[PATCH 01/14] perf/x86: Introduce PERF_RECORD_OVERHEAD

[kan . liang]

From: Kan Liang <kan.liang@xxxxxxxxx>

A new perf record is introduced to export perf overhead information to
userspace. So we can measure the overhead of sampling directly.

To output the overhead information, it takes advantage of the existing
event log mechanism. But the overhead information is the system
overhead, not per-event overhead.

Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
---
 include/linux/perf_event.h      |  4 ++++
 include/uapi/linux/perf_event.h | 29 +++++++++++++++++++++++++++
 kernel/events/core.c            | 43 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 76 insertions(+)

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 4741ecd..3a530a7 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -998,6 +998,10 @@ perf_event__output_id_sample(struct perf_event *event,
 extern void
 perf_log_lost_samples(struct perf_event *event, u64 lost);
 
+extern void
+perf_log_overhead(struct perf_event *event, u32 type,
+		  struct perf_overhead_entry *entry);
+
 static inline bool is_sampling_event(struct perf_event *event)
 {
 	return event->attr.sample_period != 0;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index c66a485..ae571be 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -862,6 +862,17 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_SWITCH_CPU_WIDE		= 15,
 
+	/*
+	 * Records perf overhead
+	 * struct {
+	 * 	struct perf_event_header 	header;
+	 * 	u32				type;
+	 * 	struct perf_overhead_entry	entry;
+	 * 	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_OVERHEAD			= 16,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -980,4 +991,22 @@ struct perf_branch_entry {
 		reserved:44;
 };
 
+enum perf_record_overhead_type {
+	PERF_OVERHEAD_MAX,
+};
+
+/*
+ * single overhead record layout:
+ *
+ * 	 cpu: The cpu which overhead occues
+ * 	  nr: Times of overhead happens.
+ * 	      E.g. for NMI, nr == times of NMI handler are called.
+ * 	time: Total overhead cost(ns)
+ */
+struct perf_overhead_entry {
+	__u32	cpu;
+	__u64	nr;
+	__u64	time;
+};
+
 #endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index ff230bb..590c399 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7037,6 +7037,49 @@ static void perf_log_itrace_start(struct perf_event *event)
 	perf_output_end(&handle);
 }
 
+
+/*
+ * Record overhead logging
+ *
+ * The overhead logged here is the system overhead, not per-event overhead.
+ * This function only take advantage of the existing event log mechanism
+ * to log the overhead record.
+ *
+ */
+void perf_log_overhead(struct perf_event *event, u32 type,
+		       struct perf_overhead_entry *entry)
+{
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	struct {
+		struct perf_event_header	header;
+		u32				type;
+		struct perf_overhead_entry	overhead;
+	} overhead_event = {
+		.header = {
+			.type = PERF_RECORD_OVERHEAD,
+			.misc = 0,
+			.size = sizeof(overhead_event),
+		},
+	};
+	overhead_event.type = type;
+	memcpy(&overhead_event.overhead, entry, sizeof(overhead_event.overhead));
+
+	perf_event_header__init_id(&overhead_event.header, &sample, event);
+	ret = perf_output_begin(&handle, event, overhead_event.header.size);
+
+	if (ret)
+		return;
+
+	perf_output_put(&handle, overhead_event);
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+	memset(entry, 0, sizeof(*entry));
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
-- 
2.5.5