[PATCH v2] sched: introduce sched_switch_post trace event

[Cong Wang <xiyou.wangcong@gmail.com>]

Currently we only have one sched_switch trace event
for task switching, which is generated very early during
task switch. When we try to monitor per-container perf
events, this is not what we expect.

For example, we have a process A which is in the cgroup
we monitor, and process B which isn't, when kernel switches
from B to A, the sched_switch event is not recorded for this
cgroup since it belongs to B (current process is still B
util we finish the switch), but we require this event to
signal that process A in this cgroup gets scheduled. This is
crucial for calculating schedule latency (like `perf sched`).

Ideally, we need to split the sched_switch event into two:
sched_in event before we perform the switch, and sched_out
event after we perform the switch. However, for compatibility,
we can not change the sched_switch event. So before we have
trace event alias, we can just reuse sched_switch and introduce
sched_switch_post event instead.

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Cong Wang <cwang@twopensource.com>
---
 include/trace/events/sched.h | 43 ++++++++++++++++++++++++++++++++++++++++++-
 kernel/sched/core.c          |  1 +
 2 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index d57a575..4bc7db5 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -112,7 +112,9 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 #endif /* CREATE_TRACE_POINTS */
 
 /*
- * Tracepoint for task switches, performed by the scheduler:
+ * Tracepoints for task switches, performed by the scheduler:
+ * sched_switch is performed before task switch,
+ * sched_switch_post is performed after task switch.
  */
 TRACE_EVENT(sched_switch,
 
@@ -153,6 +155,45 @@ TRACE_EVENT(sched_switch,
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
 
+TRACE_EVENT(sched_switch_post,
+
+	TP_PROTO(struct task_struct *prev,
+		 struct task_struct *curr),
+
+	TP_ARGS(prev, curr),
+
+	TP_STRUCT__entry(
+		__array(	char,	prev_comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	prev_pid			)
+		__field(	int,	prev_prio			)
+		__field(	long,	prev_state			)
+		__array(	char,	curr_comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	curr_pid			)
+		__field(	int,	curr_prio			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->curr_comm, curr->comm, TASK_COMM_LEN);
+		__entry->prev_pid	= prev->pid;
+		__entry->prev_prio	= prev->prio;
+		__entry->prev_state	= __trace_sched_switch_state(prev);
+		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
+		__entry->curr_pid	= curr->pid;
+		__entry->curr_prio	= curr->prio;
+	),
+
+	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> curr_comm=%s curr_pid=%d curr_prio=%d",
+		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+		__entry->prev_state & (TASK_STATE_MAX-1) ?
+		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
+				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
+				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
+				{ 128, "K" }, { 256, "W" }, { 512, "P" },
+				{ 1024, "N" }) : "R",
+		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
+		__entry->curr_comm, __entry->curr_pid, __entry->curr_prio)
+);
+
 /*
  * Tracepoint for a task being migrated:
  */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78b4bad10..3c74cf4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2490,6 +2490,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	}
 
 	tick_nohz_task_switch(current);
+	trace_sched_switch_post(prev, current);
 	return rq;
 }
 
-- 
1.8.3.1