These selftests exercise the tcp_bpf_recvmsg() and tcp_bpf_recvmsg_parser()
functions, to ensure that they are properly handling spurious wakeups in
tcp_msg_wait_data().

The expected behaviour is that recvfrom() does not return an EAGAIN
error.  If the spurious wakeups are incorrectly handled, this assertion
will fail.

Signed-off-by: Nnamdi Onyeyiri <nnamdio@gmail.com>
---
 .../selftests/bpf/prog_tests/sockmap_basic.c  | 136 ++++++++++++++++++
 1 file changed, 136 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index cb3229711f93..afda4d90e573 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -1373,6 +1373,138 @@ static void test_sockmap_multi_channels(int sotype)
 	test_sockmap_pass_prog__destroy(skel);
 }
 
+static void *test_sockmap_recvfrom_eagain_thread(void *arg)
+{
+	int fd = *(int *)arg;
+	char buf[1024];
+	void *result = NULL;
+
+	while (true) {
+		ssize_t len = recvfrom(fd, buf, sizeof(buf), 0, NULL, NULL);
+
+		if (len == -1) {
+			if (errno == EINTR)
+				continue;
+			result = (void *)1;
+			break;
+		}
+
+		if (!len || buf[len - 1] == 'e')
+			break;
+	}
+
+	send(fd, "test", 4, MSG_NOSIGNAL);
+
+	close(fd);
+
+	return result;
+}
+
+static void test_sockmap_recvfrom_eagain(bool with_verdict)
+{
+	struct test_sockmap_pass_prog *skel = NULL;
+	struct bpf_program *prog = NULL;
+	char *buf = NULL;
+	int map, err;
+
+	/*
+	 * the size of the buffer to send.  completion of the sending can trigger a spurious wake
+	 * up.  larger values make the issue more likely, but make successful test runs longer.
+	 */
+	const size_t buflen = 1024 * 1024 * 25;
+
+	/*
+	 * maximum number of attempts to reproduce EAGAIN on spurious wake up.  more attempts
+	 * increases the chances of triggering the issue, and the test ends as soon as we do.
+	 * however, successful runs would take longer to complete.
+	 */
+	const int max_attempts = 300;
+
+	skel = test_sockmap_pass_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		return;
+
+	map = bpf_map__fd(skel->maps.sock_map_rx);
+
+	if (with_verdict) {
+		prog = skel->progs.prog_skb_verdict;
+		err = bpf_prog_attach(bpf_program__fd(prog), map, BPF_SK_SKB_STREAM_VERDICT, 0);
+		if (!ASSERT_OK(err, "bpf_prog_attach verdict"))
+			goto cleanup;
+	}
+
+	buf = malloc(buflen);
+	if (!ASSERT_OK_PTR(buf, "malloc buf"))
+		goto cleanup;
+	memset(buf, 0, buflen);
+	buf[buflen - 1] = 'e';
+
+	for (int i = 0; i < max_attempts; ++i) {
+		ssize_t len;
+		char ignored[128];
+		pthread_t thread;
+		bool thread_created = false;
+		size_t rem = buflen;
+		int c = -1, p = -1, zero = 0;
+		bool success = false;
+
+		err = create_pair(AF_INET, SOCK_STREAM, &c, &p);
+		if (!ASSERT_OK(err, "create_pair"))
+			goto end_attempt;
+
+		err = pthread_create(&thread, NULL, &test_sockmap_recvfrom_eagain_thread, &p);
+		if (!ASSERT_OK(err, "pthread_create"))
+			goto end_attempt;
+		thread_created = true;
+
+		err = bpf_map_update_elem(map, &zero, &c, BPF_ANY);
+		if (!ASSERT_OK(err, "bpf_map_update_elem"))
+			goto end_attempt;
+
+		while (rem) {
+			len = xsend(c, buf + (buflen - rem), rem, 0);
+			if (len == -1)
+				goto end_attempt;
+			rem -= len;
+		}
+
+		/* we cannot use recv_timeout(), otherwise EAGAIN would be an expected errno. */
+		len = recvfrom(c, ignored, sizeof(ignored), 0, NULL, NULL);
+
+		/*
+		 * we are checking for the invalid return of EAGAIN, any other return is considered
+		 * successful for the purposes of this test.
+		 */
+		if (len < 0 && !ASSERT_NEQ(errno, EAGAIN, "recvfrom eagain"))
+			goto end_attempt;
+
+		success = true;
+
+end_attempt:
+		if (c >= 0)
+			close(c);
+
+		if (thread_created) {
+			void *retval = NULL;
+
+			pthread_join(thread, &retval);
+			if (!ASSERT_NULL(retval, "retval"))
+				success = false;
+		}
+
+		if (!thread_created && p >= 0)
+			close(p);
+		if (!success)
+			break;
+	}
+
+cleanup:
+	if (buf)
+		free(buf);
+
+	test_sockmap_pass_prog__destroy(skel);
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -1451,4 +1583,8 @@ void test_sockmap_basic(void)
 		test_sockmap_multi_channels(SOCK_STREAM);
 	if (test__start_subtest("sockmap udp multi channels"))
 		test_sockmap_multi_channels(SOCK_DGRAM);
+	if (test__start_subtest("sockmap recvfrom eagain"))
+		test_sockmap_recvfrom_eagain(false);
+	if (test__start_subtest("sockmap recvfrom eagain with verdict"))
+		test_sockmap_recvfrom_eagain(true);
 }
-- 
2.52.0