			kfree_skb(skb);
 			return 0;
 		}
@@ -521,28 +574,52 @@ static int ipip6_rcv(struct sk_buff *skb)
 		nf_reset(skb);
 		ipip6_ecn_decapsulate(iph, skb);
 		netif_rx(skb);
-		read_unlock(&ipip6_lock);
+		rcu_read_unlock();
 		return 0;
 	}
 
 	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-	read_unlock(&ipip6_lock);
+	rcu_read_unlock();
 out:
 	kfree_skb(skb);
 	return 0;
 }
 
-/* Returns the embedded IPv4 address if the IPv6 address
-   comes from 6to4 (RFC 3056) addr space */
-
-static inline __be32 try_6to4(struct in6_addr *v6dst)
+/*
+ * Returns the embedded IPv4 address if the IPv6 address
+ * comes from 6rd / 6to4 (RFC 3056) addr space.
+ */
+static inline
+__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel)
 {
 	__be32 dst = 0;
 
+#ifdef CONFIG_IPV6_SIT_6RD
+	if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
+			      tunnel->ip6rd.prefixlen)) {
+		unsigned pbw0, pbi0;
+		int pbi1;
+		u32 d;
+
+		pbw0 = tunnel->ip6rd.prefixlen >> 5;
+		pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
+
+		d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
+		    tunnel->ip6rd.relay_prefixlen;
+
+		pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
+		if (pbi1 > 0)
+			d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >>
+			     (32 - pbi1);
+
+		dst = tunnel->ip6rd.relay_prefix | htonl(d);
+	}
+#else
 	if (v6dst->s6_addr16[0] == htons(0x2002)) {
 		/* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
 		memcpy(&dst, &v6dst->s6_addr16[1], 4);
 	}
+#endif
 	return dst;
 }
 
@@ -555,7 +632,8 @@ static netdev_tx_t ipip6_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;
 	struct ipv6hdr *iph6 = ipv6_hdr(skb);
 	u8     tos = tunnel->parms.iph.tos;
@@ -595,7 +673,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 	}
 
 	if (!dst)
-		dst = try_6to4(&iph6->daddr);
+		dst = try_6rd(&iph6->daddr, tunnel);
 
 	if (!dst) {
 		struct neighbour *neigh = NULL;
@@ -688,7 +766,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		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);
 			return NETDEV_TX_OK;
 		}
@@ -785,9 +863,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 	struct ip_tunnel *t;
 	struct net *net = dev_net(dev);
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+#ifdef CONFIG_IPV6_SIT_6RD
+	struct ip_tunnel_6rd ip6rd;
+#endif
 
 	switch (cmd) {
 	case SIOCGETTUNNEL:
+#ifdef CONFIG_IPV6_SIT_6RD
+	case SIOCGET6RD:
+#endif
 		t = NULL;
 		if (dev == sitn->fb_tunnel_dev) {
 			if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
@@ -798,9 +882,25 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		}
 		if (t == NULL)
 			t = netdev_priv(dev);
-		memcpy(&p, &t->parms, sizeof(p));
-		if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
-			err = -EFAULT;
+
+		err = -EFAULT;
+		if (cmd == SIOCGETTUNNEL) {
+			memcpy(&p, &t->parms, sizeof(p));
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &p,
+					 sizeof(p)))
+				goto done;
+#ifdef CONFIG_IPV6_SIT_6RD
+		} else {
+			ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix);
+			ip6rd.relay_prefix = t->ip6rd.relay_prefix;
+			ip6rd.prefixlen = t->ip6rd.prefixlen;
+			ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
+			if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd,
+					 sizeof(ip6rd)))
+				goto done;
+#endif
+		}
+		err = 0;
 		break;
 
 	case SIOCADDTUNNEL:
@@ -921,6 +1021,54 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 		netdev_state_change(dev);
 		break;
 
+#ifdef CONFIG_IPV6_SIT_6RD
+	case SIOCADD6RD:
+	case SIOCCHG6RD:
+	case SIOCDEL6RD:
+		err = -EPERM;
+		if (!capable(CAP_NET_ADMIN))
+			goto done;
+
+		err = -EFAULT;
+		if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data,
+				   sizeof(ip6rd)))
+			goto done;
+
+		t = netdev_priv(dev);
+
+		if (cmd != SIOCDEL6RD) {
+			struct in6_addr prefix;
+			__be32 relay_prefix;
+
+			err = -EINVAL;
+			if (ip6rd.relay_prefixlen > 32 ||
+			    ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64)
+				goto done;
+
+			ipv6_addr_prefix(&prefix, &ip6rd.prefix,
+					 ip6rd.prefixlen);
+			if (!ipv6_addr_equal(&prefix, &ip6rd.prefix))
+				goto done;
+			if (ip6rd.relay_prefixlen)
+				relay_prefix = ip6rd.relay_prefix &
+					       htonl(0xffffffffUL <<
+						     (32 - ip6rd.relay_prefixlen));
+			else
+				relay_prefix = 0;
+			if (relay_prefix != ip6rd.relay_prefix)
+				goto done;
+
+			ipv6_addr_copy(&t->ip6rd.prefix, &prefix);
+			t->ip6rd.relay_prefix = relay_prefix;
+			t->ip6rd.prefixlen = ip6rd.prefixlen;
+			t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
+		} else
+			ipip6_tunnel_clone_6rd(dev, sitn);
+
+		err = 0;
+		break;
+#endif
+
 	default:
 		err = -EINVAL;
 	}
@@ -997,16 +1145,19 @@ static struct xfrm_tunnel sit_handler = {
 	.priority	=	1,
 };
 
-static void sit_destroy_tunnels(struct sit_net *sitn)
+static void sit_destroy_tunnels(struct sit_net *sitn, 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 = sitn->tunnels[prio][h]) != NULL)
-				unregister_netdevice(t->dev);
+			struct ip_tunnel *t = sitn->tunnels[prio][h];
+
+			while (t != NULL) {
+				unregister_netdevice_queue(t->dev, head);
+				t = t->next;
+			}
 		}
 	}
 }
@@ -1039,6 +1190,7 @@ static int sit_init_net(struct net *net)
 	dev_net_set(sitn->fb_tunnel_dev, net);
 
 	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
 
 	if ((err = register_netdev(sitn->fb_tunnel_dev)))
 		goto err_reg_dev;
@@ -1059,11 +1211,13 @@ err_alloc:
 static void sit_exit_net(struct net *net)
 {
 	struct sit_net *sitn;
+	LIST_HEAD(list);
 
 	sitn = net_generic(net, sit_net_id);
 	rtnl_lock();
-	sit_destroy_tunnels(sitn);
-	unregister_netdevice(sitn->fb_tunnel_dev);
+	sit_destroy_tunnels(sitn, &list);
+	unregister_netdevice_queue(sitn->fb_tunnel_dev, &list);
+	unregister_netdevice_many(&list);
 	rtnl_unlock();
 	kfree(sitn);
 }
@@ -1078,6 +1232,7 @@ static void __exit sit_cleanup(void)
 	xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
 
 	unregister_pernet_gen_device(sit_net_id, &sit_net_ops);
+	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 
 static int __init sit_init(void)