Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

1 files changed, 330 insertions, 309 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 01372dd74e38..7aa4c41a3bd9 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -43,7 +43,7 @@ static struct kmem_cache *fib6_node_kmem __read_mostly;
 struct fib6_cleaner {
 	struct fib6_walker w;
 	struct net *net;
-	int (*func)(struct rt6_info *, void *arg);
+	int (*func)(struct fib6_info *, void *arg);
 	int sernum;
 	void *arg;
 };
@@ -54,7 +54,7 @@ struct fib6_cleaner {
 #define FWS_INIT FWS_L
 #endif
 
-static struct rt6_info *fib6_find_prefix(struct net *net,
+static struct fib6_info *fib6_find_prefix(struct net *net,
 					 struct fib6_table *table,
 					 struct fib6_node *fn);
 static struct fib6_node *fib6_repair_tree(struct net *net,
@@ -105,13 +105,12 @@ enum {
 	FIB6_NO_SERNUM_CHANGE = 0,
 };
 
-void fib6_update_sernum(struct rt6_info *rt)
+void fib6_update_sernum(struct net *net, struct fib6_info *f6i)
 {
-	struct net *net = dev_net(rt->dst.dev);
 	struct fib6_node *fn;
 
-	fn = rcu_dereference_protected(rt->rt6i_node,
-			lockdep_is_held(&rt->rt6i_table->tb6_lock));
+	fn = rcu_dereference_protected(f6i->fib6_node,
+			lockdep_is_held(&f6i->fib6_table->tb6_lock));
 	if (fn)
 		fn->fn_sernum = fib6_new_sernum(net);
 }
@@ -146,6 +145,69 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
 	       addr[fn_bit >> 5];
 }
 
+struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
+{
+	struct fib6_info *f6i;
+
+	f6i = kzalloc(sizeof(*f6i), gfp_flags);
+	if (!f6i)
+		return NULL;
+
+	f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
+	if (!f6i->rt6i_pcpu) {
+		kfree(f6i);
+		return NULL;
+	}
+
+	INIT_LIST_HEAD(&f6i->fib6_siblings);
+	f6i->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
+
+	atomic_inc(&f6i->fib6_ref);
+
+	return f6i;
+}
+
+void fib6_info_destroy(struct fib6_info *f6i)
+{
+	struct rt6_exception_bucket *bucket;
+	struct dst_metrics *m;
+
+	WARN_ON(f6i->fib6_node);
+
+	bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1);
+	if (bucket) {
+		f6i->rt6i_exception_bucket = NULL;
+		kfree(bucket);
+	}
+
+	if (f6i->rt6i_pcpu) {
+		int cpu;
+
+		for_each_possible_cpu(cpu) {
+			struct rt6_info **ppcpu_rt;
+			struct rt6_info *pcpu_rt;
+
+			ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
+			pcpu_rt = *ppcpu_rt;
+			if (pcpu_rt) {
+				dst_dev_put(&pcpu_rt->dst);
+				dst_release(&pcpu_rt->dst);
+				*ppcpu_rt = NULL;
+			}
+		}
+	}
+
+	if (f6i->fib6_nh.nh_dev)
+		dev_put(f6i->fib6_nh.nh_dev);
+
+	m = f6i->fib6_metrics;
+	if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
+		kfree(m);
+
+	kfree(f6i);
+}
+EXPORT_SYMBOL_GPL(fib6_info_destroy);
+
 static struct fib6_node *node_alloc(struct net *net)
 {
 	struct fib6_node *fn;
@@ -176,28 +238,6 @@ static void node_free(struct net *net, struct fib6_node *fn)
 	net->ipv6.rt6_stats->fib_nodes--;
 }
 
-void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
-{
-	int cpu;
-
-	if (!non_pcpu_rt->rt6i_pcpu)
-		return;
-
-	for_each_possible_cpu(cpu) {
-		struct rt6_info **ppcpu_rt;
-		struct rt6_info *pcpu_rt;
-
-		ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
-		pcpu_rt = *ppcpu_rt;
-		if (pcpu_rt) {
-			dst_dev_put(&pcpu_rt->dst);
-			dst_release(&pcpu_rt->dst);
-			*ppcpu_rt = NULL;
-		}
-	}
-}
-EXPORT_SYMBOL_GPL(rt6_free_pcpu);
-
 static void fib6_free_table(struct fib6_table *table)
 {
 	inetpeer_invalidate_tree(&table->tb6_peers);
@@ -232,7 +272,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 	if (table) {
 		table->tb6_id = id;
 		rcu_assign_pointer(table->tb6_root.leaf,
-				   net->ipv6.ip6_null_entry);
+				   net->ipv6.fib6_null_entry);
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 		inet_peer_base_init(&table->tb6_peers);
 	}
@@ -314,6 +354,13 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
 	return &rt->dst;
 }
 
+/* called with rcu lock held; no reference taken on fib6_info */
+struct fib6_info *fib6_lookup(struct net *net, int oif, struct flowi6 *fl6,
+			      int flags)
+{
+	return fib6_table_lookup(net, net->ipv6.fib6_main_tbl, oif, fl6, flags);
+}
+
 static void __net_init fib6_tables_init(struct net *net)
 {
 	fib6_link_table(net, net->ipv6.fib6_main_tbl);
@@ -340,7 +387,7 @@ unsigned int fib6_tables_seq_read(struct net *net)
 
 static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
 				    enum fib_event_type event_type,
-				    struct rt6_info *rt)
+				    struct fib6_info *rt)
 {
 	struct fib6_entry_notifier_info info = {
 		.rt = rt,
@@ -351,7 +398,7 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
 
 static int call_fib6_entry_notifiers(struct net *net,
 				     enum fib_event_type event_type,
-				     struct rt6_info *rt,
+				     struct fib6_info *rt,
 				     struct netlink_ext_ack *extack)
 {
 	struct fib6_entry_notifier_info info = {
@@ -359,7 +406,7 @@ static int call_fib6_entry_notifiers(struct net *net,
 		.rt = rt,
 	};
 
