libbpf: Add gating for arena globals relocation feature

[kernel-patches-daemon-bpf]

Pull request for series with
subject: libbpf: Add gating for arena globals relocation feature
version: 2
url: https://patchwork.kernel.org/project/netdevbpf/list/?series=1052461

[kernel-patches-daemon-bpf]

Upstream branch: db975de
series: https://patchwork.kernel.org/project/netdevbpf/list/?series=1052461
version: 2

[kernel-patches-review-bot]

commit 191fe04e749a644ea3d23633b7b5a0759c053f66
Author: Emil Tsalapatis <emil@etsalapatis.com>

libbpf: Add gating for arena globals relocation feature

This commit adds feature gating for arena globals relocation to maintain
backwards compatibility with older kernels that lack the verifier patch
12a1fe6e12db ("bpf/verifier: Do not limit maximum direct offset into
arena map").

> diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
> index b842b83e2480..b1a088dd83ac 100644
> --- a/tools/lib/bpf/features.c
> +++ b/tools/lib/bpf/features.c

[ ... ]

> @@ -581,6 +670,9 @@ static struct kern_feature_desc {
>  	[FEAT_BTF_QMARK_DATASEC] = {
>  		"BTF DATASEC names starting from '?'", probe_kern_btf_qmark_datasec,
>  	},
> +	[FEAT_ARENA_GLOBAL_RELOC] = {
> +		"Relocatable arena globals support", probe_kern_arena_global_reloc,
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

In the v1 review, Andrii requested naming the feature based on what is
being detected rather than what the feature is used for:

    "we don't detect 'relocatable arena globals support', we detect if
    ldimm64 allows full range offsets, so call the detector as such
    (i.e., what you detect, not what for you are doing that)."

https://lore.kernel.org/bpf/CAEf4BzYz3KBUyqR+OJCMns2Edsd+Dhyij=f8cqSEyY9OG0KCdw@mail.gmail.com/

The feature name and description still describe the use case rather than
what the probe actually detects (whether ldimm64 allows full range
offsets). Should the naming be updated to reflect the detection
mechanism?

> +	},
>  };

> diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
> index fc59b21b51b5..e0223a6e4c95 100644
> --- a/tools/lib/bpf/libbpf_internal.h
> +++ b/tools/lib/bpf/libbpf_internal.h
> @@ -392,6 +392,8 @@ enum kern_feature_id {
>  	FEAT_ARG_CTX_TAG,
>  	/* Kernel supports '?' at the front of datasec names */
>  	FEAT_BTF_QMARK_DATASEC,
> +	/* Kernel supports relocating arena globals to end of the arena */
> +	FEAT_ARENA_GLOBAL_RELOC,

Same naming concern here - the comment and enum name describe the use
case rather than the actual detection mechanism.

>  	__FEAT_CNT,
>  };

---

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

In-Reply-To-Subject: libbpf: Add gating for arena globals relocation feature
CI run summary: https://github.com/kernel-patches/bpf/actions/runs/21845712046

AI-authorship-score: low
AI-authorship-explanation: The commit follows established libbpf feature probe patterns with appropriate technical detail and changelog formatting typical of experienced kernel developers.
issues-found: 1
issue-severity-score: low
issue-severity-explanation: Unaddressed maintainer request regarding naming convention - feature name describes use case rather than detection mechanism as requested by Andrii Nakryiko.

[kernel-patches-daemon-bpf]

Forwarding comment 3874573621 via email
In-Reply-To: 20260209234850.2750149-1-emil@etsalapatis.com
Patch: https://patchwork.kernel.org/project/netdevbpf/patch/20260209234850.2750149-1-emil@etsalapatis.com/