diff mbox series

cpufreq: schedutil: next_freq need update when cpufreq_limits changed

Message ID 20230719130527.8074-1-xuewen.yan@unisoc.com
State Accepted
Commit 9e0bc36ab07c550d791bf17feeb479f1dfc42d89
Headers show
Series cpufreq: schedutil: next_freq need update when cpufreq_limits changed | expand

Commit Message

Xuewen Yan July 19, 2023, 1:05 p.m. UTC
When cpufreq's policy is single, there is a scenario that will
cause sg_policy's next_freq to be unable to update.

When the cpu's util is always max, the cpufreq will be max,
and then if we change the policy's scaling_max_freq to be a
lower freq, indeed, the sg_policy's next_freq need change to
be the lower freq, however, because the cpu_is_busy, the next_freq
would keep the max_freq.

For example:
The cpu7 is single cpu:

unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
[1] 4737
unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
pid 4737's current affinity mask: ff
pid 4737's new affinity mask: 80
unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
2301000
unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
2301000
unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
2171000

At this time, the sg_policy's next_freq would keep 2301000.

To prevent the case happen, add the judgment of the need_freq_update flag.

Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
---
 kernel/sched/cpufreq_schedutil.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Comments

Xuewen Yan July 24, 2023, 3:36 a.m. UTC | #1
On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
>
> On 07/19/23 21:05, Xuewen Yan wrote:
> > When cpufreq's policy is single, there is a scenario that will
> > cause sg_policy's next_freq to be unable to update.
> >
> > When the cpu's util is always max, the cpufreq will be max,
> > and then if we change the policy's scaling_max_freq to be a
> > lower freq, indeed, the sg_policy's next_freq need change to
> > be the lower freq, however, because the cpu_is_busy, the next_freq
> > would keep the max_freq.
> >
> > For example:
> > The cpu7 is single cpu:
> >
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > [1] 4737
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > pid 4737's current affinity mask: ff
> > pid 4737's new affinity mask: 80
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > 2301000
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > 2301000
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > 2171000
> >
> > At this time, the sg_policy's next_freq would keep 2301000.
> >
> > To prevent the case happen, add the judgment of the need_freq_update flag.
> >
> > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > ---
> >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> >  1 file changed, 2 insertions(+), 1 deletion(-)
> >
> > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > index 4492608b7d7f..458d359f5991 100644
> > --- a/kernel/sched/cpufreq_schedutil.c
> > +++ b/kernel/sched/cpufreq_schedutil.c
> > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> >        * Except when the rq is capped by uclamp_max.
> >        */
> >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > +         !sg_policy->need_freq_update) {
>
> What about sugov_update_single_perf()? It seems to have the same problem, no?

There is no problem in sugov_update_single_perf, because the next_freq
is updated by drivers, maybe the next_freq is not used when using
sugov_update_single_perf..

But  for the last_freq_update_time, I think there are some problems
when using sugov_update_single_perf:
Now, there is no judgment condition for the update of the
last_freq_update_time. That means the last_freq_update_time is always
updated in sugov_update_single_perf.
And in sugov_should_update_freq: it would judge the
freq_update_delay_ns. As a result, If we use the
sugov_update_single_perf, the cpu frequency would only be periodically
updated according to freq_update_delay_ns.
Maybe we should judge the cpufreq_driver_adjust_perf's return value,
if the freq is not updated, the last_freq_update_time also does not
have to update.

Just like:
---
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 458d359f5991..10f18b054f01 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
update_util_data *hook, u64 time,
        struct sugov_cpu *sg_cpu = container_of(hook, struct
sugov_cpu, update_util);
        unsigned long prev_util = sg_cpu->util;
        unsigned long max_cap;
+       bool freq_updated;

        /*
         * Fall back to the "frequency" path if frequency invariance is not
@@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
update_util_data *hook, u64 time,
            sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
                sg_cpu->util = prev_util;

-       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
+       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
map_util_perf(sg_cpu->bw_dl),
                                   map_util_perf(sg_cpu->util), max_cap);

-       sg_cpu->sg_policy->last_freq_update_time = time;
+       if (freq_updated)
+               sg_cpu->sg_policy->last_freq_update_time = time;
 }


BR
Thanks!

---
xuewen
>
> LGTM otherwise.
>
>
> Cheers
>
> --
> Qais Yousef
>
> >               next_f = sg_policy->next_freq;
> >
> >               /* Restore cached freq as next_freq has changed */
> > --
> > 2.25.1
> >
Pierre Gondois July 24, 2023, 3:33 p.m. UTC | #2
On 7/24/23 05:36, Xuewen Yan wrote:
> On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
>>
>> On 07/19/23 21:05, Xuewen Yan wrote:
>>> When cpufreq's policy is single, there is a scenario that will
>>> cause sg_policy's next_freq to be unable to update.
>>>
>>> When the cpu's util is always max, the cpufreq will be max,
>>> and then if we change the policy's scaling_max_freq to be a
>>> lower freq, indeed, the sg_policy's next_freq need change to
>>> be the lower freq, however, because the cpu_is_busy, the next_freq
>>> would keep the max_freq.
>>>
>>> For example:
>>> The cpu7 is single cpu:
>>>
>>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
>>> [1] 4737
>>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
>>> pid 4737's current affinity mask: ff
>>> pid 4737's new affinity mask: 80
>>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
>>> 2301000
>>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
>>> 2301000
>>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
>>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
>>> 2171000
>>>
>>> At this time, the sg_policy's next_freq would keep 2301000.
>>>
>>> To prevent the case happen, add the judgment of the need_freq_update flag.
>>>
>>> Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
>>> Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
>>> Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
>>> ---
>>>   kernel/sched/cpufreq_schedutil.c | 3 ++-
>>>   1 file changed, 2 insertions(+), 1 deletion(-)
>>>
>>> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
>>> index 4492608b7d7f..458d359f5991 100644
>>> --- a/kernel/sched/cpufreq_schedutil.c
>>> +++ b/kernel/sched/cpufreq_schedutil.c
>>> @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
>>>         * Except when the rq is capped by uclamp_max.
>>>         */
>>>        if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
>>> -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
>>> +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
>>> +         !sg_policy->need_freq_update) {
>>
>> What about sugov_update_single_perf()? It seems to have the same problem, no?
> 
> There is no problem in sugov_update_single_perf, because the next_freq
> is updated by drivers, maybe the next_freq is not used when using
> sugov_update_single_perf..
> 
> But  for the last_freq_update_time, I think there are some problems
> when using sugov_update_single_perf:
> Now, there is no judgment condition for the update of the
> last_freq_update_time. That means the last_freq_update_time is always
> updated in sugov_update_single_perf.
> And in sugov_should_update_freq: it would judge the
> freq_update_delay_ns. As a result, If we use the
> sugov_update_single_perf, the cpu frequency would only be periodically
> updated according to freq_update_delay_ns.
> Maybe we should judge the cpufreq_driver_adjust_perf's return value,
> if the freq is not updated, the last_freq_update_time also does not
> have to update.
> 
> Just like:
> ---
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index 458d359f5991..10f18b054f01 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
> update_util_data *hook, u64 time,
>          struct sugov_cpu *sg_cpu = container_of(hook, struct
> sugov_cpu, update_util);
>          unsigned long prev_util = sg_cpu->util;
>          unsigned long max_cap;
> +       bool freq_updated;
> 
>          /*
>           * Fall back to the "frequency" path if frequency invariance is not
> @@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
> update_util_data *hook, u64 time,
>              sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
>                  sg_cpu->util = prev_util;
> 
> -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> map_util_perf(sg_cpu->bw_dl),
>                                     map_util_perf(sg_cpu->util), max_cap);
> 
> -       sg_cpu->sg_policy->last_freq_update_time = time;
> +       if (freq_updated)
> +               sg_cpu->sg_policy->last_freq_update_time = time;
>   }
> 

Hello Xuewen,
FWIW, the patch and explanation for sugov_update_single_perf() seem sensible to
me. Just a comment about cpufreq_driver_adjust_perf() and
(struct cpufreq_driver)->adjust_perf(): wouldn't their prototype need to be
updated (i.e. not return void) to do the change suggested above ?

Regards,
Pierre

> 
> BR
> Thanks!
> 
> ---
> xuewen
>>
>> LGTM otherwise.
>>
>>
>> Cheers
>>
>> --
>> Qais Yousef
>>
>>>                next_f = sg_policy->next_freq;
>>>
>>>                /* Restore cached freq as next_freq has changed */
>>> --
>>> 2.25.1
>>>
>
Qais Yousef July 24, 2023, 3:53 p.m. UTC | #3
On 07/24/23 11:36, Xuewen Yan wrote:
> On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
> >
> > On 07/19/23 21:05, Xuewen Yan wrote:
> > > When cpufreq's policy is single, there is a scenario that will
> > > cause sg_policy's next_freq to be unable to update.
> > >
> > > When the cpu's util is always max, the cpufreq will be max,
> > > and then if we change the policy's scaling_max_freq to be a
> > > lower freq, indeed, the sg_policy's next_freq need change to
> > > be the lower freq, however, because the cpu_is_busy, the next_freq
> > > would keep the max_freq.
> > >
> > > For example:
> > > The cpu7 is single cpu:
> > >
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > > [1] 4737
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > > pid 4737's current affinity mask: ff
> > > pid 4737's new affinity mask: 80
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > 2301000
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > > 2301000
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > 2171000
> > >
> > > At this time, the sg_policy's next_freq would keep 2301000.
> > >
> > > To prevent the case happen, add the judgment of the need_freq_update flag.
> > >
> > > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > > ---
> > >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > index 4492608b7d7f..458d359f5991 100644
> > > --- a/kernel/sched/cpufreq_schedutil.c
> > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> > >        * Except when the rq is capped by uclamp_max.
> > >        */
> > >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > > +         !sg_policy->need_freq_update) {
> >
> > What about sugov_update_single_perf()? It seems to have the same problem, no?
> 
> There is no problem in sugov_update_single_perf, because the next_freq
> is updated by drivers, maybe the next_freq is not used when using
> sugov_update_single_perf..

Ah I see; we just use prev_util but the request will go through and the driver
should observe the new limit regardless of what util value we pass to it. Got
ya.

> 
> But  for the last_freq_update_time, I think there are some problems
> when using sugov_update_single_perf:
> Now, there is no judgment condition for the update of the
> last_freq_update_time. That means the last_freq_update_time is always
> updated in sugov_update_single_perf.
> And in sugov_should_update_freq: it would judge the
> freq_update_delay_ns. As a result, If we use the
> sugov_update_single_perf, the cpu frequency would only be periodically
> updated according to freq_update_delay_ns.
> Maybe we should judge the cpufreq_driver_adjust_perf's return value,
> if the freq is not updated, the last_freq_update_time also does not
> have to update.
> 
> Just like:
> ---
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index 458d359f5991..10f18b054f01 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
> update_util_data *hook, u64 time,
>         struct sugov_cpu *sg_cpu = container_of(hook, struct
> sugov_cpu, update_util);
>         unsigned long prev_util = sg_cpu->util;
>         unsigned long max_cap;
> +       bool freq_updated;
> 
>         /*
>          * Fall back to the "frequency" path if frequency invariance is not
> @@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
> update_util_data *hook, u64 time,
>             sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
>                 sg_cpu->util = prev_util;
> 
> -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> map_util_perf(sg_cpu->bw_dl),
>                                    map_util_perf(sg_cpu->util), max_cap);
> 
> -       sg_cpu->sg_policy->last_freq_update_time = time;
> +       if (freq_updated)
> +               sg_cpu->sg_policy->last_freq_update_time = time;
>  }

Sound reasonable in principle, but it could lead to overhead; for example when
the system is busy and maxed out, the last_freq_update_time will never be
updated and will end up continuously calling to the driver to change frequency
without any rate limit AFAICS. Which might not be an acceptable overhead,
I don't know. Logically this is wasted cycles preventing the tasks from doing
useful work. I think we need to look at such corner cases and treat them
appropriately to not call the driver if we go with this approach.


