[PATCH v4 bpf-next 4/4] selftests/bpf: Add geneve with bpf_skb_set_tunnel_opt_dynptr test-case to test_progs

[Shmulik Ladkani <shmulik@metanetworks.com>]

Add geneve test to test_tunnel. The test setup and scheme resembles the
existing vxlan test.

The test also checks variable length tunnel option assignment using
bpf_skb_set_tunnel_opt_dynptr.

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
---
 .../selftests/bpf/prog_tests/test_tunnel.c    | 108 ++++++++++++++
 .../selftests/bpf/progs/test_tunnel_kern.c    | 136 ++++++++++++++++++
 2 files changed, 244 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
index 852da04ff281..9aae03c720e9 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_tunnel.c
@@ -87,6 +87,8 @@
 #define VXLAN_TUNL_DEV1 "vxlan11"
 #define IP6VXLAN_TUNL_DEV0 "ip6vxlan00"
 #define IP6VXLAN_TUNL_DEV1 "ip6vxlan11"
+#define GENEVE_TUNL_DEV0 "geneve00"
+#define GENEVE_TUNL_DEV1 "geneve11"
 
 #define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
 
@@ -133,6 +135,38 @@ static void cleanup(void)
 	SYS_NOFAIL("ip rule del to %s table 20 2> /dev/null", IP4_ADDR2_VETH1);
 	SYS_NOFAIL("ip link del %s 2> /dev/null", VXLAN_TUNL_DEV1);
 	SYS_NOFAIL("ip link del %s 2> /dev/null", IP6VXLAN_TUNL_DEV1);
+	SYS_NOFAIL("ip link del %s 2> /dev/null", GENEVE_TUNL_DEV1);
+}
+
+static int add_geneve_tunnel(void)
+{
+	/* at_ns0 namespace */
+	SYS("ip netns exec at_ns0 ip link add dev %s type geneve external",
+	    GENEVE_TUNL_DEV0);
+	SYS("ip netns exec at_ns0 ip link set dev %s address %s up",
+	    GENEVE_TUNL_DEV0, MAC_TUNL_DEV0);
+	SYS("ip netns exec at_ns0 ip addr add dev %s %s/24",
+	    GENEVE_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
+	SYS("ip netns exec at_ns0 ip neigh add %s lladdr %s dev %s",
+	    IP4_ADDR_TUNL_DEV1, MAC_TUNL_DEV1, GENEVE_TUNL_DEV0);
+
+	/* root namespace */
+	SYS("ip link add dev %s type geneve external", GENEVE_TUNL_DEV1);
+	SYS("ip link set dev %s address %s up", GENEVE_TUNL_DEV1, MAC_TUNL_DEV1);
+	SYS("ip addr add dev %s %s/24", GENEVE_TUNL_DEV1, IP4_ADDR_TUNL_DEV1);
+	SYS("ip neigh add %s lladdr %s dev %s",
+	    IP4_ADDR_TUNL_DEV0, MAC_TUNL_DEV0, GENEVE_TUNL_DEV1);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void delete_geneve_tunnel(void)
+{
+	SYS_NOFAIL("ip netns exec at_ns0 ip link delete dev %s",
+		   GENEVE_TUNL_DEV0);
+	SYS_NOFAIL("ip link delete dev %s", GENEVE_TUNL_DEV1);
 }
 
 static int add_vxlan_tunnel(void)
@@ -248,6 +282,79 @@ static int attach_tc_prog(struct bpf_tc_hook *hook, int igr_fd, int egr_fd)
 	return 0;
 }
 
+static void test_geneve_tunnel(void)
+{
+	struct test_tunnel_kern *skel = NULL;
+	struct nstoken *nstoken;
+	int local_ip_map_fd = -1;
+	int set_src_prog_fd, get_src_prog_fd;
+	int set_dst_prog_fd;
+	int key = 0, ifindex = -1;
+	uint local_ip;
+	int err;
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+			    .attach_point = BPF_TC_INGRESS);
+
+	/* add genve tunnel */
+	err = add_geneve_tunnel();
+	if (!ASSERT_OK(err, "add geneve tunnel"))
+		goto done;
+
+	/* load and attach bpf prog to tunnel dev tc hook point */
+	skel = test_tunnel_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_tunnel_kern__open_and_load"))
+		goto done;
+	ifindex = if_nametoindex(GENEVE_TUNL_DEV1);
+	if (!ASSERT_NEQ(ifindex, 0, "geneve11 ifindex"))
+		goto done;
+	tc_hook.ifindex = ifindex;
+	get_src_prog_fd = bpf_program__fd(skel->progs.geneve_get_tunnel_src);
+	set_src_prog_fd = bpf_program__fd(skel->progs.geneve_set_tunnel_src);
+	if (!ASSERT_GE(get_src_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
+		goto done;
+
+	/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
+	nstoken = open_netns("at_ns0");
+	if (!ASSERT_OK_PTR(nstoken, "setns src"))
+		goto done;
+	ifindex = if_nametoindex(GENEVE_TUNL_DEV0);
+	if (!ASSERT_NEQ(ifindex, 0, "geneve00 ifindex"))
+		goto done;
+	tc_hook.ifindex = ifindex;
+	set_dst_prog_fd = bpf_program__fd(skel->progs.geneve_set_tunnel_dst);
+	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	if (attach_tc_prog(&tc_hook, -1, set_dst_prog_fd))
+		goto done;
+	close_netns(nstoken);
+
+	/* use veth1 ip 1 as tunnel source ip */
+	local_ip_map_fd = bpf_map__fd(skel->maps.local_ip_map);
+	if (!ASSERT_GE(local_ip_map_fd, 0, "bpf_map__fd"))
+		goto done;
+	local_ip = IP4_ADDR1_HEX_VETH1;
+	err = bpf_map_update_elem(local_ip_map_fd, &key, &local_ip, BPF_ANY);
+	if (!ASSERT_OK(err, "update bpf local_ip_map"))
+		goto done;
+
+	/* ping test */
+	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
+	if (!ASSERT_OK(err, "test_ping"))
+		goto done;
+
+done:
+	/* delete geneve tunnel */
+	delete_geneve_tunnel();
+	if (local_ip_map_fd >= 0)
+		close(local_ip_map_fd);
+	if (skel)
+		test_tunnel_kern__destroy(skel);
+}
+
 static void test_vxlan_tunnel(void)
 {
 	struct test_tunnel_kern *skel = NULL;
@@ -408,6 +515,7 @@ static void *test_tunnel_run_tests(void *arg)
 
