Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Thomas Gleixner <tglx@linutronix.de>
To:     "Yang, WenYou" <WenYou.Yang@amd.com>,
        Peter Zijlstra <peterz@infradead.org>
Cc:     "Deucher, Alexander" <Alexander.Deucher@amd.com>,
        "Koenig, Christian" <Christian.Koenig@amd.com>,
        "Pan, Xinhui" <Xinhui.Pan@amd.com>,
        "Quan, Evan" <Evan.Quan@amd.com>,
        "Limonciello, Mario" <Mario.Limonciello@amd.com>,
        "bp@alien8.de" <bp@alien8.de>,
        "jpoimboe@kernel.org" <jpoimboe@kernel.org>,
        "Phillips, Kim" <kim.phillips@amd.com>,
        "Yuan, Perry" <Perry.Yuan@amd.com>,
        "Liang, Richard qi" <Richardqi.Liang@amd.com>,
        "Li, Ying" <YING.LI@amd.com>, "Liu, Kun" <Kun.Liu2@amd.com>,
        "gpiccoli@igalia.com" <gpiccoli@igalia.com>,
        "amd-gfx@lists.freedesktop.org" <amd-gfx@lists.freedesktop.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: RE: [PATCH v3 1/2] cpu/smt: add a notifier to notify the SMT changes
In-Reply-To: <DM6PR12MB3531340547BE346D07E88BE3FD8F9@DM6PR12MB3531.namprd12.prod.outlook.com>
References: <20230329015149.870132-1-WenYou.Yang@amd.com>
 <20230329015149.870132-2-WenYou.Yang@amd.com>
 <20230329071014.GC7701@hirez.programming.kicks-ass.net>
 <BYAPR12MB352749E2864A87C3C32B7D0FFD899@BYAPR12MB3527.namprd12.prod.outlook.com>
 <20230329085023.GO4253@hirez.programming.kicks-ass.net>
 <DM6PR12MB3531933678779C5923989925FD899@DM6PR12MB3531.namprd12.prod.outlook.com>
 <DM6PR12MB3531340547BE346D07E88BE3FD8F9@DM6PR12MB3531.namprd12.prod.outlook.com>
Date:   Fri, 31 Mar 2023 23:52:50 +0200
Message-ID: <87pm8osi4t.ffs@tglx>
MIME-Version: 1.0
Content-Type: text/plain
Precedence: bulk

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