Merge branch 'net-next-2.6-v6ready-20080703' of git://git.linux-ipv6.org/gitroot/yoshfuji/linux-2.6-next

13 files changed, 223 insertions, 26 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 71c7bea9716..72f6d52e52e 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1025,6 +1025,17 @@ max_addresses - INTEGER
 	autoconfigured addresses.
 	Default: 16
 
+disable_ipv6 - BOOLEAN
+	Disable IPv6 operation.
+	Default: FALSE (enable IPv6 operation)
+
+accept_dad - INTEGER
+	Whether to accept DAD (Duplicate Address Detection).
+	0: Disable DAD
+	1: Enable DAD (default)
+	2: Enable DAD, and disable IPv6 operation if MAC-based duplicate
+	   link-local address has been found.
+
 icmp/*:
 ratelimit - INTEGER
 	Limit the maximal rates for sending ICMPv6 packets.
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index f5a1a0db2e8..7bb3c095c15 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -228,7 +228,6 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf,
 extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf,
 		struct group_filter __user *optval, int __user *optlen);
 extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif);
-extern void ip_mr_init(void);
 extern void ip_mc_init_dev(struct in_device *);
 extern void ip_mc_destroy_dev(struct in_device *);
 extern void ip_mc_up(struct in_device *);
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index cde056e0818..391ad0843a4 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -163,6 +163,8 @@ struct ipv6_devconf {
 #ifdef CONFIG_IPV6_MROUTE
 	__s32		mc_forwarding;
 #endif
+	__s32		disable_ipv6;
+	__s32		accept_dad;
 	void		*sysctl;
 };
 
@@ -194,6 +196,8 @@ enum {
 	DEVCONF_OPTIMISTIC_DAD,
 	DEVCONF_ACCEPT_SOURCE_ROUTE,
 	DEVCONF_MC_FORWARDING,
+	DEVCONF_DISABLE_IPV6,
+	DEVCONF_ACCEPT_DAD,
 	DEVCONF_MAX
 };
 
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index de4decfa1bf..07112ee9293 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -144,11 +144,37 @@ static inline int ip_mroute_opt(int opt)
 }
 #endif
 
+#ifdef CONFIG_IP_MROUTE
 extern int ip_mroute_setsockopt(struct sock *, int, char __user *, int);
 extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
 extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
-extern void ip_mr_init(void);
+extern int ip_mr_init(void);
+#else
+static inline
+int ip_mroute_setsockopt(struct sock *sock,
+			 int optname, char __user *optval, int optlen)
+{
+	return -ENOPROTOOPT;
+}
+
+static inline
+int ip_mroute_getsockopt(struct sock *sock,
+			 int optname, char __user *optval, int __user *optlen)
+{
+	return -ENOPROTOOPT;
+}
 
+static inline
+int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
+{
+	return -ENOIOCTLCMD;
+}
+
+static inline int ip_mr_init(void)
+{
+	return 0;
+}
+#endif
 
 struct vif_device
 {
diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index e7989593142..5cf50473a10 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -131,11 +131,44 @@ static inline int ip6_mroute_opt(int opt)
 
 struct sock;
 
+#ifdef CONFIG_IPV6_MROUTE
 extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, int);
 extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *);
 extern int ip6_mr_input(struct sk_buff *skb);
 extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg);
-extern void ip6_mr_init(void);
+extern int ip6_mr_init(void);
+extern void ip6_mr_cleanup(void);
+#else
+static inline
+int ip6_mroute_setsockopt(struct sock *sock,
+			  int optname, char __user *optval, int optlen)
+{
+	return -ENOPROTOOPT;
+}
+
+static inline
+int ip6_mroute_getsockopt(struct sock *sock,
+			  int optname, char __user *optval, int __user *optlen)
+{
+	return -ENOPROTOOPT;
+}
+
+static inline
+int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
+{
+	return -ENOIOCTLCMD;
+}
+
+static inline int ip6_mr_init(void)
+{
+	return 0;
+}
+
+static inline void ip6_mr_cleanup(void)
+{
+	return;
+}
+#endif
 
 struct mif_device
 {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 42bd24b64b5..dc411335c14 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1479,14 +1479,15 @@ static int __init inet_init(void)
 	 *	Initialise the multicast router
 	 */
 #if defined(CONFIG_IP_MROUTE)
-	ip_mr_init();
+	if (ip_mr_init())
+		printk(KERN_CRIT "inet_init: Cannot init ipv4 mroute\n");
 #endif
 	/*
 	 *	Initialise per-cpu ipv4 mibs
 	 */
 
 	if (init_ipv4_mibs())
-		printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ;
+		printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n");
 
 	ipv4_proc_init();
 
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 300ab0c2919..438fab9c62a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1878,16 +1878,36 @@ static struct net_protocol pim_protocol = {
  *	Setup for IP multicast routing
  */
 
-void __init ip_mr_init(void)
+int __init ip_mr_init(void)
 {
+	int err;
+
 	mrt_cachep = kmem_cache_create("ip_mrt_cache",
 				       sizeof(struct mfc_cache),
 				       0, SLAB_HWCACHE_ALIGN|SLAB_PANIC,
 				       NULL);
+	if (!mrt_cachep)
+		return -ENOMEM;
+
 	setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
-	register_netdevice_notifier(&ip_mr_notifier);
+	err = register_netdevice_notifier(&ip_mr_notifier);
+	if (err)
+		goto reg_notif_fail;
 #ifdef CONFIG_PROC_FS
-	proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops);
-	proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops);
+	err = -ENOMEM;
+	if (!proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops))
+		goto proc_vif_fail;
+	if (!proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops))
+		goto proc_cache_fail;
 #endif
+	return 0;
+reg_notif_fail:
+	kmem_cache_destroy(mrt_cachep);
+#ifdef CONFIG_PROC_FS
+proc_vif_fail:
+	unregister_netdevice_notifier(&ip_mr_notifier);
+proc_cache_fail:
+	proc_net_remove(&init_net, "ip_mr_vif");
+#endif
+	return err;
 }
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 84127d854cf..2ec73e62202 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -119,6 +119,7 @@ static void ipv6_regen_rndid(unsigned long data);
 static int desync_factor = MAX_DESYNC_FACTOR * HZ;
 #endif
 
+static int ipv6_generate_eui64(u8 *eui, struct net_device *dev);
 static int ipv6_count_addresses(struct inet6_dev *idev);
 
 /*
@@ -183,6 +184,8 @@ struct ipv6_devconf ipv6_devconf __read_mostly = {
 #endif
 	.proxy_ndp		= 0,
 	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
+	.disable_ipv6		= 0,
+	.accept_dad		= 1,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -215,6 +218,8 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 #endif
 	.proxy_ndp		= 0,
 	.accept_source_route	= 0,	/* we do not accept RH0 by default. */
+	.disable_ipv6		= 0,
+	.accept_dad		= 1,
 };
 
 /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
@@ -378,6 +383,9 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev)
 	 */
 	in6_dev_hold(ndev);
 
+	if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
+		ndev->cnf.accept_dad = -1;
+
 #if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
 	if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) {
 		printk(KERN_INFO
@@ -578,6 +586,13 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
 	struct rt6_info *rt;
 	int hash;
 	int err = 0;
+	int addr_type = ipv6_addr_type(addr);
+
+	if (addr_type == IPV6_ADDR_ANY ||
+	    addr_type & IPV6_ADDR_MULTICAST ||
+	    (!(idev->dev->flags & IFF_LOOPBACK) &&
+	     addr_type & IPV6_ADDR_LOOPBACK))
+		return ERR_PTR(-EADDRNOTAVAIL);
 
 	rcu_read_lock_bh();
 	if (idev->dead) {
@@ -1412,6 +1427,20 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp)
 
 void addrconf_dad_failure(struct inet6_ifaddr *ifp)
 {
+	struct inet6_dev *idev = ifp->idev;
+	if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) {
+		struct in6_addr addr;
+
+		addr.s6_addr32[0] = htonl(0xfe800000);
+		addr.s6_addr32[1] = 0;
+
+		if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) &&
+		    ipv6_addr_equal(&ifp->addr, &addr)) {
+			/* DAD failed for link-local based on MAC address */
+			idev->cnf.disable_ipv6 = 1;
+		}
+	}
+
 	if (net_ratelimit())
 		printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name);
 	addrconf_dad_stop(ifp);
@@ -2744,6 +2773,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags)
 	spin_lock_bh(&ifp->lock);
 
 	if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
+	    idev->cnf.accept_dad < 1 ||
 	    !(ifp->flags&IFA_F_TENTATIVE) ||
 	    ifp->flags & IFA_F_NODAD) {
 		ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC);
@@ -2791,6 +2821,11 @@ static void addrconf_dad_timer(unsigned long data)
 		read_unlock_bh(&idev->lock);
 		goto out;
 	}
+	if (idev->cnf.accept_dad > 1 && idev->cnf.disable_ipv6) {
+		read_unlock_bh(&idev->lock);
+		addrconf_dad_failure(ifp);
+		return;
+	}
 	spin_lock_bh(&ifp->lock);
 	if (ifp->probes == 0) {
 		/*
@@ -3650,6 +3685,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf,
 #ifdef CONFIG_IPV6_MROUTE
 	array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding;
 #endif
+	array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6;
+	array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad;
 }
 
 static inline size_t inet6_if_nlmsg_size(void)
@@ -4209,6 +4246,22 @@ static struct addrconf_sysctl_table
 		},
 #endif
 		{
+			.ctl_name	=	CTL_UNNUMBERED,
+			.procname	=	"disable_ipv6",
+			.data		=	&ipv6_devconf.disable_ipv6,
+			.maxlen		=	sizeof(int),
+			.mode		=	0644,
+			.proc_handler	=	&proc_dointvec,
+		},
+		{
+			.ctl_name	=	CTL_UNNUMBERED,
+			.procname	=	"accept_dad",
+			.data		=	&ipv6_devconf.accept_dad,
+			.maxlen		=	sizeof(int),
+			.mode		=	0644,
+			.proc_handler	=	&proc_dointvec,
+		},
+		{
 			.ctl_name	=	0,	/* sentinel */
 		}
 	},
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3ce8d2f318c..3d828bc4b1c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -59,9 +59,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
-#ifdef CONFIG_IPV6_MROUTE
 #include <linux/mroute6.h>
-#endif
 
 MODULE_AUTHOR("Cast of dozens");
 MODULE_DESCRIPTION("IPv6 protocol stack for Linux");
@@ -952,9 +950,9 @@ static int __init inet6_init(void)
 	err = icmpv6_init();
 	if (err)
 		goto icmp_fail;
-#ifdef CONFIG_IPV6_MROUTE
-	ip6_mr_init();
-#endif
+	err = ip6_mr_init();
+	if (err)
+		goto ipmr_fail;
 	err = ndisc_init();
 	if (err)
 		goto ndisc_fail;
@@ -1057,6 +1055,8 @@ netfilter_fail:
 igmp_fail:
 	ndisc_cleanup();
 ndisc_fail:
+	ip6_mr_cleanup();
+ipmr_fail:
 	icmpv6_cleanup();
 icmp_fail:
 	unregister_pernet_subsys(&inet6_net_ops);
@@ -1111,6 +1111,7 @@ static void __exit inet6_exit(void)
 	ipv6_netfilter_fini();
 	igmp6_cleanup();
 	ndisc_cleanup();
+	ip6_mr_cleanup();
 	icmpv6_cleanup();
 	rawv6_exit();
 
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 34e5a96623a..ea81c614dde 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -71,7 +71,8 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 
 	IP6_INC_STATS_BH(idev, IPSTATS_MIB_INRECEIVES);
 
-	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
+	if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL ||
+	    !idev || unlikely(idev->cnf.disable_ipv6)) {
 		IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS);
 		rcu_read_unlock();
 		goto out;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index fd7cd1bfe15..0981c1ef305 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -173,6 +173,13 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
 
 int ip6_output(struct sk_buff *skb)
 {
+	struct inet6_dev *idev = ip6_dst_idev(skb->dst);
+	if (unlikely(idev->cnf.disable_ipv6)) {
+		IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS);
+		kfree_skb(skb);
+		return 0;
+	}
+
 	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
 				dst_allfrag(skb->dst))
 		return ip6_fragment(skb, ip6_output2);
@@ -498,7 +505,8 @@ int ip6_forward(struct sk_buff *skb)
 		int addrtype = ipv6_addr_type(&hdr->saddr);
 
 		/* This check is security critical. */
-		if (addrtype & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK))
+		if (addrtype == IPV6_ADDR_ANY ||
+		    addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK))
 			goto error;
 		if (addrtype & IPV6_ADDR_LINKLOCAL) {
 			icmpv6_send(skb, ICMPV6_DEST_UNREACH,
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 90e763073dc..cfac26d674e 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -948,23 +948,51 @@ static struct notifier_block ip6_mr_notifier = {
  *	Setup for IP multicast routing
  */
 
-void __init ip6_mr_init(void)
+int __init ip6_mr_init(void)
 {
+	int err;
+
 	mrt_cachep = kmem_cache_create("ip6_mrt_cache",
 				       sizeof(struct mfc6_cache),
 				       0, SLAB_HWCACHE_ALIGN,
 				       NULL);
 	if (!mrt_cachep)
-		panic("cannot allocate ip6_mrt_cache");
+		return -ENOMEM;
 
 	setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0);
-	register_netdevice_notifier(&ip6_mr_notifier);
+	err = register_netdevice_notifier(&ip6_mr_notifier);
+	if (err)
+		goto reg_notif_fail;
+#ifdef CONFIG_PROC_FS
+	err = -ENOMEM;
+	if (!proc_net_fops_create(&init_net, "ip6_mr_vif", 0, &ip6mr_vif_fops))
+		goto proc_vif_fail;
+	if (!proc_net_fops_create(&init_net, "ip6_mr_cache",
+				     0, &ip6mr_mfc_fops))
+		goto proc_cache_fail;
+#endif
+	return 0;
+reg_notif_fail:
+	kmem_cache_destroy(mrt_cachep);
 #ifdef CONFIG_PROC_FS
-	proc_net_fops_create(&init_net, "ip6_mr_vif", 0, &ip6mr_vif_fops);
-	proc_net_fops_create(&init_net, "ip6_mr_cache", 0, &ip6mr_mfc_fops);
+proc_vif_fail:
+	unregister_netdevice_notifier(&ip6_mr_notifier);
+proc_cache_fail:
+	proc_net_remove(&init_net, "ip6_mr_vif");
 #endif
+	return err;
 }
 
+void ip6_mr_cleanup(void)
+{
+#ifdef CONFIG_PROC_FS
+	proc_net_remove(&init_net, "ip6_mr_cache");
+	proc_net_remove(&init_net, "ip6_mr_vif");
+#endif
+	unregister_netdevice_notifier(&ip6_mr_notifier);
+	del_timer(&ipmr_expire_timer);
+	kmem_cache_destroy(mrt_cachep);
+}
 
 static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock)
 {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 751e98f9b8b..5d6c166dfbb 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -228,7 +228,7 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt)
 static inline int rt6_need_strict(struct in6_addr *daddr)
 {
 	return (ipv6_addr_type(daddr) &
-		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL));
+		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK));
 }
 
 /*
@@ -237,15 +237,20 @@ static inline int rt6_need_strict(struct in6_addr *daddr)
 
 static inline struct rt6_info *rt6_device_match(struct net *net,
 						    struct rt6_info *rt,
+						    struct in6_addr *saddr,
 						    int oif,
 						    int flags)
 {
 	struct rt6_info *local = NULL;
 	struct rt6_info *sprt;
 
-	if (oif) {
-		for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) {
-			struct net_device *dev = sprt->rt6i_dev;
+	if (!oif && ipv6_addr_any(saddr))
+		goto out;
+
+	for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) {
+		struct net_device *dev = sprt->rt6i_dev;
+
+		if (oif) {
 			if (dev->ifindex == oif)
 				return sprt;
 			if (dev->flags & IFF_LOOPBACK) {
@@ -259,14 +264,21 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
 				}
 				local = sprt;
 			}
+		} else {
+			if (ipv6_chk_addr(net, saddr, dev,
+					  flags & RT6_LOOKUP_F_IFACE))
+				return sprt;
 		}
+	}
 
+	if (oif) {
 		if (local)
 			return local;
 
 		if (flags & RT6_LOOKUP_F_IFACE)
 			return net->ipv6.ip6_null_entry;
 	}
+out:
 	return rt;
 }
 
@@ -539,7 +551,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
 restart:
 	rt = fn->leaf;
-	rt = rt6_device_match(net, rt, fl->oif, flags);
+	rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags);
 	BACKTRACK(net, &fl->fl6_src);
 out:
 	dst_use(&rt->u.dst, jiffies);