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

Pull networking updates from David Miller:
 "Some highlights from this development cycle:

   1) Big refactoring of ipv6 route and neigh handling to support
      nexthop objects configurable as units from userspace. From David
      Ahern.

   2) Convert explored_states in BPF verifier into a hash table,
      significantly decreased state held for programs with bpf2bpf
      calls, from Alexei Starovoitov.

   3) Implement bpf_send_signal() helper, from Yonghong Song.

   4) Various classifier enhancements to mvpp2 driver, from Maxime
      Chevallier.

   5) Add aRFS support to hns3 driver, from Jian Shen.

   6) Fix use after free in inet frags by allocating fqdirs dynamically
      and reworking how rhashtable dismantle occurs, from Eric Dumazet.

   7) Add act_ctinfo packet classifier action, from Kevin
      Darbyshire-Bryant.

   8) Add TFO key backup infrastructure, from Jason Baron.

   9) Remove several old and unused ISDN drivers, from Arnd Bergmann.

  10) Add devlink notifications for flash update status to mlxsw driver,
      from Jiri Pirko.

  11) Lots of kTLS offload infrastructure fixes, from Jakub Kicinski.

  12) Add support for mv88e6250 DSA chips, from Rasmus Villemoes.

  13) Various enhancements to ipv6 flow label handling, from Eric
      Dumazet and Willem de Bruijn.

  14) Support TLS offload in nfp driver, from Jakub Kicinski, Dirk van
      der Merwe, and others.

  15) Various improvements to axienet driver including converting it to
      phylink, from Robert Hancock.

  16) Add PTP support to sja1105 DSA driver, from Vladimir Oltean.

  17) Add mqprio qdisc offload support to dpaa2-eth, from Ioana
      Radulescu.

  18) Add devlink health reporting to mlx5, from Moshe Shemesh.

  19) Convert stmmac over to phylink, from Jose Abreu.

  20) Add PTP PHC (Physical Hardware Clock) support to mlxsw, from
      Shalom Toledo.

  21) Add nftables SYNPROXY support, from Fernando Fernandez Mancera.

  22) Convert tcp_fastopen over to use SipHash, from Ard Biesheuvel.

  23) Track spill/fill of constants in BPF verifier, from Alexei
      Starovoitov.

  24) Support bounded loops in BPF, from Alexei Starovoitov.

  25) Various page_pool API fixes and improvements, from Jesper Dangaard
      Brouer.

  26) Just like ipv4, support ref-countless ipv6 route handling. From
      Wei Wang.

  27) Support VLAN offloading in aquantia driver, from Igor Russkikh.

  28) Add AF_XDP zero-copy support to mlx5, from Maxim Mikityanskiy.

  29) Add flower GRE encap/decap support to nfp driver, from Pieter
      Jansen van Vuuren.

  30) Protect against stack overflow when using act_mirred, from John
      Hurley.

  31) Allow devmap map lookups from eBPF, from Toke Høiland-Jørgensen.

  32) Use page_pool API in netsec driver, Ilias Apalodimas.

  33) Add Google gve network driver, from Catherine Sullivan.

  34) More indirect call avoidance, from Paolo Abeni.

  35) Add kTLS TX HW offload support to mlx5, from Tariq Toukan.

  36) Add XDP_REDIRECT support to bnxt_en, from Andy Gospodarek.

  37) Add MPLS manipulation actions to TC, from John Hurley.

  38) Add sending a packet to connection tracking from TC actions, and
      then allow flower classifier matching on conntrack state. From
      Paul Blakey.

  39) Netfilter hw offload support, from Pablo Neira Ayuso"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2080 commits)
  net/mlx5e: Return in default case statement in tx_post_resync_params
  mlx5: Return -EINVAL when WARN_ON_ONCE triggers in mlx5e_tls_resync().
  net: dsa: add support for BRIDGE_MROUTER attribute
  pkt_sched: Include const.h
  net: netsec: remove static declaration for netsec_set_tx_de()
  net: netsec: remove superfluous if statement
  netfilter: nf_tables: add hardware offload support
  net: flow_offload: rename tc_cls_flower_offload to flow_cls_offload
  net: flow_offload: add flow_block_cb_is_busy() and use it
  net: sched: remove tcf block API
  drivers: net: use flow block API
  net: sched: use flow block API
  net: flow_offload: add flow_block_cb_{priv, incref, decref}()
  net: flow_offload: add list handling functions
  net: flow_offload: add flow_block_cb_alloc() and flow_block_cb_free()
  net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
  net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
  net: flow_offload: add flow_block_cb_setup_simple()
  net: hisilicon: Add an tx_desc to adapt HI13X1_GMAC
  net: hisilicon: Add an rx_desc to adapt HI13X1_GMAC
  ...

1 files changed, 1151 insertions, 320 deletions

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 97a843cf164c..4d2e6b31a8d6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -100,7 +100,7 @@ static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,
 			   int strict);
-static size_t rt6_nlmsg_size(struct fib6_info *rt);
+static size_t rt6_nlmsg_size(struct fib6_info *f6i);
 static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 struct fib6_info *rt, struct dst_entry *dst,
 			 struct in6_addr *dest, struct in6_addr *src,
@@ -176,7 +176,7 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
 			}
 
 			if (rt_dev == dev) {
-				rt->dst.dev = loopback_dev;
+				rt->dst.dev = blackhole_netdev;
 				dev_hold(rt->dst.dev);
 				dev_put(rt_dev);
 			}
@@ -429,21 +429,27 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 	struct fib6_info *sibling, *next_sibling;
 	struct fib6_info *match = res->f6i;
 
-	if (!match->fib6_nsiblings || have_oif_match)
+	if ((!match->fib6_nsiblings && !match->nh) || have_oif_match)
 		goto out;
 
 	/* We might have already computed the hash for ICMPv6 errors. In such
 	 * case it will always be non-zero. Otherwise now is the time to do it.
 	 */
-	if (!fl6->mp_hash)
+	if (!fl6->mp_hash &&
+	    (!match->nh || nexthop_is_multipath(match->nh)))
 		fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
 
-	if (fl6->mp_hash <= atomic_read(&match->fib6_nh.fib_nh_upper_bound))
+	if (unlikely(match->nh)) {
+		nexthop_path_fib6_result(res, fl6->mp_hash);
+		return;
+	}
+
+	if (fl6->mp_hash <= atomic_read(&match->fib6_nh->fib_nh_upper_bound))
 		goto out;
 
 	list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
 				 fib6_siblings) {
-		const struct fib6_nh *nh = &sibling->fib6_nh;
+		const struct fib6_nh *nh = sibling->fib6_nh;
 		int nh_upper_bound;
 
 		nh_upper_bound = atomic_read(&nh->fib_nh_upper_bound);
@@ -457,7 +463,7 @@ void fib6_select_path(const struct net *net, struct fib6_result *res,
 
 out:
 	res->f6i = match;
-	res->nh = &match->fib6_nh;
+	res->nh = match->fib6_nh;
 }
 
 /*
@@ -485,6 +491,45 @@ static bool __rt6_device_match(struct net *net, const struct fib6_nh *nh,
 	return false;
 }
 
+struct fib6_nh_dm_arg {
+	struct net		*net;
+	const struct in6_addr	*saddr;
+	int			oif;
+	int			flags;
+	struct fib6_nh		*nh;
+};
+
+static int __rt6_nh_dev_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_dm_arg *arg = _arg;
+
+	arg->nh = nh;
+	return __rt6_device_match(arg->net, nh, arg->saddr, arg->oif,
+				  arg->flags);
+}
+
+/* returns fib6_nh from nexthop or NULL */
+static struct fib6_nh *rt6_nh_dev_match(struct net *net, struct nexthop *nh,
+					struct fib6_result *res,
+					const struct in6_addr *saddr,
+					int oif, int flags)
+{
+	struct fib6_nh_dm_arg arg = {
+		.net   = net,
+		.saddr = saddr,
+		.oif   = oif,
+		.flags = flags,
+	};
+
+	if (nexthop_is_blackhole(nh))
+		return NULL;
+
+	if (nexthop_for_each_fib6_nh(nh, __rt6_nh_dev_match, &arg))
+		return arg.nh;
+
+	return NULL;
+}
+
 static void rt6_device_match(struct net *net, struct fib6_result *res,
 			     const struct in6_addr *saddr, int oif, int flags)
 {
@@ -493,14 +538,31 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
 	struct fib6_nh *nh;
 
 	if (!oif && ipv6_addr_any(saddr)) {
-		nh = &f6i->fib6_nh;
+		if (unlikely(f6i->nh)) {
+			nh = nexthop_fib6_nh(f6i->nh);
+			if (nexthop_is_blackhole(f6i->nh))
+				goto out_blackhole;
+		} else {
+			nh = f6i->fib6_nh;
+		}
 		if (!(nh->fib_nh_flags & RTNH_F_DEAD))
 			goto out;
 	}
 
 	for (spf6i = f6i; spf6i; spf6i = rcu_dereference(spf6i->fib6_next)) {
-		nh = &spf6i->fib6_nh;
-		if (__rt6_device_match(net, nh, saddr, oif, flags)) {
+		bool matched = false;
+
+		if (unlikely(spf6i->nh)) {
+			nh = rt6_nh_dev_match(net, spf6i->nh, res, saddr,
+					      oif, flags);
+			if (nh)
+				matched = true;
+		} else {
+			nh = spf6i->fib6_nh;
+			if (__rt6_device_match(net, nh, saddr, oif, flags))
+				matched = true;
+		}
+		if (matched) {
 			res->f6i = spf6i;
 			goto out;
 		}
@@ -508,19 +570,32 @@ static void rt6_device_match(struct net *net, struct fib6_result *res,
 
 	if (oif && flags & RT6_LOOKUP_F_IFACE) {
 		res->f6i = net->ipv6.fib6_null_entry;
-		nh = &res->f6i->fib6_nh;
+		nh = res->f6i->fib6_nh;
 		goto out;
 	}
 
-	nh = &f6i->fib6_nh;
+	if (unlikely(f6i->nh)) {
+		nh = nexthop_fib6_nh(f6i->nh);
+		if (nexthop_is_blackhole(f6i->nh))
+			goto out_blackhole;
+	} else {
+		nh = f6i->fib6_nh;
+	}
+
 	if (nh->fib_nh_flags & RTNH_F_DEAD) {
 		res->f6i = net->ipv6.fib6_null_entry;
-		nh = &res->f6i->fib6_nh;
+		nh = res->f6i->fib6_nh;
 	}
 out:
 	res->nh = nh;
 	res->fib6_type = res->f6i->fib6_type;
 	res->fib6_flags = res->f6i->fib6_flags;
+	return;
+
+out_blackhole:
+	res->fib6_flags |= RTF_REJECT;
+	res->fib6_type = RTN_BLACKHOLE;
+	res->nh = nh;
 }
 
