selftests/bpf: bpf tunnel encap test

Validate basic tunnel encapsulation using ipip.

Set up two namespaces connected by veth. Connect a client and server.
Do this with and without bpf encap.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/Makefile

@@ -52,7 +52,8 @@ TEST_PROGS := test_kmod.sh \
 	test_flow_dissector.sh \
 	test_xdp_vlan.sh \
 	test_lwt_ip_encap.sh \
-	test_tcp_check_syncookie.sh
+	test_tcp_check_syncookie.sh \
+	test_tc_tunnel.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \

tools/testing/selftests/bpf/progs/test_tc_tunnel.c

@@ -0,0 +1,83 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* In-place tunneling */
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <linux/types.h>
+
+#include "bpf_endian.h"
+#include "bpf_helpers.h"
+
+static const int cfg_port = 8000;
+
+static __always_inline void set_ipv4_csum(struct iphdr *iph)
+{
+	__u16 *iph16 = (__u16 *)iph;
+	__u32 csum;
+	int i;
+
+	iph->check = 0;
+
+#pragma clang loop unroll(full)
+	for (i = 0, csum = 0; i < sizeof(*iph) >> 1; i++)
+		csum += *iph16++;
+
+	iph->check = ~((csum & 0xffff) + (csum >> 16));
+}
+
+SEC("encap")
+int encap_f(struct __sk_buff *skb)
+{
+	struct iphdr iph_outer, iph_inner;
+	struct tcphdr tcph;
+
+	if (skb->protocol != __bpf_constant_htons(ETH_P_IP))
+		return TC_ACT_OK;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
+			       sizeof(iph_inner)) < 0)
+		return TC_ACT_OK;
+
+	/* filter only packets we want */
+	if (iph_inner.ihl != 5 || iph_inner.protocol != IPPROTO_TCP)
+		return TC_ACT_OK;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + sizeof(iph_inner),
+			       &tcph, sizeof(tcph)) < 0)
+		return TC_ACT_OK;
+
+	if (tcph.dest != __bpf_constant_htons(cfg_port))
+		return TC_ACT_OK;
+
+	/* add room between mac and network header */
+	if (bpf_skb_adjust_room(skb, sizeof(iph_outer), BPF_ADJ_ROOM_NET, 0))
+		return TC_ACT_SHOT;
+
+	/* prepare new outer network header */
+	iph_outer = iph_inner;
+	iph_outer.protocol = IPPROTO_IPIP;
+	iph_outer.tot_len = bpf_htons(sizeof(iph_outer) +
+				      bpf_htons(iph_outer.tot_len));
+	set_ipv4_csum(&iph_outer);
+
+	/* store new outer network header */
+	if (bpf_skb_store_bytes(skb, ETH_HLEN, &iph_outer, sizeof(iph_outer),
+				BPF_F_INVALIDATE_HASH) < 0)
+		return TC_ACT_SHOT;
+
+	/* bpf_skb_adjust_room has moved header to start of room: restore */
+	if (bpf_skb_store_bytes(skb, ETH_HLEN + sizeof(iph_outer),
+				&iph_inner, sizeof(iph_inner),
+				BPF_F_INVALIDATE_HASH) < 0)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
+char __license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_tc_tunnel.sh

@@ -0,0 +1,75 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# In-place tunneling
+
+# must match the port that the bpf program filters on
+readonly port=8000
+
+readonly ns_prefix="ns-$$-"
+readonly ns1="${ns_prefix}1"
+readonly ns2="${ns_prefix}2"
+
+readonly ns1_v4=192.168.1.1
+readonly ns2_v4=192.168.1.2
+
+setup() {
+	ip netns add "${ns1}"
+	ip netns add "${ns2}"
+
+	ip link add dev veth1 mtu 1500 netns "${ns1}" type veth \
+	      peer name veth2 mtu 1500 netns "${ns2}"
+
+	ip -netns "${ns1}" link set veth1 up
+	ip -netns "${ns2}" link set veth2 up
+
+	ip -netns "${ns1}" -4 addr add "${ns1_v4}/24" dev veth1
+	ip -netns "${ns2}" -4 addr add "${ns2_v4}/24" dev veth2
+
+	sleep 1
+}
+
+cleanup() {
+	ip netns del "${ns2}"
+	ip netns del "${ns1}"
+}
+
+server_listen() {
+	ip netns exec "${ns2}" nc -l -p "${port}" &
+	sleep 0.2
+}
+
+client_connect() {
+	ip netns exec "${ns1}" nc -z -w 1 "${ns2_v4}" "${port}"
+	echo $?
+}
+
+set -e
+trap cleanup EXIT
+
+setup
+
+# basic communication works
+echo "test basic connectivity"
+server_listen
+client_connect
+
+# clientside, insert bpf program to encap all TCP to port ${port}
+# client can no longer connect
+ip netns exec "${ns1}" tc qdisc add dev veth1 clsact
+ip netns exec "${ns1}" tc filter add dev veth1 egress \
+	bpf direct-action object-file ./test_tc_tunnel.o section encap
+echo "test bpf encap without decap (expect failure)"
+server_listen
+! client_connect
+
+# serverside, insert decap module
+# server is still running
+# client can connect again
+ip netns exec "${ns2}" ip link add dev testtun0 type ipip \
+	remote "${ns1_v4}" local "${ns2_v4}"
+ip netns exec "${ns2}" ip link set dev testtun0 up
+echo "test bpf encap with tunnel device decap"
+client_connect
+
+echo OK