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

Pull networking updates from David Miller:

 1) Allow setting bluetooth L2CAP modes via socket option, from Luiz
    Augusto von Dentz.

 2) Add GSO partial support to igc, from Sasha Neftin.

 3) Several cleanups and improvements to r8169 from Heiner Kallweit.

 4) Add IF_OPER_TESTING link state and use it when ethtool triggers a
    device self-test. From Andrew Lunn.

 5) Start moving away from custom driver versions, use the globally
    defined kernel version instead, from Leon Romanovsky.

 6) Support GRO vis gro_cells in DSA layer, from Alexander Lobakin.

 7) Allow hard IRQ deferral during NAPI, from Eric Dumazet.

 8) Add sriov and vf support to hinic, from Luo bin.

 9) Support Media Redundancy Protocol (MRP) in the bridging code, from
    Horatiu Vultur.

10) Support netmap in the nft_nat code, from Pablo Neira Ayuso.

11) Allow UDPv6 encapsulation of ESP in the ipsec code, from Sabrina
    Dubroca. Also add ipv6 support for espintcp.

12) Lots of ReST conversions of the networking documentation, from Mauro
    Carvalho Chehab.

13) Support configuration of ethtool rxnfc flows in bcmgenet driver,
    from Doug Berger.

14) Allow to dump cgroup id and filter by it in inet_diag code, from
    Dmitry Yakunin.

15) Add infrastructure to export netlink attribute policies to
    userspace, from Johannes Berg.

16) Several optimizations to sch_fq scheduler, from Eric Dumazet.

17) Fallback to the default qdisc if qdisc init fails because otherwise
    a packet scheduler init failure will make a device inoperative. From
    Jesper Dangaard Brouer.

18) Several RISCV bpf jit optimizations, from Luke Nelson.

19) Correct the return type of the ->ndo_start_xmit() method in several
    drivers, it's netdev_tx_t but many drivers were using
    'int'. From Yunjian Wang.

20) Add an ethtool interface for PHY master/slave config, from Oleksij
    Rempel.

21) Add BPF iterators, from Yonghang Song.

22) Add cable test infrastructure, including ethool interfaces, from
    Andrew Lunn. Marvell PHY driver is the first to support this
    facility.

23) Remove zero-length arrays all over, from Gustavo A. R. Silva.

24) Calculate and maintain an explicit frame size in XDP, from Jesper
    Dangaard Brouer.

25) Add CAP_BPF, from Alexei Starovoitov.

26) Support terse dumps in the packet scheduler, from Vlad Buslov.

27) Support XDP_TX bulking in dpaa2 driver, from Ioana Ciornei.

28) Add devm_register_netdev(), from Bartosz Golaszewski.

29) Minimize qdisc resets, from Cong Wang.

30) Get rid of kernel_getsockopt and kernel_setsockopt in order to
    eliminate set_fs/get_fs calls. From Christoph Hellwig.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (2517 commits)
  selftests: net: ip_defrag: ignore EPERM
  net_failover: fixed rollback in net_failover_open()
  Revert "tipc: Fix potential tipc_aead refcnt leak in tipc_crypto_rcv"
  Revert "tipc: Fix potential tipc_node refcnt leak in tipc_rcv"
  vmxnet3: allow rx flow hash ops only when rss is enabled
  hinic: add set_channels ethtool_ops support
  selftests/bpf: Add a default $(CXX) value
  tools/bpf: Don't use $(COMPILE.c)
  bpf, selftests: Use bpf_probe_read_kernel
  s390/bpf: Use bcr 0,%0 as tail call nop filler
  s390/bpf: Maintain 8-byte stack alignment
  selftests/bpf: Fix verifier test
  selftests/bpf: Fix sample_cnt shared between two threads
  bpf, selftests: Adapt cls_redirect to call csum_level helper
  bpf: Add csum_level helper for fixing up csum levels
  bpf: Fix up bpf_skb_adjust_room helper's skb csum setting
  sfc: add missing annotation for efx_ef10_try_update_nic_stats_vf()
  crypto/chtls: IPv6 support for inline TLS
  Crypto/chcr: Fixes a coccinile check error
  Crypto/chcr: Fixes compilations warnings
  ...

1 files changed, 311 insertions, 63 deletions

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index a5b415fed11e..5bb448ae6c9c 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -26,6 +26,7 @@
 #include <net/netns/generic.h>
 #include <net/tun_proto.h>
 #include <net/vxlan.h>
+#include <net/nexthop.h>
 
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ip6_tunnel.h>
@@ -78,6 +79,9 @@ struct vxlan_fdb {
 	u16		  state;	/* see ndm_state */
 	__be32		  vni;
 	u16		  flags;	/* see ndm_flags and below */
+	struct list_head  nh_list;
+	struct nexthop __rcu *nh;
+	struct vxlan_dev  __rcu *vdev;
 };
 
 #define NTF_VXLAN_ADDED_BY_USER 0x100
@@ -174,11 +178,15 @@ static inline struct hlist_head *vs_head(struct net *net, __be16 port)
  */
 static inline struct vxlan_rdst *first_remote_rcu(struct vxlan_fdb *fdb)
 {
+	if (rcu_access_pointer(fdb->nh))
+		return NULL;
 	return list_entry_rcu(fdb->remotes.next, struct vxlan_rdst, list);
 }
 
 static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
 {
+	if (rcu_access_pointer(fdb->nh))
+		return NULL;
 	return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
 }
 
@@ -251,9 +259,12 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 {
 	unsigned long now = jiffies;
 	struct nda_cacheinfo ci;
+	bool send_ip, send_eth;
 	struct nlmsghdr *nlh;
+	struct nexthop *nh;
 	struct ndmsg *ndm;
-	bool send_ip, send_eth;
+	int nh_family;
+	u32 nh_id;
 
 	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
 	if (nlh == NULL)
@@ -264,16 +275,28 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 
 	send_eth = send_ip = true;
 
+	rcu_read_lock();
+	nh = rcu_dereference(fdb->nh);
+	if (nh) {
+		nh_family = nexthop_get_family(nh);
+		nh_id = nh->id;
+	}
+	rcu_read_unlock();
+
 	if (type == RTM_GETNEIGH) {
-		send_ip = !vxlan_addr_any(&rdst->remote_ip);
+		if (rdst) {
+			send_ip = !vxlan_addr_any(&rdst->remote_ip);
+			ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET;
+		} else if (nh) {
+			ndm->ndm_family = nh_family;
+		}
 		send_eth = !is_zero_ether_addr(fdb->eth_addr);
-		ndm->ndm_family = send_ip ? rdst->remote_ip.sa.sa_family : AF_INET;
 	} else
 		ndm->ndm_family	= AF_BRIDGE;
 	ndm->ndm_state = fdb->state;
 	ndm->ndm_ifindex = vxlan->dev->ifindex;
 	ndm->ndm_flags = fdb->flags;
-	if (rdst->offloaded)
+	if (rdst && rdst->offloaded)
 		ndm->ndm_flags |= NTF_OFFLOADED;
 	ndm->ndm_type = RTN_UNICAST;
 
@@ -284,23 +307,30 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 
 	if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
 		goto nla_put_failure;
+	if (nh) {
+		if (nla_put_u32(skb, NDA_NH_ID, nh_id))
+			goto nla_put_failure;
+	} else if (rdst) {
+		if (send_ip && vxlan_nla_put_addr(skb, NDA_DST,
+						  &rdst->remote_ip))
+			goto nla_put_failure;
+
+		if (rdst->remote_port &&
+		    rdst->remote_port != vxlan->cfg.dst_port &&
+		    nla_put_be16(skb, NDA_PORT, rdst->remote_port))
+			goto nla_put_failure;
+		if (rdst->remote_vni != vxlan->default_dst.remote_vni &&
+		    nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni)))
+			goto nla_put_failure;
+		if (rdst->remote_ifindex &&
+		    nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex))
+			goto nla_put_failure;
+	}
 
-	if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip))
-		goto nla_put_failure;
-
-	if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port &&
-	    nla_put_be16(skb, NDA_PORT, rdst->remote_port))
-		goto nla_put_failure;
-	if (rdst->remote_vni != vxlan->default_dst.remote_vni &&
-	    nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni)))
-		goto nla_put_failure;
 	if ((vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) && fdb->vni &&
 	    nla_put_u32(skb, NDA_SRC_VNI,
 			be32_to_cpu(fdb->vni)))
 		goto nla_put_failure;
-	if (rdst->remote_ifindex &&
-	    nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex))
-		goto nla_put_failure;
 
 	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
 	ci.ndm_confirmed = 0;
@@ -401,7 +431,7 @@ static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
 {
 	int err;
 
-	if (swdev_notify) {
+	if (swdev_notify && rd) {
 		switch (type) {
 		case RTM_NEWNEIGH:
 			err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd,
@@ -793,8 +823,9 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-static struct vxlan_fdb *vxlan_fdb_alloc(const u8 *mac, __u16 state,
-					 __be32 src_vni, __u16 ndm_flags)
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan, const u8 *mac,
+					 __u16 state, __be32 src_vni,
+					 __u16 ndm_flags)
 {
 	struct vxlan_fdb *f;
 
@@ -805,6 +836,9 @@ static struct vxlan_fdb *vxlan_fdb_alloc(const u8 *mac, __u16 state,
 	f->flags = ndm_flags;
 	f->updated = f->used = jiffies;
 	f->vni = src_vni;
+	f->nh = NULL;
+	RCU_INIT_POINTER(f->vdev, vxlan);
+	INIT_LIST_HEAD(&f->nh_list);
 	INIT_LIST_HEAD(&f->remotes);
 	memcpy(f->eth_addr, mac, ETH_ALEN);
 
@@ -819,11 +853,78 @@ static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac,
 			   vxlan_fdb_head(vxlan, mac, src_vni));
 }
 
+static int vxlan_fdb_nh_update(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
+			       u32 nhid, struct netlink_ext_ack *extack)
+{
+	struct nexthop *old_nh = rtnl_dereference(fdb->nh);
+	struct nh_group *nhg;
+	struct nexthop *nh;
+	int err = -EINVAL;
+
+	if (old_nh && old_nh->id == nhid)
+		return 0;
+
+	nh = nexthop_find_by_id(vxlan->net, nhid);
+	if (!nh) {
+		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
+		goto err_inval;
+	}
+
+	if (nh) {
+		if (!nexthop_get(nh)) {
+			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+			nh = NULL;
+			goto err_inval;
+		}
+		if (!nh->is_fdb_nh) {
+			NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop");
+			goto err_inval;
+		}
+
+		nhg = rtnl_dereference(nh->nh_grp);
+		if (!nh->is_group || !nhg->mpath) {
+			NL_SET_ERR_MSG(extack, "Nexthop is not a multipath group");
+			goto err_inval;
+		}
+
+		/* check nexthop group family */
+		switch (vxlan->default_dst.remote_ip.sa.sa_family) {
+		case AF_INET:
+			if (!nhg->has_v4) {
+				err = -EAFNOSUPPORT;
+				NL_SET_ERR_MSG(extack, "Nexthop group family not supported");
+				goto err_inval;
+			}
+			break;
+		case AF_INET6:
+			if (nhg->has_v4) {
+				err = -EAFNOSUPPORT;
+				NL_SET_ERR_MSG(extack, "Nexthop group family not supported");
+				goto err_inval;
+			}
+		}
+	}
+
+	if (old_nh) {
+		list_del_rcu(&fdb->nh_list);
+		nexthop_put(old_nh);
+	}
+	rcu_assign_pointer(fdb->nh, nh);
+	list_add_tail_rcu(&fdb->nh_list, &nh->fdb_list);
+	return 1;
+
+err_inval:
+	if (nh)
+		nexthop_put(nh);
+	return err;
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __be16 port, __be32 src_vni,
 			    __be32 vni, __u32 ifindex, __u16 ndm_flags,
-			    struct vxlan_fdb **fdb)
+			    u32 nhid, struct vxlan_fdb **fdb,
+			    struct netlink_ext_ack *extack)
 {
 	struct vxlan_rdst *rd = NULL;
 	struct vxlan_fdb *f;
@@ -834,24 +935,37 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		return -ENOSPC;
 
 	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
-	f = vxlan_fdb_alloc(mac, state, src_vni, ndm_flags);
+	f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
 	if (!f)
 		return -ENOMEM;
 
-	rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
-	if (rc < 0) {
-		kfree(f);
-		return rc;
-	}
+	if (nhid)
+		rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack);
+	else
+		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+	if (rc < 0)
+		goto errout;
 
 	*fdb = f;
 
 	return 0;
+
+errout:
+	kfree(f);
+	return rc;
 }
 
 static void __vxlan_fdb_free(struct vxlan_fdb *f)
 {
 	struct vxlan_rdst *rd, *nd;
+	struct nexthop *nh;
+
+	nh = rcu_dereference_raw(f->nh);
+	if (nh) {
+		rcu_assign_pointer(f->nh, NULL);
+		rcu_assign_pointer(f->vdev, NULL);
+		nexthop_put(nh);
+	}
 
 	list_for_each_entry_safe(rd, nd, &f->remotes, list) {
 		dst_cache_destroy(&rd->dst_cache);
@@ -875,12 +989,18 @@ static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 	netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr);
 
 	--vxlan->addrcnt;
-	if (do_notify)
-		list_for_each_entry(rd, &f->remotes, list)
-			vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH,
+	if (do_notify) {
+		if (rcu_access_pointer(f->nh))
+			vxlan_fdb_notify(vxlan, f, NULL, RTM_DELNEIGH,
 					 swdev_notify, NULL);
+		else
+			list_for_each_entry(rd, &f->remotes, list)
+				vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH,
+						 swdev_notify, NULL);
+	}
 
 	hlist_del_rcu(&f->hlist);
+	list_del_rcu(&f->nh_list);
 	call_rcu(&f->rcu, vxlan_fdb_free);
 }
 
@@ -897,7 +1017,7 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 				     __u16 state, __u16 flags,
 				     __be16 port, __be32 vni,
 				     __u32 ifindex, __u16 ndm_flags,
-				     struct vxlan_fdb *f,
+				     struct vxlan_fdb *f, u32 nhid,
 				     bool swdev_notify,
 				     struct netlink_ext_ack *extack)
 {
@@ -908,6 +1028,18 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	int rc = 0;
 	int err;
 
+	if (nhid && !rcu_access_pointer(f->nh)) {
+		NL_SET_ERR_MSG(extack,
+			       "Cannot replace an existing non nexthop fdb with a nexthop");
+		return -EOPNOTSUPP;
+	}
+
+	if (nhid && (flags & NLM_F_APPEND)) {
+		NL_SET_ERR_MSG(extack,
+			       "Cannot append to a nexthop fdb");
+		return -EOPNOTSUPP;
+	}
+
 	/* Do not allow an externally learned entry to take over an entry added
 	 * by the user.
 	 */
@@ -929,10 +1061,17 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 		/* Only change unicasts */
 		if (!(is_multicast_ether_addr(f->eth_addr) ||
 		      is_zero_ether_addr(f->eth_addr))) {
-			rc = vxlan_fdb_replace(f, ip, port, vni,
-					       ifindex, &oldrd);
+			if (nhid) {
+				rc = vxlan_fdb_nh_update(vxlan, f, nhid, extack);
+				if (rc < 0)
+					return rc;
+			} else {
+				rc = vxlan_fdb_replace(f, ip, port, vni,
+						       ifindex, &oldrd);
+			}
 			notify |= rc;
 		} else {
+			NL_SET_ERR_MSG(extack, "Cannot replace non-unicast fdb entries");
 			return -EOPNOTSUPP;
 		}
 	}
@@ -962,6 +1101,8 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	return 0;
 
 err_notify:
+	if (nhid)
+		return err;
 	if ((flags & NLM_F_REPLACE) && rc)
 		*rd = oldrd;
 	else if ((flags & NLM_F_APPEND) && rc) {
@@ -975,7 +1116,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan,
 				   const u8 *mac, union vxlan_addr *ip,
 				   __u16 state, __u16 flags,
 				   __be16 port, __be32 src_vni, __be32 vni,
-				   __u32 ifindex, __u16 ndm_flags,
+				   __u32 ifindex, __u16 ndm_flags, u32 nhid,
 				   bool swdev_notify,
 				   struct netlink_ext_ack *extack)
 {
@@ -990,7 +1131,7 @@ static int vxlan_fdb_update_create(struct vxlan_dev *vxlan,
 
 	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
 	rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
-			      vni, ifindex, fdb_flags, &f);
+			      vni, ifindex, fdb_flags, nhid, &f, extack);
 	if (rc < 0)
 		return rc;
 
@@ -1012,7 +1153,7 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
-			    __u32 ifindex, __u16 ndm_flags,
+			    __u32 ifindex, __u16 ndm_flags, u32 nhid,
 			    bool swdev_notify,
 			    struct netlink_ext_ack *extack)
 {
@@ -1028,14 +1169,15 @@ static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 
 		return vxlan_fdb_update_existing(vxlan, ip, state, flags, port,
 						 vni, ifindex, ndm_flags, f,
-						 swdev_notify, extack);
+						 nhid, swdev_notify, extack);
 	} else {
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
 
 		return vxlan_fdb_update_create(vxlan, mac, ip, state, flags,
 					       port, src_vni, vni, ifindex,
-					       ndm_flags, swdev_notify, extack);
+					       ndm_flags, nhid, swdev_notify,
+					       extack);
 	}
 }
 
@@ -1049,11 +1191,15 @@ static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
 
 static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
 			   union vxlan_addr *ip, __be16 *port, __be32 *src_vni,
-			   __be32 *vni, u32 *ifindex)
+			   __be32 *vni, u32 *ifindex, u32 *nhid)
 {
 	struct net *net = dev_net(vxlan->dev);
 	int err;
 
+	if (tb[NDA_NH_ID] && (tb[NDA_DST] || tb[NDA_VNI] || tb[NDA_IFINDEX] ||
+	    tb[NDA_PORT]))
+		return -EINVAL;
+
 	if (tb[NDA_DST]) {
 		err = vxlan_nla_get_addr(ip, tb[NDA_DST]);
 		if (err)
@@ -1109,6 +1255,11 @@ static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
 		*ifindex = 0;
 	}
 
+	if (tb[NDA_NH_ID])
+		*nhid = nla_get_u32(tb[NDA_NH_ID]);
+	else
+		*nhid = 0;
+
 	return 0;
 }
 
@@ -1123,7 +1274,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	union vxlan_addr ip;
 	__be16 port;
 	__be32 src_vni, vni;
-	u32 ifindex;
+	u32 ifindex, nhid;
 	u32 hash_index;
 	int err;
 
@@ -1133,10 +1284,11 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EINVAL;
 	}
 
-	if (tb[NDA_DST] == NULL)
+	if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID]))
 		return -EINVAL;
 
-	err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex);
+	err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex,
+			      &nhid);
 	if (err)
 		return err;
 
@@ -1148,7 +1300,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex,
 			       ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER,
-			       true, extack);
+			       nhid, true, extack);
 	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 
 	return err;
@@ -1159,8 +1311,8 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 			      __be16 port, __be32 src_vni, __be32 vni,
 			      u32 ifindex, bool swdev_notify)
 {
-	struct vxlan_fdb *f;
 	struct vxlan_rdst *rd = NULL;
+	struct vxlan_fdb *f;
 	int err = -ENOENT;
 
 	f = vxlan_find_mac(vxlan, addr, src_vni);
@@ -1195,12 +1347,13 @@ static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	union vxlan_addr ip;
 	__be32 src_vni, vni;
-	__be16 port;
-	u32 ifindex;
+	u32 ifindex, nhid;
 	u32 hash_index;
+	__be16 port;
 	int err;
 
-	err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex);
+	err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex,
+			      &nhid);
 	if (err)
 		return err;
 
