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

Pull scheduler changes from Ingo Molnar:
 "Bigger changes:

   - sched/idle restructuring: they are WIP preparation for deeper
     integration between the scheduler and idle state selection, by
     Nicolas Pitre.

   - add NUMA scheduling pseudo-interleaving, by Rik van Riel.

   - optimize cgroup context switches, by Peter Zijlstra.

   - RT scheduling enhancements, by Thomas Gleixner.

  The rest is smaller changes, non-urgnt fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (68 commits)
  sched: Clean up the task_hot() function
  sched: Remove double calculation in fix_small_imbalance()
  sched: Fix broken setscheduler()
  sparc64, sched: Remove unused sparc64_multi_core
  sched: Remove unused mc_capable() and smt_capable()
  sched/numa: Move task_numa_free() to __put_task_struct()
  sched/fair: Fix endless loop in idle_balance()
  sched/core: Fix endless loop in pick_next_task()
  sched/fair: Push down check for high priority class task into idle_balance()
  sched/rt: Fix picking RT and DL tasks from empty queue
  trace: Replace hardcoding of 19 with MAX_NICE
  sched: Guarantee task priority in pick_next_task()
  sched/idle: Remove stale old file
  sched: Put rq's sched_avg under CONFIG_FAIR_GROUP_SCHED
  cpuidle/arm64: Remove redundant cpuidle_idle_call()
  cpuidle/powernv: Remove redundant cpuidle_idle_call()
  sched, nohz: Exclude isolated cores from load balancing
  sched: Fix select_task_rq_fair() description comments
  workqueue: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  sys: Replace hardcoding of -20 and 19 with MIN_NICE and MAX_NICE
  ...

17 files changed, 24 insertions, 83 deletions

diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84adcd2..2fe85fff5cca 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -20,9 +20,6 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_thread_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 
-#define mc_capable()	(cpu_topology[0].socket_id != -1)
-#define smt_capable()	(cpu_topology[0].thread_id != -1)
-
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 92f7b15dd221..adabeababeb0 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -30,7 +30,6 @@
 #include <linux/uaccess.h>
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
-#include <linux/cpuidle.h>
 #include <linux/leds.h>
 #include <linux/reboot.h>
 
@@ -133,7 +132,11 @@ EXPORT_SYMBOL_GPL(arm_pm_restart);
 
 void (*arm_pm_idle)(void);
 
-static void default_idle(void)
+/*
+ * Called from the core idle loop.
+ */
+
+void arch_cpu_idle(void)
 {
 	if (arm_pm_idle)
 		arm_pm_idle();
@@ -168,15 +171,6 @@ void arch_cpu_idle_dead(void)
 #endif
 
 /*
- * Called from the core idle loop.
- */
-void arch_cpu_idle(void)
-{
-	if (cpuidle_idle_call())
-		default_idle();
-}
-
-/*
  * Called by kexec, immediately prior to machine_kexec().
  *
  * This must completely disable all secondary CPUs; simply causing those CPUs
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1c0a9be2ffa8..9cce0098f4cd 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -33,7 +33,6 @@
 #include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <linux/cpuidle.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
@@ -94,10 +93,8 @@ void arch_cpu_idle(void)
 	 * This should do all the clock switching and wait for interrupt
 	 * tricks
 	 */
-	if (cpuidle_idle_call()) {
-		cpu_do_idle();
-		local_irq_enable();
-	}
+	cpu_do_idle();
+	local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index a2496e449b75..5cb55a1e606b 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -77,7 +77,6 @@ void build_cpu_to_node_map(void);
 #define topology_core_id(cpu)			(cpu_data(cpu)->core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
 #define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
-#define smt_capable() 				(smp_num_siblings > 1)
 #endif
 
 extern void arch_fix_phys_package_id(int num, u32 slot);
diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h
index 12609a17dc8b..20ea4859c822 100644
--- a/arch/mips/include/asm/topology.h
+++ b/arch/mips/include/asm/topology.h
@@ -10,8 +10,4 @@
 
 #include <topology.h>
 
-#ifdef CONFIG_SMP
-#define smt_capable()	(smp_num_siblings > 1)
-#endif
-
 #endif /* __ASM_TOPOLOGY_H */
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index d0b5fca6b077..c9202151079f 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -99,7 +99,6 @@ static inline int prrn_is_enabled(void)
 
 #ifdef CONFIG_SMP
 #include <asm/cputable.h>
-#define smt_capable()		(cpu_has_feature(CPU_FTR_SMT))
 
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 49318385d4fa..4a0a64fe25df 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -83,7 +83,6 @@ static struct timer_list spuloadavg_timer;
 #define MIN_SPU_TIMESLICE	max(5 * HZ / (1000 * SPUSCHED_TICK), 1)
 #define DEF_SPU_TIMESLICE	(100 * HZ / (1000 * SPUSCHED_TICK))
 
-#define MAX_USER_PRIO		(MAX_PRIO - MAX_RT_PRIO)
 #define SCALE_PRIO(x, prio) \
 	max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_SPU_TIMESLICE)
 
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 110f4fbd319f..81a7a0a79be7 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -26,7 +26,6 @@
 #include <linux/of_fdt.h>
 #include <linux/interrupt.h>
 #include <linux/bug.h>
-#include <linux/cpuidle.h>
 #include <linux/pci.h>
 
 #include <asm/machdep.h>
@@ -225,16 +224,6 @@ static int __init pnv_probe(void)
 	return 1;
 }
 