-	rt->rt6i_table->fib_seq++;
+	rt->fib6_table->fib_seq++;
 	return call_fib6_notifiers(net, event_type, &info.info);
 }
 
@@ -368,16 +415,16 @@ struct fib6_dump_arg {
 	struct notifier_block *nb;
 };
 
-static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg)
+static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
 {
-	if (rt == arg->net->ipv6.ip6_null_entry)
+	if (rt == arg->net->ipv6.fib6_null_entry)
 		return;
 	call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt);
 }
 
 static int fib6_node_dump(struct fib6_walker *w)
 {
-	struct rt6_info *rt;
+	struct fib6_info *rt;
 
 	for_each_fib6_walker_rt(w)
 		fib6_rt_dump(rt, w->args);
@@ -426,7 +473,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb)
 static int fib6_dump_node(struct fib6_walker *w)
 {
 	int res;
-	struct rt6_info *rt;
+	struct fib6_info *rt;
 
 	for_each_fib6_walker_rt(w) {
 		res = rt6_dump_route(rt, w->args);
@@ -441,10 +488,10 @@ static int fib6_dump_node(struct fib6_walker *w)
 		 * last sibling of this route (no need to dump the
 		 * sibling routes again)
 		 */
-		if (rt->rt6i_nsiblings)
-			rt = list_last_entry(&rt->rt6i_siblings,
-					     struct rt6_info,
-					     rt6i_siblings);
+		if (rt->fib6_nsiblings)
+			rt = list_last_entry(&rt->fib6_siblings,
+					     struct fib6_info,
+					     fib6_siblings);
 	}
 	w->leaf = NULL;
 	return 0;
@@ -579,6 +626,24 @@ out:
 	return res;
 }
 
+void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val)
+{
+	if (!f6i)
+		return;
+
+	if (f6i->fib6_metrics == &dst_default_metrics) {
+		struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC);
+
+		if (!p)
+			return;
+
+		refcount_set(&p->refcnt, 1);
+		f6i->fib6_metrics = p;
+	}
+
+	f6i->fib6_metrics->metrics[metric - 1] = val;
+}
+
 /*
  *	Routing Table
  *
@@ -608,7 +673,7 @@ static struct fib6_node *fib6_add_1(struct net *net,
 	fn = root;
 
 	do {
-		struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+		struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
 					    lockdep_is_held(&table->tb6_lock));
 		key = (struct rt6key *)((u8 *)leaf + offset);
 
@@ -637,11 +702,11 @@ static struct fib6_node *fib6_add_1(struct net *net,
 			/* clean up an intermediate node */
 			if (!(fn->fn_flags & RTN_RTINFO)) {
 				RCU_INIT_POINTER(fn->leaf, NULL);
-				rt6_release(leaf);
+				fib6_info_release(leaf);
 			/* remove null_entry in the root node */
 			} else if (fn->fn_flags & RTN_TL_ROOT &&
 				   rcu_access_pointer(fn->leaf) ==
-				   net->ipv6.ip6_null_entry) {
+				   net->ipv6.fib6_null_entry) {
 				RCU_INIT_POINTER(fn->leaf, NULL);
 			}
 
@@ -750,7 +815,7 @@ insert_above:
 		RCU_INIT_POINTER(in->parent, pn);
 		in->leaf = fn->leaf;
 		atomic_inc(&rcu_dereference_protected(in->leaf,
-				lockdep_is_held(&table->tb6_lock))->rt6i_ref);
+				lockdep_is_held(&table->tb6_lock))->fib6_ref);
 
 		/* update parent pointer */
 		if (dir)
@@ -802,44 +867,37 @@ insert_above:
 	return ln;
 }
 
-static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
-{
-	int i;
-
-	for (i = 0; i < RTAX_MAX; i++) {
-		if (test_bit(i, mxc->mx_valid))
-			mp[i] = mxc->mx[i];
-	}
-}
-
-static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
+static void fib6_drop_pcpu_from(struct fib6_info *f6i,
+				const struct fib6_table *table)
 {
-	if (!mxc->mx)
-		return 0;
-
-	if (dst->flags & DST_HOST) {
-		u32 *mp = dst_metrics_write_ptr(dst);
+	int cpu;
 
-		if (unlikely(!mp))
-			return -ENOMEM;
+	/* release the reference to this fib entry from
+	 * all of its cached pcpu routes
+	 */
+	for_each_possible_cpu(cpu) {
+		struct rt6_info **ppcpu_rt;
+		struct rt6_info *pcpu_rt;
 
-		fib6_copy_metrics(mp, mxc);
-	} else {
-		dst_init_metrics(dst, mxc->mx, false);
+		ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
+		pcpu_rt = *ppcpu_rt;
+		if (pcpu_rt) {
+			struct fib6_info *from;
 
-		/* We've stolen mx now. */
-		mxc->mx = NULL;
+			from = rcu_dereference_protected(pcpu_rt->from,
+					     lockdep_is_held(&table->tb6_lock));
+			rcu_assign_pointer(pcpu_rt->from, NULL);
+			fib6_info_release(from);
+		}
 	}
-
-	return 0;
 }
 
-static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
+static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 			  struct net *net)
 {
-	struct fib6_table *table = rt->rt6i_table;
+	struct fib6_table *table = rt->fib6_table;
 
-	if (atomic_read(&rt->rt6i_ref) != 1) {
+	if (atomic_read(&rt->fib6_ref) != 1) {
 		/* This route is used as dummy address holder in some split
 		 * nodes. It is not leaked, but it still holds other resources,
 		 * which must be released in time. So, scan ascendant nodes
@@ -847,18 +905,22 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
 		 * to still alive ones.
 		 */
 		while (fn) {
-			struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
+			struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
 					    lockdep_is_held(&table->tb6_lock));
-			struct rt6_info *new_leaf;
+			struct fib6_info *new_leaf;
 			if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) {
 				new_leaf = fib6_find_prefix(net, table, fn);
-				atomic_inc(&new_leaf->rt6i_ref);
+				atomic_inc(&new_leaf->fib6_ref);
+
 				rcu_assign_pointer(fn->leaf, new_leaf);
-				rt6_release(rt);
+				fib6_info_release(rt);
 			}
 			fn = rcu_dereference_protected(fn->parent,
 				    lockdep_is_held(&table->tb6_lock));
 		}
+
+		if (rt->rt6i_pcpu)
+			fib6_drop_pcpu_from(rt, table);
 	}
 }
 
@@ -866,37 +928,37 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
  *	Insert routing information in a node.
  */
 
-static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
-			    struct nl_info *info, struct mx6_config *mxc,
+static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
+			    struct nl_info *info,
 			    struct netlink_ext_ack *extack)
 {
-	struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
-				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
-	struct rt6_info *iter = NULL;
-	struct rt6_info __rcu **ins;
-	struct rt6_info __rcu **fallback_ins = NULL;
+	struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
+	struct fib6_info *iter = NULL, *match = NULL;
+	struct fib6_info __rcu **ins;
 	int replace = (info->nlh &&
 		       (info->nlh->nlmsg_flags & NLM_F_REPLACE));
+	int append = (info->nlh &&
+		       (info->nlh->nlmsg_flags & NLM_F_APPEND));
 	int add = (!info->nlh ||
 		   (info->nlh->nlmsg_flags & NLM_F_CREATE));
 	int found = 0;
-	bool rt_can_ecmp = rt6_qualify_for_ecmp(rt);
 	u16 nlflags = NLM_F_EXCL;
 	int err;
 
-	if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND))
+	if (append)
 		nlflags |= NLM_F_APPEND;
 
 	ins = &fn->leaf;
 
 	for (iter = leaf; iter;
-	     iter = rcu_dereference_protected(iter->rt6_next,
-				lockdep_is_held(&rt->rt6i_table->tb6_lock))) {
+	     iter = rcu_dereference_protected(iter->fib6_next,
+				lockdep_is_held(&rt->fib6_table->tb6_lock))) {
 		/*
 		 *	Search for duplicates
 		 */
 
-		if (iter->rt6i_metric == rt->rt6i_metric) {
+		if (iter->fib6_metric == rt->fib6_metric) {
 			/*
 			 *	Same priority level
 			 */
@@ -906,56 +968,32 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 
 			nlflags &= ~NLM_F_EXCL;
 			if (replace) {
-				if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
-					found++;
-					break;
-				}
-				if (rt_can_ecmp)
-					fallback_ins = fallback_ins ?: ins;
-				goto next_iter;
+				found++;
+				break;
 			}
 
 			if (rt6_duplicate_nexthop(iter, rt)) {
-				if (rt->rt6i_nsiblings)
-					rt->rt6i_nsiblings = 0;
-				if (!(iter->rt6i_flags & RTF_EXPIRES))
+				if (rt->fib6_nsiblings)
+					rt->fib6_nsiblings = 0;
+				if (!(iter->fib6_flags & RTF_EXPIRES))
 					return -EEXIST;
-				if (!(rt->rt6i_flags & RTF_EXPIRES))
-					rt6_clean_expires(iter);
+				if (!(rt->fib6_flags & RTF_EXPIRES))
+					fib6_clean_expires(iter);
 				else
-					rt6_set_expires(iter, rt->dst.expires);
-				iter->rt6i_pmtu = rt->rt6i_pmtu;
+					fib6_set_expires(iter, rt->expires);
+				fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
 				return -EEXIST;
 			}
-			/* If we have the same destination and the same metric,
-			 * but not the same gateway, then the route we try to
-			 * add is sibling to this route, increment our counter
-			 * of siblings, and later we will add our route to the
-			 * list.
-			 * Only static routes (which don't have flag
-			 * RTF_EXPIRES) are used for ECMPv6.
-			 *
-			 * To avoid long list, we only had siblings if the
-			 * route have a gateway.
-			 */
-			if (rt_can_ecmp &&
-			    rt6_qualify_for_ecmp(iter))
-				rt->rt6i_nsiblings++;
+
+			/* first route that matches */
+			if (!match)
+				match = iter;
 		}
 
-		if (iter->rt6i_metric > rt->rt6i_metric)
+		if (iter->fib6_metric > rt->fib6_metric)
 			break;
 
-next_iter:
-		ins = &iter->rt6_next;
-	}
-
-	if (fallback_ins && !found) {
-		/* No ECMP-able route found, replace first non-ECMP one */
-		ins = fallback_ins;
-		iter = rcu_dereference_protected(*ins,
-				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
-		found++;
+		ins = &iter->fib6_next;
 	}
 
 	/* Reset round-robin state, if necessary */
@@ -963,59 +1001,56 @@ next_iter:
 		fn->rr_ptr = NULL;
 
 	/* Link this route to others same route. */
-	if (rt->rt6i_nsiblings) {
-		unsigned int rt6i_nsiblings;
-		struct rt6_info *sibling, *temp_sibling;
-
-		/* Find the first route that have the same metric */
-		sibling = leaf;
-		while (sibling) {
-			if (sibling->rt6i_metric == rt->rt6i_metric &&
-			    rt6_qualify_for_ecmp(sibling)) {
-				list_add_tail(&rt->rt6i_siblings,
-					      &sibling->rt6i_siblings);
-				break;
-			}
-			sibling = rcu_dereference_protected(sibling->rt6_next,
-				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
+	if (append && match) {
+		struct fib6_info *sibling, *temp_sibling;
+
+		if (rt->fib6_flags & RTF_REJECT) {
+			NL_SET_ERR_MSG(extack,
+				       "Can not append a REJECT route");
+			return -EINVAL;
+		} else if (match->fib6_flags & RTF_REJECT) {
+			NL_SET_ERR_MSG(extack,
+				       "Can not append to a REJECT route");
+			return -EINVAL;
 		}
+		rt->fib6_nsiblings = match->fib6_nsiblings;
+		list_add_tail(&rt->fib6_siblings, &match->fib6_siblings);
+		match->fib6_nsiblings++;
+
 		/* For each sibling in the list, increment the counter of
 		 * siblings. BUG() if counters does not match, list of siblings
 		 * is broken!
 		 */
-		rt6i_nsiblings = 0;
 		list_for_each_entry_safe(sibling, temp_sibling,
-					 &rt->rt6i_siblings, rt6i_siblings) {
-			sibling->rt6i_nsiblings++;
-			BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings);
-			rt6i_nsiblings++;
+					 &match->fib6_siblings, fib6_siblings) {
+			sibling->fib6_nsiblings++;
+			BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings);
 		}
-		BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings);
-		rt6_multipath_rebalance(temp_sibling);
+
+		rt6_multipath_rebalance(match);
 	}
 
 	/*
 	 *	insert node
 	 */
 	if (!replace) {
+		enum fib_event_type event;
+
 		if (!add)
 			pr_warn("NLM_F_CREATE should be set when creating new route\n");
 
 add:
 		nlflags |= NLM_F_CREATE;
-		err = fib6_commit_metrics(&rt->dst, mxc);
-		if (err)
-			return err;
 
-		err = call_fib6_entry_notifiers(info->nl_net,
-						FIB_EVENT_ENTRY_ADD,
-						rt, extack);
+		event = append ? FIB_EVENT_ENTRY_APPEND : FIB_EVENT_ENTRY_ADD;
+		err = call_fib6_entry_notifiers(info->nl_net, event, rt,
+						extack);
 		if (err)
 			return err;
 
-		rcu_assign_pointer(rt->rt6_next, iter);
-		atomic_inc(&rt->rt6i_ref);
-		rcu_assign_pointer(rt->rt6i_node, fn);
+		rcu_assign_pointer(rt->fib6_next, iter);
+		atomic_inc(&rt->fib6_ref);
+		rcu_assign_pointer(rt->fib6_node, fn);
 		rcu_assign_pointer(*ins, rt);
 		if (!info->skip_notify)
 			inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags);
@@ -1027,7 +1062,7 @@ add:
 		}
 
 	} else {
-		int nsiblings;
+		struct fib6_info *tmp;
 
 		if (!found) {
 			if (add)
@@ -1036,67 +1071,72 @@ add:
 			return -ENOENT;
 		}
 
-		err = fib6_commit_metrics(&rt->dst, mxc);
-		if (err)
-			return err;
-
 		err = call_fib6_entry_notifiers(info->nl_net,
 						FIB_EVENT_ENTRY_REPLACE,
 						rt, extack);
 		if (err)
 			return err;
 
-		atomic_inc(&rt->rt6i_ref);
-		rcu_assign_pointer(rt->rt6i_node, fn);
-		rt->rt6_next = iter->rt6_next;
+		/* if route being replaced has siblings, set tmp to
+		 * last one, otherwise tmp is current route. this is
+		 * used to set fib6_next for new route
+		 */
+		if (iter->fib6_nsiblings)
+			tmp = list_last_entry(&iter->fib6_siblings,
+					      struct fib6_info,
+					      fib6_siblings);
+		else
+			tmp = iter;
+
+		/* insert new route */
+		atomic_inc(&rt->fib6_ref);
+		rcu_assign_pointer(rt->fib6_node, fn);
+		rt->fib6_next = tmp->fib6_next;
 		rcu_assign_pointer(*ins, rt);
+
 		if (!info->skip_notify)
 			inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE);
 		if (!(fn->fn_flags & RTN_RTINFO)) {
 			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
 			fn->fn_flags |= RTN_RTINFO;
 		}
-		nsiblings = iter->rt6i_nsiblings;
-		iter->rt6i_node = NULL;
-		fib6_purge_rt(iter, fn, info->nl_net);
-		if (rcu_access_pointer(fn->rr_ptr) == iter)
-			fn->rr_ptr = NULL;
-		rt6_release(iter);
 
-		if (nsiblings) {
+		/* delete old route */
+		rt = iter;
+
+		if (rt->fib6_nsiblings) {
+			struct fib6_info *tmp;
+
 			/* Replacing an ECMP route, remove all siblings */
-			ins = &rt->rt6_next;
-			iter = rcu_dereference_protected(*ins,
-				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
-			while (iter) {
-				if (iter->rt6i_metric > rt->rt6i_metric)
-					break;
-				if (rt6_qualify_for_ecmp(iter)) {
-					*ins = iter->rt6_next;
-					iter->rt6i_node = NULL;
-					fib6_purge_rt(iter, fn, info->nl_net);
-					if (rcu_access_pointer(fn->rr_ptr) == iter)
-						fn->rr_ptr = NULL;
-					rt6_release(iter);
-					nsiblings--;
-					info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
-				} else {
-					ins = &iter->rt6_next;
-				}
-				iter = rcu_dereference_protected(*ins,
-					lockdep_is_held(&rt->rt6i_table->tb6_lock));
+			list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings,
+						 fib6_siblings) {
+				iter->fib6_node = NULL;
+				fib6_purge_rt(iter, fn, info->nl_net);
+				if (rcu_access_pointer(fn->rr_ptr) == iter)
+					fn->rr_ptr = NULL;
+				fib6_info_release(iter);
+
+				rt->fib6_nsiblings--;
+				info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
 			}
-			WARN_ON(nsiblings != 0);
 		}
+
+		WARN_ON(rt->fib6_nsiblings != 0);
+
+		rt->fib6_node = NULL;
+		fib6_purge_rt(rt, fn, info->nl_net);
+		if (rcu_access_pointer(fn->rr_ptr) == rt)
+			fn->rr_ptr = NULL;
+		fib6_info_release(rt);
 	}
 
