linux-kernel - Re: [Letux-kernel] [RFC PATCH 0/3] Enable 1GHz support on omap36xx

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]

Date:   Mon, 9 Sep 2019 19:03:06 +0200
From:   "H. Nikolaus Schaller" <hns@...delico.com>
To:     Adam Ford <aford173@...il.com>
Cc:     Tony Lindgren <tony@...mide.com>,
        André Roth <neolynx@...il.com>,
        Linux-OMAP <linux-omap@...r.kernel.org>,
        Discussions about the Letux Kernel 
        <letux-kernel@...nphoenux.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        Andreas Kemnade <andreas@...nade.info>,
        Nishanth Menon <nm@...com>
Subject: Re: [Letux-kernel] [RFC PATCH 0/3] Enable 1GHz support on omap36xx


> Am 09.09.2019 um 18:38 schrieb Adam Ford <aford173@...il.com>:
> 
> On Mon, Sep 9, 2019 at 11:32 AM Tony Lindgren <tony@...mide.com> wrote:
>> 
>> Hi,
>> 
>> * H. Nikolaus Schaller <hns@...delico.com> [190909 14:57]:
>>> Another question that came up by private mail from André was if we
>>> should better disable the turbo OPPs of omap34xx and 36xx by default
>>> (status = "disabled";) because there are concerns about overheating
>>> the chips and we have no thermal regulation like for omap4 & 5.
> 
> I thought there was a thermal sensor?

Yes.

> 
> cpu_thermal: cpu_thermal {
>        polling-delay-passive = <250>; /* milliseconds */
>        polling-delay = <1000>; /* milliseconds */
>        coefficients = <0 20000>;
> 
>                        /* sensor       ID */
>        thermal-sensors = <&bandgap     0>;
> };
> 
> Can this driver somehow notify the cpufreq that we've hit some limit?
> I know it's not as accurate as one would like, but even for non-1GHz
> versions, having it downclock would be a good thing when running at
> extreme temps.

Indeed it is not really reliable. For me it jumps up by 10° between first
reading within the next second (and seems to stay at this offset after first use).

But yes, I think it should be possible to use it similar to omap5-core-thermal.dtsi

Maybe we have to add "trips" and "core_crit". This must obviously be linked to
the cpufreq system. Or is it done automatically?

BR,
Nikolaus