Re: [RFC 06/10] rcu/hotplug: Make rcutree_dead_cpu() parallel

[Paul E. McKenney]

On Wed, Aug 24, 2022 at 09:53:11PM +0800, Pingfan Liu wrote:
> On Tue, Aug 23, 2022 at 11:01 AM Paul E. McKenney <paulmck@xxxxxxxxxx> wrote:
> >
> > On Tue, Aug 23, 2022 at 09:50:56AM +0800, Pingfan Liu wrote:
> > > On Sun, Aug 21, 2022 at 07:45:28PM -0700, Paul E. McKenney wrote:
> > > > On Mon, Aug 22, 2022 at 10:15:16AM +0800, Pingfan Liu wrote:
> > > > > In order to support parallel, rcu_state.n_online_cpus should be
> > > > > atomic_dec()
> > > > >
> > > > > Signed-off-by: Pingfan Liu <kernelfans@xxxxxxxxx>
> > > >
> > > > I have to ask...  What testing have you subjected this patch to?
> > > >
> > >
> > > This patch subjects to [1]. The series aims to enable kexec-reboot in
> > > parallel on all cpu. As a result, the involved RCU part is expected to
> > > support parallel.
> >
> > I understand (and even sympathize with) the expectation.  But results
> > sometimes diverge from expectations.  There have been implicit assumptions
> > in RCU about only one CPU going offline at a time, and I am not sure
> > that all of them have been addressed.  Concurrent CPU onlining has
> > been looked at recently here:
> >
> > https://docs.google.com/document/d/1jymsaCPQ1PUDcfjIKm0UIbVdrJAaGX-6cXrmcfm0PRU/edit?usp=sharing
> >
> > You did us atomic_dec() to make rcu_state.n_online_cpus decrementing be
> > atomic, which is good.  Did you look through the rest of RCU's CPU-offline
> > code paths and related code paths?
> 
> I went through those codes at a shallow level, especially at each
> cpuhp_step hook in the RCU system.

And that is fine, at least as a first step.

> But as you pointed out, there are implicit assumptions about only one
> CPU going offline at a time, I will chew the google doc which you
> share.  Then I can come to a final result.

Boqun Feng, Neeraj Upadhyay, Uladzislau Rezki, and I took a quick look,
and rcu_boost_kthread_setaffinity() seems to need some help.  As it
stands, it appears that concurrent invocations of this function from the
CPU-offline path will cause all but the last outgoing CPU's bit to be
(incorrectly) set in the cpumask_var_t passed to set_cpus_allowed_ptr().

This should not be difficult to fix, for example, by maintaining a
separate per-leaf-rcu_node-structure bitmask of the concurrently outgoing
CPUs for that rcu_node structure.  (Similar in structure to the
->qsmask field.)

There are probably more where that one came from.  ;-)

> > > [1]: https://lore.kernel.org/linux-arm-kernel/20220822021520.6996-3-kernelfans@xxxxxxxxx/T/#mf62352138d7b040fdb583ba66f8cd0ed1e145feb
> >
> > Perhaps I am more blind than usual today, but I am not seeing anything
> > in this patch describing the testing.  At this point, I am thinking in
> > terms of making rcutorture test concurrent CPU offlining parallel
> 
> Yes, testing results are more convincing in this area.
> 
> After making clear the implicit assumptions, I will write some code to
> bridge my code and rcutorture test. Since the series is a little
> different from parallel cpu offlining. It happens after all devices
> are torn down, and there is no way to rollback.

Very good, looking forward to seeing what you come up with!

> > Thoughts?
> 
> Need a deeper dive into this field. Hope to bring out something soon.

Again, looking forward to seeing what you find!

							Thanx, Paul