 	return 0;
 }
 
-static void fib6_start_gc(struct net *net, struct rt6_info *rt)
+static void fib6_start_gc(struct net *net, struct fib6_info *rt)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
-	    (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
+	    (rt->fib6_flags & RTF_EXPIRES))
 		mod_timer(&net->ipv6.ip6_fib_timer,
 			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
 }
@@ -1108,22 +1148,22 @@ void fib6_force_start_gc(struct net *net)
 			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
 }
 
-static void __fib6_update_sernum_upto_root(struct rt6_info *rt,
+static void __fib6_update_sernum_upto_root(struct fib6_info *rt,
 					   int sernum)
 {
-	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
-				lockdep_is_held(&rt->rt6i_table->tb6_lock));
+	struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node,
+				lockdep_is_held(&rt->fib6_table->tb6_lock));
 
 	/* paired with smp_rmb() in rt6_get_cookie_safe() */
 	smp_wmb();
 	while (fn) {
 		fn->fn_sernum = sernum;
 		fn = rcu_dereference_protected(fn->parent,
-				lockdep_is_held(&rt->rt6i_table->tb6_lock));
+				lockdep_is_held(&rt->fib6_table->tb6_lock));
 	}
 }
 
-void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
+void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt)
 {
 	__fib6_update_sernum_upto_root(rt, fib6_new_sernum(net));
 }
@@ -1135,22 +1175,16 @@ void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
  *	Need to own table->tb6_lock
  */
 
-int fib6_add(struct fib6_node *root, struct rt6_info *rt,
-	     struct nl_info *info, struct mx6_config *mxc,
-	     struct netlink_ext_ack *extack)
+int fib6_add(struct fib6_node *root, struct fib6_info *rt,
+	     struct nl_info *info, struct netlink_ext_ack *extack)
 {
-	struct fib6_table *table = rt->rt6i_table;
+	struct fib6_table *table = rt->fib6_table;
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
 	int allow_create = 1;
 	int replace_required = 0;
 	int sernum = fib6_new_sernum(info->nl_net);
 
-	if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
-		return -EINVAL;
-	if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE))
-		return -EINVAL;
-
 	if (info->nlh) {
 		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
 			allow_create = 0;
@@ -1161,8 +1195,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 		pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n");
 
 	fn = fib6_add_1(info->nl_net, table, root,
-			&rt->rt6i_dst.addr, rt->rt6i_dst.plen,
-			offsetof(struct rt6_info, rt6i_dst), allow_create,
+			&rt->fib6_dst.addr, rt->fib6_dst.plen,
+			offsetof(struct fib6_info, fib6_dst), allow_create,
 			replace_required, extack);
 	if (IS_ERR(fn)) {
 		err = PTR_ERR(fn);
@@ -1173,7 +1207,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	pn = fn;
 
 #ifdef CONFIG_IPV6_SUBTREES
-	if (rt->rt6i_src.plen) {
+	if (rt->fib6_src.plen) {
 		struct fib6_node *sn;
 
 		if (!rcu_access_pointer(fn->subtree)) {
@@ -1194,16 +1228,16 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			if (!sfn)
 				goto failure;
 
-			atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
+			atomic_inc(&info->nl_net->ipv6.fib6_null_entry->fib6_ref);
 			rcu_assign_pointer(sfn->leaf,
-					   info->nl_net->ipv6.ip6_null_entry);
+					   info->nl_net->ipv6.fib6_null_entry);
 			sfn->fn_flags = RTN_ROOT;
 
 			/* Now add the first leaf node to new subtree */
 
 			sn = fib6_add_1(info->nl_net, table, sfn,
-					&rt->rt6i_src.addr, rt->rt6i_src.plen,
-					offsetof(struct rt6_info, rt6i_src),
+					&rt->fib6_src.addr, rt->fib6_src.plen,
+					offsetof(struct fib6_info, fib6_src),
 					allow_create, replace_required, extack);
 
 			if (IS_ERR(sn)) {
@@ -1221,8 +1255,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			rcu_assign_pointer(fn->subtree, sfn);
 		} else {
 			sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn),
-					&rt->rt6i_src.addr, rt->rt6i_src.plen,
-					offsetof(struct rt6_info, rt6i_src),
+					&rt->fib6_src.addr, rt->fib6_src.plen,
+					offsetof(struct fib6_info, fib6_src),
 					allow_create, replace_required, extack);
 
 			if (IS_ERR(sn)) {
@@ -1235,9 +1269,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 			if (fn->fn_flags & RTN_TL_ROOT) {
 				/* put back null_entry for root node */
 				rcu_assign_pointer(fn->leaf,
-					    info->nl_net->ipv6.ip6_null_entry);
+					    info->nl_net->ipv6.fib6_null_entry);
 			} else {
-				atomic_inc(&rt->rt6i_ref);
+				atomic_inc(&rt->fib6_ref);
 				rcu_assign_pointer(fn->leaf, rt);
 			}
 		}
@@ -1245,7 +1279,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
 	}
 #endif
 
-	err = fib6_add_rt2node(fn, rt, info, mxc, extack);
+	err = fib6_add_rt2node(fn, rt, info, extack);
 	if (!err) {
 		__fib6_update_sernum_upto_root(rt, sernum);
 		fib6_start_gc(info->nl_net, rt);
@@ -1259,13 +1293,13 @@ out:
 		 * super-tree leaf node we have to find a new one for it.
 		 */
 		if (pn != fn) {
-			struct rt6_info *pn_leaf =
+			struct fib6_info *pn_leaf =
 				rcu_dereference_protected(pn->leaf,
 				    lockdep_is_held(&table->tb6_lock));
 			if (pn_leaf == rt) {
 				pn_leaf = NULL;
 				RCU_INIT_POINTER(pn->leaf, NULL);
-				atomic_dec(&rt->rt6i_ref);
+				fib6_info_release(rt);
 			}
 			if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
 				pn_leaf = fib6_find_prefix(info->nl_net, table,
@@ -1274,10 +1308,10 @@ out:
 				if (!pn_leaf) {
 					WARN_ON(!pn_leaf);
 					pn_leaf =
-					    info->nl_net->ipv6.ip6_null_entry;
+					    info->nl_net->ipv6.fib6_null_entry;
 				}
 #endif
-				atomic_inc(&pn_leaf->rt6i_ref);
+				fib6_info_hold(pn_leaf);
 				rcu_assign_pointer(pn->leaf, pn_leaf);
 			}
 		}
@@ -1299,10 +1333,6 @@ failure:
 	     (fn->fn_flags & RTN_TL_ROOT &&
 	      !rcu_access_pointer(fn->leaf))))
 		fib6_repair_tree(info->nl_net, table, fn);
-	/* Always release dst as dst->__refcnt is guaranteed
-	 * to be taken before entering this function
-	 */
-	dst_release_immediate(&rt->dst);
 	return err;
 }
 
@@ -1312,12 +1342,12 @@ failure:
  */
 
 struct lookup_args {
-	int			offset;		/* key offset on rt6_info	*/
+	int			offset;		/* key offset on fib6_info */
 	const struct in6_addr	*addr;		/* search key			*/
 };
 
-static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
-				       struct lookup_args *args)
+static struct fib6_node *fib6_node_lookup_1(struct fib6_node *root,
+					    struct lookup_args *args)
 {
 	struct fib6_node *fn;
 	__be32 dir;
@@ -1350,7 +1380,7 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 		struct fib6_node *subtree = FIB6_SUBTREE(fn);
 
 		if (subtree || fn->fn_flags & RTN_RTINFO) {
-			struct rt6_info *leaf = rcu_dereference(fn->leaf);
+			struct fib6_info *leaf = rcu_dereference(fn->leaf);
 			struct rt6key *key;
 
 			if (!leaf)
@@ -1362,7 +1392,8 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
 #ifdef CONFIG_IPV6_SUBTREES
 				if (subtree) {
 					struct fib6_node *sfn;
-					sfn = fib6_lookup_1(subtree, args + 1);
+					sfn = fib6_node_lookup_1(subtree,
+								 args + 1);
 					if (!sfn)
 						goto backtrack;
 					fn = sfn;
@@ -1384,18 +1415,19 @@ backtrack:
 
 /* called with rcu_read_lock() held
  */
-struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *daddr,
-			      const struct in6_addr *saddr)
+struct fib6_node *fib6_node_lookup(struct fib6_node *root,
+				   const struct in6_addr *daddr,
+				   const struct in6_addr *saddr)
 {
 	struct fib6_node *fn;
 	struct lookup_args args[] = {
 		{
-			.offset = offsetof(struct rt6_info, rt6i_dst),
+			.offset = offsetof(struct fib6_info, fib6_dst),
 			.addr = daddr,
 		},
 #ifdef CONFIG_IPV6_SUBTREES
 		{
-			.offset = offsetof(struct rt6_info, rt6i_src),
+			.offset = offsetof(struct fib6_info, fib6_src),
 			.addr = saddr,
 		},
 #endif
@@ -1404,7 +1436,7 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad
 		}
 	};
 
-	fn = fib6_lookup_1(root, daddr ? args : args + 1);
+	fn = fib6_node_lookup_1(root, daddr ? args : args + 1);
 	if (!fn || fn->fn_flags & RTN_TL_ROOT)
 		fn = root;
 
@@ -1431,7 +1463,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root,
 	struct fib6_node *fn, *prev = NULL;
 
 	for (fn = root; fn ; ) {
-		struct rt6_info *leaf = rcu_dereference(fn->leaf);
+		struct fib6_info *leaf = rcu_dereference(fn->leaf);
 		struct rt6key *key;
 
 		/* This node is being deleted */
@@ -1480,7 +1512,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
 	struct fib6_node *fn;
 
 	fn = fib6_locate_1(root, daddr, dst_len,
-			   offsetof(struct rt6_info, rt6i_dst),
+			   offsetof(struct fib6_info, fib6_dst),
 			   exact_match);
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1491,7 +1523,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
 
 			if (subtree) {
 				fn = fib6_locate_1(subtree, saddr, src_len,
-					   offsetof(struct rt6_info, rt6i_src),
+					   offsetof(struct fib6_info, fib6_src),
 					   exact_match);
 			}
 		}
@@ -1510,14 +1542,14 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
  *
  */
 
-static struct rt6_info *fib6_find_prefix(struct net *net,
+static struct fib6_info *fib6_find_prefix(struct net *net,
 					 struct fib6_table *table,
 					 struct fib6_node *fn)
 {
 	struct fib6_node *child_left, *child_right;
 
 	if (fn->fn_flags & RTN_ROOT)
-		return net->ipv6.ip6_null_entry;
+		return net->ipv6.fib6_null_entry;
 
 	while (fn) {
 		child_left = rcu_dereference_protected(fn->left,
@@ -1554,7 +1586,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 
 	/* Set fn->leaf to null_entry for root node. */
 	if (fn->fn_flags & RTN_TL_ROOT) {
-		rcu_assign_pointer(fn->leaf, net->ipv6.ip6_null_entry);
+		rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry);
 		return fn;
 	}
 
