linux-kernel - RE: [PATCH v3 1/2] cpu/smt: add a notifier to notify the SMT changes

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: <87pm8osi4t.ffs@tglx>
Date:   Fri, 31 Mar 2023 23:52:50 +0200
From:   Thomas Gleixner <tglx@...utronix.de>
To:     "Yang, WenYou" <WenYou.Yang@....com>,
        Peter Zijlstra <peterz@...radead.org>
Cc:     "Deucher, Alexander" <Alexander.Deucher@....com>,
        "Koenig, Christian" <Christian.Koenig@....com>,
        "Pan, Xinhui" <Xinhui.Pan@....com>,
        "Quan, Evan" <Evan.Quan@....com>,
        "Limonciello, Mario" <Mario.Limonciello@....com>,
        "bp@...en8.de" <bp@...en8.de>,
        "jpoimboe@...nel.org" <jpoimboe@...nel.org>,
        "Phillips, Kim" <kim.phillips@....com>,
        "Yuan, Perry" <Perry.Yuan@....com>,
        "Liang, Richard qi" <Richardqi.Liang@....com>,
        "Li, Ying" <YING.LI@....com>, "Liu, Kun" <Kun.Liu2@....com>,
        "gpiccoli@...lia.com" <gpiccoli@...lia.com>,
        "amd-gfx@...ts.freedesktop.org" <amd-gfx@...ts.freedesktop.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
Subject: RE: [PATCH v3 1/2] cpu/smt: add a notifier to notify the SMT changes

On Fri, Mar 31 2023 at 05:49, WenYou Yang wrote:

<SNIP>
        Removing pointlessly copied mail headers. Please fix your email
        client
</SNIP>

>> >
>> > So what do you want to have happen when someone goes and manually
>> > offlines all the SMT siblings using
>> > /sys/devices/system/cpu/cpu*/online
>> > ?
>> 
>> I don't consider this situation.  Any suggestions will be deeply appreciated.
>
> Hi Peter,
>
> I don't find a good method to handle this situation.
> Yes, manually offlining all the SMT sibling will get the same result of SMT disabling on the fly.
>
> Actually, the normal way to enable/disable SMT on the fly is to echo on/off > /sys/device/system/cpu/smt/control

That's the most convenient way, right.

But why do we need a kernel notifier for this, if you can do the same
with a sysfs knob for your driver?

Then user space can fiddle with SMT control in sysfs and afterwards tell
the driver that it should reconfigure.

That makes a ton more sense than this random notifier.

Thanks,

        tglx