On Fri, Sep 06, 2024 at 03:12:11PM +0200, Frederic Weisbecker wrote:
> Le Thu, Sep 05, 2024 at 11:04:22PM -0700, Paul E. McKenney a écrit :
> > On Thu, Sep 05, 2024 at 08:41:02PM +0200, Frederic Weisbecker wrote:
> > > Le Thu, Sep 05, 2024 at 08:32:16PM +0200, Frederic Weisbecker a écrit :
> > > > Le Wed, Sep 04, 2024 at 06:52:36AM -0700, Paul E. McKenney a écrit :
> > > > > > Yes, I'm preparing an update for the offending patch (which has one
> > > > > > more
> > > > > > embarassing issue while I'm going through it again).
> > > > >
> > > > > Very good, thank you!
> > > >
> > > > So my proposal for a replacement patch is this (to replace the patch
> > > > of the same name in Neeraj tree):
> > >
> > > FYI, the diffstat against the previous version of the same patch is as
> > > follows.
> > > The rationale being:
> > >
> > > 1) rdp->nocb_cb_kthread doesn't need to be protected by
> > > nocb_gp_kthread_mutex
> > >
> > > 2) Once rcuoc is parked, we really _must_ observe the callback list
> > > counter decremented
> > > after the barrier's completion.
> > >
> > > 3) This fixes another issue: rcuoc must be parked _before_
> > > rcu_nocb_queue_toggle_rdp() is called, otherwise a nocb locked sequence
> > > within rcuoc would race with rcuog clearing SEGCBLIST_OFFLOADED
> > > concurrently,
> > > leaving the nocb locked forever.
> >
> > Thank you!!!
> >
> > Just to make sure that I understand, I apply this patch on top of
> > Neeraj's current set of branches to get the fix, correct?
>
> Exactly!
It passes the initial tests, an hour of 200*TREE01 and a 10-minute
torture.sh (which Neeraj likely already ran a longer version of). I fired
off a 12-hour 200*TREE01 run and a 60-minute torture.sh for overnight.
Here is hoping! ;-)
Thanx, Paul
