linux-kernel - Re: [PATCH] KVM: Disable wake-affine vCPU process to mitigate lock holder preemption

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] [day] [month] [year] [list]

Message-ID: <36f54918-171d-cf72-818e-dc8cec7cd3b0@redhat.com>
Date:   Fri, 2 Aug 2019 10:38:53 +0200
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Dario Faggioli <dfaggioli@...e.com>,
        Wanpeng Li <kernellwp@...il.com>, linux-kernel@...r.kernel.org,
        kvm@...r.kernel.org
Cc:     Radim Krčmář <rkrcmar@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Thomas Gleixner <tglx@...utronix.de>
Subject: Re: [PATCH] KVM: Disable wake-affine vCPU process to mitigate lock
 holder preemption

On 01/08/19 14:57, Dario Faggioli wrote:
> Can't we achieve this by removing SD_WAKE_AFFINE from the relevant
> scheduling domains? By acting on
> /proc/sys/kernel/sched_domain/cpuX/domainY/flags, I mean?
> 
> Of course this will impact all tasks, not only KVM vcpus. But if the
> host does KVM only anyway...

Perhaps add flags to the unified cgroups hierarchy instead.  But if the
"min_cap close to max_cap" heuristics are wrong they should indeed be fixed.

Paolo