 	RUN_TEST(vxlan_tunnel);
 	RUN_TEST(ip6vxlan_tunnel);
+	RUN_TEST(geneve_tunnel);
 
 	cleanup();
 
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index 17f2f325b3f3..dfd274d2f65d 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -23,6 +23,17 @@
 
 #define log_err(__ret) bpf_printk("ERROR line:%d ret:%d\n", __LINE__, __ret)
 
+struct tun_opts_raw {
+	__u8 data[64];
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, struct tun_opts_raw);
+} geneve_opts SEC(".maps");
+
 struct geneve_opt {
 	__be16	opt_class;
 	__u8	type;
@@ -285,6 +296,131 @@ int ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+SEC("tc")
+int geneve_set_tunnel_dst(struct __sk_buff *skb)
+{
+	int ret;
+	struct bpf_tunnel_key key;
+	struct tun_opts_raw *opts;
+	struct bpf_dynptr dptr;
+	__u32 index = 0;
+	__u32 *local_ip = NULL;
+	int opts_len;
+
+	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+	if (!local_ip) {
+		log_err(-1);
+		return TC_ACT_SHOT;
+	}
+
+	index = 0;
+	opts = bpf_map_lookup_elem(&geneve_opts, &index);
+	if (!opts) {
+		log_err(-1);
+		return TC_ACT_SHOT;
+	}
+
+	__builtin_memset(&key, 0x0, sizeof(key));
+	key.local_ipv4 = 0xac100164; /* 172.16.1.100 */
+	key.remote_ipv4 = *local_ip;
+	key.tunnel_id = 2;
+	key.tunnel_tos = 0;
+	key.tunnel_ttl = 64;
+
+	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+				     BPF_F_ZERO_CSUM_TX);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	__builtin_memset(opts, 0x0, sizeof(*opts));
+	bpf_dynptr_from_mem(opts, sizeof(*opts), 0, &dptr);
+	/* dynamic number of empty geneve options (4 bytes each).
+	 * total len capped at sizeof(*opts) and is multiple of 4
+	 */
+	opts_len = (skb->len % sizeof(*opts)) & ~(sizeof(__u32) - 1);
+	ret = bpf_skb_set_tunnel_opt_dynptr(skb, &dptr, opts_len);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("tc")
+int geneve_set_tunnel_src(struct __sk_buff *skb)
+{
+	int ret;
+	struct bpf_tunnel_key key;
+	__u32 index = 0;
+	__u32 *local_ip = NULL;
+
+	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+	if (!local_ip) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	__builtin_memset(&key, 0x0, sizeof(key));
+	key.local_ipv4 = *local_ip;
+	key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+	key.tunnel_id = 2;
+	key.tunnel_tos = 0;
+	key.tunnel_ttl = 64;
+
+	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+				     BPF_F_ZERO_CSUM_TX);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("tc")
+int geneve_get_tunnel_src(struct __sk_buff *skb)
+{
+	int ret;
+	struct bpf_tunnel_key key;
+	struct tun_opts_raw opts;
+	int expected_opts_len;
+	__u32 index = 0;
+	__u32 *local_ip = NULL;
+
+	local_ip = bpf_map_lookup_elem(&local_ip_map, &index);
+	if (!local_ip) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	ret = bpf_skb_get_tunnel_opt(skb, &opts, sizeof(opts));
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	expected_opts_len = (skb->len % sizeof(opts)) & ~(sizeof(__u32) - 1);
+	if (key.local_ipv4 != *local_ip || ret != expected_opts_len) {
+		bpf_printk("geneve key %d local ip 0x%x remote ip 0x%x opts_len %d\n",
+			   key.tunnel_id, key.local_ipv4,
+			   key.remote_ipv4, ret);
+		bpf_printk("local_ip 0x%x\n", *local_ip);
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
 SEC("tc")
 int vxlan_set_tunnel_dst(struct __sk_buff *skb)
 {
-- 
2.37.2