drivers/net/vxlan.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * VXLAN: Virtual eXtensible Local Area Network
 *
 * Copyright (c) 2012-2013 Vyatta Inc.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/if_ether.h>
#include <linux/ethtool.h>
#include <net/arp.h>
#include <net/ndisc.h>
#include <net/ipv6_stubs.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/rtnetlink.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#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>
#include <net/ip6_checksum.h>
#endif

#define VXLAN_VERSION	"0.1"

#define PORT_HASH_BITS	8
#define PORT_HASH_SIZE  (1<<PORT_HASH_BITS)
#define FDB_AGE_DEFAULT 300 /* 5 min */
#define FDB_AGE_INTERVAL (10 * HZ)	/* rescan interval */

/* UDP port for VXLAN traffic.
 * The IANA assigned port is 4789, but the Linux default is 8472
 * for compatibility with early adopters.
 */
static unsigned short vxlan_port __read_mostly = 8472;
module_param_named(udp_port, vxlan_port, ushort, 0444);
MODULE_PARM_DESC(udp_port, "Destination UDP port");

static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");

static unsigned int vxlan_net_id;
static struct rtnl_link_ops vxlan_link_ops;

static const u8 all_zeros_mac[ETH_ALEN + 2];

static int vxlan_sock_add(struct vxlan_dev *vxlan);

static void vxlan_vs_del_dev(struct vxlan_dev *vxlan);

/* per-network namespace private data for this module */
struct vxlan_net {
	struct list_head  vxlan_list;
	struct hlist_head sock_list[PORT_HASH_SIZE];
	spinlock_t	  sock_lock;
	struct notifier_block nexthop_notifier_block;
};

/* Forwarding table entry */
struct vxlan_fdb {
	struct hlist_node hlist;	/* linked list of entries */
	struct rcu_head	  rcu;
	unsigned long	  updated;	/* jiffies */
	unsigned long	  used;
	struct list_head  remotes;
	u8		  eth_addr[ETH_ALEN];
	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

/* salt for hash table */
static u32 vxlan_salt __read_mostly;

static inline bool vxlan_collect_metadata(struct vxlan_sock *vs)
{
	return vs->flags & VXLAN_F_COLLECT_METADATA ||
	       ip_tunnel_collect_metadata();
}

#if IS_ENABLED(CONFIG_IPV6)
static inline
bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
{
	if (a->sa.sa_family != b->sa.sa_family)
		return false;
	if (a->sa.sa_family == AF_INET6)
		return ipv6_addr_equal(&a->sin6.sin6_addr, &b->sin6.sin6_addr);
	else
		return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
}

static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
{
	if (nla_len(nla) >= sizeof(struct in6_addr)) {
		ip->sin6.sin6_addr = nla_get_in6_addr(nla);
		ip->sa.sa_family = AF_INET6;
		return 0;
	} else if (nla_len(nla) >= sizeof(__be32)) {
		ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
		ip->sa.sa_family = AF_INET;
		return 0;
	} else {
		return -EAFNOSUPPORT;
	}
}

static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
			      const union vxlan_addr *ip)
{
	if (ip->sa.sa_family == AF_INET6)
		return nla_put_in6_addr(skb, attr, &ip->sin6.sin6_addr);
	else
		return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
}

#else /* !CONFIG_IPV6 */

static inline
bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
{
	return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
}

static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
{
	if (nla_len(nla) >= sizeof(struct in6_addr)) {
		return -EAFNOSUPPORT;
	} else if (nla_len(nla) >= sizeof(__be32)) {
		ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
		ip->sa.sa_family = AF_INET;
		return 0;
	} else {
		return -EAFNOSUPPORT;
	}
}

static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
			      const union vxlan_addr *ip)
{
	return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
}
#endif

/* Virtual Network hash table head */
static inline struct hlist_head *vni_head(struct vxlan_sock *vs, __be32 vni)
{
	return &vs->vni_list[hash_32((__force u32)vni, VNI_HASH_BITS)];
}

/* Socket hash table head */
static inline struct hlist_head *vs_head(struct net *net, __be16 port)
{
	struct vxlan_net *vn = net_generic(net, vxlan_net_id);

	return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
}

/* First remote destination for a forwarding entry.
 * Guaranteed to be non-NULL because remotes are never deleted.
 */
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);
}

/* Find VXLAN socket based on network namespace, address family, UDP port,
 * enabled unshareable flags and socket device binding (see l3mdev with
 * non-default VRF).
 */
static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
					  __be16 port, u32 flags, int ifindex)
{
	struct vxlan_sock *vs;

	flags &= VXLAN_F_RCV_FLAGS;

	hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
		if (inet_sk(vs->sock->sk)->inet_sport == port &&
		    vxlan_get_sk_family(vs) == family &&
		    vs->flags == flags &&
		    vs->sock->sk->sk_bound_dev_if == ifindex)
			return vs;
	}
	return NULL;
}

static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, int ifindex,
					   __be32 vni)
{
	struct vxlan_dev_node *node;

	/* For flow based devices, map all packets to VNI 0 */
	if (vs->flags & VXLAN_F_COLLECT_METADATA)
		vni = 0;

	hlist_for_each_entry_rcu(node, vni_head(vs, vni), hlist) {
		if (node->vxlan->default_dst.remote_vni != vni)
			continue;

		if (IS_ENABLED(CONFIG_IPV6)) {
			const struct vxlan_config *cfg = &node->vxlan->cfg;

			if ((cfg->flags & VXLAN_F_IPV6_LINKLOCAL) &&
			    cfg->remote_ifindex != ifindex)
				continue;
		}

		return node->vxlan;
	}

	return NULL;
}

/* Look up VNI in a per net namespace table */
static struct vxlan_dev *vxlan_find_vni(struct net *net, int ifindex,
					__be32 vni, sa_family_t family,
					__be16 port, u32 flags)
{
	struct vxlan_sock *vs;

	vs = vxlan_find_sock(net, family, port, flags, ifindex);
	if (!vs)
		return NULL;

	return vxlan_vs_find_vni(vs, ifindex, vni);
}

/* Fill in neighbour message in skbuff. */
static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
			  const struct vxlan_fdb *fdb,
			  u32 portid, u32 seq, int type, unsigned int flags,
			  const struct vxlan_rdst *rdst)
{
	unsigned long now = jiffies;
	struct nda_cacheinfo ci;
	bool send_ip, send_eth;
	struct nlmsghdr *nlh;
	struct nexthop *nh;
	struct ndmsg *ndm;
	int nh_family;
	u32 nh_id;

	nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	ndm = nlmsg_data(nlh);
	memset(ndm, 0, sizeof(*ndm));

	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) {
		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);
	} else
		ndm->ndm_family	= AF_BRIDGE;
	ndm->ndm_state = fdb->state;
	ndm->ndm_ifindex = vxlan->dev->ifindex;
	ndm->ndm_flags = fdb->flags;
	if (rdst && rdst->offloaded)
		ndm->ndm_flags |= NTF_OFFLOADED;
	ndm->ndm_type = RTN_UNICAST;

	if (!net_eq(dev_net(vxlan->dev), vxlan->net) &&
	    nla_put_s32(skb, NDA_LINK_NETNSID,
			peernet2id(dev_net(vxlan->dev), vxlan->net)))
		goto nla_put_failure;

	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 ((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;

	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
	ci.ndm_confirmed = 0;
	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
	ci.ndm_refcnt	 = 0;

	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
		goto nla_put_failure;

	nlmsg_end(skb, nlh);
	return 0;

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static inline size_t vxlan_nlmsg_size(void)
{
	return NLMSG_ALIGN(sizeof(struct ndmsg))
		+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
		+ nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */
		+ nla_total_size(sizeof(__be16)) /* NDA_PORT */
		+ nla_total_size(sizeof(__be32)) /* NDA_VNI */
		+ nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */
		+ nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */
		+ nla_total_size(sizeof(struct nda_cacheinfo));
}

static void __vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
			       struct vxlan_rdst *rd, int type)
{
	struct net *net = dev_net(vxlan->dev);
	struct sk_buff *skb;
	int err = -ENOBUFS;

	skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC);
	if (skb == NULL)
		goto errout;

	err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}

	rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
	return;
errout:
	if (err < 0)
		rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}

static void vxlan_fdb_switchdev_notifier_info(const struct vxlan_dev *vxlan,
			    const struct vxlan_fdb *fdb,
			    const struct vxlan_rdst *rd,
			    struct netlink_ext_ack *extack,
			    struct switchdev_notifier_vxlan_fdb_info *fdb_info)
{
	fdb_info->info.dev = vxlan->dev;
	fdb_info->info.extack = extack;
	fdb_info->remote_ip = rd->remote_ip;
	fdb_info->remote_port = rd->remote_port;
	fdb_info->remote_vni = rd->remote_vni;
	fdb_info->remote_ifindex = rd->remote_ifindex;
	memcpy(fdb_info->eth_addr, fdb->eth_addr, ETH_ALEN);
	fdb_info->vni = fdb->vni;
	fdb_info->offloaded = rd->offloaded;
	fdb_info->added_by_user = fdb->flags & NTF_VXLAN_ADDED_BY_USER;
}

static int vxlan_fdb_switchdev_call_notifiers(struct vxlan_dev *vxlan,
					      struct vxlan_fdb *fdb,
					      struct vxlan_rdst *rd,
					      bool adding,
					      struct netlink_ext_ack *extack)
{
	struct switchdev_notifier_vxlan_fdb_info info;
	enum switchdev_notifier_type notifier_type;
	int ret;

	if (WARN_ON(!rd))
		return 0;

	notifier_type = adding ? SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE
			       : SWITCHDEV_VXLAN_FDB_DEL_TO_DEVICE;
	vxlan_fdb_switchdev_notifier_info(vxlan, fdb, rd, NULL, &info);
	ret = call_switchdev_notifiers(notifier_type, vxlan->dev,
				       &info.info, extack);
	return notifier_to_errno(ret);
}

static int vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
			    struct vxlan_rdst *rd, int type, bool swdev_notify,
			    struct netlink_ext_ack *extack)
{
	int err;

	if (swdev_notify && rd) {
		switch (type) {
		case RTM_NEWNEIGH:
			err = vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd,
								 true, extack);
			if (err)
				return err;
			break;
		case RTM_DELNEIGH:
			vxlan_fdb_switchdev_call_notifiers(vxlan, fdb, rd,
							   false, extack);
			break;
		}
	}

	__vxlan_fdb_notify(vxlan, fdb, rd, type);
	return 0;
}

static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	struct vxlan_fdb f = {
		.state = NUD_STALE,
	};
	struct vxlan_rdst remote = {
		.remote_ip = *ipa, /* goes to NDA_DST */
		.remote_vni = cpu_to_be32(VXLAN_N_VID),
	};

	vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL);
}

static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
{
	struct vxlan_fdb f = {
		.state = NUD_STALE,
	};
	struct vxlan_rdst remote = { };

	memcpy(f.eth_addr, eth_addr, ETH_ALEN);

	vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH, true, NULL);
}

/* Hash Ethernet address */
static u32 eth_hash(const unsigned char *addr)
{
	u64 value = get_unaligned((u64 *)addr);

	/* only want 6 bytes */
#ifdef __BIG_ENDIAN
	value >>= 16;
#else
	value <<= 16;
#endif
	return hash_64(value, FDB_HASH_BITS);
}

static u32 eth_vni_hash(const unsigned char *addr, __be32 vni)
{
	/* use 1 byte of OUI and 3 bytes of NIC */
	u32 key = get_unaligned((u32 *)(addr + 2));

	return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1);
}

static u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni)
{
	if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA)
		return eth_vni_hash(mac, vni);
	else
		return eth_hash(mac);
}

/* Hash chain to use given mac address */
static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan,
						const u8 *mac, __be32 vni)
{
	return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)];
}

/* Look up Ethernet address in forwarding table */
static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan,
					  const u8 *mac, __be32 vni)
{
	struct hlist_head *head = vxlan_fdb_head(vxlan, mac, vni);
	struct vxlan_fdb *f;

	hlist_for_each_entry_rcu(f, head, hlist) {
		if (ether_addr_equal(mac, f->eth_addr)) {
			if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) {
				if (vni == f->vni)
					return f;
			} else {
				return f;
			}
		}
	}

	return NULL;
}

static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
					const u8 *mac, __be32 vni)
{
	struct vxlan_fdb *f;

	f = __vxlan_find_mac(vxlan, mac, vni);
	if (f && f->used != jiffies)
		f->used = jiffies;

	return f;
}

/* caller should hold vxlan->hash_lock */
static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,
					      union vxlan_addr *ip, __be16 port,
					      __be32 vni, __u32 ifindex)
{
	struct vxlan_rdst *rd;

	list_for_each_entry(rd, &f->remotes, list) {
		if (vxlan_addr_equal(&rd->remote_ip, ip) &&
		    rd->remote_port == port &&
		    rd->remote_vni == vni &&
		    rd->remote_ifindex == ifindex)
			return rd;
	}

	return NULL;
}

int vxlan_fdb_find_uc(struct net_device *dev, const u8 *mac, __be32 vni,
		      struct switchdev_notifier_vxlan_fdb_info *fdb_info)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	u8 eth_addr[ETH_ALEN + 2] = { 0 };
	struct vxlan_rdst *rdst;
	struct vxlan_fdb *f;
	int rc = 0;

	if (is_multicast_ether_addr(mac) ||
	    is_zero_ether_addr(mac))
		return -EINVAL;

	ether_addr_copy(eth_addr, mac);

	rcu_read_lock();

	f = __vxlan_find_mac(vxlan, eth_addr, vni);
	if (!f) {
		rc = -ENOENT;
		goto out;
	}

	rdst = first_remote_rcu(f);
	vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, NULL, fdb_info);

out:
	rcu_read_unlock();
	return rc;
}
EXPORT_SYMBOL_GPL(vxlan_fdb_find_uc);

static int vxlan_fdb_notify_one(struct notifier_block *nb,
				const struct vxlan_dev *vxlan,
				const struct vxlan_fdb *f,
				const struct vxlan_rdst *rdst,
				struct netlink_ext_ack *extack)
{
	struct switchdev_notifier_vxlan_fdb_info fdb_info;
	int rc;

	vxlan_fdb_switchdev_notifier_info(vxlan, f, rdst, extack, &fdb_info);
	rc = nb->notifier_call(nb, SWITCHDEV_VXLAN_FDB_ADD_TO_DEVICE,
			       &fdb_info);
	return notifier_to_errno(rc);
}

int vxlan_fdb_replay(const struct net_device *dev, __be32 vni,
		     struct notifier_block *nb,
		     struct netlink_ext_ack *extack)
{
	struct vxlan_dev *vxlan;
	struct vxlan_rdst *rdst;
	struct vxlan_fdb *f;
	unsigned int h;
	int rc = 0;

	if (!netif_is_vxlan(dev))
		return -EINVAL;
	vxlan = netdev_priv(dev);

	for (h = 0; h < FDB_HASH_SIZE; ++h) {
		spin_lock_bh(&vxlan->hash_lock[h]);
		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) {
			if (f->vni == vni) {
				list_for_each_entry(rdst, &f->remotes, list) {
					rc = vxlan_fdb_notify_one(nb, vxlan,
								  f, rdst,
								  extack);
					if (rc)
						goto unlock;
				}
			}
		}
		spin_unlock_bh(&vxlan->hash_lock[h]);
	}
	return 0;

unlock:
	spin_unlock_bh(&vxlan->hash_lock[h]);
	return rc;
}
EXPORT_SYMBOL_GPL(vxlan_fdb_replay);

void vxlan_fdb_clear_offload(const struct net_device *dev, __be32 vni)
{
	struct vxlan_dev *vxlan;
	struct vxlan_rdst *rdst;
	struct vxlan_fdb *f;
	unsigned int h;

	if (!netif_is_vxlan(dev))
		return;
	vxlan = netdev_priv(dev);

	for (h = 0; h < FDB_HASH_SIZE; ++h) {
		spin_lock_bh(&vxlan->hash_lock[h]);
		hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist)
			if (f->vni == vni)
				list_for_each_entry(rdst, &f->remotes, list)
					rdst->offloaded = false;
		spin_unlock_bh(&vxlan->hash_lock[h]);
	}

}
EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload);

/* Replace destination of unicast mac */
static int vxlan_fdb_replace(struct vxlan_fdb *f,
			     union vxlan_addr *ip, __be16 port, __be32 vni,
			     __u32 ifindex, struct vxlan_rdst *oldrd)
{
	struct vxlan_rdst *rd;

	rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex);
	if (rd)
		return 0;

	rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list);
	if (!rd)
		return 0;

	*oldrd = *rd;
	dst_cache_reset(&rd->dst_cache);
	rd->remote_ip = *ip;
	rd->remote_port = port;
	rd->remote_vni = vni;
	rd->remote_ifindex = ifindex;
	rd->offloaded = false;
	return 1;
}

/* Add/update destinations for multicast */
static int vxlan_fdb_append(struct vxlan_fdb *f,
			    union vxlan_addr *ip, __be16 port, __be32 vni,
			    __u32 ifindex, struct vxlan_rdst **rdp)
{
	struct vxlan_rdst *rd;

	rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex);
	if (rd)
		return 0;

	rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
	if (rd == NULL)
		return -ENOBUFS;

	if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) {
		kfree(rd);
		return -ENOBUFS;
	}

	rd->remote_ip = *ip;
	rd->remote_port = port;
	rd->offloaded = false;
	rd->remote_vni = vni;
	rd->remote_ifindex = ifindex;

	list_add_tail_rcu(&rd->list, &f->remotes);

	*rdp = rd;
	return 1;
}

static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
					  unsigned int off,
					  struct vxlanhdr *vh, size_t hdrlen,
					  __be32 vni_field,
					  struct gro_remcsum *grc,
					  bool nopartial)
{
	size_t start, offset;

	if (skb->remcsum_offload)
		return vh;

	if (!NAPI_GRO_CB(skb)->csum_valid)
		return NULL;

	start = vxlan_rco_start(vni_field);
	offset = start + vxlan_rco_offset(vni_field);

	vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen,
				     start, offset, grc, nopartial);

	skb->remcsum_offload = 1;

	return vh;
}

static struct sk_buff *vxlan_gro_receive(struct sock *sk,
					 struct list_head *head,
					 struct sk_buff *skb)
{
	struct sk_buff *pp = NULL;
	struct sk_buff *p;
	struct vxlanhdr *vh, *vh2;
	unsigned int hlen, off_vx;
	int flush = 1;
	struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk);
	__be32 flags;
	struct gro_remcsum grc;

	skb_gro_remcsum_init(&grc);

	off_vx = skb_gro_offset(skb);
	hlen = off_vx + sizeof(*vh);
	vh   = skb_gro_header_fast(skb, off_vx);
	if (skb_gro_header_hard(skb, hlen)) {
		vh = skb_gro_header_slow(skb, hlen, off_vx);
		if (unlikely(!vh))
			goto out;
	}

	skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));

	flags = vh->vx_flags;

	if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) {
		vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr),
				       vh->vx_vni, &grc,
				       !!(vs->flags &
					  VXLAN_F_REMCSUM_NOPARTIAL));

		if (!vh)
			goto out;
	}

	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */

	list_for_each_entry(p, head, list) {
		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		vh2 = (struct vxlanhdr *)(p->data + off_vx);
		if (vh->vx_flags != vh2->vx_flags ||
		    vh->vx_vni != vh2->vx_vni) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}
	}

	pp = call_gro_receive(eth_gro_receive, head, skb);
	flush = 0;

out:
	skb_gro_flush_final_remcsum(skb, pp, flush, &grc);

	return pp;
}

static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
{
	/* Sets 'skb->inner_mac_header' since we are always called with
	 * 'skb->encapsulation' set.
	 */
	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
}

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;

	f = kmalloc(sizeof(*f), GFP_ATOMIC);
	if (!f)
		return NULL;
	f->state = 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);

	return f;
}

static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac,
			     __be32 src_vni, struct vxlan_fdb *f)
{
	++vxlan->addrcnt;
	hlist_add_head_rcu(&f->hlist,
			   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 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 (!nexthop_is_fdb(nh)) {
			NL_SET_ERR_MSG(extack, "Nexthop is not a fdb nexthop");
			goto err_inval;
		}

		if (!nexthop_is_multipath(nh)) {
			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 (!nexthop_has_v4(nh)) {
				err = -EAFNOSUPPORT;
				NL_SET_ERR_MSG(extack, "Nexthop group family not supported");
				goto err_inval;
			}
			break;
		case AF_INET6:
			if (nexthop_has_v4(nh)) {
				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,
			    u32 nhid, struct vxlan_fdb **fdb,
			    struct netlink_ext_ack *extack)
{
	struct vxlan_rdst *rd = NULL;
	struct vxlan_fdb *f;
	int rc;

	if (vxlan->cfg.addrmax &&
	    vxlan->addrcnt >= vxlan->cfg.addrmax)
		return -ENOSPC;

	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
	f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
	if (!f)
		return -ENOMEM;

	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);
		kfree(rd);
	}
	kfree(f);
}

static void vxlan_fdb_free(struct rcu_head *head)
{
	struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);

	__vxlan_fdb_free(f);
}

static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
			      bool do_notify, bool swdev_notify)
{
	struct vxlan_rdst *rd;

	netdev_dbg(vxlan->dev, "delete %pM\n", f->eth_addr);

	--vxlan->addrcnt;
	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);
}

static void vxlan_dst_free(struct rcu_head *head)
{
	struct vxlan_rdst *rd = container_of(head, struct vxlan_rdst, rcu);

	dst_cache_destroy(&rd->dst_cache);
	kfree(rd);
}

static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
				     union vxlan_addr *ip,
				     __u16 state, __u16 flags,
				     __be16 port, __be32 vni,
				     __u32 ifindex, __u16 ndm_flags,
				     struct vxlan_fdb *f, u32 nhid,
				     bool swdev_notify,
				     struct netlink_ext_ack *extack)
{
	__u16 fdb_flags = (ndm_flags & ~NTF_USE);
	struct vxlan_rdst *rd = NULL;
	struct vxlan_rdst oldrd;
	int notify = 0;
	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.
	 */
	if (!(fdb_flags & NTF_EXT_LEARNED) ||
	    !(f->flags & NTF_VXLAN_ADDED_BY_USER)) {
		if (f->state != state) {
			f->state = state;
			f->updated = jiffies;
			notify = 1;
		}
		if (f->flags != fdb_flags) {
			f->flags = fdb_flags;
			f->updated = jiffies;
			notify = 1;
		}
	}

	if ((flags & NLM_F_REPLACE)) {
		/* Only change unicasts */
		if (!(is_multicast_ether_addr(f->eth_addr) ||
		      is_zero_ether_addr(f->eth_addr))) {
			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;
		}
	}
	if ((flags & NLM_F_APPEND) &&
	    (is_multicast_ether_addr(f->eth_addr) ||
	     is_zero_ether_addr(f->eth_addr))) {
		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);

		if (rc < 0)
			return rc;
		notify |= rc;
	}

	if (ndm_flags & NTF_USE)
		f->used = jiffies;

	if (notify) {
		if (rd == NULL)
			rd = first_remote_rtnl(f);

		err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH,
				       swdev_notify, extack);
		if (err)
			goto err_notify;
	}

	return 0;

err_notify:
	if (nhid)
		return err;
	if ((flags & NLM_F_REPLACE) && rc)
		*rd = oldrd;
	else if ((flags & NLM_F_APPEND) && rc) {
		list_del_rcu(&rd->list);
		call_rcu(&rd->rcu, vxlan_dst_free);
	}
	return err;
}

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 nhid,
				   bool swdev_notify,
				   struct netlink_ext_ack *extack)
{
	__u16 fdb_flags = (ndm_flags & ~NTF_USE);
	struct vxlan_fdb *f;
	int rc;

	/* Disallow replace to add a multicast entry */
	if ((flags & NLM_F_REPLACE) &&
	    (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
		return -EOPNOTSUPP;

	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, nhid, &f, extack);
	if (rc < 0)
		return rc;

	vxlan_fdb_insert(vxlan, mac, src_vni, f);
	rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH,
			      swdev_notify, extack);
	if (rc)
		goto err_notify;

	return 0;

err_notify:
	vxlan_fdb_destroy(vxlan, f, false, false);
	return rc;
}

/* Add new entry to forwarding table -- assumes lock held */
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 nhid,
			    bool swdev_notify,
			    struct netlink_ext_ack *extack)
{
	struct vxlan_fdb *f;

	f = __vxlan_find_mac(vxlan, mac, src_vni);
	if (f) {
		if (flags & NLM_F_EXCL) {
			netdev_dbg(vxlan->dev,
				   "lost race to create %pM\n", mac);
			return -EEXIST;
		}

		return vxlan_fdb_update_existing(vxlan, ip, state, flags, port,
						 vni, ifindex, ndm_flags, f,
						 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, nhid, swdev_notify,
					       extack);
	}
}

static void vxlan_fdb_dst_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
				  struct vxlan_rdst *rd, bool swdev_notify)
{
	list_del_rcu(&rd->list);
	vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH, swdev_notify, NULL);
	call_rcu(&rd->rcu, vxlan_dst_free);
}

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, 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)
			return err;
	} else {
		union vxlan_addr *remote = &vxlan->default_dst.remote_ip;

		if (remote->sa.sa_family == AF_INET) {
			ip->sin.sin_addr.s_addr = htonl(INADDR_ANY);
			ip->sa.sa_family = AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
		} else {
			ip->sin6.sin6_addr = in6addr_any;
			ip->sa.sa_family = AF_INET6;
#endif
		}
	}

	if (tb[NDA_PORT]) {
		if (nla_len(tb[NDA_PORT]) != sizeof(__be16))
			return -EINVAL;
		*port = nla_get_be16(tb[NDA_PORT]);
	} else {
		*port = vxlan->cfg.dst_port;
	}

	if (tb[NDA_VNI]) {
		if (nla_len(tb[NDA_VNI]) != sizeof(u32))
			return -EINVAL;
		*vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI]));
	} else {
		*vni = vxlan->default_dst.remote_vni;
	}

	if (tb[NDA_SRC_VNI]) {
		if (nla_len(tb[NDA_SRC_VNI]) != sizeof(u32))
			return -EINVAL;
		*src_vni = cpu_to_be32(nla_get_u32(tb[NDA_SRC_VNI]));
	} else {
		*src_vni = vxlan->default_dst.remote_vni;
	}

	if (tb[NDA_IFINDEX]) {
		struct net_device *tdev;

		if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
			return -EINVAL;
		*ifindex = nla_get_u32(tb[NDA_IFINDEX]);
		tdev = __dev_get_by_index(net, *ifindex);
		if (!tdev)
			return -EADDRNOTAVAIL;
	} else {
		*ifindex = 0;
	}

	if (tb[NDA_NH_ID])
		*nhid = nla_get_u32(tb[NDA_NH_ID]);
	else
		*nhid = 0;

	return 0;
}

/* Add static entry (via netlink) */
static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
			 struct net_device *dev,
			 const unsigned char *addr, u16 vid, u16 flags,
			 struct netlink_ext_ack *extack)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	/* struct net *net = dev_net(vxlan->dev); */
	union vxlan_addr ip;
	__be16 port;
	__be32 src_vni, vni;
	u32 ifindex, nhid;
	u32 hash_index;
	int err;

	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) {
		pr_info("RTM_NEWNEIGH with invalid state %#x\n",
			ndm->ndm_state);
		return -EINVAL;
	}

	if (!tb || (!tb[NDA_DST] && !tb[NDA_NH_ID]))
		return -EINVAL;

	err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex,
			      &nhid);
	if (err)
		return err;

	if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
		return -EAFNOSUPPORT;

	hash_index = fdb_head_index(vxlan, addr, src_vni);
	spin_lock_bh(&vxlan->hash_lock[hash_index]);
	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
			       port, src_vni, vni, ifindex,
			       ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER,
			       nhid, true, extack);
	spin_unlock_bh(&vxlan->hash_lock[hash_index]);

	return err;
}

static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
			      const unsigned char *addr, union vxlan_addr ip,
			      __be16 port, __be32 src_vni, __be32 vni,
			      u32 ifindex, bool swdev_notify)
{
	struct vxlan_rdst *rd = NULL;
	struct vxlan_fdb *f;
	int err = -ENOENT;

	f = vxlan_find_mac(vxlan, addr, src_vni);
	if (!f)
		return err;

	if (!vxlan_addr_any(&ip)) {
		rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex);
		if (!rd)
			goto out;
	}

	/* remove a destination if it's not the only one on the list,
	 * otherwise destroy the fdb entry
	 */
	if (rd && !list_is_singular(&f->remotes)) {
		vxlan_fdb_dst_destroy(vxlan, f, rd, swdev_notify);
		goto out;
	}

	vxlan_fdb_destroy(vxlan, f, true, swdev_notify);

out:
	return 0;
}

/* Delete entry (via netlink) */
static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
			    struct net_device *dev,
			    const unsigned char *addr, u16 vid)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	union vxlan_addr ip;
	__be32 src_vni, vni;
	u32 ifindex, nhid;
	u32 hash_index;
	__be16 port;
	int err;

	err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex,
			      &nhid);
	if (err)
		return err;

	hash_index = fdb_head_index(vxlan, addr, src_vni);
	spin_lock_bh(&vxlan->hash_lock[hash_index]);
	err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex,
				 true);
	spin_unlock_bh(&vxlan->hash_lock[hash_index]);

	return err;
}

/* Dump forwarding table */
static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
			  struct net_device *dev,
			  struct net_device *filter_dev, int *idx)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	unsigned int h;
	int err = 0;

	for (h = 0; h < FDB_HASH_SIZE; ++h) {
		struct vxlan_fdb *f;

		rcu_read_lock();
		hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
			struct vxlan_rdst *rd;

			if (rcu_access_pointer(f->nh)) {
				if (*idx < cb->args[2])
					goto skip_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) {
					rcu_read_unlock();
					goto out;
				}
skip_nh:
				*idx += 1;
				continue;
			}

			list_for_each_entry_rcu(rd, &f->remotes, list) {
				if (*idx < cb->args[2])
					goto skip;

				err = vxlan_fdb_info(skb, vxlan, f,
						     NETLINK_CB(cb->skb).portid,
						     cb->nlh->nlmsg_seq,
						     RTM_NEWNEIGH,
						     NLM_F_MULTI, rd);
				if (err < 0) {
					rcu_read_unlock();
					goto out;
				}
skip:
				*idx += 1;
			}
		}
		rcu_read_unlock();
	}
out:
	return err;
}

static int vxlan_fdb_get(struct sk_buff *skb,
			 struct nlattr *tb[],
			 struct net_device *dev,
			 const unsigned char *addr,
			 u16 vid, u32 portid, u32 seq,
			 struct netlink_ext_ack *extack)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	struct vxlan_fdb *f;
	__be32 vni;
	int err;

	if (tb[NDA_VNI])
		vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI]));
	else
		vni = vxlan->default_dst.remote_vni;

	rcu_read_lock();

	f = __vxlan_find_mac(vxlan, addr, vni);
	if (!f) {
		NL_SET_ERR_MSG(extack, "Fdb entry not found");
		err = -ENOENT;
		goto errout;
	}

	err = vxlan_fdb_info(skb, vxlan, f, portid, seq,
			     RTM_NEWNEIGH, 0, first_remote_rcu(f));
errout:
	rcu_read_unlock();
	return err;
}

/* Watch incoming packets to learn mapping between Ethernet address
 * and Tunnel endpoint.
 * Return true if packet is bogus and should be dropped.
 */
static bool vxlan_snoop(struct net_device *dev,
			union vxlan_addr *src_ip, const u8 *src_mac,
			u32 src_ifindex, __be32 vni)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	struct vxlan_fdb *f;
	u32 ifindex = 0;

#if IS_ENABLED(CONFIG_IPV6)
	if (src_ip->sa.sa_family == AF_INET6 &&
	    (ipv6_addr_type(&src_ip->sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL))
		ifindex = src_ifindex;
#endif

	f = vxlan_find_mac(vxlan, src_mac, vni);
	if (likely(f)) {
		struct vxlan_rdst *rdst = first_remote_rcu(f);

		if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) &&
			   rdst->remote_ifindex == ifindex))
			return false;

		/* Don't migrate static entries, drop packets */
		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",
				    src_mac, &rdst->remote_ip.sa, &src_ip->sa);

		rdst->remote_ip = *src_ip;
		f->updated = jiffies;
		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL);
	} else {
		u32 hash_index = fdb_head_index(vxlan, src_mac, vni);

		/* learned new entry */
		spin_lock(&vxlan->hash_lock[hash_index]);

		/* close off race between vxlan_flush and incoming packets */
		if (netif_running(dev))
			vxlan_fdb_update(vxlan, src_mac, src_ip,
					 NUD_REACHABLE,
					 NLM_F_EXCL|NLM_F_CREATE,
					 vxlan->cfg.dst_port,
					 vni,
					 vxlan->default_dst.remote_vni,
					 ifindex, NTF_SELF, 0, true, NULL);
		spin_unlock(&vxlan->hash_lock[hash_index]);
	}

	return false;
}

/* See if multicast group is already in use by other ID */
static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
{
	struct vxlan_dev *vxlan;
	struct vxlan_sock *sock4;
#if IS_ENABLED(CONFIG_IPV6)
	struct vxlan_sock *sock6;
#endif
	unsigned short family = dev->default_dst.remote_ip.sa.sa_family;

	sock4 = rtnl_dereference(dev->vn4_sock);

	/* The vxlan_sock is only used by dev, leaving group has
	 * no effect on other vxlan devices.
	 */
	if (family == AF_INET && sock4 && refcount_read(&sock4->refcnt) == 1)
		return false;
#if IS_ENABLED(CONFIG_IPV6)
	sock6 = rtnl_dereference(dev->vn6_sock);
	if (family == AF_INET6 && sock6 && refcount_read(&sock6->refcnt) == 1)
		return false;
#endif

	list_for_each_entry(vxlan, &vn->vxlan_list, next) {
		if (!netif_running(vxlan->dev) || vxlan == dev)
			continue;

		if (family == AF_INET &&
		    rtnl_dereference(vxlan->vn4_sock) != sock4)
			continue;
#if IS_ENABLED(CONFIG_IPV6)
		if (family == AF_INET6 &&
		    rtnl_dereference(vxlan->vn6_sock) != sock6)
			continue;
#endif

		if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip,
				      &dev->default_dst.remote_ip))
			continue;

		if (vxlan->default_dst.remote_ifindex !=
		    dev->default_dst.remote_ifindex)
			continue;

		return true;
	}

	return false;
}

static bool __vxlan_sock_release_prep(struct vxlan_sock *vs)
{
	struct vxlan_net *vn;

	if (!vs)
		return false;
	if (!refcount_dec_and_test(&vs->refcnt))
		return false;

	vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id);
	spin_lock(&vn->sock_lock);
	hlist_del_rcu(&vs->hlist);
	udp_tunnel_notify_del_rx_port(vs->sock,
				      (vs->flags & VXLAN_F_GPE) ?
				      UDP_TUNNEL_TYPE_VXLAN_GPE :
				      UDP_TUNNEL_TYPE_VXLAN);
	spin_unlock(&vn->sock_lock);

	return true;
}

static void vxlan_sock_release(struct vxlan_dev *vxlan)
{
	struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
#if IS_ENABLED(CONFIG_IPV6)
	struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);

	RCU_INIT_POINTER(vxlan->vn6_sock, NULL);
#endif

	RCU_INIT_POINTER(vxlan->vn4_sock, NULL);
	synchronize_net();

	vxlan_vs_del_dev(vxlan);

	if (__vxlan_sock_release_prep(sock4)) {
		udp_tunnel_sock_release(sock4->sock);
		kfree(sock4);
	}

#if IS_ENABLED(CONFIG_IPV6)
	if (__vxlan_sock_release_prep(sock6)) {
		udp_tunnel_sock_release(sock6->sock);
		kfree(sock6);
	}
#endif
}

/* Update multicast group membership when first VNI on
 * multicast address is brought up
 */
static int vxlan_igmp_join(struct vxlan_dev *vxlan)
{
	struct sock *sk;
	union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
	int ifindex = vxlan->default_dst.remote_ifindex;
	int ret = -EINVAL;

	if (ip->sa.sa_family == AF_INET) {
		struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
		struct ip_mreqn mreq = {
			.imr_multiaddr.s_addr	= ip->sin.sin_addr.s_addr,
			.imr_ifindex		= ifindex,
		};

		sk = sock4->sock->sk;
		lock_sock(sk);
		ret = ip_mc_join_group(sk, &mreq);
		release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
	} else {
		struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);

		sk = sock6->sock->sk;
		lock_sock(sk);
		ret = ipv6_stub->ipv6_sock_mc_join(sk, ifindex,
						   &ip->sin6.sin6_addr);
		release_sock(sk);
#endif
	}

	return ret;
}

/* Inverse of vxlan_igmp_join when last VNI is brought down */
static int vxlan_igmp_leave(struct vxlan_dev *vxlan)
{
	struct sock *sk;
	union vxlan_addr *ip = &vxlan->default_dst.remote_ip;
	int ifindex = vxlan->default_dst.remote_ifindex;
	int ret = -EINVAL;

	if (ip->sa.sa_family == AF_INET) {
		struct vxlan_sock *sock4 = rtnl_dereference(vxlan->vn4_sock);
		struct ip_mreqn mreq = {
			.imr_multiaddr.s_addr	= ip->sin.sin_addr.s_addr,
			.imr_ifindex		= ifindex,
		};

		sk = sock4->sock->sk;
		lock_sock(sk);
		ret = ip_mc_leave_group(sk, &mreq);
		release_sock(sk);
#if IS_ENABLED(CONFIG_IPV6)
	} else {
		struct vxlan_sock *sock6 = rtnl_dereference(vxlan->vn6_sock);

		sk = sock6->sock->sk;
		lock_sock(sk);
		ret = ipv6_stub->ipv6_sock_mc_drop(sk, ifindex,
						   &ip->sin6.sin6_addr);
		release_sock(sk);
#endif
	}

	return ret;
}

static bool vxlan_remcsum(struct vxlanhdr *unparsed,
			  struct sk_buff *skb, u32 vxflags)
{
	size_t start, offset;

	if (!(unparsed->vx_flags & VXLAN_HF_RCO) || skb->remcsum_offload)
		goto out;

	start = vxlan_rco_start(unparsed->vx_vni);
	offset = start + vxlan_rco_offset(unparsed->vx_vni);

	if (!pskb_may_pull(skb, offset + sizeof(u16)))
		return false;

	skb_remcsum_process(skb, (void *)(vxlan_hdr(skb) + 1), start, offset,
			    !!(vxflags & VXLAN_F_REMCSUM_NOPARTIAL));
out:
	unparsed->vx_flags &= ~VXLAN_HF_RCO;
	unparsed->vx_vni &= VXLAN_VNI_MASK;
	return true;
}

static void vxlan_parse_gbp_hdr(struct vxlanhdr *unparsed,
				struct sk_buff *skb, u32 vxflags,
				struct vxlan_metadata *md)
{
	struct vxlanhdr_gbp *gbp = (struct vxlanhdr_gbp *)unparsed;
	struct metadata_dst *tun_dst;

	if (!(unparsed->vx_flags & VXLAN_HF_GBP))
		goto out;

	md->gbp = ntohs(gbp->policy_id);

	tun_dst = (struct metadata_dst *)skb_dst(skb);
	if (tun_dst) {
		tun_dst->u.tun_info.key.tun_flags |= TUNNEL_VXLAN_OPT;
		tun_dst->u.tun_info.options_len = sizeof(*md);
	}
	if (gbp->dont_learn)
		md->gbp |= VXLAN_GBP_DONT_LEARN;

	if (gbp->policy_applied)
		md->gbp |= VXLAN_GBP_POLICY_APPLIED;

