linux-kernel - Re: [PATCH] arm64: dts: meson: vim3: reduce cpu thermal fan trigger temperature

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]

Date:   Mon, 14 Jun 2021 15:17:26 +0200
From:   Neil Armstrong <narmstrong@...libre.com>
To:     Daniel Lezcano <daniel.lezcano@...aro.org>,
        Nick Xie <xieqinick@...il.com>
Cc:     robh+dt@...nel.org, khilman@...libre.com, jbrunet@...libre.com,
        martin.blumenstingl@...glemail.com, devicetree@...r.kernel.org,
        linux-arm-kernel@...ts.infradead.org,
        linux-amlogic@...ts.infradead.org, linux-kernel@...r.kernel.org,
        Nick <nick@...das.com>, artem@...das.com
Subject: Re: [PATCH] arm64: dts: meson: vim3: reduce cpu thermal fan trigger
 temperature

Hi,
On 11/06/2021 09:45, Daniel Lezcano wrote:
> On 11/06/2021 09:30, Nick Xie wrote:
>> Hello Neil,
>>
>>
>> Neil Armstrong <narmstrong@...libre.com> 于2021年6月11日周五 下午3:15写道：
>>>
>>> Hi,
>>>
>>> On 11/06/2021 08:54, Nick Xie wrote:
>>>> Hello Neil,
>>>>
>>>> The MCU FAN won't work until the temperature reach to 80 degree centigrade,
>>>> Do you think the temperature is too high?
>>>
>>> I think 80 is tool high, but I fear 50 is way too low, but if you think 50 is OK after you ran some tests, just add it to the commit log and it's ok for me.
>>
>> I think it is OK, we use it for a long time.
> 
> 50°C sounds like normal temperature with regular load. That means the
> fan will be switched on most of the time when the board is used.
> 
> And this change may be put in regard with the other trip points in the
> common DT. For instance, enable the fan when reaching 80°C but set the
> passive trip point to 75°C instead of 85°C.
> 
> All that depends on the hardware characteristics and TDP which are in
> the TRM normally.
> 

I don't think such data exist in the datasheet or other public document, but the vendor source tree
sets:
- passive: 75°C
- hot 85°C
- critical 110°C

we set upstream:
- passive: 85°C
- hot 95°C
- critical 110°C

so maybe we should lower the passive & hot trip points, then the FAN 80°C trip point would be ok now according to Daniel's explanation.

Neil