[PATCH 09/11] x86, perf: Support sysfs files depending on SMT status
From: Andi Kleen
Date: Fri Jan 15 2016 - 20:13:44 EST
From: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Add a way to show different sysfs events attributes depending on
HyperThreading is on or off. This is difficult to determine
early at boot, so we just do it dynamically when the sysfs
attribute is read.
v2:
Compute HT status only once in CPU online/offline hooks.
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
arch/x86/kernel/cpu/perf_event.c | 35 +++++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/perf_event.h | 15 +++++++++++++++
include/linux/perf_event.h | 7 +++++++
3 files changed, 57 insertions(+)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 1b443db..7379eb9 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1463,6 +1463,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
unsigned int cpu = (long)hcpu;
struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
int i, ret = NOTIFY_OK;
+ bool ht_on;
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
@@ -1482,6 +1483,7 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
kfree(cpuc->kfree_on_online[i]);
cpuc->kfree_on_online[i] = NULL;
}
+ x86_pmu.ht_on = cpumask_weight(topology_sibling_cpumask(cpu)) > 1;
break;
case CPU_DYING:
@@ -1493,6 +1495,15 @@ x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
case CPU_DEAD:
if (x86_pmu.cpu_dead)
x86_pmu.cpu_dead(cpu);
+ /* Recompute HT state for all CPUs on offline */
+ ht_on = false;
+ for_each_online_cpu (cpu) {
+ if (cpumask_weight(topology_sibling_cpumask(cpu)) > 1) {
+ ht_on = true;
+ break;
+ }
+ }
+ x86_pmu.ht_on = ht_on;
break;
default:
@@ -1602,6 +1613,30 @@ ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
return x86_pmu.events_sysfs_show(page, config);
}
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page)
+{
+ struct perf_pmu_events_ht_attr *pmu_attr =
+ container_of(attr, struct perf_pmu_events_ht_attr, attr);
+
+ /*
+ * Report conditional events depending on Hyper-Threading.
+ *
+ * This is overly conservative as usually the HT special
+ * handling is not needed if the other CPU thread is idle.
+ *
+ * Note this does not (cannot) handle the case when thread
+ * siblings are invisible, for example with virtualization
+ * if they are owned by some other guest. The user tool
+ * has to re-read when a thread sibling gets onlined later.
+ */
+
+ return sprintf(page, "%s",
+ x86_pmu.ht_on ?
+ pmu_attr->event_str_ht :
+ pmu_attr->event_str_noht);
+}
+
EVENT_ATTR(cpu-cycles, CPU_CYCLES );
EVENT_ATTR(instructions, INSTRUCTIONS );
EVENT_ATTR(cache-references, CACHE_REFERENCES );
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 7bb61e3..a7e0148 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -616,6 +616,11 @@ struct x86_pmu {
* Intel host/guest support (KVM)
*/
struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
+
+ /*
+ * Hyper Threading on?
+ */
+ bool ht_on;
};
struct x86_perf_task_context {
@@ -661,6 +666,14 @@ static struct perf_pmu_events_attr event_attr_##v = { \
.event_str = str, \
};
+#define EVENT_ATTR_STR_HT(_name, v, noht, ht) \
+static struct perf_pmu_events_ht_attr event_attr_##v = { \
+ .attr = __ATTR(_name, 0444, events_ht_sysfs_show, NULL),\
+ .id = 0, \
+ .event_str_noht = noht, \
+ .event_str_ht = ht, \
+}
+
extern struct x86_pmu x86_pmu __read_mostly;
static inline bool x86_pmu_has_lbr_callstack(void)
@@ -922,6 +935,8 @@ int knc_pmu_init(void);
ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
+ssize_t events_ht_sysfs_show(struct device *dev, struct device_attribute *attr,
+ char *page);
static inline int is_ht_workaround_enabled(void)
{
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f9828a4..ea2d830 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1166,6 +1166,13 @@ struct perf_pmu_events_attr {
const char *event_str;
};
+struct perf_pmu_events_ht_attr {
+ struct device_attribute attr;
+ u64 id;
+ const char *event_str_ht;
+ const char *event_str_noht;
+};
+
ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr,
char *page);
--
2.4.3