[PATCH RFC nf-next 3/4] netfilter: flowtable: Add IP6IP6 tx sw acceleration

[Lorenzo Bianconi <lorenzo@kernel.org>]

Introduce sw acceleration for tx path of IP6IP6 tunnels relying on the
netfilter flowtable infrastructure.
IP6IP6 tx sw acceleration can be tested running the following scenario
where the traffic is forwarded between two NICs (eth0 and eth1) and an
IP6IP6 tunnel is used to access a remote site (using eth1 as the underlay
device):

ETH0 -- TUN0 <==> ETH1 -- [IP network] -- TUN1 (2001:db8:3::2)

$ip addr show
6: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
    link/ether 00:00:22:33:11:55 brd ff:ff:ff:ff:ff:ff
    inet6 2001:db8:1::2/64 scope global nodad
       valid_lft forever preferred_lft forever
7: eth1: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
    link/ether 00:11:22:33:11:55 brd ff:ff:ff:ff:ff:ff
    inet6 2001:db8:2::1/64 scope global nodad
       valid_lft forever preferred_lft forever
8: tun0@NONE: <POINTOPOINT,NOARP,UP,LOWER_UP> mtu 1480 qdisc noqueue state UNKNOWN group default qlen 1000
    link/tunnel6 2001:db8:2::1 peer 2001:db8:2::2 permaddr ce9c:2940:7dcc::
    inet6 2002:db8:1::1/64 scope global nodad
       valid_lft forever preferred_lft forever

$ip -6 route show
2001:db8:1::/64 dev eth0 proto kernel metric 256 pref medium
2001:db8:2::/64 dev eth1 proto kernel metric 256 pref medium
2002:db8:1::/64 dev tun0 proto kernel metric 256 pref medium
default via 2002:db8:1::2 dev tun0 metric 1024 pref medium

$nft list ruleset
table inet filter {
        flowtable ft {
                hook ingress priority filter
                devices = { eth0, eth1 }
        }

        chain forward {
                type filter hook forward priority filter; policy accept;
                meta l4proto { tcp, udp } flow add @ft
        }
}

Reproducing the scenario described above using veths I got the following
results:
- TCP stream received from the IPIP tunnel:
  - net-next: (baseline)                  ~93Gbps
  - net-next + IP6IP6 flowtbale support:  ~98Gbps

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 net/netfilter/nf_flow_table_ip.c | 93 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 93 insertions(+)

diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index ca5a5d58eb2edbd61fe826eb892eaaf2d5b9e537..e5182630a83e3e959c7bde293ddc3beef295cd51 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -12,6 +12,7 @@
 #include <net/ip.h>
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
+#include <net/ip6_tunnel.h>
 #include <net/neighbour.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_conntrack_acct.h>
@@ -646,6 +647,91 @@ static int nf_flow_tunnel_v4_push(struct net *net, struct sk_buff *skb,
 	return 0;
 }
 
+struct ipv6_tel_txoption {
+	struct ipv6_txoptions ops;
+	__u8 dst_opt[8];
+};
+
+static int nf_flow_tunnel_ip6ip6_push(struct net *net, struct sk_buff *skb,
+				      struct flow_offload_tuple *tuple,
+				      struct in6_addr **ip6_daddr)
+{
+	struct ipv6hdr *ip6h = (struct ipv6hdr *)skb_network_header(skb);
+	int err, mtu, encap_limit = IPV6_DEFAULT_TNL_ENCAP_LIMIT;
+	u8 hop_limit = ip6h->hop_limit, proto = IPPROTO_IPV6;
+	struct rtable *rt = dst_rtable(tuple->dst_cache);
+	__u8 dsfield = ipv6_get_dsfield(ip6h);
+	struct flowi6 fl6 = {
+		.daddr = tuple->tun.src_v6,
+		.saddr = tuple->tun.dst_v6,
+		.flowi6_proto = proto,
+	};
+	u32 headroom;
+
+	err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
+	if (err)
+		return err;
+
+	skb_set_inner_ipproto(skb, proto);
+	headroom = sizeof(*ip6h) + LL_RESERVED_SPACE(rt->dst.dev) +
+		   rt->dst.header_len;
+	if (encap_limit)
+		headroom += 8;
+	err = skb_cow_head(skb, headroom);
+	if (err)
+		return err;
+
+	skb_scrub_packet(skb, true);
+	mtu = dst_mtu(&rt->dst) - sizeof(*ip6h);
+	if (encap_limit)
+		mtu -= 8;
+	mtu = max(mtu, IPV6_MIN_MTU);
+	skb_dst_update_pmtu_no_confirm(skb, mtu);
+
+	if (encap_limit > 0) {
+		struct ipv6_tel_txoption opt = {
+			.dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT,
+			.dst_opt[3] = 1,
+			.dst_opt[4] = encap_limit,
+			.dst_opt[5] = IPV6_TLV_PADN,
+			.dst_opt[6] = 1,
+		};
+
+		opt.ops.dst1opt = (struct ipv6_opt_hdr *)opt.dst_opt;
+		opt.ops.opt_nflen = 8;
+		ipv6_push_frag_opts(skb, &opt.ops, &proto);
+	}
+
+	skb_push(skb, sizeof(*ip6h));
+	skb_reset_network_header(skb);
+
+	ip6h = ipv6_hdr(skb);
+	ip6_flow_hdr(ip6h, dsfield,
+		     ip6_make_flowlabel(net, skb, fl6.flowlabel, true, &fl6));
+	ip6h->hop_limit = hop_limit;
+	ip6h->nexthdr = proto;
+	ip6h->daddr = tuple->tun.src_v6;
+	ip6h->saddr = tuple->tun.dst_v6;
+	ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(*ip6h));
+	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
+	IP6CB(skb)->flags = 0;
+	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
+
+	*ip6_daddr = &tuple->tun.src_v6;
+
+	return 0;
+}
+
+static int nf_flow_tunnel_v6_push(struct net *net, struct sk_buff *skb,
+				  struct flow_offload_tuple *tuple,
+				  struct in6_addr **ip6_daddr)
+{
+	if (tuple->tun_num)
+		return nf_flow_tunnel_ip6ip6_push(net, skb, tuple, ip6_daddr);
+
+	return 0;
+}
+
 static int nf_flow_encap_push(struct sk_buff *skb,
 			      struct flow_offload_tuple *tuple)
 {
@@ -934,6 +1020,9 @@ static int nf_flow_offload_ipv6_forward(struct nf_flowtable_ctx *ctx,
 	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
 
 	mtu = flow->tuplehash[dir].tuple.mtu + ctx->offset;
+	if (flow->tuplehash[!dir].tuple.tun_num)
+		mtu -= sizeof(*ip6h);
+
 	if (unlikely(nf_flow_exceeds_mtu(skb, mtu)))
 		return 0;
 
@@ -1023,6 +1112,10 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	other_tuple = &flow->tuplehash[!dir].tuple;
 	ip6_daddr = &other_tuple->src_v6;
 
+	if (nf_flow_tunnel_v6_push(state->net, skb, other_tuple,
+				   &ip6_daddr) < 0)
+		return NF_DROP;
+
 	if (nf_flow_encap_push(skb, other_tuple) < 0)
 		return NF_DROP;
 

-- 
2.52.0