Re: scheduler problems in -next (was: Re: [PATCH 6.4 000/227] 6.4.7-rc1 review)

[Paul E. McKenney]

On Tue, Aug 01, 2023 at 09:08:52PM +0200, Peter Zijlstra wrote:
> On Tue, Aug 01, 2023 at 10:32:45AM -0700, Guenter Roeck wrote:
> > On 7/31/23 14:15, Peter Zijlstra wrote:
> > > On Mon, Jul 31, 2023 at 09:34:29AM -0700, Guenter Roeck wrote:
> > > > > Ha!, I was poking around the same thing. My hack below seems to (so far,
> > > > > <20 boots) help things.
> > > > > 
> > > > 
> > > > So, dumb question:
> > > > How comes this bisects to "sched/fair: Remove sched_feat(START_DEBIT)" ?
> > > 
> > > That commit changes the timings of things; dumb luck otherwise.
> > 
> > Kind of scary. So I only experienced the problem because the START_DEBIT patch
> > happened to be queued roughly at the same time, and it might otherwise have
> > found its way unnoticed into the upstream kernel. That makes me wonder if this
> > or other similar patches may uncover similar problems elsewhere in the kernel
> > (i.e., either hide new or existing race conditions or expose existing ones).
> > 
> > This in turn makes me wonder if it would be possible to define a test which
> > would uncover such problems without the START_DEBIT patch. Any idea ?
> 
> IIRC some of the thread sanitizers use breakpoints to inject random
> sleeps, specifically to tickle races.

I have heard of are some of these, arguably including KCSAN, but they
would have a tough time on this one.

They would have to inject many milliseconds between the check of
->kthread_ptr in synchronize_rcu_tasks_generic() and that mutex_lock()
in rcu_tasks_one_gp().  Plus this window only occurs during boot shortly
before init is spawned.

On the other hand, randomly injecting delay just before acquiring each
lock would cover this case.  But such a sanitzer would still only get
one shot per boot of the kernel for this particular bug.

							Thanx, Paul