Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/l…

…inux/kernel/git/tip/tip

Pull more scheduler updates from Ingo Molnar:
 "Second round of scheduler changes:
   - try-to-wakeup and IPI reduction speedups, from Andy Lutomirski
   - continued power scheduling cleanups and refactorings, from Nicolas
     Pitre
   - misc fixes and enhancements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Delete extraneous extern for to_ratio()
  sched/idle: Optimize try-to-wake-up IPI
  sched/idle: Simplify wake_up_idle_cpu()
  sched/idle: Clear polling before descheduling the idle thread
  sched, trace: Add a tracepoint for IPI-less remote wakeups
  cpuidle: Set polling in poll_idle
  sched: Remove redundant assignment to "rt_rq" in update_curr_rt(...)
  sched: Rename capacity related flags
  sched: Final power vs. capacity cleanups
  sched: Remove remaining dubious usage of "power"
  sched: Let 'struct sched_group_power' care about CPU capacity
  sched/fair: Disambiguate existing/remaining "capacity" usage
  sched/fair: Change "has_capacity" to "has_free_capacity"
  sched/fair: Remove "power" from 'struct numa_stats'
  sched: Fix signedness bug in yield_to()
  sched/fair: Use time_after() in record_wakee()
  sched/balancing: Reduce the rate of needless idle load balancing
  sched/fair: Fix unlocked reads of some cfs_b->quota/period

arch/arm/kernel/topology.c

@@ -26,30 +26,30 @@
 #include <asm/topology.h>
 
 /*
- * cpu power scale management
+ * cpu capacity scale management
  */
 
 /*
- * cpu power table
+ * cpu capacity table
  * This per cpu data structure describes the relative capacity of each core.
  * On a heteregenous system, cores don't have the same computation capacity
- * and we reflect that difference in the cpu_power field so the scheduler can
- * take this difference into account during load balance. A per cpu structure
- * is preferred because each CPU updates its own cpu_power field during the
- * load balance except for idle cores. One idle core is selected to run the
- * rebalance_domains for all idle cores and the cpu_power can be updated
- * during this sequence.
+ * and we reflect that difference in the cpu_capacity field so the scheduler
+ * can take this difference into account during load balance. A per cpu
+ * structure is preferred because each CPU updates its own cpu_capacity field
+ * during the load balance except for idle cores. One idle core is selected
+ * to run the rebalance_domains for all idle cores and the cpu_capacity can be
+ * updated during this sequence.
  */
 static DEFINE_PER_CPU(unsigned long, cpu_scale);
 
-unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
 {
 	return per_cpu(cpu_scale, cpu);
 }
 
-static void set_power_scale(unsigned int cpu, unsigned long power)
+static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
 {
-	per_cpu(cpu_scale, cpu) = power;
+	per_cpu(cpu_scale, cpu) = capacity;
 }
 
 #ifdef CONFIG_OF
@@ -62,11 +62,11 @@ struct cpu_efficiency {
  * Table of relative efficiency of each processors
  * The efficiency value must fit in 20bit and the final
  * cpu_scale value must be in the range
- *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ *   0 < cpu_scale < 3*SCHED_CAPACITY_SCALE/2
  * in order to return at most 1 when DIV_ROUND_CLOSEST
  * is used to compute the capacity of a CPU.
  * Processors that are not defined in the table,
- * use the default SCHED_POWER_SCALE value for cpu_scale.
+ * use the default SCHED_CAPACITY_SCALE value for cpu_scale.
  */
 static const struct cpu_efficiency table_efficiency[] = {
 	{"arm,cortex-a15", 3891},
@@ -83,9 +83,9 @@ static unsigned long middle_capacity = 1;
  * Iterate all CPUs' descriptor in DT and compute the efficiency
  * (as per table_efficiency). Also calculate a middle efficiency
  * as close as possible to  (max{eff_i} - min{eff_i}) / 2
- * This is later used to scale the cpu_power field such that an
- * 'average' CPU is of middle power. Also see the comments near
- * table_efficiency[] and update_cpu_power().
+ * This is later used to scale the cpu_capacity field such that an
+ * 'average' CPU is of middle capacity. Also see the comments near
+ * table_efficiency[] and update_cpu_capacity().
  */
 static void __init parse_dt_topology(void)
 {
@@ -141,15 +141,15 @@ static void __init parse_dt_topology(void)
 	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
 	 * compute a middle_capacity factor that will ensure that the capacity
 	 * of an 'average' CPU of the system will be as close as possible to
-	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * SCHED_CAPACITY_SCALE, which is the default value, but with the
 	 * constraint explained near table_efficiency[].
 	 */
 	if (4*max_capacity < (3*(max_capacity + min_capacity)))
 		middle_capacity = (min_capacity + max_capacity)
-				>> (SCHED_POWER_SHIFT+1);
+				>> (SCHED_CAPACITY_SHIFT+1);
 	else
 		middle_capacity = ((max_capacity / 3)
-				>> (SCHED_POWER_SHIFT-1)) + 1;
+				>> (SCHED_CAPACITY_SHIFT-1)) + 1;
 
 }
 
@@ -158,20 +158,20 @@ static void __init parse_dt_topology(void)
  * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
  * function returns directly for SMP system.
  */
-static void update_cpu_power(unsigned int cpu)
+static void update_cpu_capacity(unsigned int cpu)
 {
 	if (!cpu_capacity(cpu))
 		return;
 
