Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758828Ab2HISIk (ORCPT ); Thu, 9 Aug 2012 14:08:40 -0400 Received: from casper.infradead.org ([85.118.1.10]:37206 "EHLO casper.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754668Ab2HISIj convert rfc822-to-8bit (ORCPT ); Thu, 9 Aug 2012 14:08:39 -0400 Message-ID: <1344535707.20277.20.camel@twins> Subject: Re: [BUG] perf: sharing of cpuctx between core and ibs PMU causes problems From: Peter Zijlstra To: Stephane Eranian Cc: "Yan, Zheng" , LKML , Robert Richter , mingo@elte.hu Date: Thu, 09 Aug 2012 20:08:27 +0200 In-Reply-To: References: <50235ED0.5010107@intel.com> Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT X-Mailer: Evolution 3.2.2- Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 850 Lines: 21 On Thu, 2012-08-09 at 16:05 +0200, Stephane Eranian wrote: > > uncore PMU does not have this issue because uncore_pmu->task_ctx_nr > > is 'perf_invalid_context'. find_pmu_context() always return NULL in > > that case. > > > Yes, I think IBS should do the same and that should fix the problem > there too. Will try that. I'm afraid not, per-task profiling with uncore doesn't really make that much sense. For IBS it does. We can't share a context with different PMUs, that'll totally mess up the event scheduling. We'll have to grow perf_event_task_context with an extra context and have IBS use that. -- 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/