[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <579899d18d5aa4422f970d28e19dc363c9ed218a.camel@sipsolutions.net>
Date: Thu, 11 Sep 2025 08:59:57 +0200
From: Johannes Berg <johannes@...solutions.net>
To: Tiwei Bie <tiwei.bie@...ux.dev>
Cc: richard@....at, anton.ivanov@...bridgegreys.com,
benjamin@...solutions.net, arnd@...db.de, linux-um@...ts.infradead.org,
linux-kernel@...r.kernel.org, tiwei.btw@...group.com
Subject: Re: [PATCH v2 05/10] um: Determine sleep based on need_resched()
On Thu, 2025-09-11 at 12:39 +0800, Tiwei Bie wrote:
> On Wed, 10 Sep 2025 14:10:37 +0200, Johannes Berg wrote:
> > On Sun, 2025-08-10 at 13:51 +0800, Tiwei Bie wrote:
> > > From: Tiwei Bie <tiwei.btw@...group.com>
> > >
> > > With SMP and NO_HZ enabled, the CPU may still need to sleep even
> > > if the timer is disarmed. Switch to deciding whether to sleep based
> > > on pending resched. This is a preparation for adding SMP support.
> >
> > What's the rationale for need_resched()? Is that somehow defined for
> > this? Is it what other architectures use? I guess I'm just not entirely
> > sure what it means.
>
> Here is a relevant document:
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/Documentation/scheduler/sched-arch.rst?h=v6.17-rc5#n37
>
> There is a similar check on x86:
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/arch/x86/kernel/process.c?h=v6.17-rc5#n916
Ah cool, thanks for the pointers. Though "1." part there is a bit
confusing, I guess I'll send a patch to reword it :)
FWIW I already applied a few patches, but I'll take another look,
hopefully today.
johannes
Powered by blists - more mailing lists