Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756604Ab0KKUC5 (ORCPT ); Thu, 11 Nov 2010 15:02:57 -0500 Received: from e35.co.us.ibm.com ([32.97.110.153]:56341 "EHLO e35.co.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756301Ab0KKUC4 (ORCPT ); Thu, 11 Nov 2010 15:02:56 -0500 Subject: Re: [RFC-PATCH] clocksource: update lpj if clocksource has been changed. From: john stultz To: MyungJoo Ham Cc: linux-kernel@vger.kernel.org, kyungmin.park@samsung.com, myungjoo.ham@gmail.com, Thomas Gleixner , Magnus Damm , Andrew Morton , Jon Hunter In-Reply-To: <1289464582-26898-1-git-send-email-myungjoo.ham@samsung.com> References: <1289464582-26898-1-git-send-email-myungjoo.ham@samsung.com> Content-Type: text/plain; charset="UTF-8" Date: Thu, 11 Nov 2010 12:02:41 -0800 Message-ID: <1289505761.2742.24.camel@work-vm> Mime-Version: 1.0 X-Mailer: Evolution 2.30.3 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2754 Lines: 77 On Thu, 2010-11-11 at 17:36 +0900, MyungJoo Ham wrote: > With a clocksource change, loops_per_jiffy may have been changed; thus, > the loops_per_jiffy in each cpu should be updated. Especially after some > of the cpus were turned off and on, their loops_per_jiffy values are > updated while the cpus kept on are not. Therefore, in order to make them > "normalized equally", we need to let the loops_per_jiffy values of > different cpus be based on the same clocksource. > > Signed-off-by: MyungJoo Ham > Signed-off-by: Kyungmin Park First, Thanks for reporting the issue and submitting the patch! So the premise is that read_current_timer -> get_cycles -> clocksource_read on some arches. And then when we select a different clocksource for timekeeping, this also changes the get_cycles source breaking delay loops. The clocksource selected for timekeeping and the counter being used for get_cycles really shouldn't be explicitly bound. On most systems I don't think that is the case, so this patch would force needless recalibration calls on clocksource changes. Which arch specifically are you seeing the issue on? I suspect there is be a better way to fix this. thanks -john > --- > kernel/time/clocksource.c | 13 +++++++++++++ > 1 files changed, 13 insertions(+), 0 deletions(-) > > diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c > index c18d7ef..a9d7935 100644 > --- a/kernel/time/clocksource.c > +++ b/kernel/time/clocksource.c > @@ -30,6 +30,9 @@ > #include /* for spin_unlock_irq() using preempt_count() m68k */ > #include > #include > +#include > > void timecounter_init(struct timecounter *tc, > const struct cyclecounter *cc, > @@ -592,6 +593,9 @@ static inline void clocksource_select(void) { } > */ > static int __init clocksource_done_booting(void) > { > +#ifdef CONFIG_SMP > + int cpu; > +#endif > mutex_lock(&clocksource_mutex); > curr_clocksource = clocksource_default_clock(); > mutex_unlock(&clocksource_mutex); > @@ -606,6 +610,13 @@ static int __init clocksource_done_booting(void) > mutex_lock(&clocksource_mutex); > clocksource_select(); > mutex_unlock(&clocksource_mutex); > + > + calibrate_delay(); > +#ifdef CONFIG_SMP > + /* loops_per_jiffy may have been changed. */ > + for_each_online_cpu(cpu) > + smp_store_cpu_info(cpu); > +#endif > return 0; > } > fs_initcall(clocksource_done_booting); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/