linux-kernel - Re: [PATCH] sched/arm64: store cpu topology before notify_cpu

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]

Date:   Fri, 10 Apr 2020 21:49:18 +0800
From:   "chengjian (D)" <cj.chengjian@...wei.com>
To:     Joel Fernandes <joelaf@...gle.com>
CC:     Vineeth Remanan Pillai <vpillai@...italocean.com>,
        <aaron.lwe@...il.com>, <aubrey.intel@...il.com>,
        <aubrey.li@...ux.intel.com>,
        "Cc: Frederic Weisbecker" <fweisbec@...il.com>,
        Julien Desfossez <jdesfossez@...italocean.com>,
        "Joel Fernandes (Google)" <joel@...lfernandes.org>,
        Kees Cook <keescook@...omium.org>,
        Greg Kerr <kerrnel@...gle.com>,
        LKML <linux-kernel@...r.kernel.org>,
        <mgorman@...hsingularity.net>, Ingo Molnar <mingo@...nel.org>,
        <naravamudan@...italocean.com>, <pauld@...hat.com>,
        <pawan.kumar.gupta@...ux.intel.com>, <pbonzini@...hat.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Paul Turner <pjt@...gle.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        <tim.c.chen@...ux.intel.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Valentin Schneider <valentin.schneider@....com>,
        <xiexiuqi@...wei.com>, <huawei.libin@...wei.com>, <w.f@...wei.com>,
        "chengjian (D)" <cj.chengjian@...wei.com>,
        "wxf.wang@...ilicon.com >> Xuefeng Wang" <wxf.wang@...ilicon.com>
Subject: Re: [PATCH] sched/arm64: store cpu topology before
 notify_cpu_starting


On 2020/4/10 1:54, Joel Fernandes wrote:
> On Wed, Apr 1, 2020 at 7:27 AM Cheng Jian <cj.chengjian@...wei.com> wrote:
>> when SCHED_CORE enabled, sched_cpu_starting() uses thread_sibling as
>> SMT_MASK to initialize rq->core, but only after store_cpu_topology(),
>> the thread_sibling is ready for use.
>>
>>          notify_cpu_starting()
>>              -> sched_cpu_starting()     # use thread_sibling
>>
>>          store_cpu_topology(cpu)
>>              -> update_siblings_masks    # set thread_sibling
>>
>> Fix this by doing notify_cpu_starting later, just like x86 do.
>>
>> Signed-off-by: Cheng Jian <cj.chengjian@...wei.com>
> Just a high-level question, why does core-scheduling matter on ARM64?
> Is it for HPC workloads?
>
> Thanks,
>
>   - Joel

Hi, Joel

I am analyzing the mainline scheduling patches and find this problem.


ARM has some platforms that support SMT, and provides some emulate

can be used.



Thanks.

--Cheng Jian