Commit 35c1b273 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'consolidate-udp-ipv6-route-lookups' 



Beniamino Galvani says:

====================
net: consolidate IPv6 route lookup for UDP tunnels

At the moment different UDP tunnels rely on different functions for
IPv6 route lookup, and those functions all implement the same
logic.

Extend the generic lookup function so that it is suitable for all UDP
tunnel implementations, and then adapt bareudp, geneve and vxlan to
use it.

This is similar to what already done for IPv4.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 92fc97ae 2aceb896

drivers/net/bareudp.c

+8 −5
Original line number Diff line number Diff line
@@ -371,8 +371,10 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, 
	if (!sock)

		return -ESHUTDOWN;



	dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, &saddr, info,

				    IPPROTO_UDP, use_cache);

	dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, 0, &saddr,

				     key, 0, 0, key->tos,

				     use_cache ?

				     (struct dst_cache *) &info->dst_cache : NULL);

	if (IS_ERR(dst))

		return PTR_ERR(dst);
@@ -498,9 +500,10 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, 
		struct in6_addr saddr;

		struct socket *sock = rcu_dereference(bareudp->sock);



		dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock,

					    &saddr, info, IPPROTO_UDP,

					    use_cache);

		dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock,

					     0, &saddr, &info->key,

					     0, 0, info->key.tos,

					     use_cache ? &info->dst_cache : NULL);

		if (IS_ERR(dst))

			return PTR_ERR(dst);

drivers/net/geneve.c

+31 −65
Original line number Diff line number Diff line
@@ -800,57 +800,6 @@ static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev, 
	return dsfield;

}



#if IS_ENABLED(CONFIG_IPV6)

static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,

					   struct net_device *dev,

					   struct geneve_sock *gs6,

					   struct flowi6 *fl6,

					   const struct ip_tunnel_info *info,

					   __be16 dport, __be16 sport)

{

	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);

	struct geneve_dev *geneve = netdev_priv(dev);

	struct dst_entry *dst = NULL;

	struct dst_cache *dst_cache;

	__u8 prio;



	if (!gs6)

		return ERR_PTR(-EIO);



	memset(fl6, 0, sizeof(*fl6));

	fl6->flowi6_mark = skb->mark;

	fl6->flowi6_proto = IPPROTO_UDP;

	fl6->daddr = info->key.u.ipv6.dst;

	fl6->saddr = info->key.u.ipv6.src;

	fl6->fl6_dport = dport;

	fl6->fl6_sport = sport;



	prio = geneve_get_dsfield(skb, dev, info, &use_cache);

	fl6->flowlabel = ip6_make_flowinfo(prio, info->key.label);

	dst_cache = (struct dst_cache *)&info->dst_cache;

	if (use_cache) {

		dst = dst_cache_get_ip6(dst_cache, &fl6->saddr);

		if (dst)

			return dst;

	}

	dst = ipv6_stub->ipv6_dst_lookup_flow(geneve->net, gs6->sock->sk, fl6,

					      NULL);

	if (IS_ERR(dst)) {

		netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr);

		return ERR_PTR(-ENETUNREACH);

	}

	if (dst->dev == dev) { /* is this necessary? */

		netdev_dbg(dev, "circular route to %pI6\n", &fl6->daddr);

		dst_release(dst);

		return ERR_PTR(-ELOOP);

	}



	if (use_cache)

		dst_cache_set_ip6(dst_cache, dst, &fl6->saddr);

	return dst;

}

#endif



static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,

			   struct geneve_dev *geneve,

			   const struct ip_tunnel_info *info)
@@ -967,7 +916,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, 
	struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);

	const struct ip_tunnel_key *key = &info->key;

	struct dst_entry *dst = NULL;

	struct flowi6 fl6;

	struct in6_addr saddr;

	bool use_cache;

	__u8 prio, ttl;

	__be16 sport;

	int err;
@@ -975,9 +925,18 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, 
	if (!pskb_inet_may_pull(skb))

		return -EINVAL;



	if (!gs6)

		return -EIO;



	use_cache = ip_tunnel_dst_cache_usable(skb, info);

	prio = geneve_get_dsfield(skb, dev, info, &use_cache);

	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);

	dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,

				geneve->cfg.info.key.tp_dst, sport);



	dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0,

				     &saddr, key, sport,

				     geneve->cfg.info.key.tp_dst, prio,

				     use_cache ?

				     (struct dst_cache *)&info->dst_cache : NULL);

	if (IS_ERR(dst))

		return PTR_ERR(dst);
@@ -999,8 +958,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, 
				return -ENOMEM;

			}



			unclone->key.u.ipv6.dst = fl6.saddr;

			unclone->key.u.ipv6.src = fl6.daddr;

			unclone->key.u.ipv6.dst = saddr;

			unclone->key.u.ipv6.src = info->key.u.ipv6.dst;

		}



		if (!pskb_may_pull(skb, ETH_HLEN)) {
@@ -1014,12 +973,10 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, 
		return -EMSGSIZE;

	}



	prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb);

	if (geneve->cfg.collect_md) {

		prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);

		ttl = key->ttl;

	} else {

		prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel),

					   ip_hdr(skb), skb);

		if (geneve->cfg.ttl_inherit)

			ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);

		else
@@ -1032,7 +989,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, 
		return err;



	udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev,

			     &fl6.saddr, &fl6.daddr, prio, ttl,

			     &saddr, &key->u.ipv6.dst, prio, ttl,

			     info->key.label, sport, geneve->cfg.info.key.tp_dst,

			     !(info->key.tun_flags & TUNNEL_CSUM));

	return 0;
@@ -1126,19 +1083,28 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) 
#if IS_ENABLED(CONFIG_IPV6)

	} else if (ip_tunnel_info_af(info) == AF_INET6) {

		struct dst_entry *dst;

		struct flowi6 fl6;



		struct geneve_sock *gs6 = rcu_dereference(geneve->sock6);

		struct in6_addr saddr;

		bool use_cache;

		u8 prio;



		if (!gs6)

			return -EIO;



		use_cache = ip_tunnel_dst_cache_usable(skb, info);

		prio = geneve_get_dsfield(skb, dev, info, &use_cache);

		sport = udp_flow_src_port(geneve->net, skb,

					  1, USHRT_MAX, true);



		dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info,

					geneve->cfg.info.key.tp_dst, sport);

		dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0,

					     &saddr, &info->key, sport,

					     geneve->cfg.info.key.tp_dst, prio,

					     use_cache ? &info->dst_cache : NULL);

		if (IS_ERR(dst))

			return PTR_ERR(dst);



		dst_release(dst);

		info->key.u.ipv6.src = fl6.saddr;

		info->key.u.ipv6.src = saddr;

#endif

	} else {

		return -EINVAL;

drivers/net/vxlan/vxlan_core.c

+30 −106
Original line number Diff line number Diff line
@@ -2215,63 +2215,6 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, 
	return 0;

}



#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(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,
@@ -2325,7 +2268,7 @@ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, 


static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev,

				 struct vxlan_dev *vxlan,

				 union vxlan_addr *daddr,

				 int addr_family,

				 __be16 dst_port, int dst_ifindex, __be32 vni,

				 struct dst_entry *dst,

				 u32 rt_flags)
@@ -2345,7 +2288,7 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, 


		dst_release(dst);

		dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni,

					   daddr->sa.sa_family, dst_port,

					   addr_family, dst_port,

					   vxlan->cfg.flags);

		if (!dst_vxlan) {

			dev->stats.tx_errors++;
@@ -2371,13 +2314,12 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
	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;

	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;

	int addr_family;

	__u8 tos, ttl;

	int ifindex;

	int err;
@@ -2386,20 +2328,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
	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 (vxlan_addr_any(&rdst->remote_ip)) {

			if (did_rsc) {

				/* short-circuited back to local bridge */

				vxlan_encap_bypass(skb, vxlan, vxlan,
@@ -2409,11 +2346,12 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
			goto drop;

		}



		addr_family = vxlan->cfg.saddr.sa.sa_family;

		dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port;

		vni = (rdst->remote_vni) ? : default_vni;

		ifindex = rdst->remote_ifindex;



		if (dst->sa.sa_family == AF_INET) {

		if (addr_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 {
@@ -2427,23 +2365,21 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
			ttl = ip_tunnel_get_ttl(old_iph, skb);

		} else {

			ttl = vxlan->cfg.ttl;

			if (!ttl && vxlan_addr_multicast(dst))

			if (!ttl && vxlan_addr_multicast(&rdst->remote_ip))

				ttl = 1;

		}



		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)

		if (addr_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;

		key.label = vxlan->cfg.label;

#endif

	} else {

		if (!info) {
@@ -2451,17 +2387,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
				  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;

		} 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;

		addr_family = ip_tunnel_info_af(info);

		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;

		vni = tunnel_id_to_key32(info->key.tun_id);

		ifindex = 0;
@@ -2473,16 +2400,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
		}

		ttl = info->key.ttl;

		tos = info->key.tos;

#if IS_ENABLED(CONFIG_IPV6)

		label = info->key.label;

#endif

		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) {

	if (addr_family == AF_INET) {

		struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock);

		struct rtable *rt;

		__be16 df = 0;
@@ -2501,7 +2425,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 


		if (!info) {

			/* Bypass encapsulation if the destination is local */

			err = encap_bypass_if_local(skb, dev, vxlan, dst,

			err = encap_bypass_if_local(skb, dev, vxlan, AF_INET,

						    dst_port, ifindex, vni,

						    &rt->dst, rt->rt_flags);

			if (err)
@@ -2555,15 +2479,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
#if IS_ENABLED(CONFIG_IPV6)

	} else {

		struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);

		struct in6_addr saddr;



		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);

		ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock,

					      ifindex, &saddr, pkey,

					      src_port, dst_port, tos,

					      use_cache ? dst_cache : NULL);

		if (IS_ERR(ndst)) {

			err = PTR_ERR(ndst);

			ndst = NULL;
@@ -2573,7 +2497,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
		if (!info) {

			u32 rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags;



			err = encap_bypass_if_local(skb, dev, vxlan, dst,

			err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6,

						    dst_port, ifindex, vni,

						    ndst, rt6i_flags);

			if (err)
@@ -2588,16 +2512,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
		} 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;

				unclone->key.u.ipv6.src = pkey->u.ipv6.dst;

				unclone->key.u.ipv6.dst = saddr;

			}



			vxlan_encap_bypass(skb, vxlan, vxlan, vni, false);
@@ -2614,9 +2535,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, 
			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);

				     &saddr, &pkey->u.ipv6.dst, tos, ttl,

				     pkey->label, src_port, dst_port, !udp_sum);

#endif

	}

	vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len);
@@ -3267,10 +3187,14 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) 
		struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock);

		struct dst_entry *ndst;



		ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos,

					info->key.label, &info->key.u.ipv6.dst,

					&info->key.u.ipv6.src, dport, sport,

					&info->dst_cache, info);

		if (!sock6)

			return -EIO;



		ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock,

					      0, &info->key.u.ipv6.src,

					      &info->key,

					      sport, dport, info->key.tos,

					      &info->dst_cache);

		if (IS_ERR(ndst))

			return PTR_ERR(ndst);

		dst_release(ndst);

include/net/ipv6.h

+0 −6
Original line number Diff line number Diff line
@@ -1133,12 +1133,6 @@ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, st 
struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,

					 const struct in6_addr *final_dst,

					 bool connected);

struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb,

					struct net_device *dev,

					struct net *net, struct socket *sock,

					struct in6_addr *saddr,

					const struct ip_tunnel_info *info,

					u8 protocol, bool use_cache);

struct dst_entry *ip6_blackhole_route(struct net *net,

				      struct dst_entry *orig_dst);

include/net/udp_tunnel.h

+8 −0
Original line number Diff line number Diff line
@@ -169,6 +169,14 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, 
				     const struct ip_tunnel_key *key,

				     __be16 sport, __be16 dport, u8 tos,

				     struct dst_cache *dst_cache);

struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb,

					 struct net_device *dev,

					 struct net *net,

					 struct socket *sock, int oif,

					 struct in6_addr *saddr,

					 const struct ip_tunnel_key *key,

					 __be16 sport, __be16 dport, u8 dsfield,

					 struct dst_cache *dst_cache);



struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family,

				    __be16 flags, __be64 tunnel_id,