Add the following tracepoints:
* sched_set_need_resched(tsk, cpu, tif)
Called when a task is set the need resched [lazy] flag
* sched_switch_vain(preempt, tsk, tsk_state)
Called when a task is selected again during __schedule
i.e. prev == next == tsk : no real context switch
These tracepoints are useful to describe the Linux task model and are
adapted from the patches by Daniel Bristot de Oliveira
(https://bristot.me/linux-task-model/).
Signed-off-by: Gabriele Monaco <gmon...@redhat.com>
---
include/linux/sched.h | 7 ++++++-
include/trace/events/sched.h | 8 ++++++++
kernel/sched/core.c | 9 +++++++++
3 files changed, 23 insertions(+), 1 deletion(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index f96ac19828934..7bcd37493ab07 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -340,9 +340,11 @@ extern void io_schedule_finish(int token);
extern long io_schedule_timeout(long timeout);
extern void io_schedule(void);
-/* wrapper function to trace from this header file */
+/* wrapper functions to trace from this header file */
DECLARE_TRACEPOINT(sched_set_state_tp);
extern void __trace_set_current_state(int state_value);
+DECLARE_TRACEPOINT(sched_set_need_resched_tp);
+extern void __trace_set_need_resched(struct task_struct *curr, int tif);
/**
* struct prev_cputime - snapshot of system and user cputime
@@ -2064,6 +2066,9 @@ static inline int test_tsk_thread_flag(struct task_struct
*tsk, int flag)
static inline void set_tsk_need_resched(struct task_struct *tsk)
{
+ if (tracepoint_enabled(sched_set_need_resched_tp) &&
+ !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED))
+ __trace_set_need_resched(tsk, TIF_NEED_RESCHED);
set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
}
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8994e97d86c13..77bbcce407cb4 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -835,6 +835,14 @@ DECLARE_TRACE_CONDITION(sched_set_state_tp,
TP_ARGS(tsk, state),
TP_CONDITION(!!(tsk->__state) != !!state));
+DECLARE_TRACE(sched_set_need_resched_tp,
+ TP_PROTO(struct task_struct *tsk, int cpu, int tif),
+ TP_ARGS(tsk, cpu, tif));
+
+DECLARE_TRACE(sched_switch_vain_tp,
+ TP_PROTO(bool preempt, struct task_struct *tsk, unsigned int
prev_state),
+ TP_ARGS(preempt, tsk, prev_state));
+
#endif /* _TRACE_SCHED_H */
/* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cfaca3040b2f8..f2f79236d5811 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1109,6 +1109,7 @@ static void __resched_curr(struct rq *rq, int tif)
cpu = cpu_of(rq);
+ trace_sched_set_need_resched_tp(curr, cpu, tif);
if (cpu == smp_processor_id()) {
set_ti_thread_flag(cti, tif);
if (tif == TIF_NEED_RESCHED)
@@ -1124,6 +1125,13 @@ static void __resched_curr(struct rq *rq, int tif)
}
}
+#ifdef CONFIG_SMP
+void __trace_set_need_resched(struct task_struct *curr, int tif)
+{
+ trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif);
+}
+#endif
+
void resched_curr(struct rq *rq)
{
__resched_curr(rq, TIF_NEED_RESCHED);
@@ -6767,6 +6775,7 @@ static void __sched notrace __schedule(int sched_mode)
rq = context_switch(rq, prev, next, &rf);
} else {
rq_unpin_lock(rq, &rf);
+ trace_sched_switch_vain_tp(preempt, prev, prev_state);
__balance_callbacks(rq);
raw_spin_rq_unlock_irq(rq);
}
--
2.49.0
