perf/x86: Add sysfs entry to freeze counters on SMI

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 counted - for example, to calculate
the cost of an 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 processors.

Also serialize the entire setting so we don't get multiple concurrent
threads trying to update to different values.

Signed-off-by: Kan Liang <Kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Cc: bp@alien8.de
Cc: jolsa@kernel.org
Link: http://lkml.kernel.org/r/1494600673-244667-1-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 63 insertions, 0 deletions

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a6d91d4e37a1..da9047eec7ba 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3160,6 +3160,19 @@ err:
 	return -ENOMEM;
 }
 
+static void flip_smm_bit(void *data)
+{
+	unsigned long set = *(unsigned long *)data;
+
+	if (set > 0) {
+		msr_set_bit(MSR_IA32_DEBUGCTLMSR,
+			    DEBUGCTLMSR_FREEZE_IN_SMM_BIT);
+	} else {
+		msr_clear_bit(MSR_IA32_DEBUGCTLMSR,
+			      DEBUGCTLMSR_FREEZE_IN_SMM_BIT);
+	}
+}
+
 static void intel_pmu_cpu_starting(int cpu)
 {
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
@@ -3174,6 +3187,8 @@ static void intel_pmu_cpu_starting(int cpu)
 
 	cpuc->lbr_sel = NULL;
 
+	flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
+
 	if (!cpuc->shared_regs)
 		return;
 
@@ -3595,6 +3610,52 @@ 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, "%lu\n", x86_pmu.attr_freeze_on_smi);
+}
+
+static DEFINE_MUTEX(freeze_on_smi_mutex);
+
+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;
+
+	mutex_lock(&freeze_on_smi_mutex);
+
+	if (x86_pmu.attr_freeze_on_smi == val)
+		goto done;
+
+	x86_pmu.attr_freeze_on_smi = val;
+
+	get_online_cpus();
+	on_each_cpu(flip_smm_bit, &val, 1);
+	put_online_cpus();
+done:
+	mutex_unlock(&freeze_on_smi_mutex);
+
+	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 +3702,8 @@ __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: