1 files changed, 90 insertions, 48 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 0ef1f086feb..f02fe523bd3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -72,7 +72,8 @@
 #define RT6_TRACE(x...) do { ; } while (0)
 #endif
 
-static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
+static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
+                                    const struct in6_addr *dest);
 static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int      ip6_default_advmss(const struct dst_entry *dst);
 static unsigned int      ip6_default_mtu(const struct dst_entry *dst);
@@ -103,6 +104,9 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
         struct inet_peer *peer;
         u32 *p = NULL;
 
+        if (!(rt->dst.flags & DST_HOST))
+                return NULL;
+
         if (!rt->rt6i_peer)
                 rt6_bind_peer(rt, 1);
 
@@ -127,6 +131,11 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
         return p;
 }
 
+static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr)
+{
+        return __neigh_lookup_errno(&nd_tbl, daddr, dst->dev);
+}
+
 static struct dst_ops ip6_dst_ops_template = {
         .family                 =       AF_INET6,
         .protocol               =       cpu_to_be16(ETH_P_IPV6),
@@ -142,6 +151,7 @@ static struct dst_ops ip6_dst_ops_template = {
         .link_failure           =       ip6_link_failure,
         .update_pmtu            =       ip6_rt_update_pmtu,
         .local_out              =       __ip6_local_out,
+        .neigh_lookup           =       ip6_neigh_lookup,
 };
 
 static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst)
@@ -168,6 +178,7 @@ static struct dst_ops ip6_dst_blackhole_ops = {
         .default_advmss         =       ip6_default_advmss,
         .update_pmtu            =       ip6_rt_blackhole_update_pmtu,
         .cow_metrics            =       ip6_rt_blackhole_cow_metrics,
+        .neigh_lookup           =       ip6_neigh_lookup,
 };
 
 static const u32 ip6_template_metrics[RTAX_MAX] = {
@@ -233,7 +244,9 @@ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
 {
         struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
 
-        memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+        if (rt != NULL)
+                memset(&rt->rt6i_table, 0,
+                        sizeof(*rt) - sizeof(struct dst_entry));
 
         return rt;
 }
@@ -244,6 +257,9 @@ static void ip6_dst_destroy(struct dst_entry *dst)
         struct inet6_dev *idev = rt->rt6i_idev;
         struct inet_peer *peer = rt->rt6i_peer;
 
+        if (!(rt->dst.flags & DST_HOST))
+                dst_destroy_metrics_generic(dst);
+
         if (idev != NULL) {
                 rt->rt6i_idev = NULL;
                 in6_dev_put(idev);
@@ -356,7 +372,7 @@ out:
 #ifdef CONFIG_IPV6_ROUTER_PREF
 static void rt6_probe(struct rt6_info *rt)
 {
-        struct neighbour *neigh = rt ? rt->rt6i_nexthop : NULL;
+        struct neighbour *neigh;
         /*
          * Okay, this does not seem to be appropriate
          * for now, however, we need to check if it
@@ -365,8 +381,10 @@ static void rt6_probe(struct rt6_info *rt)
          * Router Reachability Probe MUST be rate-limited
          * to no more than one per minute.
          */
+        rcu_read_lock();
+        neigh = rt ? dst_get_neighbour(&rt->dst) : NULL;
         if (!neigh || (neigh->nud_state & NUD_VALID))
-                return;
+                goto out;
         read_lock_bh(&neigh->lock);
         if (!(neigh->nud_state & NUD_VALID) &&
             time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
@@ -379,8 +397,11 @@ static void rt6_probe(struct rt6_info *rt)
                 target = (struct in6_addr *)&neigh->primary_key;
                 addrconf_addr_solict_mult(target, &mcaddr);
                 ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL);
-        } else
+        } else {
                 read_unlock_bh(&neigh->lock);
+        }
+out:
+        rcu_read_unlock();
 }
 #else
 static inline void rt6_probe(struct rt6_info *rt)
@@ -404,8 +425,11 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif)
 
 static inline int rt6_check_neigh(struct rt6_info *rt)
 {
-        struct neighbour *neigh = rt->rt6i_nexthop;
+        struct neighbour *neigh;
         int m;
+
+        rcu_read_lock();
+        neigh = dst_get_neighbour(&rt->dst);
         if (rt->rt6i_flags & RTF_NONEXTHOP ||
             !(rt->rt6i_flags & RTF_GATEWAY))
                 m = 1;
@@ -422,6 +446,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
                 read_unlock_bh(&neigh->lock);
         } else
                 m = 0;
+        rcu_read_unlock();
         return m;
 }
 
@@ -683,7 +708,8 @@ int ip6_ins_rt(struct rt6_info *rt)
         return __ip6_ins_rt(rt, &info);
 }
 
-static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_addr *daddr,
+static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort,
+                                      const struct in6_addr *daddr,
                                       const struct in6_addr *saddr)
 {
         struct rt6_info *rt;
@@ -692,23 +718,20 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_add
          *      Clone the route.
          */
 
-        rt = ip6_rt_copy(ort);
+        rt = ip6_rt_copy(ort, daddr);
 
         if (rt) {
                 struct neighbour *neigh;
                 int attempts = !in_softirq();
 
                 if (!(rt->rt6i_flags&RTF_GATEWAY)) {
-                        if (rt->rt6i_dst.plen != 128 &&
-                            ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
+                        if (ort->rt6i_dst.plen != 128 &&
+                            ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
                                 rt->rt6i_flags |= RTF_ANYCAST;
                         ipv6_addr_copy(&rt->rt6i_gateway, daddr);
                 }
 
-                ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
-                rt->rt6i_dst.plen = 128;
                 rt->rt6i_flags |= RTF_CACHE;
-                rt->dst.flags |= DST_HOST;
 
 #ifdef CONFIG_IPV6_SUBTREES
                 if (rt->rt6i_src.plen && saddr) {
@@ -745,22 +768,21 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_add
                         dst_free(&rt->dst);
                         return NULL;
                 }
-                rt->rt6i_nexthop = neigh;
+                dst_set_neighbour(&rt->dst, neigh);
 
         }
 
         return rt;
 }
 
-static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, const struct in6_addr *daddr)
+static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
+                                        const struct in6_addr *daddr)
 {
-        struct rt6_info *rt = ip6_rt_copy(ort);
+        struct rt6_info *rt = ip6_rt_copy(ort, daddr);
+
         if (rt) {
-                ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
-                rt->rt6i_dst.plen = 128;
                 rt->rt6i_flags |= RTF_CACHE;
-                rt->dst.flags |= DST_HOST;
-                rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop);
+                dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst)));
         }
         return rt;
 }
@@ -794,7 +816,7 @@ restart:
         dst_hold(&rt->dst);
         read_unlock_bh(&table->tb6_lock);
 
-        if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
+        if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
                 nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
         else if (!(rt->dst.flags & DST_HOST))
                 nrt = rt6_alloc_clone(rt, &fl6->daddr);
@@ -900,7 +922,10 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
                 new->input = dst_discard;
                 new->output = dst_discard;
 
-                dst_copy_metrics(new, &ort->dst);
+                if (dst_metrics_read_only(&ort->dst))
+                        new->_metrics = ort->dst._metrics;
+                else
+                        dst_copy_metrics(new, &ort->dst);
                 rt->rt6i_idev = ort->rt6i_idev;
                 if (rt->rt6i_idev)
                         in6_dev_hold(rt->rt6i_idev);
@@ -1057,11 +1082,14 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
                         neigh = NULL;
         }
 
-        rt->rt6i_idev     = idev;
-        rt->rt6i_nexthop  = neigh;
+        rt->dst.flags |= DST_HOST;
+        rt->dst.output  = ip6_output;
+        dst_set_neighbour(&rt->dst, neigh);
         atomic_set(&rt->dst.__refcnt, 1);
+        ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
+        rt->rt6i_dst.plen = 128;
+        rt->rt6i_idev     = idev;
         dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
-        rt->dst.output  = ip6_output;
 
         spin_lock_bh(&icmp6_dst_lock);
         rt->dst.next = icmp6_dst_gc_list;
@@ -1239,6 +1267,14 @@ int ip6_route_add(struct fib6_config *cfg)
         if (rt->rt6i_dst.plen == 128)
                rt->dst.flags |= DST_HOST;
 
+        if (!(rt->dst.flags & DST_HOST) && cfg->fc_mx) {
+                u32 *metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
+                if (!metrics) {
+                        err = -ENOMEM;
+                        goto out;
+                }
+                dst_init_metrics(&rt->dst, metrics, 0);
+        }
 #ifdef CONFIG_IPV6_SUBTREES
         ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
         rt->rt6i_src.plen = cfg->fc_src_len;
@@ -1338,12 +1374,12 @@ int ip6_route_add(struct fib6_config *cfg)
                 rt->rt6i_prefsrc.plen = 0;
 
         if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
-                rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
-                if (IS_ERR(rt->rt6i_nexthop)) {
-                        err = PTR_ERR(rt->rt6i_nexthop);
-                        rt->rt6i_nexthop = NULL;
+                struct neighbour *n = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
+                if (IS_ERR(n)) {
+                        err = PTR_ERR(n);
                         goto out;
                 }
+                dst_set_neighbour(&rt->dst, n);
         }
 
         rt->rt6i_flags = cfg->fc_flags;
@@ -1574,10 +1610,10 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
         dst_confirm(&rt->dst);
 