 #ifdef CONFIG_IPV6_ROUTER_PREF
@@ -691,6 +766,24 @@ out:
 	return rc;
 }
 
+struct fib6_nh_frl_arg {
+	u32		flags;
+	int		oif;
+	int		strict;
+	int		*mpri;
+	bool		*do_rr;
+	struct fib6_nh	*nh;
+};
+
+static int rt6_nh_find_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_frl_arg *arg = _arg;
+
+	arg->nh = nh;
+	return find_match(nh, arg->flags, arg->oif, arg->strict,
+			  arg->mpri, arg->do_rr);
+}
+
 static void __find_rr_leaf(struct fib6_info *f6i_start,
 			   struct fib6_info *nomatch, u32 metric,
 			   struct fib6_result *res, struct fib6_info **cont,
@@ -701,6 +794,7 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
 	for (f6i = f6i_start;
 	     f6i && f6i != nomatch;
 	     f6i = rcu_dereference(f6i->fib6_next)) {
+		bool matched = false;
 		struct fib6_nh *nh;
 
 		if (cont && f6i->fib6_metric != metric) {
@@ -711,8 +805,34 @@ static void __find_rr_leaf(struct fib6_info *f6i_start,
 		if (fib6_check_expired(f6i))
 			continue;
 
-		nh = &f6i->fib6_nh;
-		if (find_match(nh, f6i->fib6_flags, oif, strict, mpri, do_rr)) {
+		if (unlikely(f6i->nh)) {
+			struct fib6_nh_frl_arg arg = {
+				.flags  = f6i->fib6_flags,
+				.oif    = oif,
+				.strict = strict,
+				.mpri   = mpri,
+				.do_rr  = do_rr
+			};
+
+			if (nexthop_is_blackhole(f6i->nh)) {
+				res->fib6_flags = RTF_REJECT;
+				res->fib6_type = RTN_BLACKHOLE;
+				res->f6i = f6i;
+				res->nh = nexthop_fib6_nh(f6i->nh);
+				return;
+			}
+			if (nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_find_match,
+						     &arg)) {
+				matched = true;
+				nh = arg.nh;
+			}
+		} else {
+			nh = f6i->fib6_nh;
+			if (find_match(nh, f6i->fib6_flags, oif, strict,
+				       mpri, do_rr))
+				matched = true;
+		}
+		if (matched) {
 			res->f6i = f6i;
 			res->nh = nh;
 			res->fib6_flags = f6i->fib6_flags;
@@ -793,7 +913,7 @@ static void rt6_select(struct net *net, struct fib6_node *fn, int oif,
 out:
 	if (!res->f6i) {
 		res->f6i = net->ipv6.fib6_null_entry;
-		res->nh = &res->f6i->fib6_nh;
+		res->nh = res->f6i->fib6_nh;
 		res->fib6_flags = res->f6i->fib6_flags;
 		res->fib6_type = res->f6i->fib6_type;
 	}
@@ -1114,6 +1234,8 @@ restart:
 		rt = net->ipv6.ip6_null_entry;
 		dst_hold(&rt->dst);
 		goto out;
+	} else if (res.fib6_flags & RTF_REJECT) {
+		goto do_create;
 	}
 
 	fib6_select_path(net, &res, fl6, fl6->flowi6_oif,
@@ -1125,6 +1247,7 @@ restart:
 		if (ip6_hold_safe(net, &rt))
 			dst_use_noref(&rt->dst, jiffies);
 	} else {
+do_create:
 		rt = ip6_create_rt_rcu(&res);
 	}
 
@@ -1265,13 +1388,9 @@ static struct rt6_info *ip6_rt_pcpu_alloc(const struct fib6_result *res)
 /* It should be called with rcu_read_lock() acquired */
 static struct rt6_info *rt6_get_pcpu_route(const struct fib6_result *res)
 {
-	struct rt6_info *pcpu_rt, **p;
-
-	p = this_cpu_ptr(res->f6i->rt6i_pcpu);
-	pcpu_rt = *p;
+	struct rt6_info *pcpu_rt;
 
-	if (pcpu_rt)
-		ip6_hold_safe(NULL, &pcpu_rt);
+	pcpu_rt = this_cpu_read(*res->nh->rt6i_pcpu);
 
 	return pcpu_rt;
 }
@@ -1282,13 +1401,10 @@ static struct rt6_info *rt6_make_pcpu_route(struct net *net,
 	struct rt6_info *pcpu_rt, *prev, **p;
 
 	pcpu_rt = ip6_rt_pcpu_alloc(res);
-	if (!pcpu_rt) {
-		dst_hold(&net->ipv6.ip6_null_entry->dst);
-		return net->ipv6.ip6_null_entry;
-	}
+	if (!pcpu_rt)
+		return NULL;
 
-	dst_hold(&pcpu_rt->dst);
-	p = this_cpu_ptr(res->f6i->rt6i_pcpu);
+	p = this_cpu_ptr(res->nh->rt6i_pcpu);
 	prev = cmpxchg(p, NULL, pcpu_rt);
 	BUG_ON(prev);
 
@@ -1458,25 +1574,74 @@ static unsigned int fib6_mtu(const struct fib6_result *res)
 	return mtu - lwtunnel_headroom(nh->fib_nh_lws, mtu);
 }
 
+#define FIB6_EXCEPTION_BUCKET_FLUSHED  0x1UL
+
+/* used when the flushed bit is not relevant, only access to the bucket
+ * (ie., all bucket users except rt6_insert_exception);
+ *
+ * called under rcu lock; sometimes called with rt6_exception_lock held
+ */
+static
+struct rt6_exception_bucket *fib6_nh_get_excptn_bucket(const struct fib6_nh *nh,
+						       spinlock_t *lock)
+{
+	struct rt6_exception_bucket *bucket;
+
+	if (lock)
+		bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
+						   lockdep_is_held(lock));
+	else
+		bucket = rcu_dereference(nh->rt6i_exception_bucket);
+
+	/* remove bucket flushed bit if set */
+	if (bucket) {
+		unsigned long p = (unsigned long)bucket;
+
+		p &= ~FIB6_EXCEPTION_BUCKET_FLUSHED;
+		bucket = (struct rt6_exception_bucket *)p;
+	}
+
+	return bucket;
+}
+
+static bool fib6_nh_excptn_bucket_flushed(struct rt6_exception_bucket *bucket)
+{
+	unsigned long p = (unsigned long)bucket;
+
+	return !!(p & FIB6_EXCEPTION_BUCKET_FLUSHED);
+}
+
+/* called with rt6_exception_lock held */
+static void fib6_nh_excptn_bucket_set_flushed(struct fib6_nh *nh,
+					      spinlock_t *lock)
+{
+	struct rt6_exception_bucket *bucket;
+	unsigned long p;
+
+	bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
+					   lockdep_is_held(lock));
+
+	p = (unsigned long)bucket;
+	p |= FIB6_EXCEPTION_BUCKET_FLUSHED;
+	bucket = (struct rt6_exception_bucket *)p;
+	rcu_assign_pointer(nh->rt6i_exception_bucket, bucket);
+}
+
 static int rt6_insert_exception(struct rt6_info *nrt,
 				const struct fib6_result *res)
 {
 	struct net *net = dev_net(nrt->dst.dev);
 	struct rt6_exception_bucket *bucket;
+	struct fib6_info *f6i = res->f6i;
 	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
-	struct fib6_info *f6i = res->f6i;
+	struct fib6_nh *nh = res->nh;
 	int err = 0;
 
 	spin_lock_bh(&rt6_exception_lock);
 
-	if (f6i->exception_bucket_flushed) {
-		err = -EINVAL;
-		goto out;
-	}
-
-	bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket,
-					lockdep_is_held(&rt6_exception_lock));
+	bucket = rcu_dereference_protected(nh->rt6i_exception_bucket,
+					  lockdep_is_held(&rt6_exception_lock));
 	if (!bucket) {
 		bucket = kcalloc(FIB6_EXCEPTION_BUCKET_SIZE, sizeof(*bucket),
 				 GFP_ATOMIC);
@@ -1484,7 +1649,10 @@ static int rt6_insert_exception(struct rt6_info *nrt,
 			err = -ENOMEM;
 			goto out;
 		}
-		rcu_assign_pointer(f6i->rt6i_exception_bucket, bucket);
+		rcu_assign_pointer(nh->rt6i_exception_bucket, bucket);
+	} else if (fib6_nh_excptn_bucket_flushed(bucket)) {
+		err = -EINVAL;
+		goto out;
 	}
 
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1539,7 +1707,7 @@ out:
 	return err;
 }
 
-void rt6_flush_exceptions(struct fib6_info *rt)
+static void fib6_nh_flush_exceptions(struct fib6_nh *nh, struct fib6_info *from)
 {
 	struct rt6_exception_bucket *bucket;
 	struct rt6_exception *rt6_ex;
@@ -1547,25 +1715,46 @@ void rt6_flush_exceptions(struct fib6_info *rt)
 	int i;
 
 	spin_lock_bh(&rt6_exception_lock);
-	/* Prevent rt6_insert_exception() to recreate the bucket list */
-	rt->exception_bucket_flushed = 1;
 
-	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
-				    lockdep_is_held(&rt6_exception_lock));
+	bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
 	if (!bucket)
 		goto out;
 
+	/* Prevent rt6_insert_exception() to recreate the bucket list */
+	if (!from)
+		fib6_nh_excptn_bucket_set_flushed(nh, &rt6_exception_lock);
+
 	for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
-		hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist)
-			rt6_remove_exception(bucket, rt6_ex);
-		WARN_ON_ONCE(bucket->depth);
+		hlist_for_each_entry_safe(rt6_ex, tmp, &bucket->chain, hlist) {
+			if (!from ||
+			    rcu_access_pointer(rt6_ex->rt6i->from) == from)
+				rt6_remove_exception(bucket, rt6_ex);
+		}
+		WARN_ON_ONCE(!from && bucket->depth);
 		bucket++;
 	}
-
 out:
 	spin_unlock_bh(&rt6_exception_lock);
 }
 
+static int rt6_nh_flush_exceptions(struct fib6_nh *nh, void *arg)
+{
+	struct fib6_info *f6i = arg;
+
+	fib6_nh_flush_exceptions(nh, f6i);
+
+	return 0;
+}
+
+void rt6_flush_exceptions(struct fib6_info *f6i)
+{
+	if (f6i->nh)
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_flush_exceptions,
+					 f6i);
+	else
+		fib6_nh_flush_exceptions(f6i->fib6_nh, f6i);
+}
+
 /* Find cached rt in the hash table inside passed in rt
  * Caller has to hold rcu_read_lock()
  */
@@ -1594,7 +1783,7 @@ static struct rt6_info *rt6_find_cached_rt(const struct fib6_result *res,
 		src_key = saddr;
 find_ex:
 #endif
-	bucket = rcu_dereference(res->f6i->rt6i_exception_bucket);
+	bucket = fib6_nh_get_excptn_bucket(res->nh, NULL);
 	rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
 
 	if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
@@ -1612,25 +1801,20 @@ find_ex:
 }
 
 /* Remove the passed in cached rt from the hash table that contains it */
-static int rt6_remove_exception_rt(struct rt6_info *rt)
+static int fib6_nh_remove_exception(const struct fib6_nh *nh, int plen,
+				    const struct rt6_info *rt)
 {
+	const struct in6_addr *src_key = NULL;
 	struct rt6_exception_bucket *bucket;
-	struct in6_addr *src_key = NULL;
 	struct rt6_exception *rt6_ex;
-	struct fib6_info *from;
 	int err;
 
-	from = rcu_dereference(rt->from);
-	if (!from ||
-	    !(rt->rt6i_flags & RTF_CACHE))
-		return -EINVAL;
-
-	if (!rcu_access_pointer(from->rt6i_exception_bucket))
+	if (!rcu_access_pointer(nh->rt6i_exception_bucket))
 		return -ENOENT;
 
 	spin_lock_bh(&rt6_exception_lock);
-	bucket = rcu_dereference_protected(from->rt6i_exception_bucket,
-				    lockdep_is_held(&rt6_exception_lock));
+	bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
+
 #ifdef CONFIG_IPV6_SUBTREES
 	/* rt6i_src.plen != 0 indicates 'from' is in subtree
 	 * and exception table is indexed by a hash of
@@ -1638,7 +1822,7 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
 	 * Otherwise, the exception table is indexed by
 	 * a hash of only rt6i_dst.
 	 */
-	if (from->fib6_src.plen)
+	if (plen)
 		src_key = &rt->rt6i_src.addr;
 #endif
 	rt6_ex = __rt6_find_exception_spinlock(&bucket,
@@ -1655,23 +1839,60 @@ static int rt6_remove_exception_rt(struct rt6_info *rt)
 	return err;
 }
 
-/* Find rt6_ex which contains the passed in rt cache and
- * refresh its stamp
- */
-static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
+struct fib6_nh_excptn_arg {
+	struct rt6_info	*rt;
+	int		plen;
+};
+
+static int rt6_nh_remove_exception_rt(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_excptn_arg *arg = _arg;
+	int err;
+
+	err = fib6_nh_remove_exception(nh, arg->plen, arg->rt);
+	if (err == 0)
+		return 1;
+
+	return 0;
+}
+
+static int rt6_remove_exception_rt(struct rt6_info *rt)
 {
-	struct rt6_exception_bucket *bucket;
-	struct in6_addr *src_key = NULL;
-	struct rt6_exception *rt6_ex;
 	struct fib6_info *from;
 
-	rcu_read_lock();
 	from = rcu_dereference(rt->from);
 	if (!from || !(rt->rt6i_flags & RTF_CACHE))
-		goto unlock;
+		return -EINVAL;
 
-	bucket = rcu_dereference(from->rt6i_exception_bucket);
+	if (from->nh) {
+		struct fib6_nh_excptn_arg arg = {
+			.rt = rt,
+			.plen = from->fib6_src.plen
+		};
+		int rc;
+
+		/* rc = 1 means an entry was found */
+		rc = nexthop_for_each_fib6_nh(from->nh,
+					      rt6_nh_remove_exception_rt,
+					      &arg);
+		return rc ? 0 : -ENOENT;
+	}
 
+	return fib6_nh_remove_exception(from->fib6_nh,
+					from->fib6_src.plen, rt);
+}
+
+/* Find rt6_ex which contains the passed in rt cache and
+ * refresh its stamp
+ */
+static void fib6_nh_update_exception(const struct fib6_nh *nh, int plen,
+				     const struct rt6_info *rt)
+{
+	const struct in6_addr *src_key = NULL;
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+
+	bucket = fib6_nh_get_excptn_bucket(nh, NULL);
 #ifdef CONFIG_IPV6_SUBTREES
 	/* rt6i_src.plen != 0 indicates 'from' is in subtree
 	 * and exception table is indexed by a hash of
@@ -1679,15 +1900,63 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
 	 * Otherwise, the exception table is indexed by
 	 * a hash of only rt6i_dst.
 	 */
-	if (from->fib6_src.plen)
+	if (plen)
 		src_key = &rt->rt6i_src.addr;
 #endif
-	rt6_ex = __rt6_find_exception_rcu(&bucket,
-					  &rt->rt6i_dst.addr,
-					  src_key);
+	rt6_ex = __rt6_find_exception_rcu(&bucket, &rt->rt6i_dst.addr, src_key);
 	if (rt6_ex)
 		rt6_ex->stamp = jiffies;
+}
+
+struct fib6_nh_match_arg {
+	const struct net_device *dev;
+	const struct in6_addr	*gw;
+	struct fib6_nh		*match;
+};
+
+/* determine if fib6_nh has given device and gateway */
+static int fib6_nh_find_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_match_arg *arg = _arg;
+
+	if (arg->dev != nh->fib_nh_dev ||
+	    (arg->gw && !nh->fib_nh_gw_family) ||
+	    (!arg->gw && nh->fib_nh_gw_family) ||
+	    (arg->gw && !ipv6_addr_equal(arg->gw, &nh->fib_nh_gw6)))
+		return 0;
+
+	arg->match = nh;
+
+	/* found a match, break the loop */
+	return 1;
+}
+
+static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
+{
+	struct fib6_info *from;
+	struct fib6_nh *fib6_nh;
+
+	rcu_read_lock();
+
+	from = rcu_dereference(rt->from);
+	if (!from || !(rt->rt6i_flags & RTF_CACHE))
+		goto unlock;
 
+	if (from->nh) {
+		struct fib6_nh_match_arg arg = {
+			.dev = rt->dst.dev,
+			.gw = &rt->rt6i_gateway,
+		};
+
+		nexthop_for_each_fib6_nh(from->nh, fib6_nh_find_match, &arg);
+
+		if (!arg.match)
+			return;
+		fib6_nh = arg.match;
+	} else {
+		fib6_nh = from->fib6_nh;
+	}
+	fib6_nh_update_exception(fib6_nh, from->fib6_src.plen, rt);
 unlock:
 	rcu_read_unlock();
 }
@@ -1715,15 +1984,13 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
 }
 
 static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
-				       struct fib6_info *rt, int mtu)
+				       const struct fib6_nh *nh, int mtu)
 {
 	struct rt6_exception_bucket *bucket;
 	struct rt6_exception *rt6_ex;
 	int i;
 
-	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
-					lockdep_is_held(&rt6_exception_lock));
-
+	bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
 	if (!bucket)
 		return;
 
@@ -1745,21 +2012,19 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
 
 #define RTF_CACHE_GATEWAY	(RTF_GATEWAY | RTF_CACHE)
 
-static void rt6_exceptions_clean_tohost(struct fib6_info *rt,
-					struct in6_addr *gateway)
+static void fib6_nh_exceptions_clean_tohost(const struct fib6_nh *nh,
+					    const struct in6_addr *gateway)
 {
 	struct rt6_exception_bucket *bucket;
 	struct rt6_exception *rt6_ex;
 	struct hlist_node *tmp;
 	int i;
 
-	if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+	if (!rcu_access_pointer(nh->rt6i_exception_bucket))
 		return;
 
 	spin_lock_bh(&rt6_exception_lock);
-	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
-				     lockdep_is_held(&rt6_exception_lock));
-
+	bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
 	if (bucket) {
 		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
 			hlist_for_each_entry_safe(rt6_ex, tmp,
@@ -1824,23 +2089,21 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
 	gc_args->more++;
 }
 
-void rt6_age_exceptions(struct fib6_info *rt,
-			struct fib6_gc_args *gc_args,
-			unsigned long now)
+static void fib6_nh_age_exceptions(const struct fib6_nh *nh,
+				   struct fib6_gc_args *gc_args,
+				   unsigned long now)
 {
 	struct rt6_exception_bucket *bucket;
 	struct rt6_exception *rt6_ex;
 	struct hlist_node *tmp;
 	int i;
 
-	if (!rcu_access_pointer(rt->rt6i_exception_bucket))
+	if (!rcu_access_pointer(nh->rt6i_exception_bucket))
 		return;
 
 	rcu_read_lock_bh();
 	spin_lock(&rt6_exception_lock);
-	bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
-				    lockdep_is_held(&rt6_exception_lock));
-
+	bucket = fib6_nh_get_excptn_bucket(nh, &rt6_exception_lock);
 	if (bucket) {
 		for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
 			hlist_for_each_entry_safe(rt6_ex, tmp,
@@ -1855,6 +2118,36 @@ void rt6_age_exceptions(struct fib6_info *rt,
 	rcu_read_unlock_bh();
 }
 
+struct fib6_nh_age_excptn_arg {
+	struct fib6_gc_args	*gc_args;
+	unsigned long		now;
+};
+
+static int rt6_nh_age_exceptions(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_age_excptn_arg *arg = _arg;
+
+	fib6_nh_age_exceptions(nh, arg->gc_args, arg->now);
+	return 0;
+}
+
+void rt6_age_exceptions(struct fib6_info *f6i,
+			struct fib6_gc_args *gc_args,
+			unsigned long now)
+{
+	if (f6i->nh) {
+		struct fib6_nh_age_excptn_arg arg = {
+			.gc_args = gc_args,
+			.now = now
+		};
+
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_age_exceptions,
+					 &arg);
+	} else {
+		fib6_nh_age_exceptions(f6i->fib6_nh, gc_args, now);
+	}
+}
+
 /* must be called with rcu lock held */
 int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif,
 		      struct flowi6 *fl6, struct fib6_result *res, int strict)
@@ -1891,9 +2184,12 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 			       const struct sk_buff *skb, int flags)
 {
 	struct fib6_result res = {};
-	struct rt6_info *rt;
+	struct rt6_info *rt = NULL;
 	int strict = 0;
 
+	WARN_ON_ONCE((flags & RT6_LOOKUP_F_DST_NOREF) &&
+		     !rcu_read_lock_held());
+
 	strict |= flags & RT6_LOOKUP_F_IFACE;
 	strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
 	if (net->ipv6.devconf_all->forwarding == 0)
@@ -1902,23 +2198,15 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 	rcu_read_lock();
 
 	fib6_table_lookup(net, table, oif, fl6, &res, strict);
-	if (res.f6i == net->ipv6.fib6_null_entry) {
-		rt = net->ipv6.ip6_null_entry;
-		rcu_read_unlock();
-		dst_hold(&rt->dst);
-		return rt;
-	}
+	if (res.f6i == net->ipv6.fib6_null_entry)
+		goto out;
 
 	fib6_select_path(net, &res, fl6, oif, false, skb, strict);
 
 	/*Search through exception table */
 	rt = rt6_find_cached_rt(&res, &fl6->daddr, &fl6->saddr);
 	if (rt) {
-		if (ip6_hold_safe(net, &rt))
-			dst_use_noref(&rt->dst, jiffies);
-
-		rcu_read_unlock();
-		return rt;
+		goto out;
 	} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
 			    !res.nh->fib_nh_gw_family)) {
 		/* Create a RTF_CACHE clone which will not be
@@ -1926,40 +2214,38 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
 		 * the daddr in the skb during the neighbor look-up is different
 		 * from the fl6->daddr used to look-up route here.
 		 */
-		struct rt6_info *uncached_rt;
-
-		uncached_rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL);
+		rt = ip6_rt_cache_alloc(&res, &fl6->daddr, NULL);
 
-		rcu_read_unlock();
-
-		if (uncached_rt) {
-			/* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc()
-			 * No need for another dst_hold()
+		if (rt) {
+			/* 1 refcnt is taken during ip6_rt_cache_alloc().
+			 * As rt6_uncached_list_add() does not consume refcnt,
+			 * this refcnt is always returned to the caller even
+			 * if caller sets RT6_LOOKUP_F_DST_NOREF flag.
 			 */
-			rt6_uncached_list_add(uncached_rt);
+			rt6_uncached_list_add(rt);
 			atomic_inc(&net->ipv6.rt6_stats->fib_rt_uncache);
-		} else {
-			uncached_rt = net->ipv6.ip6_null_entry;
-			dst_hold(&uncached_rt->dst);
-		}
+			rcu_read_unlock();
 
