1. Patchew
  2. linux
  3. [PATCH bpf-next 0/3] Fix test_cgroup_iter_memcg issues found during back-porting
  4. View patch

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

Hui Zhu posted 3 patches 1 month, 2 weeks ago
There is a newer version of this series
[PATCH bpf-next 1/3] selftests/bpf: Check bpf_mem_cgroup_page_state return value
Posted by Hui Zhu 1 month, 2 weeks ago 
From: Hui Zhu <zhuhui@kylinos.cn>

When back-porting test_progs to different kernel versions, I encountered
an issue where the test_cgroup_iter_memcg test would falsely pass even
when bpf_mem_cgroup_page_state() failed.

The problem occurs when test_progs compiled on one kernel version is
executed on another kernel with different enum values for memory
statistics (e.g., NR_ANON_MAPPED, NR_FILE_PAGES). In such cases,
bpf_mem_cgroup_page_state() returns -1 to indicate failure, but the test
didn't check for this error condition and incorrectly reported success.

This patch adds explicit checks to ensure bpf_mem_cgroup_page_state()
doesn't return -1 before validating the actual statistics values. This
prevents false positives when running test_progs in cross-kernel
environments.

Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
---
 .../selftests/bpf/prog_tests/cgroup_iter_memcg.c     | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
index a5afd16705f0..13b299512429 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_iter_memcg.c
@@ -53,6 +53,8 @@ static void test_anon(struct bpf_link *link, struct memcg_query *memcg_query)
 	if (!ASSERT_OK(read_stats(link), "read stats"))
 		goto cleanup;
 
+	ASSERT_NEQ(memcg_query->nr_anon_mapped, (unsigned long)-1,
+		  "bpf_mem_cgroup_page_state NR_ANON_MAPPED");
 	ASSERT_GT(memcg_query->nr_anon_mapped, 0, "final anon mapped val");
 
 cleanup:
@@ -88,6 +90,10 @@ static void test_file(struct bpf_link *link, struct memcg_query *memcg_query)
 	if (!ASSERT_OK(read_stats(link), "read stats"))
 		goto cleanup_map;
 
+	ASSERT_NEQ(memcg_query->nr_file_pages, (unsigned long)-1,
+		  "bpf_mem_cgroup_page_state NR_FILE_PAGES");
+	ASSERT_NEQ(memcg_query->nr_file_mapped, (unsigned long)-1,
+		  "bpf_mem_cgroup_page_state NR_FILE_MAPPED");
 	ASSERT_GT(memcg_query->nr_file_pages, 0, "final file value");
 	ASSERT_GT(memcg_query->nr_file_mapped, 0, "final file mapped value");
 
@@ -119,6 +125,8 @@ static void test_shmem(struct bpf_link *link, struct memcg_query *memcg_query)
 	if (!ASSERT_OK(read_stats(link), "read stats"))
 		goto cleanup;
 
+	ASSERT_NEQ(memcg_query->nr_shmem, (unsigned long)-1,
+		  "bpf_mem_cgroup_page_state NR_SHMEM");
 	ASSERT_GT(memcg_query->nr_shmem, 0, "final shmem value");
 
 cleanup:
@@ -143,6 +151,8 @@ static void test_kmem(struct bpf_link *link, struct memcg_query *memcg_query)
 	if (!ASSERT_OK(read_stats(link), "read stats"))
 		goto cleanup;
 
+	ASSERT_NEQ(memcg_query->memcg_kmem, (unsigned long)-1,
+		  "bpf_mem_cgroup_page_state MEMCG_KMEM");
 	ASSERT_GT(memcg_query->memcg_kmem, 0, "kmem value");
 
 cleanup:
@@ -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");
 	ASSERT_GT(memcg_query->pgfault, 0, "final pgfault val");
 
 cleanup:
-- 
2.43.0
Re: [PATCH bpf-next 1/3] selftests/bpf: Check bpf_mem_cgroup_page_state return value
Posted by JP Kobryn 1 month, 2 weeks ago 
On 2/12/26 12:23 AM, Hui Zhu wrote:
> From: Hui Zhu <zhuhui@kylinos.cn>
> 
> When back-porting test_progs to different kernel versions, I encountered
> an issue where the test_cgroup_iter_memcg test would falsely pass even
> when bpf_mem_cgroup_page_state() failed.
> 
> The problem occurs when test_progs compiled on one kernel version is
> executed on another kernel with different enum values for memory
> statistics (e.g., NR_ANON_MAPPED, NR_FILE_PAGES). [...]

This patch looks good but I think to fully solve this cross-kernel issue
we should use co-re in the bpf program. In your second revision, can you
add an additional patch to make use of bpf_core_enum_value()? This way
instead of relying on enum values in vmlinux.h at compile-time, we use
the btf info at load-time instead to get the proper value for the given
kernel.
Re: [PATCH bpf-next 1/3] selftests/bpf: Check bpf_mem_cgroup_page_state return value
Posted by hui.zhu@linux.dev 1 month, 2 weeks ago 
2026年2月13日 08:14, "JP Kobryn" <inwardvessel@gmail.com mailto:inwardvessel@gmail.com?to=%22JP%20Kobryn%22%20%3Cinwardvessel%40gmail.com%3E > 写到:


> 
> On 2/12/26 12:23 AM, Hui Zhu wrote:
> 
> > 
> > From: Hui Zhu <zhuhui@kylinos.cn>
> >  When back-porting test_progs to different kernel versions, I encountered
> >  an issue where the test_cgroup_iter_memcg test would falsely pass even
> >  when bpf_mem_cgroup_page_state() failed.
> >  The problem occurs when test_progs compiled on one kernel version is
> >  executed on another kernel with different enum values for memory
> >  statistics (e.g., NR_ANON_MAPPED, NR_FILE_PAGES). [...]
> > 
> This patch looks good but I think to fully solve this cross-kernel issue
> we should use co-re in the bpf program. In your second revision, can you
> add an additional patch to make use of bpf_core_enum_value()? This way
> instead of relying on enum values in vmlinux.h at compile-time, we use
> the btf info at load-time instead to get the proper value for the given
> kernel.
>

I post v2 according to your comments.
Thanks for your review.

Best,
Hui
Re: [PATCH bpf-next 1/3] selftests/bpf: Check bpf_mem_cgroup_page_state return value
Posted by bot+bpf-ci@kernel.org 1 month, 2 weeks ago 
> 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?


---
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.
Re: [PATCH bpf-next 1/3] selftests/bpf: Check bpf_mem_cgroup_page_state return value
Posted by hui.zhu@linux.dev 1 month, 2 weeks ago 
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.
>

Patchew 2.1-devel-ea86937

© 2016 - 2026 Red Hat, Inc.