Re: [RFC][PATCH 12/13] stop_machine: Remove lglock

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

On Wed, Jun 24, 2015 at 09:35:03AM +0200, Peter Zijlstra wrote:
> On Tue, Jun 23, 2015 at 11:26:26AM -0700, Paul E. McKenney wrote:
> > > I really think you're making that expedited nonsense far too accessible.
> > 
> > This has nothing to do with accessibility and everything to do with
> > robustness.  And with me not becoming the triage center for too many
> > non-RCU bugs.
> 
> But by making it so you're rewarding abuse instead of flagging it :-(

As discussed in the thread with Ingo, I will do both.

Alternatively, RCU -is- abuse.  Anyone who tries to tell you
otherwise simply lacks proper respect for and adoration of traditional
synchronization mechanisms.  ;-)

> > > > And we still need to be able to drop back to synchronize_sched()
> > > > (AKA wait_rcu_gp(call_rcu_sched) in this case) in case we have both a
> > > > creative user and a long-running RCU-sched read-side critical section.
> > > 
> > > No, a long-running RCU-sched read-side is a bug and we should fix that,
> > > its called a preemption-latency, we don't like those.
> > 
> > Yes, we should fix them.  No, they absolutely must not result in a
> > meltdown of some unrelated portion of the kernel (like RCU), particularly
> > if this situation occurs on some system running a production workload
> > that doesn't happen to care about preemption latency.
> 
> I still don't see a problem here though; the stop_one_cpu() invocation
> for the CPU that's suffering its preemption latency will take longer,
> but so what?
> 
> How does polling and dropping back to sync_rcu() generate better
> behaviour than simply waiting for the completion?

Because if there is too much delay, synchronize_rcu() is no slower
than is synchronize_rcu_expedited(), plus synchronize_rcu() is much
more efficient.

That said, it appears that I have not given any particular thought to the
polling code since about 2008 or so, and it could use quite an upgrade...

> > > > > +		stop_one_cpu(cpu, synchronize_sched_expedited_cpu_stop, NULL);
> > > > 
> > > > My thought was to use smp_call_function_single(), and to have the function
> > > > called recheck dyntick-idle state, avoiding doing a set_tsk_need_resched()
> > > > if so.
> > > 
> > > set_tsk_need_resched() is buggy and should not be used.
> > 
> > OK, what API is used for this purpose?
> 
> As per exception you (rcu) already have access to resched_cpu(), use
> that -- if it doesn't do what you need it to, we'll fix it, you're the
> only consumer of it.

Color me slow and stupid!

And it looks like resched_cpu() does just fine on the local CPU, so it
should be just fine as is.  Thank you for the reminder.

							Thanx, Paul