sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance()

Currently, in idle_balance(), we update rq->next_balance when we pull_tasks.
However, it is also important to update this in the !pulled_tasks case too.

When the CPU is "busy" (the CPU isn't idle), rq->next_balance gets computed
using sd->busy_factor (so we increase the balance interval when the CPU is
busy). However, when the CPU goes idle, rq->next_balance could still be set
to a large value that was computed with the sd->busy_factor.

Thus, we need to also update rq->next_balance in idle_balance() in the cases
where !pulled_tasks too, so that rq->next_balance gets updated without taking
the busy_factor into account when the CPU is about to go idle.

This patch makes rq->next_balance get updated independently of whether or
not we pulled_task. Also, we add logic to ensure that we always traverse
at least 1 of the sched domains to get a proper next_balance value for
updating rq->next_balance.

Additionally, since load_balance() modifies the sd->balance_interval, we
need to re-obtain the sched domain's interval after the call to
load_balance() in rebalance_domains() before we update rq->next_balance.

This patch adds and uses 2 new helper functions, update_next_balance() and
get_sd_balance_interval() to update next_balance and obtain the sched
domain's balance_interval.
Signed-off-by: Jason Low <jason.low2@hp.com>
Reviewed-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: daniel.lezcano@linaro.org
Cc: alex.shi@linaro.org
Cc: efault@gmx.de
Cc: vincent.guittot@linaro.org
Cc: morten.rasmussen@arm.com
Cc: aswin@hp.com
Link: http://lkml.kernel.org/r/1399596562.2200.7.camel@j-VirtualBoxSigned-off-by: Ingo Molnar <mingo@kernel.org>

kernel/sched/fair.c

@@ -6672,17 +6672,44 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 	return ld_moved;
 }
 
+static inline unsigned long
+get_sd_balance_interval(struct sched_domain *sd, int cpu_busy)
+{
+	unsigned long interval = sd->balance_interval;
+
+	if (cpu_busy)
+		interval *= sd->busy_factor;
+
+	/* scale ms to jiffies */
+	interval = msecs_to_jiffies(interval);
+	interval = clamp(interval, 1UL, max_load_balance_interval);
+
+	return interval;
+}
+
+static inline void
+update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance)
+{
+	unsigned long interval, next;
+
+	interval = get_sd_balance_interval(sd, cpu_busy);
+	next = sd->last_balance + interval;
+
+	if (time_after(*next_balance, next))
+		*next_balance = next;
+}
+
 /*
  * idle_balance is called by schedule() if this_cpu is about to become
  * idle. Attempts to pull tasks from other CPUs.
  */
 static int idle_balance(struct rq *this_rq)
 {
+	unsigned long next_balance = jiffies + HZ;
+	int this_cpu = this_rq->cpu;
 	struct sched_domain *sd;
 	int pulled_task = 0;
-	unsigned long next_balance = jiffies + HZ;
 	u64 curr_cost = 0;
-	int this_cpu = this_rq->cpu;
 
 	idle_enter_fair(this_rq);
 
@@ -6692,8 +6719,15 @@ static int idle_balance(struct rq *this_rq)
 	 */
 	this_rq->idle_stamp = rq_clock(this_rq);
 
-	if (this_rq->avg_idle < sysctl_sched_migration_cost)
+	if (this_rq->avg_idle < sysctl_sched_migration_cost) {
+		rcu_read_lock();
+		sd = rcu_dereference_check_sched_domain(this_rq->sd);
+		if (sd)
+			update_next_balance(sd, 0, &next_balance);
+		rcu_read_unlock();
+
 		goto out;
+	}
 
 	/*
 	 * Drop the rq->lock, but keep IRQ/preempt disabled.
@@ -6703,15 +6737,16 @@ static int idle_balance(struct rq *this_rq)
 	update_blocked_averages(this_cpu);
 	rcu_read_lock();
 	for_each_domain(this_cpu, sd) {
-		unsigned long interval;
 		int continue_balancing = 1;
 		u64 t0, domain_cost;
 
 		if (!(sd->flags & SD_LOAD_BALANCE))
 			continue;
 
-		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost)
+		if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) {
+			update_next_balance(sd, 0, &next_balance);
 			break;
+		}
 
 		if (sd->flags & SD_BALANCE_NEWIDLE) {
 			t0 = sched_clock_cpu(this_cpu);
@@ -6727,9 +6762,7 @@ static int idle_balance(struct rq *this_rq)
 			curr_cost += domain_cost;
 		}
 
-		interval = msecs_to_jiffies(sd->balance_interval);
-		if (time_after(next_balance, sd->last_balance + interval))
-			next_balance = sd->last_balance + interval;
+		update_next_balance(sd, 0, &next_balance);
 
 		/*
 		 * Stop searching for tasks to pull if there are
@@ -6753,15 +6786,11 @@ static int idle_balance(struct rq *this_rq)
 	if (this_rq->cfs.h_nr_running && !pulled_task)
 		pulled_task = 1;
 
-	if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
-		/*
-		 * We are going idle. next_balance may be set based on
-		 * a busy processor. So reset next_balance.
-		 */
+out:
+	/* Move the next balance forward */
+	if (time_after(this_rq->next_balance, next_balance))
 		this_rq->next_balance = next_balance;
-	}
 
-out:
 	/* Is there a task of a high priority class? */
 	if (this_rq->nr_running != this_rq->cfs.h_nr_running)
 		pulled_task = -1;
@@ -7044,16 +7073,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 			break;
 		}
 
-		interval = sd->balance_interval;
-		if (idle != CPU_IDLE)
-			interval *= sd->busy_factor;
-
-		/* scale ms to jiffies */
-		interval = msecs_to_jiffies(interval);
-		interval = clamp(interval, 1UL, max_load_balance_interval);
+		interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
 
 		need_serialize = sd->flags & SD_SERIALIZE;
-
 		if (need_serialize) {
 			if (!spin_trylock(&balancing))
 				goto out;
@@ -7069,6 +7091,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle)
 				idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE;
 			}
 			sd->last_balance = jiffies;
+			interval = get_sd_balance_interval(sd, idle != CPU_IDLE);
 		}
 		if (need_serialize)
 			spin_unlock(&balancing);