User: Password:
|
|
Subscribe / Log in / New account

RIFS-V3-Test For 3.4.x kernel.

From:  Chen <hi3766691@gmail.com>
To:  linux-kernel@vger.kernel.org
Subject:  [PATCH]RIFS-V3-Test For 3.4.x kernel.
Date:  Sun, 8 Jul 2012 04:58:57 +0800
Message-ID:  <CANQmPXibzo2OVPorHX3dcgbDFPnr=3FPm5Bu1-DbthSykzkJcA@mail.gmail.com>
Archive-link:  Article

1. Benchmark:
[admin@localhost ~]$ latt -c255 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=255
Entries logged: 1020

Wakeup averages
-------------------------------------
	Max		  106549 usec
	Avg		    1446 usec
	Stdev		    6182 usec
	Stdev mean	     194 usec

Work averages
-------------------------------------
	Max		 2793229 usec
	Avg		 2189141 usec
	Stdev		  351389 usec
	Stdev mean	   11002 usec
[admin@localhost ~]$ latt -c128 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=128
Entries logged: 768

Wakeup averages
-------------------------------------
	Max		   70824 usec
	Avg		    1761 usec
	Stdev		    5074 usec
	Stdev mean	     183 usec

Work averages
-------------------------------------
	Max		 1464295 usec
	Avg		 1163262 usec
	Stdev		  210801 usec
	Stdev mean	    7607 usec
[admin@localhost ~]$ latt -c64 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=64
Entries logged: 640

Wakeup averages
-------------------------------------
	Max		   53780 usec
	Avg		    1375 usec
	Stdev		    4772 usec
	Stdev mean	     189 usec

Work averages
-------------------------------------
	Max		  797045 usec
	Avg		  596825 usec
	Stdev		  111695 usec
	Stdev mean	    4415 usec
[admin@localhost ~]$ latt -c32 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=32
Entries logged: 480

Wakeup averages
-------------------------------------
	Max		   86032 usec
	Avg		    2147 usec
	Stdev		    7659 usec
	Stdev mean	     350 usec

Work averages
-------------------------------------
	Max		  374303 usec
	Avg		  309004 usec
	Stdev		   43155 usec
	Stdev mean	    1970 usec
[admin@localhost ~]$ latt -c16 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=16
Entries logged: 320

Wakeup averages
-------------------------------------
	Max		   41166 usec
	Avg		    1150 usec
	Stdev		    4706 usec
	Stdev mean	     263 usec

Work averages
-------------------------------------
	Max		  178917 usec
	Avg		  155367 usec
	Stdev		   16074 usec
	Stdev mean	     899 usec
[admin@localhost ~]$ latt -c8 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=8
Entries logged: 184

Wakeup averages
-------------------------------------
	Max		   20256 usec
	Avg		     585 usec
	Stdev		    2306 usec
	Stdev mean	     170 usec

Work averages
-------------------------------------
	Max		   88262 usec
	Avg		   75957 usec
	Stdev		    7102 usec
	Stdev mean	     524 usec
[admin@localhost ~]$ latt -c4 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=4
Entries logged: 104

Wakeup averages
-------------------------------------
	Max		    7950 usec
	Avg		     663 usec
	Stdev		    1719 usec
	Stdev mean	     169 usec

Work averages
-------------------------------------
	Max		   50647 usec
	Avg		   38685 usec
	Stdev		    4053 usec
	Stdev mean	     397 usec
[admin@localhost ~]$ latt -c2 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=2
Entries logged: 54

Wakeup averages
-------------------------------------
	Max		      33 usec
	Avg		       9 usec
	Stdev		       5 usec
	Stdev mean	       1 usec

Work averages
-------------------------------------
	Max		   21700 usec
	Avg		   20590 usec
	Stdev		     258 usec
	Stdev mean	      35 usec
[admin@localhost ~]$ latt -c1 sleep 10

Parameters: min_wait=100ms, max_wait=500ms, clients=1
Entries logged: 27

Wakeup averages
-------------------------------------
	Max		      22 usec
	Avg		       9 usec
	Stdev		       3 usec
	Stdev mean	       1 usec

Work averages
-------------------------------------
	Max		   20614 usec
	Avg		   20162 usec
	Stdev		     125 usec
	Stdev mean	      24 usec



RIFS-V3 is the new name of RIFS-ES. It looks like CFS. but with RIFS,
the latency is much lower.
diff -ruN linux-3.4.1/fs/proc/base.c linux-3.4.1-RIFS/fs/proc/base.c
--- linux-3.4.1/fs/proc/base.c	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/fs/proc/base.c	2012-06-06 15:02:18.000000000 +0800
@@ -342,7 +342,7 @@
 static int proc_pid_schedstat(struct task_struct *task, char *buffer)
 {
 	return sprintf(buffer, "%llu %llu %lu\n",
-			(unsigned long long)task->se.sum_exec_runtime,
+			(unsigned long long)tsk_seruntime(task),
 			(unsigned long long)task->sched_info.run_delay,
 			task->sched_info.pcount);
 }
diff -ruN linux-3.4.1/include/linux/init_task.h linux-3.4.1-RIFS/include/linux/init_task.h
--- linux-3.4.1/include/linux/init_task.h	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/include/linux/init_task.h	2012-06-06 14:50:29.000000000 +0800
@@ -132,12 +132,68 @@
 # define INIT_PERF_EVENTS(tsk)
 #endif
 
-#define INIT_TASK_COMM "swapper"
-
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
  */
+#ifdef CONFIG_SCHED_RIFS
+#define INIT_TASK_COMM "RIFS"
+#define INIT_TASK(tsk)	\
+{									\
+	.state		= 0,						\
+	.stack		= &init_thread_info,				\
+	.usage		= ATOMIC_INIT(2),				\
+	.flags		= PF_KTHREAD,					\
+	.prio		= NORMAL_PRIO,					\
+	.static_prio	= MAX_PRIO-20,					\
+	.normal_prio	= NORMAL_PRIO,					\
+	.policy		= SCHED_NORMAL,					\
+	.cpus_allowed	= CPU_MASK_ALL,					\
+	.mm		= NULL,						\
+	.active_mm	= &init_mm,					\
+	.run_list	= LIST_HEAD_INIT(tsk.run_list),			\
+	.time_slice	= HZ,					\
+	.tasks		= LIST_HEAD_INIT(tsk.tasks),			\
+	INIT_PUSHABLE_TASKS(tsk)					\
+	.ptraced	= LIST_HEAD_INIT(tsk.ptraced),			\
+	.ptrace_entry	= LIST_HEAD_INIT(tsk.ptrace_entry),		\
+	.real_parent	= &tsk,						\
+	.parent		= &tsk,						\
+	.children	= LIST_HEAD_INIT(tsk.children),			\
+	.sibling	= LIST_HEAD_INIT(tsk.sibling),			\
+	.group_leader	= &tsk,						\
+	RCU_INIT_POINTER(.real_cred, &init_cred),			\
+	RCU_INIT_POINTER(.cred, &init_cred),				\
+	.comm		= INIT_TASK_COMM,				\
+	.thread		= INIT_THREAD,					\
+	.fs		= &init_fs,					\
+	.files		= &init_files,					\
+	.signal		= &init_signals,				\
+	.sighand	= &init_sighand,				\
+	.nsproxy	= &init_nsproxy,				\
+	.pending	= {						\
+		.list = LIST_HEAD_INIT(tsk.pending.list),		\
+		.signal = {{0}}},					\
+	.blocked	= {{0}},					\
+	.alloc_lock	= __SPIN_LOCK_UNLOCKED(tsk.alloc_lock),		\
+	.journal_info	= NULL,						\
+	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
+	.pi_lock	= __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock),		\
+	.timer_slack_ns = 50000, /* 50 usec default slack */		\
+	.pids = {							\
+		[PIDTYPE_PID]  = INIT_PID_LINK(PIDTYPE_PID),		\
+		[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),		\
+		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
+	},								\
+	INIT_IDS							\
+	INIT_PERF_EVENTS(tsk)						\
+	INIT_TRACE_IRQFLAGS						\
+	INIT_LOCKDEP							\
+	INIT_FTRACE_GRAPH						\
+	INIT_TRACE_RECURSION						\
+	INIT_TASK_RCU_PREEMPT(tsk)					\
+}
+#else /* CONFIG_SCHED_RIFS */
 #define INIT_TASK(tsk)	\
 {									\
 	.state		= 0,						\
@@ -201,7 +257,7 @@
 	INIT_TASK_RCU_PREEMPT(tsk)					\
 	INIT_CPUSET_SEQ							\
 }
-
+#endif
 
 #define INIT_CPU_TIMERS(cpu_timers)					\
 {									\
diff -ruN linux-3.4.1/include/linux/sched.h linux-3.4.1-RIFS/include/linux/sched.h
--- linux-3.4.1/include/linux/sched.h	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/include/linux/sched.h	2012-07-08 04:36:16.000000000 +0800
@@ -37,9 +37,13 @@
 #define SCHED_FIFO		1
 #define SCHED_RR		2
 #define SCHED_BATCH		3
-/* SCHED_ISO: reserved but not implemented yet */
 #define SCHED_IDLE		5
-/* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */
+#define SCHED_IDLEPRIO		SCHED_IDLE
+#ifdef CONFIG_SCHED_RIFS
+#define SCHED_MAX		(SCHED_IDLEPRIO)
+#define SCHED_RANGE(policy)	((policy) <= SCHED_MAX)
+#endif
+
 #define SCHED_RESET_ON_FORK     0x40000000
 
 #ifdef __KERNEL__
@@ -268,8 +272,6 @@
 extern void init_idle(struct task_struct *idle, int cpu);
 extern void init_idle_bootup_task(struct task_struct *idle);
 
-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);
@@ -1270,15 +1272,31 @@
 
 #ifdef CONFIG_SMP
 	struct llist_node wake_entry;
-	int on_cpu;
 #endif
+#ifndef CONFIG_SCHED_RIFS
+	int on_cpu;
 	int on_rq;
-
+#else
+	bool on_cpu;
+	bool on_rq;
+#endif
 	int prio, static_prio, normal_prio;
 	unsigned int rt_priority;
+#ifdef CONFIG_SCHED_RIFS
+	int time_slice;
+	struct list_head run_list;
+	u64 last_ran;
+	u64 sleep_jiffy;
+	u64 sched_time; /* sched_clock time spent running */
+#ifdef CONFIG_SMP
+	bool sticky; /* Soft affined flag */
+#endif
+	unsigned long rt_timeout;
+#else /* CONFIG_SCHED_RIFS */
 	const struct sched_class *sched_class;
 	struct sched_entity se;
 	struct sched_rt_entity rt;
+#endif
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 	/* list of struct preempt_notifier: */
@@ -1391,6 +1409,9 @@
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
+#ifdef CONFIG_SCHED_RIFS
+	unsigned long utime_pc, stime_pc;
+#endif
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	cputime_t prev_utime, prev_stime;
 #endif
@@ -1619,6 +1640,55 @@
 #endif
 };
 
+#ifdef CONFIG_SCHED_RIFS
+bool grunqueue_is_locked(void);
+void grq_unlock_wait(void);
+void cpu_scaling(int cpu);
+void cpu_nonscaling(int cpu);
+bool above_background_load(void);
+#define tsk_seruntime(t)		((t)->sched_time)
+#define tsk_rttimeout(t)		((t)->rt_timeout)
+
+static inline void tsk_cpus_current(struct task_struct *p)
+{
+}
+
+static inline int runqueue_is_locked(int cpu)
+{
+	return grunqueue_is_locked();
+}
+
+void print_scheduler_version(void);
+
+#else /* CFS */
+extern int runqueue_is_locked(int cpu);
+static inline void cpu_scaling(int cpu)
+{
+}
+
+static inline void cpu_nonscaling(int cpu)
+{
+}
+#define tsk_seruntime(t)	((t)->se.sum_exec_runtime)
+#define tsk_rttimeout(t)	((t)->rt.timeout)
+
+static inline void tsk_cpus_current(struct task_struct *p)
+{
+	p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed;
+}
+
+static inline void print_scheduler_version(void)
+{
+	printk(KERN_INFO"CFS CPU scheduler.\n");
+}
+
+/* Anyone feel like implementing this? */
+static inline bool above_background_load(void)
+{
+	return false;
+}
+#endif /* CONFIG_SCHED_RIFS */
+
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
@@ -1636,10 +1706,20 @@
  */
 
 #define MAX_USER_RT_PRIO	100
-#define MAX_RT_PRIO		MAX_USER_RT_PRIO
+#define MAX_RT_PRIO		(MAX_USER_RT_PRIO)
+#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
 
+#ifdef CONFIG_SCHED_RIFS
+#define PRIO_RANGE		(40)
+#define MAX_PRIO		(MAX_RT_PRIO + PRIO_RANGE)
+//#define ISO_PRIO		(MAX_RT_PRIO) 已经被我干掉,哈哈
+#define NORMAL_PRIO		(MAX_RT_PRIO + 1)
+#define IDLE_PRIO		(MAX_PRIO + 1)
+#define PRIO_LIMIT		((IDLE_PRIO) + 1)
+#else /* CONFIG_SCHED_RIFS */
 #define MAX_PRIO		(MAX_RT_PRIO + 40)
-#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
+#define NORMAL_PRIO		(DEFAULT_PRIO)
+#endif /* CONFIG_SCHED_RIFS */
 
 static inline int rt_prio(int prio)
 {
@@ -2002,7 +2082,7 @@
 task_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_RIFS)
 extern void sched_exec(void);
 #else
 #define sched_exec()   {}
diff -ruN linux-3.4.1/init/Kconfig linux-3.4.1-RIFS/init/Kconfig
--- linux-3.4.1/init/Kconfig	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/init/Kconfig	2012-06-08 22:15:30.000000000 +0800
@@ -29,6 +29,18 @@
 
 menu "General setup"
 
+config SCHED_RIFS
+	bool "RIFS cpu scheduler"
+	---help---
+	  The RIFS cpu scheduler is designed for excellent interactivity and
+	  responsiveness.
+
+	  Currently incompatible with the Group CPU scheduler, and RCU TORTURE
+          TEST so these options are disabled.
+
+          Say Y here.
+	default y
+
 config EXPERIMENTAL
 	bool "Prompt for development and/or incomplete code/drivers"
 	---help---
@@ -631,6 +643,7 @@
 
 config CGROUP_CPUACCT
 	bool "Simple CPU accounting cgroup subsystem"
+	depends on !SCHED_RIFS
 	help
 	  Provides a simple Resource Controller for monitoring the
 	  total CPU consumed by the tasks in a cgroup.
@@ -718,6 +731,7 @@
 
 menuconfig CGROUP_SCHED
 	bool "Group CPU scheduler"
+	depends on !SCHED_RIFS
 	default n
 	help
 	  This feature lets CPU scheduler recognize task groups and control CPU
@@ -854,6 +868,7 @@
 
 config SCHED_AUTOGROUP
 	bool "Automatic process group scheduling"
+	depends on !SCHED_RIFS
 	select EVENTFD
 	select CGROUPS
 	select CGROUP_SCHED
diff -ruN linux-3.4.1/kernel/delayacct.c linux-3.4.1-RIFS/kernel/delayacct.c
--- linux-3.4.1/kernel/delayacct.c	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/delayacct.c	2012-06-06 15:03:30.000000000 +0800
@@ -130,7 +130,7 @@
 	 */
 	t1 = tsk->sched_info.pcount;
 	t2 = tsk->sched_info.run_delay;
-	t3 = tsk->se.sum_exec_runtime;
+	t3 = tsk_seruntime(tsk);
 
 	d->cpu_count += t1;
 
diff -ruN linux-3.4.1/kernel/exit.c linux-3.4.1-RIFS/kernel/exit.c
--- linux-3.4.1/kernel/exit.c	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/exit.c	2012-06-05 20:46:45.000000000 +0800
@@ -133,7 +133,7 @@
 		sig->inblock += task_io_get_inblock(tsk);
 		sig->oublock += task_io_get_oublock(tsk);
 		task_io_accounting_add(&sig->ioac, &tsk->ioac);
-		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
+		sig->sum_sched_runtime += tsk_seruntime(tsk);
 	}
 
 	sig->nr_threads--;
diff -ruN linux-3.4.1/kernel/posix-cpu-timers.c linux-3.4.1-RIFS/kernel/posix-cpu-timers.c
--- linux-3.4.1/kernel/posix-cpu-timers.c	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/posix-cpu-timers.c	2012-06-06 14:37:35.000000000 +0800
@@ -495,7 +495,7 @@
 void posix_cpu_timers_exit(struct task_struct *tsk)
 {
 	cleanup_timers(tsk->cpu_timers,
-		       tsk->utime, tsk->stime, tsk->se.sum_exec_runtime);
+		       tsk->utime, tsk->stime, tsk_seruntime(tsk));
 
