1 files changed, 242 insertions, 125 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a998db6e7895..de2b1decd786 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -89,14 +89,44 @@ static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_add_route_info(struct net *net,
-                                           struct in6_addr *prefix, int prefixlen,
-                                           struct in6_addr *gwaddr, int ifindex,
+                                           const struct in6_addr *prefix, int prefixlen,
+                                           const struct in6_addr *gwaddr, int ifindex,
                                            unsigned pref);
 static struct rt6_info *rt6_get_route_info(struct net *net,
-                                           struct in6_addr *prefix, int prefixlen,
-                                           struct in6_addr *gwaddr, int ifindex);
+                                           const struct in6_addr *prefix, int prefixlen,
+                                           const struct in6_addr *gwaddr, int ifindex);
 #endif
 
+static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
+{
+        struct rt6_info *rt = (struct rt6_info *) dst;
+        struct inet_peer *peer;
+        u32 *p = NULL;
+
+        if (!rt->rt6i_peer)
+                rt6_bind_peer(rt, 1);
+
+        peer = rt->rt6i_peer;
+        if (peer) {
+                u32 *old_p = __DST_METRICS_PTR(old);
+                unsigned long prev, new;
+
+                p = peer->metrics;
+                if (inet_metrics_new(peer))
+                        memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+
+                new = (unsigned long) p;
+                prev = cmpxchg(&dst->_metrics, old, new);
+
+                if (prev != old) {
+                        p = __DST_METRICS_PTR(prev);
+                        if (prev & DST_METRICS_READ_ONLY)
+                                p = NULL;
+                }
+        }
+        return p;
+}
+
 static struct dst_ops ip6_dst_ops_template = {
         .family                 =       AF_INET6,
         .protocol               =       cpu_to_be16(ETH_P_IPV6),
@@ -105,6 +135,7 @@ static struct dst_ops ip6_dst_ops_template = {
         .check                  =       ip6_dst_check,
         .default_advmss         =       ip6_default_advmss,
         .default_mtu            =       ip6_default_mtu,
+        .cow_metrics            =       ipv6_cow_metrics,
         .destroy                =       ip6_dst_destroy,
         .ifdown                 =       ip6_dst_ifdown,
         .negative_advice        =       ip6_negative_advice,
@@ -122,6 +153,12 @@ static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
 }
 
+static u32 *ip6_rt_blackhole_cow_metrics(struct dst_entry *dst,
+                                         unsigned long old)
+{
+        return NULL;
+}
+
 static struct dst_ops ip6_dst_blackhole_ops = {
         .family                 =       AF_INET6,
         .protocol               =       cpu_to_be16(ETH_P_IPV6),
@@ -130,6 +167,11 @@ static struct dst_ops ip6_dst_blackhole_ops = {
         .default_mtu            =       ip6_blackhole_default_mtu,
         .default_advmss         =       ip6_default_advmss,
         .update_pmtu            =       ip6_rt_blackhole_update_pmtu,
+        .cow_metrics            =       ip6_rt_blackhole_cow_metrics,
+};
+
+static const u32 ip6_template_metrics[RTAX_MAX] = {
+        [RTAX_HOPLIMIT - 1] = 255,
 };
 
 static struct rt6_info ip6_null_entry_template = {
@@ -185,9 +227,14 @@ static struct rt6_info ip6_blk_hole_entry_template = {
 #endif
 
 /* allocate dst with ip6_dst_ops */
-static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops)
+static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
+                                             struct net_device *dev)
 {
-        return (struct rt6_info *)dst_alloc(ops);
+        struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, 0);
+
+        memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+
+        return rt;
 }
 
 static void ip6_dst_destroy(struct dst_entry *dst)
@@ -206,6 +253,13 @@ static void ip6_dst_destroy(struct dst_entry *dst)
         }
 }
 
