Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965112Ab1C3VJX (ORCPT ); Wed, 30 Mar 2011 17:09:23 -0400 Received: from mga02.intel.com ([134.134.136.20]:33640 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964977Ab1C3VJR (ORCPT ); Wed, 30 Mar 2011 17:09:17 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.63,270,1299484800"; d="scan'208";a="727133809" From: Andi Kleen References: <20110330203.501921634@firstfloor.org> In-Reply-To: <20110330203.501921634@firstfloor.org> To: anton@samba.org, a.p.zijlstra@chello.nl, ak@linux.intel.com, mingo@elte.hu, gregkh@suse.de, linux-kernel@vger.kernel.org, stable@kernel.org, tim.bird@am.sony.com Subject: [PATCH] [210/275] perf, powerpc: Handle events that raise an exception without overflowing Message-Id: <20110330210734.C95103E1A05@tassilo.jf.intel.com> Date: Wed, 30 Mar 2011 14:07:34 -0700 (PDT) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2938 Lines: 84 2.6.35-longterm review patch. If anyone has any objections, please let me know. ------------------ From: Anton Blanchard commit 0837e3242c73566fc1c0196b4ec61779c25ffc93 upstream. Events on POWER7 can roll back if a speculative event doesn't eventually complete. Unfortunately in some rare cases they will raise a performance monitor exception. We need to catch this to ensure we reset the PMC. In all cases the PMC will be 256 or less cycles from overflow. Signed-off-by: Anton Blanchard Signed-off-by: Peter Zijlstra Signed-off-by: Andi Kleen LKML-Reference: <20110309143842.6c22845e@kryten> Signed-off-by: Ingo Molnar Signed-off-by: Greg Kroah-Hartman --- arch/powerpc/include/asm/reg.h | 1 + arch/powerpc/kernel/perf_event.c | 24 +++++++++++++++++++++++- 2 files changed, 24 insertions(+), 1 deletion(-) Index: linux-2.6.35.y/arch/powerpc/include/asm/reg.h =================================================================== --- linux-2.6.35.y.orig/arch/powerpc/include/asm/reg.h 2011-03-29 22:50:34.616372673 -0700 +++ linux-2.6.35.y/arch/powerpc/include/asm/reg.h 2011-03-29 23:03:02.632232817 -0700 @@ -878,6 +878,7 @@ #define PV_970 0x0039 #define PV_POWER5 0x003A #define PV_POWER5p 0x003B +#define PV_POWER7 0x003F #define PV_970FX 0x003C #define PV_630 0x0040 #define PV_630p 0x0041 Index: linux-2.6.35.y/arch/powerpc/kernel/perf_event.c =================================================================== --- linux-2.6.35.y.orig/arch/powerpc/kernel/perf_event.c 2011-03-29 22:50:34.616372673 -0700 +++ linux-2.6.35.y/arch/powerpc/kernel/perf_event.c 2011-03-29 23:03:02.633232791 -0700 @@ -1230,6 +1230,28 @@ return ip; } +static bool pmc_overflow(unsigned long val) +{ + if ((int)val < 0) + return true; + + /* + * Events on POWER7 can roll back if a speculative event doesn't + * eventually complete. Unfortunately in some rare cases they will + * raise a performance monitor exception. We need to catch this to + * ensure we reset the PMC. In all cases the PMC will be 256 or less + * cycles from overflow. + * + * We only do this if the first pass fails to find any overflowing + * PMCs because a user might set a period of less than 256 and we + * don't want to mistakenly reset them. + */ + if (__is_processor(PV_POWER7) && ((0x80000000 - val) <= 256)) + return true; + + return false; +} + /* * Performance monitor interrupt stuff */ @@ -1277,7 +1299,7 @@ if (is_limited_pmc(i + 1)) continue; val = read_pmc(i + 1); - if ((int)val < 0) + if (pmc_overflow(val)) write_pmc(i + 1, 0); } } -- 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/