linux-kernel - Re: [Patch v9 8/8] arm64: Enable averaging of thermal pressure for arm64 based SoCs

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, 3 Feb 2020 09:59:32 +0100
From:   Dietmar Eggemann <dietmar.eggemann@....com>
To:     Thara Gopinath <thara.gopinath@...aro.org>, mingo@...hat.com,
        peterz@...radead.org, ionela.voinescu@....com,
        vincent.guittot@...aro.org, rui.zhang@...el.com,
        qperret@...gle.com, daniel.lezcano@...aro.org,
        viresh.kumar@...aro.org, rostedt@...dmis.org, will@...nel.org,
        catalin.marinas@....com, sudeep.holla@....com,
        juri.lelli@...hat.com, corbet@....net
Cc:     linux-kernel@...r.kernel.org, amit.kachhap@...il.com,
        javi.merino@...nel.org, amit.kucheria@...durent.com
Subject: Re: [Patch v9 8/8] arm64: Enable averaging of thermal pressure for
 arm64 based SoCs

On 28.01.20 23:36, Thara Gopinath wrote:
> Enable CONFIG_HAVE_SCHED_THERMAL_PRESSURE in arm64 defconfig.
> 
> Signed-off-by: Thara Gopinath <thara.gopinath@...aro.org>
> ---
>  arch/arm64/configs/defconfig | 1 +
>  1 file changed, 1 insertion(+)
> 
> diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
> index 0565a61..7a8145b 100644
> --- a/arch/arm64/configs/defconfig
> +++ b/arch/arm64/configs/defconfig
> @@ -5,6 +5,7 @@ CONFIG_NO_HZ_IDLE=y
>  CONFIG_HIGH_RES_TIMERS=y
>  CONFIG_PREEMPT=y
>  CONFIG_IRQ_TIME_ACCOUNTING=y
> +CONFIG_HAVE_SCHED_THERMAL_PRESSURE=y

I thought about this a bit more and maybe it's not a good idea to enable
this by default. An erroneous thermal setup could have bad influence on
the CPU capacities and hence on the performance without people
understanding the cause of it.
If they have to actively enable it, chances are higher that they also
try to understand how higher thermal-cpufreq-X cooling states lead to
CPU capacity reduction and possibly inversion (big-LITTLE swap).

So if the thermal pressure feature is guarded by
CONFIG_HAVE_SCHED_THERMAL_PRESSURE the thermal pressure related code in
arch_topology.c (thermal_pressure, arch_set_thermal_pressure,
topology_get_thermal_pressure) should too. Saves some text and data of
arch_topology.o. Moreover Arm32 and Arm64 will be handled equally.