Re: [PATCH tip/core/rcu 18/18] rcu: Better hotplug handling for synchronize_sched_expedited()

["Paul E. McKenney" <paulmck@linux.vnet.ibm.com>]

On Wed, Oct 07, 2015 at 04:26:27PM +0200, Peter Zijlstra wrote:
> On Tue, Oct 06, 2015 at 09:29:37AM -0700, Paul E. McKenney wrote:
> >  void rcu_sched_qs(void)
> >  {
> > +	unsigned long flags;
> > +
> >  	if (__this_cpu_read(rcu_sched_data.cpu_no_qs.s)) {
> >  		trace_rcu_grace_period(TPS("rcu_sched"),
> >  				       __this_cpu_read(rcu_sched_data.gpnum),
> >  				       TPS("cpuqs"));
> >  		__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
> > +		if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
> > +			return;
> > +		local_irq_save(flags);
> >  		if (__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp)) {
> >  			__this_cpu_write(rcu_sched_data.cpu_no_qs.b.exp, false);
> >  			rcu_report_exp_rdp(&rcu_sched_state,
> >  					   this_cpu_ptr(&rcu_sched_data),
> >  					   true);
> >  		}
> > +		local_irq_restore(flags);
> >  	}
> >  }
> 
> *sigh*.. still rare I suppose, but should we look at doing something
> like this?

Indeed, that approach looks better than moving rcu_note_context_switch(),
which probably results in deadlocks.  I will update my patch accordingly.

							Thanx, Paul

> ---
>  kernel/sched/core.c | 6 ++++--
>  1 file changed, 4 insertions(+), 2 deletions(-)
> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index fe819298c220..3d830c3491c4 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3050,7 +3050,6 @@ static void __sched __schedule(void)
> 
>  	cpu = smp_processor_id();
>  	rq = cpu_rq(cpu);
> -	rcu_note_context_switch();
>  	prev = rq->curr;
> 
>  	schedule_debug(prev);
> @@ -3058,13 +3057,16 @@ static void __sched __schedule(void)
>  	if (sched_feat(HRTICK))
>  		hrtick_clear(rq);
> 
> +	local_irq_disable();
> +	rcu_note_context_switch();
> +
>  	/*
>  	 * Make sure that signal_pending_state()->signal_pending() below
>  	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
>  	 * done by the caller to avoid the race with signal_wake_up().
>  	 */
>  	smp_mb__before_spinlock();
> -	raw_spin_lock_irq(&rq->lock);
> +	raw_spin_lock(&rq->lock);
>  	lockdep_pin_lock(&rq->lock);
> 
>  	rq->clock_skip_update <<= 1; /* promote REQ to ACT */
>