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

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 24fcdbf..706ca23 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2449,7 +2449,9 @@  static int dl_overflow(struct task_struct *p, int policy,
 	} 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);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index cd64c97..2480cab 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);
@@ -506,6 +509,7 @@  static void update_dl_entity(struct sched_dl_entity *dl_se,
 	 */
 	if (dl_se->dl_new) {
 		setup_new_dl_entity(dl_se, pi_se);
+		__dl_add_ac(rq, dl_se->dl_bw);
 		return;
 	}
 
@@ -955,6 +959,9 @@  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 +987,8 @@  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 +1228,8 @@  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 +1522,10 @@  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 +1612,10 @@  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? */
@@ -1705,6 +1720,9 @@  static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (!start_dl_timer(p))
 		__dl_clear_params(p);
 
+	if (dl_prio(p->normal_prio))
+		__dl_sub_ac(rq, p->dl.dl_bw);
+
 	/*
 	 * Since this might be the only -deadline task on the rq,
 	 * this is the right place to try to pull some other one
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 10f1637..e754680 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 == 0);
+
+	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);