Re: [PATCH bpf-next 1/3] selftests/bpf: Check bpf_mem_cgroup_page_state return value

[hui.zhu@linux.dev]

2026年2月12日 16:50, bot+bpf-ci@kernel.org mailto:bot+bpf-ci@kernel.org  写到:


> 
> > 
> > diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
> >  --- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
> >  +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
> > 
> [ ... ]
> 
> > 
> > @@ -170,6 +180,8 @@ static void test_pgfault(struct bpf_link *link, struct memcg_query *memcg_query)
> >  if (!ASSERT_OK(read_stats(link), "read stats"))
> >  goto cleanup;
> > 
> >  + ASSERT_NEQ(memcg_query->pgfault, (unsigned long)-1,
> >  + "bpf_mem_cgroup_page_state PGFAULT");
> > 
>  ^^^^^^^^^^^^^^^^^^^^^^^^^^^
> 
> The assertion message references bpf_mem_cgroup_page_state(), but the BPF
> program actually uses bpf_mem_cgroup_vm_events() to retrieve the pgfault
> value:
> 
> tools/testing/selftests/bpf/progs/cgroup_iter_memcg.c:
>  memcg_query.pgfault = bpf_mem_cgroup_vm_events(memcg, PGFAULT);
> 
> Should the message be "bpf_mem_cgroup_vm_events PGFAULT" instead?

Good catch!  I will fix it in the next version.

Best,
Hui

> 
> ---
> AI reviewed your patch. Please fix the bug or email reply why it's not a bug.
> See: https://github.com/kernel-patches/vmtest/blob/master/ci/claude/README.md
> 
> CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21939182103
> 
> AI-authorship-score: low
> AI-authorship-explanation: The commit message uses first-person narrative describing a real back-porting scenario, and the code changes are simple repetitive assertions typical of human-written test improvements.
> issues-found: 1
> issue-severity-score: low
> issue-severity-explanation: Minor documentation issue where an assertion message references the wrong BPF function name; does not affect test correctness or system behavior.
>