@@ -1569,11 +1601,11 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 					    lockdep_is_held(&table->tb6_lock));
 		struct fib6_node *pn_l = rcu_dereference_protected(pn->left,
 					    lockdep_is_held(&table->tb6_lock));
-		struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
+		struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
 					    lockdep_is_held(&table->tb6_lock));
-		struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
+		struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
 					    lockdep_is_held(&table->tb6_lock));
-		struct rt6_info *new_fn_leaf;
+		struct fib6_info *new_fn_leaf;
 
 		RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
 		iter++;
@@ -1599,10 +1631,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 #if RT6_DEBUG >= 2
 			if (!new_fn_leaf) {
 				WARN_ON(!new_fn_leaf);
-				new_fn_leaf = net->ipv6.ip6_null_entry;
+				new_fn_leaf = net->ipv6.fib6_null_entry;
 			}
 #endif
-			atomic_inc(&new_fn_leaf->rt6i_ref);
+			fib6_info_hold(new_fn_leaf);
 			rcu_assign_pointer(fn->leaf, new_fn_leaf);
 			return pn;
 		}
@@ -1658,26 +1690,24 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 			return pn;
 
 		RCU_INIT_POINTER(pn->leaf, NULL);
-		rt6_release(pn_leaf);
+		fib6_info_release(pn_leaf);
 		fn = pn;
 	}
 }
 
 static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
-			   struct rt6_info __rcu **rtp, struct nl_info *info)
+			   struct fib6_info __rcu **rtp, struct nl_info *info)
 {
 	struct fib6_walker *w;
-	struct rt6_info *rt = rcu_dereference_protected(*rtp,
+	struct fib6_info *rt = rcu_dereference_protected(*rtp,
 				    lockdep_is_held(&table->tb6_lock));
 	struct net *net = info->nl_net;
 
 	RT6_TRACE("fib6_del_route\n");
 
-	WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
-
 	/* Unlink it */
-	*rtp = rt->rt6_next;
-	rt->rt6i_node = NULL;
+	*rtp = rt->fib6_next;
+	rt->fib6_node = NULL;
 	net->ipv6.rt6_stats->fib_rt_entries--;
 	net->ipv6.rt6_stats->fib_discarded_routes++;
 
@@ -1689,14 +1719,14 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 		fn->rr_ptr = NULL;
 
 	/* Remove this entry from other siblings */
-	if (rt->rt6i_nsiblings) {
-		struct rt6_info *sibling, *next_sibling;
+	if (rt->fib6_nsiblings) {
+		struct fib6_info *sibling, *next_sibling;
 
 		list_for_each_entry_safe(sibling, next_sibling,
-					 &rt->rt6i_siblings, rt6i_siblings)
-			sibling->rt6i_nsiblings--;
-		rt->rt6i_nsiblings = 0;
-		list_del_init(&rt->rt6i_siblings);
+					 &rt->fib6_siblings, fib6_siblings)
+			sibling->fib6_nsiblings--;
+		rt->fib6_nsiblings = 0;
+		list_del_init(&rt->fib6_siblings);
 		rt6_multipath_rebalance(next_sibling);
 	}
 
@@ -1705,7 +1735,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	FOR_WALKERS(net, w) {
 		if (w->state == FWS_C && w->leaf == rt) {
 			RT6_TRACE("walker %p adjusted by delroute\n", w);
-			w->leaf = rcu_dereference_protected(rt->rt6_next,
+			w->leaf = rcu_dereference_protected(rt->fib6_next,
 					    lockdep_is_held(&table->tb6_lock));
 			if (!w->leaf)
 				w->state = FWS_U;
@@ -1730,46 +1760,36 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
 	if (!info->skip_notify)
 		inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
-	rt6_release(rt);
+	fib6_info_release(rt);
 }
 
 /* Need to own table->tb6_lock */
-int fib6_del(struct rt6_info *rt, struct nl_info *info)
+int fib6_del(struct fib6_info *rt, struct nl_info *info)
 {
-	struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
-				    lockdep_is_held(&rt->rt6i_table->tb6_lock));
-	struct fib6_table *table = rt->rt6i_table;
+	struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node,
+				    lockdep_is_held(&rt->fib6_table->tb6_lock));
+	struct fib6_table *table = rt->fib6_table;
 	struct net *net = info->nl_net;
-	struct rt6_info __rcu **rtp;
-	struct rt6_info __rcu **rtp_next;
+	struct fib6_info __rcu **rtp;
+	struct fib6_info __rcu **rtp_next;
 
-#if RT6_DEBUG >= 2
-	if (rt->dst.obsolete > 0) {
-		WARN_ON(fn);
-		return -ENOENT;
-	}
-#endif
-	if (!fn || rt == net->ipv6.ip6_null_entry)
+	if (!fn || rt == net->ipv6.fib6_null_entry)
 		return -ENOENT;
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
 
