linux-kernel - Can we backport EEVDF performance fixes to 6.6?

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-next>] [day] [month] [year] [list]

Message-ID: <00d0bd1d13ad2faa3766fd16394f882ff8e286c4.camel@alliedtelesis.co.nz>
Date: Thu, 17 Jul 2025 04:18:19 +0000
From: Thomas Winter <Thomas.Winter@...iedtelesis.co.nz>
To: "juri.lelli@...hat.com" <juri.lelli@...hat.com>,
	"vincent.guittot@...aro.org" <vincent.guittot@...aro.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: Can we backport EEVDF performance fixes to 6.6?

Hi All,

After upgrading a product from 5.15 to 6.6, we found that performance
took a hit on some workloads. Narrowed this down to the switch to
EEVDF.

I backported commit 6d71a9c61604 "sched/fair: Fix EEVDF entity
placement bug causing scheduling lag" which appears to mostly resolve
the issue.

I also applied related commits 4423af84b297 "sched/fair: optimize the
PLACE_LAG when se->vlag is zero" and c70fc32f4443 "sched/fair: Adhere
to place_entity() constraints" to avoid the warnings referenced there.

Can these patches be safely backported to 6.6? We would prefer to use
an official 6.6 release with the fixes.
Otherwise we have to wait for the next LTS to get these changes which
were put in 6.13.

Regards,
Thomas Winter