RE: [PATCH] sched/topology: remove redundant cpumask_and in init_overlap_sched_group

[Valentin Schneider]

On 05/03/21 20:25, Song Bao Hua (Barry Song) wrote:
>> -----Original Message-----
>> From: Valentin Schneider [mailto:valentin.schneider@xxxxxxx]
>> Sent: Saturday, March 6, 2021 12:49 AM
>> To: Song Bao Hua (Barry Song) <song.bao.hua@xxxxxxxxxxxxx>;
>> vincent.guittot@xxxxxxxxxx; mingo@xxxxxxxxxx; peterz@xxxxxxxxxxxxx;
>> juri.lelli@xxxxxxxxxx; dietmar.eggemann@xxxxxxx; rostedt@xxxxxxxxxxx;
>> bsegall@xxxxxxxxxx; mgorman@xxxxxxx
>> Cc: linux-kernel@xxxxxxxxxxxxxxx; linuxarm@xxxxxxxxxxxxx; Song Bao Hua (Barry
>> Song) <song.bao.hua@xxxxxxxxxxxxx>
>> Subject: Re: [PATCH] sched/topology: remove redundant cpumask_and in
>> init_overlap_sched_group
>>
>> On 05/03/21 11:29, Barry Song wrote:
>> > mask is built in build_balance_mask() by for_each_cpu(i, sg_span), so
>> > it must be a subset of sched_group_span(sg).
>>
>> So we should indeed have
>>
>>   cpumask_subset(sched_group_span(sg), mask)
>>
>> but that doesn't imply
>>
>>   cpumask_first(sched_group_span(sg)) == cpumask_first(mask)
>>
>> does it? I'm thinking if in your topology of N CPUs, CPUs 0 and N-1 are the
>> furthest away, you will most likely hit
>
> It is true:
> cpumask_first(sched_group_span(sg)) != cpumask_first(mask)
>
> but
>
> cpumask_first_and(sched_group_span(sg), mask) = cpumask_first(mask)
>
> since mask is always subset of sched_group_span(sg).
>

You're right, I read it the wrong way around, sorry about that.

Reviewed-by: Valentin Schneider <Valentin.Schneider@xxxxxxx>