Re: INFO: rcu detected stall in do_idle

[Juri Lelli]

On 27/10/18 12:16, Dmitry Vyukov wrote:
> On Wed, Oct 24, 2018 at 1:03 PM, Juri Lelli <juri.lelli@xxxxxxxxxx> wrote:
> >
> > On 19/10/18 22:50, luca abeni wrote:
> > > On Fri, 19 Oct 2018 13:39:42 +0200
> > > Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> > >
> > > > On Thu, Oct 18, 2018 at 01:08:11PM +0200, luca abeni wrote:
> > > > > Ok, I see the issue now: the problem is that the "while
> > > > > (dl_se->runtime <= 0)" loop is executed at replenishment time, but
> > > > > the deadline should be postponed at enforcement time.
> > > > >
> > > > > I mean: in update_curr_dl() we do:
> > > > >   dl_se->runtime -= scaled_delta_exec;
> > > > >   if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) {
> > > > >           ...
> > > > >           enqueue replenishment timer at dl_next_period(dl_se)
> > > > > But dl_next_period() is based on a "wrong" deadline!
> > > > >
> > > > >
> > > > > I think that inserting a
> > > > >         while (dl_se->runtime <= -pi_se->dl_runtime) {
> > > > >                 dl_se->deadline += pi_se->dl_period;
> > > > >                 dl_se->runtime += pi_se->dl_runtime;
> > > > >         }
> > > > > immediately after "dl_se->runtime -= scaled_delta_exec;" would fix
> > > > > the problem, no?
> > > >
> > > > That certainly makes sense to me.
> > >
> > > Good; I'll try to work on this idea in the weekend.
> >
> > So, we (me and Luca) managed to spend some more time on this and found a
> > few more things worth sharing. I'll try to summarize what we have got so
> > far (including what already discussed) because impression is that each
> > point might deserve a fix or at least consideration (just amazing how a
> > simple random fuzzer thing can highlight all that :).
> 
> 1. Fuzzing finds bugs in any code. Always.
> If a code wasn't fuzzed, there are bugs.
> 
> 2. This fuzzer is not so simple ;)

Indeed! I meant that it's amazing how the fuzzer was able to forge a
relatively simple reproducer that highlighted the problem.