[tip:sched/core] sched/deadline: Fix the update of the total -deadline utilization

[tip-bot for Luca Abeni <tipbot@zytor.com>]

Commit-ID:  387e31300b5760169e6d3f7a9e1eeed12cc5a30b
Gitweb:     http://git.kernel.org/tip/387e31300b5760169e6d3f7a9e1eeed12cc5a30b
Author:     Luca Abeni <luca.abeni@santannapisa.it>
AuthorDate: Thu, 18 May 2017 22:13:30 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 8 Jun 2017 10:31:50 +0200

sched/deadline: Fix the update of the total -deadline utilization

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().

Tested-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Luca Abeni <luca.abeni@santannapisa.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Claudio Scordino <claudio@evidence.eu.com>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Juri Lelli <juri.lelli@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mathieu Poirier <mathieu.poirier@linaro.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>
Cc: Tommaso Cucinotta <tommaso.cucinotta@sssup.it>
Link: http://lkml.kernel.org/r/1495138417-6203-4-git-send-email-luca.abeni@santannapisa.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c     | 38 ++++++++++++++------------------------
 kernel/sched/deadline.c | 28 +++++++++++++---------------
 2 files changed, 27 insertions(+), 39 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 968c655..126339d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2475,9 +2475,6 @@ 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)
@@ -2502,16 +2499,29 @@ static int dl_overflow(struct task_struct *p, int policy,
 	cpus = dl_bw_cpus(task_cpu(p));
 	if (dl_policy(policy) && !task_has_dl_policy(p) &&
 	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+		if (hrtimer_active(&p->dl.inactive_timer))
+			__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_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);
 		dl_change_utilization(p, 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);
@@ -4020,26 +4030,6 @@ __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 6480a92..add9cba 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -175,8 +175,14 @@ static void task_non_contending(struct task_struct *p)
 	if (zerolag_time < 0) {
 		if (dl_task(p))
 			sub_running_bw(dl_se->dl_bw, dl_rq);
-		if (!dl_task(p) || p->state == TASK_DEAD)
+		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);
+		}
 
 		return;
 	}
@@ -1004,10 +1010,16 @@ static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
 	rq = task_rq_lock(p, &rf);
 
 	if (!dl_task(p) || p->state == TASK_DEAD) {
+		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
 		if (p->state == TASK_DEAD && dl_se->dl_non_contending) {
 			sub_running_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl));
 			dl_se->dl_non_contending = 0;
 		}
+
+		raw_spin_lock(&dl_b->lock);
+		__dl_clear(dl_b, p->dl.dl_bw);
+		raw_spin_unlock(&dl_b->lock);
 		__dl_clear_params(p);
 
 		goto unlock;
@@ -1534,19 +1546,6 @@ 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);
-}
-
 static void set_curr_task_dl(struct rq *rq)
 {
 	struct task_struct *p = rq->curr;
@@ -2141,7 +2140,6 @@ const struct sched_class dl_sched_class = {
 	.set_curr_task		= set_curr_task_dl,
 	.task_tick		= task_tick_dl,
 	.task_fork              = task_fork_dl,
-	.task_dead		= task_dead_dl,
 
 	.prio_changed           = prio_changed_dl,
 	.switched_from		= switched_from_dl,