[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20090529145614.77694e20@skybase>
Date: Fri, 29 May 2009 14:56:14 +0200
From: Martin Schwidefsky <schwidefsky@...ibm.com>
To: Thomas Gleixner <tglx@...utronix.de>
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 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.
--
blue skies,
Martin.
"Reality continues to ruin my life." - Calvin.
--
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