[RFC PATCH 4.1-rt backport] sched: Introduce the 'trace_sched_waking' tracepoint

[Mathieu Desnoyers]

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Mathieu reported that since 317f394160e9 ("sched: Move the second half
of ttwu() to the remote cpu") trace_sched_wakeup() can happen out of
context of the waker.

This is a problem when you want to analyse wakeup paths because it is
now very hard to correlate the wakeup event to whoever issued the
wakeup.

OTOH trace_sched_wakeup() is issued at the point where we set
p->state = TASK_RUNNING, which is right were we hand the task off to
the scheduler, so this is an important point when looking at
scheduling behaviour, up to here its been the wakeup path everything
hereafter is due to scheduler policy.

To bridge this gap, introduce a second tracepoint: trace_sched_waking.
It is guaranteed to be called in the waker context.

[ Ported to linux-4.1.y-rt kernel by Mathieu Desnoyers. Resolved
  conflict: try_to_wake_up_local() does not exist in -rt kernel. Removed
  its instrumentation hunk. ]

Reported-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
CC: Julien Desfossez <jdesfossez@xxxxxxxxxxxx>
CC: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Cc: Francis Giraldeau <francis.giraldeau@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CC: Ingo Molnar <mingo@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/20150609091336.GQ3644@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
---
Julien Desfossez is currently implementing an in-kernel latency tracker
module performing automated latency/deadline analysis, which main target
is the real time kernel.

In order to follow the wakeup chains, we need the sched_waking
tracepoint. This is a backport of this tracepoint to the 4.1-rt kernel.
I'm not sure what is the policy regarding patch backport from mainline
to -rt kernels, hence the RFC.

Thanks,

Mathieu
---
 include/trace/events/sched.h      | 30 +++++++++++++++++++++---------
 kernel/sched/core.c               |  8 +++++---
 kernel/trace/trace_sched_switch.c |  2 +-
 kernel/trace/trace_sched_wakeup.c |  2 +-
 4 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 30fedaf..3b63828 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -55,9 +55,9 @@ TRACE_EVENT(sched_kthread_stop_ret,
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-	TP_PROTO(struct task_struct *p, int success),
+	TP_PROTO(struct task_struct *p),
 
-	TP_ARGS(__perf_task(p), success),
+	TP_ARGS(__perf_task(p)),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -71,25 +71,37 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->success	= success;
+		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
 
-	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
+	TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success, __entry->target_cpu)
+		  __entry->target_cpu)
 );
 
+/*
+ * Tracepoint called when waking a task; this tracepoint is guaranteed to be
+ * called from the waking context.
+ */
+DEFINE_EVENT(sched_wakeup_template, sched_waking,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
+
+/*
+ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
+ * It it not always called from the waking context.
+ */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 /*
  * Tracepoint for waking up a new task:
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
 static inline long __trace_sched_switch_state(struct task_struct *p)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 799b75b..b8b53df 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1558,9 +1558,9 @@ static void
 ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	check_preempt_curr(rq, p, wake_flags);
-	trace_sched_wakeup(p, true);
-
 	p->state = TASK_RUNNING;
+	trace_sched_wakeup(p);
+
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
 		p->sched_class->task_woken(rq, p);
@@ -1784,6 +1784,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (!(wake_flags & WF_LOCK_SLEEPER))
 		p->saved_state = TASK_RUNNING;
 
+	trace_sched_waking(p);
+
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
@@ -2188,7 +2190,7 @@ void wake_up_new_task(struct task_struct *p)
 	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
-	trace_sched_wakeup_new(p, true);
+	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c
index 419ca37..f270088 100644
--- a/kernel/trace/trace_sched_switch.c
+++ b/kernel/trace/trace_sched_switch.c
@@ -26,7 +26,7 @@ probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *n
 }
 
 static void
-probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
+probe_sched_wakeup(void *ignore, struct task_struct *wakee)
 {
 	if (unlikely(!sched_ref))
 		return;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index d6e1003..79a2a5f 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -514,7 +514,7 @@ static void wakeup_reset(struct trace_array *tr)
 }
 
 static void
-probe_wakeup(void *ignore, struct task_struct *p, int success)
+probe_wakeup(void *ignore, struct task_struct *p)
 {
 	struct trace_array_cpu *data;
 	int cpu = smp_processor_id();
-- 
2.1.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/