From: Viresh Kumar <viresh.kumar@linaro.org>
To: Sumit Gupta <sumitg@nvidia.com>
Cc: bbasu@nvidia.com, linux-pm@vger.kernel.org,
catalin.marinas@arm.com, rjw@rjwysocki.net,
linux-kernel@vger.kernel.org, jonathanh@nvidia.com,
talho@nvidia.com, thierry.reding@gmail.com,
linux-tegra@vger.kernel.org, mperttunen@nvidia.com,
will@kernel.org, linux-arm-kernel@lists.infradead.org
Subject: Re: [TEGRA194_CPUFREQ Patch 2/3] cpufreq: Add Tegra194 cpufreq driver
Date: Mon, 13 Apr 2020 11:51:41 +0530 [thread overview]
Message-ID: <20200413062141.a6hmwipexhv3sctq@vireshk-i7> (raw)
In-Reply-To: <00390070-38a1-19aa-ca59-42c4658bee7e@nvidia.com>
On 09-04-20, 16:51, Sumit Gupta wrote:
> We are using "read_counters_work" as local variable. So every invocation the
> function will have its own copy of counters for corresponding cpu. That's
> why are doing INIT_WORK_ONSTACK here.
Why? To support parallel calls to reading the freq ?
> > > > > > > > > + queue_work_on(cpu, read_counters_wq, &read_counters_work.work);
> > > > > > > > > + flush_work(&read_counters_work.work);
> > > > > > > >
> > > > > > > > Why can't this be done in current context ?
> > > > > > > >
> > > > > > > We used work queue instead of smp_call_function_single() to have long delay.
> > > > > >
> > > > > > Please explain completely, you have raised more questions than you
> > > > > > answered :)
> > > > > >
> > > > > > Why do you want to have long delays ?
> > > > > >
> > > > > Long delay value is used to have the observation window long enough for
> > > > > correctly reconstructing the CPU frequency considering noise.
> > > > > In next patch version, changed delay value to 500us which in our tests is
> > > > > considered reliable.
> > > >
> > > > I understand that you need to put a udelay() while reading the freq from
> > > > hardware, that is fine, but why do you need a workqueue for that? Why can't you
> > > > just read the values directly from the same context ?
> > > >
> > > The register to read frequency is per core and not accessible to other
> > > cores. So, we have to execute the function remotely as the target core to
> > > read frequency might be different from current.
> > > The functions for that are smp_call_function_single or queue_work_on.
> > > We used queue_work_on() to avoid long delay inside ipi interrupt context
> > > with interrupts disabled.
> >
> > Okay, I understand this now, finally :)
> >
> > But if the interrupts are disabled during some call, won't workqueues face the
> > same problem ?
> >
> Yes, we are trying to minimize the case.
But how do you know workqueues will perform better than
smp_call_function_single() ? Just asking for clarity on this as normally
everyone tries to do smp_call_function_single().
--
viresh
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2020-04-13 6:21 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-03 17:32 [TEGRA194_CPUFREQ Patch 1/3] firmware: tegra: adding function to get BPMP data Sumit Gupta
2019-12-03 17:32 ` [TEGRA194_CPUFREQ Patch 2/3] cpufreq: Add Tegra194 cpufreq driver Sumit Gupta
2019-12-04 5:40 ` Viresh Kumar
2019-12-04 10:55 ` sumitg
2019-12-04 11:27 ` Viresh Kumar
2019-12-04 13:57 ` Dmitry Osipenko
2019-12-05 2:51 ` Viresh Kumar
2019-12-05 12:55 ` Dmitry Osipenko
2020-03-25 23:59 ` sumitg
2019-12-04 13:59 ` Dmitry Osipenko
2019-12-05 14:15 ` Dmitry Osipenko
2020-03-26 11:50 ` Viresh Kumar
2020-04-04 18:38 ` sumitg
2020-04-06 2:55 ` Viresh Kumar
2020-04-07 18:18 ` sumitg
2020-04-08 5:53 ` Viresh Kumar
2020-04-08 11:24 ` sumitg
2020-04-09 7:44 ` Viresh Kumar
2020-04-09 11:21 ` Sumit Gupta
2020-04-13 6:21 ` Viresh Kumar [this message]
2020-04-13 12:20 ` Sumit Gupta
2020-04-14 5:45 ` Viresh Kumar
2020-04-15 11:25 ` Sumit Gupta
2020-04-16 3:37 ` Viresh Kumar
2020-04-16 7:06 ` Sumit Gupta
2019-12-03 17:32 ` [TEGRA194_CPUFREQ Patch 3/3] arm64: defconfig: Enable CONFIG_ARM_TEGRA194_CPUFREQ Sumit Gupta
2019-12-03 17:42 ` [TEGRA194_CPUFREQ Patch 1/3] firmware: tegra: adding function to get BPMP data Thierry Reding
2019-12-04 8:45 ` Mikko Perttunen
2019-12-04 9:17 ` Viresh Kumar
2019-12-04 9:33 ` Thierry Reding
2019-12-04 9:51 ` Viresh Kumar
2020-04-07 10:05 ` Thierry Reding
2020-04-27 7:18 ` Thierry Reding
2020-04-29 8:21 ` Sumit Gupta
2020-05-06 16:58 ` Thierry Reding
2020-05-20 14:43 ` Rob Herring
2020-05-20 15:38 ` Thierry Reding
2020-05-20 16:21 ` Rob Herring
2019-12-04 10:21 ` Mikko Perttunen
2019-12-04 10:26 ` Viresh Kumar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200413062141.a6hmwipexhv3sctq@vireshk-i7 \
--to=viresh.kumar@linaro.org \
--cc=bbasu@nvidia.com \
--cc=catalin.marinas@arm.com \
--cc=jonathanh@nvidia.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=linux-tegra@vger.kernel.org \
--cc=mperttunen@nvidia.com \
--cc=rjw@rjwysocki.net \
--cc=sumitg@nvidia.com \
--cc=talho@nvidia.com \
--cc=thierry.reding@gmail.com \
--cc=will@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).