@@ -1228,6 +1381,17 @@ static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
 		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
 			struct vxlan_rdst *rd;
 
+			if (rcu_access_pointer(f->nh)) {
+				err = vxlan_fdb_info(skb, vxlan, f,
+						     NETLINK_CB(cb->skb).portid,
+						     cb->nlh->nlmsg_seq,
+						     RTM_NEWNEIGH,
+						     NLM_F_MULTI, NULL);
+				if (err < 0)
+					goto out;
+				continue;
+			}
+
 			list_for_each_entry_rcu(rd, &f->remotes, list) {
 				if (*idx < cb->args[2])
 					goto skip;
@@ -1311,6 +1475,10 @@ static bool vxlan_snoop(struct net_device *dev,
 		if (f->state & (NUD_PERMANENT | NUD_NOARP))
 			return true;
 
+		/* Don't override an fdb with nexthop with a learnt entry */
+		if (rcu_access_pointer(f->nh))
+			return true;
+
 		if (net_ratelimit())
 			netdev_info(dev,
 				    "%pM migrated from %pIS to %pIS\n",
@@ -1333,7 +1501,7 @@ static bool vxlan_snoop(struct net_device *dev,
 					 vxlan->cfg.dst_port,
 					 vni,
 					 vxlan->default_dst.remote_vni,
-					 ifindex, NTF_SELF, true, NULL);
+					 ifindex, NTF_SELF, 0, true, NULL);
 		spin_unlock(&vxlan->hash_lock[hash_index]);
 	}
 
@@ -1924,6 +2092,10 @@ static struct sk_buff *vxlan_na_create(struct sk_buff *request,
 	ns_olen = request->len - skb_network_offset(request) -
 		sizeof(struct ipv6hdr) - sizeof(*ns);
 	for (i = 0; i < ns_olen-1; i += (ns->opt[i+1]<<3)) {
+		if (!ns->opt[i + 1]) {
+			kfree_skb(reply);
+			return NULL;
+		}
 		if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) {
 			daddr = ns->opt + i + sizeof(struct nd_opt_hdr);
 			break;
@@ -2616,6 +2788,38 @@ tx_error:
 	kfree_skb(skb);
 }
 
+static void vxlan_xmit_nh(struct sk_buff *skb, struct net_device *dev,
+			  struct vxlan_fdb *f, __be32 vni, bool did_rsc)
+{
+	struct vxlan_rdst nh_rdst;
+	struct nexthop *nh;
+	bool do_xmit;
+	u32 hash;
+
+	memset(&nh_rdst, 0, sizeof(struct vxlan_rdst));
+	hash = skb_get_hash(skb);
+
+	rcu_read_lock();
+	nh = rcu_dereference(f->nh);
+	if (!nh) {
+		rcu_read_unlock();
+		goto drop;
+	}
+	do_xmit = vxlan_fdb_nh_path_select(nh, hash, &nh_rdst);
+	rcu_read_unlock();
+
+	if (likely(do_xmit))
+		vxlan_xmit_one(skb, dev, vni, &nh_rdst, did_rsc);
+	else
+		goto drop;
+
+	return;
+
+drop:
+	dev->stats.tx_dropped++;
+	dev_kfree_skb(skb);
+}
+
 /* Transmit local packets over Vxlan
  *
  * Outer IP header inherits ECN and DF from inner header.
@@ -2692,22 +2896,27 @@ static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	list_for_each_entry_rcu(rdst, &f->remotes, list) {
-		struct sk_buff *skb1;
+	if (rcu_access_pointer(f->nh)) {
+		vxlan_xmit_nh(skb, dev, f,
+			      (vni ? : vxlan->default_dst.remote_vni), did_rsc);
+	} else {
+		list_for_each_entry_rcu(rdst, &f->remotes, list) {
+			struct sk_buff *skb1;
 
