Add a test to verify that it is OK to iter the percpu_array map used for
global percpu data.

Signed-off-by: Leon Hwang <leon.hwang@linux.dev>
---
 .../bpf/prog_tests/global_data_init.c         | 52 +++++++++++++++++++
 .../bpf/progs/test_global_percpu_data.c       | 25 +++++++++
 2 files changed, 77 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
index c3b9423246b5..6c1813ffe5f3 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
@@ -333,6 +333,56 @@ static void test_global_percpu_data_xlated(void)
 	free(insns);
 }
 
+static void test_global_percpu_data_iter(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct test_global_percpu_data *skel;
+	union bpf_iter_link_info linfo = {};
+	struct bpf_link *link = NULL;
+	int fd, num_cpus, len, err;
+	char buf[16];
+
+	num_cpus = libbpf_num_possible_cpus();
+	if (!ASSERT_GT(num_cpus, 0, "libbpf_num_possible_cpus"))
+		return;
+
+	skel = test_global_percpu_data__open();
+	if (!ASSERT_OK_PTR(skel, "test_global_percpu_data__open"))
+		return;
+
+	skel->rodata->num_cpus = num_cpus;
+	skel->rodata->offsetof_num = offsetof(struct test_global_percpu_data__percpu, struct_data);
+	skel->rodata->offsetof_num += sizeof(skel->percpu->struct_data) - sizeof(int);
+	skel->rodata->elem_sz = roundup(sizeof(struct test_global_percpu_data__percpu), 8);
+	skel->percpu->struct_data.nums[6] = 0xc0de;
+
+	err = test_global_percpu_data__load(skel);
+	if (!ASSERT_OK(err, "test_global_percpu_data__load"))
+		goto out;
+
+	linfo.map.map_fd = bpf_map__fd(skel->maps.percpu);
+	opts.link_info = &linfo;
+	opts.link_info_len = sizeof(linfo);
+	link = bpf_program__attach_iter(skel->progs.dump_percpu_data, &opts);
+	if (!ASSERT_OK_PTR(link, "bpf_program__attach_iter"))
+		goto out;
+
+	fd = bpf_iter_create(bpf_link__fd(link));
+	if (!ASSERT_GE(fd, 0, "bpf_iter_create"))
+		goto out;
+
+	while ((len = read(fd, buf, sizeof(buf))) > 0)
+		do { } while (0);
+	ASSERT_EQ(len, 0, "read iter");
+	ASSERT_TRUE(skel->bss->run_iter, "run_iter");
+	ASSERT_EQ(skel->bss->percpu_data_sum, 0xc0de * num_cpus, "percpu_data_sum");
+
+	close(fd);
+out:
+	bpf_link__destroy(link);
+	test_global_percpu_data__destroy(skel);
+}
+
 void test_global_percpu_data(void)
 {
 	if (!feat_supported(NULL, FEAT_PERCPU_DATA)) {
@@ -348,4 +398,6 @@ void test_global_percpu_data(void)
 		test_global_percpu_data_verifier_log();
 	if (test__start_subtest("xlated"))
 		test_global_percpu_data_xlated();
+	if (test__start_subtest("iter"))
+		test_global_percpu_data_iter();
 }
diff --git a/tools/testing/selftests/bpf/progs/test_global_percpu_data.c b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
index 9a1b1a314c2f..037c8a05be4b 100644
--- a/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
+++ b/tools/testing/selftests/bpf/progs/test_global_percpu_data.c
@@ -62,4 +62,29 @@ int verifier_percpu_read(void *ctx)
 	return c == ' ';
 }
 
+volatile const __u32 num_cpus = 0;
+volatile const int offsetof_num;
+volatile const int elem_sz;
+__u32 percpu_data_sum = 0;
+bool run_iter = false;
+
+SEC("iter/bpf_map_elem")
+__auxiliary
+int dump_percpu_data(struct bpf_iter__bpf_map_elem *ctx)
+{
+	void *pptr = ctx->value;
+	int i;
+
+	if (!pptr)
+		return 0;
+
+	run_iter = true;
+
+	for (i = 0; i < num_cpus; i++) {
+		percpu_data_sum += *(int *) (pptr + offsetof_num);
+		pptr += elem_sz;
+	}
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
-- 
2.54.0