sched, nohz: Track nr_busy_cpus in the sched_group_power

Introduce nr_busy_cpus in the struct sched_group_power [Not in sched_group
because sched groups are duplicated for the SD_OVERLAP scheduler domain]
and for each cpu that enters and exits idle, this parameter will
be updated in each scheduler group of the scheduler domain that this cpu
belongs to.

To avoid the frequent update of this state as the cpu enters
and exits idle, the update of the stat during idle exit is
delayed to the first timer tick that happens after the cpu becomes busy.
This is done using NOHZ_IDLE flag in the struct rq's nohz_flags.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20111202010832.555984323@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 42 insertions, 0 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f1da77b83f3..699ff1499a8a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6024,6 +6024,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
                 return;
 
         update_group_power(sd, cpu);
+        atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight);
 }
 
 int __weak arch_sd_sibling_asym_packing(void)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 50c06b0e9fab..e050563e97a4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4901,6 +4901,36 @@ static void nohz_balancer_kick(int cpu)
         return;
 }
 
+static inline void set_cpu_sd_state_busy(void)
+{
+        struct sched_domain *sd;
+        int cpu = smp_processor_id();
+
+        if (!test_bit(NOHZ_IDLE, nohz_flags(cpu)))
+                return;
+        clear_bit(NOHZ_IDLE, nohz_flags(cpu));
+
+        rcu_read_lock();
+        for_each_domain(cpu, sd)
+                atomic_inc(&sd->groups->sgp->nr_busy_cpus);
+        rcu_read_unlock();
+}
+
+void set_cpu_sd_state_idle(void)
+{
+        struct sched_domain *sd;
+        int cpu = smp_processor_id();
+
+        if (test_bit(NOHZ_IDLE, nohz_flags(cpu)))
+                return;
+        set_bit(NOHZ_IDLE, nohz_flags(cpu));
+
+        rcu_read_lock();
+        for_each_domain(cpu, sd)
+                atomic_dec(&sd->groups->sgp->nr_busy_cpus);
+        rcu_read_unlock();
+}
+
 /*
  * This routine will try to nominate the ilb (idle load balancing)
  * owner among the cpus whose ticks are stopped. ilb owner will do the idle
@@ -5135,6 +5165,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
         * We may be recently in ticked or tickless idle mode. At the first
         * busy tick after returning from idle, we will update the busy stats.
         */
+        set_cpu_sd_state_busy();
         if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))))
                 clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu));
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index cf7d02662bc2..91810f0ee3af 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1069,6 +1069,7 @@ extern void account_cfs_bandwidth_used(int enabled, int was_enabled);
 enum rq_nohz_flag_bits {
         NOHZ_TICK_STOPPED,
         NOHZ_BALANCE_KICK,
+        NOHZ_IDLE,
 };
 
 #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 40420644d0ba..31cc06163ed5 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -297,6 +297,15 @@ void tick_nohz_stop_sched_tick(int inidle)
         ts = &per_cpu(tick_cpu_sched, cpu);
 
         /*
+         * 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.
+         */
+        if (inidle)
+                set_cpu_sd_state_idle();
+
+        /*
          * Call to tick_nohz_start_idle stops the last_update_time from being
          * updated. Thus, it must not be called in the event we are called from
          * irq_exit() with the prior state different than idle.