selftests: bpf: add test_lwt_ip_encap selftest

This patch adds a bpf self-test to cover BPF_LWT_ENCAP_IP mode
in bpf_lwt_push_encap.

Covered:
- encapping in LWT_IN and LWT_XMIT
- IPv4 and IPv6

A follow-up patch will add GSO and VRF-enabled tests.

Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 398 insertions, 1 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c3edf47da05d..ccffaa0a0787 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -50,7 +50,8 @@ TEST_PROGS := test_kmod.sh \
 	test_lirc_mode2.sh \
 	test_skb_cgroup_id.sh \
 	test_flow_dissector.sh \
-	test_xdp_vlan.sh
+	test_xdp_vlan.sh \
+	test_lwt_ip_encap.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
new file mode 100644
index 000000000000..c957d6dfe6d7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_lwt_ip_encap.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+struct grehdr {
+	__be16 flags;
+	__be16 protocol;
+};
+
+SEC("encap_gre")
+int bpf_lwt_encap_gre(struct __sk_buff *skb)
+{
+	struct encap_hdr {
+		struct iphdr iph;
+		struct grehdr greh;
+	} hdr;
+	int err;
+
+	memset(&hdr, 0, sizeof(struct encap_hdr));
+
+	hdr.iph.ihl = 5;
+	hdr.iph.version = 4;
+	hdr.iph.ttl = 0x40;
+	hdr.iph.protocol = 47;  /* IPPROTO_GRE */
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
+	hdr.iph.saddr = 0x640110ac;  /* 172.16.1.100 */
+	hdr.iph.daddr = 0x641010ac;  /* 172.16.16.100 */
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
+	hdr.iph.saddr = 0xac100164;  /* 172.16.1.100 */
+	hdr.iph.daddr = 0xac101064;  /* 172.16.16.100 */
+#else
+#error "Fix your compiler's __BYTE_ORDER__?!"
+#endif
+	hdr.iph.tot_len = bpf_htons(skb->len + sizeof(struct encap_hdr));
+
+	hdr.greh.protocol = skb->protocol;
+
+	err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr,
+				 sizeof(struct encap_hdr));
+	if (err)
+		return BPF_DROP;
+
+	return BPF_LWT_REROUTE;
+}
+
+SEC("encap_gre6")
+int bpf_lwt_encap_gre6(struct __sk_buff *skb)
+{
+	struct encap_hdr {
+		struct ipv6hdr ip6hdr;
+		struct grehdr greh;
+	} hdr;
+	int err;
+
+	memset(&hdr, 0, sizeof(struct encap_hdr));
+
+	hdr.ip6hdr.version = 6;
+	hdr.ip6hdr.payload_len = bpf_htons(skb->len + sizeof(struct grehdr));
+	hdr.ip6hdr.nexthdr = 47;  /* IPPROTO_GRE */
+	hdr.ip6hdr.hop_limit = 0x40;
+	/* fb01::1 */
+	hdr.ip6hdr.saddr.s6_addr[0] = 0xfb;
+	hdr.ip6hdr.saddr.s6_addr[1] = 1;
+	hdr.ip6hdr.saddr.s6_addr[15] = 1;
+	/* fb10::1 */
+	hdr.ip6hdr.daddr.s6_addr[0] = 0xfb;
+	hdr.ip6hdr.daddr.s6_addr[1] = 0x10;
+	hdr.ip6hdr.daddr.s6_addr[15] = 1;
+
+	hdr.greh.protocol = skb->protocol;
+
+	err = bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &hdr,
+				 sizeof(struct encap_hdr));
+	if (err)
+		return BPF_DROP;
+
+	return BPF_LWT_REROUTE;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lwt_ip_encap.sh b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
new file mode 100755
index 000000000000..4ca714e23ab0
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lwt_ip_encap.sh
@@ -0,0 +1,311 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Setup/topology:
+#
+#    NS1             NS2             NS3
+#   veth1 <---> veth2   veth3 <---> veth4 (the top route)
+#   veth5 <---> veth6   veth7 <---> veth8 (the bottom route)
+#
+#   each vethN gets IPv[4|6]_N address
+#
+#   IPv*_SRC = IPv*_1
+#   IPv*_DST = IPv*_4
+#
+#   all tests test pings from IPv*_SRC to IPv*_DST
+#
+#   by default, routes are configured to allow packets to go
+#   IP*_1 <=> IP*_2 <=> IP*_3 <=> IP*_4 (the top route)
+#
+#   a GRE device is installed in NS3 with IPv*_GRE, and
+#   NS1/NS2 are configured to route packets to IPv*_GRE via IP*_8
+#   (the bottom route)
+#
+# Tests:
+#
+#   1. routes NS2->IPv*_DST are brought down, so the only way a ping
+#      from IP*_SRC to IP*_DST can work is via IPv*_GRE
+#
+#   2a. in an egress test, a bpf LWT_XMIT program is installed on veth1
+#       that encaps the packets with an IP/GRE header to route to IPv*_GRE
+#
+#       ping: SRC->[encap at veth1:egress]->GRE:decap->DST
+#       ping replies go DST->SRC directly
+#
+#   2b. in an ingress test, a bpf LWT_IN program is installed on veth2
+#       that encaps the packets with an IP/GRE header to route to IPv*_GRE
+#
+#       ping: SRC->[encap at veth2:ingress]->GRE:decap->DST
+#       ping replies go DST->SRC directly
+
+set -e  # exit on error
+
+if [[ $EUID -ne 0 ]]; then
+	echo "This script must be run as root"
+	echo "FAIL"
+	exit 1
+fi
+
+readonly NS1="ns1-$(mktemp -u XXXXXX)"
+readonly NS2="ns2-$(mktemp -u XXXXXX)"
+readonly NS3="ns3-$(mktemp -u XXXXXX)"
+
+readonly IPv4_1="172.16.1.100"
+readonly IPv4_2="172.16.2.100"
+readonly IPv4_3="172.16.3.100"
+readonly IPv4_4="172.16.4.100"
+readonly IPv4_5="172.16.5.100"
+readonly IPv4_6="172.16.6.100"
+readonly IPv4_7="172.16.7.100"
+readonly IPv4_8="172.16.8.100"
+readonly IPv4_GRE="172.16.16.100"
+
+readonly IPv4_SRC=$IPv4_1
+readonly IPv4_DST=$IPv4_4
+
+readonly IPv6_1="fb01::1"
+readonly IPv6_2="fb02::1"
+readonly IPv6_3="fb03::1"
+readonly IPv6_4="fb04::1"
+readonly IPv6_5="fb05::1"
+readonly IPv6_6="fb06::1"
+readonly IPv6_7="fb07::1"
+readonly IPv6_8="fb08::1"
+readonly IPv6_GRE="fb10::1"
+
+readonly IPv6_SRC=$IPv6_1
+readonly IPv6_DST=$IPv6_4
+
+setup() {
+set -e  # exit on error
+	# create devices and namespaces
+	ip netns add "${NS1}"
+	ip netns add "${NS2}"
+	ip netns add "${NS3}"
+
+	ip link add veth1 type veth peer name veth2
+	ip link add veth3 type veth peer name veth4
+	ip link add veth5 type veth peer name veth6
+	ip link add veth7 type veth peer name veth8
+
+	ip netns exec ${NS2} sysctl -wq net.ipv4.ip_forward=1
+	ip netns exec ${NS2} sysctl -wq net.ipv6.conf.all.forwarding=1
+
+	ip link set veth1 netns ${NS1}
+	ip link set veth2 netns ${NS2}
+	ip link set veth3 netns ${NS2}
+	ip link set veth4 netns ${NS3}
+	ip link set veth5 netns ${NS1}
+	ip link set veth6 netns ${NS2}
+	ip link set veth7 netns ${NS2}
+	ip link set veth8 netns ${NS3}
+
+	# configure addesses: the top route (1-2-3-4)
+	ip -netns ${NS1}    addr add ${IPv4_1}/24  dev veth1
+	ip -netns ${NS2}    addr add ${IPv4_2}/24  dev veth2
+	ip -netns ${NS2}    addr add ${IPv4_3}/24  dev veth3
+	ip -netns ${NS3}    addr add ${IPv4_4}/24  dev veth4
+	ip -netns ${NS1} -6 addr add ${IPv6_1}/128 nodad dev veth1
+	ip -netns ${NS2} -6 addr add ${IPv6_2}/128 nodad dev veth2
+	ip -netns ${NS2} -6 addr add ${IPv6_3}/128 nodad dev veth3
+	ip -netns ${NS3} -6 addr add ${IPv6_4}/128 nodad dev veth4
+
+	# configure addresses: the bottom route (5-6-7-8)
+	ip -netns ${NS1}    addr add ${IPv4_5}/24  dev veth5
+	ip -netns ${NS2}    addr add ${IPv4_6}/24  dev veth6
+	ip -netns ${NS2}    addr add ${IPv4_7}/24  dev veth7
+	ip -netns ${NS3}    addr add ${IPv4_8}/24  dev veth8
+	ip -netns ${NS1} -6 addr add ${IPv6_5}/128 nodad dev veth5
+	ip -netns ${NS2} -6 addr add ${IPv6_6}/128 nodad dev veth6
+	ip -netns ${NS2} -6 addr add ${IPv6_7}/128 nodad dev veth7
+	ip -netns ${NS3} -6 addr add ${IPv6_8}/128 nodad dev veth8
+
+
+	ip -netns ${NS1} link set dev veth1 up
+	ip -netns ${NS2} link set dev veth2 up
+	ip -netns ${NS2} link set dev veth3 up
+	ip -netns ${NS3} link set dev veth4 up
+	ip -netns ${NS1} link set dev veth5 up
+	ip -netns ${NS2} link set dev veth6 up
+	ip -netns ${NS2} link set dev veth7 up
+	ip -netns ${NS3} link set dev veth8 up
+
+	# configure routes: IP*_SRC -> veth1/IP*_2 (= top route) default;
+	# the bottom route to specific bottom addresses
+
+	# NS1
+	# top route
+	ip -netns ${NS1}    route add ${IPv4_2}/32  dev veth1
+	ip -netns ${NS1}    route add default dev veth1 via ${IPv4_2}  # go top by default
+	ip -netns ${NS1} -6 route add ${IPv6_2}/128 dev veth1
+	ip -netns ${NS1} -6 route add default dev veth1 via ${IPv6_2}  # go top by default
+	# bottom route
+	ip -netns ${NS1}    route add ${IPv4_6}/32  dev veth5
+	ip -netns ${NS1}    route add ${IPv4_7}/32  dev veth5 via ${IPv4_6}
+	ip -netns ${NS1}    route add ${IPv4_8}/32  dev veth5 via ${IPv4_6}
+	ip -netns ${NS1} -6 route add ${IPv6_6}/128 dev veth5
+	ip -netns ${NS1} -6 route add ${IPv6_7}/128 dev veth5 via ${IPv6_6}
+	ip -netns ${NS1} -6 route add ${IPv6_8}/128 dev veth5 via ${IPv6_6}
+
+	# NS2
+	# top route
+	ip -netns ${NS2}    route add ${IPv4_1}/32  dev veth2
+	ip -netns ${NS2}    route add ${IPv4_4}/32  dev veth3
+	ip -netns ${NS2} -6 route add ${IPv6_1}/128 dev veth2
+	ip -netns ${NS2} -6 route add ${IPv6_4}/128 dev veth3
+	# bottom route
+	ip -netns ${NS2}    route add ${IPv4_5}/32  dev veth6
+	ip -netns ${NS2}    route add ${IPv4_8}/32  dev veth7
+	ip -netns ${NS2} -6 route add ${IPv6_5}/128 dev veth6
+	ip -netns ${NS2} -6 route add ${IPv6_8}/128 dev veth7
+
+	# NS3
+	# top route
+	ip -netns ${NS3}    route add ${IPv4_3}/32  dev veth4
+	ip -netns ${NS3}    route add ${IPv4_1}/32  dev veth4 via ${IPv4_3}
+	ip -netns ${NS3}    route add ${IPv4_2}/32  dev veth4 via ${IPv4_3}
+	ip -netns ${NS3} -6 route add ${IPv6_3}/128 dev veth4
+	ip -netns ${NS3} -6 route add ${IPv6_1}/128 dev veth4 via ${IPv6_3}
+	ip -netns ${NS3} -6 route add ${IPv6_2}/128 dev veth4 via ${IPv6_3}
+	# bottom route
+	ip -netns ${NS3}    route add ${IPv4_7}/32  dev veth8
+	ip -netns ${NS3}    route add ${IPv4_5}/32  dev veth8 via ${IPv4_7}
+	ip -netns ${NS3}    route add ${IPv4_6}/32  dev veth8 via ${IPv4_7}
+	ip -netns ${NS3} -6 route add ${IPv6_7}/128 dev veth8
+	ip -netns ${NS3} -6 route add ${IPv6_5}/128 dev veth8 via ${IPv6_7}
+	ip -netns ${NS3} -6 route add ${IPv6_6}/128 dev veth8 via ${IPv6_7}
+
+	# configure IPv4 GRE device in NS3, and a route to it via the "bottom" route
+	ip -netns ${NS3} tunnel add gre_dev mode gre remote ${IPv4_1} local ${IPv4_GRE} ttl 255
+	ip -netns ${NS3} link set gre_dev up
+	ip -netns ${NS3} addr add ${IPv4_GRE} dev gre_dev
+	ip -netns ${NS1} route add ${IPv4_GRE}/32 dev veth5 via ${IPv4_6}
+	ip -netns ${NS2} route add ${IPv4_GRE}/32 dev veth7 via ${IPv4_8}
+
+
+	# configure IPv6 GRE device in NS3, and a route to it via the "bottom" route
+	ip -netns ${NS3} -6 tunnel add name gre6_dev mode ip6gre remote ${IPv6_1} local ${IPv6_GRE} ttl 255
+	ip -netns ${NS3} link set gre6_dev up
+	ip -netns ${NS3} -6 addr add ${IPv6_GRE} nodad dev gre6_dev
+	ip -netns ${NS1} -6 route add ${IPv6_GRE}/128 dev veth5 via ${IPv6_6}
+	ip -netns ${NS2} -6 route add ${IPv6_GRE}/128 dev veth7 via ${IPv6_8}
+
+	# rp_filter gets confused by what these tests are doing, so disable it
+	ip netns exec ${NS1} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${NS2} sysctl -wq net.ipv4.conf.all.rp_filter=0
+	ip netns exec ${NS3} sysctl -wq net.ipv4.conf.all.rp_filter=0
+}
+
+cleanup() {
+	ip netns del ${NS1} 2> /dev/null
+	ip netns del ${NS2} 2> /dev/null
+	ip netns del ${NS3} 2> /dev/null
+}
+
+trap cleanup EXIT
+
+test_ping() {
+	local readonly PROTO=$1
+	local readonly EXPECTED=$2
+	local RET=0
+
+	set +e
+	if [ "${PROTO}" == "IPv4" ] ; then
+		ip netns exec ${NS1} ping  -c 1 -W 1 -I ${IPv4_SRC} ${IPv4_DST} 2>&1 > /dev/null
+		RET=$?
+	elif [ "${PROTO}" == "IPv6" ] ; then
+		ip netns exec ${NS1} ping6 -c 1 -W 6 -I ${IPv6_SRC} ${IPv6_DST} 2>&1 > /dev/null
+		RET=$?
+	else
+		echo "test_ping: unknown PROTO: ${PROTO}"
+		exit 1
+	fi
+	set -e
+
+	if [ "0" != "${RET}" ]; then
+		RET=1
+	fi
+
+	if [ "${EXPECTED}" != "${RET}" ] ; then
+		echo "FAIL: test_ping: ${RET}"
+		exit 1
+	fi
+}
+
+test_egress() {
+	local readonly ENCAP=$1
+	echo "starting egress ${ENCAP} encap test"
+	setup
+
+	# need to wait a bit for IPv6 to autoconf, otherwise
+	# ping6 sometimes fails with "unable to bind to address"
+
+	# by default, pings work
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	# remove NS2->DST routes, ping fails
+	ip -netns ${NS2}    route del ${IPv4_DST}/32  dev veth3
+	ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	# install replacement routes (LWT/eBPF), pings succeed
+	if [ "${ENCAP}" == "IPv4" ] ; then
+		ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1
+		ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre dev veth1
+	elif [ "${ENCAP}" == "IPv6" ] ; then
+		ip -netns ${NS1} route add ${IPv4_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1
+		ip -netns ${NS1} -6 route add ${IPv6_DST} encap bpf xmit obj test_lwt_ip_encap.o sec encap_gre6 dev veth1
+	else
+		echo "FAIL: unknown encap ${ENCAP}"
+	fi
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	cleanup
+	echo "PASS"
+}
+
+test_ingress() {
+	local readonly ENCAP=$1
+	echo "starting ingress ${ENCAP} encap test"
+	setup
+
+	# need to wait a bit for IPv6 to autoconf, otherwise
+	# ping6 sometimes fails with "unable to bind to address"
+
+	# by default, pings work
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	# remove NS2->DST routes, pings fail
+	ip -netns ${NS2}    route del ${IPv4_DST}/32  dev veth3
+	ip -netns ${NS2} -6 route del ${IPv6_DST}/128 dev veth3
+	test_ping IPv4 1
+	test_ping IPv6 1
+
+	# install replacement routes (LWT/eBPF), pings succeed
+	if [ "${ENCAP}" == "IPv4" ] ; then
+		ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2
+		ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre dev veth2
+	elif [ "${ENCAP}" == "IPv6" ] ; then
+		ip -netns ${NS2} route add ${IPv4_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2
+		ip -netns ${NS2} -6 route add ${IPv6_DST} encap bpf in obj test_lwt_ip_encap.o sec encap_gre6 dev veth2
+	else
+		echo "FAIL: unknown encap ${ENCAP}"
+	fi
+	test_ping IPv4 0
+	test_ping IPv6 0
+
+	cleanup
+	echo "PASS"
+}
+
+test_egress IPv4
+test_egress IPv6
+
+test_ingress IPv4
+test_ingress IPv6
+
+echo "all tests passed"