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

Conflicts:
	drivers/cpufreq/cpufreq_conservative.c
	drivers/cpufreq/cpufreq_ondemand.c
	drivers/macintosh/rack-meter.c
	fs/proc/stat.c
	fs/proc/uptime.c
	kernel/sched/core.c

arch/s390/appldata/appldata_os.c

@@ -115,21 +115,21 @@ static void appldata_get_os_data(void *data)
 	j = 0;
 	for_each_online_cpu(i) {
 		os_data->os_cpu[j].per_cpu_user =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.user);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_USER]);
 		os_data->os_cpu[j].per_cpu_nice =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.nice);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_NICE]);
 		os_data->os_cpu[j].per_cpu_system =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.system);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM]);
 		os_data->os_cpu[j].per_cpu_idle =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.idle);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IDLE]);
 		os_data->os_cpu[j].per_cpu_irq =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.irq);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IRQ]);
 		os_data->os_cpu[j].per_cpu_softirq =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.softirq);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ]);
 		os_data->os_cpu[j].per_cpu_iowait =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.iowait);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_IOWAIT]);
 		os_data->os_cpu[j].per_cpu_steal =
-			cputime_to_jiffies(kstat_cpu(i).cpustat.steal);
+			cputime_to_jiffies(kcpustat_cpu(i).cpustat[CPUTIME_STEAL]);
 		os_data->os_cpu[j].cpu_id = i;
 		j++;
 	}

arch/x86/include/asm/i387.h

@@ -218,7 +218,7 @@ static inline void fpu_fxsave(struct fpu *fpu)
 #ifdef CONFIG_SMP
 #define safe_address (__per_cpu_offset[0])
 #else
-#define safe_address (kstat_cpu(0).cpustat.user)
+#define safe_address (__get_cpu_var(kernel_cpustat).cpustat[CPUTIME_USER])
 #endif
 
 /*

drivers/cpufreq/cpufreq_conservative.c

@@ -95,26 +95,26 @@ static struct dbs_tuners {
 	.freq_step = 5,
 };
 
-static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu,
-							cputime64_t *wall)
+static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
-	cputime64_t idle_time;
-	cputime64_t cur_wall_time;
-	cputime64_t busy_time;
+	u64 idle_time;
+	u64 cur_wall_time;
+	u64 busy_time;
 
 	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
-	busy_time  = kstat_cpu(cpu).cpustat.user;
-	busy_time += kstat_cpu(cpu).cpustat.system;
-	busy_time += kstat_cpu(cpu).cpustat.irq;
-	busy_time += kstat_cpu(cpu).cpustat.softirq;
-	busy_time += kstat_cpu(cpu).cpustat.steal;
-	busy_time += kstat_cpu(cpu).cpustat.nice;
+
+	busy_time  = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)
-		*wall = (cputime64_t)jiffies_to_usecs(cur_wall_time);
+		*wall = jiffies_to_usecs(cur_wall_time);
 
-	return (cputime64_t)jiffies_to_usecs(idle_time);
+	return jiffies_to_usecs(idle_time);
 }
 
 static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
@@ -271,7 +271,7 @@ static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
 						&dbs_info->prev_cpu_wall);
 		if (dbs_tuners_ins.ignore_nice)
-			dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;
+			dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 	}
 	return count;
 }
@@ -361,10 +361,10 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 		j_dbs_info->prev_cpu_idle = cur_idle_time;
 
 		if (dbs_tuners_ins.ignore_nice) {
-			cputime64_t cur_nice;
+			u64 cur_nice;
 			unsigned long cur_nice_jiffies;
 
-			cur_nice = kstat_cpu(j).cpustat.nice -
+			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
 					 j_dbs_info->prev_cpu_nice;
 			/*
 			 * Assumption: nice time between sampling periods will
@@ -373,7 +373,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 			cur_nice_jiffies = (unsigned long)
 					cputime64_to_jiffies64(cur_nice);
 
-			j_dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;
+			j_dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 			idle_time += jiffies_to_usecs(cur_nice_jiffies);
 		}
 
