[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <alpine.LFD.2.00.0905291514470.3397@localhost.localdomain>
Date: Fri, 29 May 2009 15:15:26 +0200 (CEST)
From: Thomas Gleixner <tglx@...utronix.de>
To: Martin Schwidefsky <schwidefsky@...ibm.com>
cc: linux-kernel@...r.kernel.org, Rob van der Heij <rvdheij@...il.com>,
Heiko Carstens <heiko.carstens@...ibm.com>,
Ingo Molnar <mingo@...e.hu>, john stultz <johnstul@...ibm.com>
Subject: Re: [patch 1/2] idle profile hits with NOHZ
On Fri, 29 May 2009, Martin Schwidefsky wrote:
> On Thu, 28 May 2009 22:19:44 +0200 (CEST)
> Thomas Gleixner <tglx@...utronix.de> wrote:
>
> > On Thu, 28 May 2009, Martin Schwidefsky wrote:
> > > --- quilt-2.6.orig/kernel/time/tick-sched.c
> > > +++ quilt-2.6/kernel/time/tick-sched.c
> > > @@ -166,6 +166,7 @@ static void tick_nohz_stop_idle(int cpu)
> > > ts->idle_lastupdate = now;
> > > ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
> > > ts->idle_active = 0;
> > > + ts->idle_pc = profile_pc(get_irq_regs());
> >
> > Hmm, tick_nohz_stop_idle() is called from
> > tick_nohz_restart_sched_tick() as well in the context of the idle
> > task.
> >
> > I think there is no guarantee that get_irq_regs() will return
> > anything useful in thread context.
> >
> > So get_irq_regs() might return a NULL pointer which will explode
> > some of the profile_pc() implementations. If not it can still feed
> > total nonsense to the profile_hits() call.
>
> Drat, but if it is called from idle we should be able to just skip the
> assignment to ts->idle_pc, no? Then a simple in_interrupt() test is
> missing.
That should do the trick.
Thanks,
tglx
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists