[tip:sched/core] sched/deadline: Track the active utilization

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

Commit-ID:  e36d8677bfa55054e4194ec3683189b882a538f6
Gitweb:     http://git.kernel.org/tip/e36d8677bfa55054e4194ec3683189b882a538f6
Author:     Luca Abeni <luca.abeni@unitn.it>
AuthorDate: Thu, 18 May 2017 22:13:28 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 8 Jun 2017 10:27:56 +0200

sched/deadline: Track the active utilization

Active utilization is defined as the total utilization of active
(TASK_RUNNING) tasks queued on a runqueue. Hence, it is increased
when a task wakes up and is decreased when a task blocks.

When a task is migrated from CPUi to CPUj, immediately subtract the
task's utilization from CPUi and add it to CPUj. This mechanism is
implemented by modifying the pull and push functions.
Note: this is not fully correct from the theoretical point of view
(the utilization should be removed from CPUi only at the 0 lag
time), a more theoretically sound solution is presented in the
next patches.

Tested-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Luca Abeni <luca.abeni@unitn.it>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Juri Lelli <juri.lelli@arm.com>
Cc: Claudio Scordino <claudio@evidence.eu.com>
Cc: Joel Fernandes <joelaf@google.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/1495138417-6203-2-git-send-email-luca.abeni@santannapisa.it
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/deadline.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++---
 kernel/sched/sched.h    |  6 +++++
 2 files changed, 67 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index df6c291..b36ecc2 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -43,6 +43,28 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se)
 	return !RB_EMPTY_NODE(&dl_se->rb_node);
 }
 
+static inline
+void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->running_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->running_bw += dl_bw;
+	SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
+}
+
+static inline
+void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->running_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->running_bw -= dl_bw;
+	SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
+	if (dl_rq->running_bw > old)
+		dl_rq->running_bw = 0;
+}
+
 static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
@@ -83,6 +105,8 @@ void init_dl_rq(struct dl_rq *dl_rq)
 #else
 	init_dl_bw(&dl_rq->dl_bw);
 #endif
+
+	dl_rq->running_bw = 0;
 }
 
 #ifdef CONFIG_SMP
@@ -946,10 +970,14 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (flags & ENQUEUE_WAKEUP)
+	if (flags & ENQUEUE_WAKEUP) {
+		struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+		add_running_bw(dl_se->dl_bw, dl_rq);
 		update_dl_entity(dl_se, pi_se);
-	else if (flags & ENQUEUE_REPLENISH)
+	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se, pi_se);
+	}
 
 	__enqueue_dl_entity(dl_se);
 }
@@ -998,14 +1026,25 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
 		dl_check_constrained_dl(&p->dl);
 
+	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE)
+		add_running_bw(p->dl.dl_bw, &rq->dl);
+
 	/*
-	 * If p is throttled, we do nothing. In fact, if it exhausted
+	 * If p is throttled, we do not enqueue it. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
 	 * its rq, the bandwidth timer callback (which clearly has not
 	 * run yet) will take care of this.
+	 * However, the active utilization does not depend on the fact
+	 * that the task is on the runqueue or not (but depends on the
+	 * task's state - in GRUB parlance, "inactive" vs "active contending").
+	 * In other words, even if a task is throttled its utilization must
+	 * be counted in the active utilization; hence, we need to call
+	 * add_running_bw().
 	 */
-	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH))
+	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
+		add_running_bw(p->dl.dl_bw, &rq->dl);
 		return;
+	}
 
 	enqueue_dl_entity(&p->dl, pi_se, flags);
 
@@ -1023,6 +1062,20 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
 	__dequeue_task_dl(rq, p, flags);
+
+	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE)
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
+
+	/*
+	 * This check allows to decrease the active utilization in two cases:
+	 * when the task blocks and when it is terminating
+	 * (p->state == TASK_DEAD). We can handle the two cases in the same
+	 * way, because from GRUB's point of view the same thing is happening
+	 * (the task moves from "active contending" to "active non contending"
+	 * or "inactive")
+	 */
+	if (flags & DEQUEUE_SLEEP)
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
 }
 
 /*
@@ -1551,7 +1604,9 @@ retry:
 	}
 
 	deactivate_task(rq, next_task, 0);
+	sub_running_bw(next_task->dl.dl_bw, &rq->dl);
 	set_task_cpu(next_task, later_rq->cpu);
+	add_running_bw(next_task->dl.dl_bw, &later_rq->dl);
 	activate_task(later_rq, next_task, 0);
 	ret = 1;
 
@@ -1639,7 +1694,9 @@ static void pull_dl_task(struct rq *this_rq)
 			resched = true;
 
 			deactivate_task(src_rq, p, 0);
+			sub_running_bw(p->dl.dl_bw, &src_rq->dl);
 			set_task_cpu(p, this_cpu);
+			add_running_bw(p->dl.dl_bw, &this_rq->dl);
 			activate_task(this_rq, p, 0);
 			dmin = p->dl.deadline;
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f8cf1d8..ee26867 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -558,6 +558,12 @@ struct dl_rq {
 #else
 	struct dl_bw dl_bw;
 #endif
+	/*
+	 * "Active utilization" for this runqueue: increased when a
+	 * task wakes up (becomes TASK_RUNNING) and decreased when a
+	 * task blocks
+	 */
+	u64 running_bw;
 };
 
 #ifdef CONFIG_SMP