[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210929192431.GG5106@worktop.programming.kicks-ass.net>
Date: Wed, 29 Sep 2021 21:24:31 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: "Paul E. McKenney" <paulmck@...nel.org>
Cc: gor@...ux.ibm.com, jpoimboe@...hat.com, jikos@...nel.org,
mbenes@...e.cz, pmladek@...e.com, mingo@...nel.org,
linux-kernel@...r.kernel.org, joe.lawrence@...hat.com,
fweisbec@...il.com, tglx@...utronix.de, hca@...ux.ibm.com,
svens@...ux.ibm.com, sumanthk@...ux.ibm.com,
live-patching@...r.kernel.org, rostedt@...dmis.org, x86@...nel.org
Subject: Re: [RFC][PATCH v2 08/11] context_tracking,rcu: Replace RCU dynticks
counter with context_tracking
On Wed, Sep 29, 2021 at 09:13:26PM +0200, Peter Zijlstra wrote:
> On Wed, Sep 29, 2021 at 11:37:01AM -0700, Paul E. McKenney wrote:
>
> > And what happens to all of this in !CONFIG_CONTEXT_TRACKING kernels?
> > Of course, RCU needs it unconditionally. (There appear to be at least
> > parts of it that are unconditionally available, but I figured that I
> > should ask. Especially given the !CONFIG_CONTEXT_TRACKING definition
> > of the __context_tracking_cpu_seq() function.)
>
> For !CONFIG_CONTEXT_TRACKING it goes *poof*.
>
> Since the thing was called dynticks, I presumed it was actually dynticks
> only, silly me (also, I didn't see any obvious !context_tracking usage
> of it, i'll go audit it more carefully.
Oh argh, it does idle too... damn. And I don't suppose having 2 counters
is going to be nice :/
I'll go back to thinking about this.
Powered by blists - more mailing lists