From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757554Ab0HaPUO (ORCPT ); Tue, 31 Aug 2010 11:20:14 -0400 Received: from arkanian.console-pimps.org ([212.110.184.194]:42860 "EHLO arkanian.console-pimps.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757541Ab0HaPUN (ORCPT ); Tue, 31 Aug 2010 11:20:13 -0400 Date: Tue, 31 Aug 2010 16:20:12 +0100 From: Matt Fleming To: Frederic Weisbecker Cc: Peter Zijlstra , Zhang Rui , linux-kernel@vger.kernel.org, Ingo Molnar , Robert Richter , Lin Ming , Paul Mackerras , Arnaldo Carvalho de Melo , Don Zickus , Cyrill Gorcunov , Len Brown , Matthew Garrett Subject: Re: [RFC][PATCH 1/5] perf: Check if we should exclude idle thread in perf_exclude_event() Message-ID: <20100831152012.GC27532@console-pimps.org> References: <72c0ed93ff0b24365cc4d0a40e24efa3be3fe3df.1283123521.git.matt@console-pimps.org> <20100831145405.GB5259@nowhere> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20100831145405.GB5259@nowhere> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Aug 31, 2010 at 04:54:07PM +0200, Frederic Weisbecker wrote: > On Mon, Aug 30, 2010 at 01:13:43PM +0100, Matt Fleming wrote: > > Don't open code the event check for excluding the idle thread. Instead > > include the check in perf_exclude_event(). > > > > Signed-off-by: Matt Fleming > > --- > > kernel/perf_event.c | 8 +++++--- > > 1 files changed, 5 insertions(+), 3 deletions(-) > > > > diff --git a/kernel/perf_event.c b/kernel/perf_event.c > > index 0d38f27..16b0476 100644 > > --- a/kernel/perf_event.c > > +++ b/kernel/perf_event.c > > @@ -4310,6 +4310,9 @@ static int perf_exclude_event(struct perf_event *event, > > > > if (event->attr.exclude_kernel && !user_mode(regs)) > > return 1; > > + > > + if (event->attr.exclude_idle && current->pid == 0) > > + return 1; > > > > Right. > > But one of the problems people have reported is that they can miss > interrupts samples if they happen in idle. Hence we have decided > that exclude_idle should exclude events that happen in idle process > context but not in interrupts interrupting idle. > > So adding an in_interrupt() check would perhaps be better. > > I plan to do this exclusion using the per context exclusion, which is > a patchset I have in queue. But until then, having this patch is better. > > > > > } > > > > return 0; > > @@ -4512,9 +4515,8 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) > > regs = get_irq_regs(); > > > > if (regs && !perf_exclude_event(event, regs)) { > > - if (!(event->attr.exclude_idle && current->pid == 0)) > > - if (perf_event_overflow(event, 0, &data, regs)) > > - ret = HRTIMER_NORESTART; > > + if (perf_event_overflow(event, 0, &data, regs)) > > + ret = HRTIMER_NORESTART; > > > > But yeah if we add an in_interrupt() check in perf_exclude_event(), it > won't work here. This one needs to check if irqs are nesting :) > > Bah, checking we interrupted softirqs is probably enough. I guess we > don't care about nesting hardirqs. This patch isn't really worth it on its own, I only grouped the idle check into perf_exclude_event() because patch 3/5 introduced a new caller. As you've said, the semantics at the various callsites are quite complex. It's probably best to wait for your patchset :)