-		return uncached_rt;
+			return rt;
+		}
 	} else {
 		/* Get a percpu copy */
-
-		struct rt6_info *pcpu_rt;
-
 		local_bh_disable();
-		pcpu_rt = rt6_get_pcpu_route(&res);
+		rt = rt6_get_pcpu_route(&res);
 
-		if (!pcpu_rt)
-			pcpu_rt = rt6_make_pcpu_route(net, &res);
+		if (!rt)
+			rt = rt6_make_pcpu_route(net, &res);
 
 		local_bh_enable();
-		rcu_read_unlock();
-
-		return pcpu_rt;
 	}
+out:
+	if (!rt)
+		rt = net->ipv6.ip6_null_entry;
+	if (!(flags & RT6_LOOKUP_F_DST_NOREF))
+		ip6_hold_safe(net, &rt);
+	rcu_read_unlock();
+
+	return rt;
 }
 EXPORT_SYMBOL_GPL(ip6_pol_route);
 
@@ -2084,17 +2370,54 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
 			hash_keys.basic.ip_proto = fl6->flowi6_proto;
 		}
 		break;
+	case 2:
+		memset(&hash_keys, 0, sizeof(hash_keys));
+		hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+		if (skb) {
+			struct flow_keys keys;
+
+			if (!flkeys) {
+				skb_flow_dissect_flow_keys(skb, &keys, 0);
+				flkeys = &keys;
+			}
+
+			/* Inner can be v4 or v6 */
+			if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
+				hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src;
+				hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst;
+			} else if (flkeys->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+				hash_keys.addrs.v6addrs.src = flkeys->addrs.v6addrs.src;
+				hash_keys.addrs.v6addrs.dst = flkeys->addrs.v6addrs.dst;
+				hash_keys.tags.flow_label = flkeys->tags.flow_label;
+				hash_keys.basic.ip_proto = flkeys->basic.ip_proto;
+			} else {
+				/* Same as case 0 */
+				hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+				ip6_multipath_l3_keys(skb, &hash_keys, flkeys);
+			}
+		} else {
+			/* Same as case 0 */
+			hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+			hash_keys.addrs.v6addrs.src = fl6->saddr;
+			hash_keys.addrs.v6addrs.dst = fl6->daddr;
+			hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
+			hash_keys.basic.ip_proto = fl6->flowi6_proto;
+		}
+		break;
 	}
 	mhash = flow_hash_from_keys(&hash_keys);
 
 	return mhash >> 1;
 }
 
+/* Called with rcu held */
 void ip6_route_input(struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct net *net = dev_net(skb->dev);
-	int flags = RT6_LOOKUP_F_HAS_SADDR;
+	int flags = RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_DST_NOREF;
 	struct ip_tunnel_info *tun_info;
 	struct flowi6 fl6 = {
 		.flowi6_iif = skb->dev->ifindex,
@@ -2116,8 +2439,8 @@ void ip6_route_input(struct sk_buff *skb)
 	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
 		fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, flkeys);
 	skb_dst_drop(skb);
-	skb_dst_set(skb,
-		    ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags));
+	skb_dst_set_noref(skb, ip6_route_input_lookup(net, skb->dev,
+						      &fl6, skb, flags));
 }
 
 static struct rt6_info *ip6_pol_route_output(struct net *net,
@@ -2129,8 +2452,9 @@ static struct rt6_info *ip6_pol_route_output(struct net *net,
 	return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, skb, flags);
 }
 
-struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
-					 struct flowi6 *fl6, int flags)
+struct dst_entry *ip6_route_output_flags_noref(struct net *net,
+					       const struct sock *sk,
+					       struct flowi6 *fl6, int flags)
 {
 	bool any_src;
 
@@ -2138,6 +2462,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 	    (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)) {
 		struct dst_entry *dst;
 
+		/* This function does not take refcnt on the dst */
 		dst = l3mdev_link_scope_lookup(net, fl6);
 		if (dst)
 			return dst;
@@ -2145,6 +2470,7 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 
 	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
+	flags |= RT6_LOOKUP_F_DST_NOREF;
 	any_src = ipv6_addr_any(&fl6->saddr);
 	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
 	    (fl6->flowi6_oif && any_src))
@@ -2157,6 +2483,28 @@ struct dst_entry *ip6_route_output_flags(struct net *net, const struct sock *sk,
 
 	return fib6_rule_lookup(net, fl6, NULL, flags, ip6_pol_route_output);
 }
+EXPORT_SYMBOL_GPL(ip6_route_output_flags_noref);
+
+struct dst_entry *ip6_route_output_flags(struct net *net,
+					 const struct sock *sk,
+					 struct flowi6 *fl6,
+					 int flags)
+{
+        struct dst_entry *dst;
+        struct rt6_info *rt6;
+
+        rcu_read_lock();
+        dst = ip6_route_output_flags_noref(net, sk, fl6, flags);
+        rt6 = (struct rt6_info *)dst;
+        /* For dst cached in uncached_list, refcnt is already taken. */
+        if (list_empty(&rt6->rt6i_uncached) && !dst_hold_safe(dst)) {
+                dst = &net->ipv6.ip6_null_entry->dst;
+                dst_hold(dst);
+        }
+        rcu_read_unlock();
+
+        return dst;
+}
 EXPORT_SYMBOL_GPL(ip6_route_output_flags);
 
 struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_orig)
@@ -2381,10 +2729,31 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 			rcu_read_unlock();
 			return;
 		}
-		res.nh = &res.f6i->fib6_nh;
 		res.fib6_flags = res.f6i->fib6_flags;
 		res.fib6_type = res.f6i->fib6_type;
 
+		if (res.f6i->nh) {
+			struct fib6_nh_match_arg arg = {
+				.dev = dst->dev,
+				.gw = &rt6->rt6i_gateway,
+			};
+
+			nexthop_for_each_fib6_nh(res.f6i->nh,
+						 fib6_nh_find_match, &arg);
+
+			/* fib6_info uses a nexthop that does not have fib6_nh
+			 * using the dst->dev + gw. Should be impossible.
+			 */
+			if (!arg.match) {
+				rcu_read_unlock();
+				return;
+			}
+
+			res.nh = arg.match;
+		} else {
+			res.nh = res.f6i->fib6_nh;
+		}
+
 		nrt6 = ip6_rt_cache_alloc(&res, daddr, saddr);
 		if (nrt6) {
 			rt6_do_update_pmtu(nrt6, mtu);
@@ -2491,6 +2860,21 @@ static bool ip6_redirect_nh_match(const struct fib6_result *res,
 	return true;
 }
 
+struct fib6_nh_rd_arg {
+	struct fib6_result	*res;
+	struct flowi6		*fl6;
+	const struct in6_addr	*gw;
+	struct rt6_info		**ret;
+};
+
+static int fib6_nh_redirect_match(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_rd_arg *arg = _arg;
+
+	arg->res->nh = nh;
+	return ip6_redirect_nh_match(arg->res, arg->fl6, arg->gw, arg->ret);
+}
+
 /* Handle redirects */
 struct ip6rd_flowi {
 	struct flowi6 fl6;
@@ -2506,6 +2890,12 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
 	struct rt6_info *ret = NULL;
 	struct fib6_result res = {};
+	struct fib6_nh_rd_arg arg = {
+		.res = &res,
+		.fl6 = fl6,
+		.gw  = &rdfl->gateway,
+		.ret = &ret
+	};
 	struct fib6_info *rt;
 	struct fib6_node *fn;
 
@@ -2530,14 +2920,24 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
 restart:
 	for_each_fib6_node_rt_rcu(fn) {
 		res.f6i = rt;
-		res.nh = &rt->fib6_nh;
-
 		if (fib6_check_expired(rt))
 			continue;
 		if (rt->fib6_flags & RTF_REJECT)
 			break;
-		if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway, &ret))
-			goto out;
+		if (unlikely(rt->nh)) {
+			if (nexthop_is_blackhole(rt->nh))
+				continue;
+			/* on match, res->nh is filled in and potentially ret */
+			if (nexthop_for_each_fib6_nh(rt->nh,
+						     fib6_nh_redirect_match,
+						     &arg))
+				goto out;
+		} else {
+			res.nh = rt->fib6_nh;
+			if (ip6_redirect_nh_match(&res, fl6, &rdfl->gateway,
+						  &ret))
+				goto out;
+		}
 	}
 
 	if (!rt)
@@ -2554,7 +2954,7 @@ restart:
 	}
 
 	res.f6i = rt;
-	res.nh = &rt->fib6_nh;
+	res.nh = rt->fib6_nh;
 out:
 	if (ret) {
 		ip6_hold_safe(net, &ret);
@@ -2781,10 +3181,9 @@ out:
 	return entries > rt_max_size;
 }
 
-static struct rt6_info *ip6_nh_lookup_table(struct net *net,
-					    struct fib6_config *cfg,
-					    const struct in6_addr *gw_addr,
-					    u32 tbid, int flags)
+static int ip6_nh_lookup_table(struct net *net, struct fib6_config *cfg,
+			       const struct in6_addr *gw_addr, u32 tbid,
+			       int flags, struct fib6_result *res)
 {
 	struct flowi6 fl6 = {
 		.flowi6_oif = cfg->fc_ifindex,
@@ -2792,25 +3191,23 @@ static struct rt6_info *ip6_nh_lookup_table(struct net *net,
 		.saddr = cfg->fc_prefsrc,
 	};
 	struct fib6_table *table;
-	struct rt6_info *rt;
+	int err;
 
 	table = fib6_get_table(net, tbid);
 	if (!table)
-		return NULL;
+		return -EINVAL;
 
 	if (!ipv6_addr_any(&cfg->fc_prefsrc))
 		flags |= RT6_LOOKUP_F_HAS_SADDR;
 
 	flags |= RT6_LOOKUP_F_IGNORE_LINKSTATE;
-	rt = ip6_pol_route(net, table, cfg->fc_ifindex, &fl6, NULL, flags);
 
-	/* if table lookup failed, fall back to full lookup */
-	if (rt == net->ipv6.ip6_null_entry) {
-		ip6_rt_put(rt);
-		rt = NULL;
-	}
+	err = fib6_table_lookup(net, table, cfg->fc_ifindex, &fl6, res, flags);
+	if (!err && res->f6i != net->ipv6.fib6_null_entry)
+		fib6_select_path(net, res, &fl6, cfg->fc_ifindex,
+				 cfg->fc_ifindex != 0, NULL, flags);
 
-	return rt;
+	return err;
 }
 
 static int ip6_route_check_nh_onlink(struct net *net,
@@ -2818,29 +3215,19 @@ static int ip6_route_check_nh_onlink(struct net *net,
 				     const struct net_device *dev,
 				     struct netlink_ext_ack *extack)
 {
-	u32 tbid = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN;
+	u32 tbid = l3mdev_fib_table_rcu(dev) ? : RT_TABLE_MAIN;
 	const struct in6_addr *gw_addr = &cfg->fc_gateway;
-	u32 flags = RTF_LOCAL | RTF_ANYCAST | RTF_REJECT;
-	struct fib6_info *from;
-	struct rt6_info *grt;
+	struct fib6_result res = {};
 	int err;
 
