sched: Remove unnecessary iteration over sched domains to update nr_busy_cpus

nr_busy_cpus parameter is used by nohz_kick_needed() to find out the
number of busy cpus in a sched domain which has SD_SHARE_PKG_RESOURCES
flag set.  Therefore instead of updating nr_busy_cpus at every level
of sched domain, since it is irrelevant, we can update this parameter
only at the parent domain of the sd which has this flag set. Introduce
a per-cpu parameter sd_busy which represents this parent domain.

In nohz_kick_needed() we directly query the nr_busy_cpus parameter
associated with the groups of sd_busy.

By associating sd_busy with the highest domain which has
SD_SHARE_PKG_RESOURCES flag set, we cover all lower level domains
which could have this flag set and trigger nohz_idle_balancing if any
of the levels have more than one busy cpu.

sd_busy is irrelevant for asymmetric load balancing. However sd_asym
has been introduced to represent the highest sched domain which has
SD_ASYM_PACKING flag set so that it can be queried directly when
required.

While we are at it, we might as well change the nohz_idle parameter to
be updated at the sd_busy domain level alone and not the base domain
level of a CPU.  This will unify the concept of busy cpus at just one
level of sched domain where it is currently used.

Signed-off-by: Preeti U Murthy<[email protected]>
Signed-off-by: Peter Zijlstra <[email protected]>
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Cc: [email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Ingo Molnar <[email protected]>

kernel/sched/core.c

@@ -4883,6 +4883,8 @@ DEFINE_PER_CPU(struct sched_domain *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
 DEFINE_PER_CPU(struct sched_domain *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain *, sd_busy);
+DEFINE_PER_CPU(struct sched_domain *, sd_asym);
 
 static void update_top_cache_domain(int cpu)
 {
@@ -4894,6 +4896,7 @@ static void update_top_cache_domain(int cpu)
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
+		rcu_assign_pointer(per_cpu(sd_busy, cpu), sd->parent);
 	}
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
@@ -4902,6 +4905,9 @@ static void update_top_cache_domain(int cpu)
 
 	sd = lowest_flag_domain(cpu, SD_NUMA);
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
+
+	sd = highest_flag_domain(cpu, SD_ASYM_PACKING);
+	rcu_assign_pointer(per_cpu(sd_asym, cpu), sd);
 }
 
 /*

kernel/sched/fair.c

@@ -6534,16 +6534,16 @@ static inline void nohz_balance_exit_idle(int cpu)
 static inline void set_cpu_sd_state_busy(void)
 {
 	struct sched_domain *sd;
+	int cpu = smp_processor_id();
 
 	rcu_read_lock();
-	sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+	sd = rcu_dereference(per_cpu(sd_busy, cpu));
 
 	if (!sd || !sd->nohz_idle)
 		goto unlock;
 	sd->nohz_idle = 0;
 
-	for (; sd; sd = sd->parent)
-		atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+	atomic_inc(&sd->groups->sgp->nr_busy_cpus);
 unlock:
 	rcu_read_unlock();
 }
@@ -6551,16 +6551,16 @@ unlock:
 void set_cpu_sd_state_idle(void)
 {
 	struct sched_domain *sd;
+	int cpu = smp_processor_id();
 
 	rcu_read_lock();
-	sd = rcu_dereference_check_sched_domain(this_rq()->sd);
+	sd = rcu_dereference(per_cpu(sd_busy, cpu));
 
 	if (!sd || sd->nohz_idle)
 		goto unlock;
 	sd->nohz_idle = 1;
 
-	for (; sd; sd = sd->parent)
-		atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+	atomic_dec(&sd->groups->sgp->nr_busy_cpus);
 unlock:
 	rcu_read_unlock();
 }
@@ -6767,6 +6767,8 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 {
 	unsigned long now = jiffies;
 	struct sched_domain *sd;
+	struct sched_group_power *sgp;
+	int nr_busy;
 
 	if (unlikely(idle_cpu(cpu)))
 		return 0;
@@ -6792,22 +6794,22 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 		goto need_kick;
 
 	rcu_read_lock();
-	for_each_domain(cpu, sd) {
-		struct sched_group *sg = sd->groups;
-		struct sched_group_power *sgp = sg->sgp;
-		int nr_busy = atomic_read(&sgp->nr_busy_cpus);
+	sd = rcu_dereference(per_cpu(sd_busy, cpu));
 
-		if (sd->flags & SD_SHARE_PKG_RESOURCES && nr_busy > 1)
+	if (sd) {
+		sgp = sd->groups->sgp;
+		nr_busy = atomic_read(&sgp->nr_busy_cpus);
+
+		if (nr_busy > 1)
 			goto need_kick_unlock;
-
-		if (sd->flags & SD_ASYM_PACKING
-		    && (cpumask_first_and(nohz.idle_cpus_mask,
-					  sched_domain_span(sd)) < cpu))
-			goto need_kick_unlock;
-
-		if (!(sd->flags & (SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING)))
-			break;
 	}
+
+	sd = rcu_dereference(per_cpu(sd_asym, cpu));
+
+	if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
+				  sched_domain_span(sd)) < cpu))
+		goto need_kick_unlock;
+
 	rcu_read_unlock();
 	return 0;
 

kernel/sched/sched.h

@@ -623,6 +623,8 @@ DECLARE_PER_CPU(struct sched_domain *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
 DECLARE_PER_CPU(struct sched_domain *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain *, sd_busy);
+DECLARE_PER_CPU(struct sched_domain *, sd_asym);
 
 struct sched_group_power {
 	atomic_t ref;