perf/core: Store context switch out type in PERF_RECORD_SWITCH[_CPU_WIDE]

Store preempting context switch out event into Perf trace as a part of
PERF_RECORD_SWITCH[_CPU_WIDE] record.

Percentage of preempting and non-preempting context switches help
understanding the nature of workloads (CPU or IO bound) that are running
on a machine;

The event is treated as preemption one when task->state value of the
thread being switched out is TASK_RUNNING. Event type encoding is
implemented using PERF_RECORD_MISC_SWITCH_OUT_PREEMPT bit;

Signed-off-by: Alexey Budankov <[email protected]>
Acked-by: Peter Zijlstra <[email protected]>
Tested-by: Arnaldo Carvalho de Melo <[email protected]>
Cc: Alexander Shishkin <[email protected]>
Cc: Andi Kleen <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: Namhyung Kim <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Arnaldo Carvalho de Melo <[email protected]>

Author: Alexey Budankov

include/uapi/linux/perf_event.h

@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ *   PERF_RECORD_MISC_EXACT_IP           - PERF_RECORD_SAMPLE of precise events
+ *   PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ *   Indicates that the content of PERF_SAMPLE_IP points to
+ *   the actual instruction that triggered the event. See also
+ *   perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ *   Indicates that thread was preempted in TASK_RUNNING state.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */

kernel/events/core.c

@@ -7587,6 +7587,10 @@ static void perf_event_switch(struct task_struct *task,
 		},
 	};
 
+	if (!sched_in && task->state == TASK_RUNNING)
+		switch_event.event_id.header.misc |=
+				PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
+
 	perf_iterate_sb(perf_event_switch_output,
 		       &switch_event,
 		       NULL);

tools/include/uapi/linux/perf_event.h

@@ -650,11 +650,23 @@ struct perf_event_mmap_page {
 #define PERF_RECORD_MISC_COMM_EXEC		(1 << 13)
 #define PERF_RECORD_MISC_SWITCH_OUT		(1 << 13)
 /*
- * Indicates that the content of PERF_SAMPLE_IP points to
- * the actual instruction that triggered the event. See also
- * perf_event_attr::precise_ip.
+ * These PERF_RECORD_MISC_* flags below are safely reused
+ * for the following events:
+ *
+ *   PERF_RECORD_MISC_EXACT_IP           - PERF_RECORD_SAMPLE of precise events
+ *   PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ *
+ *
+ * PERF_RECORD_MISC_EXACT_IP:
+ *   Indicates that the content of PERF_SAMPLE_IP points to
+ *   the actual instruction that triggered the event. See also
+ *   perf_event_attr::precise_ip.
+ *
+ * PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
+ *   Indicates that thread was preempted in TASK_RUNNING state.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */