[PATCH bpf v3 2/2] selftests/bpf: Test TCP_NODELAY in TCP hdr opt callbacks

[KaFai Wan <kafai.wan@linux.dev>]

Add a sockops selftest for the TCP_NODELAY restriction in
BPF_SOCK_OPS_HDR_OPT_LEN_CB and BPF_SOCK_OPS_WRITE_HDR_OPT_CB.

With BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG enabled,
bpf_setsockopt(TCP_NODELAY) returns -EOPNOTSUPP from
BPF_SOCK_OPS_HDR_OPT_LEN_CB and BPF_SOCK_OPS_WRITE_HDR_OPT_CB, avoiding
unbounded recursion and kernel stack overflow.

Other cases continue to work as before, including
BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB and user space
setsockopt(TCP_NODELAY).

Signed-off-by: KaFai Wan <kafai.wan@linux.dev>
---
 .../selftests/bpf/prog_tests/tcp_hdr_options.c    | 12 +++++++++++-
 .../bpf/progs/test_misc_tcp_hdr_options.c         | 15 ++++++++++++++-
 2 files changed, 25 insertions(+), 2 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
index 56685fc03c7e..7b9dbbb84316 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -461,7 +461,7 @@ static void misc(void)
 	const unsigned int nr_data = 2;
 	struct bpf_link *link;
 	struct sk_fds sk_fds;
-	int i, ret;
+	int i, ret, true_val = 1;
 
 	lport_linum_map_fd = bpf_map__fd(misc_skel->maps.lport_linum_map);
 
@@ -477,6 +477,10 @@ static void misc(void)
 		return;
 	}
 
+	ret = setsockopt(sk_fds.active_fd, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val));
+	if (!ASSERT_OK(ret, "setsockopt(TCP_NODELAY)"))
+		goto check_linum;
+
 	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),
@@ -507,6 +511,12 @@ static void misc(void)
 
 	ASSERT_EQ(misc_skel->bss->nr_hwtstamp, 0, "nr_hwtstamp");
 
+	ASSERT_TRUE(misc_skel->data->nodelay_est_ok, "unexpected nodelay_est_ok");
+
+	ASSERT_TRUE(misc_skel->data->nodelay_hdr_len_err, "unexpected nodelay_hdr_len_err");
+
+	ASSERT_TRUE(misc_skel->data->nodelay_write_hdr_err, "unexpected nodelay_write_hdr_err");
+
 check_linum:
 	ASSERT_FALSE(check_error_linum(&sk_fds), "check_error_linum");
 	sk_fds_close(&sk_fds);
diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
index d487153a839d..a02e28d9db2e 100644
--- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
@@ -29,6 +29,10 @@ unsigned int nr_syn = 0;
 unsigned int nr_fin = 0;
 unsigned int nr_hwtstamp = 0;
 
+bool nodelay_est_ok = true;
+bool nodelay_hdr_len_err = true;
+bool nodelay_write_hdr_err = true;
+
 /* Check the header received from the active side */
 static int __check_active_hdr_in(struct bpf_sock_ops *skops, bool check_syn)
 {
@@ -300,7 +304,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops)
 SEC("sockops")
 int misc_estab(struct bpf_sock_ops *skops)
 {
-	int true_val = 1;
+	int true_val = 1, false_val = 0, ret;
 
 	switch (skops->op) {
 	case BPF_SOCK_OPS_TCP_LISTEN_CB:
@@ -316,10 +320,19 @@ int misc_estab(struct bpf_sock_ops *skops)
 	case BPF_SOCK_OPS_PARSE_HDR_OPT_CB:
 		return handle_parse_hdr(skops);
 	case BPF_SOCK_OPS_HDR_OPT_LEN_CB:
+		ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val));
+		nodelay_hdr_len_err &= ret == -EOPNOTSUPP;
+
 		return handle_hdr_opt_len(skops);
 	case BPF_SOCK_OPS_WRITE_HDR_OPT_CB:
+		ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &true_val, sizeof(true_val));
+		nodelay_write_hdr_err &= ret == -EOPNOTSUPP;
+
 		return handle_write_hdr_opt(skops);
 	case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+		ret = bpf_setsockopt(skops, SOL_TCP, TCP_NODELAY, &false_val, sizeof(false_val));
+		nodelay_est_ok &= ret == 0;
+
 		return handle_passive_estab(skops);
 	}
 
-- 
2.43.0