From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932333Ab0KVV4N (ORCPT ); Mon, 22 Nov 2010 16:56:13 -0500 Received: from mx1.redhat.com ([209.132.183.28]:64551 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932211Ab0KVV4M (ORCPT ); Mon, 22 Nov 2010 16:56:12 -0500 From: Don Zickus To: Ingo Molnar Cc: Peter Zijlstra , jason.wessel@windriver.com, gorcunov@gmail.com, LKML , Don Zickus Subject: [PATCH] x86, perf, nmi: Disable perf if counters are not accessable Date: Mon, 22 Nov 2010 16:55:23 -0500 Message-Id: <1290462923-30734-1-git-send-email-dzickus@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org In a kvm virt guests, the perf counters are not emulated. Instead they return zero on a rdmsrl. The perf nmi handler uses the fact that crossing a zero means the counter overflowed (for those counters that do not have specific interrupt bits). Therefore on kvm guests, perf will swallow all NMIs thinking the counters overflowed. This causes problems for subsystems like kgdb which needs NMIs to do its magic. This problem was discovered by running kgdb tests. The solution is to write garbage into a perf counter during the initialization and hopefully reading back the same number. On kvm guests, the value will be read back as zero and we disable perf as a result. Reported-by: Jason Wessel Patch-inspired-by: Peter Zijlstra Signed-off-by: Don Zickus --- arch/x86/kernel/cpu/perf_event.c | 19 +++++++++++++++++++ 1 files changed, 19 insertions(+), 0 deletions(-) diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index bbe3c4a..e4c4899 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -381,6 +381,19 @@ static void release_pmc_hardware(void) {} #endif +static bool check_hw_exists(void) +{ + u64 val, val_new; + + val = 0xabcdUL; + (void) checking_wrmsrl(x86_pmu.perfctr, val); + rdmsrl_safe(x86_pmu.perfctr, &val_new); + if (val != val_new) + return false; + + return true; +} + static void reserve_ds_buffers(void); static void release_ds_buffers(void); @@ -1371,6 +1384,12 @@ void __init init_hw_perf_events(void) pmu_check_apic(); + /* sanity check that the hardware exists or is emulated */ + if (!check_hw_exists()) { + pr_cont("Broken PMU hardware detected, software events only.\n"); + return; + } + pr_cont("%s PMU driver.\n", x86_pmu.name); if (x86_pmu.quirks) -- 1.7.3.2