[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAJ5Y-ebrzQfhac2eoEkt-haZiG_tMiix6dVvunrf9_+JzFVA0g@mail.gmail.com>
Date: Wed, 11 Feb 2015 20:57:28 -0500
From: Ashwin Chaugule <ashwin.chaugule@...aro.org>
To: Stephen Boyd <sboyd@...eaurora.org>
Cc: Will Deacon <will.deacon@....com>,
Devicetree List <devicetree@...r.kernel.org>,
Ashwin Chaugule <ashwinc@...eaurora.org>,
linux-arm-msm@...r.kernel.org,
Neil Leeder <nleeder@...eaurora.org>,
lkml <linux-kernel@...r.kernel.org>,
"linux-arm-kernel@...ts.infradead.org"
<linux-arm-kernel@...ts.infradead.org>
Subject: Re: [PATCH 2/2] ARM: perf: Add support for Scorpion PMUs
On 11 February 2015 at 13:27, Stephen Boyd <sboyd@...eaurora.org> wrote:
> On 02/10, Ashwin Chaugule wrote:
>> Hi Stephen,
>>
>> On 10 February 2015 at 20:05, Stephen Boyd <sboyd@...eaurora.org> wrote:
>> > Scorpion supports a set of local performance monitor event
>> > selection registers (LPM) sitting behind a cp15 based interface
>> > that extend the architected PMU events to include Scorpion CPU
>> > and Venum VFP specific events. To use these events the user is
>> > expected to program the lpm register with the event code shifted
>> > into the group they care about and then point the PMNx event at
>> > that region+group combo by writing a LPMn_GROUPx event. Add
>> > support for this hardware.
>> >
>> > Note: the raw event number is a pure software construct that
>> > allows us to map the multi-dimensional number space of regions,
>> > groups, and event codes into a flat event number space suitable
>> > for use by the perf framework.
>> >
>> > This is based on code originally written by Ashwin Chaugule and
>> > Neil Leeder [1] massed to become similar to the Krait PMU support
>> > code.
>>
>> Thanks for taking this up!
>> Overall this series looks good to me, but from what I faintly
>> recollect, doesn't this (and the Krait pmu code) get affected by
>> powercollapse issues anymore?
>> e.g.
>> https://www.codeaurora.org/cgit/quic/la/kernel/msm/commit/arch/arm/kernel/perf_event_msm.c?h=msm-3.4&id=b5ca687960f0fea2f4735e83ca5c9543474c19de
>>
>
> Right now there isn't any power collapse support in mainline so
> there's no immediate problem. Once we add power collapse support
> (i.e. cpuidle) to the Scorpion and Krait platforms we'll need to
> do something in the perf event code to properly maintain the
> counts across idle. I imagine it would be done by registering for
> cpu_pm notifications and then doing the save/restore on
> CPU_PM_ENTER and CPU_PM_EXIT. At least, that's what you started
> doing in this patch[1]. And then it seems the patch you mention
> came after that and actually did the save/restore of the counts.
>
> [1] https://www.codeaurora.org/cgit/quic/la/kernel/msm/commit/?h=msm-3.4&id=464983a7e991a484cac0bc0885cee4fee318d659
Right. Thats essential whenever the power collapse stuff goes in.
Thanks,
Ashwin.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists