[RFC v3 3/6] Fix the update of the total -deadline utilization

[Luca Abeni]

Now that the inactive timer can be armed to fire at the 0-lag time,
it is possible to use inactive_task_timer() to update the total
-deadline utilization (dl_b->total_bw) at the correct time, fixing
dl_overflow() and __setparam_dl().

Signed-off-by: Luca Abeni <luca.abeni@xxxxxxxx>
---
 kernel/sched/core.c     | 36 ++++++++++++------------------------
 kernel/sched/deadline.c | 34 +++++++++++++++++++++++++---------
 2 files changed, 37 insertions(+), 33 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 664c618..337a5f0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2507,9 +2507,6 @@ static inline int dl_bw_cpus(int i)
  * allocated bandwidth to reflect the new situation.
  *
  * This function is called while holding p's rq->lock.
- *
- * XXX we should delay bw change until the task's 0-lag point, see
- * __setparam_dl().
  */
 static int dl_overflow(struct task_struct *p, int policy,
 		       const struct sched_attr *attr)
@@ -2538,11 +2535,22 @@ static int dl_overflow(struct task_struct *p, int policy,
 		err = 0;
 	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
 		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		/*
+		 * XXX this is slightly incorrect: when the task
+		 * utilization decreases, we should delay the total
+		 * utilization change until the task's 0-lag point.
+		 * But this would require to set the task's "inactive
+		 * timer" when the task is not inactive.
+		 */
 		__dl_clear(dl_b, p->dl.dl_bw);
 		__dl_add(dl_b, new_bw);
 		err = 0;
 	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
-		__dl_clear(dl_b, p->dl.dl_bw);
+		/*
+		 * Do not decrease the total deadline utilization here,
+		 * switched_from_dl() will take care to do it at the correct
+		 * (0-lag) time.
+		 */
 		err = 0;
 	}
 	raw_spin_unlock(&dl_b->lock);
@@ -3912,26 +3920,6 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
 	dl_se->flags = attr->sched_flags;
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-
-	/*
-	 * Changing the parameters of a task is 'tricky' and we're not doing
-	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
-	 *
-	 * What we SHOULD do is delay the bandwidth release until the 0-lag
-	 * point. This would include retaining the task_struct until that time
-	 * and change dl_overflow() to not immediately decrement the current
-	 * amount.
-	 *
-	 * Instead we retain the current runtime/deadline and let the new
-	 * parameters take effect after the current reservation period lapses.
-	 * This is safe (albeit pessimistic) because the 0-lag point is always
-	 * before the current scheduling deadline.
-	 *
-	 * We can still have temporary overloads because we do not delay the
-	 * change in bandwidth until that time; so admission control is
-	 * not on the safe side. It does however guarantee tasks will never
-	 * consume more than promised.
-	 */
 }
 
 /*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 80d1541..4d3545b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -91,8 +91,14 @@ static void task_go_inactive(struct task_struct *p)
 	 */
 	if (zerolag_time < 0) {
 		sub_running_bw(dl_se, dl_rq);
-		if (!dl_task(p))
+		if (!dl_task(p)) {
+			struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+			raw_spin_lock(&dl_b->lock);
+			__dl_clear(dl_b, p->dl.dl_bw);
 			__dl_clear_params(p);
+			raw_spin_unlock(&dl_b->lock);
+		}
 
 		return;
 	}
@@ -856,8 +862,13 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 
 	rq = task_rq_lock(p, &rf);
 
-	if (!dl_task(p)) {
+	if (!dl_task(p) || p->state == TASK_DEAD) {
+		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+		raw_spin_lock(&dl_b->lock);
+		__dl_clear(dl_b, p->dl.dl_bw);
 		__dl_clear_params(p);
+		raw_spin_unlock(&dl_b->lock);
 
 		goto unlock;
 	}
@@ -1330,16 +1341,21 @@ static void task_fork_dl(struct task_struct *p)
 
 static void task_dead_dl(struct task_struct *p)
 {
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-
 	/*
 	 * Since we are TASK_DEAD we won't slip out of the domain!
 	 */
-	raw_spin_lock_irq(&dl_b->lock);
-	/* XXX we should retain the bw until 0-lag */
-	dl_b->total_bw -= p->dl.dl_bw;
-	raw_spin_unlock_irq(&dl_b->lock);
-	if (hrtimer_active(&p->dl.inactive_timer)) {
+	if (!hrtimer_active(&p->dl.inactive_timer)) {
+		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+		/*
+		 * If the "inactive timer is not active, the 0-lag time
+		 * is already passed, so we immediately decrease the
+		 * total deadline utilization
+		 */
+		raw_spin_lock_irq(&dl_b->lock);
+		__dl_clear(dl_b, p->dl.dl_bw);
+		raw_spin_unlock_irq(&dl_b->lock);
+	} else {
 		raw_spin_lock_irq(&task_rq(p)->lock);
 		sub_running_bw(&p->dl, dl_rq_of_se(&p->dl));
 		raw_spin_unlock_irq(&task_rq(p)->lock);
-- 
2.7.4