ipv6: Compute multipath hash for ICMP errors from offending packet

When forwarding or sending out an ICMPv6 error, look at the embedded
packet that triggered the error and compute a flow hash over its
headers.

This let's us route the ICMP error together with the flow it belongs to
when multipath (ECMP) routing is in use, which in turn makes Path MTU
Discovery work in ECMP load-balanced or anycast setups (RFC 7690).

Granted, end-hosts behind the ECMP router (aka servers) need to reflect
the IPv6 Flow Label for PMTUD to work.

The code is organized to be in parallel with ipv4 stack:

  ip_multipath_l3_keys -> ip6_multipath_l3_keys
  fib_multipath_hash   -> rt6_multipath_hash

Signed-off-by: Jakub Sitnicki <jkbs@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 51 insertions, 0 deletions

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4f82830fc068..dd7608cf1d72 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -519,6 +519,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
+	fl6.mp_hash = rt6_multipath_hash(&fl6, skb);
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
 
 	sk = icmpv6_xmit_lock(net);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 9b02064c3335..6c4dd5796a31 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1214,6 +1214,54 @@ struct dst_entry *ip6_route_input_lookup(struct net *net,
 }
 EXPORT_SYMBOL_GPL(ip6_route_input_lookup);
 
+static void ip6_multipath_l3_keys(const struct sk_buff *skb,
+				  struct flow_keys *keys)
+{
+	const struct ipv6hdr *outer_iph = ipv6_hdr(skb);
+	const struct ipv6hdr *key_iph = outer_iph;
+	const struct ipv6hdr *inner_iph;
+	const struct icmp6hdr *icmph;
+	struct ipv6hdr _inner_iph;
+
+	if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6))
+		goto out;
+
+	icmph = icmp6_hdr(skb);
+	if (icmph->icmp6_type != ICMPV6_DEST_UNREACH &&
+	    icmph->icmp6_type != ICMPV6_PKT_TOOBIG &&
+	    icmph->icmp6_type != ICMPV6_TIME_EXCEED &&
+	    icmph->icmp6_type != ICMPV6_PARAMPROB)
+		goto out;
+
+	inner_iph = skb_header_pointer(skb,
+				       skb_transport_offset(skb) + sizeof(*icmph),
+				       sizeof(_inner_iph), &_inner_iph);
+	if (!inner_iph)
+		goto out;
+
+	key_iph = inner_iph;
+out:
+	memset(keys, 0, sizeof(*keys));
+	keys->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
+	keys->addrs.v6addrs.src = key_iph->saddr;
+	keys->addrs.v6addrs.dst = key_iph->daddr;
+	keys->tags.flow_label = ip6_flowinfo(key_iph);
+	keys->basic.ip_proto = key_iph->nexthdr;
+}
+
+/* if skb is set it will be used and fl6 can be NULL */
+u32 rt6_multipath_hash(const struct flowi6 *fl6, const struct sk_buff *skb)
+{
+	struct flow_keys hash_keys;
+
+	if (skb) {
+		ip6_multipath_l3_keys(skb, &hash_keys);
+		return flow_hash_from_keys(&hash_keys);
+	}
+
+	return get_hash_from_flowi6(fl6);
+}
+
 void ip6_route_input(struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -1232,6 +1280,8 @@ void ip6_route_input(struct sk_buff *skb)
 	tun_info = skb_tunnel_info(skb);
 	if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX))
 		fl6.flowi6_tun_key.tun_id = tun_info->key.tun_id;
+	if (unlikely(fl6.flowi6_proto == IPPROTO_ICMPV6))
+		fl6.mp_hash = rt6_multipath_hash(&fl6, skb);
 	skb_dst_drop(skb);
 	skb_dst_set(skb, ip6_route_input_lookup(net, skb->dev, &fl6, flags));
 }