-void powernv_idle(void)
-{
-	/* Hook to cpuidle framework if available, else
-	 * call on default platform idle code
-	 */
-	if (cpuidle_idle_call()) {
-		power7_idle();
-	}
-}
-
 define_machine(powernv) {
 	.name			= "PowerNV",
 	.probe			= pnv_probe,
@@ -244,7 +233,7 @@ define_machine(powernv) {
 	.show_cpuinfo		= pnv_show_cpuinfo,
 	.progress		= pnv_progress,
 	.machine_shutdown	= pnv_shutdown,
-	.power_save             = powernv_idle,
+	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
 	.dma_set_mask		= pnv_dma_set_mask,
 #ifdef CONFIG_KEXEC
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 972df0ffd4dc..2db8cc691bf4 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -39,7 +39,6 @@
 #include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
-#include <linux/cpuidle.h>
 #include <linux/of.h>
 #include <linux/kexec.h>
 
@@ -356,29 +355,24 @@ early_initcall(alloc_dispatch_log_kmem_cache);
 
 static void pseries_lpar_idle(void)
 {
-	/* This would call on the cpuidle framework, and the back-end pseries
-	 * driver to  go to idle states
+	/*
+	 * Default handler to go into low thread priority and possibly
+	 * low power mode by cedeing processor to hypervisor
 	 */
-	if (cpuidle_idle_call()) {
-		/* On error, execute default handler
-		 * to go into low thread priority and possibly
-		 * low power mode by cedeing processor to hypervisor
-		 */
 
-		/* Indicate to hypervisor that we are idle. */
-		get_lppaca()->idle = 1;
+	/* Indicate to hypervisor that we are idle. */
+	get_lppaca()->idle = 1;
 
-		/*
-		 * Yield the processor to the hypervisor.  We return if
-		 * an external interrupt occurs (which are driven prior
-		 * to returning here) or if a prod occurs from another
-		 * processor. When returning here, external interrupts
-		 * are enabled.
-		 */
-		cede_processor();
+	/*
+	 * Yield the processor to the hypervisor.  We return if
+	 * an external interrupt occurs (which are driven prior
+	 * to returning here) or if a prod occurs from another
+	 * processor. When returning here, external interrupts
+	 * are enabled.
+	 */
+	cede_processor();
 
-		get_lppaca()->idle = 0;
-	}
+	get_lppaca()->idle = 0;
 }
 
 /*
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 2ea4483fd722..be616ee0cf87 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -16,7 +16,6 @@
 #include <linux/thread_info.h>
 #include <linux/irqflags.h>
 #include <linux/smp.h>
-#include <linux/cpuidle.h>
 #include <linux/atomic.h>
 #include <asm/pgalloc.h>
 #include <asm/smp.h>
@@ -40,8 +39,7 @@ void arch_cpu_idle_dead(void)
 
 void arch_cpu_idle(void)
 {
-	if (cpuidle_idle_call())
-		sh_idle();
+	sh_idle();
 }
 
 void __init select_idle_routine(void)
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index dd3bef4b9896..05710393959f 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -32,7 +32,6 @@
 
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern cpumask_t cpu_core_map[NR_CPUS];
-extern int sparc64_multi_core;
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index 1754390a426f..a2d10fc64faf 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -42,8 +42,6 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #define topology_core_id(cpu)			(cpu_data(cpu).core_id)
 #define topology_core_cpumask(cpu)		(&cpu_core_map[cpu])
 #define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
-#define mc_capable()				(sparc64_multi_core)
-#define smt_capable()				(sparc64_multi_core)
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index b90bf23e3aab..a1a4400d4025 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -896,10 +896,6 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask)
 
 	mdesc_iterate_over_cpus(fill_in_one_cpu, NULL, mask);
 
-#ifdef CONFIG_SMP
-	sparc64_multi_core = 1;
-#endif
-
 	hp = mdesc_grab();
 
 	set_core_ids(hp);
diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
index 6b39125eb927..9a690d39c01b 100644
--- a/arch/sparc/kernel/prom_64.c
+++ b/arch/sparc/kernel/prom_64.c
@@ -555,9 +555,6 @@ static void *fill_in_one_cpu(struct device_node *dp, int cpuid, int arg)
 
 		cpu_data(cpuid).core_id = portid + 1;
 		cpu_data(cpuid).proc_id = portid;
-#ifdef CONFIG_SMP
-		sparc64_multi_core = 1;
-#endif
 	} else {
 		cpu_data(cpuid).dcache_size =
 			of_getintprop_default(dp, "dcache-size", 16 * 1024);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b085311dcd0e..9781048161ab 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -53,8 +53,6 @@
 
 #include "cpumap.h"
 
-int sparc64_multi_core __read_mostly;
-
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
 	{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 1306d117967d..b28097e4c8c3 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -134,12 +134,6 @@ static inline void arch_fix_phys_package_id(int num, u32 slot)
 struct pci_bus;
 void x86_pci_root_bus_resources(int bus, struct list_head *resources);
 
-#ifdef CONFIG_SMP
-#define mc_capable()	((boot_cpu_data.x86_max_cores > 1) && \
-			(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
-#define smt_capable()			(smp_num_siblings > 1)
-#endif
-
 #ifdef CONFIG_NUMA
 extern int get_mp_bus_to_node(int busnum);
 extern void set_mp_bus_to_node(int busnum, int node);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3fb8d95ab8b5..4505e2a950d8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -298,10 +298,7 @@ void arch_cpu_idle_dead(void)
  */
 void arch_cpu_idle(void)
 {
-	if (cpuidle_idle_call())
-		x86_idle();
-	else
-		local_irq_enable();
+	x86_idle();
 }
 
 /*