sched: Introduce the 'trace_sched_waking' tracepoint

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.

Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Francis Giraldeau <francis.giraldeau@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150609091336.GQ3644@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

4 files changed, 30 insertions, 14 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index d57a575fe31f..539d6bc3216a 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 48be7dc3d497..fa5826cc612f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1654,9 +1654,9 @@ 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) {
                 /*
@@ -1874,6 +1874,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
         if (!(p->state & state))
                 goto out;
 
+        trace_sched_waking(p);
+
         success = 1; /* we're going to change ->state */
         cpu = task_cpu(p);
 
@@ -1949,6 +1951,8 @@ static void try_to_wake_up_local(struct task_struct *p)
         if (!(p->state & TASK_NORMAL))
                 goto out;
 
+        trace_sched_waking(p);
+
         if (!task_on_rq_queued(p))
                 ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
@@ -2307,7 +2311,7 @@ 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 419ca37e72c9..f270088e9929 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 9b33dd117f3f..12cbe77b4136 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();