-		if (!fdst) {
-			fdst = rdst;
-			continue;
+			if (!fdst) {
+				fdst = rdst;
+				continue;
+			}
+			skb1 = skb_clone(skb, GFP_ATOMIC);
+			if (skb1)
+				vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc);
 		}
-		skb1 = skb_clone(skb, GFP_ATOMIC);
-		if (skb1)
-			vxlan_xmit_one(skb1, dev, vni, rdst, did_rsc);
+		if (fdst)
+			vxlan_xmit_one(skb, dev, vni, fdst, did_rsc);
+		else
+			kfree_skb(skb);
 	}
 
-	if (fdst)
-		vxlan_xmit_one(skb, dev, vni, fdst, did_rsc);
-	else
-		kfree_skb(skb);
 	return NETDEV_TX_OK;
 }
 
@@ -3615,7 +3824,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 				       dst->remote_vni,
 				       dst->remote_vni,
 				       dst->remote_ifindex,
-				       NTF_SELF, &f);
+				       NTF_SELF, 0, &f, extack);
 		if (err)
 			return err;
 	}
@@ -4013,7 +4222,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					       vxlan->cfg.dst_port,
 					       conf.vni, conf.vni,
 					       conf.remote_ifindex,
-					       NTF_SELF, true, extack);
+					       NTF_SELF, 0, true, extack);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 				netdev_adjacent_change_abort(dst->remote_dev,
@@ -4335,7 +4544,7 @@ vxlan_fdb_external_learn_add(struct net_device *dev,
 			       fdb_info->remote_vni,
 			       fdb_info->remote_ifindex,
 			       NTF_USE | NTF_SELF | NTF_EXT_LEARNED,
-			       false, extack);
+			       0, false, extack);
 	spin_unlock_bh(&vxlan->hash_lock[hash_index]);
 
 	return err;
@@ -4410,6 +4619,43 @@ static struct notifier_block vxlan_switchdev_notifier_block __read_mostly = {
 	.notifier_call = vxlan_switchdev_event,
 };
 
+static void vxlan_fdb_nh_flush(struct nexthop *nh)
+{
+	struct vxlan_fdb *fdb;
+	struct vxlan_dev *vxlan;
+	u32 hash_index;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(fdb, &nh->fdb_list, nh_list) {
+		vxlan = rcu_dereference(fdb->vdev);
+		WARN_ON(!vxlan);
+		hash_index = fdb_head_index(vxlan, fdb->eth_addr,
+					    vxlan->default_dst.remote_vni);
+		spin_lock_bh(&vxlan->hash_lock[hash_index]);
+		if (!hlist_unhashed(&fdb->hlist))
+			vxlan_fdb_destroy(vxlan, fdb, false, false);
+		spin_unlock_bh(&vxlan->hash_lock[hash_index]);
+	}
+	rcu_read_unlock();
+}
+
+static int vxlan_nexthop_event(struct notifier_block *nb,
+			       unsigned long event, void *ptr)
+{
+	struct nexthop *nh = ptr;
+
+	if (!nh || event != NEXTHOP_EVENT_DEL)
+		return NOTIFY_DONE;
+
+	vxlan_fdb_nh_flush(nh);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block vxlan_nexthop_notifier_block __read_mostly = {
+	.notifier_call = vxlan_nexthop_event,
+};
+
 static __net_init int vxlan_init_net(struct net *net)
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
@@ -4421,7 +4667,7 @@ static __net_init int vxlan_init_net(struct net *net)
 	for (h = 0; h < PORT_HASH_SIZE; ++h)
 		INIT_HLIST_HEAD(&vn->sock_list[h]);
 
-	return 0;
+	return register_nexthop_notifier(net, &vxlan_nexthop_notifier_block);
 }
 
 static void vxlan_destroy_tunnels(struct net *net, struct list_head *head)
@@ -4454,6 +4700,8 @@ static void __net_exit vxlan_exit_batch_net(struct list_head *net_list)
 
 	rtnl_lock();
 	list_for_each_entry(net, net_list, exit_list)
+		unregister_nexthop_notifier(net, &vxlan_nexthop_notifier_block);
+	list_for_each_entry(net, net_list, exit_list)
 		vxlan_destroy_tunnels(net, &list);
 
 	unregister_netdevice_many(&list);