-	err = 0;
-	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
-	if (grt) {
-		rcu_read_lock();
-		from = rcu_dereference(grt->from);
-		if (!grt->dst.error &&
-		    /* ignore match if it is the default route */
-		    from && !ipv6_addr_any(&from->fib6_dst.addr) &&
-		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
-			NL_SET_ERR_MSG(extack,
-				       "Nexthop has invalid gateway or device mismatch");
-			err = -EINVAL;
-		}
-		rcu_read_unlock();
-
-		ip6_rt_put(grt);
+	err = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0, &res);
+	if (!err && !(res.fib6_flags & RTF_REJECT) &&
+	    /* ignore match if it is the default route */
+	    !ipv6_addr_any(&res.f6i->fib6_dst.addr) &&
+	    (res.fib6_type != RTN_UNICAST || dev != res.nh->fib_nh_dev)) {
+		NL_SET_ERR_MSG(extack,
+			       "Nexthop has invalid gateway or device mismatch");
+		err = -EINVAL;
 	}
 
 	return err;
@@ -2853,47 +3240,50 @@ static int ip6_route_check_nh(struct net *net,
 {
 	const struct in6_addr *gw_addr = &cfg->fc_gateway;
 	struct net_device *dev = _dev ? *_dev : NULL;
-	struct rt6_info *grt = NULL;
+	int flags = RT6_LOOKUP_F_IFACE;
+	struct fib6_result res = {};
 	int err = -EHOSTUNREACH;
 
 	if (cfg->fc_table) {
-		int flags = RT6_LOOKUP_F_IFACE;
-
-		grt = ip6_nh_lookup_table(net, cfg, gw_addr,
-					  cfg->fc_table, flags);
-		if (grt) {
-			if (grt->rt6i_flags & RTF_GATEWAY ||
-			    (dev && dev != grt->dst.dev)) {
-				ip6_rt_put(grt);
-				grt = NULL;
-			}
-		}
+		err = ip6_nh_lookup_table(net, cfg, gw_addr,
+					  cfg->fc_table, flags, &res);
+		/* gw_addr can not require a gateway or resolve to a reject
+		 * route. If a device is given, it must match the result.
+		 */
+		if (err || res.fib6_flags & RTF_REJECT ||
+		    res.nh->fib_nh_gw_family ||
+		    (dev && dev != res.nh->fib_nh_dev))
+			err = -EHOSTUNREACH;
 	}
 
-	if (!grt)
-		grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, NULL, 1);
+	if (err < 0) {
+		struct flowi6 fl6 = {
+			.flowi6_oif = cfg->fc_ifindex,
+			.daddr = *gw_addr,
+		};
 
-	if (!grt)
-		goto out;
+		err = fib6_lookup(net, cfg->fc_ifindex, &fl6, &res, flags);
+		if (err || res.fib6_flags & RTF_REJECT ||
+		    res.nh->fib_nh_gw_family)
+			err = -EHOSTUNREACH;
 
+		if (err)
+			return err;
+
+		fib6_select_path(net, &res, &fl6, cfg->fc_ifindex,
+				 cfg->fc_ifindex != 0, NULL, flags);
+	}
+
+	err = 0;
 	if (dev) {
-		if (dev != grt->dst.dev) {
-			ip6_rt_put(grt);
-			goto out;
-		}
+		if (dev != res.nh->fib_nh_dev)
+			err = -EHOSTUNREACH;
 	} else {
-		*_dev = dev = grt->dst.dev;
-		*idev = grt->rt6i_idev;
+		*_dev = dev = res.nh->fib_nh_dev;
 		dev_hold(dev);
-		in6_dev_hold(grt->rt6i_idev);
+		*idev = in6_dev_get(dev);
 	}
 
-	if (!(grt->rt6i_flags & RTF_GATEWAY))
-		err = 0;
-
-	ip6_rt_put(grt);
-
-out:
 	return err;
 }
 
@@ -2934,11 +3324,15 @@ static int ip6_validate_gw(struct net *net, struct fib6_config *cfg,
 			goto out;
 		}
 
+		rcu_read_lock();
+
 		if (cfg->fc_flags & RTNH_F_ONLINK)
 			err = ip6_route_check_nh_onlink(net, cfg, dev, extack);
 		else
 			err = ip6_route_check_nh(net, cfg, _dev, idev);
 
+		rcu_read_unlock();
+
 		if (err)
 			goto out;
 	}
@@ -3039,7 +3433,7 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 				goto out;
 			}
 		}
-		goto set_dev;
+		goto pcpu_alloc;
 	}
 
 	if (cfg->fc_flags & RTF_GATEWAY) {
@@ -3075,7 +3469,14 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 				 cfg->fc_encap_type, cfg, gfp_flags, extack);
 	if (err)
 		goto out;
-set_dev:
+
+pcpu_alloc:
+	fib6_nh->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
+	if (!fib6_nh->rt6i_pcpu) {
+		err = -ENOMEM;
+		goto out;
+	}
+
 	fib6_nh->fib_nh_dev = dev;
 	fib6_nh->fib_nh_oif = dev->ifindex;
 	err = 0;
@@ -3095,6 +3496,38 @@ out:
 
 void fib6_nh_release(struct fib6_nh *fib6_nh)
 {
+	struct rt6_exception_bucket *bucket;
+
+	rcu_read_lock();
+
+	fib6_nh_flush_exceptions(fib6_nh, NULL);
+	bucket = fib6_nh_get_excptn_bucket(fib6_nh, NULL);
+	if (bucket) {
+		rcu_assign_pointer(fib6_nh->rt6i_exception_bucket, NULL);
+		kfree(bucket);
+	}
+
+	rcu_read_unlock();
+
+	if (fib6_nh->rt6i_pcpu) {
+		int cpu;
+
+		for_each_possible_cpu(cpu) {
+			struct rt6_info **ppcpu_rt;
+			struct rt6_info *pcpu_rt;
+
+			ppcpu_rt = per_cpu_ptr(fib6_nh->rt6i_pcpu, cpu);
+			pcpu_rt = *ppcpu_rt;
+			if (pcpu_rt) {
+				dst_dev_put(&pcpu_rt->dst);
+				dst_release(&pcpu_rt->dst);
+				*ppcpu_rt = NULL;
+			}
+		}
+
+		free_percpu(fib6_nh->rt6i_pcpu);
+	}
+
 	fib_nh_common_release(&fib6_nh->nh_common);
 }
 
@@ -3104,7 +3537,9 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 {
 	struct net *net = cfg->fc_nlinfo.nl_net;
 	struct fib6_info *rt = NULL;
+	struct nexthop *nh = NULL;
 	struct fib6_table *table;
+	struct fib6_nh *fib6_nh;
 	int err = -EINVAL;
 	int addr_type;
 
@@ -3140,6 +3575,16 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 	}
 #endif
+	if (cfg->fc_nh_id) {
+		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
+		if (!nh) {
+			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+			goto out;
+		}
+		err = fib6_check_nexthop(nh, cfg, extack);
+		if (err)
+			goto out;
+	}
 
 	err = -ENOBUFS;
 	if (cfg->fc_nlinfo.nlh &&
@@ -3157,7 +3602,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 		goto out;
 
 	err = -ENOMEM;
-	rt = fib6_info_alloc(gfp_flags);
+	rt = fib6_info_alloc(gfp_flags, !nh);
 	if (!rt)
 		goto out;
 
@@ -3197,19 +3642,35 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
 	rt->fib6_src.plen = cfg->fc_src_len;
 #endif
-	err = fib6_nh_init(net, &rt->fib6_nh, cfg, gfp_flags, extack);
-	if (err)
-		goto out;
+	if (nh) {
+		if (!nexthop_get(nh)) {
+			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+			goto out;
+		}
+		if (rt->fib6_src.plen) {
+			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+			goto out;
+		}
+		rt->nh = nh;
+		fib6_nh = nexthop_fib6_nh(rt->nh);
+	} else {
+		err = fib6_nh_init(net, rt->fib6_nh, cfg, gfp_flags, extack);
+		if (err)
+			goto out;
 
-	/* We cannot add true routes via loopback here,
-	 * they would result in kernel looping; promote them to reject routes
-	 */
-	addr_type = ipv6_addr_type(&cfg->fc_dst);
-	if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh.fib_nh_dev, addr_type))
-		rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP;
+		fib6_nh = rt->fib6_nh;
+
+		/* We cannot add true routes via loopback here, they would
+		 * result in kernel looping; promote them to reject routes
+		 */
+		addr_type = ipv6_addr_type(&cfg->fc_dst);
+		if (fib6_is_reject(cfg->fc_flags, rt->fib6_nh->fib_nh_dev,
+				   addr_type))
+			rt->fib6_flags = RTF_REJECT | RTF_NONEXTHOP;
+	}
 
 	if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
-		struct net_device *dev = fib6_info_nh_dev(rt);
+		struct net_device *dev = fib6_nh->fib_nh_dev;
 
 		if (!ipv6_chk_addr(net, &cfg->fc_prefsrc, dev, 0)) {
 			NL_SET_ERR_MSG(extack, "Invalid source address");
@@ -3301,6 +3762,12 @@ static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg)
 				info->skip_notify = 1;
 		}
 
+		info->skip_notify_kernel = 1;
+		call_fib6_multipath_entry_notifiers(net,
+						    FIB_EVENT_ENTRY_DEL,
+						    rt,
+						    rt->fib6_nsiblings,
+						    NULL);
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &rt->fib6_siblings,
 					 fib6_siblings) {
@@ -3323,7 +3790,7 @@ out_put:
 	return err;
 }
 
-static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
+static int __ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
 {
 	int rc = -ESRCH;
 
@@ -3339,10 +3806,49 @@ out:
 	return rc;
 }
 
+static int ip6_del_cached_rt(struct fib6_config *cfg, struct fib6_info *rt,
+			     struct fib6_nh *nh)
+{
+	struct fib6_result res = {
+		.f6i = rt,
+		.nh = nh,
+	};
+	struct rt6_info *rt_cache;
+
+	rt_cache = rt6_find_cached_rt(&res, &cfg->fc_dst, &cfg->fc_src);
+	if (rt_cache)
+		return __ip6_del_cached_rt(rt_cache, cfg);
+
+	return 0;
+}
+
+struct fib6_nh_del_cached_rt_arg {
+	struct fib6_config *cfg;
+	struct fib6_info *f6i;
+};
+
+static int fib6_nh_del_cached_rt(struct fib6_nh *nh, void *_arg)
+{
+	struct fib6_nh_del_cached_rt_arg *arg = _arg;
+	int rc;
+
+	rc = ip6_del_cached_rt(arg->cfg, arg->f6i, nh);
+	return rc != -ESRCH ? rc : 0;
+}
+
+static int ip6_del_cached_rt_nh(struct fib6_config *cfg, struct fib6_info *f6i)
+{
+	struct fib6_nh_del_cached_rt_arg arg = {
+		.cfg = cfg,
+		.f6i = f6i
+	};
+
+	return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_del_cached_rt, &arg);
+}
+
 static int ip6_route_del(struct fib6_config *cfg,
 			 struct netlink_ext_ack *extack)
 {
-	struct rt6_info *rt_cache;
 	struct fib6_table *table;
 	struct fib6_info *rt;
 	struct fib6_node *fn;
@@ -3365,26 +3871,45 @@ static int ip6_route_del(struct fib6_config *cfg,
 		for_each_fib6_node_rt_rcu(fn) {
 			struct fib6_nh *nh;
 
+			if (rt->nh && cfg->fc_nh_id &&
+			    rt->nh->id != cfg->fc_nh_id)
+				continue;
+
 			if (cfg->fc_flags & RTF_CACHE) {
-				struct fib6_result res = {
-					.f6i = rt,
-				};
-				int rc;
-
-				rt_cache = rt6_find_cached_rt(&res,
-							      &cfg->fc_dst,
-							      &cfg->fc_src);
-				if (rt_cache) {
-					rc = ip6_del_cached_rt(rt_cache, cfg);
-					if (rc != -ESRCH) {
-						rcu_read_unlock();
-						return rc;
-					}
+				int rc = 0;
+
+				if (rt->nh) {
+					rc = ip6_del_cached_rt_nh(cfg, rt);
+				} else if (cfg->fc_nh_id) {
+					continue;
+				} else {
+					nh = rt->fib6_nh;
+					rc = ip6_del_cached_rt(cfg, rt, nh);
+				}
+				if (rc != -ESRCH) {
+					rcu_read_unlock();
+					return rc;
 				}
 				continue;
 			}
 
-			nh = &rt->fib6_nh;
+			if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
+				continue;
+			if (cfg->fc_protocol &&
+			    cfg->fc_protocol != rt->fib6_protocol)
+				continue;
+
+			if (rt->nh) {
+				if (!fib6_info_hold_safe(rt))
+					continue;
+				rcu_read_unlock();
+
+				return __ip6_del_rt(rt, &cfg->fc_nlinfo);
+			}
+			if (cfg->fc_nh_id)
+				continue;
+
+			nh = rt->fib6_nh;
 			if (cfg->fc_ifindex &&
 			    (!nh->fib_nh_dev ||
 			     nh->fib_nh_dev->ifindex != cfg->fc_ifindex))
@@ -3392,10 +3917,6 @@ static int ip6_route_del(struct fib6_config *cfg,
 			if (cfg->fc_flags & RTF_GATEWAY &&
 			    !ipv6_addr_equal(&cfg->fc_gateway, &nh->fib_nh_gw6))
 				continue;
-			if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
-				continue;
-			if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
-				continue;
 			if (!fib6_info_hold_safe(rt))
 				continue;
 			rcu_read_unlock();
@@ -3506,7 +4027,25 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
 	if (!res.f6i)
 		goto out;
 
-	res.nh = &res.f6i->fib6_nh;
+	if (res.f6i->nh) {
+		struct fib6_nh_match_arg arg = {
+			.dev = dst->dev,
+			.gw = &rt->rt6i_gateway,
+		};
+
+		nexthop_for_each_fib6_nh(res.f6i->nh,
+					 fib6_nh_find_match, &arg);
+
+		/* fib6_info uses a nexthop that does not have fib6_nh
+		 * using the dst->dev. Should be impossible
+		 */
+		if (!arg.match)
+			goto out;
+		res.nh = arg.match;
+	} else {
+		res.nh = res.f6i->fib6_nh;
+	}
+
 	res.fib6_flags = res.f6i->fib6_flags;
 	res.fib6_type = res.f6i->fib6_type;
 	nrt = ip6_rt_cache_alloc(&res, &msg->dest, NULL);
@@ -3558,12 +4097,15 @@ static struct fib6_info *rt6_get_route_info(struct net *net,
 		goto out;
 
 	for_each_fib6_node_rt_rcu(fn) {
-		if (rt->fib6_nh.fib_nh_dev->ifindex != ifindex)
+		/* these routes do not use nexthops */
+		if (rt->nh)
+			continue;
+		if (rt->fib6_nh->fib_nh_dev->ifindex != ifindex)
 			continue;
 		if (!(rt->fib6_flags & RTF_ROUTEINFO) ||
-		    !rt->fib6_nh.fib_nh_gw_family)
+		    !rt->fib6_nh->fib_nh_gw_family)
 			continue;
-		if (!ipv6_addr_equal(&rt->fib6_nh.fib_nh_gw6, gwaddr))
+		if (!ipv6_addr_equal(&rt->fib6_nh->fib_nh_gw6, gwaddr))
 			continue;
 		if (!fib6_info_hold_safe(rt))
 			continue;
@@ -3621,8 +4163,13 @@ struct fib6_info *rt6_get_dflt_router(struct net *net,
 
 	rcu_read_lock();
 	for_each_fib6_node_rt_rcu(&table->tb6_root) {
-		struct fib6_nh *nh = &rt->fib6_nh;
+		struct fib6_nh *nh;
+
+		/* RA routes do not use nexthops */
+		if (rt->nh)
+			continue;
 
+		nh = rt->fib6_nh;
 		if (dev == nh->fib_nh_dev &&
 		    ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
 		    ipv6_addr_equal(&nh->fib_nh_gw6, addr))
@@ -3873,7 +4420,8 @@ static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
 	struct net *net = ((struct arg_dev_net_ip *)arg)->net;
 	struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
 
-	if (((void *)rt->fib6_nh.fib_nh_dev == dev || !dev) &&
+	if (!rt->nh &&
+	    ((void *)rt->fib6_nh->fib_nh_dev == dev || !dev) &&
 	    rt != net->ipv6.fib6_null_entry &&
 	    ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) {
 		spin_lock_bh(&rt6_exception_lock);
@@ -3901,18 +4449,22 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
 static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
 {
 	struct in6_addr *gateway = (struct in6_addr *)arg;
+	struct fib6_nh *nh;
 
+	/* RA routes do not use nexthops */
+	if (rt->nh)
+		return 0;
+
+	nh = rt->fib6_nh;
 	if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
-	    rt->fib6_nh.fib_nh_gw_family &&
-	    ipv6_addr_equal(gateway, &rt->fib6_nh.fib_nh_gw6)) {
+	    nh->fib_nh_gw_family && ipv6_addr_equal(gateway, &nh->fib_nh_gw6))
 		return -1;
-	}
 
 	/* Further clean up cached routes in exception table.
 	 * This is needed because cached route may have a different
 	 * gateway than its 'parent' in the case of an ip redirect.
 	 */
-	rt6_exceptions_clean_tohost(rt, gateway);
+	fib6_nh_exceptions_clean_tohost(nh, gateway);
 
 	return 0;
 }
@@ -3950,11 +4502,12 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
 	return NULL;
 }
 
+/* only called for fib entries with builtin fib6_nh */
 static bool rt6_is_dead(const struct fib6_info *rt)
 {
-	if (rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD ||
-	    (rt->fib6_nh.fib_nh_flags & RTNH_F_LINKDOWN &&
-	     ip6_ignore_linkdown(rt->fib6_nh.fib_nh_dev)))
+	if (rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD ||
+	    (rt->fib6_nh->fib_nh_flags & RTNH_F_LINKDOWN &&
+	     ip6_ignore_linkdown(rt->fib6_nh->fib_nh_dev)))
 		return true;
 
 	return false;
@@ -3966,11 +4519,11 @@ static int rt6_multipath_total_weight(const struct fib6_info *rt)
 	int total = 0;
 
 	if (!rt6_is_dead(rt))
-		total += rt->fib6_nh.fib_nh_weight;
+		total += rt->fib6_nh->fib_nh_weight;
 
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
 		if (!rt6_is_dead(iter))
-			total += iter->fib6_nh.fib_nh_weight;
+			total += iter->fib6_nh->fib_nh_weight;
 	}
 
 	return total;
@@ -3981,11 +4534,11 @@ static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total)
 	int upper_bound = -1;
 
 	if (!rt6_is_dead(rt)) {
-		*weight += rt->fib6_nh.fib_nh_weight;
+		*weight += rt->fib6_nh->fib_nh_weight;
 		upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31,
 						    total) - 1;
 	}
-	atomic_set(&rt->fib6_nh.fib_nh_upper_bound, upper_bound);
+	atomic_set(&rt->fib6_nh->fib_nh_upper_bound, upper_bound);
 }
 
 static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total)
@@ -4028,9 +4581,9 @@ static int fib6_ifup(struct fib6_info *rt, void *p_arg)
 	const struct arg_netdev_event *arg = p_arg;
 	struct net *net = dev_net(arg->dev);
 
-	if (rt != net->ipv6.fib6_null_entry &&
-	    rt->fib6_nh.fib_nh_dev == arg->dev) {
-		rt->fib6_nh.fib_nh_flags &= ~arg->nh_flags;
+	if (rt != net->ipv6.fib6_null_entry && !rt->nh &&
+	    rt->fib6_nh->fib_nh_dev == arg->dev) {
+		rt->fib6_nh->fib_nh_flags &= ~arg->nh_flags;
 		fib6_update_sernum_upto_root(net, rt);
 		rt6_multipath_rebalance(rt);
 	}
@@ -4053,15 +4606,16 @@ void rt6_sync_up(struct net_device *dev, unsigned char nh_flags)
 	fib6_clean_all(dev_net(dev), fib6_ifup, &arg);
 }
 
+/* only called for fib entries with inline fib6_nh */
 static bool rt6_multipath_uses_dev(const struct fib6_info *rt,
 				   const struct net_device *dev)
 {
 	struct fib6_info *iter;
 
-	if (rt->fib6_nh.fib_nh_dev == dev)
+	if (rt->fib6_nh->fib_nh_dev == dev)
 		return true;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.fib_nh_dev == dev)
+		if (iter->fib6_nh->fib_nh_dev == dev)
 			return true;
 
 	return false;
@@ -4082,12 +4636,12 @@ static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt,
 	struct fib6_info *iter;
 	unsigned int dead = 0;
 
-	if (rt->fib6_nh.fib_nh_dev == down_dev ||
-	    rt->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
+	if (rt->fib6_nh->fib_nh_dev == down_dev ||
+	    rt->fib6_nh->fib_nh_flags & RTNH_F_DEAD)
 		dead++;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.fib_nh_dev == down_dev ||
-		    iter->fib6_nh.fib_nh_flags & RTNH_F_DEAD)
+		if (iter->fib6_nh->fib_nh_dev == down_dev ||
+		    iter->fib6_nh->fib_nh_flags & RTNH_F_DEAD)
 			dead++;
 
 	return dead;
@@ -4099,11 +4653,11 @@ static void rt6_multipath_nh_flags_set(struct fib6_info *rt,
 {
 	struct fib6_info *iter;
 
-	if (rt->fib6_nh.fib_nh_dev == dev)
-		rt->fib6_nh.fib_nh_flags |= nh_flags;
+	if (rt->fib6_nh->fib_nh_dev == dev)
+		rt->fib6_nh->fib_nh_flags |= nh_flags;
 	list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
-		if (iter->fib6_nh.fib_nh_dev == dev)
-			iter->fib6_nh.fib_nh_flags |= nh_flags;
+		if (iter->fib6_nh->fib_nh_dev == dev)
+			iter->fib6_nh->fib_nh_flags |= nh_flags;
 }
 
