bpf: selftests: Tcp header options

This patch adds tests for the new bpf tcp header option feature.

test_tcp_hdr_options.c:
- It tests header option writing and parsing in 3WHS: regular
  connection establishment, fastopen, and syncookie.
- In syncookie, the passive side's bpf prog is asking the active side
  to resend its bpf header option by specifying a RESEND bit in the
  outgoing SYNACK. handle_active_estab() and write_nodata_opt() has
  some details.
- handle_passive_estab() has comments on fastopen.
- It also has test for header writing and parsing in FIN packet.
- Most of the tests is writing an experimental option 254 with magic 0xeB9F.
- The no_exprm_estab() also tests writing a regular TCP option
  without any magic.

test_misc_tcp_options.c:
- It is an one directional test.  Active side writes option and
  passive side parses option.  The focus is to exercise
  the new helpers and API.
- Testing the new helper: bpf_load_hdr_opt() and bpf_store_hdr_opt().
- Testing the bpf_getsockopt(TCP_BPF_SYN).
- Negative tests for the above helpers.
- Testing the sock_ops->skb_data.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200820190117.2886749-1-kafai@fb.com

1 files changed, 622 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
new file mode 100644
index 000000000000..24ba0d21b641
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -0,0 +1,622 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/socket.h>
+#include <linux/compiler.h>
+
+#include "test_progs.h"
+#include "cgroup_helpers.h"
+#include "network_helpers.h"
+#include "test_tcp_hdr_options.h"
+#include "test_tcp_hdr_options.skel.h"
+#include "test_misc_tcp_hdr_options.skel.h"
+
+#define LO_ADDR6 "::eB9F"
+#define CG_NAME "/tcpbpf-hdr-opt-test"
+
+struct bpf_test_option exp_passive_estab_in;
+struct bpf_test_option exp_active_estab_in;
+struct bpf_test_option exp_passive_fin_in;
+struct bpf_test_option exp_active_fin_in;
+struct hdr_stg exp_passive_hdr_stg;
+struct hdr_stg exp_active_hdr_stg = { .active = true, };
+
+static struct test_misc_tcp_hdr_options *misc_skel;
+static struct test_tcp_hdr_options *skel;
+static int lport_linum_map_fd;
+static int hdr_stg_map_fd;
+static __u32 duration;
+static int cg_fd;
+
+struct sk_fds {
+	int srv_fd;
+	int passive_fd;
+	int active_fd;
+	int passive_lport;
+	int active_lport;
+};
+
+static int add_lo_addr(void)
+{
+	char ip_addr_cmd[256];
+	int cmdlen;
+
+	cmdlen = snprintf(ip_addr_cmd, sizeof(ip_addr_cmd),
+			  "ip -6 addr add %s/128 dev lo scope host",
+			  LO_ADDR6);
+
+	if (CHECK(cmdlen >= sizeof(ip_addr_cmd), "compile ip cmd",
+		  "failed to add host addr %s to lo. ip cmdlen is too long\n",
+		  LO_ADDR6))
+		return -1;
+
+	if (CHECK(system(ip_addr_cmd), "run ip cmd",
+		  "failed to add host addr %s to lo\n", LO_ADDR6))
+		return -1;
+
+	return 0;
+}
+
+static int create_netns(void)
+{
+	if (CHECK(unshare(CLONE_NEWNET), "create netns",
+		  "unshare(CLONE_NEWNET): %s (%d)",
+		  strerror(errno), errno))
+		return -1;
+
+	if (CHECK(system("ip link set dev lo up"), "run ip cmd",
+		  "failed to bring lo link up\n"))
+		return -1;
+
+	if (add_lo_addr())
+		return -1;
+
+	return 0;
+}
+
+static int write_sysctl(const char *sysctl, const char *value)
+{
+	int fd, err, len;
+
+	fd = open(sysctl, O_WRONLY);
+	if (CHECK(fd == -1, "open sysctl", "open(%s): %s (%d)\n",
+		  sysctl, strerror(errno), errno))
+		return -1;
+
+	len = strlen(value);
+	err = write(fd, value, len);
+	close(fd);
+	if (CHECK(err != len, "write sysctl",
+		  "write(%s, %s): err:%d %s (%d)\n",
+		  sysctl, value, err, strerror(errno), errno))
+		return -1;
+
+	return 0;
+}
+
+static void print_hdr_stg(const struct hdr_stg *hdr_stg, const char *prefix)
+{
+	fprintf(stderr, "%s{active:%u, resend_syn:%u, syncookie:%u, fastopen:%u}\n",
+		prefix ? : "", hdr_stg->active, hdr_stg->resend_syn,
+		hdr_stg->syncookie, hdr_stg->fastopen);
+}
+
+static void print_option(const struct bpf_test_option *opt, const char *prefix)
+{
+	fprintf(stderr, "%s{flags:0x%x, max_delack_ms:%u, rand:0x%x}\n",
+		prefix ? : "", opt->flags, opt->max_delack_ms, opt->rand);
+}
+
+static void sk_fds_close(struct sk_fds *sk_fds)
+{
+	close(sk_fds->srv_fd);
+	close(sk_fds->passive_fd);
+	close(sk_fds->active_fd);
+}
+
+static int sk_fds_shutdown(struct sk_fds *sk_fds)
+{
+	int ret, abyte;
+
+	shutdown(sk_fds->active_fd, SHUT_WR);
+	ret = read(sk_fds->passive_fd, &abyte, sizeof(abyte));
+	if (CHECK(ret != 0, "read-after-shutdown(passive_fd):",
+		  "ret:%d %s (%d)\n",
+		  ret, strerror(errno), errno))
+		return -1;
+
+	shutdown(sk_fds->passive_fd, SHUT_WR);
+	ret = read(sk_fds->active_fd, &abyte, sizeof(abyte));
+	if (CHECK(ret != 0, "read-after-shutdown(active_fd):",
+		  "ret:%d %s (%d)\n",
+		  ret, strerror(errno), errno))
+		return -1;
+
+	return 0;
+}
+
+static int sk_fds_connect(struct sk_fds *sk_fds, bool fast_open)
+{
+	const char fast[] = "FAST!!!";
+	struct sockaddr_in6 addr6;
+	socklen_t len;
+
+	sk_fds->srv_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0);
+	if (CHECK(sk_fds->srv_fd == -1, "start_server", "%s (%d)\n",
+		  strerror(errno), errno))
+		goto error;
+
+	if (fast_open)
+		sk_fds->active_fd = fastopen_connect(sk_fds->srv_fd, fast,
+						     sizeof(fast), 0);
+	else
+		sk_fds->active_fd = connect_to_fd(sk_fds->srv_fd, 0);
+
+	if (CHECK_FAIL(sk_fds->active_fd == -1)) {
+		close(sk_fds->srv_fd);
+		goto error;
+	}
+
+	len = sizeof(addr6);
+	if (CHECK(getsockname(sk_fds->srv_fd, (struct sockaddr *)&addr6,
+			      &len), "getsockname(srv_fd)", "%s (%d)\n",
+		  strerror(errno), errno))
+		goto error_close;
+	sk_fds->passive_lport = ntohs(addr6.sin6_port);
+
+	len = sizeof(addr6);
+	if (CHECK(getsockname(sk_fds->active_fd, (struct sockaddr *)&addr6,
+			      &len), "getsockname(active_fd)", "%s (%d)\n",
+		  strerror(errno), errno))
+		goto error_close;
+	sk_fds->active_lport = ntohs(addr6.sin6_port);
+
+	sk_fds->passive_fd = accept(sk_fds->srv_fd, NULL, 0);
+	if (CHECK(sk_fds->passive_fd == -1, "accept(srv_fd)", "%s (%d)\n",
+		  strerror(errno), errno))
+		goto error_close;
+
+	if (fast_open) {
+		char bytes_in[sizeof(fast)];
+		int ret;
+
+		ret = read(sk_fds->passive_fd, bytes_in, sizeof(bytes_in));
+		if (CHECK(ret != sizeof(fast), "read fastopen syn data",
+			  "expected=%lu actual=%d\n", sizeof(fast), ret)) {
+			close(sk_fds->passive_fd);
+			goto error_close;
+		}
+	}
+
+	return 0;
+
+error_close:
+	close(sk_fds->active_fd);
+	close(sk_fds->srv_fd);
+
+error:
+	memset(sk_fds, -1, sizeof(*sk_fds));
+	return -1;
+}
+
+static int check_hdr_opt(const struct bpf_test_option *exp,
+			 const struct bpf_test_option *act,
+			 const char *hdr_desc)
+{
+	if (CHECK(memcmp(exp, act, sizeof(*exp)),
+		  "expected-vs-actual", "unexpected %s\n", hdr_desc)) {
+		print_option(exp, "expected: ");
+		print_option(act, "  actual: ");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int check_hdr_stg(const struct hdr_stg *exp, int fd,
