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;
Message-ID: <4baa3654-9a1b-b60c-4a3c-55debe9e8044@igalia.com>
Date:   Thu, 29 Sep 2022 14:15:05 -0300
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
 Thunderbird/102.2.2
Subject: Re: [PATCH] x86/split_lock: Restore warn mode (and add a new one) to
 avoid userspace regression
Content-Language: en-US
To:     Dave Hansen <dave.hansen@intel.com>, tony.luck@intel.com,
        tglx@linutronix.de, linux-kernel@vger.kernel.org, x86@kernel.org
Cc:     mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com,
        hpa@zytor.com, luto@kernel.org, kernel-dev@igalia.com,
        kernel@gpiccoli.net, Fenghua Yu <fenghua.yu@intel.com>,
        Joshua Ashton <joshua@froggi.es>,
        Paul Gofman <pgofman@codeweavers.com>,
        Pavel Machek <pavel@denx.de>,
        Pierre-Loup Griffais <pgriffais@valvesoftware.com>,
        Melissa Wen <mwen@igalia.com>
References: <20220928142109.150263-1-gpiccoli@igalia.com>
 <24f31510-5b33-ada5-9f0e-117420403e8c@intel.com>
 <1c742ae1-98cb-a5c1-ba3f-5e79b8861f0b@igalia.com>
 <cc8d0101-73b9-b286-a7a7-e9305cdc1bd9@intel.com>
 <7917fde2-a381-5404-c5ae-6ffd433f85ec@igalia.com>
 <ecbc58bc-a250-cf39-dea6-9b0b1c3e6503@intel.com>
From:   "Guilherme G. Piccoli" <gpiccoli@igalia.com>
In-Reply-To: <ecbc58bc-a250-cf39-dea6-9b0b1c3e6503@intel.com>
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 7bit
Precedence: bulk

Two responses in one:

First, I like Tony's idea - heuristic based on CPU number seems to make
sense. This number could be purely based on CPU number with a hardcoded
value, or based in a Kconfig (after N CPUs, add misery).


Now, second part below, inline:

On 29/09/2022 13:26, Dave Hansen wrote:
> [...]
> Let's be precise here, though.  It isn't that folks can't play.  It's
> that we *intentionally* put something in place that kept them from
> playing.  They can play just fine after disabling split lock detection.
>

Agreed with your wording, would just maybe "s/put something/added a
policy" heheh


>> [...]
> They don't have to live with it.  They can turn it off.  That's why the
> command-line disable is there.
> 

If they know how to do it, right? I'd rather have it as a new
non-default mechanism or at least, a Kconfig option in which gamer
distros could tune for their users, so we're not requiring them to tune
x86-specific parameters to play some game.