[PATCH v2 1/3] perf/core: store context switch out type into Perf trace

[Alexey Budankov]

Store thread context-switch-out event type into Perf trace as a part of 
PERF_RECORD_SWITCH[_CPU_WIDE] records.

Introduced types of switch-out events assumed to be 
a) preempt: task->state == TASK_RUNNING and b) yield: !preempt;

New yield event type is encoded using special 
PERF_RECORD_MISC_SWITCH_OUT_YIELD bit extending PERF_RECORD_MISC_SWITCH_OUT 
meaning traditional preemption switch out event:

    misc &= PERF_RECORD_MISC_SWITCH_OUT | PERF_RECORD_MISC_SWITCH_OUT_YIELD
	
Signed-off-by: Alexey Budankov <alexey.budankov@xxxxxxxxxxxxxxx>
---
 include/uapi/linux/perf_event.h       | 5 +++++
 kernel/events/core.c                  | 4 +++-
 tools/include/uapi/linux/perf_event.h | 5 +++++
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 912b85b52344..f5dd823d0ff1 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -655,6 +655,11 @@ struct perf_event_mmap_page {
  * perf_event_attr::precise_ip.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Indicates that thread explicitly yielded cpu due to
+ * a call of some synchronization API e.g. futex system call
+ */
+#define PERF_RECORD_MISC_SWITCH_OUT_YIELD	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 74a6e8f12a3c..f15af15af474 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7556,6 +7556,8 @@ static void perf_event_switch(struct task_struct *task,
 			      struct task_struct *next_prev, bool sched_in)
 {
 	struct perf_switch_event switch_event;
+	__u16 switch_type = sched_in ? 0 : PERF_RECORD_MISC_SWITCH_OUT |
+		(task->state == TASK_RUNNING ? 0 : PERF_RECORD_MISC_SWITCH_OUT_YIELD);
 
 	/* N.B. caller checks nr_switch_events != 0 */
 
@@ -7565,7 +7567,7 @@ static void perf_event_switch(struct task_struct *task,
 		.event_id	= {
 			.header = {
 				/* .type */
-				.misc = sched_in ? 0 : PERF_RECORD_MISC_SWITCH_OUT,
+				.misc = switch_type,
 				/* .size */
 			},
 			/* .next_prev_pid */
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 912b85b52344..f5dd823d0ff1 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -655,6 +655,11 @@ struct perf_event_mmap_page {
  * perf_event_attr::precise_ip.
  */
 #define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Indicates that thread explicitly yielded cpu due to
+ * a call of some synchronization API e.g. futex system call
+ */
+#define PERF_RECORD_MISC_SWITCH_OUT_YIELD	(1 << 14)
 /*
  * Reserve the last bit to indicate some extended misc field
  */