@@ -500,10 +500,9 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
 						&j_dbs_info->prev_cpu_wall);
-			if (dbs_tuners_ins.ignore_nice) {
+			if (dbs_tuners_ins.ignore_nice)
 				j_dbs_info->prev_cpu_nice =
-						kstat_cpu(j).cpustat.nice;
-			}
+						kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 		}
 		this_dbs_info->down_skip = 0;
 		this_dbs_info->requested_freq = policy->cur;

drivers/cpufreq/cpufreq_ondemand.c

@@ -119,26 +119,26 @@ static struct dbs_tuners {
 	.powersave_bias = 0,
 };
 
-static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu,
-							cputime64_t *wall)
+static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
-	cputime64_t idle_time;
-	cputime64_t cur_wall_time;
-	cputime64_t busy_time;
+	u64 idle_time;
+	u64 cur_wall_time;
+	u64 busy_time;
 
 	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
-	busy_time  = kstat_cpu(cpu).cpustat.user;
-	busy_time += kstat_cpu(cpu).cpustat.system;
-	busy_time += kstat_cpu(cpu).cpustat.irq;
-	busy_time += kstat_cpu(cpu).cpustat.softirq;
-	busy_time += kstat_cpu(cpu).cpustat.steal;
-	busy_time += kstat_cpu(cpu).cpustat.nice;
+
+	busy_time  = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
 
 	idle_time = cur_wall_time - busy_time;
 	if (wall)
-		*wall = (cputime64_t)jiffies_to_usecs(cur_wall_time);
+		*wall = jiffies_to_usecs(cur_wall_time);
 
-	return (cputime64_t)jiffies_to_usecs(idle_time);
+	return jiffies_to_usecs(idle_time);
 }
 
 static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
@@ -344,7 +344,7 @@ static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
 						&dbs_info->prev_cpu_wall);
 		if (dbs_tuners_ins.ignore_nice)
-			dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;
+			dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
 	}
 	return count;
@@ -454,10 +454,10 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 		j_dbs_info->prev_cpu_iowait = cur_iowait_time;
 
 		if (dbs_tuners_ins.ignore_nice) {
-			cputime64_t cur_nice;
+			u64 cur_nice;
 			unsigned long cur_nice_jiffies;
 
-			cur_nice = kstat_cpu(j).cpustat.nice -
+			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
 					 j_dbs_info->prev_cpu_nice;
 			/*
 			 * Assumption: nice time between sampling periods will
@@ -466,7 +466,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
 			cur_nice_jiffies = (unsigned long)
 					cputime64_to_jiffies64(cur_nice);
 
-			j_dbs_info->prev_cpu_nice = kstat_cpu(j).cpustat.nice;
+			j_dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 			idle_time += jiffies_to_usecs(cur_nice_jiffies);
 		}
 
@@ -645,10 +645,9 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 
 			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
 						&j_dbs_info->prev_cpu_wall);
-			if (dbs_tuners_ins.ignore_nice) {
+			if (dbs_tuners_ins.ignore_nice)
 				j_dbs_info->prev_cpu_nice =
-						kstat_cpu(j).cpustat.nice;
-			}
+						kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 		}
 		this_dbs_info->cpu = cpu;
 		this_dbs_info->rate_mult = 1;

drivers/macintosh/rack-meter.c

@@ -81,12 +81,13 @@ static int rackmeter_ignore_nice;
  */
 static inline cputime64_t get_cpu_idle_time(unsigned int cpu)
 {
-	cputime64_t retval;
+	u64 retval;
 
-	retval = kstat_cpu(cpu).cpustat.idle + kstat_cpu(cpu).cpustat.iowait;
+	retval = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE] +
+		 kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 
 	if (rackmeter_ignore_nice)
-		retval += kstat_cpu(cpu).cpustat.nice;
+		retval += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
 
 	return retval;
 }

fs/proc/stat.c

@@ -22,14 +22,13 @@
 #define arch_idle_time(cpu) 0
 #endif
 
-static cputime64_t get_idle_time(int cpu)
+static u64 get_idle_time(int cpu)
 {
-	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
-	cputime64_t idle;
+	u64 idle, idle_time = get_cpu_idle_time_us(cpu, NULL);
 
 	if (idle_time == -1ULL) {
 		/* !NO_HZ so we can rely on cpustat.idle */
-		idle = kstat_cpu(cpu).cpustat.idle;
+		idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 		idle += arch_idle_time(cpu);
 	} else
 		idle = nsecs_to_jiffies64(1000 * idle_time);
@@ -37,14 +36,13 @@ static cputime64_t get_idle_time(int cpu)
 	return idle;
 }
 
