netdev - Re: [PATCH net-next 0/5] net/sched: Retire some tc qdiscs and classifiers

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]

Date:   Thu, 16 Feb 2023 09:51:37 +0100
From:   Paolo Abeni <pabeni@...hat.com>
To:     Jamal Hadi Salim <jhs@...atatu.com>, netdev@...r.kernel.org
Cc:     xiyou.wangcong@...il.com, jiri@...nulli.us, davem@...emloft.net,
        edumazet@...gle.com, kuba@...nel.org, stephen@...workplumber.org,
        dsahern@...il.com
Subject: Re: [PATCH net-next 0/5] net/sched: Retire some tc qdiscs and
 classifiers

On Tue, 2023-02-14 at 08:49 -0500, Jamal Hadi Salim wrote:
> The CBQ + dsmark qdiscs and the tcindex + rsvp classifiers have served us for
> over 2 decades. Unfortunately, they have not been getting much attention due
> to reduced usage. While we dont have a good metric for tabulating how much use
> a specific kernel feature gets, for these specific features we observed that
> some of the functionality has been broken for some time and no users complained.
> In addition, syzkaller has been going to town on most of these and finding
> issues; and while we have been fixing those issues, at times it becomes obvious
> that we would need to perform bigger surgeries to resolve things found while
> getting a syzkaller fix in place. After some discussion we feel that in order
> to reduce the maintenance burden it is best to retire them.
> 
> This patchset leaves the UAPI alone. I could send another version which deletes
> the UAPI as well. AFAIK, this has not been done before - so it wasnt clear what
> how to handle UAPI. It seems legit to just delete it but we would need to
> coordinate with iproute2 (given they sync up with kernel uapi headers). There
> are probably other users we don't know of that copy kernel headers.
> If folks feel differently I will resend the patches deleting UAPI for these
> qdiscs and classifiers.

I guess we could additionally remove all the references to the retired
qdiscs and classifiers from the default configs and from the self-tests
dependencies.

AFAICS such references do not cause any problem, as the now unexisting
kconfig knobs are automatically stripped at config generation time by
kbuild, but possibly worth a follow-up patch/series.

Thanks!

Paolo