Re: [PATCH RFC tip/core/rcu 2/5] rcu: Short-circuit normal GPs via expedited GPs

From: Paul E. McKenney
Date: Thu Jul 02 2015 - 11:21:55 EST


On Thu, Jul 02, 2015 at 02:03:29PM +0200, Peter Zijlstra wrote:
> On Wed, Jul 01, 2015 at 07:03:13AM -0700, Paul E. McKenney wrote:
> > On Wed, Jul 01, 2015 at 03:48:06PM +0200, Peter Zijlstra wrote:
> > > On Wed, Jul 01, 2015 at 06:41:44AM -0700, Paul E. McKenney wrote:
> > > > On Wed, Jul 01, 2015 at 12:05:21PM +0200, Peter Zijlstra wrote:
> > > > > On Tue, Jun 30, 2015 at 02:48:27PM -0700, Paul E. McKenney wrote:
> > > > > > rsp->gp_state = RCU_GP_WAIT_FQS;
> > > > > > ret = wait_event_interruptible_timeout(rsp->gp_wq,
> > > > > > + ((gf = READ_ONCE(rsp->gp_flags)) &
> > > > > > + RCU_GP_FLAG_FQS) ||
> > > > > > + (!READ_ONCE(rnp->qsmask) &&
> > > > > > + !rcu_preempt_blocked_readers_cgp(rnp)) ||
> > > > > > + rcu_exp_gp_seq_done(rsp->exp_rsp,
> > > > > > + rsp->gp_exp_snap),
> > > > > > + j);
> > > > > > rsp->gp_state = RCU_GP_DONE_FQS;
> > > > >
> > > > > How can the GP be done if we timed out or got interrupted?
> > > >
> > > > If all the CPUs still blocking the grace period went idle, or in a
> > > > NO_HZ_FULL kernel, entered nohz_full userspace execution. Or, if
> > > > certain low-probability races happen, went offline.
> > >
> > > But what if none of those are true and we still timed out? You
> > > unconditionally grant the GP.
> >
> > Say what???
> >
> > I recheck the conditions and break out of the loop only if one or more
> > of the grace-period-end conditions is satisfied. If not, I invoke
> > rcu_gp_fqs() to do the scan to see if all remaining CPUs are idle,
> > in nohz_full userspace execution, or offline.
> >
> > What am I mising here?
>
> The whole wait_event_interruptible_timeout() thing can end without @cond
> being true, after which you unconditionally set ->gp_state =
> RCU_GP_DONE_FQS.

Ah, but then if the grace period is not done, even after a scan forcing
quiescent states, we go back through the loop and set it back to
RCU_GP_WAIT_FQS.

Or is your point that RCU_GP_DONE_FQS is a bad name? Perhaps I should
change it to something like RCU_GP_DOING_FQS. Or am I still missing
something here?

Thanx, Paul

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/