-static cputime64_t get_iowait_time(int cpu)
+static u64 get_iowait_time(int cpu)
 {
-	u64 iowait_time = get_cpu_iowait_time_us(cpu, NULL);
-	cputime64_t iowait;
+	u64 iowait, iowait_time = get_cpu_iowait_time_us(cpu, NULL);
 
 	if (iowait_time == -1ULL)
 		/* !NO_HZ so we can rely on cpustat.iowait */
-		iowait = kstat_cpu(cpu).cpustat.iowait;
+		iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	else
 		iowait = nsecs_to_jiffies64(1000 * iowait_time);
 
@@ -55,8 +53,8 @@ static int show_stat(struct seq_file *p, void *v)
 {
 	int i, j;
 	unsigned long jif;
-	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
-	cputime64_t guest, guest_nice;
+	u64 user, nice, system, idle, iowait, irq, softirq, steal;
+	u64 guest, guest_nice;
 	u64 sum = 0;
 	u64 sum_softirq = 0;
 	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
@@ -69,18 +67,16 @@ static int show_stat(struct seq_file *p, void *v)
 	jif = boottime.tv_sec;
 
 	for_each_possible_cpu(i) {
-		user += kstat_cpu(i).cpustat.user;
-		nice += kstat_cpu(i).cpustat.nice;
-		system += kstat_cpu(i).cpustat.system;
+		user += kcpustat_cpu(i).cpustat[CPUTIME_USER];
+		nice += kcpustat_cpu(i).cpustat[CPUTIME_NICE];
+		system += kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
 		idle += get_idle_time(i);
 		iowait += get_iowait_time(i);
-		irq += kstat_cpu(i).cpustat.irq;
-		softirq += kstat_cpu(i).cpustat.softirq;
-		steal += kstat_cpu(i).cpustat.steal;
-		guest += kstat_cpu(i).cpustat.guest;
-		guest_nice += kstat_cpu(i).cpustat.guest_nice;
-		sum += kstat_cpu_irqs_sum(i);
-		sum += arch_irq_stat_cpu(i);
+		irq += kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
+		softirq += kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
+		steal += kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
+		guest += kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
+		guest_nice += kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
 
 		for (j = 0; j < NR_SOFTIRQS; j++) {
 			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
@@ -105,16 +101,16 @@ static int show_stat(struct seq_file *p, void *v)
 		(unsigned long long)cputime64_to_clock_t(guest_nice));
 	for_each_online_cpu(i) {
 		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
-		user = kstat_cpu(i).cpustat.user;
-		nice = kstat_cpu(i).cpustat.nice;
-		system = kstat_cpu(i).cpustat.system;
+		user = kcpustat_cpu(i).cpustat[CPUTIME_USER];
+		nice = kcpustat_cpu(i).cpustat[CPUTIME_NICE];
+		system = kcpustat_cpu(i).cpustat[CPUTIME_SYSTEM];
 		idle = get_idle_time(i);
 		iowait = get_iowait_time(i);
-		irq = kstat_cpu(i).cpustat.irq;
-		softirq = kstat_cpu(i).cpustat.softirq;
-		steal = kstat_cpu(i).cpustat.steal;
-		guest = kstat_cpu(i).cpustat.guest;
-		guest_nice = kstat_cpu(i).cpustat.guest_nice;
+		irq = kcpustat_cpu(i).cpustat[CPUTIME_IRQ];
+		softirq = kcpustat_cpu(i).cpustat[CPUTIME_SOFTIRQ];
+		steal = kcpustat_cpu(i).cpustat[CPUTIME_STEAL];
+		guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
+		guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
 		seq_printf(p,
 			"cpu%d %llu %llu %llu %llu %llu %llu %llu %llu %llu "
 			"%llu\n",

