RE: [PATCH] cpufreq, intel_pstate, set max_sysfs_pct and min_sysfs_pct on governor switch

From: Doug Smythies
Date: Wed Oct 07 2015 - 02:59:49 EST

Next message: Jiri Pirko: "Re: [PATCH v2] mlxsw: fix warnings for big-endian 32-bit dma_addr_t"
Previous message: Arnd Bergmann: "[PATCH v2] mlxsw: fix warnings for big-endian 32-bit dma_addr_t"
In reply to: Rafael J. Wysocki: "Re: [PATCH] cpufreq, intel_pstate, set max_sysfs_pct and min_sysfs_pct on governor switch"
Next in thread: Prarit Bhargava: "Re: [PATCH] cpufreq, intel_pstate, set max_sysfs_pct and min_sysfs_pct on governor switch"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

On 2015.09.06 16:48 Rafael J. Wysocki wrote:
> On Wednesday, October 07, 2015 12:43:55 AM Rafael J. Wysocki wrote:
>> On Tuesday, October 06, 2015 05:49:07 PM Prarit Bhargava wrote:
>>> Intel CPUs will not enter higher p-states when after switching from the
>>> performance governor to the powersave governor, until
>>> /sys/devices/system/cpu/intel_pstate/min_perf_pct is set to a low value.

It works properly for me.

Isn't the root issue here an incompatibility between
tools/power/cpupower/utils/cpufreq-set.c and
drivers/cpufreq/intel_pstate.c?
(see experiment results below, where I do not use "cpupower")

I am not familiar with tools/power/cpupower/utils/cpufreq-set.c, but will
look at it more tomorrow.

>>> This differs from previous behaviour in which a switch to the powersave
>>> governor would result in a low default value for min_perf_pct.
>>>
>>> The behavior of the powersave governor changed after commit a04759924e25
>>> ("[cpufreq] intel_pstate: honor user space min_perf_pct override on
>>> resume"). The commit introduced tracking of performance percentage
>>> changes via sysfs in order to restore userspace changes during
>>> suspend/resume. The problem occurs because the global values of the newly
>>> introduced max_sysfs_pct and min_sysfs_pct are not reset on a governor
>>> change and this causes the new governor to inherit the previous governor's
>>> settings.
>>>
>>> This patch sets max_sysfs_pct to 100 and min_sysfs_pct to 0 on a governor
>>> change which fixes the problem with governor switching. These changes
>>> also make the initial calculations for max_perf_pct and min_perf_pct
>>> slightly simpler.
>>>
>>> Before patch:
>>> [root@intel-skylake-y-01 power]# cpupower frequency-set -g performance
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/min_perf_pct
>>> 100
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/max_perf_pct
>>> 100
>>> [root@intel-skylake-y-01 power]# cpupower frequency-set -g powersave
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/min_perf_pct
>>> 100
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/max_perf_pct
>>> 100

And before patch I get, using primitives and not cpupower:
Executive Summary: Everything works fine (or at least as I thought it was supposed to).

root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:powersave
...
/sys/devices/system/cpu/cpu7/cpufreq/scaling_governor:powersave
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100
/sys/devices/system/cpu/intel_pstate/min_perf_pct:42
root@s15:/home/doug/temp# echo 50 > /sys/devices/system/cpu/intel_pstate/min_perf_pct
root@s15:/home/doug/temp# echo 80 > /sys/devices/system/cpu/intel_pstate/max_perf_pct
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:80
/sys/devices/system/cpu/intel_pstate/min_perf_pct:50
root@s15:/home/doug/temp# for file in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor; do echo "performance" > $file; done
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100
/sys/devices/system/cpu/intel_pstate/min_perf_pct:100
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:performance
...
/sys/devices/system/cpu/cpu7/cpufreq/scaling_governor:performance
root@s15:/home/doug/temp# for file in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor; do echo "powersave" > $file; done
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:powersave
...
/sys/devices/system/cpu/cpu7/cpufreq/scaling_governor:powersave
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:80
/sys/devices/system/cpu/intel_pstate/min_perf_pct:50

>>>
>>> After patch:
>>> [root@intel-skylake-y-01 power]# cpupower frequency-set -g performance
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/min_perf_pct
>>> 100
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/max_perf_pct
>>> 100
>>> [root@intel-skylake-y-01 power]# cpupower frequency-set -g powersave
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/min_perf_pct
>>> 14
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/max_perf_pct
>>> 100
>>>

And after the patch I get, using primitives and not cpupower:
Executive Summary: Settings go back to default, and user settings are lost.
This is not how I thought things were supposed to behave, but I'm not actually sure.

root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:powersave
...
/sys/devices/system/cpu/cpu7/cpufreq/scaling_governor:powersave
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100
/sys/devices/system/cpu/intel_pstate/min_perf_pct:42
root@s15:/home/doug/temp# echo 50 > /sys/devices/system/cpu/intel_pstate/min_perf_pct
root@s15:/home/doug/temp# echo 80 > /sys/devices/system/cpu/intel_pstate/max_perf_pct
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:80
/sys/devices/system/cpu/intel_pstate/min_perf_pct:50
root@s15:/home/doug/temp# for file in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor; do echo "performance" > $file; done
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:performance
...
/sys/devices/system/cpu/cpu7/cpufreq/scaling_governor:performance
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100
/sys/devices/system/cpu/intel_pstate/min_perf_pct:100
root@s15:/home/doug/temp# for file in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor; do echo "powersave" > $file; done
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor:powersave
...
/sys/devices/system/cpu/cpu7/cpufreq/scaling_governor:powersave
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100
/sys/devices/system/cpu/intel_pstate/min_perf_pct:42

>>> Also note that I have tested suspend/resume (using CONFIG_PM_DEBUG):
>>> [root@intel-skylake-y-01 power]# echo 50 > /sys/devices/system/cpu/intel_pstate/min_perf_pct
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/*_perf_pct
>>> 100
>>> 50
>>> [root@intel-skylake-y-01 power]# echo devices > /sys/power/pm_test
>>> [root@intel-skylake-y-01 power]# echo platform > /sys/power/disk
>>> [root@intel-skylake-y-01 power]# echo disk > /sys/power/state
>>> [root@intel-skylake-y-01 power]# cat /sys/devices/system/cpu/intel_pstate/*_perf_pct
>>> 100
>>> 50

Before Patch, I get:

root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:80
/sys/devices/system/cpu/intel_pstate/min_perf_pct:50
root@s15:/home/doug/temp# pm-suspend
...
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:80
/sys/devices/system/cpu/intel_pstate/min_perf_pct:50

After Patch, I get:

root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:80
/sys/devices/system/cpu/intel_pstate/min_perf_pct:50
root@s15:/home/doug/temp# pm-suspend
...
root@s15:/home/doug/temp# grep . /sys/devices/system/cpu/intel_pstate/*_perf_*
/sys/devices/system/cpu/intel_pstate/max_perf_pct:100
/sys/devices/system/cpu/intel_pstate/min_perf_pct:42

>>>
>>> Fixes: a04759924e25 ("[cpufreq] intel_pstate: honor user space min_perf_pct override on resume")
>>> Cc: Kristen Carlson Accardi <kristen@xxxxxxxxxxxxxxx>
>>> Cc: "Rafael J. Wysocki" <rjw@xxxxxxxxxxxxx>
>>> Cc: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
>>> Cc: linux-pm@xxxxxxxxxxxxxxx
>>> Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
>>> ---
>>> drivers/cpufreq/intel_pstate.c | 7 +++++--
>>> 1 file changed, 5 insertions(+), 2 deletions(-)
>>>
>>> diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
>>> index 3af9dd7..bb24458 100644
>>> --- a/drivers/cpufreq/intel_pstate.c
>>> +++ b/drivers/cpufreq/intel_pstate.c
>>> @@ -986,6 +986,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
>>> if (!policy->cpuinfo.max_freq)
>>> return -ENODEV;
>>>
>>> + limits.min_sysfs_pct = 0;
>>> + limits.max_sysfs_pct = 100;
>>> +
>>> if (policy->policy == CPUFREQ_POLICY_PERFORMANCE &&
>>> policy->max >= policy->cpuinfo.max_freq) {
>>> limits.min_policy_pct = 100;
>>> @@ -1004,9 +1007,9 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
>>> limits.max_policy_pct = clamp_t(int, limits.max_policy_pct, 0 , 100);
>>>
>>> /* Normalize user input to [min_policy_pct, max_policy_pct] */
>>> - limits.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct);
>>> + limits.min_perf_pct = limits.min_policy_pct;
>>> limits.min_perf_pct = min(limits.max_policy_pct, limits.min_perf_pct);
>>> - limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
>>> + limits.max_perf_pct = limits.max_sysfs_pct;
>
> On a second thought, isn't that always 100? If so, doesn't it basically discard
> limits.max_policy_pct?
>

Yes, I think so, see above.

>>> limits.max_perf_pct = max(limits.min_policy_pct, limits.max_perf_pct);
>>>
>>> /* Make sure min_perf_pct <= max_perf_pct */
>>>

Kernels used: 4.3-rc4 and same plus this patch.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Jiri Pirko: "Re: [PATCH v2] mlxsw: fix warnings for big-endian 32-bit dma_addr_t"
Previous message: Arnd Bergmann: "[PATCH v2] mlxsw: fix warnings for big-endian 32-bit dma_addr_t"
In reply to: Rafael J. Wysocki: "Re: [PATCH] cpufreq, intel_pstate, set max_sysfs_pct and min_sysfs_pct on governor switch"
Next in thread: Prarit Bhargava: "Re: [PATCH] cpufreq, intel_pstate, set max_sysfs_pct and min_sysfs_pct on governor switch"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]