+			 const char *stg_desc)
+{
+	struct hdr_stg act;
+
+	if (CHECK(bpf_map_lookup_elem(hdr_stg_map_fd, &fd, &act),
+		  "map_lookup(hdr_stg_map_fd)", "%s %s (%d)\n",
+		  stg_desc, strerror(errno), errno))
+		return -1;
+
+	if (CHECK(memcmp(exp, &act, sizeof(*exp)),
+		  "expected-vs-actual", "unexpected %s\n", stg_desc)) {
+		print_hdr_stg(exp, "expected: ");
+		print_hdr_stg(&act, "  actual: ");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int check_error_linum(const struct sk_fds *sk_fds)
+{
+	unsigned int nr_errors = 0;
+	struct linum_err linum_err;
+	int lport;
+
+	lport = sk_fds->passive_lport;
+	if (!bpf_map_lookup_elem(lport_linum_map_fd, &lport, &linum_err)) {
+		fprintf(stderr,
+			"bpf prog error out at lport:passive(%d), linum:%u err:%d\n",
+			lport, linum_err.linum, linum_err.err);
+		nr_errors++;
+	}
+
+	lport = sk_fds->active_lport;
+	if (!bpf_map_lookup_elem(lport_linum_map_fd, &lport, &linum_err)) {
+		fprintf(stderr,
+			"bpf prog error out at lport:active(%d), linum:%u err:%d\n",
+			lport, linum_err.linum, linum_err.err);
+		nr_errors++;
+	}
+
+	return nr_errors;
+}
+
+static void check_hdr_and_close_fds(struct sk_fds *sk_fds)
+{
+	if (sk_fds_shutdown(sk_fds))
+		goto check_linum;
+
+	if (check_hdr_stg(&exp_passive_hdr_stg, sk_fds->passive_fd,
+			  "passive_hdr_stg"))
+		goto check_linum;
+
+	if (check_hdr_stg(&exp_active_hdr_stg, sk_fds->active_fd,
+			  "active_hdr_stg"))
+		goto check_linum;
+
+	if (check_hdr_opt(&exp_passive_estab_in, &skel->bss->passive_estab_in,
+			  "passive_estab_in"))
+		goto check_linum;
+
+	if (check_hdr_opt(&exp_active_estab_in, &skel->bss->active_estab_in,
+			  "active_estab_in"))
+		goto check_linum;
+
+	if (check_hdr_opt(&exp_passive_fin_in, &skel->bss->passive_fin_in,
+			  "passive_fin_in"))
+		goto check_linum;
+
+	check_hdr_opt(&exp_active_fin_in, &skel->bss->active_fin_in,
+		      "active_fin_in");
+
+check_linum:
+	CHECK_FAIL(check_error_linum(sk_fds));
+	sk_fds_close(sk_fds);
+}
+
+static void prepare_out(void)
+{
+	skel->bss->active_syn_out = exp_passive_estab_in;
+	skel->bss->passive_synack_out = exp_active_estab_in;
+
+	skel->bss->active_fin_out = exp_passive_fin_in;
+	skel->bss->passive_fin_out = exp_active_fin_in;
+}
+
+static void reset_test(void)
+{
+	size_t optsize = sizeof(struct bpf_test_option);
+	int lport, err;
+
+	memset(&skel->bss->passive_synack_out, 0, optsize);
+	memset(&skel->bss->passive_fin_out, 0, optsize);
+
+	memset(&skel->bss->passive_estab_in, 0, optsize);
+	memset(&skel->bss->passive_fin_in, 0, optsize);
+
+	memset(&skel->bss->active_syn_out, 0, optsize);
+	memset(&skel->bss->active_fin_out, 0, optsize);
+
+	memset(&skel->bss->active_estab_in, 0, optsize);
+	memset(&skel->bss->active_fin_in, 0, optsize);
+
+	skel->data->test_kind = TCPOPT_EXP;
+	skel->data->test_magic = 0xeB9F;
+
+	memset(&exp_passive_estab_in, 0, optsize);
+	memset(&exp_active_estab_in, 0, optsize);
+	memset(&exp_passive_fin_in, 0, optsize);
+	memset(&exp_active_fin_in, 0, optsize);
+
+	memset(&exp_passive_hdr_stg, 0, sizeof(exp_passive_hdr_stg));
+	memset(&exp_active_hdr_stg, 0, sizeof(exp_active_hdr_stg));
+	exp_active_hdr_stg.active = true;
+
+	err = bpf_map_get_next_key(lport_linum_map_fd, NULL, &lport);
+	while (!err) {
+		bpf_map_delete_elem(lport_linum_map_fd, &lport);
+		err = bpf_map_get_next_key(lport_linum_map_fd, &lport, &lport);
+	}
+}
+
+static void fastopen_estab(void)
+{
+	struct bpf_link *link;
