linux-kernel - Re: [PATCH v3 2/2] arm64: dts: qcom: sm8650: setup gpu thermal with higher temperatures

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] [thread-next>] [day] [month] [year] [list]

Message-ID: <82828c3a-ed8c-42b8-b603-bc73d3be7497@linaro.org>
Date: Mon, 3 Feb 2025 09:23:52 +0100
From: neil.armstrong@...aro.org
To: Konrad Dybcio <konrad.dybcio@....qualcomm.com>,
 Bjorn Andersson <andersson@...nel.org>,
 Konrad Dybcio <konradybcio@...nel.org>, Rob Herring <robh@...nel.org>,
 Krzysztof Kozlowski <krzk+dt@...nel.org>, Conor Dooley <conor+dt@...nel.org>
Cc: linux-arm-msm@...r.kernel.org, devicetree@...r.kernel.org,
 linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3 2/2] arm64: dts: qcom: sm8650: setup gpu thermal with
 higher temperatures

On 01/02/2025 16:37, Konrad Dybcio wrote:
> On 29.01.2025 3:41 PM, Neil Armstrong wrote:
>> On 29/01/2025 10:43, Neil Armstrong wrote:
>>> On the SM8650, the dynamic clock and voltage scaling (DCVS) for the GPU
>>> is done from the HLOS, but the GPU can achieve a much higher temperature
>>> before failing according the the reference downstream implementation.
>>>
>>> Set higher temperatures in the GPU trip points corresponding to
>>> the temperatures provided by Qualcomm in the dowstream source, much
>>> closer to the junction temperature and with a higher critical
>>> temperature trip in the case the HLOS DCVS cannot handle the
>>> temperature surge.
>>
>> Since the tsens MAX_THRESHOLD which leads to a system
>> monitor thermal shutdown is set at 120C, I need to lower
>> the critical and hot trip point, so please ignore this patchset.
> 
> Should we make the "critical" trip point something like 110 or so? If
> LMH triggers a hard shutdown at 120, the OS will not have any time to
> take action. And 120 sounds like we're pushing it quite hard anyway.


My plan is to harmonize and use 110 for hot and 115 for critical, and
if available any passive cooling devices is available at 95C

Neil

> 
> Konrad