Re: [RFC] rcu: Prevent expedite reporting within RCU read-side section

From: Paul E. McKenney
Date: Tue Mar 06 2018 - 12:24:15 EST


On Tue, Mar 06, 2018 at 09:43:19PM +0900, Byungchul Park wrote:
> On Mar 6, 2018 2:34 PM, "Byungchul Park" <byungchul.park@xxxxxxx> wrote:
> >
> > Hello Paul and RCU folks,
> >
> > I am afraid I correctly understand and fix it. But I really wonder why
> > sync_rcu_exp_handler() reports the quiescent state even in the case that
> > current task is within a RCU read-side section. Do I miss something?
>
> Hello,
>
> I missed the fact that the original code is anyway safe because
> the case is gonna be handled properly in rcu_read_unlock().
>
> This patch just makes unnecessary spin lock/unlock within *report*()
> avoided. Please ignore this if you don't think it's that worthy. I am
> also not sure if it is.
>
> Sorry bothering you. And thanks.

Not a problem, especially given that you figured it out before I got
to your email. And thank you for your review of RCU!

Thanx, Paul

> > If I correctly understand it and you agree with it, I can add more logic
> > which make it more expedited by boosting current or making it urgent
> > when we fail to report the quiescent state on the IPI.
> >
> > ----->8-----
> > From 0b0191f506c19ce331a1fdb7c2c5a00fb23fbcf2 Mon Sep 17 00:00:00 2001
> > From: Byungchul Park <byungchul.park@xxxxxxx>
> > Date: Tue, 6 Mar 2018 13:54:41 +0900
> > Subject: [RFC] rcu: Prevent expedite reporting within RCU read-side section
> >
> > We report the quiescent state for this cpu if it's out of RCU read-side
> > section at the moment IPI was just fired during the expedite process.
> >
> > However, current code reports the quiescent state even in the case:
> >
> > 1) the current task is still within a RCU read-side section
> > 2) the current task has been blocked within the RCU read-side section
> >
> > Since we don't get to the quiescent state yet in the case, we shouldn't
> > report it but check it another time.
> >
> > Signed-off-by: Byungchul Park <byungchul.park@xxxxxxx>
> > ---
> > kernel/rcu/tree_exp.h | 12 ++++++------
> > 1 file changed, 6 insertions(+), 6 deletions(-)
> >
> > diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
> > index 73e1d3d..cc69d14 100644
> > --- a/kernel/rcu/tree_exp.h
> > +++ b/kernel/rcu/tree_exp.h
> > @@ -731,13 +731,13 @@ static void sync_rcu_exp_handler(void *info)
> > /*
> > * We are either exiting an RCU read-side critical section (negative
> > * values of t->rcu_read_lock_nesting) or are not in one at all
> > - * (zero value of t->rcu_read_lock_nesting). Or we are in an RCU
> > - * read-side critical section that blocked before this expedited
> > - * grace period started. Either way, we can immediately report
> > - * the quiescent state.
> > + * (zero value of t->rcu_read_lock_nesting). We can immediately
> > + * report the quiescent state.
> > */
> > - rdp = this_cpu_ptr(rsp->rda);
> > - rcu_report_exp_rdp(rsp, rdp, true);
> > + if (t->rcu_read_lock_nesting <= 0) {
> > + rdp = this_cpu_ptr(rsp->rda);
> > + rcu_report_exp_rdp(rsp, rdp, true);
> > + }
> > }
> >
> > /**
> > --
> > 1.9.1
> >
>