 /* called with write lock held for table with rt */
@@ -4113,17 +4667,17 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
 	const struct net_device *dev = arg->dev;
 	struct net *net = dev_net(dev);
 
-	if (rt == net->ipv6.fib6_null_entry)
+	if (rt == net->ipv6.fib6_null_entry || rt->nh)
 		return 0;
 
 	switch (arg->event) {
 	case NETDEV_UNREGISTER:
-		return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
+		return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0;
 	case NETDEV_DOWN:
 		if (rt->should_flush)
 			return -1;
 		if (!rt->fib6_nsiblings)
-			return rt->fib6_nh.fib_nh_dev == dev ? -1 : 0;
+			return rt->fib6_nh->fib_nh_dev == dev ? -1 : 0;
 		if (rt6_multipath_uses_dev(rt, dev)) {
 			unsigned int count;
 
@@ -4139,10 +4693,10 @@ static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
 		}
 		return -2;
 	case NETDEV_CHANGE:
-		if (rt->fib6_nh.fib_nh_dev != dev ||
+		if (rt->fib6_nh->fib_nh_dev != dev ||
 		    rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
 			break;
-		rt->fib6_nh.fib_nh_flags |= RTNH_F_LINKDOWN;
+		rt->fib6_nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 		rt6_multipath_rebalance(rt);
 		break;
 	}
@@ -4176,9 +4730,36 @@ void rt6_disable_ip(struct net_device *dev, unsigned long event)
 struct rt6_mtu_change_arg {
 	struct net_device *dev;
 	unsigned int mtu;
+	struct fib6_info *f6i;
 };
 
-static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
+static int fib6_nh_mtu_change(struct fib6_nh *nh, void *_arg)
+{
+	struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *)_arg;
+	struct fib6_info *f6i = arg->f6i;
+
+	/* For administrative MTU increase, there is no way to discover
+	 * IPv6 PMTU increase, so PMTU increase should be updated here.
+	 * Since RFC 1981 doesn't include administrative MTU increase
+	 * update PMTU increase is a MUST. (i.e. jumbo frame)
+	 */
+	if (nh->fib_nh_dev == arg->dev) {
+		struct inet6_dev *idev = __in6_dev_get(arg->dev);
+		u32 mtu = f6i->fib6_pmtu;
+
+		if (mtu >= arg->mtu ||
+		    (mtu < arg->mtu && mtu == idev->cnf.mtu6))
+			fib6_metric_set(f6i, RTAX_MTU, arg->mtu);
+
+		spin_lock_bh(&rt6_exception_lock);
+		rt6_exceptions_update_pmtu(idev, nh, arg->mtu);
+		spin_unlock_bh(&rt6_exception_lock);
+	}
+
+	return 0;
+}
+
+static int rt6_mtu_change_route(struct fib6_info *f6i, void *p_arg)
 {
 	struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
 	struct inet6_dev *idev;
@@ -4193,24 +4774,17 @@ static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
 	if (!idev)
 		return 0;
 
-	/* For administrative MTU increase, there is no way to discover
-	   IPv6 PMTU increase, so PMTU increase should be updated here.
-	   Since RFC 1981 doesn't include administrative MTU increase
-	   update PMTU increase is a MUST. (i.e. jumbo frame)
-	 */
-	if (rt->fib6_nh.fib_nh_dev == arg->dev &&
-	    !fib6_metric_locked(rt, RTAX_MTU)) {
-		u32 mtu = rt->fib6_pmtu;
-
-		if (mtu >= arg->mtu ||
-		    (mtu < arg->mtu && mtu == idev->cnf.mtu6))
-			fib6_metric_set(rt, RTAX_MTU, arg->mtu);
+	if (fib6_metric_locked(f6i, RTAX_MTU))
+		return 0;
 
-		spin_lock_bh(&rt6_exception_lock);
-		rt6_exceptions_update_pmtu(idev, rt, arg->mtu);
-		spin_unlock_bh(&rt6_exception_lock);
+	arg->f6i = f6i;
+	if (f6i->nh) {
+		/* fib6_nh_mtu_change only returns 0, so this is safe */
+		return nexthop_for_each_fib6_nh(f6i->nh, fib6_nh_mtu_change,
+						arg);
 	}
-	return 0;
+
+	return fib6_nh_mtu_change(f6i->fib6_nh, arg);
 }
 
 void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
@@ -4224,6 +4798,7 @@ void rt6_mtu_change(struct net_device *dev, unsigned int mtu)
 }
 
 static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
+	[RTA_UNSPEC]		= { .strict_start_type = RTA_DPORT + 1 },
 	[RTA_GATEWAY]           = { .len = sizeof(struct in6_addr) },
 	[RTA_PREFSRC]		= { .len = sizeof(struct in6_addr) },
 	[RTA_OIF]               = { .type = NLA_U32 },
@@ -4241,6 +4816,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
 	[RTA_IP_PROTO]		= { .type = NLA_U8 },
 	[RTA_SPORT]		= { .type = NLA_U16 },
 	[RTA_DPORT]		= { .type = NLA_U16 },
+	[RTA_NH_ID]		= { .type = NLA_U32 },
 };
 
 static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4287,6 +4863,16 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	cfg->fc_flags |= (rtm->rtm_flags & RTNH_F_ONLINK);
 
+	if (tb[RTA_NH_ID]) {
+		if (tb[RTA_GATEWAY]   || tb[RTA_OIF] ||
+		    tb[RTA_MULTIPATH] || tb[RTA_ENCAP]) {
+			NL_SET_ERR_MSG(extack,
+				       "Nexthop specification and nexthop id are mutually exclusive");
+			goto errout;
+		}
+		cfg->fc_nh_id = nla_get_u32(tb[RTA_NH_ID]);
+	}
+
 	if (tb[RTA_GATEWAY]) {
 		cfg->fc_gateway = nla_get_in6_addr(tb[RTA_GATEWAY]);
 		cfg->fc_flags |= RTF_GATEWAY;
@@ -4430,6 +5016,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 {
 	struct fib6_info *rt_notif = NULL, *rt_last = NULL;
 	struct nl_info *info = &cfg->fc_nlinfo;
+	enum fib_event_type event_type;
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
 	struct fib6_info *rt;
@@ -4489,7 +5076,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 			goto cleanup;
 		}
 
-		rt->fib6_nh.fib_nh_weight = rtnh->rtnh_hops + 1;
+		rt->fib6_nh->fib_nh_weight = rtnh->rtnh_hops + 1;
 
 		err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
 					    rt, &r_cfg);
@@ -4501,12 +5088,23 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		rtnh = rtnh_next(rtnh, &remaining);
 	}
 
+	if (list_empty(&rt6_nh_list)) {
+		NL_SET_ERR_MSG(extack,
+			       "Invalid nexthop configuration - no valid nexthops");
+		return -EINVAL;
+	}
+
 	/* for add and replace send one notification with all nexthops.
 	 * Skip the notification in fib6_add_rt2node and send one with
 	 * the full route when done
 	 */
 	info->skip_notify = 1;
 
+	/* For add and replace, send one notification with all nexthops. For
+	 * append, send one notification with all appended nexthops.
+	 */
+	info->skip_notify_kernel = 1;
+
 	err_nh = NULL;
 	list_for_each_entry(nh, &rt6_nh_list, next) {
 		err = __ip6_ins_rt(nh->fib6_info, info, extack);
@@ -4543,6 +5141,15 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
 		nhn++;
 	}
 
+	event_type = replace ? FIB_EVENT_ENTRY_REPLACE : FIB_EVENT_ENTRY_ADD;
+	err = call_fib6_multipath_entry_notifiers(info->nl_net, event_type,
+						  rt_notif, nhn - 1, extack);
+	if (err) {
+		/* Delete all the siblings that were just added */
+		err_nh = NULL;
+		goto add_errout;
+	}
+
 	/* success ... tell user about new route */
 	ip6_route_mpath_notify(rt_notif, rt_last, info, nlflags);
 	goto cleanup;
@@ -4621,6 +5228,12 @@ static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		return err;
 
+	if (cfg.fc_nh_id &&
+	    !nexthop_find_by_id(sock_net(skb->sk), cfg.fc_nh_id)) {
+		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+		return -EINVAL;
+	}
+
 	if (cfg.fc_mp)
 		return ip6_route_multipath_del(&cfg, extack);
 	else {
@@ -4648,17 +5261,46 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return ip6_route_add(&cfg, GFP_KERNEL, extack);
 }
 
-static size_t rt6_nlmsg_size(struct fib6_info *rt)
+/* add the overhead of this fib6_nh to nexthop_len */
+static int rt6_nh_nlmsg_size(struct fib6_nh *nh, void *arg)
 {
-	int nexthop_len = 0;
+	int *nexthop_len = arg;
 
-	if (rt->fib6_nsiblings) {
-		nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
-			    + NLA_ALIGN(sizeof(struct rtnexthop))
-			    + nla_total_size(16) /* RTA_GATEWAY */
-			    + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws);
+	*nexthop_len += nla_total_size(0)	 /* RTA_MULTIPATH */
+		     + NLA_ALIGN(sizeof(struct rtnexthop))
+		     + nla_total_size(16); /* RTA_GATEWAY */
 
-		nexthop_len *= rt->fib6_nsiblings;
+	if (nh->fib_nh_lws) {
+		/* RTA_ENCAP_TYPE */
+		*nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
+		/* RTA_ENCAP */
+		*nexthop_len += nla_total_size(2);
+	}
+
+	return 0;
+}
+
+static size_t rt6_nlmsg_size(struct fib6_info *f6i)
+{
+	int nexthop_len;
+
+	if (f6i->nh) {
+		nexthop_len = nla_total_size(4); /* RTA_NH_ID */
+		nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size,
+					 &nexthop_len);
+	} else {
+		struct fib6_nh *nh = f6i->fib6_nh;
+
+		nexthop_len = 0;
+		if (f6i->fib6_nsiblings) {
+			nexthop_len = nla_total_size(0)	 /* RTA_MULTIPATH */
+				    + NLA_ALIGN(sizeof(struct rtnexthop))
+				    + nla_total_size(16) /* RTA_GATEWAY */
+				    + lwtunnel_get_encap_size(nh->fib_nh_lws);
+
+			nexthop_len *= f6i->fib6_nsiblings;
+		}
+		nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws);
 	}
 
 	return NLMSG_ALIGN(sizeof(struct rtmsg))
@@ -4674,10 +5316,38 @@ static size_t rt6_nlmsg_size(struct fib6_info *rt)
 	       + nla_total_size(sizeof(struct rta_cacheinfo))
 	       + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
 	       + nla_total_size(1) /* RTA_PREF */
-	       + lwtunnel_get_encap_size(rt->fib6_nh.fib_nh_lws)
 	       + nexthop_len;
 }
 
+static int rt6_fill_node_nexthop(struct sk_buff *skb, struct nexthop *nh,
+				 unsigned char *flags)
+{
+	if (nexthop_is_multipath(nh)) {
+		struct nlattr *mp;
+
+		mp = nla_nest_start(skb, RTA_MULTIPATH);
+		if (!mp)
+			goto nla_put_failure;
+
+		if (nexthop_mpath_fill_node(skb, nh))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, mp);
+	} else {
+		struct fib6_nh *fib6_nh;
+
+		fib6_nh = nexthop_fib6_nh(nh);
+		if (fib_nexthop_info(skb, &fib6_nh->nh_common,
+				     flags, false) < 0)
+			goto nla_put_failure;
+	}
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
 static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 			 struct fib6_info *rt, struct dst_entry *dst,
 			 struct in6_addr *dest, struct in6_addr *src,
@@ -4687,6 +5357,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 	struct rt6key *rt6_dst, *rt6_src;
 	u32 *pmetrics, table, rt6_flags;
+	unsigned char nh_flags = 0;
 	struct nlmsghdr *nlh;
 	struct rtmsg *rtm;
 	long expires = 0;
@@ -4794,22 +5465,31 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 		if (!mp)
 			goto nla_put_failure;
 
-		if (fib_add_nexthop(skb, &rt->fib6_nh.nh_common,
-				    rt->fib6_nh.fib_nh_weight) < 0)
+		if (fib_add_nexthop(skb, &rt->fib6_nh->nh_common,
+				    rt->fib6_nh->fib_nh_weight) < 0)
 			goto nla_put_failure;
 
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &rt->fib6_siblings, fib6_siblings) {
-			if (fib_add_nexthop(skb, &sibling->fib6_nh.nh_common,
-					    sibling->fib6_nh.fib_nh_weight) < 0)
+			if (fib_add_nexthop(skb, &sibling->fib6_nh->nh_common,
+					    sibling->fib6_nh->fib_nh_weight) < 0)
 				goto nla_put_failure;
 		}
 
 		nla_nest_end(skb, mp);
-	} else {
-		unsigned char nh_flags = 0;
+	} else if (rt->nh) {
+		if (nla_put_u32(skb, RTA_NH_ID, rt->nh->id))
+			goto nla_put_failure;
 
-		if (fib_nexthop_info(skb, &rt->fib6_nh.nh_common,
+		if (nexthop_is_blackhole(rt->nh))
+			rtm->rtm_type = RTN_BLACKHOLE;
+
+		if (rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0)
+			goto nla_put_failure;
+
+		rtm->rtm_flags |= nh_flags;
+	} else {
+		if (fib_nexthop_info(skb, &rt->fib6_nh->nh_common,
 				     &nh_flags, false) < 0)
 			goto nla_put_failure;
 
@@ -4836,10 +5516,28 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static int fib6_info_nh_uses_dev(struct fib6_nh *nh, void *arg)
+{
+	const struct net_device *dev = arg;
+
+	if (nh->fib_nh_dev == dev)
+		return 1;
+
+	return 0;
+}
+
 static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 			       const struct net_device *dev)
 {
-	if (f6i->fib6_nh.fib_nh_dev == dev)
+	if (f6i->nh) {
+		struct net_device *_dev = (struct net_device *)dev;
+
+		return !!nexthop_for_each_fib6_nh(f6i->nh,
+						  fib6_info_nh_uses_dev,
+						  _dev);
+	}
+
+	if (f6i->fib6_nh->fib_nh_dev == dev)
 		return true;
 
 	if (f6i->fib6_nsiblings) {
@@ -4847,7 +5545,7 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 
 		list_for_each_entry_safe(sibling, next_sibling,
 					 &f6i->fib6_siblings, fib6_siblings) {
-			if (sibling->fib6_nh.fib_nh_dev == dev)
+			if (sibling->fib6_nh->fib_nh_dev == dev)
 				return true;
 		}
 	}
@@ -4855,33 +5553,131 @@ static bool fib6_info_uses_dev(const struct fib6_info *f6i,
 	return false;
 }
 
-int rt6_dump_route(struct fib6_info *rt, void *p_arg)
+struct fib6_nh_exception_dump_walker {
+	struct rt6_rtnl_dump_arg *dump;
+	struct fib6_info *rt;
+	unsigned int flags;
+	unsigned int skip;
+	unsigned int count;
+};
+
+static int rt6_nh_dump_exceptions(struct fib6_nh *nh, void *arg)
+{
+	struct fib6_nh_exception_dump_walker *w = arg;
+	struct rt6_rtnl_dump_arg *dump = w->dump;
+	struct rt6_exception_bucket *bucket;
+	struct rt6_exception *rt6_ex;
+	int i, err;
+
+	bucket = fib6_nh_get_excptn_bucket(nh, NULL);
+	if (!bucket)
+		return 0;
+
+	for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+		hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+			if (w->skip) {
+				w->skip--;
+				continue;
+			}
+
+			/* Expiration of entries doesn't bump sernum, insertion
+			 * does. Removal is triggered by insertion, so we can
+			 * rely on the fact that if entries change between two
+			 * partial dumps, this node is scanned again completely,
+			 * see rt6_insert_exception() and fib6_dump_table().
+			 *
+			 * Count expired entries we go through as handled
+			 * entries that we'll skip next time, in case of partial
+			 * node dump. Otherwise, if entries expire meanwhile,
+			 * we'll skip the wrong amount.
+			 */
+			if (rt6_check_expired(rt6_ex->rt6i)) {
+				w->count++;
+				continue;
+			}
+
+			err = rt6_fill_node(dump->net, dump->skb, w->rt,
+					    &rt6_ex->rt6i->dst, NULL, NULL, 0,
+					    RTM_NEWROUTE,
+					    NETLINK_CB(dump->cb->skb).portid,
+					    dump->cb->nlh->nlmsg_seq, w->flags);
+			if (err)
+				return err;
+
+			w->count++;
+		}
+		bucket++;
+	}
+
+	return 0;
+}
+
+/* Return -1 if done with node, number of handled routes on partial dump */
+int rt6_dump_route(struct fib6_info *rt, void *p_arg, unsigned int skip)
 {
 	struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
 	struct fib_dump_filter *filter = &arg->filter;
 	unsigned int flags = NLM_F_MULTI;
 	struct net *net = arg->net;
+	int count = 0;
 
 	if (rt == net->ipv6.fib6_null_entry)
-		return 0;
+		return -1;
 
 	if ((filter->flags & RTM_F_PREFIX) &&
 	    !(rt->fib6_flags & RTF_PREFIX_RT)) {
 		/* success since this is not a prefix route */
-		return 1;
+		return -1;
 	}
-	if (filter->filter_set) {
-		if ((filter->rt_type && rt->fib6_type != filter->rt_type) ||
-		    (filter->dev && !fib6_info_uses_dev(rt, filter->dev)) ||
-		    (filter->protocol && rt->fib6_protocol != filter->protocol)) {
-			return 1;
-		}
+	if (filter->filter_set &&
+	    ((filter->rt_type  && rt->fib6_type != filter->rt_type) ||
+	     (filter->dev      && !fib6_info_uses_dev(rt, filter->dev)) ||
+	     (filter->protocol && rt->fib6_protocol != filter->protocol))) {
+		return -1;
+	}
+
+	if (filter->filter_set ||
+	    !filter->dump_routes || !filter->dump_exceptions) {
 		flags |= NLM_F_DUMP_FILTERED;
 	}
 
-	return rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0,
-			     RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid,
-			     arg->cb->nlh->nlmsg_seq, flags);
+	if (filter->dump_routes) {
+		if (skip) {
+			skip--;
+		} else {
+			if (rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL,
+					  0, RTM_NEWROUTE,
+					  NETLINK_CB(arg->cb->skb).portid,
+					  arg->cb->nlh->nlmsg_seq, flags)) {
+				return 0;
+			}
+			count++;
+		}
+	}
+
+	if (filter->dump_exceptions) {
+		struct fib6_nh_exception_dump_walker w = { .dump = arg,
+							   .rt = rt,
+							   .flags = flags,
+							   .skip = skip,
+							   .count = 0 };
+		int err;
+
+		rcu_read_lock();
+		if (rt->nh) {
+			err = nexthop_for_each_fib6_nh(rt->nh,
+						       rt6_nh_dump_exceptions,
+						       &w);
+		} else {
+			err = rt6_nh_dump_exceptions(rt->fib6_nh, &w);
+		}
+		rcu_read_unlock();
+
+		if (err)
+			return count += w.count;
+	}
+
+	return -1;
 }
 
 static int inet6_rtm_valid_getroute_req(struct sk_buff *skb,
@@ -5126,6 +5922,38 @@ errout:
 		rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
 }
 
+void fib6_rt_update(struct net *net, struct fib6_info *rt,
+		    struct nl_info *info)
+{
+	u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	/* call_fib6_entry_notifiers will be removed when in-kernel notifier
+	 * is implemented and supported for nexthop objects
+	 */
+	call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, rt, NULL);
+
+	skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
+	if (!skb)
+		goto errout;
+
+	err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0,
+			    RTM_NEWROUTE, info->portid, seq, NLM_F_REPLACE);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+	rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
+		    info->nlh, gfp_any());
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
+}
+
 static int ip6_route_dev_notify(struct notifier_block *this,
 				unsigned long event, void *ptr)
 {
@@ -5136,7 +5964,7 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 		return NOTIFY_OK;
 
 	if (event == NETDEV_REGISTER) {
-		net->ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = dev;
+		net->ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = dev;
 		net->ipv6.ip6_null_entry->dst.dev = dev;
 		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -5330,11 +6158,11 @@ static int __net_init ip6_route_net_init(struct net *net)
 	if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
 		goto out_ip6_dst_ops;
 
-	net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template,
-					    sizeof(*net->ipv6.fib6_null_entry),
-					    GFP_KERNEL);
+	net->ipv6.fib6_null_entry = fib6_info_alloc(GFP_KERNEL, true);
 	if (!net->ipv6.fib6_null_entry)
 		goto out_ip6_dst_entries;
+	memcpy(net->ipv6.fib6_null_entry, &fib6_null_entry_template,
+	       sizeof(*net->ipv6.fib6_null_entry));
 
 	net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
 					   sizeof(*net->ipv6.ip6_null_entry),
@@ -5344,6 +6172,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
 			 ip6_template_metrics, true);
+	INIT_LIST_HEAD(&net->ipv6.ip6_null_entry->rt6i_uncached);
 
 #ifdef CONFIG_IPV6_MULTIPLE_TABLES
 	net->ipv6.fib6_has_custom_rules = false;
@@ -5355,6 +6184,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
 			 ip6_template_metrics, true);
+	INIT_LIST_HEAD(&net->ipv6.ip6_prohibit_entry->rt6i_uncached);
 
 	net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
 					       sizeof(*net->ipv6.ip6_blk_hole_entry),
@@ -5364,6 +6194,7 @@ static int __net_init ip6_route_net_init(struct net *net)
 	net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
 	dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
 			 ip6_template_metrics, true);
+	INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->rt6i_uncached);
 #endif
 
 	net->ipv6.sysctl.flush_delay = 0;
@@ -5471,7 +6302,7 @@ void __init ip6_route_init_special_entries(void)
 	/* Registering of the loopback is done before this portion of code,
 	 * the loopback reference in rt6_info will not be taken, do it
 	 * manually for init_net */
-	init_net.ipv6.fib6_null_entry->fib6_nh.fib_nh_dev = init_net.loopback_dev;
+	init_net.ipv6.fib6_null_entry->fib6_nh->fib_nh_dev = init_net.loopback_dev;
 	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
 	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
   #ifdef CONFIG_IPV6_MULTIPLE_TABLES