[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 11 Nov 2021 16:46:31 -0500
From: Waiman Long <longman@...hat.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Hillf Danton <hdanton@...a.com>,
马振华 <mazhenhua@...omi.com>,
mingo <mingo@...hat.com>, will <will@...nel.org>,
"boqun.feng" <boqun.feng@...il.com>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [BUG]locking/rwsem: only clean RWSEM_FLAG_HANDOFF when already
set
On 11/11/21 16:38, Peter Zijlstra wrote:
> On Thu, Nov 11, 2021 at 04:01:16PM -0500, Waiman Long wrote:
>
>>>> + if (has_handoff || (!waiter->rt_task &&
>>>> + !time_after(jiffies, waiter->timeout)))
>>> Does ->rt_task really help over rt_task(current) ? I suppose there's an
>>> argument for locality, but that should be pretty much it, no?
>> Waiting for the timeout may introduce too much latency for RT task. That is
>> the only reason I am doing it. I can take it out if you think it is not
>> necessary.
> I meant simply calling rt_task(waiter->task) here, instead of mucking about
> with the extra variable.
OK, that make sense.
Cheers,
Longman
Powered by blists - more mailing lists