> The `bpf_struct_ops_opts` struct is extended with a `flags` member,
> which is then passed to the `bpf_link_create` syscall within
> `bpf_map__attach_struct_ops_opts`.
The commit message states the struct is "extended with a `flags` member", but
the flags field already exists in bpf_struct_ops_opts. It was added in commit
a09c73b18 ("libbpf: introduce bpf_map__attach_struct_ops_opts()"):
struct bpf_struct_ops_opts {
size_t sz;
__u32 flags;
__u32 relative_fd;
__u64 expected_revision;
size_t :0;
};
This patch adds code to USE the existing flags field, not extend the struct.
Would a message like "Pass the existing flags field from bpf_struct_ops_opts
to bpf_link_create" be more accurate?
---
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/21665371660
AI-authorship-score: medium
AI-authorship-explanation: The commit message contains a factual inaccuracy
about extending the struct when the field already existed, which could indicate
AI-generated text that didn't fully analyze the prior commit in the series.
issues-found: 1
issue-severity-score: low
issue-severity-explanation: The only issue is an inaccurate commit message that
claims to extend a struct with a field that already exists; this is a
documentation issue, not a code bug.