+	struct sk_fds sk_fds;
+
+	hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map);
+	lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map);
+
+	exp_passive_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS;
+	exp_passive_estab_in.rand = 0xfa;
+	exp_passive_estab_in.max_delack_ms = 11;
+
+	exp_active_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS;
+	exp_active_estab_in.rand = 0xce;
+	exp_active_estab_in.max_delack_ms = 22;
+
+	exp_passive_hdr_stg.fastopen = true;
+
+	prepare_out();
+
+	/* Allow fastopen without fastopen cookie */
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_fastopen", "1543"))
+		return;
+
+	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
+	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
+		  PTR_ERR(link)))
+		return;
+
+	if (sk_fds_connect(&sk_fds, true)) {
+		bpf_link__destroy(link);
+		return;
+	}
+
+	check_hdr_and_close_fds(&sk_fds);
+	bpf_link__destroy(link);
+}
+
+static void syncookie_estab(void)
+{
+	struct bpf_link *link;
+	struct sk_fds sk_fds;
+
+	hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map);
+	lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map);
+
+	exp_passive_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS;
+	exp_passive_estab_in.rand = 0xfa;
+	exp_passive_estab_in.max_delack_ms = 11;
+
+	exp_active_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS |
+					OPTION_F_RESEND;
+	exp_active_estab_in.rand = 0xce;
+	exp_active_estab_in.max_delack_ms = 22;
+
+	exp_passive_hdr_stg.syncookie = true;
+	exp_active_hdr_stg.resend_syn = true,
+
+	prepare_out();
+
+	/* Clear the RESEND to ensure the bpf prog can learn
+	 * want_cookie and set the RESEND by itself.
+	 */
+	skel->bss->passive_synack_out.flags &= ~OPTION_F_RESEND;
+
+	/* Enforce syncookie mode */
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "2"))
+		return;
+
+	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
+	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
+		  PTR_ERR(link)))
+		return;
+
+	if (sk_fds_connect(&sk_fds, false)) {
+		bpf_link__destroy(link);
+		return;
+	}
+
+	check_hdr_and_close_fds(&sk_fds);
+	bpf_link__destroy(link);
+}
+
+static void fin(void)
+{
+	struct bpf_link *link;
+	struct sk_fds sk_fds;
+
+	hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map);
+	lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map);
+
+	exp_passive_fin_in.flags = OPTION_F_RAND;
+	exp_passive_fin_in.rand = 0xfa;
+
+	exp_active_fin_in.flags = OPTION_F_RAND;
+	exp_active_fin_in.rand = 0xce;
+
+	prepare_out();
+
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1"))
+		return;
+
+	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
+	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
+		  PTR_ERR(link)))
+		return;
+
+	if (sk_fds_connect(&sk_fds, false)) {
+		bpf_link__destroy(link);
+		return;
+	}
+
+	check_hdr_and_close_fds(&sk_fds);
+	bpf_link__destroy(link);
+}
+
+static void __simple_estab(bool exprm)
+{
+	struct bpf_link *link;
+	struct sk_fds sk_fds;
+
+	hdr_stg_map_fd = bpf_map__fd(skel->maps.hdr_stg_map);
+	lport_linum_map_fd = bpf_map__fd(skel->maps.lport_linum_map);
+
+	exp_passive_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS;
+	exp_passive_estab_in.rand = 0xfa;
+	exp_passive_estab_in.max_delack_ms = 11;
+
+	exp_active_estab_in.flags = OPTION_F_RAND | OPTION_F_MAX_DELACK_MS;
+	exp_active_estab_in.rand = 0xce;
+	exp_active_estab_in.max_delack_ms = 22;
+
+	prepare_out();
+
+	if (!exprm) {