-	/* remove cached dst from exception table */
-	if (rt->rt6i_flags & RTF_CACHE)
-		return rt6_remove_exception_rt(rt);
-
 	/*
 	 *	Walk the leaf entries looking for ourself
 	 */
 
 	for (rtp = &fn->leaf; *rtp; rtp = rtp_next) {
-		struct rt6_info *cur = rcu_dereference_protected(*rtp,
+		struct fib6_info *cur = rcu_dereference_protected(*rtp,
 					lockdep_is_held(&table->tb6_lock));
 		if (rt == cur) {
 			fib6_del_route(table, fn, rtp, info);
 			return 0;
 		}
-		rtp_next = &cur->rt6_next;
+		rtp_next = &cur->fib6_next;
 	}
 	return -ENOENT;
 }
@@ -1907,7 +1927,7 @@ static int fib6_walk(struct net *net, struct fib6_walker *w)
 static int fib6_clean_node(struct fib6_walker *w)
 {
 	int res;
-	struct rt6_info *rt;
+	struct fib6_info *rt;
 	struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
 	struct nl_info info = {
 		.nl_net = c->net,
@@ -1932,17 +1952,17 @@ static int fib6_clean_node(struct fib6_walker *w)
 #if RT6_DEBUG >= 2
 				pr_debug("%s: del failed: rt=%p@%p err=%d\n",
 					 __func__, rt,
-					 rcu_access_pointer(rt->rt6i_node),
+					 rcu_access_pointer(rt->fib6_node),
 					 res);
 #endif
 				continue;
 			}
 			return 0;
 		} else if (res == -2) {
-			if (WARN_ON(!rt->rt6i_nsiblings))
+			if (WARN_ON(!rt->fib6_nsiblings))
 				continue;
-			rt = list_last_entry(&rt->rt6i_siblings,
-					     struct rt6_info, rt6i_siblings);
+			rt = list_last_entry(&rt->fib6_siblings,
+					     struct fib6_info, fib6_siblings);
 			continue;
 		}
 		WARN_ON(res != 0);
@@ -1961,7 +1981,7 @@ static int fib6_clean_node(struct fib6_walker *w)
  */
 
 static void fib6_clean_tree(struct net *net, struct fib6_node *root,
-			    int (*func)(struct rt6_info *, void *arg),
+			    int (*func)(struct fib6_info *, void *arg),
 			    int sernum, void *arg)
 {
 	struct fib6_cleaner c;
@@ -1979,7 +1999,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 }
 
 static void __fib6_clean_all(struct net *net,
-			     int (*func)(struct rt6_info *, void *),
+			     int (*func)(struct fib6_info *, void *),
 			     int sernum, void *arg)
 {
 	struct fib6_table *table;
@@ -1999,7 +2019,7 @@ static void __fib6_clean_all(struct net *net,
 	rcu_read_unlock();
 }
 
-void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
+void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *),
 		    void *arg)
 {
 	__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
@@ -2016,7 +2036,7 @@ static void fib6_flush_trees(struct net *net)
  *	Garbage collection
  */
 
-static int fib6_age(struct rt6_info *rt, void *arg)
+static int fib6_age(struct fib6_info *rt, void *arg)
 {
 	struct fib6_gc_args *gc_args = arg;
 	unsigned long now = jiffies;
@@ -2026,8 +2046,8 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 	 *	Routes are expired even if they are in use.
 	 */
 
-	if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
-		if (time_after(now, rt->dst.expires)) {
+	if (rt->fib6_flags & RTF_EXPIRES && rt->expires) {
+		if (time_after(now, rt->expires)) {
 			RT6_TRACE("expiring %p\n", rt);
 			return -1;
 		}
@@ -2110,7 +2130,7 @@ static int __net_init fib6_net_init(struct net *net)
 
 	net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
 	rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf,
-			   net->ipv6.ip6_null_entry);
+			   net->ipv6.fib6_null_entry);
 	net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
@@ -2122,7 +2142,7 @@ static int __net_init fib6_net_init(struct net *net)
 		goto out_fib6_main_tbl;
 	net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
 	rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf,
-			   net->ipv6.ip6_null_entry);
+			   net->ipv6.fib6_null_entry);
 	net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
 		RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
 	inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
@@ -2211,25 +2231,26 @@ void fib6_gc_cleanup(void)
 #ifdef CONFIG_PROC_FS
 static int ipv6_route_seq_show(struct seq_file *seq, void *v)
 {
-	struct rt6_info *rt = v;
+	struct fib6_info *rt = v;
 	struct ipv6_route_iter *iter = seq->private;
+	const struct net_device *dev;
 
-	seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
+	seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen);
 
 #ifdef CONFIG_IPV6_SUBTREES
-	seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
+	seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen);
 #else
 	seq_puts(seq, "00000000000000000000000000000000 00 ");
 #endif
-	if (rt->rt6i_flags & RTF_GATEWAY)
-		seq_printf(seq, "%pi6", &rt->rt6i_gateway);
+	if (rt->fib6_flags & RTF_GATEWAY)
+		seq_printf(seq, "%pi6", &rt->fib6_nh.nh_gw);
 	else
 		seq_puts(seq, "00000000000000000000000000000000");
 
+	dev = rt->fib6_nh.nh_dev;
 	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
-		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
-		   rt->dst.__use, rt->rt6i_flags,
-		   rt->dst.dev ? rt->dst.dev->name : "");
+		   rt->fib6_metric, atomic_read(&rt->fib6_ref), 0,
+		   rt->fib6_flags, dev ? dev->name : "");
 	iter->w.leaf = NULL;
 	return 0;
 }
@@ -2243,7 +2264,7 @@ static int ipv6_route_yield(struct fib6_walker *w)
 
 	do {
 		iter->w.leaf = rcu_dereference_protected(
-				iter->w.leaf->rt6_next,
+				iter->w.leaf->fib6_next,
 				lockdep_is_held(&iter->tbl->tb6_lock));
 		iter->skip--;
 		if (!iter->skip && iter->w.leaf)
@@ -2302,14 +2323,14 @@ static void ipv6_route_check_sernum(struct ipv6_route_iter *iter)
 static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	int r;
-	struct rt6_info *n;
+	struct fib6_info *n;
 	struct net *net = seq_file_net(seq);
 	struct ipv6_route_iter *iter = seq->private;
 
 	if (!v)
 		goto iter_table;
 
-	n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next);
+	n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next);
 	if (n) {
 		++*pos;
 		return n;