+static atomic_t __rt6_peer_genid = ATOMIC_INIT(0);
+
+static u32 rt6_peer_genid(void)
+{
+        return atomic_read(&__rt6_peer_genid);
+}
+
 void rt6_bind_peer(struct rt6_info *rt, int create)
 {
         struct inet_peer *peer;
@@ -213,6 +267,8 @@ void rt6_bind_peer(struct rt6_info *rt, int create)
         peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create);
         if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL)
                 inet_putpeer(peer);
+        else
+                rt->rt6i_peer_genid = rt6_peer_genid();
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -239,7 +295,7 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt)
                 time_after(jiffies, rt->rt6i_expires);
 }
 
-static inline int rt6_need_strict(struct in6_addr *daddr)
+static inline int rt6_need_strict(const struct in6_addr *daddr)
 {
         return ipv6_addr_type(daddr) &
                 (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
@@ -251,7 +307,7 @@ 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,
+                                                    const struct in6_addr *saddr,
                                                     int oif,
                                                     int flags)
 {
@@ -463,7 +519,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
-                  struct in6_addr *gwaddr)
+                  const struct in6_addr *gwaddr)
 {
         struct net *net = dev_net(dev);
         struct route_info *rinfo = (struct route_info *) opt;
@@ -555,17 +611,17 @@ do { \
 
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
                                              struct fib6_table *table,
-                                             struct flowi *fl, int flags)
+                                             struct flowi6 *fl6, int flags)
 {
         struct fib6_node *fn;
         struct rt6_info *rt;
 
         read_lock_bh(&table->tb6_lock);
-        fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+        fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
         rt = fn->leaf;
-        rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags);
-        BACKTRACK(net, &fl->fl6_src);
+        rt = rt6_device_match(net, rt, &fl6->saddr, fl6->flowi6_oif, flags);
+        BACKTRACK(net, &fl6->saddr);
 out:
         dst_use(&rt->dst, jiffies);
         read_unlock_bh(&table->tb6_lock);
@@ -576,19 +632,19 @@ out:
 struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
                             const struct in6_addr *saddr, int oif, int strict)
 {
-        struct flowi fl = {
-                .oif = oif,
-                .fl6_dst = *daddr,
+        struct flowi6 fl6 = {
+                .flowi6_oif = oif,
+                .daddr = *daddr,
         };
         struct dst_entry *dst;
         int flags = strict ? RT6_LOOKUP_F_IFACE : 0;
 
         if (saddr) {
-                memcpy(&fl.fl6_src, saddr, sizeof(*saddr));
+                memcpy(&fl6.saddr, saddr, sizeof(*saddr));
                 flags |= RT6_LOOKUP_F_HAS_SADDR;
         }
 
-        dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_lookup);
+        dst = fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_lookup);
         if (dst->error == 0)
                 return (struct rt6_info *) dst;
 
@@ -626,8 +682,8 @@ 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, struct in6_addr *daddr,
-                                      struct in6_addr *saddr)
+static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_addr *daddr,
+                                      const struct in6_addr *saddr)
 {
         struct rt6_info *rt;
 
@@ -695,7 +751,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
         return rt;
 }
 
-static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, 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);
         if (rt) {
@@ -709,7 +765,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *d
 }
 
 static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
-                                      struct flowi *fl, int flags)
+                                      struct flowi6 *fl6, int flags)
 {
         struct fib6_node *fn;
         struct rt6_info *rt, *nrt;
@@ -724,12 +780,12 @@ relookup:
         read_lock_bh(&table->tb6_lock);
 
 restart_2:
-        fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+        fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 
 restart:
         rt = rt6_select(fn, oif, strict | reachable);
 
-        BACKTRACK(net, &fl->fl6_src);
+        BACKTRACK(net, &fl6->saddr);
         if (rt == net->ipv6.ip6_null_entry ||
             rt->rt6i_flags & RTF_CACHE)
                 goto out;
@@ -738,9 +794,11 @@ restart:
         read_unlock_bh(&table->tb6_lock);
 
         if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
-                nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
+                nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
+        else if (!(rt->dst.flags & DST_HOST))
+                nrt = rt6_alloc_clone(rt, &fl6->daddr);
         else
-                nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
+                goto out2;
 
         dst_release(&rt->dst);
         rt = nrt ? : net->ipv6.ip6_null_entry;
@@ -777,74 +835,71 @@ out2:
 }
 
 static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
-                                            struct flowi *fl, int flags)
+                                            struct flowi6 *fl6, int flags)
 {
-        return ip6_pol_route(net, table, fl->iif, fl, flags);
+        return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags);
 }
 
 void ip6_route_input(struct sk_buff *skb)
 {
-        struct ipv6hdr *iph = ipv6_hdr(skb);
+        const struct ipv6hdr *iph = ipv6_hdr(skb);
         struct net *net = dev_net(skb->dev);
         int flags = RT6_LOOKUP_F_HAS_SADDR;
-        struct flowi fl = {
-                .iif = skb->dev->ifindex,
-                .fl6_dst = iph->daddr,
-                .fl6_src = iph->saddr,
-                .fl6_flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
-                .mark = skb->mark,
-                .proto = iph->nexthdr,
+        struct flowi6 fl6 = {
+                .flowi6_iif = skb->dev->ifindex,
+                .daddr = iph->daddr,
+                .saddr = iph->saddr,
+                .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
+                .flowi6_mark = skb->mark,
+                .flowi6_proto = iph->nexthdr,
         };
 
         if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
                 flags |= RT6_LOOKUP_F_IFACE;
 
-        skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input));
+        skb_dst_set(skb, fib6_rule_lookup(net, &fl6, flags, ip6_pol_route_input));
 }
 
 static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
-                                             struct flowi *fl, int flags)
+                                             struct flowi6 *fl6, int flags)
 {
-        return ip6_pol_route(net, table, fl->oif, fl, flags);
+        return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
 }
 
-struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
-                                    struct flowi *fl)
+struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
+                                    struct flowi6 *fl6)
 {
         int flags = 0;
 
-        if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl->fl6_dst))
+        if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
                 flags |= RT6_LOOKUP_F_IFACE;
 
-        if (!ipv6_addr_any(&fl->fl6_src))
+        if (!ipv6_addr_any(&fl6->saddr))
                 flags |= RT6_LOOKUP_F_HAS_SADDR;
         else if (sk)
                 flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);
 
-        return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
+        return fib6_rule_lookup(net, fl6, flags, ip6_pol_route_output);
 }
 
 EXPORT_SYMBOL(ip6_route_output);
 
-int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl)
+struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
 {
-        struct rt6_info *ort = (struct rt6_info *) *dstp;
-        struct rt6_info *rt = (struct rt6_info *)
-                dst_alloc(&ip6_dst_blackhole_ops);
+        struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
         struct dst_entry *new = NULL;
 
+        rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
         if (rt) {
+                memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+
                 new = &rt->dst;
 
-                atomic_set(&new->__refcnt, 1);
                 new->__use = 1;
                 new->input = dst_discard;
                 new->output = dst_discard;
 
                 dst_copy_metrics(new, &ort->dst);
-                new->dev = ort->dst.dev;
-                if (new->dev)
-                        dev_hold(new->dev);
                 rt->rt6i_idev = ort->rt6i_idev;
                 if (rt->rt6i_idev)
                         in6_dev_hold(rt->rt6i_idev);
@@ -862,11 +917,9 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl
                 dst_free(new);
         }
 
-        dst_release(*dstp);
-        *dstp = new;
-        return new ? 0 : -ENOMEM;
+        dst_release(dst_orig);
+        return new ? new : ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL_GPL(ip6_dst_blackhole);
 
