[PATCH 08/10] x86, perf: Support sysfs files depending on SMT status

[Andi Kleen]

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.

Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 arch/x86/kernel/cpu/perf_event.c | 34 ++++++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/perf_event.h | 10 ++++++++++
 include/linux/perf_event.h       |  7 +++++++
 3 files changed, 51 insertions(+)

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 9dfbba5..976686f 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1590,6 +1590,40 @@ 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);
+	bool ht_on = false;
+	int cpu;
+
+	/*
+	 * Report conditional events depending on Hyper-Threading.
+	 *
+	 * Check all online CPUs if any have a thread sibling,
+	 * as perf may measure any of them.
+	 *
+	 * 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.
+	 */
+	for_each_online_cpu (cpu) {
+		ht_on = cpumask_weight(topology_sibling_cpumask(cpu)) > 1;
+		if (ht_on)
+			break;
+	}
+
+	return sprintf(page, "%s",
+			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 799e6bd..ce87cd6 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -660,6 +660,14 @@ 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)
@@ -919,6 +927,8 @@ 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

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/