[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210929191115.GY4323@worktop.programming.kicks-ass.net>
Date: Wed, 29 Sep 2021 21:11:15 +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 11:37:01AM -0700, Paul E. McKenney wrote:
> > +void context_tracking_idle(void)
> > +{
> > + atomic_add_return(CT_SEQ, &raw_cpu_ptr(&context_tracking)->seq);
>
> This is presumably a momentary idle.
> > notrace void rcu_momentary_dyntick_idle(void)
> > {
> > - int seq;
> > -
> > raw_cpu_write(rcu_data.rcu_need_heavy_qs, false);
> > - seq = rcu_dynticks_inc(2);
> > - /* It is illegal to call this from idle state. */
> > - WARN_ON_ONCE(!(seq & 0x1));
> > + context_tracking_idle();
> > rcu_preempt_deferred_qs(current);
> > }
It's whatever that is. It increments the actual sequence count without
modifying the state.
Powered by blists - more mailing lists