-	set_power_scale(cpu, cpu_capacity(cpu) / middle_capacity);
+	set_capacity_scale(cpu, cpu_capacity(cpu) / middle_capacity);
 
-	printk(KERN_INFO "CPU%u: update cpu_power %lu\n",
-		cpu, arch_scale_freq_power(NULL, cpu));
+	printk(KERN_INFO "CPU%u: update cpu_capacity %lu\n",
+		cpu, arch_scale_freq_capacity(NULL, cpu));
 }
 
 #else
 static inline void parse_dt_topology(void) {}
-static inline void update_cpu_power(unsigned int cpuid) {}
+static inline void update_cpu_capacity(unsigned int cpuid) {}
 #endif
 
  /*
@@ -267,7 +267,7 @@ void store_cpu_topology(unsigned int cpuid)
 
 	update_siblings_masks(cpuid);
 
-	update_cpu_power(cpuid);
+	update_cpu_capacity(cpuid);
 
 	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
 		cpuid, cpu_topology[cpuid].thread_id,
@@ -297,7 +297,7 @@ void __init init_cpu_topology(void)
 {
 	unsigned int cpu;
 
-	/* init core mask and power*/
+	/* init core mask and capacity */
 	for_each_possible_cpu(cpu) {
 		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
 
@@ -307,7 +307,7 @@ void __init init_cpu_topology(void)
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
 
-		set_power_scale(cpu, SCHED_POWER_SCALE);
+		set_capacity_scale(cpu, SCHED_CAPACITY_SCALE);
 	}
 	smp_wmb();
 

arch/powerpc/kernel/smp.c

@@ -749,7 +749,7 @@ int setup_profiling_timer(unsigned int multiplier)
 /* cpumask of CPUs with asymetric SMT dependancy */
 static const int powerpc_smt_flags(void)
 {
-	int flags = SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
+	int flags = SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
 
 	if (cpu_has_feature(CPU_FTR_ASYM_SMT)) {
 		printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n");

drivers/cpuidle/driver.c

@@ -187,8 +187,11 @@ static int poll_idle(struct cpuidle_device *dev,
 
 	t1 = ktime_get();
 	local_irq_enable();
-	while (!need_resched())
-		cpu_relax();
+	if (!current_set_polling_and_test()) {
+		while (!need_resched())
+			cpu_relax();
+	}
+	current_clr_polling();
 
 	t2 = ktime_get();
 	diff = ktime_to_us(ktime_sub(t2, t1));

include/linux/kvm_host.h

@@ -586,7 +586,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
-bool kvm_vcpu_yield_to(struct kvm_vcpu *target);
+int kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);

include/linux/sched.h

@@ -847,10 +847,10 @@ enum cpu_idle_type {
 };
 
 /*
- * Increase resolution of cpu_power calculations
+ * Increase resolution of cpu_capacity calculations
  */
-#define SCHED_POWER_SHIFT	10
-#define SCHED_POWER_SCALE	(1L << SCHED_POWER_SHIFT)
+#define SCHED_CAPACITY_SHIFT	10
+#define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
 
 /*
  * sched-domains (multiprocessor balancing) declarations:
@@ -862,7 +862,7 @@ enum cpu_idle_type {
 #define SD_BALANCE_FORK		0x0008	/* Balance on fork, clone */
 #define SD_BALANCE_WAKE		0x0010  /* Balance on wakeup */
 #define SD_WAKE_AFFINE		0x0020	/* Wake task to waking CPU */
-#define SD_SHARE_CPUPOWER	0x0080	/* Domain members share cpu power */
+#define SD_SHARE_CPUCAPACITY	0x0080	/* Domain members share cpu power */
 #define SD_SHARE_POWERDOMAIN	0x0100	/* Domain members share power domain */
 #define SD_SHARE_PKG_RESOURCES	0x0200	/* Domain members share cpu pkg resources */
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
@@ -874,7 +874,7 @@ enum cpu_idle_type {
 #ifdef CONFIG_SCHED_SMT
 static inline const int cpu_smt_flags(void)
 {
-	return SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES;
+	return SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES;
 }
 #endif
 
@@ -1006,7 +1006,7 @@ typedef const int (*sched_domain_flags_f)(void);
 struct sd_data {
 	struct sched_domain **__percpu sd;
 	struct sched_group **__percpu sg;
-	struct sched_group_power **__percpu sgp;
+	struct sched_group_capacity **__percpu sgc;
 };
 
 struct sched_domain_topology_level {
@@ -2173,7 +2173,7 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { }
 static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 #endif
 
-extern bool yield_to(struct task_struct *p, bool preempt);
+extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
 /**

include/trace/events/sched.h

@@ -530,6 +530,26 @@ TRACE_EVENT(sched_swap_numa,
 			__entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
 			__entry->dst_cpu, __entry->dst_nid)
 );
+
+/*
+ * Tracepoint for waking a polling cpu without an IPI.
+ */
+TRACE_EVENT(sched_wake_idle_without_ipi,
+
+	TP_PROTO(int cpu),
+
+	TP_ARGS(cpu),
+
+	TP_STRUCT__entry(
+		__field(	int,	cpu	)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+	),
+
+	TP_printk("cpu=%d", __entry->cpu)
+);
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */