Commit 6f19b2c1 authored by Beniamino Galvani's avatar Beniamino Galvani Committed by David S. Miller
Browse files

vxlan: use generic function for tunnel IPv4 route lookup



The route lookup can be done now via generic function
udp_tunnel_dst_lookup() to replace the custom implementations in
vxlan_get_route().

Note that this patch only touches IPv4, while IPv6 still uses
vxlan6_get_route(). After IPv6 route lookup gets converted as well,
vxlan_xmit_one() can be simplified by removing local variables that
will be passed via "struct ip_tunnel_key", such as remote_ip,
local_ip, flow_flags, label.

Suggested-by: default avatarGuillaume Nault <gnault@redhat.com>
Signed-off-by: default avatarBeniamino Galvani <b.galvani@gmail.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent daa2ba7e
Loading
Loading
Loading
Loading
+41 −73
Original line number Diff line number Diff line
@@ -2215,57 +2215,6 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst,
	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,
				      __u8 flow_flags, 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;
	fl4.flowi4_flags = flow_flags;

	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,
@@ -2418,30 +2367,38 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
{
	struct dst_cache *dst_cache;
	struct ip_tunnel_info *info;
	struct ip_tunnel_key *pkey;
	struct ip_tunnel_key key;
	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;
	union vxlan_addr remote_ip;
	struct vxlan_metadata _md;
	struct vxlan_metadata *md = &_md;
	unsigned int pkt_len = skb->len;
	__be16 src_port = 0, dst_port;
	struct dst_entry *ndst = NULL;
	__u8 tos, ttl, flow_flags = 0;
	__u8 tos, ttl;
	int ifindex;
	int err;
	u32 flags = vxlan->cfg.flags;
	bool use_cache;
	bool udp_sum = false;
	bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev));
	__be32 vni = 0;
#if IS_ENABLED(CONFIG_IPV6)
	union vxlan_addr local_ip;
	__be32 label;
#endif

	info = skb_tunnel_info(skb);
	use_cache = ip_tunnel_dst_cache_usable(skb, info);

	if (rdst) {
		dst = &rdst->remote_ip;
		memset(&key, 0, sizeof(key));
		pkey = &key;

		if (vxlan_addr_any(dst)) {
			if (did_rsc) {
				/* short-circuited back to local bridge */
@@ -2455,7 +2412,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
		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;

		if (dst->sa.sa_family == AF_INET) {
			key.u.ipv4.src = vxlan->cfg.saddr.sin.sin_addr.s_addr;
			key.u.ipv4.dst = rdst->remote_ip.sin.sin_addr.s_addr;
		} else {
			key.u.ipv6.src = vxlan->cfg.saddr.sin6.sin6_addr;
			key.u.ipv6.dst = rdst->remote_ip.sin6.sin6_addr;
		}

		dst_cache = &rdst->dst_cache;
		md->gbp = skb->mark;
		if (flags & VXLAN_F_TTL_INHERIT) {
@@ -2469,12 +2434,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
		tos = vxlan->cfg.tos;
		if (tos == 1)
			tos = ip_tunnel_get_dsfield(old_iph, skb);
		if (tos && !info)
			use_cache = false;

		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);
#if IS_ENABLED(CONFIG_IPV6)
		local_ip = vxlan->cfg.saddr;
		label = vxlan->cfg.label;
#endif
	} else {
@@ -2486,14 +2454,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
		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;
#if IS_ENABLED(CONFIG_IPV6)
			local_ip.sin6.sin6_addr = info->key.u.ipv6.src;
#endif
		}
		dst = &remote_ip;
		pkey = &info->key;
		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
		flow_flags = info->key.flow_flags;
		vni = tunnel_id_to_key32(info->key.tun_id);
		ifindex = 0;
		dst_cache = &info->dst_cache;
@@ -2517,15 +2486,14 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
		struct rtable *rt;
		__be16 df = 0;
		__be32 saddr;

		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, flow_flags,
				     dst_cache, info);
		rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, ifindex,
					   &saddr, pkey, src_port, dst_port,
					   tos, use_cache ? dst_cache : NULL);
		if (IS_ERR(rt)) {
			err = PTR_ERR(rt);
			goto tx_error;
@@ -2561,16 +2529,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
		} 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;
				unclone->key.u.ipv4.src = pkey->u.ipv4.dst;
				unclone->key.u.ipv4.dst = saddr;
			}
			vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);
			dst_release(ndst);
@@ -2584,8 +2549,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
		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,
		udp_tunnel_xmit_skb(rt, sock4->sock->sk, skb, saddr,
				    pkey->u.ipv4.dst, tos, ttl, df,
				    src_port, dst_port, xnet, !udp_sum);
#if IS_ENABLED(CONFIG_IPV6)
	} else {
@@ -3286,11 +3251,14 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);
		struct rtable *rt;

		rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos,
				     info->key.u.ipv4.dst,
				     &info->key.u.ipv4.src, dport, sport,
				     info->key.flow_flags, &info->dst_cache,
				     info);
		if (!sock4)
			return -EIO;

		rt = udp_tunnel_dst_lookup(skb, dev, vxlan->net, 0,
					   &info->key.u.ipv4.src,
					   &info->key,
					   sport, dport, info->key.tos,
					   &info->dst_cache);
		if (IS_ERR(rt))
			return PTR_ERR(rt);
		ip_rt_put(rt);