linux-kernel - Re: [PATCH] LoongArch:support CONFIG_SCHED

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] [day] [month] [year] [list]

Message-ID: <CAAhV-H7BejoBtsGWP8tn99Pa93M0ij=yXg_E+GJKLETYWhCt3A@mail.gmail.com>
Date: Tue, 29 Apr 2025 19:52:59 +0800
From: Huacai Chen <chenhuacai@...nel.org>
To: Xi Ruoyao <xry111@...111.site>
Cc: Tianyang Zhang <zhangtianyang@...ngson.cn>, kernel@...0n.name, wanghongliang@...ngson.cn, 
	yangtiezhu@...ngson.cn, loongarch@...ts.linux.dev, 
	linux-kernel@...r.kernel.org
Subject: Re: [PATCH] LoongArch:support CONFIG_SCHED_MC

On Tue, Apr 29, 2025 at 7:44 PM Xi Ruoyao <xry111@...111.site> wrote:
>
> On Tue, 2025-04-29 at 19:33 +0800, Tianyang Zhang wrote:
> > From: wanghongliang <wanghongliang@...ngson.cn>
> >
> > In order to achieve more reasonable load balancing behavior,
> > support for SCHED_MC has been added.
> > The LLC distribution of Loongarch now is consistent with numa-node,
> > the balancing domain of SCHED_MC can effectively reduce the situation
> > where processes are awakened to smt_slibing
> >
> > Co-developed-by: wanghongliang <wanghongliang@...ngson.cn>
> > Signed-off-by: wanghongliang <wanghongliang@...ngson.cn>
> > Signed-off-by: Tianyang Zhang <zhangtianyang@...ngson.cn>
> > ---
> >  arch/loongarch/Kconfig                |  9 ++++++
> >  arch/loongarch/include/asm/smp.h      |  1 +
> >  arch/loongarch/include/asm/topology.h |  8 +++++
> >  arch/loongarch/kernel/smp.c           | 46 +++++++++++++++++++++++++++
> >  4 files changed, 64 insertions(+)
> >
> > diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
> > index 1a2cf012b..72a142a85 100644
> > --- a/arch/loongarch/Kconfig
> > +++ b/arch/loongarch/Kconfig
> > @@ -493,6 +493,15 @@ config NR_CPUS
> >         This allows you to specify the maximum number of CPUs which this
> >         kernel will support.
> >
> > +config SCHED_MC
> > +     def_bool y
> > +     prompt "Multi-core scheduler support"
> > +     depends on SMP
> > +     help
> > +       Multi-core scheduler support improves the CPU scheduler's decision
> > +       making when dealing with multi-core CPU chips at a cost of slightly
> > +       increased overhead in some places. If unsure say N here.
>
> To me it's puzzling to say "if unsure say N here" while setting the
> default to y.
It seems copied from x86, I suggest to modify to

+config SCHED_MC
+ bool "Multi-core scheduler support"
+ depends on SMP
+ default y
+ help
+  Multi-core scheduler support improves the CPU scheduler's decision
+  making when dealing with multi-core CPU chips at a cost of slightly
+  increased overhead in some places.

And put it after SCHED_SMT.

Huacai


>
> --
> Xi Ruoyao <xry111@...111.site>
> School of Aerospace Science and Technology, Xidian University