	/* In flow-based mode, GBP is carried in dst_metadata */
	if (!(vxflags & VXLAN_F_COLLECT_METADATA))
		skb->mark = md->gbp;
out:
	unparsed->vx_flags &= ~VXLAN_GBP_USED_BITS;
}

static bool vxlan_parse_gpe_hdr(struct vxlanhdr *unparsed,
				__be16 *protocol,
				struct sk_buff *skb, u32 vxflags)
{
	struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)unparsed;

	/* Need to have Next Protocol set for interfaces in GPE mode. */
	if (!gpe->np_applied)
		return false;
	/* "The initial version is 0. If a receiver does not support the
	 * version indicated it MUST drop the packet.
	 */
	if (gpe->version != 0)
		return false;
	/* "When the O bit is set to 1, the packet is an OAM packet and OAM
	 * processing MUST occur." However, we don't implement OAM
	 * processing, thus drop the packet.
	 */
	if (gpe->oam_flag)
		return false;

	*protocol = tun_p_to_eth_p(gpe->next_protocol);
	if (!*protocol)
		return false;

	unparsed->vx_flags &= ~VXLAN_GPE_USED_BITS;
	return true;
}

static bool vxlan_set_mac(struct vxlan_dev *vxlan,
			  struct vxlan_sock *vs,
			  struct sk_buff *skb, __be32 vni)
{
	union vxlan_addr saddr;
	u32 ifindex = skb->dev->ifindex;

	skb_reset_mac_header(skb);
	skb->protocol = eth_type_trans(skb, vxlan->dev);
	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);

	/* Ignore packet loops (and multicast echo) */
	if (ether_addr_equal(eth_hdr(skb)->h_source, vxlan->dev->dev_addr))
		return false;

	/* Get address from the outer IP header */
	if (vxlan_get_sk_family(vs) == AF_INET) {
		saddr.sin.sin_addr.s_addr = ip_hdr(skb)->saddr;
		saddr.sa.sa_family = AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
	} else {
		saddr.sin6.sin6_addr = ipv6_hdr(skb)->saddr;
		saddr.sa.sa_family = AF_INET6;
#endif
	}

	if ((vxlan->cfg.flags & VXLAN_F_LEARN) &&
	    vxlan_snoop(skb->dev, &saddr, eth_hdr(skb)->h_source, ifindex, vni))
		return false;

	return true;
}

static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph,
				  struct sk_buff *skb)
{
	int err = 0;

	if (vxlan_get_sk_family(vs) == AF_INET)
		err = IP_ECN_decapsulate(oiph, skb);
#if IS_ENABLED(CONFIG_IPV6)
	else
		err = IP6_ECN_decapsulate(oiph, skb);
#endif

	if (unlikely(err) && log_ecn_error) {
		if (vxlan_get_sk_family(vs) == AF_INET)
			net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
					     &((struct iphdr *)oiph)->saddr,
					     ((struct iphdr *)oiph)->tos);
		else
			net_info_ratelimited("non-ECT from %pI6\n",
					     &((struct ipv6hdr *)oiph)->saddr);
	}
	return err <= 1;
}

/* Callback from net/ipv4/udp.c to receive packets */
static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct vxlan_dev *vxlan;
	struct vxlan_sock *vs;
	struct vxlanhdr unparsed;
	struct vxlan_metadata _md;
	struct vxlan_metadata *md = &_md;
	__be16 protocol = htons(ETH_P_TEB);
	bool raw_proto = false;
	void *oiph;
	__be32 vni = 0;

	/* Need UDP and VXLAN header to be present */
	if (!pskb_may_pull(skb, VXLAN_HLEN))
		goto drop;

	unparsed = *vxlan_hdr(skb);
	/* VNI flag always required to be set */
	if (!(unparsed.vx_flags & VXLAN_HF_VNI)) {
		netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
			   ntohl(vxlan_hdr(skb)->vx_flags),
			   ntohl(vxlan_hdr(skb)->vx_vni));
		/* Return non vxlan pkt */
		goto drop;
	}
	unparsed.vx_flags &= ~VXLAN_HF_VNI;
	unparsed.vx_vni &= ~VXLAN_VNI_MASK;

	vs = rcu_dereference_sk_user_data(sk);
	if (!vs)
		goto drop;

	vni = vxlan_vni(vxlan_hdr(skb)->vx_vni);

	vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni);
	if (!vxlan)
		goto drop;

	/* For backwards compatibility, only allow reserved fields to be
	 * used by VXLAN extensions if explicitly requested.
	 */
	if (vs->flags & VXLAN_F_GPE) {
		if (!vxlan_parse_gpe_hdr(&unparsed, &protocol, skb, vs->flags))
			goto drop;
		raw_proto = true;
	}

	if (__iptunnel_pull_header(skb, VXLAN_HLEN, protocol, raw_proto,
				   !net_eq(vxlan->net, dev_net(vxlan->dev))))
		goto drop;

	if (vs->flags & VXLAN_F_REMCSUM_RX)
		if (unlikely(!vxlan_remcsum(&unparsed, skb, vs->flags)))
			goto drop;

	if (vxlan_collect_metadata(vs)) {
		struct metadata_dst *tun_dst;

		tun_dst = udp_tun_rx_dst(skb, vxlan_get_sk_family(vs), TUNNEL_KEY,
					 key32_to_tunnel_id(vni), sizeof(*md));

		if (!tun_dst)
			goto drop;

		md = ip_tunnel_info_opts(&tun_dst->u.tun_info);

		skb_dst_set(skb, (struct dst_entry *)tun_dst);
	} else {
		memset(md, 0, sizeof(*md));
	}

	if (vs->flags & VXLAN_F_GBP)
		vxlan_parse_gbp_hdr(&unparsed, skb, vs->flags, md);
	/* Note that GBP and GPE can never be active together. This is
	 * ensured in vxlan_dev_configure.
	 */

	if (unparsed.vx_flags || unparsed.vx_vni) {
		/* If there are any unprocessed flags remaining treat
		 * this as a malformed packet. This behavior diverges from
		 * VXLAN RFC (RFC7348) which stipulates that bits in reserved
		 * in reserved fields are to be ignored. The approach here
		 * maintains compatibility with previous stack code, and also
		 * is more robust and provides a little more security in
		 * adding extensions to VXLAN.
		 */
		goto drop;
	}

	if (!raw_proto) {
		if (!vxlan_set_mac(vxlan, vs, skb, vni))
			goto drop;
	} else {
		skb_reset_mac_header(skb);
		skb->dev = vxlan->dev;
		skb->pkt_type = PACKET_HOST;
	}

	oiph = skb_network_header(skb);
	skb_reset_network_header(skb);

	if (!vxlan_ecn_decapsulate(vs, oiph, skb)) {
		++vxlan->dev->stats.rx_frame_errors;
		++vxlan->dev->stats.rx_errors;
		goto drop;
	}

	rcu_read_lock();

	if (unlikely(!(vxlan->dev->flags & IFF_UP))) {
		rcu_read_unlock();
		atomic_long_inc(&vxlan->dev->rx_dropped);
		goto drop;
	}

	dev_sw_netstats_rx_add(vxlan->dev, skb->len);
	gro_cells_receive(&vxlan->gro_cells, skb);

	rcu_read_unlock();

	return 0;

drop:
	/* Consume bad packet */
	kfree_skb(skb);
	return 0;
}

/* Callback from net/ipv{4,6}/udp.c to check that we have a VNI for errors */
static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb)
{
	struct vxlan_dev *vxlan;
	struct vxlan_sock *vs;
	struct vxlanhdr *hdr;
	__be32 vni;

	if (!pskb_may_pull(skb, skb_transport_offset(skb) + VXLAN_HLEN))
		return -EINVAL;

	hdr = vxlan_hdr(skb);

	if (!(hdr->vx_flags & VXLAN_HF_VNI))
		return -EINVAL;

	vs = rcu_dereference_sk_user_data(sk);
	if (!vs)
		return -ENOENT;

	vni = vxlan_vni(hdr->vx_vni);
	vxlan = vxlan_vs_find_vni(vs, skb->dev->ifindex, vni);
	if (!vxlan)
		return -ENOENT;

	return 0;
}

static int arp_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	struct arphdr *parp;
	u8 *arpptr, *sha;
	__be32 sip, tip;
	struct neighbour *n;

	if (dev->flags & IFF_NOARP)
		goto out;

