Linux-ARM-MSM Archive on
 help / color / Atom feed
From: Viresh Kumar <>
To:, Rajendra Nayak <>,,
Subject: Re: [RFC v2 01/11] OPP: Don't overwrite rounded clk rate
Date: Thu, 13 Jun 2019 15:24:19 +0530
Message-ID: <20190613095419.lfjeko7nmxtix2n4@vireshk-i7> (raw)
In-Reply-To: <20190612082506.m735bsk7bjijf2yg@vireshk-i7>

On 12-06-19, 13:55, Viresh Kumar wrote:
> Okay, I have applied this patch (alone) to the OPP tree with minor
> modifications in commit log and diff.

And I have removed it now :)

I am confused as hell on what we should be doing and what we are doing
right now. And if we should do better.

Let me explain with an example.

- The clock provider supports following frequencies: 500, 600, 700,
  800, 900, 1000 MHz.

- The OPP table contains/supports only a subset: 500, 700, 1000 MHz.

Now, the request to change the frequency starts from cpufreq
governors, like schedutil when they calls:

__cpufreq_driver_target(policy, 599 MHz, CPUFREQ_RELATION_L);

CPUFREQ_RELATION_L means: lowest frequency at or above target. And so
I would expect the frequency to get set to 600MHz (if we look at clock
driver) or 700MHz (if we look at OPP table). I think we should decide
this thing from the OPP table only as that's what the platform guys
want us to use. So, we should end up with 700 MHz.

Then we land into dev_pm_opp_set_rate(), which does this (which is
code copied from earlier version of cpufreq-dt driver):

- clk_round_rate(clk, 599 MHz).

  clk_round_rate() returns the highest frequency lower than target. So
  it must return 500 MHz (I haven't tested this yet, all theoretical).

- _find_freq_ceil(opp_table, 500 MHz).

  This works like CPUFREQ_RELATION_L, so we find lowest frequency >=
  target freq. And so we should get: 500 MHz itself as OPP table has

- clk_set_rate(clk, 500 MHz).

  This must be doing round-rate again, but I think we will settle with
  500 MHz eventually.

Now the questionnaire:

- Is this whole exercise correct ?
- We shouldn't have landed on 500 MHz, right ?
- Is there anything wrong with the above theory (I am going to test it soon though).
- Why do we need to do the first clock_round_rate() ? Should we remove
  it ?

Now lets move to this patch, which makes it more confusing.

The OPP tables for CPUs and GPUs should already be somewhat like fmax
tables for particular voltage values and that's why both cpufreq and
OPP core try to find a frequency higher than target so we choose the
most optimum one power-efficiency wise.

For cases where the OPP table is only a subset of the clk-providers
table (almost always), if we let the clock provider to find the
nearest frequency (which is lower) we will run the CPU/GPU at a
not-so-optimal frequency. i.e. if 500, 600, 700 MHz all need voltage
to be 1.2 V, we should be running at 700 always, while we may end up
running at 500 MHz.

This kind of behavior (introduced by this patch) is important for
other devices which want to run at the nearest frequency to target
one, but not for CPUs/GPUs. So, we need to tag these IO devices
separately, maybe from DT ? So we select the closest match instead of
most optimal one.

But lets fix the existing issues first and then think about this


  reply index

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-20  9:49 [RFC v2 00/11] DVFS in the OPP core Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 01/11] OPP: Don't overwrite rounded clk rate Rajendra Nayak
2019-06-11 10:54   ` Viresh Kumar
2019-06-12  7:42     ` Rajendra Nayak
2019-06-12  8:25       ` Viresh Kumar
2019-06-13  9:54         ` Viresh Kumar [this message]
2019-06-14  5:27           ` Viresh Kumar
2019-06-17  3:50             ` Viresh Kumar
2019-06-17  4:07               ` Rajendra Nayak
2019-06-17  4:17                 ` Viresh Kumar
2019-06-17  4:25                   ` Rajendra Nayak
2019-06-14  5:54           ` Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 02/11] OPP: Make dev_pm_opp_set_rate() with freq=0 as valid Rajendra Nayak
2019-06-14  6:32   ` Viresh Kumar
2019-06-17  4:04     ` Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 03/11] tty: serial: qcom_geni_serial: Use OPP API to set clk/perf state Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 04/11] spi: spi-geni-qcom: " Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 05/11] arm64: dts: sdm845: Add OPP table for all qup devices Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 06/11] scsi: ufs: Add support to manage multiple power domains in ufshcd-pltfrm Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 07/11] scsi: ufs: Add support for specifying OPP tables in DT Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 08/11] arm64: dts: sdm845: Add ufs opps and power-domains Rajendra Nayak
2019-05-14  7:53   ` Ulf Hansson
2019-03-20  9:49 ` [RFC v2 09/11] drm/msm/dpu: Use OPP API to set clk/perf state Rajendra Nayak
2019-04-10  3:49   ` Viresh Kumar
2019-04-10  3:49     ` Viresh Kumar
2019-03-20  9:49 ` [RFC v2 10/11] drm/msm: dsi: " Rajendra Nayak
2019-03-20  9:49 ` [RFC v2 11/11] arm64: dts: sdm845: Add DSI and MDP OPP tables and power-domains Rajendra Nayak
2019-04-10  3:51 ` [RFC v2 00/11] DVFS in the OPP core Viresh Kumar
2019-04-10  3:51   ` Viresh Kumar
2019-05-21  6:22 ` Viresh Kumar
2019-05-24  6:03   ` Rajendra Nayak
2019-06-17  4:26 ` Viresh Kumar

Reply instructions:

You may reply publically 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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190613095419.lfjeko7nmxtix2n4@vireshk-i7 \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-ARM-MSM Archive on

Archives are clonable:
	git clone --mirror linux-arm-msm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-arm-msm linux-arm-msm/ \
	public-inbox-index linux-arm-msm

Example config snippet for mirrors

Newsgroup available over NNTP:

AGPL code for this site: git clone