Cheers

--
Qais Yousef

> 
> 
> BR
> Thanks!
> 
> ---
> xuewen
> >
> > LGTM otherwise.
> >
> >
> > Cheers
> >
> > --
> > Qais Yousef
> >
> > >               next_f = sg_policy->next_freq;
> > >
> > >               /* Restore cached freq as next_freq has changed */
> > > --
> > > 2.25.1
> > >
Xuewen Yan July 25, 2023, 2:01 a.m. UTC | #4
Hi Pierre,

On Mon, Jul 24, 2023 at 11:33 PM Pierre Gondois <pierre.gondois@arm.com> wrote:
>
>
>
> On 7/24/23 05:36, Xuewen Yan wrote:
> > On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
> >>
> >> On 07/19/23 21:05, Xuewen Yan wrote:
> >>> When cpufreq's policy is single, there is a scenario that will
> >>> cause sg_policy's next_freq to be unable to update.
> >>>
> >>> When the cpu's util is always max, the cpufreq will be max,
> >>> and then if we change the policy's scaling_max_freq to be a
> >>> lower freq, indeed, the sg_policy's next_freq need change to
> >>> be the lower freq, however, because the cpu_is_busy, the next_freq
> >>> would keep the max_freq.
> >>>
> >>> For example:
> >>> The cpu7 is single cpu:
> >>>
> >>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> >>> [1] 4737
> >>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> >>> pid 4737's current affinity mask: ff
> >>> pid 4737's new affinity mask: 80
> >>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> >>> 2301000
> >>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> >>> 2301000
> >>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> >>> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> >>> 2171000
> >>>
> >>> At this time, the sg_policy's next_freq would keep 2301000.
> >>>
> >>> To prevent the case happen, add the judgment of the need_freq_update flag.
> >>>
> >>> Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> >>> Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> >>> Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> >>> ---
> >>>   kernel/sched/cpufreq_schedutil.c | 3 ++-
> >>>   1 file changed, 2 insertions(+), 1 deletion(-)
> >>>
> >>> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> >>> index 4492608b7d7f..458d359f5991 100644
> >>> --- a/kernel/sched/cpufreq_schedutil.c
> >>> +++ b/kernel/sched/cpufreq_schedutil.c
> >>> @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> >>>         * Except when the rq is capped by uclamp_max.
> >>>         */
> >>>        if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> >>> -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> >>> +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> >>> +         !sg_policy->need_freq_update) {
> >>
> >> What about sugov_update_single_perf()? It seems to have the same problem, no?
> >
> > There is no problem in sugov_update_single_perf, because the next_freq
> > is updated by drivers, maybe the next_freq is not used when using
> > sugov_update_single_perf..
> >
> > But  for the last_freq_update_time, I think there are some problems
> > when using sugov_update_single_perf:
> > Now, there is no judgment condition for the update of the
> > last_freq_update_time. That means the last_freq_update_time is always
> > updated in sugov_update_single_perf.
> > And in sugov_should_update_freq: it would judge the
> > freq_update_delay_ns. As a result, If we use the
> > sugov_update_single_perf, the cpu frequency would only be periodically
> > updated according to freq_update_delay_ns.
> > Maybe we should judge the cpufreq_driver_adjust_perf's return value,
> > if the freq is not updated, the last_freq_update_time also does not
> > have to update.
> >
> > Just like:
> > ---
> > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > index 458d359f5991..10f18b054f01 100644
> > --- a/kernel/sched/cpufreq_schedutil.c
> > +++ b/kernel/sched/cpufreq_schedutil.c
> > @@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
> > update_util_data *hook, u64 time,
> >          struct sugov_cpu *sg_cpu = container_of(hook, struct
> > sugov_cpu, update_util);
> >          unsigned long prev_util = sg_cpu->util;
> >          unsigned long max_cap;
> > +       bool freq_updated;
> >
> >          /*
> >           * Fall back to the "frequency" path if frequency invariance is not
> > @@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
> > update_util_data *hook, u64 time,
> >              sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
> >                  sg_cpu->util = prev_util;
> >
> > -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> > +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> > map_util_perf(sg_cpu->bw_dl),
> >                                     map_util_perf(sg_cpu->util), max_cap);
> >
> > -       sg_cpu->sg_policy->last_freq_update_time = time;
> > +       if (freq_updated)
> > +               sg_cpu->sg_policy->last_freq_update_time = time;
> >   }
> >
>
> Hello Xuewen,
> FWIW, the patch and explanation for sugov_update_single_perf() seem sensible to
> me. Just a comment about cpufreq_driver_adjust_perf() and
> (struct cpufreq_driver)->adjust_perf(): wouldn't their prototype need to be
> updated (i.e. not return void) to do the change suggested above ?

Yes, their function type should be changed from void to bool or init.
For this patch, I just raise a question for everyone to discuss. If
this is a problem, the official patch needs to be revised later.

BR
xuewen

>
> Regards,
> Pierre
>
> >
> > BR
> > Thanks!
> >
> > ---
> > xuewen
> >>
> >> LGTM otherwise.
> >>
> >>
> >> Cheers
> >>
> >> --
> >> Qais Yousef
> >>
> >>>                next_f = sg_policy->next_freq;
> >>>
> >>>                /* Restore cached freq as next_freq has changed */
> >>> --
> >>> 2.25.1
> >>>
> >
Xuewen Yan July 25, 2023, 2:21 a.m. UTC | #5
On Mon, Jul 24, 2023 at 11:53 PM Qais Yousef <qyousef@layalina.io> wrote:
>
> On 07/24/23 11:36, Xuewen Yan wrote:
> > On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
> > >
> > > On 07/19/23 21:05, Xuewen Yan wrote:
> > > > When cpufreq's policy is single, there is a scenario that will
> > > > cause sg_policy's next_freq to be unable to update.
> > > >
> > > > When the cpu's util is always max, the cpufreq will be max,
> > > > and then if we change the policy's scaling_max_freq to be a
> > > > lower freq, indeed, the sg_policy's next_freq need change to
> > > > be the lower freq, however, because the cpu_is_busy, the next_freq
> > > > would keep the max_freq.
> > > >
> > > > For example:
> > > > The cpu7 is single cpu:
> > > >
> > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > > > [1] 4737
> > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > > > pid 4737's current affinity mask: ff
> > > > pid 4737's new affinity mask: 80
> > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > 2301000
> > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > > > 2301000
> > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > 2171000
> > > >
> > > > At this time, the sg_policy's next_freq would keep 2301000.
> > > >
> > > > To prevent the case happen, add the judgment of the need_freq_update flag.
> > > >
> > > > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > > > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > ---
> > > >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> > > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > > >
> > > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > > index 4492608b7d7f..458d359f5991 100644
> > > > --- a/kernel/sched/cpufreq_schedutil.c
> > > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> > > >        * Except when the rq is capped by uclamp_max.
> > > >        */
> > > >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > > > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > > > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > > > +         !sg_policy->need_freq_update) {
> > >
> > > What about sugov_update_single_perf()? It seems to have the same problem, no?
> >
> > There is no problem in sugov_update_single_perf, because the next_freq
> > is updated by drivers, maybe the next_freq is not used when using
> > sugov_update_single_perf..
>
> Ah I see; we just use prev_util but the request will go through and the driver
> should observe the new limit regardless of what util value we pass to it. Got
> ya.
>
> >
> > But  for the last_freq_update_time, I think there are some problems
> > when using sugov_update_single_perf:
> > Now, there is no judgment condition for the update of the
> > last_freq_update_time. That means the last_freq_update_time is always
> > updated in sugov_update_single_perf.
> > And in sugov_should_update_freq: it would judge the
> > freq_update_delay_ns. As a result, If we use the
> > sugov_update_single_perf, the cpu frequency would only be periodically
> > updated according to freq_update_delay_ns.
> > Maybe we should judge the cpufreq_driver_adjust_perf's return value,
> > if the freq is not updated, the last_freq_update_time also does not
> > have to update.
> >
> > Just like:
> > ---
> > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > index 458d359f5991..10f18b054f01 100644
> > --- a/kernel/sched/cpufreq_schedutil.c
> > +++ b/kernel/sched/cpufreq_schedutil.c
> > @@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
> > update_util_data *hook, u64 time,
> >         struct sugov_cpu *sg_cpu = container_of(hook, struct
> > sugov_cpu, update_util);
> >         unsigned long prev_util = sg_cpu->util;
> >         unsigned long max_cap;
> > +       bool freq_updated;
> >
> >         /*
> >          * Fall back to the "frequency" path if frequency invariance is not
> > @@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
> > update_util_data *hook, u64 time,
> >             sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
> >                 sg_cpu->util = prev_util;
> >
> > -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> > +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> > map_util_perf(sg_cpu->bw_dl),
> >                                    map_util_perf(sg_cpu->util), max_cap);
> >
> > -       sg_cpu->sg_policy->last_freq_update_time = time;
> > +       if (freq_updated)
> > +               sg_cpu->sg_policy->last_freq_update_time = time;
> >  }
>
> Sound reasonable in principle, but it could lead to overhead; for example when
> the system is busy and maxed out, the last_freq_update_time will never be
> updated and will end up continuously calling to the driver to change frequency
> without any rate limit AFAICS. Which might not be an acceptable overhead,
> I don't know. Logically this is wasted cycles preventing the tasks from doing
> useful work. I think we need to look at such corner cases and treat them
> appropriately to not call the driver if we go with this approach.

Hi Qais,

I can understand what you mean, but I don't think this is a problem.
For the driver, the calculation of whether to update the frequency may
not be the main time-consuming, but the main time-consuming may be the
frequency conversion time of the hardware. If the hardware does not
need frequency conversion, the operation of calculating the frequency
takes a very short time.
If the operation of calling the driver frequently is unacceptable, can
prev_util be used?

---
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4492608b7d7f..3febfd032eee 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -379,7 +379,9 @@ static void sugov_update_single_perf(struct
update_util_data *hook, u64 time,
 {
        struct sugov_cpu *sg_cpu = container_of(hook, struct
sugov_cpu, update_util);
        unsigned long prev_util = sg_cpu->util;
+       unsigned long prev_bw_dl = sg_cpu->bw_dl;
        unsigned long max_cap;
+       bool freq_updated;

        /*
         * Fall back to the "frequency" path if frequency invariance is not
@@ -406,10 +408,14 @@ static void sugov_update_single_perf(struct
update_util_data *hook, u64 time,
            sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
                sg_cpu->util = prev_util;

-       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
+       if (prev_util == sg_cpu->util && prev_bw_dl == sg_cpu->bw_dl)
+               return;
+
+       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
map_util_perf(sg_cpu->bw_dl),
                                   map_util_perf(sg_cpu->util), max_cap);

-       sg_cpu->sg_policy->last_freq_update_time = time;
+       if (freq_updated)
+               sg_cpu->sg_policy->last_freq_update_time = time;
 }

 static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)