	if (!pskb_may_pull(skb, arp_hdr_len(dev))) {
		dev->stats.tx_dropped++;
		goto out;
	}
	parp = arp_hdr(skb);

	if ((parp->ar_hrd != htons(ARPHRD_ETHER) &&
	     parp->ar_hrd != htons(ARPHRD_IEEE802)) ||
	    parp->ar_pro != htons(ETH_P_IP) ||
	    parp->ar_op != htons(ARPOP_REQUEST) ||
	    parp->ar_hln != dev->addr_len ||
	    parp->ar_pln != 4)
		goto out;
	arpptr = (u8 *)parp + sizeof(struct arphdr);
	sha = arpptr;
	arpptr += dev->addr_len;	/* sha */
	memcpy(&sip, arpptr, sizeof(sip));
	arpptr += sizeof(sip);
	arpptr += dev->addr_len;	/* tha */
	memcpy(&tip, arpptr, sizeof(tip));

	if (ipv4_is_loopback(tip) ||
	    ipv4_is_multicast(tip))
		goto out;

	n = neigh_lookup(&arp_tbl, &tip, dev);

	if (n) {
		struct vxlan_fdb *f;
		struct sk_buff	*reply;

		if (!(n->nud_state & NUD_CONNECTED)) {
			neigh_release(n);
			goto out;
		}

		f = vxlan_find_mac(vxlan, n->ha, vni);
		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
			/* bridge-local neighbor */
			neigh_release(n);
			goto out;
		}

		reply = arp_create(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha,
				n->ha, sha);

		neigh_release(n);

		if (reply == NULL)
			goto out;

		skb_reset_mac_header(reply);
		__skb_pull(reply, skb_network_offset(reply));
		reply->ip_summed = CHECKSUM_UNNECESSARY;
		reply->pkt_type = PACKET_HOST;

		if (netif_rx_ni(reply) == NET_RX_DROP)
			dev->stats.rx_dropped++;
	} else if (vxlan->cfg.flags & VXLAN_F_L3MISS) {
		union vxlan_addr ipa = {
			.sin.sin_addr.s_addr = tip,
			.sin.sin_family = AF_INET,
		};

		vxlan_ip_miss(dev, &ipa);
	}
out:
	consume_skb(skb);
	return NETDEV_TX_OK;
}

#if IS_ENABLED(CONFIG_IPV6)
static struct sk_buff *vxlan_na_create(struct sk_buff *request,
	struct neighbour *n, bool isrouter)
{
	struct net_device *dev = request->dev;
	struct sk_buff *reply;
	struct nd_msg *ns, *na;
	struct ipv6hdr *pip6;
	u8 *daddr;
	int na_olen = 8; /* opt hdr + ETH_ALEN for target */
	int ns_olen;
	int i, len;

	if (dev == NULL || !pskb_may_pull(request, request->len))
		return NULL;

	len = LL_RESERVED_SPACE(dev) + sizeof(struct ipv6hdr) +
		sizeof(*na) + na_olen + dev->needed_tailroom;
	reply = alloc_skb(len, GFP_ATOMIC);
	if (reply == NULL)
		return NULL;

	reply->protocol = htons(ETH_P_IPV6);
	reply->dev = dev;
	skb_reserve(reply, LL_RESERVED_SPACE(request->dev));
	skb_push(reply, sizeof(struct ethhdr));
	skb_reset_mac_header(reply);

	ns = (struct nd_msg *)(ipv6_hdr(request) + 1);

	daddr = eth_hdr(request)->h_source;
	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;
		}
	}

	/* Ethernet header */
	ether_addr_copy(eth_hdr(reply)->h_dest, daddr);
	ether_addr_copy(eth_hdr(reply)->h_source, n->ha);
	eth_hdr(reply)->h_proto = htons(ETH_P_IPV6);
	reply->protocol = htons(ETH_P_IPV6);

	skb_pull(reply, sizeof(struct ethhdr));
	skb_reset_network_header(reply);
	skb_put(reply, sizeof(struct ipv6hdr));

	/* IPv6 header */

	pip6 = ipv6_hdr(reply);
	memset(pip6, 0, sizeof(struct ipv6hdr));
	pip6->version = 6;
	pip6->priority = ipv6_hdr(request)->priority;
	pip6->nexthdr = IPPROTO_ICMPV6;
	pip6->hop_limit = 255;
	pip6->daddr = ipv6_hdr(request)->saddr;
	pip6->saddr = *(struct in6_addr *)n->primary_key;

	skb_pull(reply, sizeof(struct ipv6hdr));
	skb_reset_transport_header(reply);

	/* Neighbor Advertisement */
	na = skb_put_zero(reply, sizeof(*na) + na_olen);
	na->icmph.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT;
	na->icmph.icmp6_router = isrouter;
	na->icmph.icmp6_override = 1;
	na->icmph.icmp6_solicited = 1;
	na->target = ns->target;
	ether_addr_copy(&na->opt[2], n->ha);
	na->opt[0] = ND_OPT_TARGET_LL_ADDR;
	na->opt[1] = na_olen >> 3;

	na->icmph.icmp6_cksum = csum_ipv6_magic(&pip6->saddr,
		&pip6->daddr, sizeof(*na)+na_olen, IPPROTO_ICMPV6,
		csum_partial(na, sizeof(*na)+na_olen, 0));

	pip6->payload_len = htons(sizeof(*na)+na_olen);

	skb_push(reply, sizeof(struct ipv6hdr));

	reply->ip_summed = CHECKSUM_UNNECESSARY;

	return reply;
}

static int neigh_reduce(struct net_device *dev, struct sk_buff *skb, __be32 vni)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	const struct in6_addr *daddr;
	const struct ipv6hdr *iphdr;
	struct inet6_dev *in6_dev;
	struct neighbour *n;
	struct nd_msg *msg;

	rcu_read_lock();
	in6_dev = __in6_dev_get(dev);
	if (!in6_dev)
		goto out;

	iphdr = ipv6_hdr(skb);
	daddr = &iphdr->daddr;
	msg = (struct nd_msg *)(iphdr + 1);

	if (ipv6_addr_loopback(daddr) ||
	    ipv6_addr_is_multicast(&msg->target))
		goto out;

	n = neigh_lookup(ipv6_stub->nd_tbl, &msg->target, dev);

	if (n) {
		struct vxlan_fdb *f;
		struct sk_buff *reply;

		if (!(n->nud_state & NUD_CONNECTED)) {
			neigh_release(n);
			goto out;
		}

		f = vxlan_find_mac(vxlan, n->ha, vni);
		if (f && vxlan_addr_any(&(first_remote_rcu(f)->remote_ip))) {
			/* bridge-local neighbor */
			neigh_release(n);
			goto out;
		}

		reply = vxlan_na_create(skb, n,
					!!(f ? f->flags & NTF_ROUTER : 0));

		neigh_release(n);

		if (reply == NULL)
			goto out;

		if (netif_rx_ni(reply) == NET_RX_DROP)
			dev->stats.rx_dropped++;

	} else if (vxlan->cfg.flags & VXLAN_F_L3MISS) {
		union vxlan_addr ipa = {
			.sin6.sin6_addr = msg->target,
			.sin6.sin6_family = AF_INET6,
		};

		vxlan_ip_miss(dev, &ipa);
	}

out:
	rcu_read_unlock();
	consume_skb(skb);
	return NETDEV_TX_OK;
}
#endif

static bool route_shortcircuit(struct net_device *dev, struct sk_buff *skb)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	struct neighbour *n;

	if (is_multicast_ether_addr(eth_hdr(skb)->h_dest))
		return false;

	n = NULL;
	switch (ntohs(eth_hdr(skb)->h_proto)) {
	case ETH_P_IP:
	{
		struct iphdr *pip;

		if (!pskb_may_pull(skb, sizeof(struct iphdr)))
			return false;
		pip = ip_hdr(skb);
		n = neigh_lookup(&arp_tbl, &pip->daddr, dev);
		if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) {
			union vxlan_addr ipa = {
				.sin.sin_addr.s_addr = pip->daddr,
				.sin.sin_family = AF_INET,
			};

			vxlan_ip_miss(dev, &ipa);
			return false;
		}

		break;
	}
#if IS_ENABLED(CONFIG_IPV6)
	case ETH_P_IPV6:
	{
		struct ipv6hdr *pip6;

		if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
			return false;
		pip6 = ipv6_hdr(skb);
		n = neigh_lookup(ipv6_stub->nd_tbl, &pip6->daddr, dev);
		if (!n && (vxlan->cfg.flags & VXLAN_F_L3MISS)) {
			union vxlan_addr ipa = {
				.sin6.sin6_addr = pip6->daddr,
				.sin6.sin6_family = AF_INET6,
			};

			vxlan_ip_miss(dev, &ipa);
			return false;
		}

		break;
	}
#endif
	default:
		return false;
	}

	if (n) {
		bool diff;

		diff = !ether_addr_equal(eth_hdr(skb)->h_dest, n->ha);
		if (diff) {
			memcpy(eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
				dev->addr_len);
			memcpy(eth_hdr(skb)->h_dest, n->ha, dev->addr_len);
		}
		neigh_release(n);
		return diff;
	}

	return false;
}

static void vxlan_build_gbp_hdr(struct vxlanhdr *vxh, u32 vxflags,
				struct vxlan_metadata *md)
{
	struct vxlanhdr_gbp *gbp;

	if (!md->gbp)
		return;

	gbp = (struct vxlanhdr_gbp *)vxh;
	vxh->vx_flags |= VXLAN_HF_GBP;

	if (md->gbp & VXLAN_GBP_DONT_LEARN)
		gbp->dont_learn = 1;

	if (md->gbp & VXLAN_GBP_POLICY_APPLIED)
		gbp->policy_applied = 1;

	gbp->policy_id = htons(md->gbp & VXLAN_GBP_ID_MASK);
}

static int vxlan_build_gpe_hdr(struct vxlanhdr *vxh, u32 vxflags,
			       __be16 protocol)
{
	struct vxlanhdr_gpe *gpe = (struct vxlanhdr_gpe *)vxh;

	gpe->np_applied = 1;
	gpe->next_protocol = tun_p_from_eth_p(protocol);
	if (!gpe->next_protocol)
		return -EPFNOSUPPORT;
	return 0;
}

static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
			   int iphdr_len, __be32 vni,
			   struct vxlan_metadata *md, u32 vxflags,
			   bool udp_sum)
{
	struct vxlanhdr *vxh;
	int min_headroom;
	int err;
	int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
	__be16 inner_protocol = htons(ETH_P_TEB);

	if ((vxflags & VXLAN_F_REMCSUM_TX) &&
	    skb->ip_summed == CHECKSUM_PARTIAL) {
		int csum_start = skb_checksum_start_offset(skb);

		if (csum_start <= VXLAN_MAX_REMCSUM_START &&
		    !(csum_start & VXLAN_RCO_SHIFT_MASK) &&
		    (skb->csum_offset == offsetof(struct udphdr, check) ||
		     skb->csum_offset == offsetof(struct tcphdr, check)))
			type |= SKB_GSO_TUNNEL_REMCSUM;
	}

	min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len
			+ VXLAN_HLEN + iphdr_len;

	/* Need space for new headers (invalidates iph ptr) */
	err = skb_cow_head(skb, min_headroom);
	if (unlikely(err))
		return err;

	err = iptunnel_handle_offloads(skb, type);
	if (err)
		return err;

	vxh = __skb_push(skb, sizeof(*vxh));
	vxh->vx_flags = VXLAN_HF_VNI;
	vxh->vx_vni = vxlan_vni_field(vni);

	if (type & SKB_GSO_TUNNEL_REMCSUM) {
		unsigned int start;

		start = skb_checksum_start_offset(skb) - sizeof(struct vxlanhdr);
		vxh->vx_vni |= vxlan_compute_rco(start, skb->csum_offset);
		vxh->vx_flags |= VXLAN_HF_RCO;

		if (!skb_is_gso(skb)) {
			skb->ip_summed = CHECKSUM_NONE;
			skb->encapsulation = 0;
		}
	}

	if (vxflags & VXLAN_F_GBP)
		vxlan_build_gbp_hdr(vxh, vxflags, md);
	if (vxflags & VXLAN_F_GPE) {
		err = vxlan_build_gpe_hdr(vxh, vxflags, skb->protocol);
		if (err < 0)
			return err;
		inner_protocol = skb->protocol;
	}

	skb_set_inner_protocol(skb, inner_protocol);
	return 0;
}

static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device *dev,
				      struct vxlan_sock *sock4,
				      struct sk_buff *skb, int oif, u8 tos,
				      __be32 daddr, __be32 *saddr, __be16 dport, __be16 sport,
				      struct dst_cache *dst_cache,
				      const struct ip_tunnel_info *info)
{
	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
	struct rtable *rt = NULL;
	struct flowi4 fl4;

	if (!sock4)
		return ERR_PTR(-EIO);

	if (tos && !info)
		use_cache = false;
	if (use_cache) {
		rt = dst_cache_get_ip4(dst_cache, saddr);
		if (rt)
			return rt;
	}

	memset(&fl4, 0, sizeof(fl4));
	fl4.flowi4_oif = oif;
	fl4.flowi4_tos = RT_TOS(tos);
	fl4.flowi4_mark = skb->mark;
	fl4.flowi4_proto = IPPROTO_UDP;
	fl4.daddr = daddr;
	fl4.saddr = *saddr;
	fl4.fl4_dport = dport;
	fl4.fl4_sport = sport;

	rt = ip_route_output_key(vxlan->net, &fl4);
	if (!IS_ERR(rt)) {
		if (rt->dst.dev == dev) {
			netdev_dbg(dev, "circular route to %pI4\n", &daddr);
			ip_rt_put(rt);
			return ERR_PTR(-ELOOP);
		}

		*saddr = fl4.saddr;
		if (use_cache)
			dst_cache_set_ip4(dst_cache, &rt->dst, fl4.saddr);
	} else {
		netdev_dbg(dev, "no route to %pI4\n", &daddr);
		return ERR_PTR(-ENETUNREACH);
	}
	return rt;
}

#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan,
					  struct net_device *dev,
					  struct vxlan_sock *sock6,
					  struct sk_buff *skb, int oif, u8 tos,
					  __be32 label,
					  const struct in6_addr *daddr,
					  struct in6_addr *saddr,
					  __be16 dport, __be16 sport,
					  struct dst_cache *dst_cache,
					  const struct ip_tunnel_info *info)
{
	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
	struct dst_entry *ndst;
	struct flowi6 fl6;

	if (!sock6)
		return ERR_PTR(-EIO);

	if (tos && !info)
		use_cache = false;
	if (use_cache) {
		ndst = dst_cache_get_ip6(dst_cache, saddr);
		if (ndst)
			return ndst;
	}

	memset(&fl6, 0, sizeof(fl6));
	fl6.flowi6_oif = oif;
	fl6.daddr = *daddr;
	fl6.saddr = *saddr;
	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tos), label);
	fl6.flowi6_mark = skb->mark;
	fl6.flowi6_proto = IPPROTO_UDP;
	fl6.fl6_dport = dport;
	fl6.fl6_sport = sport;

	ndst = ipv6_stub->ipv6_dst_lookup_flow(vxlan->net, sock6->sock->sk,
					       &fl6, NULL);
	if (IS_ERR(ndst)) {
		netdev_dbg(dev, "no route to %pI6\n", daddr);
		return ERR_PTR(-ENETUNREACH);
	}

	if (unlikely(ndst->dev == dev)) {
		netdev_dbg(dev, "circular route to %pI6\n", daddr);
		dst_release(ndst);
		return ERR_PTR(-ELOOP);
	}

	*saddr = fl6.saddr;
	if (use_cache)
		dst_cache_set_ip6(dst_cache, ndst, saddr);
	return ndst;
}
#endif

/* Bypass encapsulation if the destination is local */
static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan,
			       struct vxlan_dev *dst_vxlan, __be32 vni,
			       bool snoop)
{
	struct pcpu_sw_netstats *tx_stats, *rx_stats;
	union vxlan_addr loopback;
	union vxlan_addr *remote_ip = &dst_vxlan->default_dst.remote_ip;
	struct net_device *dev;
	int len = skb->len;

	tx_stats = this_cpu_ptr(src_vxlan->dev->tstats);
	rx_stats = this_cpu_ptr(dst_vxlan->dev->tstats);
	skb->pkt_type = PACKET_HOST;
	skb->encapsulation = 0;
	skb->dev = dst_vxlan->dev;
	__skb_pull(skb, skb_network_offset(skb));

	if (remote_ip->sa.sa_family == AF_INET) {
		loopback.sin.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
		loopback.sa.sa_family =  AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
	} else {
		loopback.sin6.sin6_addr = in6addr_loopback;
		loopback.sa.sa_family =  AF_INET6;
#endif
	}

	rcu_read_lock();
	dev = skb->dev;
	if (unlikely(!(dev->flags & IFF_UP))) {
		kfree_skb(skb);
		goto drop;
	}

	if ((dst_vxlan->cfg.flags & VXLAN_F_LEARN) && snoop)
		vxlan_snoop(dev, &loopback, eth_hdr(skb)->h_source, 0, vni);

	u64_stats_update_begin(&tx_stats->syncp);
	tx_stats->tx_packets++;
	tx_stats->tx_bytes += len;
	u64_stats_update_end(&tx_stats->syncp);

	if (netif_rx(skb) == NET_RX_SUCCESS) {
		u64_stats_update_begin(&rx_stats->syncp);
		rx_stats->rx_packets++;
		rx_stats->rx_bytes += len;
		u64_stats_update_end(&rx_stats->syncp);
	} else {
drop:
		dev->stats.rx_dropped++;
	}
	rcu_read_unlock();
}

static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,
				 struct vxlan_dev *vxlan,
				 union vxlan_addr *daddr,
				 __be16 dst_port, int dst_ifindex, __be32 vni,
				 struct dst_entry *dst,
				 u32 rt_flags)
{
#if IS_ENABLED(CONFIG_IPV6)
	/* IPv6 rt-flags are checked against RTF_LOCAL, but the value of
	 * RTF_LOCAL is equal to RTCF_LOCAL. So to keep code simple
	 * we can use RTCF_LOCAL which works for ipv4 and ipv6 route entry.
	 */
	BUILD_BUG_ON(RTCF_LOCAL != RTF_LOCAL);
#endif
	/* Bypass encapsulation if the destination is local */
	if (rt_flags & RTCF_LOCAL &&
	    !(rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))) {
		struct vxlan_dev *dst_vxlan;

		dst_release(dst);
		dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni,
					   daddr->sa.sa_family, dst_port,
					   vxlan->cfg.flags);
		if (!dst_vxlan) {
			dev->stats.tx_errors++;
			kfree_skb(skb);

			return -ENOENT;
		}
		vxlan_encap_bypass(skb, vxlan, dst_vxlan, vni, true);
		return 1;
	}

	return 0;
}

static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
			   __be32 default_vni, struct vxlan_rdst *rdst,
			   bool did_rsc)
{
	struct dst_cache *dst_cache;
	struct ip_tunnel_info *info;
	struct vxlan_dev *vxlan = netdev_priv(dev);
	const struct iphdr *old_iph = ip_hdr(skb);
	union vxlan_addr *dst;
	union vxlan_addr remote_ip, local_ip;
	struct vxlan_metadata _md;
	struct vxlan_metadata *md = &_md;
	__be16 src_port = 0, dst_port;
	struct dst_entry *ndst = NULL;
	__be32 vni, label;
	__u8 tos, ttl;
	int ifindex;
	int err;
	u32 flags = vxlan->cfg.flags;
	bool udp_sum = false;
	bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev));

	info = skb_tunnel_info(skb);

	if (rdst) {
		dst = &rdst->remote_ip;
		if (vxlan_addr_any(dst)) {
			if (did_rsc) {
				/* short-circuited back to local bridge */
				vxlan_encap_bypass(skb, vxlan, vxlan,
						   default_vni, true);
				return;
			}
			goto drop;
		}

		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;
		vni = (rdst->remote_vni) ? : default_vni;
		ifindex = rdst->remote_ifindex;
		local_ip = vxlan->cfg.saddr;
		dst_cache = &rdst->dst_cache;
		md->gbp = skb->mark;
		if (flags & VXLAN_F_TTL_INHERIT) {
			ttl = ip_tunnel_get_ttl(old_iph, skb);
		} else {
			ttl = vxlan->cfg.ttl;
			if (!ttl && vxlan_addr_multicast(dst))
				ttl = 1;
		}

		tos = vxlan->cfg.tos;
		if (tos == 1)
			tos = ip_tunnel_get_dsfield(old_iph, skb);

		if (dst->sa.sa_family == AF_INET)
			udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX);
		else
			udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
		label = vxlan->cfg.label;
	} else {
		if (!info) {
			WARN_ONCE(1, "%s: Missing encapsulation instructions\n",
				  dev->name);
			goto drop;
		}
		remote_ip.sa.sa_family = ip_tunnel_info_af(info);
		if (remote_ip.sa.sa_family == AF_INET) {
			remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst;
			local_ip.sin.sin_addr.s_addr = info->key.u.ipv4.src;
		} else {
			remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst;
			local_ip.sin6.sin6_addr = info->key.u.ipv6.src;
		}
		dst = &remote_ip;
		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
		vni = tunnel_id_to_key32(info->key.tun_id);
		ifindex = 0;
		dst_cache = &info->dst_cache;
		if (info->key.tun_flags & TUNNEL_VXLAN_OPT) {
			if (info->options_len < sizeof(*md))
				goto drop;
			md = ip_tunnel_info_opts(info);
		}
		ttl = info->key.ttl;
		tos = info->key.tos;
		label = info->key.label;
		udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
	}
	src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min,
				     vxlan->cfg.port_max, true);

	rcu_read_lock();
	if (dst->sa.sa_family == AF_INET) {
		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
		struct rtable *rt;
		__be16 df = 0;

		if (!ifindex)
			ifindex = sock4->sock->sk->sk_bound_dev_if;

		rt = vxlan_get_route(vxlan, dev, sock4, skb, ifindex, tos,
				     dst->sin.sin_addr.s_addr,
				     &local_ip.sin.sin_addr.s_addr,
				     dst_port, src_port,
				     dst_cache, info);
		if (IS_ERR(rt)) {
			err = PTR_ERR(rt);
			goto tx_error;
		}

		if (!info) {
			/* Bypass encapsulation if the destination is local */
			err = encap_bypass_if_local(skb, dev, vxlan, dst,
						    dst_port, ifindex, vni,
						    &rt->dst, rt->rt_flags);
			if (err)
				goto out_unlock;

			if (vxlan->cfg.df == VXLAN_DF_SET) {
				df = htons(IP_DF);
			} else if (vxlan->cfg.df == VXLAN_DF_INHERIT) {
				struct ethhdr *eth = eth_hdr(skb);

				if (ntohs(eth->h_proto) == ETH_P_IPV6 ||
				    (ntohs(eth->h_proto) == ETH_P_IP &&
				     old_iph->frag_off & htons(IP_DF)))
					df = htons(IP_DF);
			}
		} else if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT) {
			df = htons(IP_DF);
		}

		ndst = &rt->dst;
		err = skb_tunnel_check_pmtu(skb, ndst, VXLAN_HEADROOM,
					    netif_is_any_bridge_port(dev));
		if (err < 0) {
			goto tx_error;
		} else if (err) {
			if (info) {
				struct ip_tunnel_info *unclone;
				struct in_addr src, dst;

				unclone = skb_tunnel_info_unclone(skb);
				if (unlikely(!unclone))
					goto tx_error;

				src = remote_ip.sin.sin_addr;
				dst = local_ip.sin.sin_addr;
				unclone->key.u.ipv4.src = src.s_addr;
				unclone->key.u.ipv4.dst = dst.s_addr;
			}
			vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);
			dst_release(ndst);
			goto out_unlock;
		}

		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
		err = vxlan_build_skb(skb, ndst, sizeof(struct iphdr),
				      vni, md, flags, udp_sum);
		if (err < 0)
			goto tx_error;

		udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, local_ip.sin.sin_addr.s_addr,
				    dst->sin.sin_addr.s_addr, tos, ttl, df,
				    src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
	} else {
		struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);

		if (!ifindex)
			ifindex = sock6->sock->sk->sk_bound_dev_if;

		ndst = vxlan6_get_route(vxlan, dev, sock6, skb, ifindex, tos,
					label, &dst->sin6.sin6_addr,
					&local_ip.sin6.sin6_addr,
					dst_port, src_port,
					dst_cache, info);
		if (IS_ERR(ndst)) {
			err = PTR_ERR(ndst);
			ndst = NULL;
			goto tx_error;
		}

		if (!info) {
			u32 rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;

			err = encap_bypass_if_local(skb, dev, vxlan, dst,
						    dst_port, ifindex, vni,
						    ndst, rt6i_flags);
			if (err)
				goto out_unlock;
		}

		err = skb_tunnel_check_pmtu(skb, ndst, VXLAN6_HEADROOM,
					    netif_is_any_bridge_port(dev));
		if (err < 0) {
			goto tx_error;
		} else if (err) {
			if (info) {
				struct ip_tunnel_info *unclone;
				struct in6_addr src, dst;

				unclone = skb_tunnel_info_unclone(skb);
				if (unlikely(!unclone))
					goto tx_error;

				src = remote_ip.sin6.sin6_addr;
				dst = local_ip.sin6.sin6_addr;
				unclone->key.u.ipv6.src = src;
				unclone->key.u.ipv6.dst = dst;
			}

			vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);
			dst_release(ndst);
			goto out_unlock;
		}

		tos = ip_tunnel_ecn_encap(tos, old_iph, skb);
		ttl = ttl ? : ip6_dst_hoplimit(ndst);
		skb_scrub_packet(skb, xnet);
		err = vxlan_build_skb(skb, ndst, sizeof(struct ipv6hdr),
				      vni, md, flags, udp_sum);
		if (err < 0)
			goto tx_error;

		udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev,
				     &local_ip.sin6.sin6_addr,
				     &dst->sin6.sin6_addr, tos, ttl,
				     label, src_port, dst_port, !udp_sum);
#endif
	}
out_unlock:
	rcu_read_unlock();
	return;

drop:
	dev->stats.tx_dropped++;
	dev_kfree_skb(skb);
	return;

tx_error:
	rcu_read_unlock();
	if (err == -ELOOP)
		dev->stats.collisions++;
	else if (err == -ENETUNREACH)
		dev->stats.tx_carrier_errors++;
	dst_release(ndst);
	dev->stats.tx_errors++;
	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.
 * Outer UDP destination is the VXLAN assigned port.
 *           source port is based on hash of flow
 */
static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct vxlan_dev *vxlan = netdev_priv(dev);
	struct vxlan_rdst *rdst, *fdst = NULL;
	const struct ip_tunnel_info *info;
	bool did_rsc = false;
	struct vxlan_fdb *f;
	struct ethhdr *eth;
	__be32 vni = 0;

	info = skb_tunnel_info(skb);

	skb_reset_mac_header(skb);

	if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) {
		if (info && info->mode & IP_TUNNEL_INFO_BRIDGE &&
		    info->mode & IP_TUNNEL_INFO_TX) {
			vni = tunnel_id_to_key32(info->key.tun_id);
		} else {
			if (info && info->mode & IP_TUNNEL_INFO_TX)
				vxlan_xmit_one(skb, dev, vni, NULL, false);
			else
				kfree_skb(skb);
			return NETDEV_TX_OK;
		}
	}

	if (vxlan->cfg.flags & VXLAN_F_PROXY) {
		eth = eth_hdr(skb);
		if (ntohs(eth->h_proto) == ETH_P_ARP)
			return arp_reduce(dev, skb, vni);
#if IS_ENABLED(CONFIG_IPV6)
		else if (ntohs(eth->h_proto) == ETH_P_IPV6 &&
			 pskb_may_pull(skb, sizeof(struct ipv6hdr) +
					    sizeof(struct nd_msg)) &&
			 ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) {
			struct nd_msg *m = (struct nd_msg *)(ipv6_hdr(skb) + 1);

			if (m->icmph.icmp6_code == 0 &&
			    m->icmph.icmp6_type == NDISC_NEIGHBOUR_SOLICITATION)
				return neigh_reduce(dev, skb, vni);
		}
#endif
	}

	eth = eth_hdr(skb);
	f = vxlan_find_mac(vxlan, eth->h_dest, vni);
	did_rsc = false;

	if (f && (f->flags & NTF_ROUTER) && (vxlan->cfg.flags & VXLAN_F_RSC) &&
	    (ntohs(eth->h_proto) == ETH_P_IP ||
	     ntohs(eth->h_proto) == ETH_P_IPV6)) {
		did_rsc = route_shortcircuit(dev, skb);
		if (did_rsc)
			f = vxlan_find_mac(vxlan, eth->h_dest, vni);
	}

	if (f == NULL) {
		f = vxlan_find_mac(vxlan, all_zeros_mac, vni);
		if (f == NULL) {
			if ((vxlan->cfg.