[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5f96c7e306546af4604cfaddb895a089811cb99b.camel@redhat.com>
Date: Tue, 22 Feb 2022 16:21:26 +0100
From: Nicolas Saenz Julienne <nsaenzju@...hat.com>
To: Marcelo Tosatti <mtosatti@...hat.com>, linux-kernel@...r.kernel.org
Cc: linux-mm@...ck.org, Minchan Kim <minchan@...nel.org>,
Matthew Wilcox <willy@...radead.org>,
Mel Gorman <mgorman@...hsingularity.net>,
Juri Lelli <juril@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
"Paul E. McKenney" <paulmck@...nel.org>
Subject: Re: [patch 1/2] mm: protect local lock sections with rcu_read_lock
(on RT)
On Tue, 2022-02-22 at 11:47 -0300, Marcelo Tosatti wrote:
> For the per-CPU LRU page vectors, augment the local lock protected
> code sections with rcu_read_lock.
>
> This makes it possible to replace the queueing of work items on all
> CPUs by synchronize_rcu (which is necessary to run FIFO:1 applications
> uninterrupted on isolated CPUs).
I don't think this is needed. In RT local_locks use a spinlock. See
kernel/locking/spinlock_rt.c:
"The RT [spinlock] substitutions explicitly disable migration and take
rcu_read_lock() across the lock held section."
Regards,
--
Nicolás Sáenz
Powered by blists - more mailing lists