Re: [PATCH 1/2] sched/topology: Don't enable EAS on SMT systems

[Dietmar Eggemann]

On 27.02.20 13:00, Quentin Perret wrote:
> On Wednesday 26 Feb 2020 at 16:41:17 (+0000), Valentin Schneider wrote:
>> EAS already requires asymmetric CPU capacities to be enabled, and mixing
>> this with SMT is an aberration, but better be safe than sorry.
>>
>> Signed-off-by: Valentin Schneider <valentin.schneider@xxxxxxx>
> 
> Acked-by: Quentin Perret <qperret@xxxxxxxxxx>
> 
> Thanks,
> Quentin
> 
>> ---
>>  kernel/sched/topology.c | 4 ++++
>>  1 file changed, 4 insertions(+)
>>
>> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
>> index 00911884b7e7..76cd0a370b9a 100644
>> --- a/kernel/sched/topology.c
>> +++ b/kernel/sched/topology.c
>> @@ -360,6 +360,10 @@ static bool build_perf_domains(const struct cpumask *cpu_map)
>>  		goto free;
>>  	}
>>  
>> +	/* EAS definitely does *not* handle SMT */
>> +	if (sched_smt_active())

Can you add a pr_warn() and use the current comment as the warning
message? Since we have one for !Asym CPU capacity and !schedutil.

>> +		goto free;
>> +

[...]

There is this 'EAS can be used ...' list of currently 4 items in the
build_perf_domains() function header. You could include 'X. No SMT
support' there.
 ;-)