[PATCH 23/30] sched/fair: handle tick expiry under lazy preemption

[Ankur Arora <ankur.a.arora@oracle.com>]

The default policy for lazy scheduling is to schedule in exit-to-user,
assuming that would happen within the remaining time quanta of the
task.

However, that runs into the 'hog' problem -- the target task might
be running in the kernel and might not relinquish CPU on its own.

Handle that by upgrading the ignored tif_resched(NR_lazy) bit to
tif_resched(NR_now) at the next tick.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Originally-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/87jzshhexi.ffs@tglx/
Signed-off-by: Ankur Arora <ankur.a.arora@oracle.com>

---
Note:
  Instead of special casing the tick, it might be simpler to always
  do the upgrade on the second resched_curr().

  The theoretical problem with doing that is that the current
  approach deterministically provides a well-defined extra unit of
  time. Going with a second resched_curr() might mean that the
  amount of extra time the task gets depends on the vagaries of
  the incoming resched_curr() (which is fine if it's mostly from
  the tick; not fine if we could get it due to other reasons.)

  Practically, both performed equally well in my tests.

  Thoughts?

 kernel/sched/core.c     | 8 ++++++++
 kernel/sched/deadline.c | 2 +-
 kernel/sched/fair.c     | 2 +-
 kernel/sched/rt.c       | 2 +-
 kernel/sched/sched.h    | 6 ++++++
 5 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index de963e8e2bee..5df59a4548dc 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1038,6 +1038,10 @@ void wake_up_q(struct wake_q_head *head)
  * For PREEMPT_AUTO: schedule idle threads eagerly, allow everything
  * else, whether running in user or kernel context, to finish its time
  * quanta, and mark for rescheduling at the next exit to user.
+ *
+ * Note: to avoid the hog problem, where the user does not relinquish
+ * CPU even after its time quanta has expired, upgrade lazy to eager
+ * on the second tick.
  */
 static resched_t resched_opt_translate(struct task_struct *curr,
 				       enum resched_opt opt)
@@ -1051,6 +1055,10 @@ static resched_t resched_opt_translate(struct task_struct *curr,
 	if (is_idle_task(curr))
 		return NR_now;
 
+	if (opt == RESCHED_TICK &&
+	    unlikely(test_tsk_need_resched(curr, NR_lazy)))
+		return NR_now;
+
 	return NR_lazy;
 }
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b4e68cfc3c3a..b935e634fbf8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1379,7 +1379,7 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
 		}
 
 		if (!is_leftmost(dl_se, &rq->dl))
-			resched_curr(rq);
+			resched_curr_tick(rq);
 	}
 
 	/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 278eebe6656a..92910b721adb 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12621,7 +12621,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 	}
 
 	if (resched)
-		resched_curr(rq);
+		resched_curr_tick(rq);
 
 	if (static_branch_unlikely(&sched_numa_balancing))
 		task_tick_numa(rq, curr);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index c57cc8427a57..1a2f3524d0eb 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1023,7 +1023,7 @@ static void update_curr_rt(struct rq *rq)
 			rt_rq->rt_time += delta_exec;
 			exceeded = sched_rt_runtime_exceeded(rt_rq);
 			if (exceeded)
-				resched_curr(rq);
+				resched_curr_tick(rq);
 			raw_spin_unlock(&rt_rq->rt_runtime_lock);
 			if (exceeded)
 				do_start_rt_bandwidth(sched_rt_bandwidth(rt_rq));
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3600a8673d08..c7e7acab1022 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2465,6 +2465,7 @@ extern void reweight_task(struct task_struct *p, int prio);
 enum resched_opt {
 	RESCHED_DEFAULT,
 	RESCHED_FORCE,
+	RESCHED_TICK,
 };
 
 extern void __resched_curr(struct rq *rq, enum resched_opt opt);
@@ -2474,6 +2475,11 @@ static inline void resched_curr(struct rq *rq)
 	__resched_curr(rq, RESCHED_DEFAULT);
 }
 
+static inline void resched_curr_tick(struct rq *rq)
+{
+	__resched_curr(rq, RESCHED_TICK);
+}
+
 extern void resched_cpu(int cpu);
 
 extern struct rt_bandwidth def_rt_bandwidth;
-- 
2.31.1