fs/proc/uptime.c

@@ -11,14 +11,14 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec uptime;
 	struct timespec idle;
-	cputime64_t idletime;
+	u64 idletime;
 	u64 nsec;
 	u32 rem;
 	int i;
 
 	idletime = 0;
 	for_each_possible_cpu(i)
-		idletime += kstat_cpu(i).cpustat.idle;
+		idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
 
 	do_posix_clock_monotonic_gettime(&uptime);
 	monotonic_to_bootbased(&uptime);

include/linux/kernel_stat.h

@@ -6,6 +6,7 @@
 #include <linux/percpu.h>
 #include <linux/cpumask.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <asm/irq.h>
 #include <asm/cputime.h>
 
@@ -15,21 +16,25 @@
  * used by rstatd/perfmeter
  */
 
-struct cpu_usage_stat {
-	cputime64_t user;
-	cputime64_t nice;
-	cputime64_t system;
-	cputime64_t softirq;
-	cputime64_t irq;
-	cputime64_t idle;
-	cputime64_t iowait;
-	cputime64_t steal;
-	cputime64_t guest;
-	cputime64_t guest_nice;
+enum cpu_usage_stat {
+	CPUTIME_USER,
+	CPUTIME_NICE,
+	CPUTIME_SYSTEM,
+	CPUTIME_SOFTIRQ,
+	CPUTIME_IRQ,
+	CPUTIME_IDLE,
+	CPUTIME_IOWAIT,
+	CPUTIME_STEAL,
+	CPUTIME_GUEST,
+	CPUTIME_GUEST_NICE,
+	NR_STATS,
+};
+
+struct kernel_cpustat {
+	u64 cpustat[NR_STATS];
 };
 
 struct kernel_stat {
-	struct cpu_usage_stat	cpustat;
 #ifndef CONFIG_GENERIC_HARDIRQS
        unsigned int irqs[NR_IRQS];
 #endif
@@ -38,10 +43,13 @@ struct kernel_stat {
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
+DECLARE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 
-#define kstat_cpu(cpu)	per_cpu(kstat, cpu)
 /* Must have preemption disabled for this to be meaningful. */
-#define kstat_this_cpu	__get_cpu_var(kstat)
+#define kstat_this_cpu (&__get_cpu_var(kstat))
+#define kcpustat_this_cpu (&__get_cpu_var(kernel_cpustat))
+#define kstat_cpu(cpu) per_cpu(kstat, cpu)
+#define kcpustat_cpu(cpu) per_cpu(kernel_cpustat, cpu)
 
 extern unsigned long long nr_context_switches(void);
 

include/linux/latencytop.h

@@ -10,6 +10,8 @@
 #define _INCLUDE_GUARD_LATENCYTOP_H_
 
 #include <linux/compiler.h>
+struct task_struct;
+
 #ifdef CONFIG_LATENCYTOP
 
 #define LT_SAVECOUNT		32
@@ -23,7 +25,6 @@ struct latency_record {
 };
 
 
-struct task_struct;
 
 extern int latencytop_enabled;
 void __account_scheduler_latency(struct task_struct *task, int usecs, int inter);

include/linux/sched.h

@@ -273,9 +273,11 @@ extern int runqueue_is_locked(int cpu);
 
 #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);
 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) { }
 #endif
 
 /*
@@ -901,6 +903,10 @@ struct sched_group_power {
 	 * single CPU.
 	 */
 	unsigned int power, power_orig;
+	/*
+	 * Number of busy cpus in this group.
+	 */
+	atomic_t nr_busy_cpus;
 };
 
 struct sched_group {
@@ -925,6 +931,15 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
 	return to_cpumask(sg->cpumask);
 }
 
