perf_counter: PERF_RECORD_TIME

By popular request, provide means to log a timestamp along with the
counter overflow event.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
LKML-Reference: <20090406094518.024173282@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

include/linux/perf_counter.h

@@ -102,6 +102,7 @@ enum perf_counter_record_format {
 	PERF_RECORD_TID		= 1U << 1,
 	PERF_RECORD_GROUP	= 1U << 2,
 	PERF_RECORD_CALLCHAIN	= 1U << 3,
+	PERF_RECORD_TIME	= 1U << 4,
 };
 
 /*
@@ -221,6 +222,7 @@ enum perf_event_type {
 	__PERF_EVENT_TID		= PERF_RECORD_TID,
 	__PERF_EVENT_GROUP		= PERF_RECORD_GROUP,
 	__PERF_EVENT_CALLCHAIN		= PERF_RECORD_CALLCHAIN,
+	__PERF_EVENT_TIME		= PERF_RECORD_TIME,
 };
 
 #ifdef __KERNEL__

kernel/perf_counter.c

@@ -1826,6 +1826,7 @@ static void perf_counter_output(struct perf_counter *counter,
 	} group_entry;
 	struct perf_callchain_entry *callchain = NULL;
 	int callchain_size = 0;
+	u64 time;
 
 	header.type = PERF_EVENT_COUNTER_OVERFLOW;
 	header.size = sizeof(header);
@@ -1862,6 +1863,16 @@ static void perf_counter_output(struct perf_counter *counter,
 		}
 	}
 
+	if (record_type & PERF_RECORD_TIME) {
+		/*
+		 * Maybe do better on x86 and provide cpu_clock_nmi()
+		 */
+		time = sched_clock();
+
+		header.type |= __PERF_EVENT_TIME;
+		header.size += sizeof(u64);
+	}
+
 	ret = perf_output_begin(&handle, counter, header.size, nmi);
 	if (ret)
 		return;
@@ -1895,6 +1906,9 @@ static void perf_counter_output(struct perf_counter *counter,
 	if (callchain)
 		perf_output_copy(&handle, callchain, callchain_size);
 
+	if (record_type & PERF_RECORD_TIME)
+		perf_output_put(&handle, time);
+
 	perf_output_end(&handle);
 }