netdev - Re: [PATCH bpf-next v4 14/16] selftests/bpf: Update task_local_storage/task_storage

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <bc860132eed39c90ac3599a9db86e80c781cce157f7edf455826d46260905a7f@mail.kernel.org>
Date: Sat, 31 Jan 2026 05:33:26 +0000 (UTC)
From: bot+bpf-ci@...nel.org
To: ameryhung@...il.com,bpf@...r.kernel.org
Cc: netdev@...r.kernel.org,alexei.starovoitov@...il.com,andrii@...nel.org,daniel@...earbox.net,memxor@...il.com,martin.lau@...nel.org,kpsingh@...nel.org,yonghong.song@...ux.dev,song@...nel.org,haoluo@...gle.com,ameryhung@...il.com,kernel-team@...a.com,ast@...nel.org,andrii@...nel.org,daniel@...earbox.net,martin.lau@...nel.org,eddyz87@...il.com,yonghong.song@...ux.dev,clm@...a.com,ihor.solodrai@...ux.dev
Subject: Re: [PATCH bpf-next v4 14/16] selftests/bpf: Update task_local_storage/task_storage_nodeadlock test

commit d58597062a783f7c4b2997c007bb7178b268dd14
Author: Amery Hung <ameryhung@...il.com>

selftests/bpf: Update task_local_storage/task_storage_nodeadlock test

This commit updates the task_storage_nodeadlock test to check for the new
error codes (-EDEADLK or -ETIMEDOUT) that bpf_task_storage_delete() returns
after the rqspinlock conversion, replacing the previous -EBUSY check.

> Adjsut the error code we are checking against as bpf_task_storage_get()
  ^^^^^^

There's a typo here: "Adjsut" should be "Adjust".

> Adjsut the error code we are checking against as bpf_task_storage_get()
>                                                  ^^^^^^^^^^^^^^^^^^^^^^
> now returns -EDEADLK or -ETIMEDOUT when deadlock happens.

Should this say bpf_task_storage_delete() instead of bpf_task_storage_get()?

The test code checks the return value of bpf_task_storage_delete():

    ret = bpf_task_storage_delete(&task_storage,
                                  bpf_get_current_task_btf());
    if (ret == -EDEADLK || ret == -ETIMEDOUT)

Looking at the kernel implementation, bpf_task_storage_get() returns NULL on
failure (not error codes), while bpf_task_storage_delete() propagates integer
error codes from bpf_selem_unlink() which can return -EDEADLK or -ETIMEDOUT
from the rqspinlock.

---
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/21539340647

AI-authorship-score: low
AI-authorship-explanation: The typo 'Adjsut' and incorrect function name reference suggest human error rather than AI generation, which typically produces more precise but sometimes generic content.
issues-found: 2
issue-severity-score: low
issue-severity-explanation: Both issues are commit message errors (typo and wrong function name) that do not affect functionality of the selftest code.