 /*
  *      Destination cache support functions
@@ -878,9 +931,14 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 
         rt = (struct rt6_info *) dst;
 
-        if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
+        if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
+                if (rt->rt6i_peer_genid != rt6_peer_genid()) {
+                        if (!rt->rt6i_peer)
+                                rt6_bind_peer(rt, 0);
+                        rt->rt6i_peer_genid = rt6_peer_genid();
+                }
                 return dst;
-
+        }
         return NULL;
 }
 
@@ -931,7 +989,6 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
                         dst_metric_set(dst, RTAX_FEATURES, features);
                 }
                 dst_metric_set(dst, RTAX_MTU, mtu);
-                call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
         }
 }
 
@@ -985,13 +1042,12 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
         if (unlikely(idev == NULL))
                 return NULL;
 
-        rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+        rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev);
         if (unlikely(rt == NULL)) {
                 in6_dev_put(idev);
                 goto out;
         }
 
-        dev_hold(dev);
         if (neigh)
                 neigh_hold(neigh);
         else {
@@ -1000,7 +1056,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
                         neigh = NULL;
         }
 
-        rt->rt6i_dev      = dev;
         rt->rt6i_idev     = idev;
         rt->rt6i_nexthop  = neigh;
         atomic_set(&rt->dst.__refcnt, 1);
@@ -1028,11 +1083,9 @@ out:
 
 int icmp6_dst_gc(void)
 {
-        struct dst_entry *dst, *next, **pprev;
+        struct dst_entry *dst, **pprev;
         int more = 0;
 
-        next = NULL;
-
         spin_lock_bh(&icmp6_dst_lock);
         pprev = &icmp6_dst_gc_list;
 
@@ -1161,7 +1214,7 @@ int ip6_route_add(struct fib6_config *cfg)
                 goto out;
         }
 
-        rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+        rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL);
 
         if (rt == NULL) {
                 err = -ENOMEM;
@@ -1228,7 +1281,7 @@ int ip6_route_add(struct fib6_config *cfg)
         }
 
         if (cfg->fc_flags & RTF_GATEWAY) {
-                struct in6_addr *gw_addr;
+                const struct in6_addr *gw_addr;
                 int gwa_type;
 
                 gw_addr = &cfg->fc_gateway;
@@ -1281,6 +1334,16 @@ int ip6_route_add(struct fib6_config *cfg)
         if (dev == NULL)
                 goto out;
 
+        if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
+                if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
+                        err = -EINVAL;
+                        goto out;
+                }
+                ipv6_addr_copy(&rt->rt6i_prefsrc.addr, &cfg->fc_prefsrc);
+                rt->rt6i_prefsrc.plen = 128;
+        } else
+                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)) {
@@ -1400,16 +1463,16 @@ static int ip6_route_del(struct fib6_config *cfg)
  *      Handle redirects
  */
 struct ip6rd_flowi {
-        struct flowi fl;
+        struct flowi6 fl6;
         struct in6_addr gateway;
 };
 
 static struct rt6_info *__ip6_route_redirect(struct net *net,
                                              struct fib6_table *table,
-                                             struct flowi *fl,
+                                             struct flowi6 *fl6,
                                              int flags)
 {
-        struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl;
+        struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
         struct rt6_info *rt;
         struct fib6_node *fn;
 
@@ -1425,7 +1488,7 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
          */
 
         read_lock_bh(&table->tb6_lock);
-        fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
+        fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
 restart:
         for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
                 /*
@@ -1440,7 +1503,7 @@ restart:
                         continue;
                 if (!(rt->rt6i_flags & RTF_GATEWAY))
                         continue;
-                if (fl->oif != rt->rt6i_dev->ifindex)
+                if (fl6->flowi6_oif != rt->rt6i_dev->ifindex)
                         continue;
                 if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
                         continue;
@@ -1449,7 +1512,7 @@ restart:
 
         if (!rt)
                 rt = net->ipv6.ip6_null_entry;
-        BACKTRACK(net, &fl->fl6_src);
+        BACKTRACK(net, &fl6->saddr);
 out:
         dst_hold(&rt->dst);
 
@@ -1458,18 +1521,18 @@ out:
         return rt;
 };
 
-static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
-                                           struct in6_addr *src,
-                                           struct in6_addr *gateway,
+static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest,
+                                           const struct in6_addr *src,
+                                           const struct in6_addr *gateway,
                                            struct net_device *dev)
 {
         int flags = RT6_LOOKUP_F_HAS_SADDR;
         struct net *net = dev_net(dev);
         struct ip6rd_flowi rdfl = {
-                .fl = {
-                        .oif = dev->ifindex,
-                        .fl6_dst = *dest,
-                        .fl6_src = *src,
+                .fl6 = {
+                        .flowi6_oif = dev->ifindex,
+                        .daddr = *dest,
+                        .saddr = *src,
                 },
         };
 
@@ -1478,12 +1541,12 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
         if (rt6_need_strict(dest))
                 flags |= RT6_LOOKUP_F_IFACE;
 
-        return (struct rt6_info *)fib6_rule_lookup(net, (struct flowi *)&rdfl,
+        return (struct rt6_info *)fib6_rule_lookup(net, &rdfl.fl6,
                                                    flags, __ip6_route_redirect);
 }
 
-void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
-                  struct in6_addr *saddr,
+void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
+                  const struct in6_addr *saddr,
                   struct neighbour *neigh, u8 *lladdr, int on_link)
 {
         struct rt6_info *rt, *nrt = NULL;
@@ -1557,7 +1620,7 @@ out:
  *      i.e. Path MTU discovery
  */
 
-static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
+static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr *saddr,
                              struct net *net, u32 pmtu, int ifindex)
 {
         struct rt6_info *rt, *nrt;
@@ -1642,7 +1705,7 @@ out:
         dst_release(&rt->dst);
 }
 
-void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
+void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *saddr,
                         struct net_device *dev, u32 pmtu)
 {
         struct net *net = dev_net(dev);
@@ -1670,7 +1733,8 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
 static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
 {
         struct net *net = dev_net(ort->rt6i_dev);
-        struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+        struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
+                                            ort->dst.dev);
 
         if (rt) {
                 rt->dst.input = ort->dst.input;
@@ -1678,9 +1742,6 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
 
                 dst_copy_metrics(&rt->dst, &ort->dst);
                 rt->dst.error = ort->dst.error;
-                rt->dst.dev = ort->dst.dev;
-                if (rt->dst.dev)
-                        dev_hold(rt->dst.dev);
                 rt->rt6i_idev = ort->rt6i_idev;
                 if (rt->rt6i_idev)
                         in6_dev_hold(rt->rt6i_idev);
@@ -1695,6 +1756,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
 #ifdef CONFIG_IPV6_SUBTREES
                 memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
 #endif
+                memcpy(&rt->rt6i_prefsrc, &ort->rt6i_prefsrc, sizeof(struct rt6key));
                 rt->rt6i_table = ort->rt6i_table;
         }
         return rt;
@@ -1702,8 +1764,8 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
 static struct rt6_info *rt6_get_route_info(struct net *net,
-                                           struct in6_addr *prefix, int prefixlen,
-                                           struct in6_addr *gwaddr, int ifindex)
+                                           const struct in6_addr *prefix, int prefixlen,
+                                           const struct in6_addr *gwaddr, int ifindex)
 {
         struct fib6_node *fn;
         struct rt6_info *rt = NULL;
@@ -1734,8 +1796,8 @@ out:
 }
 
 static struct rt6_info *rt6_add_route_info(struct net *net,
-                                           struct in6_addr *prefix, int prefixlen,
-                                           struct in6_addr *gwaddr, int ifindex,
+                                           const struct in6_addr *prefix, int prefixlen,
+                                           const struct in6_addr *gwaddr, int ifindex,
                                            unsigned pref)
 {
         struct fib6_config cfg = {
@@ -1763,7 +1825,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 }
 #endif
 
-struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev)
+struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
 {
         struct rt6_info *rt;
         struct fib6_table *table;
@@ -1785,7 +1847,7 @@ struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *d
         return rt;
 }
 
-struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
+struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
                                      struct net_device *dev,
                                      unsigned int pref)
 {
@@ -1950,7 +2012,8 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
                                     int anycast)
 {
         struct net *net = dev_net(idev->dev);
-        struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
+        struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
+                                            net->loopback_dev);
         struct neighbour *neigh;
 
         if (rt == NULL) {
@@ -1960,15 +2023,12 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
                 return ERR_PTR(-ENOMEM);
         }
 
-        dev_hold(net->loopback_dev);
         in6_dev_hold(idev);
 
         rt->dst.flags = DST_HOST;
         rt->dst.input = ip6_input;
         rt->dst.output = ip6_output;
-        rt->rt6i_dev = net->loopback_dev;
         rt->rt6i_idev = idev;
-        dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1);
         rt->dst.obsolete = -1;
 
         rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
@@ -1980,12 +2040,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
         if (IS_ERR(neigh)) {
                 dst_free(&rt->dst);
 
-                /* We are casting this because that is the return
-                 * value type.  But an errno encoded pointer is the
-                 * same regardless of the underlying pointer type,
-                 * and that's what we are returning.  So this is OK.
-                 */
-                return (struct rt6_info *) neigh;
+                return ERR_CAST(neigh);
         }
         rt->rt6i_nexthop = neigh;
 
@@ -1998,6 +2053,55 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
         return rt;
 }
 
+int ip6_route_get_saddr(struct net *net,
+                        struct rt6_info *rt,
+                        const struct in6_addr *daddr,
+                        unsigned int prefs,
+                        struct in6_addr *saddr)
+{
+        struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
+        int err = 0;
+        if (rt->rt6i_prefsrc.plen)
+                ipv6_addr_copy(saddr, &rt->rt6i_prefsrc.addr);
+        else
+                err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
+                                         daddr, prefs, saddr);
+        return err;
+}
+
+/* remove deleted ip from prefsrc entries */
+struct arg_dev_net_ip {
+        struct net_device *dev;
+        struct net *net;
+        struct in6_addr *addr;
+};
+
+static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
+{
+        struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
+        struct net *net = ((struct arg_dev_net_ip *)arg)->net;
+        struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
+
+        if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
+            rt != net->ipv6.ip6_null_entry &&
+            ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
+                /* remove prefsrc entry */
+                rt->rt6i_prefsrc.plen = 0;
+        }
+        return 0;
+}
+
+void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
+{
+        struct net *net = dev_net(ifp->idev->dev);
+        struct arg_dev_net_ip adni = {
+                .dev = ifp->idev->dev,
+                .net = net,
+                .addr = &ifp->addr,
+        };
+        fib6_clean_all(net, fib6_remove_prefsrc, 0, &adni);
+}
+
 struct arg_dev_net {
         struct net_device *dev;
         struct net *net;
@@ -2144,6 +2248,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
                 nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen);
         }
 
+        if (tb[RTA_PREFSRC])
+                nla_memcpy(&cfg->fc_prefsrc, tb[RTA_PREFSRC], 16);
+
         if (tb[RTA_OIF])
                 cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);
 
@@ -2286,13 +2393,17 @@ static int rt6_fill_node(struct net *net,
 #endif
                         NLA_PUT_U32(skb, RTA_IIF, iif);
         } else if (dst) {
-                struct inet6_dev *idev = ip6_dst_idev(&rt->dst);
                 struct in6_addr saddr_buf;
-                if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
-                                       dst, 0, &saddr_buf) == 0)
+                if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0)
                         NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
         }
 
