[RFC][PATCH 4/7] sched: Replace sd_busy/nr_busy_cpus with sched_domain_shared

[Peter Zijlstra]

Move the nr_busy_cpus thing from its hacky sd->parent->groups->sgc
location into the much more natural sched_domain_shared location.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 include/linux/sched.h    |    1 +
 kernel/sched/core.c      |   10 +++++-----
 kernel/sched/fair.c      |   22 ++++++++++++----------
 kernel/sched/sched.h     |    6 +-----
 kernel/time/tick-sched.c |   10 +++++-----
 5 files changed, 24 insertions(+), 25 deletions(-)

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1059,6 +1059,7 @@ struct sched_group;
 
 struct sched_domain_shared {
 	atomic_t	ref;
+	atomic_t	nr_busy_cpus;
 };
 
 struct sched_domain {
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5866,14 +5866,14 @@ static void destroy_sched_domains(struct
 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_shared *, sd_llc_shared);
 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)
 {
+	struct sched_domain_shared *sds = NULL;
 	struct sched_domain *sd;
-	struct sched_domain *busy_sd = NULL;
 	int id = cpu;
 	int size = 1;
 
@@ -5881,13 +5881,13 @@ static void update_top_cache_domain(int
 	if (sd) {
 		id = cpumask_first(sched_domain_span(sd));
 		size = cpumask_weight(sched_domain_span(sd));
-		busy_sd = sd->parent; /* sd_busy */
+		sds = sd->shared;
 	}
-	rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd);
 
 	rcu_assign_pointer(per_cpu(sd_llc, cpu), sd);
 	per_cpu(sd_llc_size, cpu) = size;
 	per_cpu(sd_llc_id, cpu) = id;
+	rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds);
 
 	sd = lowest_flag_domain(cpu, SD_NUMA);
 	rcu_assign_pointer(per_cpu(sd_numa, cpu), sd);
@@ -6184,7 +6184,6 @@ static void init_sched_groups_capacity(i
 		return;
 
 	update_group_capacity(sd, cpu);
-	atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight);
 }
 
 /*
@@ -6388,6 +6387,7 @@ sd_init(struct sched_domain_topology_lev
 
 		sd->shared = *per_cpu_ptr(sdd->sds, sd_id);
 		atomic_inc(&sd->shared->ref);
+		atomic_set(&sd->shared->nr_busy_cpus, sd_weight);
 
 #ifdef CONFIG_NUMA
 	} else if (sd->flags & SD_NUMA) {
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7842,13 +7842,13 @@ static inline void set_cpu_sd_state_busy
 	int cpu = smp_processor_id();
 
 	rcu_read_lock();
-	sd = rcu_dereference(per_cpu(sd_busy, cpu));
+	sd = rcu_dereference(per_cpu(sd_llc, cpu));
 
 	if (!sd || !sd->nohz_idle)
 		goto unlock;
 	sd->nohz_idle = 0;
 
-	atomic_inc(&sd->groups->sgc->nr_busy_cpus);
+	atomic_inc(&sd->shared->nr_busy_cpus);
 unlock:
 	rcu_read_unlock();
 }
@@ -7859,13 +7859,13 @@ void set_cpu_sd_state_idle(void)
 	int cpu = smp_processor_id();
 
 	rcu_read_lock();
-	sd = rcu_dereference(per_cpu(sd_busy, cpu));
+	sd = rcu_dereference(per_cpu(sd_llc, cpu));
 
 	if (!sd || sd->nohz_idle)
 		goto unlock;
 	sd->nohz_idle = 1;
 
-	atomic_dec(&sd->groups->sgc->nr_busy_cpus);
+	atomic_dec(&sd->shared->nr_busy_cpus);
 unlock:
 	rcu_read_unlock();
 }
@@ -8092,8 +8092,8 @@ static void nohz_idle_balance(struct rq
 static inline bool nohz_kick_needed(struct rq *rq)
 {
 	unsigned long now = jiffies;
+	struct sched_domain_shared *sds;
 	struct sched_domain *sd;
-	struct sched_group_capacity *sgc;
 	int nr_busy, cpu = rq->cpu;
 	bool kick = false;
 
@@ -8121,11 +8121,13 @@ static inline bool nohz_kick_needed(stru
 		return true;
 
 	rcu_read_lock();
-	sd = rcu_dereference(per_cpu(sd_busy, cpu));
-	if (sd) {
-		sgc = sd->groups->sgc;
-		nr_busy = atomic_read(&sgc->nr_busy_cpus);
-
+	sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
+	if (sds) {
+		/*
+		 * XXX: write a coherent comment on why we do this.
+		 * See also: http:lkml.kernel.org/r/20111202010832.602203411@xxxxxxxxxxxxxxxxxxxxxxxxxx
+		 */
+		nr_busy = atomic_read(&sds->nr_busy_cpus);
 		if (nr_busy > 1) {
 			kick = true;
 			goto unlock;
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -856,8 +856,8 @@ static inline struct sched_domain *lowes
 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_shared *, sd_llc_shared);
 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_capacity {
@@ -869,10 +869,6 @@ struct sched_group_capacity {
 	unsigned int capacity;
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
-	/*
-	 * Number of busy cpus in this group.
-	 */
-	atomic_t nr_busy_cpus;
 
 	unsigned long cpumask[0]; /* iteration mask */
 };
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -933,11 +933,11 @@ void tick_nohz_idle_enter(void)
 	WARN_ON_ONCE(irqs_disabled());
 
 	/*
- 	 * Update the idle state in the scheduler domain hierarchy
- 	 * when tick_nohz_stop_sched_tick() is called from the idle loop.
- 	 * State will be updated to busy during the first busy tick after
- 	 * exiting idle.
- 	 */
+	 * Update the idle state in the scheduler domain hierarchy
+	 * when tick_nohz_stop_sched_tick() is called from the idle loop.
+	 * State will be updated to busy during the first busy tick after
+	 * exiting idle.
+	 */
 	set_cpu_sd_state_idle();
 
 	local_irq_disable();