BR
---
xuewen
>
>
> Cheers
>
> --
> Qais Yousef
>
> >
> >
> > BR
> > Thanks!
> >
> > ---
> > xuewen
> > >
> > > LGTM otherwise.
> > >
> > >
> > > Cheers
> > >
> > > --
> > > Qais Yousef
> > >
> > > >               next_f = sg_policy->next_freq;
> > > >
> > > >               /* Restore cached freq as next_freq has changed */
> > > > --
> > > > 2.25.1
> > > >
Rafael J. Wysocki July 25, 2023, 8:50 a.m. UTC | #6
On Tue, Jul 25, 2023 at 4:21 AM Xuewen Yan <xuewen.yan94@gmail.com> wrote:
>
> On Mon, Jul 24, 2023 at 11:53 PM Qais Yousef <qyousef@layalina.io> wrote:
> >
> > On 07/24/23 11:36, Xuewen Yan wrote:
> > > On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
> > > >
> > > > On 07/19/23 21:05, Xuewen Yan wrote:
> > > > > When cpufreq's policy is single, there is a scenario that will
> > > > > cause sg_policy's next_freq to be unable to update.
> > > > >
> > > > > When the cpu's util is always max, the cpufreq will be max,
> > > > > and then if we change the policy's scaling_max_freq to be a
> > > > > lower freq, indeed, the sg_policy's next_freq need change to
> > > > > be the lower freq, however, because the cpu_is_busy, the next_freq
> > > > > would keep the max_freq.
> > > > >
> > > > > For example:
> > > > > The cpu7 is single cpu:
> > > > >
> > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > > > > [1] 4737
> > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > > > > pid 4737's current affinity mask: ff
> > > > > pid 4737's new affinity mask: 80
> > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > > 2301000
> > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > > > > 2301000
> > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > > 2171000
> > > > >
> > > > > At this time, the sg_policy's next_freq would keep 2301000.
> > > > >
> > > > > To prevent the case happen, add the judgment of the need_freq_update flag.
> > > > >
> > > > > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > > > > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > > ---
> > > > >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> > > > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > > > >
> > > > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > > > index 4492608b7d7f..458d359f5991 100644
> > > > > --- a/kernel/sched/cpufreq_schedutil.c
> > > > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > > > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> > > > >        * Except when the rq is capped by uclamp_max.
> > > > >        */
> > > > >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > > > > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > > > > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > > > > +         !sg_policy->need_freq_update) {
> > > >
> > > > What about sugov_update_single_perf()? It seems to have the same problem, no?
> > >
> > > There is no problem in sugov_update_single_perf, because the next_freq
> > > is updated by drivers, maybe the next_freq is not used when using
> > > sugov_update_single_perf..
> >
> > Ah I see; we just use prev_util but the request will go through and the driver
> > should observe the new limit regardless of what util value we pass to it. Got
> > ya.
> >
> > >
> > > But  for the last_freq_update_time, I think there are some problems
> > > when using sugov_update_single_perf:
> > > Now, there is no judgment condition for the update of the
> > > last_freq_update_time. That means the last_freq_update_time is always
> > > updated in sugov_update_single_perf.
> > > And in sugov_should_update_freq: it would judge the
> > > freq_update_delay_ns. As a result, If we use the
> > > sugov_update_single_perf, the cpu frequency would only be periodically
> > > updated according to freq_update_delay_ns.
> > > Maybe we should judge the cpufreq_driver_adjust_perf's return value,
> > > if the freq is not updated, the last_freq_update_time also does not
> > > have to update.
> > >
> > > Just like:
> > > ---
> > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > index 458d359f5991..10f18b054f01 100644
> > > --- a/kernel/sched/cpufreq_schedutil.c
> > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > @@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
> > > update_util_data *hook, u64 time,
> > >         struct sugov_cpu *sg_cpu = container_of(hook, struct
> > > sugov_cpu, update_util);
> > >         unsigned long prev_util = sg_cpu->util;
> > >         unsigned long max_cap;
> > > +       bool freq_updated;
> > >
> > >         /*
> > >          * Fall back to the "frequency" path if frequency invariance is not
> > > @@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
> > > update_util_data *hook, u64 time,
> > >             sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
> > >                 sg_cpu->util = prev_util;
> > >
> > > -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> > > +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> > > map_util_perf(sg_cpu->bw_dl),
> > >                                    map_util_perf(sg_cpu->util), max_cap);
> > >
> > > -       sg_cpu->sg_policy->last_freq_update_time = time;
> > > +       if (freq_updated)
> > > +               sg_cpu->sg_policy->last_freq_update_time = time;
> > >  }
> >
> > Sound reasonable in principle, but it could lead to overhead; for example when
> > the system is busy and maxed out, the last_freq_update_time will never be
> > updated and will end up continuously calling to the driver to change frequency
> > without any rate limit AFAICS. Which might not be an acceptable overhead,
> > I don't know. Logically this is wasted cycles preventing the tasks from doing
> > useful work. I think we need to look at such corner cases and treat them
> > appropriately to not call the driver if we go with this approach.
>
> Hi Qais,
>
> I can understand what you mean, but I don't think this is a problem.
> For the driver, the calculation of whether to update the frequency may
> not be the main time-consuming, but the main time-consuming may be the
> frequency conversion time of the hardware. If the hardware does not
> need frequency conversion, the operation of calculating the frequency
> takes a very short time.
> If the operation of calling the driver frequently is unacceptable, can
> prev_util be used?

No, it's better to pass the data to the driver directly and let it
sort that out in this particular case.

> ---
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index 4492608b7d7f..3febfd032eee 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -379,7 +379,9 @@ static void sugov_update_single_perf(struct
> update_util_data *hook, u64 time,
>  {
>         struct sugov_cpu *sg_cpu = container_of(hook, struct
> sugov_cpu, update_util);
>         unsigned long prev_util = sg_cpu->util;
> +       unsigned long prev_bw_dl = sg_cpu->bw_dl;
>         unsigned long max_cap;
> +       bool freq_updated;
>
>         /*
>          * Fall back to the "frequency" path if frequency invariance is not
> @@ -406,10 +408,14 @@ static void sugov_update_single_perf(struct
> update_util_data *hook, u64 time,
>             sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
>                 sg_cpu->util = prev_util;
>
> -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> +       if (prev_util == sg_cpu->util && prev_bw_dl == sg_cpu->bw_dl)
> +               return;
> +
> +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> map_util_perf(sg_cpu->bw_dl),
>                                    map_util_perf(sg_cpu->util), max_cap);
>
> -       sg_cpu->sg_policy->last_freq_update_time = time;
> +       if (freq_updated)
> +               sg_cpu->sg_policy->last_freq_update_time = time;
>  }
>
>  static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
>
>
> BR
> ---
> xuewen
> >
> >
> > Cheers
> >
> > --
> > Qais Yousef
> >
> > >
> > >
> > > BR
> > > Thanks!
> > >
> > > ---
> > > xuewen
> > > >
> > > > LGTM otherwise.
> > > >
> > > >
> > > > Cheers
> > > >
> > > > --
> > > > Qais Yousef
> > > >
> > > > >               next_f = sg_policy->next_freq;
> > > > >
> > > > >               /* Restore cached freq as next_freq has changed */
> > > > > --
> > > > > 2.25.1
> > > > >
Xuewen Yan July 25, 2023, 12:08 p.m. UTC | #7
Hi Rafael

On Tue, Jul 25, 2023 at 4:51 PM Rafael J. Wysocki <rafael@kernel.org> wrote:
>
> On Tue, Jul 25, 2023 at 4:21 AM Xuewen Yan <xuewen.yan94@gmail.com> wrote:
> >
> > On Mon, Jul 24, 2023 at 11:53 PM Qais Yousef <qyousef@layalina.io> wrote:
> > >
> > > On 07/24/23 11:36, Xuewen Yan wrote:
> > > > On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
> > > > >
> > > > > On 07/19/23 21:05, Xuewen Yan wrote:
> > > > > > When cpufreq's policy is single, there is a scenario that will
> > > > > > cause sg_policy's next_freq to be unable to update.
> > > > > >
> > > > > > When the cpu's util is always max, the cpufreq will be max,
> > > > > > and then if we change the policy's scaling_max_freq to be a
> > > > > > lower freq, indeed, the sg_policy's next_freq need change to
> > > > > > be the lower freq, however, because the cpu_is_busy, the next_freq
> > > > > > would keep the max_freq.
> > > > > >
> > > > > > For example:
> > > > > > The cpu7 is single cpu:
> > > > > >
> > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > > > > > [1] 4737
> > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > > > > > pid 4737's current affinity mask: ff
> > > > > > pid 4737's new affinity mask: 80
> > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > > > 2301000
> > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > > > > > 2301000
> > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > > > 2171000
> > > > > >
> > > > > > At this time, the sg_policy's next_freq would keep 2301000.
> > > > > >
> > > > > > To prevent the case happen, add the judgment of the need_freq_update flag.
> > > > > >
> > > > > > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > > > > > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > > > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > > > ---
> > > > > >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> > > > > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > > > > >
> > > > > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > > > > index 4492608b7d7f..458d359f5991 100644
> > > > > > --- a/kernel/sched/cpufreq_schedutil.c
> > > > > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > > > > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> > > > > >        * Except when the rq is capped by uclamp_max.
> > > > > >        */
> > > > > >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > > > > > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > > > > > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > > > > > +         !sg_policy->need_freq_update) {
> > > > >
> > > > > What about sugov_update_single_perf()? It seems to have the same problem, no?
> > > >
> > > > There is no problem in sugov_update_single_perf, because the next_freq
> > > > is updated by drivers, maybe the next_freq is not used when using
> > > > sugov_update_single_perf..
> > >
> > > Ah I see; we just use prev_util but the request will go through and the driver
> > > should observe the new limit regardless of what util value we pass to it. Got
> > > ya.
> > >
> > > >
> > > > But  for the last_freq_update_time, I think there are some problems
> > > > when using sugov_update_single_perf:
> > > > Now, there is no judgment condition for the update of the
> > > > last_freq_update_time. That means the last_freq_update_time is always
> > > > updated in sugov_update_single_perf.
> > > > And in sugov_should_update_freq: it would judge the
> > > > freq_update_delay_ns. As a result, If we use the
> > > > sugov_update_single_perf, the cpu frequency would only be periodically
> > > > updated according to freq_update_delay_ns.
> > > > Maybe we should judge the cpufreq_driver_adjust_perf's return value,
> > > > if the freq is not updated, the last_freq_update_time also does not
> > > > have to update.
> > > >
> > > > Just like:
> > > > ---
> > > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > > index 458d359f5991..10f18b054f01 100644
> > > > --- a/kernel/sched/cpufreq_schedutil.c
> > > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > > @@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
> > > > update_util_data *hook, u64 time,
> > > >         struct sugov_cpu *sg_cpu = container_of(hook, struct
> > > > sugov_cpu, update_util);
> > > >         unsigned long prev_util = sg_cpu->util;
> > > >         unsigned long max_cap;
> > > > +       bool freq_updated;
> > > >
> > > >         /*
> > > >          * Fall back to the "frequency" path if frequency invariance is not
> > > > @@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
> > > > update_util_data *hook, u64 time,
> > > >             sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
> > > >                 sg_cpu->util = prev_util;
> > > >
> > > > -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> > > > +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> > > > map_util_perf(sg_cpu->bw_dl),
> > > >                                    map_util_perf(sg_cpu->util), max_cap);
> > > >
> > > > -       sg_cpu->sg_policy->last_freq_update_time = time;
> > > > +       if (freq_updated)
> > > > +               sg_cpu->sg_policy->last_freq_update_time = time;
> > > >  }
> > >
> > > Sound reasonable in principle, but it could lead to overhead; for example when
> > > the system is busy and maxed out, the last_freq_update_time will never be
> > > updated and will end up continuously calling to the driver to change frequency
> > > without any rate limit AFAICS. Which might not be an acceptable overhead,
> > > I don't know. Logically this is wasted cycles preventing the tasks from doing
> > > useful work. I think we need to look at such corner cases and treat them
> > > appropriately to not call the driver if we go with this approach.
> >
> > Hi Qais,
> >
> > I can understand what you mean, but I don't think this is a problem.
> > For the driver, the calculation of whether to update the frequency may
> > not be the main time-consuming, but the main time-consuming may be the
> > frequency conversion time of the hardware. If the hardware does not
> > need frequency conversion, the operation of calculating the frequency
> > takes a very short time.
> > If the operation of calling the driver frequently is unacceptable, can
> > prev_util be used?
>
> No, it's better to pass the data to the driver directly and let it
> sort that out in this particular case.

Yes, I know. we should not interfere with the driver's behavior.

By the way, What do you think of the patch fixing the sugov_update_single_freq?

Thanks!

---
xuewen

>
> > ---
> > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > index 4492608b7d7f..3febfd032eee 100644
> > --- a/kernel/sched/cpufreq_schedutil.c
> > +++ b/kernel/sched/cpufreq_schedutil.c
> > @@ -379,7 +379,9 @@ static void sugov_update_single_perf(struct
> > update_util_data *hook, u64 time,
> >  {
> >         struct sugov_cpu *sg_cpu = container_of(hook, struct
> > sugov_cpu, update_util);
> >         unsigned long prev_util = sg_cpu->util;
> > +       unsigned long prev_bw_dl = sg_cpu->bw_dl;
> >         unsigned long max_cap;
> > +       bool freq_updated;
> >
> >         /*
> >          * Fall back to the "frequency" path if frequency invariance is not
> > @@ -406,10 +408,14 @@ static void sugov_update_single_perf(struct
> > update_util_data *hook, u64 time,
> >             sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
> >                 sg_cpu->util = prev_util;
> >
> > -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> > +       if (prev_util == sg_cpu->util && prev_bw_dl == sg_cpu->bw_dl)
> > +               return;
> > +
> > +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> > map_util_perf(sg_cpu->bw_dl),
> >                                    map_util_perf(sg_cpu->util), max_cap);
> >
> > -       sg_cpu->sg_policy->last_freq_update_time = time;
> > +       if (freq_updated)
> > +               sg_cpu->sg_policy->last_freq_update_time = time;
> >  }
> >
> >  static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
> >
> >
> > BR
> > ---
> > xuewen
> > >
> > >
> > > Cheers
> > >
> > > --
> > > Qais Yousef
> > >
> > > >
> > > >
> > > > BR
> > > > Thanks!
> > > >
> > > > ---
> > > > xuewen
> > > > >
> > > > > LGTM otherwise.
> > > > >
> > > > >
> > > > > Cheers
> > > > >
> > > > > --
> > > > > Qais Yousef
> > > > >
> > > > > >               next_f = sg_policy->next_freq;
> > > > > >
> > > > > >               /* Restore cached freq as next_freq has changed */
> > > > > > --
> > > > > > 2.25.1
> > > > > >
Rafael J. Wysocki Aug. 22, 2023, 7:28 p.m. UTC | #8
On Tue, Jul 25, 2023 at 2:09 PM Xuewen Yan <xuewen.yan94@gmail.com> wrote:
>
> Hi Rafael
>
> On Tue, Jul 25, 2023 at 4:51 PM Rafael J. Wysocki <rafael@kernel.org> wrote:
> >
> > On Tue, Jul 25, 2023 at 4:21 AM Xuewen Yan <xuewen.yan94@gmail.com> wrote:
> > >
> > > On Mon, Jul 24, 2023 at 11:53 PM Qais Yousef <qyousef@layalina.io> wrote:
> > > >
> > > > On 07/24/23 11:36, Xuewen Yan wrote:
> > > > > On Sat, Jul 22, 2023 at 7:02 AM Qais Yousef <qyousef@layalina.io> wrote:
> > > > > >
> > > > > > On 07/19/23 21:05, Xuewen Yan wrote:
> > > > > > > When cpufreq's policy is single, there is a scenario that will
> > > > > > > cause sg_policy's next_freq to be unable to update.
> > > > > > >
> > > > > > > When the cpu's util is always max, the cpufreq will be max,
> > > > > > > and then if we change the policy's scaling_max_freq to be a
> > > > > > > lower freq, indeed, the sg_policy's next_freq need change to
> > > > > > > be the lower freq, however, because the cpu_is_busy, the next_freq
> > > > > > > would keep the max_freq.
> > > > > > >
> > > > > > > For example:
> > > > > > > The cpu7 is single cpu:
> > > > > > >
> > > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > > > > > > [1] 4737
> > > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > > > > > > pid 4737's current affinity mask: ff
> > > > > > > pid 4737's new affinity mask: 80
> > > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > > > > 2301000
> > > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > > > > > > 2301000
> > > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > > > > > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > > > > > 2171000
> > > > > > >
> > > > > > > At this time, the sg_policy's next_freq would keep 2301000.
> > > > > > >
> > > > > > > To prevent the case happen, add the judgment of the need_freq_update flag.
> > > > > > >
> > > > > > > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > > > > > > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > > > > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > > > > > > ---
> > > > > > >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> > > > > > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > > > > > >
> > > > > > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > > > > > index 4492608b7d7f..458d359f5991 100644
> > > > > > > --- a/kernel/sched/cpufreq_schedutil.c
> > > > > > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > > > > > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> > > > > > >        * Except when the rq is capped by uclamp_max.
> > > > > > >        */
> > > > > > >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > > > > > > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > > > > > > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > > > > > > +         !sg_policy->need_freq_update) {
> > > > > >
> > > > > > What about sugov_update_single_perf()? It seems to have the same problem, no?
> > > > >
> > > > > There is no problem in sugov_update_single_perf, because the next_freq
> > > > > is updated by drivers, maybe the next_freq is not used when using
> > > > > sugov_update_single_perf..
> > > >
> > > > Ah I see; we just use prev_util but the request will go through and the driver
> > > > should observe the new limit regardless of what util value we pass to it. Got
> > > > ya.
> > > >
> > > > >
> > > > > But  for the last_freq_update_time, I think there are some problems
> > > > > when using sugov_update_single_perf:
> > > > > Now, there is no judgment condition for the update of the
> > > > > last_freq_update_time. That means the last_freq_update_time is always
> > > > > updated in sugov_update_single_perf.
> > > > > And in sugov_should_update_freq: it would judge the
> > > > > freq_update_delay_ns. As a result, If we use the
> > > > > sugov_update_single_perf, the cpu frequency would only be periodically
> > > > > updated according to freq_update_delay_ns.
> > > > > Maybe we should judge the cpufreq_driver_adjust_perf's return value,
> > > > > if the freq is not updated, the last_freq_update_time also does not
> > > > > have to update.
> > > > >
> > > > > Just like:
> > > > > ---
> > > > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > > > index 458d359f5991..10f18b054f01 100644
> > > > > --- a/kernel/sched/cpufreq_schedutil.c
> > > > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > > > @@ -381,6 +381,7 @@ static void sugov_update_single_perf(struct
> > > > > update_util_data *hook, u64 time,
> > > > >         struct sugov_cpu *sg_cpu = container_of(hook, struct
> > > > > sugov_cpu, update_util);
> > > > >         unsigned long prev_util = sg_cpu->util;
> > > > >         unsigned long max_cap;
> > > > > +       bool freq_updated;
> > > > >
> > > > >         /*
> > > > >          * Fall back to the "frequency" path if frequency invariance is not
> > > > > @@ -407,10 +408,11 @@ static void sugov_update_single_perf(struct
> > > > > update_util_data *hook, u64 time,
> > > > >             sugov_cpu_is_busy(sg_cpu) && sg_cpu->util < prev_util)
> > > > >                 sg_cpu->util = prev_util;
> > > > >
> > > > > -       cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
> > > > > +       freq_updated = cpufreq_driver_adjust_perf(sg_cpu->cpu,
> > > > > map_util_perf(sg_cpu->bw_dl),
> > > > >                                    map_util_perf(sg_cpu->util), max_cap);
> > > > >
> > > > > -       sg_cpu->sg_policy->last_freq_update_time = time;
> > > > > +       if (freq_updated)
> > > > > +               sg_cpu->sg_policy->last_freq_update_time = time;
> > > > >  }
> > > >
> > > > Sound reasonable in principle, but it could lead to overhead; for example when
> > > > the system is busy and maxed out, the last_freq_update_time will never be
> > > > updated and will end up continuously calling to the driver to change frequency
> > > > without any rate limit AFAICS. Which might not be an acceptable overhead,
> > > > I don't know. Logically this is wasted cycles preventing the tasks from doing
> > > > useful work. I think we need to look at such corner cases and treat them
> > > > appropriately to not call the driver if we go with this approach.
> > >
> > > Hi Qais,
> > >
> > > I can understand what you mean, but I don't think this is a problem.
> > > For the driver, the calculation of whether to update the frequency may
> > > not be the main time-consuming, but the main time-consuming may be the
> > > frequency conversion time of the hardware. If the hardware does not
> > > need frequency conversion, the operation of calculating the frequency
> > > takes a very short time.
> > > If the operation of calling the driver frequently is unacceptable, can
> > > prev_util be used?
> >
> > No, it's better to pass the data to the driver directly and let it
> > sort that out in this particular case.
>
> Yes, I know. we should not interfere with the driver's behavior.
>
> By the way, What do you think of the patch fixing the sugov_update_single_freq?

IIUC, you have found a genuine issue and the patch should address it.
Ingo Molnar Oct. 5, 2023, 11:26 a.m. UTC | #9
* Xuewen Yan <xuewen.yan@unisoc.com> wrote:

> When cpufreq's policy is single, there is a scenario that will
> cause sg_policy's next_freq to be unable to update.
> 
> When the cpu's util is always max, the cpufreq will be max,
> and then if we change the policy's scaling_max_freq to be a
> lower freq, indeed, the sg_policy's next_freq need change to
> be the lower freq, however, because the cpu_is_busy, the next_freq
> would keep the max_freq.
> 
> For example:
> The cpu7 is single cpu:
> 
> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> [1] 4737
> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> pid 4737's current affinity mask: ff
> pid 4737's new affinity mask: 80
> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> 2301000
> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> 2301000
> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> 2171000
> 
> At this time, the sg_policy's next_freq would keep 2301000.
> 
> To prevent the case happen, add the judgment of the need_freq_update flag.
> 
> Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> ---
>  kernel/sched/cpufreq_schedutil.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> index 4492608b7d7f..458d359f5991 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
>  	 * Except when the rq is capped by uclamp_max.
>  	 */
>  	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> -	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> +	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> +	    !sg_policy->need_freq_update) {
>  		next_f = sg_policy->next_freq;
>  
>  		/* Restore cached freq as next_freq has changed */

Just wondering about the status of this fix - is it pending in
some tree, or should we apply it to the scheduler tree?

Thanks,

	Ingo
Rafael J. Wysocki Oct. 5, 2023, 11:35 a.m. UTC | #10
On Thu, Oct 5, 2023 at 1:26 PM Ingo Molnar <mingo@kernel.org> wrote:
>
>
> * Xuewen Yan <xuewen.yan@unisoc.com> wrote:
>
> > When cpufreq's policy is single, there is a scenario that will
> > cause sg_policy's next_freq to be unable to update.
> >
> > When the cpu's util is always max, the cpufreq will be max,
> > and then if we change the policy's scaling_max_freq to be a
> > lower freq, indeed, the sg_policy's next_freq need change to
> > be the lower freq, however, because the cpu_is_busy, the next_freq
> > would keep the max_freq.
> >
> > For example:
> > The cpu7 is single cpu:
> >
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > [1] 4737
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > pid 4737's current affinity mask: ff
> > pid 4737's new affinity mask: 80
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > 2301000
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > 2301000
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > 2171000
> >
> > At this time, the sg_policy's next_freq would keep 2301000.
> >
> > To prevent the case happen, add the judgment of the need_freq_update flag.
> >
> > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > ---
> >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> >  1 file changed, 2 insertions(+), 1 deletion(-)
> >
> > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > index 4492608b7d7f..458d359f5991 100644
> > --- a/kernel/sched/cpufreq_schedutil.c
> > +++ b/kernel/sched/cpufreq_schedutil.c
> > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> >        * Except when the rq is capped by uclamp_max.
> >        */
> >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > +         !sg_policy->need_freq_update) {
> >               next_f = sg_policy->next_freq;
> >
> >               /* Restore cached freq as next_freq has changed */
>
> Just wondering about the status of this fix - is it pending in
> some tree, or should we apply it to the scheduler tree?

I have not queued it up yet, so it can be applied to the scheduler tree.

Thanks!
Ingo Molnar Oct. 5, 2023, 8:09 p.m. UTC | #11
* Rafael J. Wysocki <rafael@kernel.org> wrote:

> On Thu, Oct 5, 2023 at 1:26 PM Ingo Molnar <mingo@kernel.org> wrote:
> >
> >
> > * Xuewen Yan <xuewen.yan@unisoc.com> wrote:
> >
> > > When cpufreq's policy is single, there is a scenario that will
> > > cause sg_policy's next_freq to be unable to update.
> > >
> > > When the cpu's util is always max, the cpufreq will be max,
> > > and then if we change the policy's scaling_max_freq to be a
> > > lower freq, indeed, the sg_policy's next_freq need change to
> > > be the lower freq, however, because the cpu_is_busy, the next_freq
> > > would keep the max_freq.
> > >
> > > For example:
> > > The cpu7 is single cpu:
> > >
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # while true;do done&
> > > [1] 4737
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # taskset -p 80 4737
> > > pid 4737's current affinity mask: ff
> > > pid 4737's new affinity mask: 80
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > 2301000
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_cur_freq
> > > 2301000
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # echo 2171000 > scaling_max_freq
> > > unisoc:/sys/devices/system/cpu/cpufreq/policy7 # cat scaling_max_freq
> > > 2171000
> > >
> > > At this time, the sg_policy's next_freq would keep 2301000.
> > >
> > > To prevent the case happen, add the judgment of the need_freq_update flag.
> > >
> > > Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
> > > Co-developed-by: Guohua Yan <guohua.yan@unisoc.com>
> > > Signed-off-by: Guohua Yan <guohua.yan@unisoc.com>
> > > ---
> > >  kernel/sched/cpufreq_schedutil.c | 3 ++-
> > >  1 file changed, 2 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
> > > index 4492608b7d7f..458d359f5991 100644
> > > --- a/kernel/sched/cpufreq_schedutil.c
> > > +++ b/kernel/sched/cpufreq_schedutil.c
> > > @@ -350,7 +350,8 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
> > >        * Except when the rq is capped by uclamp_max.
> > >        */
> > >       if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
> > > -         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
> > > +         sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
> > > +         !sg_policy->need_freq_update) {
> > >               next_f = sg_policy->next_freq;
> > >
> > >               /* Restore cached freq as next_freq has changed */
> >
> > Just wondering about the status of this fix - is it pending in
> > some tree, or should we apply it to the scheduler tree?
> 
> I have not queued it up yet, so it can be applied to the scheduler tree.

Ok, I've applied it - and I've added your Acked-by.

Thanks,

	Ingo
diff mbox series

Patch

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 4492608b7d7f..458d359f5991 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -350,7 +350,8 @@  static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
 	 * Except when the rq is capped by uclamp_max.
 	 */
 	if (!uclamp_rq_is_capped(cpu_rq(sg_cpu->cpu)) &&
-	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq) {
+	    sugov_cpu_is_busy(sg_cpu) && next_f < sg_policy->next_freq &&
+	    !sg_policy->need_freq_update) {
 		next_f = sg_policy->next_freq;
 
 		/* Restore cached freq as next_freq has changed */