+		skel->data->test_kind = 0xB9;
+		skel->data->test_magic = 0;
+	}
+
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1"))
+		return;
+
+	link = bpf_program__attach_cgroup(skel->progs.estab, cg_fd);
+	if (CHECK(IS_ERR(link), "attach_cgroup(estab)", "err: %ld\n",
+		  PTR_ERR(link)))
+		return;
+
+	if (sk_fds_connect(&sk_fds, false)) {
+		bpf_link__destroy(link);
+		return;
+	}
+
+	check_hdr_and_close_fds(&sk_fds);
+	bpf_link__destroy(link);
+}
+
+static void no_exprm_estab(void)
+{
+	__simple_estab(false);
+}
+
+static void simple_estab(void)
+{
+	__simple_estab(true);
+}
+
+static void misc(void)
+{
+	const char send_msg[] = "MISC!!!";
+	char recv_msg[sizeof(send_msg)];
+	const unsigned int nr_data = 2;
+	struct bpf_link *link;
+	struct sk_fds sk_fds;
+	int i, ret;
+
+	lport_linum_map_fd = bpf_map__fd(misc_skel->maps.lport_linum_map);
+
+	if (write_sysctl("/proc/sys/net/ipv4/tcp_syncookies", "1"))
+		return;
+
+	link = bpf_program__attach_cgroup(misc_skel->progs.misc_estab, cg_fd);
+	if (CHECK(IS_ERR(link), "attach_cgroup(misc_estab)", "err: %ld\n",
+		  PTR_ERR(link)))
+		return;
+
+	if (sk_fds_connect(&sk_fds, false)) {
+		bpf_link__destroy(link);
+		return;
+	}
+
+	for (i = 0; i < nr_data; i++) {
+		/* MSG_EOR to ensure skb will not be combined */
+		ret = send(sk_fds.active_fd, send_msg, sizeof(send_msg),
+			   MSG_EOR);
+		if (CHECK(ret != sizeof(send_msg), "send(msg)", "ret:%d\n",
+			  ret))
+			goto check_linum;
+
+		ret = read(sk_fds.passive_fd, recv_msg, sizeof(recv_msg));
+		if (CHECK(ret != sizeof(send_msg), "read(msg)", "ret:%d\n",
+			  ret))
+			goto check_linum;
+	}
+
+	if (sk_fds_shutdown(&sk_fds))
+		goto check_linum;
+
+	CHECK(misc_skel->bss->nr_syn != 1, "unexpected nr_syn",
+	      "expected (1) != actual (%u)\n",
+		misc_skel->bss->nr_syn);
+
+	CHECK(misc_skel->bss->nr_data != nr_data, "unexpected nr_data",
+	      "expected (%u) != actual (%u)\n",
+	      nr_data, misc_skel->bss->nr_data);
+
+	/* The last ACK may have been delayed, so it is either 1 or 2. */
+	CHECK(misc_skel->bss->nr_pure_ack != 1 &&
+	      misc_skel->bss->nr_pure_ack != 2,
+	      "unexpected nr_pure_ack",
+	      "expected (1 or 2) != actual (%u)\n",
+		misc_skel->bss->nr_pure_ack);
+
+	CHECK(misc_skel->bss->nr_fin != 1, "unexpected nr_fin",
+	      "expected (1) != actual (%u)\n",
+	      misc_skel->bss->nr_fin);
+
+check_linum:
+	CHECK_FAIL(check_error_linum(&sk_fds));
+	sk_fds_close(&sk_fds);
+	bpf_link__destroy(link);
+}
+
+struct test {
+	const char *desc;
+	void (*run)(void);
+};
+
+#define DEF_TEST(name) { #name, name }
+static struct test tests[] = {
+	DEF_TEST(simple_estab),
+	DEF_TEST(no_exprm_estab),
+	DEF_TEST(syncookie_estab),
+	DEF_TEST(fastopen_estab),
+	DEF_TEST(fin),
+	DEF_TEST(misc),
+};
+
+void test_tcp_hdr_options(void)
+{
+	int i;
+
+	skel = test_tcp_hdr_options__open_and_load();
+	if (CHECK(!skel, "open and load skel", "failed"))
+		return;
+
+	misc_skel = test_misc_tcp_hdr_options__open_and_load();
+	if (CHECK(!misc_skel, "open and load misc test skel", "failed"))
+		goto skel_destroy;
+
+	cg_fd = test__join_cgroup(CG_NAME);
+	if (CHECK_FAIL(cg_fd < 0))
+		goto skel_destroy;
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		if (!test__start_subtest(tests[i].desc))
+			continue;
+
+		if (create_netns())
+			break;
+
+		tests[i].run();
+
+		reset_test();
+	}
+
+	close(cg_fd);
+skel_destroy:
+	test_misc_tcp_hdr_options__destroy(misc_skel);
+	test_tcp_hdr_options__destroy(skel);
+}