Re: [PATCH v2] x86,acpi: Limit "Dummy wait" workaround to older AMD and Intel processors

From: Andreas Mohr <andi@lisas.de>
To: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	linux-kernel@vger.kernel.org, rafael@kernel.org, lenb@kernel.org,
	linux-acpi@vger.kernel.org, linux-pm@vger.kernel.org,
	dave.hansen@linux.intel.com, bp@alien8.de, tglx@linutronix.de,
	andi@lisas.de, puwen@hygon.cn, mario.limonciello@amd.com,
	rui.zhang@intel.com, gpiccoli@igalia.com,
	daniel.lezcano@linaro.org, ananth.narayan@amd.com,
	gautham.shenoy@amd.com, Calvin Ong <calvin.ong@amd.com>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	stable@vger.kernel.org
Subject: Re: [PATCH v2] x86,acpi: Limit "Dummy wait" workaround to older AMD and Intel processors
Date: Mon, 26 Sep 2022 21:55:52 +0200	[thread overview]
Message-ID: <YzIDyLbGgzEv0wzP@rhlx01.hs-esslingen.de> (raw)
In-Reply-To: <9875e20e-8363-74ef-349d-d339eddb3cc2@amd.com>

Hi,

Am Mon, Sep 26, 2022 at 10:02:44PM +0530 schrieb K Prateek Nayak:
> Hello Peter,
> 
> On 9/26/2022 5:37 PM, Peter Zijlstra wrote:
> > For how many of the above have you changed behaviour?
> 
> The proposed logic does alter the behavior for x86 chipsets that depend
> on acpi_idle driver and have IOPORT based C-state. Based on what
> Rafael and Dave suggested, I have marked all Intel processors to be
> affected by this bug. In light of Andreas' report, I've also marked
> all the pre-family 17h AMD processors to be affected by this bug to avoid
> causing any regression.
> 
> It is hard to tell if any other vendor had this bug in their chipsets.
> Dave's patch does not make this consideration either and limits the
> dummy operation to only Intel chipsets using acpi_idle driver.
> (https://lore.kernel.org/all/78d13a19-2806-c8af-573e-7f2625edfab8@intel.com/)
> If folks reported a regression, I would have been happy to fix it for
> them.

Despite certain, umm, controversies, the discussion/patch activities
appear to be heading into a good direction ;)

This text somehow prompted me to think of
whether STPCLK# [quirk] behaviour is
a property of the CPU family, or the chipset, or actually a combination of it.

Given that [from recollection] VIA 8233/8235 spec PDFs do mention STPCLK#,
possibly a chipset does have a say in it? (which
obviously would then mean that
the kernel's quirk state decision-making would have to be refined)

Minor reference (note 8237, not 8233):
http://www.chipset-ic.com/datasheet/VT8237.pdf
  "STPCLK# is asserted by the VT8237R to the CPU to throttle the processor."
  (and many other STPCLK# mentions there)

Greetings

Andreas Mohr