[PATCH bpf-next v2] selftests/bpf: Fix map_kptr test failure

[Yonghong Song <yonghong.song@linux.dev>]

On my arm64 machine, I get the following failure:
  ...
  tester_init:PASS:tester_log_buf 0 nsec
  process_subtest:PASS:obj_open_mem 0 nsec
  process_subtest:PASS:specs_alloc 0 nsec
  serial_test_map_kptr:PASS:rcu_tasks_trace_gp__open_and_load 0 nsec
  ...
  test_map_kptr_success:PASS:map_kptr__open_and_load 0 nsec
  test_map_kptr_success:PASS:test_map_kptr_ref1 refcount 0 nsec
  test_map_kptr_success:FAIL:test_map_kptr_ref1 retval unexpected error: 2 (errno 2)
  test_map_kptr_success:PASS:test_map_kptr_ref2 refcount 0 nsec
  test_map_kptr_success:FAIL:test_map_kptr_ref2 retval unexpected error: 1 (errno 2)
  ...
  #201/21  map_kptr/success-map:FAIL

In serial_test_map_kptr(), before test_map_kptr_success(), one
kern_sync_rcu() is used to have some delay for freeing the map.
But in my environment, one kern_sync_rcu() seems not enough and
caused the test failure.

In bpf_map_free_in_work() in syscall.c, the queue time for
  queue_work(system_dfl_wq, &map->work)
may be longer than expected. This may cause the test failure
since test_map_kptr_success() expects all previous maps having been freed.

Since it is not clear how long queue_work() time takes, a bpf prog
is added to count the reference after bpf_kfunc_call_test_acquire().
If the number of references is 2 (for initial ref and the one just
acquired), all previous maps should have been released. This will
resolve the above 'retval unexpected error' issue.

Cc: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 .../selftests/bpf/prog_tests/map_kptr.c       | 23 +++++++++++++++++++
 tools/testing/selftests/bpf/progs/map_kptr.c  | 18 +++++++++++++++
 2 files changed, 41 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/map_kptr.c b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
index 8743df599567..f372162c0280 100644
--- a/tools/testing/selftests/bpf/prog_tests/map_kptr.c
+++ b/tools/testing/selftests/bpf/prog_tests/map_kptr.c
@@ -131,6 +131,25 @@ static int kern_sync_rcu_tasks_trace(struct rcu_tasks_trace_gp *rcu)
 	return 0;
 }
 
+static void wait_for_map_release(void)
+{
+	LIBBPF_OPTS(bpf_test_run_opts, lopts);
+	struct map_kptr *skel;
+	int ret;
+
+	skel = map_kptr__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "map_kptr__open_and_load"))
+		return;
+
+	do {
+		ret = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.count_ref), &lopts);
+		ASSERT_OK(ret, "count_ref ret");
+		ASSERT_OK(lopts.retval, "count_ref retval");
+	} while (skel->bss->num_of_refs != 2);
+
+	map_kptr__destroy(skel);
+}
+
 void serial_test_map_kptr(void)
 {
 	struct rcu_tasks_trace_gp *skel;
@@ -148,11 +167,15 @@ void serial_test_map_kptr(void)
 
 		ASSERT_OK(kern_sync_rcu_tasks_trace(skel), "sync rcu_tasks_trace");
 		ASSERT_OK(kern_sync_rcu(), "sync rcu");
+		wait_for_map_release();
+
 		/* Observe refcount dropping to 1 on bpf_map_free_deferred */
 		test_map_kptr_success(false);
 
 		ASSERT_OK(kern_sync_rcu_tasks_trace(skel), "sync rcu_tasks_trace");
 		ASSERT_OK(kern_sync_rcu(), "sync rcu");
+		wait_for_map_release();
+
 		/* Observe refcount dropping to 1 on synchronous delete elem */
 		test_map_kptr_success(true);
 	}
diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c
index edaba481db9d..e708ffbe1f61 100644
--- a/tools/testing/selftests/bpf/progs/map_kptr.c
+++ b/tools/testing/selftests/bpf/progs/map_kptr.c
@@ -487,6 +487,24 @@ int test_map_kptr_ref3(struct __sk_buff *ctx)
 	return 0;
 }
 
+int num_of_refs;
+
+SEC("syscall")
+int count_ref(void *ctx)
+{
+	struct prog_test_ref_kfunc *p;
+	unsigned long arg = 0;
+
+	p = bpf_kfunc_call_test_acquire(&arg);
+	if (!p)
+		return 1;
+
+	num_of_refs = p->cnt.refs.counter;
+
+	bpf_kfunc_call_test_release(p);
+	return 0;
+}
+
 SEC("syscall")
 int test_ls_map_kptr_ref1(void *ctx)
 {
-- 
2.47.3