Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755228AbaBTJAz (ORCPT ); Thu, 20 Feb 2014 04:00:55 -0500 Received: from mga09.intel.com ([134.134.136.24]:27408 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754397AbaBTJAx (ORCPT ); Thu, 20 Feb 2014 04:00:53 -0500 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.97,511,1389772800"; d="scan'208";a="458684774" Message-ID: <5305C43D.8090206@intel.com> Date: Thu, 20 Feb 2014 17:00:45 +0800 From: "Yan, Zheng" User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.3.0 MIME-Version: 1.0 To: Stephane Eranian CC: LKML , Peter Zijlstra , "mingo@elte.hu" , "ak@linux.intel.com" Subject: Re: [PATCH] perf/x86/uncore: Fix IVT/SNB-EP uncore CBOX NID filter table References: <20140219131018.GA24475@quad> <53059E9D.1030109@intel.com> In-Reply-To: Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/20/2014 04:56 PM, Stephane Eranian wrote: > On Thu, Feb 20, 2014 at 7:20 AM, Yan, Zheng wrote: >> On 02/19/2014 09:10 PM, Stephane Eranian wrote: >>> >>> This patch updates the CBOX PMU filters mapping tables for SNB-EP >>> and IVT (model 45 and 62 respectively). >>> >>> The NID umask always comes in addition to another umask. >>> When set, the NID filter is applied. >> >> Do you means the NID always applies for LLC_LOOKUP no matter what umask is. >> If yes, I think it's better to define filter as SNBEP_CBO_EVENT_EXTRA_REG(0x34, 0xff, 0x6) >> > No. I mean you can add NID umask to any other umask but it cannot be > used by itself. > In other words, LLC_LOOKUP.NID is not allowed but LLC_LOOKUP.DATA_READ.NID is. > > That is what I gathered from the description in the specs. Thanks Reviewed-by: Yan, Zheng > > >> Regards >> Yan, Zheng >> >>> >>> The current mapping tables were missing some code/umask >>> combinations to account for the NID umask. This patch >>> fixes that. >>> >>> Signed-off-by: Stephane Eranian >>> >>> diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c >>> --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c >>> +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c >>> @@ -501,8 +501,11 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = { >>> SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, >>> SNBEP_CBO_PMON_CTL_TID_EN, 0x1), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0x6), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0x6), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0x6), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), >>> @@ -1178,10 +1181,15 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = { >>> SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, >>> SNBEP_CBO_PMON_CTL_TID_EN, 0x1), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x4334, 0xffff, 0xc), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x4534, 0xffff, 0xc), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), >>> - SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), >>> + SNBEP_CBO_EVENT_EXTRA_REG(0x4934, 0xffff, 0xc), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), >>> SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), >>> >> -- 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/