Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752940AbdC0QCz (ORCPT ); Mon, 27 Mar 2017 12:02:55 -0400 Received: from mga03.intel.com ([134.134.136.65]:64346 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752318AbdC0QCp (ORCPT ); Mon, 27 Mar 2017 12:02:45 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.36,232,1486454400"; d="scan'208";a="81480678" From: kan.liang@intel.com To: peterz@infradead.org, tglx@linutronix.de, mingo@redhat.com, linux-kernel@vger.kernel.org Cc: acme@kernel.org, eranian@google.com, jolsa@kernel.org, ak@linux.intel.com, Kan Liang Subject: [PATCH V2 2/2] perf/x86: add sysfs entry to freeze counter on SMI Date: Mon, 27 Mar 2017 08:47:38 -0700 Message-Id: <1490629658-4308-3-git-send-email-kan.liang@intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1490629658-4308-1-git-send-email-kan.liang@intel.com> References: <1490629658-4308-1-git-send-email-kan.liang@intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4778 Lines: 155 From: Kan Liang Currently, the SMIs are visible to all performance counters. Because many users want to measure everything including SMIs. But in some cases, the SMI cycles should not be count. For example, to calculate the cost of SMI itself. So a knob is needed. When setting FREEZE_WHILE_SMM bit in IA32_DEBUGCTL, all performance counters will be effected. There is no way to do per-counter freeze on SMI. So it should not use the per-event interface (e.g. ioctl or event attribute) to set FREEZE_WHILE_SMM bit. Adds sysfs entry /sys/device/cpu/freeze_on_smi to set FREEZE_WHILE_SMM bit in IA32_DEBUGCTL. When set, freezes perfmon and trace messages while in SMM. Value has to be 0 or 1. It will be applied to all possible cpus. Signed-off-by: Kan Liang --- arch/x86/events/core.c | 10 +++++++++ arch/x86/events/intel/core.c | 48 ++++++++++++++++++++++++++++++++++++++++ arch/x86/events/perf_event.h | 3 +++ arch/x86/include/asm/msr-index.h | 2 ++ 4 files changed, 63 insertions(+) diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 349d4d1..c16fb50 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1750,6 +1750,8 @@ ssize_t x86_event_sysfs_show(char *page, u64 config, u64 event) return ret; } +static struct attribute_group x86_pmu_attr_group; + static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -1813,6 +1815,14 @@ static int __init init_hw_perf_events(void) x86_pmu_events_group.attrs = tmp; } + if (x86_pmu.attrs) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_attr_group.attrs, x86_pmu.attrs); + if (!WARN_ON(!tmp)) + x86_pmu_attr_group.attrs = tmp; + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 4244bed..ecb321e 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3174,6 +3174,11 @@ static void intel_pmu_cpu_starting(int cpu) cpuc->lbr_sel = NULL; + if (x86_pmu.attr_freeze_on_smi) + msr_set_bit_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_FREEZE_WHILE_SMM_BIT); + else + msr_clear_bit_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_FREEZE_WHILE_SMM_BIT); + if (!cpuc->shared_regs) return; @@ -3595,6 +3600,47 @@ static struct attribute *hsw_events_attrs[] = { NULL }; +static ssize_t freeze_on_smi_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "%d\n", x86_pmu.attr_freeze_on_smi); +} + +static ssize_t freeze_on_smi_store(struct device *cdev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + unsigned long val; + ssize_t ret; + + ret = kstrtoul(buf, 0, &val); + if (ret) + return ret; + + if (val > 1) + return -EINVAL; + + if (x86_pmu.attr_freeze_on_smi == val) + return count; + + if (val) + msr_set_bit_on_cpus(cpu_possible_mask, MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_FREEZE_WHILE_SMM_BIT); + else + msr_clear_bit_on_cpus(cpu_possible_mask, MSR_IA32_DEBUGCTLMSR, DEBUGCTLMSR_FREEZE_WHILE_SMM_BIT); + + x86_pmu.attr_freeze_on_smi = val; + + return count; +} + +static DEVICE_ATTR_RW(freeze_on_smi); + +static struct attribute *intel_pmu_attrs[] = { + &dev_attr_freeze_on_smi.attr, + NULL, +}; + __init int intel_pmu_init(void) { union cpuid10_edx edx; @@ -3641,6 +3687,8 @@ __init int intel_pmu_init(void) x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters); + + x86_pmu.attrs = intel_pmu_attrs; /* * Quirk: v2 perfmon does not report fixed-purpose events, so * assume at least 3 events, when not running in a hypervisor: diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index bcbb1d2..110cb9b0 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -561,6 +561,9 @@ struct x86_pmu { ssize_t (*events_sysfs_show)(char *page, u64 config); struct attribute **cpu_events; + int attr_freeze_on_smi; + struct attribute **attrs; + /* * CPU Hotplug hooks */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d8b5f8a..bdb00fa 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -134,6 +134,8 @@ #define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) #define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define DEBUGCTLMSR_FREEZE_WHILE_SMM_BIT 14 +#define DEBUGCTLMSR_FREEZE_WHILE_SMM (1UL << DEBUGCTLMSR_FREEZE_WHILE_SMM_BIT) #define MSR_PEBS_FRONTEND 0x000003f7 -- 2.7.4