Date: Wed, 9 Nov 2016 20:52:13 -0800
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Andy Lutomirski <luto@amacapital.net>
Cc: Chris Metcalf <cmetcalf@mellanox.com>,
        Gilad Ben Yossef <giladb@mellanox.com>,
        Steven Rostedt <rostedt@goodmis.org>, Ingo Molnar <mingo@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Rik van Riel <riel@redhat.com>, Tejun Heo <tj@kernel.org>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        Thomas Gleixner <tglx@linutronix.de>, Christoph Lameter <cl@linux.com>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        Catalin Marinas <catalin.marinas@arm.com>,
        Will Deacon <will.deacon@arm.com>,
        Daniel Lezcano <daniel.lezcano@linaro.org>,
        Francis Giraldeau <francis.giraldeau@gmail.com>,
        Andi Kleen <andi@firstfloor.org>, Arnd Bergmann <arnd@arndb.de>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: Re: task isolation discussion at Linux Plumbers
Reply-To: paulmck@linux.vnet.ibm.com
References: <1471382376-5443-1-git-send-email-cmetcalf@mellanox.com>
 <1605b087-2b3b-77c1-01ac-084e378f5f28@mellanox.com>
 <20161109014045.GI4127@linux.vnet.ibm.com>
 <CALCETrWjMrdJPHSjA64rJpVCaEtZCr-ZeE08sKP1-rbvw-4+tQ@mail.gmail.com>
 <20161109173808.GJ4127@linux.vnet.ibm.com>
 <CALCETrXs6BkR+MhRJh5k9-BWTZOQ1=nBy5ycy+1U02ei+BJRcw@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CALCETrXs6BkR+MhRJh5k9-BWTZOQ1=nBy5ycy+1U02ei+BJRcw@mail.gmail.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Message-Id: <20161110045213.GY4127@linux.vnet.ibm.com>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 3062
Lines: 87

On Wed, Nov 09, 2016 at 05:44:02PM -0800, Andy Lutomirski wrote:
> On Wed, Nov 9, 2016 at 9:38 AM, Paul E. McKenney
> <paulmck@linux.vnet.ibm.com> wrote:
> 
> Are you planning on changing rcu_nmi_enter()?  It would make it easier
> to figure out how they interact if I could see the code.

It already calls rcu_dynticks_eqs_exit(), courtesy of the earlier
consolidation patches.

> > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
> > index dbf20b058f48..342c8ee402d6 100644
> > --- a/kernel/rcu/tree.c
> > +++ b/kernel/rcu/tree.c
> 
> 
> >  /*
> > @@ -305,17 +318,22 @@ static void rcu_dynticks_eqs_enter(void)
> >  static void rcu_dynticks_eqs_exit(void)
> >  {
> >         struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
> > +       int seq;
> >
> >         /*
> > -        * CPUs seeing atomic_inc() must see prior idle sojourns,
> > +        * CPUs seeing atomic_inc_return() must see prior idle sojourns,
> >          * and we also must force ordering with the next RCU read-side
> >          * critical section.
> >          */
> > -       smp_mb__before_atomic(); /* See above. */
> > -       atomic_inc(&rdtp->dynticks);
> > -       smp_mb__after_atomic(); /* See above. */
> > +       seq = atomic_inc_return(&rdtp->dynticks);
> >         WARN_ON_ONCE(IS_ENABLED(CONFIG_RCU_EQS_DEBUG) &&
> > -                    !(atomic_read(&rdtp->dynticks) & 0x1));
> > +                    !(seq & RCU_DYNTICK_CTRL_CTR));
> 
> I think there's still a race here.  Suppose we're running this code on
> cpu n and...
> 
> > +       if (seq & RCU_DYNTICK_CTRL_MASK) {
> > +               rcu_eqs_special_exit();
> > +               /* Prefer duplicate flushes to losing a flush. */
> > +               smp_mb__before_atomic(); /* NMI safety. */
> 
> ... another CPU changes the page tables and calls rcu_eqs_special_set(n) here.

But then rcu_eqs_special_set() will return false because we already
exited the extended quiescent state at the atomic_inc_return() above.

That should tell the caller to send an IPI.

> That CPU expects that we will flush prior to continuing, but we won't.
> Admittedly it's highly unlikely that any stale TLB entries would be
> created yet, but nothing rules it out.

That said, 0day is having some heartburn from this, so I must have broken
something somewhere.  My own tests of course complete just fine...

> > +               atomic_and(~RCU_DYNTICK_CTRL_MASK, &rdtp->dynticks);
> > +       }
> 
> Maybe the way to handle it is something like:
> 
> this_cpu_write(rcu_nmi_needs_eqs_special, 1);
> barrier();
> 
> /* NMI here will call rcu_eqs_special_exit() regardless of the value
> in dynticks */
> 
> atomic_and(...);
> smp_mb__after_atomic();
> rcu_eqs_special_exit();
> 
> barrier();
> this_cpu_write(rcu_nmi_needs_eqs_special, 0);
> 
> 
> Then rcu_nmi_enter() would call rcu_eqs_special_exit() if the dynticks
> bit is set *or* rcu_nmi_needs_eqs_special is set.
> 
> Does that make sense?

I believe that rcu_eqs_special_set() returning false covers this, but
could easily be missing something.

							Thanx, Paul