selftests/bpf: Test FOU kfuncs for externally controlled ipip devices

Add tests for FOU and GUE encapsulation via the bpf_skb_{set,get}_fou_encap
kfuncs, using ipip devices in collect-metadata mode.

These tests make sure that we can successfully set and obtain FOU and GUE
encap parameters using ingress / egress BPF tc-hooks.
Signed-off-by: Christian Ehrig <cehrig@cloudflare.com>
Link: https://lore.kernel.org/r/040193566ddbdb0b53eb359f7ac7bbd316f338b5.1680874078.git.cehrig@cloudflare.comSigned-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/prog_tests/test_tunnel.c

@@ -89,6 +89,9 @@
 #define IP6VXLAN_TUNL_DEV0 "ip6vxlan00"
 #define IP6VXLAN_TUNL_DEV1 "ip6vxlan11"
 
+#define IPIP_TUNL_DEV0 "ipip00"
+#define IPIP_TUNL_DEV1 "ipip11"
+
 #define PING_ARGS "-i 0.01 -c 3 -w 10 -q"
 
 static int config_device(void)
@@ -188,6 +191,79 @@ static void delete_ip6vxlan_tunnel(void)
 	SYS_NOFAIL("ip link delete dev %s", IP6VXLAN_TUNL_DEV1);
 }
 
+enum ipip_encap {
+	NONE	= 0,
+	FOU	= 1,
+	GUE	= 2,
+};
+
+static int set_ipip_encap(const char *ipproto, const char *type)
+{
+	SYS(fail, "ip -n at_ns0 fou add port 5555 %s", ipproto);
+	SYS(fail, "ip -n at_ns0 link set dev %s type ipip encap %s",
+	    IPIP_TUNL_DEV0, type);
+	SYS(fail, "ip -n at_ns0 link set dev %s type ipip encap-dport 5555",
+	    IPIP_TUNL_DEV0);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static int add_ipip_tunnel(enum ipip_encap encap)
+{
+	int err;
+	const char *ipproto, *type;
+
+	switch (encap) {
+	case FOU:
+		ipproto = "ipproto 4";
+		type = "fou";
+		break;
+	case GUE:
+		ipproto = "gue";
+		type = ipproto;
+		break;
+	default:
+		ipproto = NULL;
+		type = ipproto;
+	}
+
+	/* at_ns0 namespace */
+	SYS(fail, "ip -n at_ns0 link add dev %s type ipip local %s remote %s",
+	    IPIP_TUNL_DEV0, IP4_ADDR_VETH0, IP4_ADDR1_VETH1);
+
+	if (type && ipproto) {
+		err = set_ipip_encap(ipproto, type);
+		if (!ASSERT_OK(err, "set_ipip_encap"))
+			goto fail;
+	}
+
+	SYS(fail, "ip -n at_ns0 link set dev %s up", IPIP_TUNL_DEV0);
+	SYS(fail, "ip -n at_ns0 addr add dev %s %s/24",
+	    IPIP_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
+
+	/* root namespace */
+	if (type && ipproto)
+		SYS(fail, "ip fou add port 5555 %s", ipproto);
+	SYS(fail, "ip link add dev %s type ipip external", IPIP_TUNL_DEV1);
+	SYS(fail, "ip link set dev %s up", IPIP_TUNL_DEV1);
+	SYS(fail, "ip addr add dev %s %s/24", IPIP_TUNL_DEV1,
+	    IP4_ADDR_TUNL_DEV1);
+
+	return 0;
+fail:
+	return -1;
+}
+
+static void delete_ipip_tunnel(void)
+{
+	SYS_NOFAIL("ip -n at_ns0 link delete dev %s", IPIP_TUNL_DEV0);
+	SYS_NOFAIL("ip -n at_ns0 fou del port 5555 2> /dev/null");
+	SYS_NOFAIL("ip link delete dev %s", IPIP_TUNL_DEV1);
+	SYS_NOFAIL("ip fou del port 5555 2> /dev/null");
+}
+
 static int test_ping(int family, const char *addr)
 {
 	SYS(fail, "%s %s %s > /dev/null", ping_command(family), PING_ARGS, addr);
@@ -386,10 +462,80 @@ static void test_ip6vxlan_tunnel(void)
 		test_tunnel_kern__destroy(skel);
 }
 
-#define RUN_TEST(name)							\
+static void test_ipip_tunnel(enum ipip_encap encap)
+{
+	struct test_tunnel_kern *skel = NULL;
+	struct nstoken *nstoken;
+	int set_src_prog_fd, get_src_prog_fd;
+	int ifindex = -1;
+	int err;
+	DECLARE_LIBBPF_OPTS(bpf_tc_hook, tc_hook,
+			    .attach_point = BPF_TC_INGRESS);
+
+	/* add ipip tunnel */
+	err = add_ipip_tunnel(encap);
+	if (!ASSERT_OK(err, "add_ipip_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(IPIP_TUNL_DEV1);
+	if (!ASSERT_NEQ(ifindex, 0, "ipip11 ifindex"))
+		goto done;
+	tc_hook.ifindex = ifindex;
+
+	switch (encap) {
+	case FOU:
+		get_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_encap_get_tunnel);
+		set_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_fou_set_tunnel);
+		break;
+	case GUE:
+		get_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_encap_get_tunnel);
+		set_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_gue_set_tunnel);
+		break;
+	default:
+		get_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_get_tunnel);
+		set_src_prog_fd = bpf_program__fd(
+			skel->progs.ipip_set_tunnel);
+	}
+
+	if (!ASSERT_GE(set_src_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	if (!ASSERT_GE(get_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;
+
+	/* ping from root namespace test */
+	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV0);
+	if (!ASSERT_OK(err, "test_ping"))
+		goto done;
+
+	/* ping from at_ns0 namespace test */
+	nstoken = open_netns("at_ns0");
+	err = test_ping(AF_INET, IP4_ADDR_TUNL_DEV1);
+	if (!ASSERT_OK(err, "test_ping"))
+		goto done;
+	close_netns(nstoken);
+
+done:
+	/* delete ipip tunnel */
+	delete_ipip_tunnel();
+	if (skel)
+		test_tunnel_kern__destroy(skel);
+}
+
+#define RUN_TEST(name, ...)						\
 	({								\
 		if (test__start_subtest(#name)) {			\
-			test_ ## name();				\
+			test_ ## name(__VA_ARGS__);			\
 		}							\
 	})
 
@@ -400,6 +546,9 @@ static void *test_tunnel_run_tests(void *arg)
 
 	RUN_TEST(vxlan_tunnel);
 	RUN_TEST(ip6vxlan_tunnel);
+	RUN_TEST(ipip_tunnel, NONE);
+	RUN_TEST(ipip_tunnel, FOU);
+	RUN_TEST(ipip_tunnel, GUE);
 
 	cleanup();
 

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

@@ -52,6 +52,21 @@ struct vxlan_metadata {
 	__u32     gbp;
 };
 
+struct bpf_fou_encap {
+	__be16 sport;
+	__be16 dport;
+};
+
+enum bpf_fou_encap_type {
+	FOU_BPF_ENCAP_FOU,
+	FOU_BPF_ENCAP_GUE,
+};
+
+int bpf_skb_set_fou_encap(struct __sk_buff *skb_ctx,
+			  struct bpf_fou_encap *encap, int type) __ksym;
+int bpf_skb_get_fou_encap(struct __sk_buff *skb_ctx,
+			  struct bpf_fou_encap *encap) __ksym;
+
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 1);
@@ -749,6 +764,108 @@ int ipip_get_tunnel(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+SEC("tc")
+int ipip_gue_set_tunnel(struct __sk_buff *skb)
+{
+	struct bpf_tunnel_key key = {};
+	struct bpf_fou_encap encap = {};
+	void *data = (void *)(long)skb->data;
+	struct iphdr *iph = data;
+	void *data_end = (void *)(long)skb->data_end;
+	int ret;
+
+	if (data + sizeof(*iph) > data_end) {
+		log_err(1);
+		return TC_ACT_SHOT;
+	}
+
+	key.tunnel_ttl = 64;
+	if (iph->protocol == IPPROTO_ICMP)
+		key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+
+	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	encap.sport = 0;
+	encap.dport = bpf_htons(5555);
+
+	ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_GUE);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("tc")
+int ipip_fou_set_tunnel(struct __sk_buff *skb)
+{
+	struct bpf_tunnel_key key = {};
+	struct bpf_fou_encap encap = {};
+	void *data = (void *)(long)skb->data;
+	struct iphdr *iph = data;
+	void *data_end = (void *)(long)skb->data_end;
+	int ret;
+
+	if (data + sizeof(*iph) > data_end) {
+		log_err(1);
+		return TC_ACT_SHOT;
+	}
+
+	key.tunnel_ttl = 64;
+	if (iph->protocol == IPPROTO_ICMP)
+		key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+
+	ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	encap.sport = 0;
+	encap.dport = bpf_htons(5555);
+
+	ret = bpf_skb_set_fou_encap(skb, &encap, FOU_BPF_ENCAP_FOU);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	return TC_ACT_OK;
+}
+
+SEC("tc")
+int ipip_encap_get_tunnel(struct __sk_buff *skb)
+{
+	int ret;
+	struct bpf_tunnel_key key = {};
+	struct bpf_fou_encap encap = {};
+
+	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_fou_encap(skb, &encap);
+	if (ret < 0) {
+		log_err(ret);
+		return TC_ACT_SHOT;
+	}
+
+	if (bpf_ntohs(encap.dport) != 5555)
+		return TC_ACT_SHOT;
+
+	bpf_printk("%d remote ip 0x%x, sport %d, dport %d\n", ret,
+		   key.remote_ipv4, bpf_ntohs(encap.sport),
+		   bpf_ntohs(encap.dport));
+	return TC_ACT_OK;
+}
+
 SEC("tc")
 int ipip6_set_tunnel(struct __sk_buff *skb)
 {