Merge branch 'test' into weekly

arch/arm/kernel/smp.c

@@ -24,7 +24,6 @@
 #include <linux/percpu.h>
 #include <linux/clockchips.h>
 #include <linux/completion.h>
-#include <linux/cpufreq.h>
 
 #include <linux/atomic.h>
 #include <asm/smp.h>
@@ -717,56 +716,3 @@ int setup_profiling_timer(unsigned int multiplier)
 {
 	return -EINVAL;
 }
-
-#ifdef CONFIG_CPU_FREQ
-
-static DEFINE_PER_CPU(unsigned long, l_p_j_ref);
-static DEFINE_PER_CPU(unsigned long, l_p_j_ref_freq);
-static unsigned long global_l_p_j_ref;
-static unsigned long global_l_p_j_ref_freq;
-
-static int cpufreq_callback(struct notifier_block *nb,
-					unsigned long val, void *data)
-{
-	struct cpufreq_freqs *freq = data;
-	int cpu = freq->cpu;
-
-	if (freq->flags & CPUFREQ_CONST_LOOPS)
-		return NOTIFY_OK;
-
-	if (!per_cpu(l_p_j_ref, cpu)) {
-		per_cpu(l_p_j_ref, cpu) =
-			per_cpu(cpu_data, cpu).loops_per_jiffy;
-		per_cpu(l_p_j_ref_freq, cpu) = freq->old;
-		if (!global_l_p_j_ref) {
-			global_l_p_j_ref = loops_per_jiffy;
-			global_l_p_j_ref_freq = freq->old;
-		}
-	}
-
-	if ((val == CPUFREQ_PRECHANGE  && freq->old < freq->new) ||
-	    (val == CPUFREQ_POSTCHANGE && freq->old > freq->new) ||
-	    (val == CPUFREQ_RESUMECHANGE || val == CPUFREQ_SUSPENDCHANGE)) {
-		loops_per_jiffy = cpufreq_scale(global_l_p_j_ref,
-						global_l_p_j_ref_freq,
-						freq->new);
-		per_cpu(cpu_data, cpu).loops_per_jiffy =
-			cpufreq_scale(per_cpu(l_p_j_ref, cpu),
-					per_cpu(l_p_j_ref_freq, cpu),
-					freq->new);
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpufreq_notifier = {
-	.notifier_call  = cpufreq_callback,
-};
-
-static int __init register_cpufreq_notifier(void)
-{
-	return cpufreq_register_notifier(&cpufreq_notifier,
-						CPUFREQ_TRANSITION_NOTIFIER);
-}
-core_initcall(register_cpufreq_notifier);
-
-#endif

include/linux/sched.h

@@ -271,28 +271,10 @@ extern void init_idle_bootup_task(struct task_struct *idle);
 
 extern int runqueue_is_locked(int cpu);
 
-#ifdef CONFIG_SMP
-extern int sched_select_non_idle_cpu(void);
-#else
-static inline int sched_select_non_idle_cpu(void)
-{
-	return smp_processor_id();
-}
-#endif
-
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ)
 extern void select_nohz_load_balancer(int stop_tick);
 extern void set_cpu_sd_state_idle(void);
-
-/*
- * In the semi idle case, use the nearest busy cpu for migrating timers
- * from an idle cpu.  This is good for power-savings.
- *
- * We don't do similar optimization for completely idle system, as
- * selecting an idle cpu will add more delays to the timers than intended
- * (as that cpu's timer base may not be uptodate wrt jiffies etc).
- */
-#define get_nohz_timer_target() sched_select_non_idle_cpu()
+extern int get_nohz_timer_target(void);
 #else
 static inline void select_nohz_load_balancer(int stop_tick) { }
 static inline void set_cpu_sd_state_idle(void) { }

kernel/hrtimer.c

@@ -160,7 +160,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer,
 static int hrtimer_get_target(int this_cpu, int pinned)
 {
 #ifdef CONFIG_NO_HZ
-	if (!pinned && get_sysctl_timer_migration())
+	if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu))
 		return get_nohz_timer_target();
 #endif
 	return this_cpu;

kernel/sched/core.c

@@ -542,6 +542,33 @@ void resched_cpu(int cpu)
 }
 
 #ifdef CONFIG_NO_HZ
+/*
+ * In the semi idle case, use the nearest busy cpu for migrating timers
+ * from an idle cpu.  This is good for power-savings.
+ *
+ * We don't do similar optimization for completely idle system, as
+ * selecting an idle cpu will add more delays to the timers than intended
+ * (as that cpu's timer base may not be uptodate wrt jiffies etc).
+ */
+int get_nohz_timer_target(void)
+{
+	int cpu = smp_processor_id();
+	int i;
+	struct sched_domain *sd;
+
+	rcu_read_lock();
+	for_each_domain(cpu, sd) {
+		for_each_cpu(i, sched_domain_span(sd)) {
+			if (!idle_cpu(i)) {
+				cpu = i;
+				goto unlock;
+			}
+		}
+	}
+unlock:
+	rcu_read_unlock();
+	return cpu;
+}
 /*
  * When add_timer_on() enqueues a timer into the timer wheel of an
  * idle CPU then this timer might expire before the next timer event
@@ -613,37 +640,6 @@ void sched_avg_update(struct rq *rq)
 	}
 }
 
-/*
- * This routine returns the cpu which is non-idle. If the local CPU isn't idle
- * OR all cpus are idle, local cpu is returned back. If local cpu is idle, then
- * we must look for another CPU which isn't idle.
- */
-int sched_select_non_idle_cpu(void)
-{
-	struct sched_domain *sd;
-	int cpu = smp_processor_id();
-	int i;
-
-	/* If Current cpu isn't idle, don't migrate anything */
-	if (!idle_cpu(cpu))
-		return cpu;
-
-	rcu_read_lock();
-	for_each_domain(cpu, sd) {
-		for_each_cpu(i, sched_domain_span(sd)) {
-			if (i == cpu)
-				continue;
-			if (!idle_cpu(i)) {
-				cpu = i;
-				goto unlock;
-			}
-		}
-	}
-unlock:
-	rcu_read_unlock();
-	return cpu;
-}
-
 #else /* !CONFIG_SMP */
 void resched_task(struct task_struct *p)
 {

kernel/timer.c

@@ -731,7 +731,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires,
 	cpu = smp_processor_id();
 
 #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
-	if (!pinned && get_sysctl_timer_migration())
+	if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu))
 		cpu = get_nohz_timer_target();
 #endif
 	new_base = per_cpu(tvec_bases, cpu);