[PATCH v2 29/35] sched: handle preempt=voluntary under PREEMPT_AUTO

[Ankur Arora]

The default preemption policy for voluntary preemption under
PREEMPT_AUTO is to schedule eagerly for tasks of higher scheduling
class, and lazily for well-behaved, non-idle tasks.

This is the same policy as preempt=none, with an eager handling of
higher priority scheduling classes.

Comparing a cyclictest workload with a background kernel load of
'stress-ng --mmap', shows that both the average and the maximum
latencies improve:

 # stress-ng --mmap 0 &
 # cyclictest --mlockall --smp --priority=80 --interval=200 --distance=0 -q -D 300

                                     Min     (  %stdev )    Act     (  %stdev )   Avg     (  %stdev )   Max      (  %stdev )

  PREEMPT_AUTO, preempt=voluntary    1.73  ( +-  25.43% )   62.16 ( +- 303.39% )  14.92 ( +-  17.96% )  2778.22 ( +-  15.04% )
  PREEMPT_DYNAMIC, preempt=voluntary 1.83  ( +-  20.76% )  253.45 ( +- 233.21% )  18.70 ( +-  15.88% )  2992.45 ( +-  15.95% )

The table above shows the aggregated latencies across all CPUs.

Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Ziljstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Originally-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/lkml/87jzshhexi.ffs@tglx/
Signed-off-by: Ankur Arora <ankur.a.arora@xxxxxxxxxx>
---
 kernel/sched/core.c  | 12 ++++++++----
 kernel/sched/sched.h |  6 ++++++
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c25cccc09b65..2bc3ae21a9d0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1052,6 +1052,9 @@ static resched_t resched_opt_translate(struct task_struct *curr,
 	if (preempt_model_preemptible())
 		return RESCHED_NOW;
 
+	if (preempt_model_voluntary() && opt == RESCHED_PRIORITY)
+		return RESCHED_NOW;
+
 	if (is_idle_task(curr))
 		return RESCHED_NOW;
 
@@ -2289,7 +2292,7 @@ void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
 	if (p->sched_class == rq->curr->sched_class)
 		rq->curr->sched_class->wakeup_preempt(rq, p, flags);
 	else if (sched_class_above(p->sched_class, rq->curr->sched_class))
-		resched_curr(rq);
+		resched_curr_priority(rq);
 
 	/*
 	 * A queue event has occurred, and we're going to schedule.  In
@@ -8989,11 +8992,11 @@ static void __sched_dynamic_update(int mode)
 	case preempt_dynamic_none:
 		if (mode != preempt_dynamic_mode)
 			pr_info("%s: none\n", PREEMPT_MODE);
-		preempt_dynamic_mode = mode;
 		break;
 
 	case preempt_dynamic_voluntary:
-		preempt_dynamic_mode = preempt_dynamic_undefined;
+		if (mode != preempt_dynamic_mode)
+			pr_info("%s: voluntary\n", PREEMPT_MODE);
 		break;
 
 	case preempt_dynamic_full:
@@ -9003,9 +9006,10 @@ static void __sched_dynamic_update(int mode)
 
 		if (mode != preempt_dynamic_mode)
 			pr_info("%s: full\n", PREEMPT_MODE);
-		preempt_dynamic_mode = mode;
 		break;
 	}
+
+	preempt_dynamic_mode = mode;
 }
 
 #endif /* CONFIG_PREEMPT_AUTO */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 107c5fc2b7bb..ee8e99a9a677 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2468,6 +2468,7 @@ enum resched_opt {
 	RESCHED_DEFAULT,
 	RESCHED_FORCE,
 	RESCHED_TICK,
+	RESCHED_PRIORITY,
 };
 
 extern void __resched_curr(struct rq *rq, enum resched_opt opt);
@@ -2482,6 +2483,11 @@ static inline void resched_curr_tick(struct rq *rq)
 	__resched_curr(rq, RESCHED_TICK);
 }
 
+static inline void resched_curr_priority(struct rq *rq)
+{
+	__resched_curr(rq, RESCHED_PRIORITY);
+}
+
 extern void resched_cpu(int cpu);
 
 extern struct rt_bandwidth def_rt_bandwidth;
-- 
2.31.1