[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20170413174249.GA12617@linux.vnet.ibm.com>
Date: Thu, 13 Apr 2017 10:42:49 -0700
From: "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: linux-kernel@...r.kernel.org, mingo@...nel.org,
jiangshanlai@...il.com, dipankar@...ibm.com,
akpm@...ux-foundation.org, mathieu.desnoyers@...icios.com,
josh@...htriplett.org, tglx@...utronix.de, rostedt@...dmis.org,
dhowells@...hat.com, edumazet@...gle.com, fweisbec@...il.com,
oleg@...hat.com, bobby.prani@...il.com, laurent.dufour@...ibm.com,
npiggin@....ibm.com
Subject: Re: [PATCH tip/core/rcu 40/40] srcu: Parallelize callback handling
On Thu, Apr 13, 2017 at 09:37:10AM -0700, Paul E. McKenney wrote:
> On Thu, Apr 13, 2017 at 11:50:29AM +0200, Peter Zijlstra wrote:
> > On Wed, Apr 12, 2017 at 10:40:25AM -0700, Paul E. McKenney wrote:
> > > Peter Zijlstra proposed using SRCU to reduce mmap_sem contention [1],
> >
> > Bugger, now you're making me feel bad for not having updated those
> > patches in ages.. I'll try and bump it on the todo list.
>
> Apologies, I wasn't trying to make you feel bad. But I did get an old
> version of the patch. A much more recent one is here, which I have
> added to the commit log:
>
> https://patchwork.kernel.org/patch/5108281/
>
> For my part, I feel bad that I didn't realize much earlier that parallel
> SRCU callbacks were needed. As it was, someone had to tell me late
> last year.
And it turns out that Laurent Dufour (CCed) forward-ported your
patch from the above patchworks URL to 4.11. He is chasing down
some mmseq bugs on a best-effort basis.
Thanx, Paul
> But yes, it would be really cool to have lockless VMA lookup!!!
>
> Thanx, Paul
Powered by blists - more mailing lists