10 files changed, 131 insertions, 74 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index f9afb452249c..1220e2c7831e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -493,15 +493,17 @@ static void addrconf_forward_change(struct net *net, __s32 newf)
         read_unlock(&dev_base_lock);
 }
 
-static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
+static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
 {
         struct net *net;
 
         net = (struct net *)table->extra2;
         if (p == &net->ipv6.devconf_dflt->forwarding)
-                return;
+                return 0;
+
+        if (!rtnl_trylock())
+                return -ERESTARTSYS;
 
-        rtnl_lock();
         if (p == &net->ipv6.devconf_all->forwarding) {
                 __s32 newf = net->ipv6.devconf_all->forwarding;
                 net->ipv6.devconf_dflt->forwarding = newf;
@@ -512,6 +514,7 @@ static void addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old)
 
         if (*p)
                 rt6_purge_dflt_routers(net);
+        return 1;
 }
 #endif
 
@@ -2608,9 +2611,6 @@ static int addrconf_ifdown(struct net_device *dev, int how)
 
         ASSERT_RTNL();
 
-        if ((dev->flags & IFF_LOOPBACK) && how == 1)
-                how = 0;
-
         rt6_ifdown(net, dev);
         neigh_ifdown(&nd_tbl, dev);
 
@@ -3983,7 +3983,7 @@ int addrconf_sysctl_forward(ctl_table *ctl, int write, struct file * filp,
         ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
 
         if (write)
-                addrconf_fixup_forwarding(ctl, valp, val);
+                ret = addrconf_fixup_forwarding(ctl, valp, val);
         return ret;
 }
 
@@ -4019,8 +4019,7 @@ static int addrconf_sysctl_forward_strategy(ctl_table *table,
         }
 
         *valp = new;
-        addrconf_fixup_forwarding(table, valp, val);
-        return 1;
+        return addrconf_fixup_forwarding(table, valp, val);
 }
 
 static struct addrconf_sysctl_table
@@ -4446,25 +4445,6 @@ int unregister_inet6addr_notifier(struct notifier_block *nb)
 
 EXPORT_SYMBOL(unregister_inet6addr_notifier);
 
-static void addrconf_net_exit(struct net *net)
-{
-        struct net_device *dev;
-
-        rtnl_lock();
-        /* clean dev list */
-        for_each_netdev(net, dev) {
-                if (__in6_dev_get(dev) == NULL)
-                        continue;
-                addrconf_ifdown(dev, 1);
-        }
-        addrconf_ifdown(net->loopback_dev, 2);
-        rtnl_unlock();
-}
-
-static struct pernet_operations addrconf_net_ops = {
-        .exit = addrconf_net_exit,
-};
-
 /*
  *      Init / cleanup code
  */
@@ -4506,10 +4486,6 @@ int __init addrconf_init(void)
         if (err)
                 goto errlo;
 
-        err = register_pernet_device(&addrconf_net_ops);
-        if (err)
-                return err;
-
         register_netdevice_notifier(&ipv6_dev_notf);
 
         addrconf_verify(0);
@@ -4539,15 +4515,22 @@ errlo:
 void addrconf_cleanup(void)
 {
         struct inet6_ifaddr *ifa;
+        struct net_device *dev;
         int i;
 
         unregister_netdevice_notifier(&ipv6_dev_notf);
-        unregister_pernet_device(&addrconf_net_ops);
-
         unregister_pernet_subsys(&addrconf_ops);
 
         rtnl_lock();
 
+        /* clean dev list */
+        for_each_netdev(&init_net, dev) {
+                if (__in6_dev_get(dev) == NULL)
+                        continue;
+                addrconf_ifdown(dev, 1);
+        }
+        addrconf_ifdown(init_net.loopback_dev, 2);
+
         /*
          *      Check hash table.
          */
@@ -4568,6 +4551,4 @@ void addrconf_cleanup(void)
 
         del_timer(&addr_chk_timer);
         rtnl_unlock();
-
-        unregister_pernet_subsys(&addrconf_net_ops);
 }
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c802bc1658a8..9c8309ed35cf 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -72,6 +72,10 @@ MODULE_LICENSE("GPL");
 static struct list_head inetsw6[SOCK_MAX];
 static DEFINE_SPINLOCK(inetsw6_lock);
 
+static int disable_ipv6 = 0;
+module_param_named(disable, disable_ipv6, int, 0);
+MODULE_PARM_DESC(disable, "Disable IPv6 such that it is non-functional");
+
 static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk)
 {
         const int offset = sk->sk_prot->obj_size - sizeof(struct ipv6_pinfo);
@@ -991,10 +995,21 @@ static int __init inet6_init(void)
 {
         struct sk_buff *dummy_skb;
         struct list_head *r;
-        int err;
+        int err = 0;
 
         BUILD_BUG_ON(sizeof(struct inet6_skb_parm) > sizeof(dummy_skb->cb));
 
+        /* Register the socket-side information for inet6_create.  */
+        for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
+                INIT_LIST_HEAD(r);
+
+        if (disable_ipv6) {
+                printk(KERN_INFO
+                       "IPv6: Loaded, but administratively disabled, "
+                       "reboot required to enable\n");
+                goto out;
+        }
+
         err = proto_register(&tcpv6_prot, 1);
         if (err)
                 goto out;
@@ -1012,10 +1027,6 @@ static int __init inet6_init(void)
                 goto out_unregister_udplite_proto;
 
 
-        /* Register the socket-side information for inet6_create.  */
-        for(r = &inetsw6[0]; r < &inetsw6[SOCK_MAX]; ++r)
-                INIT_LIST_HEAD(r);
-
         /* We MUST register RAW sockets before we create the ICMP6,
          * IGMP6, or NDISC control sockets.
          */
@@ -1181,6 +1192,9 @@ module_init(inet6_init);
 
 static void __exit inet6_exit(void)
 {
+        if (disable_ipv6)
+                return;
+
         /* First of all disallow new sockets creation. */
         sock_unregister(PF_INET6);
         /* Disallow any further netlink messages */
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 8fe267feb81e..1bcc3431859e 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -258,11 +258,11 @@ unique:
 
         if (twp != NULL) {
                 *twp = tw;
-                NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED);
+                NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED);
         } else if (tw != NULL) {
                 /* Silly. Should hash-dance instead... */
                 inet_twsk_deschedule(tw, death_row);
-                NET_INC_STATS_BH(twsk_net(tw), LINUX_MIB_TIMEWAITRECYCLED);
+                NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED);
 
                 inet_twsk_put(tw);
         }
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index c62dd247774f..7712578bdc66 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -323,17 +323,21 @@ static struct ip6_flowlabel *
 fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval,
           int optlen, int *err_p)
 {
-        struct ip6_flowlabel *fl;
+        struct ip6_flowlabel *fl = NULL;
         int olen;
         int addr_type;
         int err;
 
+        olen = optlen - CMSG_ALIGN(sizeof(*freq));
+        err = -EINVAL;
+        if (olen > 64 * 1024)
+                goto done;
+
         err = -ENOMEM;
         fl = kzalloc(sizeof(*fl), GFP_KERNEL);
         if (fl == NULL)
                 goto done;
 
-        olen = optlen - CMSG_ALIGN(sizeof(*freq));
         if (olen > 0) {
                 struct msghdr msg;
                 struct flowi flowi;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 4b15938bef4d..9fb49c3b518a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1105,6 +1105,18 @@ static inline int ip6_ufo_append_data(struct sock *sk,
         return err;
 }
 
+static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src,
+                                               gfp_t gfp)
+{
+        return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
+}
+
+static inline struct ipv6_rt_hdr *ip6_rthdr_dup(struct ipv6_rt_hdr *src,
+                                                gfp_t gfp)
+{
+        return src ? kmemdup(src, (src->hdrlen + 1) * 8, gfp) : NULL;
+}
+
 int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
         int offset, int len, int odd, struct sk_buff *skb),
         void *from, int length, int transhdrlen,
@@ -1130,17 +1142,37 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
                  * setup for corking
                  */
                 if (opt) {
-                        if (np->cork.opt == NULL) {
-                                np->cork.opt = kmalloc(opt->tot_len,
-                                                       sk->sk_allocation);
-                                if (unlikely(np->cork.opt == NULL))
-                                        return -ENOBUFS;
-                        } else if (np->cork.opt->tot_len < opt->tot_len) {
-                                printk(KERN_DEBUG "ip6_append_data: invalid option length\n");
+                        if (WARN_ON(np->cork.opt))
                                 return -EINVAL;
-                        }
-                        memcpy(np->cork.opt, opt, opt->tot_len);
-                        inet->cork.flags |= IPCORK_OPT;
+
+                        np->cork.opt = kmalloc(opt->tot_len, sk->sk_allocation);
+                        if (unlikely(np->cork.opt == NULL))
+                                return -ENOBUFS;
+
+                        np->cork.opt->tot_len = opt->tot_len;
+                        np->cork.opt->opt_flen = opt->opt_flen;
+                        np->cork.opt->opt_nflen = opt->opt_nflen;
+
+                        np->cork.opt->dst0opt = ip6_opt_dup(opt->dst0opt,
+                                                            sk->sk_allocation);
+                        if (opt->dst0opt && !np->cork.opt->dst0opt)
+                                return -ENOBUFS;
+
+                        np->cork.opt->dst1opt = ip6_opt_dup(opt->dst1opt,
+                                                            sk->sk_allocation);
+                        if (opt->dst1opt && !np->cork.opt->dst1opt)
+                                return -ENOBUFS;
+
+                        np->cork.opt->hopopt = ip6_opt_dup(opt->hopopt,
+                                                           sk->sk_allocation);
+                        if (opt->hopopt && !np->cork.opt->hopopt)
+                                return -ENOBUFS;
+
+                        np->cork.opt->srcrt = ip6_rthdr_dup(opt->srcrt,
+                                                            sk->sk_allocation);
+                        if (opt->srcrt && !np->cork.opt->srcrt)
+                                return -ENOBUFS;
+
                         /* need source address above miyazawa*/
                 }
                 dst_hold(&rt->u.dst);
@@ -1167,8 +1199,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
         } else {
                 rt = (struct rt6_info *)inet->cork.dst;
                 fl = &inet->cork.fl;
-                if (inet->cork.flags & IPCORK_OPT)
-                        opt = np->cork.opt;
+                opt = np->cork.opt;
                 transhdrlen = 0;
                 exthdrlen = 0;
                 mtu = inet->cork.fragsize;
@@ -1407,9 +1438,15 @@ error:
 
 static void ip6_cork_release(struct inet_sock *inet, struct ipv6_pinfo *np)
 {
-        inet->cork.flags &= ~IPCORK_OPT;
-        kfree(np->cork.opt);
-        np->cork.opt = NULL;
+        if (np->cork.opt) {
+                kfree(np->cork.opt->dst0opt);
+                kfree(np->cork.opt->dst1opt);
+                kfree(np->cork.opt->hopopt);
+                kfree(np->cork.opt->srcrt);
+                kfree(np->cork.opt);
+                np->cork.opt = NULL;
+        }
+
         if (inet->cork.dst) {
                 dst_release(inet->cork.dst);
                 inet->cork.dst = NULL;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 58e2b0d93758..d994c55a5b16 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -249,8 +249,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
         }
 
         t = netdev_priv(dev);
-        ip6_tnl_dev_init(dev);
         t->parms = *p;
+        ip6_tnl_dev_init(dev);
 
         if ((err = register_netdevice(dev)) < 0)
                 goto failed_free;
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index c455cf4ee756..72dbb6d1a6b3 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -49,8 +49,19 @@ static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb,
 static const u_int8_t invmap[] = {
         [ICMPV6_ECHO_REQUEST - 128]     = ICMPV6_ECHO_REPLY + 1,
         [ICMPV6_ECHO_REPLY - 128]       = ICMPV6_ECHO_REQUEST + 1,
-        [ICMPV6_NI_QUERY - 128]         = ICMPV6_NI_QUERY + 1,
-        [ICMPV6_NI_REPLY - 128]         = ICMPV6_NI_REPLY +1
+        [ICMPV6_NI_QUERY - 128]         = ICMPV6_NI_REPLY + 1,
+        [ICMPV6_NI_REPLY - 128]         = ICMPV6_NI_QUERY +1
+};
+
+static const u_int8_t noct_valid_new[] = {
+        [ICMPV6_MGM_QUERY - 130] = 1,
+        [ICMPV6_MGM_REPORT -130] = 1,
+        [ICMPV6_MGM_REDUCTION - 130] = 1,
+        [NDISC_ROUTER_SOLICITATION - 130] = 1,
+        [NDISC_ROUTER_ADVERTISEMENT - 130] = 1,
+        [NDISC_NEIGHBOUR_SOLICITATION - 130] = 1,
+        [NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1,
+        [ICMPV6_MLD2_REPORT - 130] = 1
 };
 
 static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
@@ -178,6 +189,7 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
 {
         const struct icmp6hdr *icmp6h;
         struct icmp6hdr _ih;
+        int type;
 
         icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
         if (icmp6h == NULL) {
@@ -189,11 +201,21 @@ icmpv6_error(struct net *net, struct sk_buff *skb, unsigned int dataoff,
 
         if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
             nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
-                nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
-                              "nf_ct_icmpv6: ICMPv6 checksum failed\n");
+                if (LOG_INVALID(net, IPPROTO_ICMPV6))
+                        nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
+                                      "nf_ct_icmpv6: ICMPv6 checksum failed ");
                 return -NF_ACCEPT;
         }
 
+        type = icmp6h->icmp6_type - 130;
+        if (type >= 0 && type < sizeof(noct_valid_new) &&
+            noct_valid_new[type]) {
+                skb->nfct = &nf_conntrack_untracked.ct_general;
+                skb->nfctinfo = IP_CT_NEW;
+                nf_conntrack_get(skb->nfct);
+                return NF_ACCEPT;
+        }
+
         /* is not error message ? */
         if (icmp6h->icmp6_type >= 128)
                 return NF_ACCEPT;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index ed4d79a9e4a6..058a5e4a60c3 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -528,14 +528,14 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
                 if (!ipv6_ext_hdr(nexthdr)) {
                         return -1;
                 }
-                if (len < (int)sizeof(struct ipv6_opt_hdr)) {
-                        pr_debug("too short\n");
-                        return -1;
-                }
                 if (nexthdr == NEXTHDR_NONE) {
                         pr_debug("next header is none\n");
                         return -1;
                 }
+                if (len < (int)sizeof(struct ipv6_opt_hdr)) {
+                        pr_debug("too short\n");
+                        return -1;
+                }
                 if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
                         BUG();
                 if (nexthdr == NEXTHDR_AUTH)
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 3c575118fca5..e9ac7a12f595 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -452,6 +452,7 @@ err:
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
                           struct net_device *dev)
 {
+        struct net *net = container_of(fq->q.net, struct net, ipv6.frags);
         struct sk_buff *fp, *head = fq->q.fragments;
         int    payload_len;
         unsigned int nhoff;
@@ -551,8 +552,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
                                           head->csum);
 
         rcu_read_lock();
-        IP6_INC_STATS_BH(dev_net(dev),
-                         __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
+        IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
         rcu_read_unlock();
         fq->q.fragments = NULL;
         return 1;
@@ -566,8 +566,7 @@ out_oom:
                 printk(KERN_DEBUG "ip6_frag_reasm: no memory for reassembly\n");
 out_fail:
         rcu_read_lock();
-        IP6_INC_STATS_BH(dev_net(dev),
-                         __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+        IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
         rcu_read_unlock();
         return -1;
 }
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index d3467e563f02..5cee2bcbcece 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -188,9 +188,9 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
         }
 
         nt = netdev_priv(dev);
-        ipip6_tunnel_init(dev);
 
         nt->parms = *parms;
+        ipip6_tunnel_init(dev);
 
         if (parms->i_flags & SIT_ISATAP)
                 dev->priv_flags |= IFF_ISATAP;