+/**
+ * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
+ * @group: The group whose first cpu is to be returned.
+ */
+static inline unsigned int group_first_cpu(struct sched_group *group)
+{
+	return cpumask_first(sched_group_cpus(group));
+}
+
 struct sched_domain_attr {
 	int relax_domain_level;
 };
@@ -1315,8 +1330,8 @@ struct task_struct {
 	 * older sibling, respectively.  (p->father can be replaced with 
 	 * p->real_parent->pid)
 	 */
-	struct task_struct *real_parent; /* real parent process */
-	struct task_struct *parent; /* recipient of SIGCHLD, wait4() reports */
+	struct task_struct __rcu *real_parent; /* real parent process */
+	struct task_struct __rcu *parent; /* recipient of SIGCHLD, wait4() reports */
 	/*
 	 * children/sibling forms the list of my natural children
 	 */

include/trace/events/sched.h

@@ -330,6 +330,13 @@ DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
 	     TP_PROTO(struct task_struct *tsk, u64 delay),
 	     TP_ARGS(tsk, delay));
 
+/*
+ * Tracepoint for accounting blocked time (time the task is in uninterruptible).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
 /*
  * Tracepoint for accounting runtime (time the task is executing
  * on a CPU).

kernel/Makefile

@@ -2,16 +2,15 @@
 # Makefile for the linux kernel.
 #
 
-obj-y     = sched.o fork.o exec_domain.o panic.o printk.o \
+obj-y     = fork.o exec_domain.o panic.o printk.o \
 	    cpu.o exit.o itimer.o time.o softirq.o resource.o \
 	    sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
 	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
 	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
-	    notifier.o ksysfs.o sched_clock.o cred.o \
-	    async.o range.o
-obj-y += groups.o
+	    notifier.o ksysfs.o cred.o \
+	    async.o range.o groups.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -20,10 +19,11 @@ CFLAGS_REMOVE_lockdep_proc.o = -pg
 CFLAGS_REMOVE_mutex-debug.o = -pg
 CFLAGS_REMOVE_rtmutex-debug.o = -pg
 CFLAGS_REMOVE_cgroup-debug.o = -pg
-CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
+obj-y += sched/
+
 obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
@@ -99,7 +99,6 @@ obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_X86_DS) += trace/
 obj-$(CONFIG_RING_BUFFER) += trace/
 obj-$(CONFIG_TRACEPOINTS) += trace/
-obj-$(CONFIG_SMP) += sched_cpupri.o
 obj-$(CONFIG_IRQ_WORK) += irq_work.o
 obj-$(CONFIG_CPU_PM) += cpu_pm.o
 
@@ -110,15 +109,6 @@ obj-$(CONFIG_PADATA) += padata.o
 obj-$(CONFIG_CRASH_DUMP) += crash_dump.o
 obj-$(CONFIG_JUMP_LABEL) += jump_label.o
 
-ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
-# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
-# needed for x86 only.  Why this used to be enabled for all architectures is beyond
-# me.  I suspect most platforms don't need this, but until we know that for sure
-# I turn this off for IA-64 only.  Andreas Schwab says it's also needed on m68k
-# to get a correct value for the wait-channel (WCHAN in ps). --davidm
-CFLAGS_sched.o := $(PROFILING) -fno-omit-frame-pointer
-endif
-
 $(obj)/configs.o: $(obj)/config_data.h
 
 # config_data.h contains the same information as ikconfig.h but gzipped.

kernel/sched/Makefile

+ifdef CONFIG_FUNCTION_TRACER
+CFLAGS_REMOVE_clock.o = -pg
+endif
+
+ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
+# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
+# needed for x86 only.  Why this used to be enabled for all architectures is beyond
+# me.  I suspect most platforms don't need this, but until we know that for sure
+# I turn this off for IA-64 only.  Andreas Schwab says it's also needed on m68k
+# to get a correct value for the wait-channel (WCHAN in ps). --davidm
+CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
+endif
+
+obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SCHEDSTATS) += stats.o
+obj-$(CONFIG_SCHED_DEBUG) += debug.o
+
+

kernel/sched_autogroup.c → kernel/sched/auto_group.c

 #ifdef CONFIG_SCHED_AUTOGROUP
 
+#include "sched.h"
+
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
+#include <linux/security.h>
+#include <linux/export.h>
 
 unsigned int __read_mostly sysctl_sched_autogroup_enabled = 1;
 static struct autogroup autogroup_default;
 static atomic_t autogroup_seq_nr;
 
-static void __init autogroup_init(struct task_struct *init_task)
+void __init autogroup_init(struct task_struct *init_task)
 {
 	autogroup_default.tg = &root_task_group;
 	kref_init(&autogroup_default.kref);
@@ -17,7 +21,7 @@ static void __init autogroup_init(struct task_struct *init_task)
 	init_task->signal->autogroup = &autogroup_default;
 }
 
-static inline void autogroup_free(struct task_group *tg)
+void autogroup_free(struct task_group *tg)
 {
 	kfree(tg->autogroup);
 }
@@ -59,10 +63,6 @@ static inline struct autogroup *autogroup_task_get(struct task_struct *p)
 	return ag;
 }
 
-#ifdef CONFIG_RT_GROUP_SCHED
-static void free_rt_sched_group(struct task_group *tg);
-#endif
-
 static inline struct autogroup *autogroup_create(void)
 {
 	struct autogroup *ag = kzalloc(sizeof(*ag), GFP_KERNEL);
@@ -108,8 +108,7 @@ static inline struct autogroup *autogroup_create(void)
 	return autogroup_kref_get(&autogroup_default);
 }
 
-static inline bool
-task_wants_autogroup(struct task_struct *p, struct task_group *tg)
+bool task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 {
 	if (tg != &root_task_group)
 		return false;
@@ -127,22 +126,6 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 	return true;
 }
 
-static inline bool task_group_is_autogroup(struct task_group *tg)
-{
-	return !!tg->autogroup;
-}
-
-static inline struct task_group *
-autogroup_task_group(struct task_struct *p, struct task_group *tg)
-{
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (enabled && task_wants_autogroup(p, tg))
-		return p->signal->autogroup->tg;
-
-	return tg;
-}
-
 static void
 autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 {
@@ -263,7 +246,7 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SCHED_DEBUG
-static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
+int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
 	if (!task_group_is_autogroup(tg))
 		return 0;

kernel/sched_autogroup.h → kernel/sched/auto_group.h

 #ifdef CONFIG_SCHED_AUTOGROUP
 
+#include <linux/kref.h>
+#include <linux/rwsem.h>
+
 struct autogroup {
 	/*
 	 * reference doesn't mean how many thread attach to this
@@ -13,9 +16,28 @@ struct autogroup {
 	int			nice;
 };
 
-static inline bool task_group_is_autogroup(struct task_group *tg);
+extern void autogroup_init(struct task_struct *init_task);
+extern void autogroup_free(struct task_group *tg);
+
+static inline bool task_group_is_autogroup(struct task_group *tg)
+{
+	return !!tg->autogroup;
+}
+
+extern bool task_wants_autogroup(struct task_struct *p, struct task_group *tg);
+
 static inline struct task_group *
-autogroup_task_group(struct task_struct *p, struct task_group *tg);
+autogroup_task_group(struct task_struct *p, struct task_group *tg)
+{
+	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
+
+	if (enabled && task_wants_autogroup(p, tg))
+		return p->signal->autogroup->tg;
+
+	return tg;
+}
+
+extern int autogroup_path(struct task_group *tg, char *buf, int buflen);
 
 #else /* !CONFIG_SCHED_AUTOGROUP */
 

kernel/sched_cpupri.c → kernel/sched/cpupri.c

 /*
- *  kernel/sched_cpupri.c
+ *  kernel/sched/cpupri.c
  *
  *  CPU priority management
  *
@@ -28,7 +28,7 @@
  */
 
 #include <linux/gfp.h>
-#include "sched_cpupri.h"
+#include "cpupri.h"
 
 /* Convert between a 140 based task->prio, and our 102 based cpupri */
 static int convert_prio(int prio)

kernel/sched_debug.c → kernel/sched/debug.c

 /*
- * kernel/time/sched_debug.c
+ * kernel/sched/debug.c
  *
  * Print the CFS rbtree
  *
@@ -16,6 +16,8 @@
 #include <linux/kallsyms.h>
 #include <linux/utsname.h>
 
+#include "sched.h"
+
 static DEFINE_SPINLOCK(sched_debug_lock);
 
 /*
@@ -373,7 +375,7 @@ static int sched_debug_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static void sysrq_sched_debug_show(void)
+void sysrq_sched_debug_show(void)
 {
 	sched_debug_show(NULL, NULL);
 }

kernel/sched_features.h → kernel/sched/features.h

@@ -3,13 +3,13 @@
  * them to run sooner, but does not allow tons of sleepers to
  * rip the spread apart.
  */
-SCHED_FEAT(GENTLE_FAIR_SLEEPERS, 1)
+SCHED_FEAT(GENTLE_FAIR_SLEEPERS, true)
 
 /*
  * Place new tasks ahead so that they do not starve already running
  * tasks
  */
-SCHED_FEAT(START_DEBIT, 1)
+SCHED_FEAT(START_DEBIT, true)
 
 /*
  * Based on load and program behaviour, see if it makes sense to place
@@ -17,54 +17,54 @@ SCHED_FEAT(START_DEBIT, 1)
  * improve cache locality. Typically used with SYNC wakeups as
  * generated by pipes and the like, see also SYNC_WAKEUPS.
  */
-SCHED_FEAT(AFFINE_WAKEUPS, 1)
+SCHED_FEAT(AFFINE_WAKEUPS, true)
 
 /*
  * Prefer to schedule the task we woke last (assuming it failed
  * wakeup-preemption), since its likely going to consume data we
  * touched, increases cache locality.
  */
-SCHED_FEAT(NEXT_BUDDY, 0)
+SCHED_FEAT(NEXT_BUDDY, false)
 
 /*
  * Prefer to schedule the task that ran last (when we did
  * wake-preempt) as that likely will touch the same data, increases
  * cache locality.
  */
-SCHED_FEAT(LAST_BUDDY, 1)
+SCHED_FEAT(LAST_BUDDY, true)
 
 /*
  * Consider buddies to be cache hot, decreases the likelyness of a
  * cache buddy being migrated away, increases cache locality.
  */
-SCHED_FEAT(CACHE_HOT_BUDDY, 1)
+SCHED_FEAT(CACHE_HOT_BUDDY, true)
 
 /*
  * Use arch dependent cpu power functions
  */
-SCHED_FEAT(ARCH_POWER, 0)
+SCHED_FEAT(ARCH_POWER, false)
 
-SCHED_FEAT(HRTICK, 0)
-SCHED_FEAT(DOUBLE_TICK, 0)
-SCHED_FEAT(LB_BIAS, 1)
+SCHED_FEAT(HRTICK, false)
+SCHED_FEAT(DOUBLE_TICK, false)
+SCHED_FEAT(LB_BIAS, true)
 
 /*
  * Spin-wait on mutex acquisition when the mutex owner is running on
  * another cpu -- assumes that when the owner is running, it will soon
  * release the lock. Decreases scheduling overhead.
  */
-SCHED_FEAT(OWNER_SPIN, 1)
+SCHED_FEAT(OWNER_SPIN, true)
 
 /*
  * Decrement CPU power based on time not spent running tasks
  */
-SCHED_FEAT(NONTASK_POWER, 1)
+SCHED_FEAT(NONTASK_POWER, true)
 
 /*
  * Queue remote wakeups on the target CPU and process them
  * using the scheduler IPI. Reduces rq->lock contention/bounces.
  */
-SCHED_FEAT(TTWU_QUEUE, 1)
+SCHED_FEAT(TTWU_QUEUE, true)
 
-SCHED_FEAT(FORCE_SD_OVERLAP, 0)
-SCHED_FEAT(RT_RUNTIME_SHARE, 1)
+SCHED_FEAT(FORCE_SD_OVERLAP, false)
+SCHED_FEAT(RT_RUNTIME_SHARE, true)

kernel/sched_idletask.c → kernel/sched/idle_task.c

+#include "sched.h"
+
 /*
  * idle-task scheduling class.
  *
@@ -71,7 +73,7 @@ static unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task
 /*
  * Simple, special scheduling class for the per-CPU idle tasks:
  */
-static const struct sched_class idle_sched_class = {
+const struct sched_class idle_sched_class = {
 	/* .next is NULL */
 	/* no enqueue/yield_task for idle tasks */
 

kernel/sched/stats.c

+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/seq_file.h>
+#include <linux/proc_fs.h>
+
+#include "sched.h"
+
+/*
+ * bump this up when changing the output format or the meaning of an existing
+ * format, so that tools can adapt (or abort)
+ */
+#define SCHEDSTAT_VERSION 15
+
+static int show_schedstat(struct seq_file *seq, void *v)
+{
+	int cpu;
+	int mask_len = DIV_ROUND_UP(NR_CPUS, 32) * 9;
+	char *mask_str = kmalloc(mask_len, GFP_KERNEL);
+
+	if (mask_str == NULL)
+		return -ENOMEM;
+
+	seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
+	seq_printf(seq, "timestamp %lu\n", jiffies);
+	for_each_online_cpu(cpu) {
+		struct rq *rq = cpu_rq(cpu);
+#ifdef CONFIG_SMP
+		struct sched_domain *sd;
+		int dcount = 0;
+#endif
+
+		/* runqueue-specific stats */
+		seq_printf(seq,
+		    "cpu%d %u %u %u %u %u %u %llu %llu %lu",
+		    cpu, rq->yld_count,
+		    rq->sched_switch, rq->sched_count, rq->sched_goidle,
+		    rq->ttwu_count, rq->ttwu_local,
+		    rq->rq_cpu_time,
+		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
+
+		seq_printf(seq, "\n");
+
+#ifdef CONFIG_SMP
+		/* domain-specific stats */
+		rcu_read_lock();
+		for_each_domain(cpu, sd) {
+			enum cpu_idle_type itype;
+
+			cpumask_scnprintf(mask_str, mask_len,
+					  sched_domain_span(sd));
+			seq_printf(seq, "domain%d %s", dcount++, mask_str);
+			for (itype = CPU_IDLE; itype < CPU_MAX_IDLE_TYPES;
+					itype++) {
+				seq_printf(seq, " %u %u %u %u %u %u %u %u",
+				    sd->lb_count[itype],
+				    sd->lb_balanced[itype],
+				    sd->lb_failed[itype],
+				    sd->lb_imbalance[itype],
+				    sd->lb_gained[itype],
+				    sd->lb_hot_gained[itype],
+				    sd->lb_nobusyq[itype],
+				    sd->lb_nobusyg[itype]);
+			}
+			seq_printf(seq,
+				   " %u %u %u %u %u %u %u %u %u %u %u %u\n",
+			    sd->alb_count, sd->alb_failed, sd->alb_pushed,
+			    sd->sbe_count, sd->sbe_balanced, sd->sbe_pushed,
+			    sd->sbf_count, sd->sbf_balanced, sd->sbf_pushed,
+			    sd->ttwu_wake_remote, sd->ttwu_move_affine,
+			    sd->ttwu_move_balance);
+		}
+		rcu_read_unlock();
+#endif
+	}
+	kfree(mask_str);
+	return 0;
+}
+
+static int schedstat_open(struct inode *inode, struct file *file)
+{
+	unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
+	char *buf = kmalloc(size, GFP_KERNEL);
+	struct seq_file *m;
+	int res;
+
+	if (!buf)
+		return -ENOMEM;
+	res = single_open(file, show_schedstat, NULL);
+	if (!res) {
+		m = file->private_data;
+		m->buf = buf;
+		m->size = size;
+	} else
+		kfree(buf);
+	return res;
+}
+
+static const struct file_operations proc_schedstat_operations = {
+	.open    = schedstat_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = single_release,
+};
+
+static int __init proc_schedstat_init(void)
+{
+	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
+	return 0;
+}
+module_init(proc_schedstat_init);

kernel/sched_stoptask.c → kernel/sched/stop_task.c

+#include "sched.h"
+
 /*
  * stop-task scheduling class.
  *
@@ -80,7 +82,7 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task)
 /*
  * Simple, special scheduling class for the per-CPU stop tasks:
  */
-static const struct sched_class stop_sched_class = {
+const struct sched_class stop_sched_class = {
 	.next			= &rt_sched_class,
 
 	.enqueue_task		= enqueue_task_stop,

kernel/time/tick-sched.c

@@ -296,6 +296,15 @@ void tick_nohz_stop_sched_tick(int inidle)
 	cpu = smp_processor_id();
 	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