[PATCH 1/3] perf/x86: add sysfs entry to freeze counter on SMI

[kan . liang]

From: Kan Liang <Kan.liang@xxxxxxxxx>

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 <Kan.liang@xxxxxxxxx>
---
 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 |  1 +
 4 files changed, 62 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..a99a4ea 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3595,6 +3595,52 @@ 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;
+	u64 debugctlmsr;
+	ssize_t ret;
+	int cpu;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val > 1)
+		return -EINVAL;
+
+	if (x86_pmu.attr_freeze_on_smi == val)
+		return count;
+
+	for_each_possible_cpu(cpu) {
+		rdmsrl_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, &debugctlmsr);
+		if (val)
+			wrmsrl_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, debugctlmsr | DEBUGCTLMSR_FREEZE_WHILE_SMM);
+		else
+			wrmsrl_on_cpu(cpu, MSR_IA32_DEBUGCTLMSR, debugctlmsr & ~DEBUGCTLMSR_FREEZE_WHILE_SMM);
+	}
+
+	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..26c861f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -134,6 +134,7 @@
 #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	(1UL << 14)
 
 #define MSR_PEBS_FRONTEND		0x000003f7
 
-- 
2.7.4