+        if (rt->rt6i_prefsrc.plen) {
+                struct in6_addr saddr_buf;
+                ipv6_addr_copy(&saddr_buf, &rt->rt6i_prefsrc.addr);
+                NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
+        }
+
         if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
                 goto nla_put_failure;
 
@@ -2346,7 +2457,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
         struct rt6_info *rt;
         struct sk_buff *skb;
         struct rtmsg *rtm;
-        struct flowi fl;
+        struct flowi6 fl6;
         int err, iif = 0;
 
         err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
@@ -2354,27 +2465,27 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
                 goto errout;
 
         err = -EINVAL;
-        memset(&fl, 0, sizeof(fl));
+        memset(&fl6, 0, sizeof(fl6));
 
         if (tb[RTA_SRC]) {
                 if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
                         goto errout;
 
-                ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC]));
+                ipv6_addr_copy(&fl6.saddr, nla_data(tb[RTA_SRC]));
         }
 
         if (tb[RTA_DST]) {
                 if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
                         goto errout;
 
-                ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST]));
+                ipv6_addr_copy(&fl6.daddr, nla_data(tb[RTA_DST]));
         }
 
         if (tb[RTA_IIF])
                 iif = nla_get_u32(tb[RTA_IIF]);
 
         if (tb[RTA_OIF])
-                fl.oif = nla_get_u32(tb[RTA_OIF]);
+                fl6.flowi6_oif = nla_get_u32(tb[RTA_OIF]);
 
         if (iif) {
                 struct net_device *dev;
@@ -2397,10 +2508,10 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
         skb_reset_mac_header(skb);
         skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));
 
-        rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl);
+        rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl6);
         skb_dst_set(skb, &rt->dst);
 
-        err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
+        err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
                             RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
                             nlh->nlmsg_seq, 0, 0, 0);
         if (err < 0) {
@@ -2557,14 +2668,16 @@ static
 int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
                               void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-        struct net *net = current->nsproxy->net_ns;
-        int delay = net->ipv6.sysctl.flush_delay;
-        if (write) {
-                proc_dointvec(ctl, write, buffer, lenp, ppos);
-                fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
-                return 0;
-        } else
+        struct net *net;
+        int delay;
+        if (!write)
                 return -EINVAL;
+
+        net = (struct net *)ctl->extra1;
+        delay = net->ipv6.sysctl.flush_delay;
+        proc_dointvec(ctl, write, buffer, lenp, ppos);
+        fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
+        return 0;
 }
 
 ctl_table ipv6_route_table_template[] = {
@@ -2651,6 +2764,7 @@ struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
 
         if (table) {
                 table[0].data = &net->ipv6.sysctl.flush_delay;
+                table[0].extra1 = net;
                 table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh;
                 table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
                 table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
@@ -2684,7 +2798,8 @@ static int __net_init ip6_route_net_init(struct net *net)
         net->ipv6.ip6_null_entry->dst.path =
                 (struct dst_entry *)net->ipv6.ip6_null_entry;
         net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-        dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255);
+        dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
+                         ip6_template_metrics, true);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
         net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
@@ -2695,7 +2810,8 @@ static int __net_init ip6_route_net_init(struct net *net)
         net->ipv6.ip6_prohibit_entry->dst.path =
                 (struct dst_entry *)net->ipv6.ip6_prohibit_entry;
         net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-        dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255);
+        dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
+                         ip6_template_metrics, true);
 
         net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
                                                sizeof(*net->ipv6.ip6_blk_hole_entry),
@@ -2705,7 +2821,8 @@ static int __net_init ip6_route_net_init(struct net *net)
         net->ipv6.ip6_blk_hole_entry->dst.path =
                 (struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
         net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
-        dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255);
+        dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
+                         ip6_template_metrics, true);
 #endif
 
         net->ipv6.sysctl.flush_delay = 0;