         /* Duplicate redirect: silently ignore. */
-        if (neigh == rt->dst.neighbour)
+        if (neigh == dst_get_neighbour_raw(&rt->dst))
                 goto out;
 
-        nrt = ip6_rt_copy(rt);
+        nrt = ip6_rt_copy(rt, dest);
         if (nrt == NULL)
                 goto out;
 
@@ -1585,12 +1621,8 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
         if (on_link)
                 nrt->rt6i_flags &= ~RTF_GATEWAY;
 
-        ipv6_addr_copy(&nrt->rt6i_dst.addr, dest);
-        nrt->rt6i_dst.plen = 128;
-        nrt->dst.flags |= DST_HOST;
-
         ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
-        nrt->rt6i_nexthop = neigh_clone(neigh);
+        dst_set_neighbour(&nrt->dst, neigh_clone(neigh));
 
         if (ip6_ins_rt(nrt))
                 goto out;
@@ -1670,7 +1702,7 @@ again:
            1. It is connected route. Action: COW
            2. It is gatewayed route or NONEXTHOP route. Action: clone it.
          */
-        if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
+        if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
                 nrt = rt6_alloc_cow(rt, daddr, saddr);
         else
                 nrt = rt6_alloc_clone(rt, daddr);
@@ -1723,7 +1755,8 @@ void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *sad
  *      Misc support functions
  */
 
-static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
+static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
+                                    const struct in6_addr *dest)
 {
         struct net *net = dev_net(ort->rt6i_dev);
         struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
@@ -1732,7 +1765,10 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
         if (rt) {
                 rt->dst.input = ort->dst.input;
                 rt->dst.output = ort->dst.output;
+                rt->dst.flags |= DST_HOST;
 
+                ipv6_addr_copy(&rt->rt6i_dst.addr, dest);
+                rt->rt6i_dst.plen = 128;
                 dst_copy_metrics(&rt->dst, &ort->dst);
                 rt->dst.error = ort->dst.error;
                 rt->rt6i_idev = ort->rt6i_idev;
@@ -1745,7 +1781,6 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
                 rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
                 rt->rt6i_metric = 0;
 
-                memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
 #ifdef CONFIG_IPV6_SUBTREES
                 memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
 #endif
@@ -2035,7 +2070,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 
                 return ERR_CAST(neigh);
         }
-        rt->rt6i_nexthop = neigh;
+        dst_set_neighbour(&rt->dst, neigh);
 
         ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
         rt->rt6i_dst.plen = 128;
@@ -2312,6 +2347,7 @@ static int rt6_fill_node(struct net *net,
         struct nlmsghdr *nlh;
         long expires;
         u32 table;
+        struct neighbour *n;
 
         if (prefix) {   /* user wants prefix routes only */
                 if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
@@ -2400,8 +2436,11 @@ static int rt6_fill_node(struct net *net,
         if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
                 goto nla_put_failure;
 
-        if (rt->dst.neighbour)
-                NLA_PUT(skb, RTA_GATEWAY, 16, &rt->dst.neighbour->primary_key);
+        rcu_read_lock();
+        n = dst_get_neighbour(&rt->dst);
+        if (n)
+                NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key);
+        rcu_read_unlock();
 
         if (rt->dst.dev)
                 NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex);
@@ -2585,6 +2624,7 @@ struct rt6_proc_arg
 static int rt6_info_route(struct rt6_info *rt, void *p_arg)
 {
         struct seq_file *m = p_arg;
+        struct neighbour *n;
 
         seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
 
@@ -2593,12 +2633,14 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
 #else
         seq_puts(m, "00000000000000000000000000000000 00 ");
 #endif
-
-        if (rt->rt6i_nexthop) {
-                seq_printf(m, "%pi6", rt->rt6i_nexthop->primary_key);
+        rcu_read_lock();
+        n = dst_get_neighbour(&rt->dst);
+        if (n) {
+                seq_printf(m, "%pi6", n->primary_key);
         } else {
                 seq_puts(m, "00000000000000000000000000000000");
         }
+        rcu_read_unlock();
         seq_printf(m, " %08x %08x %08x %08x %8s\n",
                    rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
                    rt->dst.__use, rt->rt6i_flags,
@@ -2918,9 +2960,9 @@ int __init ip6_route_init(void)
                 goto xfrm6_init;
 
         ret = -ENOBUFS;
-        if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) ||
-            __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) ||
-            __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL))
+        if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) ||
+            __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) ||
+            __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL))
                 goto fib6_rules_init;
 
         ret = register_netdevice_notifier(&ip6_route_dev_notifier);