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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <7ce12aa2-1925-f991-a85f-5bd81ba668fb@arm.com>
Date:   Thu, 27 Feb 2020 16:28:01 +0000
From:   Dietmar Eggemann <dietmar.eggemann@....com>
To:     Quentin Perret <qperret@...gle.com>,
        Valentin Schneider <valentin.schneider@....com>
Cc:     linux-kernel@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
        Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...nel.org>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        morten.rasmussen@....com,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>,
        Mark Rutland <mark.rutland@....com>, kernel-team@...roid.com
Subject: Re: [PATCH 1/2] sched/topology: Don't enable EAS on SMT systems

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@....com>
> 
> Acked-by: Quentin Perret <qperret@...gle.com>
> 
> 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.
 ;-)