[PATCH 1/2] sched/deadline: add per rq tracking of admitted bandwidth

[Juri Lelli]

Currently SCHED_DEADLINE scheduling policy tracks bandwidth of tasks
that passed admission control at root_domain level only. This creates
problems when such data structure(s) are destroyed, when we reconfigure
scheduling domains for example.

This is part one of two changes required to fix the problem. In this
patch we add per-rq tracking of admitted bandwidth. Tasks bring with
them their bandwidth contribution when they enter the system and are
enqueued for the first time. Contributions are then moved around when
migrations happen and removed when tasks die.

Per-rq admitted bandwidth information will be leveraged in the next
commit to save/restore per-rq bandwidth contribution towards the root
domain (using the rq_{online,offline} mechanism).

Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Reported-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxx>
Reported-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
[ original patch by ]
Signed-off-by: Luca Abeni <luca.abeni@xxxxxxxx>
Signed-off-by: Juri Lelli <juri.lelli@xxxxxxx>
---
 kernel/sched/core.c     |  6 +++++-
 kernel/sched/deadline.c | 16 +++++++++++++++-
 kernel/sched/sched.h    | 22 ++++++++++++++++++++++
 3 files changed, 42 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9503d59..0ee0ec2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2432,7 +2432,7 @@ static int dl_overflow(struct task_struct *p, int policy,
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
 	int cpus, err = -1;
 
-	if (new_bw == p->dl.dl_bw)
+	if (task_has_dl_policy(p) && new_bw == p->dl.dl_bw)
 		return 0;
 
 	/*
@@ -2445,14 +2445,18 @@ static int dl_overflow(struct task_struct *p, int policy,
 	if (dl_policy(policy) && !task_has_dl_policy(p) &&
 	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
 		__dl_add(dl_b, new_bw);
+		__dl_add_ac(task_rq(p), 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)) {
 		__dl_clear(dl_b, p->dl.dl_bw);
+		__dl_sub_ac(task_rq(p), p->dl.dl_bw);
 		__dl_add(dl_b, new_bw);
+		__dl_add_ac(task_rq(p), new_bw);
 		err = 0;
 	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
 		__dl_clear(dl_b, p->dl.dl_bw);
+		__dl_sub_ac(task_rq(p), p->dl.dl_bw);
 		err = 0;
 	}
 	raw_spin_unlock(&dl_b->lock);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index cd64c97..8ac0fee 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -83,6 +83,7 @@ void init_dl_rq(struct dl_rq *dl_rq)
 #else
 	init_dl_bw(&dl_rq->dl_bw);
 #endif
+	dl_rq->ac_bw = 0;
 }
 
 #ifdef CONFIG_SMP
@@ -278,8 +279,10 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 	 * By now the task is replenished and enqueued; migrate it.
 	 */
 	deactivate_task(rq, p, 0);
+	__dl_sub_ac(rq, p->dl.dl_bw);
 	set_task_cpu(p, later_rq->cpu);
 	activate_task(later_rq, p, 0);
+	__dl_add_ac(later_rq, p->dl.dl_bw);
 
 	if (!fallback)
 		resched_curr(later_rq);
@@ -597,7 +600,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 
 	/*
 	 * The task might have changed its scheduling policy to something
-	 * different than SCHED_DEADLINE (through switched_fromd_dl()).
+	 * different than SCHED_DEADLINE (through switched_from_dl()).
 	 */
 	if (!dl_task(p)) {
 		__dl_clear_params(p);
@@ -955,6 +958,9 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 		return;
 	}
 
+	if (p->on_rq == TASK_ON_RQ_MIGRATING)
+		__dl_add_ac(rq, p->dl.dl_bw);
+
 	/*
 	 * If p is throttled, we do nothing. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
@@ -980,6 +986,8 @@ 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)
+		__dl_sub_ac(rq, p->dl.dl_bw);
 }
 
 /*
@@ -1219,6 +1227,8 @@ static void task_dead_dl(struct task_struct *p)
 {
 	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 
+	__dl_sub_ac(task_rq(p), p->dl.dl_bw);
+
 	/*
 	 * Since we are TASK_DEAD we won't slip out of the domain!
 	 */
@@ -1511,8 +1521,10 @@ retry:
 	}
 
 	deactivate_task(rq, next_task, 0);
+	__dl_sub_ac(rq, next_task->dl.dl_bw);
 	set_task_cpu(next_task, later_rq->cpu);
 	activate_task(later_rq, next_task, 0);
+	__dl_add_ac(later_rq, next_task->dl.dl_bw);
 	ret = 1;
 
 	resched_curr(later_rq);
@@ -1599,8 +1611,10 @@ static void pull_dl_task(struct rq *this_rq)
 			resched = true;
 
 			deactivate_task(src_rq, p, 0);
+			__dl_sub_ac(src_rq, p->dl.dl_bw);
 			set_task_cpu(p, this_cpu);
 			activate_task(this_rq, p, 0);
+			__dl_add_ac(this_rq, p->dl.dl_bw);
 			dmin = p->dl.deadline;
 
 			/* Is there any other task even earlier? */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 10f1637..242907f 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -519,6 +519,14 @@ struct dl_rq {
 #else
 	struct dl_bw dl_bw;
 #endif
+
+	/*
+	 * ac_bw keeps track of per rq admitted bandwidth. It only changes
+	 * when a new task is admitted, it dies, it changes scheduling policy
+	 * or is migrated to another rq. It is used to correctly save/resore
+	 * total_bw on root_domain changes.
+	 */
+	u64 ac_bw;
 };
 
 #ifdef CONFIG_SMP
@@ -720,6 +728,20 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 #define raw_rq()		raw_cpu_ptr(&runqueues)
 
+static inline
+void __dl_sub_ac(struct rq *rq, u64 tsk_bw)
+{
+	WARN_ON(rq->dl.ac_bw < tsk_bw);
+
+	rq->dl.ac_bw -= tsk_bw;
+}
+
+static inline
+void __dl_add_ac(struct rq *rq, u64 tsk_bw)
+{
+	rq->dl.ac_bw += tsk_bw;
+}
+
 static inline u64 __rq_clock_broken(struct rq *rq)
 {
 	return READ_ONCE(rq->clock);
-- 
2.7.0