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
@@ -504,7 +504,7 @@
 
 	cleanup_timers(tsk->signal->cpu_timers,
 		       tsk->utime + sig->utime, tsk->stime + sig->stime,
-		       tsk->se.sum_exec_runtime + sig->sum_sched_runtime);
+		       tsk_seruntime(tsk) + sig->sum_sched_runtime);
 }
 
 static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
@@ -934,7 +934,7 @@
 		struct cpu_timer_list *t = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
-		if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
+		if (!--maxfire || tsk_seruntime(tsk) < t->expires.sched) {
 			tsk->cputime_expires.sched_exp = t->expires.sched;
 			break;
 		}
@@ -951,7 +951,7 @@
 			ACCESS_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max);
 
 		if (hard != RLIM_INFINITY &&
-		    tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
+		    tsk_rttimeout(tsk) > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) {
 			/*
 			 * At the hard limit, we just die.
 			 * No need to calculate anything else now.
@@ -959,7 +959,7 @@
 			__group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk);
 			return;
 		}
-		if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
+		if (tsk_rttimeout(tsk) > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) {
 			/*
 			 * At the soft limit, send a SIGXCPU every second.
 			 */
@@ -1252,7 +1252,7 @@
 		struct task_cputime task_sample = {
 			.utime = tsk->utime,
 			.stime = tsk->stime,
-			.sum_exec_runtime = tsk->se.sum_exec_runtime
+			.sum_exec_runtime = tsk_seruntime(tsk)
 		};
 
 		if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
diff -ruN linux-3.4.1/kernel/sched/Makefile linux-3.4.1-RIFS/kernel/sched/Makefile
--- linux-3.4.1/kernel/sched/Makefile	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/sched/Makefile	2012-06-05 20:42:22.000000000 +0800
@@ -11,10 +11,13 @@
 CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 endif
 
+ifdef CONFIG_SCHED_RIFS
+obj-y += rifs.o clock.o
+else
 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
+endif
+obj-$(CONFIG_SMP) += cpupri.o
 
 
diff -ruN linux-3.4.1/kernel/sched/rifs.c linux-3.4.1-RIFS/kernel/sched/rifs.c
--- linux-3.4.1/kernel/sched/rifs.c	1970-01-01 08:00:00.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/sched/rifs.c	2012-07-08 04:29:08.000000000 +0800
@@ -0,0 +1,6708 @@
+/*
+ *  kernel/sched/rifs.c
+ *
+ *  Kernel scheduler and related syscalls
+ *
+ *  Copyright (C) 1991-2002  Linus Torvalds
+ *
+ *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
+ *		make semaphores SMP safe
+ *  1998-11-19	Implemented schedule_timeout() and related stuff
+ *		by Andrea Arcangeli
+ *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
+ *		hybrid priority-list and round-robin design with
+ *		an array-switch method of distributing timeslices
+ *		and per-CPU runqueues.  Cleanups and useful suggestions
+ *		by Davide Libenzi, preemptible kernel bits by Robert Love.
+ *  2003-09-03	Interactivity tuning by Con Kolivas.
+ *  2004-04-02	Scheduler domains code by Nick Piggin
+ *  2007-04-15  Work begun on replacing all interactivity tuning with a
+ *			  fair scheduling design by Con Kolivas.
+ *  2007-05-05  Load balancing (smp-nice) and other improvements
+ *			  by Peter Williams
+ *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
+ *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
+ *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
+ *			  Thomas Gleixner, Mike Kravetz
+ *  2012-04-05  The First RIFS has borned to bring good interactivity
+ *			  to Linux, it is posted on tieba.baidu.com.
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/init.h>
+#include <asm/uaccess.h>
+#include <linux/highmem.h>
+#include <asm/mmu_context.h>
+#include <linux/interrupt.h>
+#include <linux/capability.h>
+#include <linux/completion.h>
+#include <linux/kernel_stat.h>
+#include <linux/debug_locks.h>
+#include <linux/perf_event.h>
+#include <linux/security.h>
+#include <linux/notifier.h>
+#include <linux/profile.h>
+#include <linux/freezer.h>
+#include <linux/vmalloc.h>
+#include <linux/blkdev.h>
+#include <linux/delay.h>
+#include <linux/smp.h>
+#include <linux/threads.h>
+#include <linux/timer.h>
+#include <linux/rcupdate.h>
+#include <linux/cpu.h>
+#include <linux/cpuset.h>
+#include <linux/cpumask.h>
+#include <linux/percpu.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/syscalls.h>
+#include <linux/times.h>
+#include <linux/tsacct_kern.h>
+#include <linux/kprobes.h>
+#include <linux/delayacct.h>
+#include <linux/log2.h>
+#include <linux/bootmem.h>
+#include <linux/ftrace.h>
+#include <linux/slab.h>
+#include <linux/init_task.h>
+#include <linux/math64.h>
+
+#include <asm/switch_to.h>
+#include <asm/tlb.h>
+#include <asm/unistd.h>
+#include <asm/mutex.h>
+
+#include "cpupri.h"
+#include "../workqueue_sched.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
+#define resched_tick			sleep_jiffy
+#define sleep_task(p)		(p->state != TASK_RUNNING)
+#define rt_prio(prio)		unlikely((prio) < MAX_RT_PRIO)
+#define rt_task(p)		rt_prio((p)->prio)
+#define rt_queue(rq)		rt_prio((rq)->rq_prio)
+#define batch_task(p)		(unlikely((p)->policy == SCHED_BATCH))
+#define is_rt_policy(policy)	((policy) == SCHED_FIFO || \
+					(policy) == SCHED_RR)
+#define has_rt_policy(p)	unlikely(is_rt_policy((p)->policy))
+#define idleprio_task(p)	unlikely((p)->policy == SCHED_IDLEPRIO)
+#define normal_prio(prio)	(((prio) >= NORMAL_PRIO) && \
+					((prio) < IDLE_PRIO))
+
+/*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+ * and back.
+ */
+#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
+#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
+#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)
+
+/*
+ * 'User priority' is the nice value converted to something we
+ * can work with better when scaling various scheduler parameters,
+ * it's a [ 0 ... 39 ] range.
+ */
+#define USER_PRIO(p)		((p) - MAX_RT_PRIO)
+#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
+#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))
+#define SCHED_PRIO(p)		((p) + MAX_RT_PRIO)
+#define STOP_PRIO		(MAX_RT_PRIO - 1)
+#define MAX_DELTA		MS_TO_US(rr_interval * 2)
+
+/*
+ * Some helpers for converting to/from various scales. Use shifts to get
+ * approximate multiples of ten for less overhead.
+ */
+#define JIFFIES_TO_NS(TIME)	((TIME) * (1000000000 / HZ))
+#define JIFFY_NS		(1000000000 / HZ)
+#define HALF_JIFFY_NS		(1000000000 / HZ / 2)
+#define HALF_JIFFY_US		(1000000 / HZ / 2)
+#define MS_TO_NS(TIME)		((TIME) << 20)
+#define MS_TO_US(TIME)		((TIME) << 10)
+#define NS_TO_MS(TIME)		((TIME) >> 20)
+#define NS_TO_US(TIME)		((TIME) >> 10)
+
+#define RESCHED_US	(100) /* Reschedule if less than this many μs left */
+
+void print_scheduler_version(void)
+{
+	printk(KERN_INFO "Rotary Interactivity Favor Scheduler - RIFS By QQ:3766691.\n");
+}
+
+/*
+ * This is the time all tasks within the same priority round robin.
+ * Value is in ms and set to a minimum of 6ms. Scales with number of cpus.
+ * Tunable via /proc interface.
+ */
+int rr_interval __read_mostly = 6;
+
+/*
+ * The percentage watermark to interrupt the increasing of priorities.
+ * Default is 50%
+ */
+int ts_percent __read_mostly = 50;
+
+static int sched_method = 1;
+
+/*
+ * sched_round = 10ms(Default)
+ */
+static int sched_round = 10;
+
+struct prio_queue {
+	struct list_head queue[PRIO_LIMIT];
+	DECLARE_BITMAP(prio_bitmap, PRIO_LIMIT + 1);
+};
+
+/*
+ * The global runqueue data that all CPUs work off. Data is protected either
+ * by the global grq lock, or the discrete lock that precedes the data in this
+ * struct.
+ */
+struct global_rq {
+	raw_spinlock_t lock;
+	unsigned long nr_running;
+	unsigned long nr_uninterruptible;
+	unsigned long long nr_switches;
+	struct list_head queue[PRIO_LIMIT];
+	DECLARE_BITMAP(prio_bitmap, PRIO_LIMIT + 1);
+#ifdef CONFIG_SMP
+	unsigned long qnr; /* queued not running */
+	cpumask_t cpu_idle_map;
+	bool idle_cpus;
+#endif
+	int noc; /* num_online_cpus stored and updated when it changes */
+};
+
+#ifdef CONFIG_SMP
+
+/*
+ * We add the notion of a root-domain which will be used to define per-domain
+ * variables. Each exclusive cpuset essentially defines an island domain by
+ * fully partitioning the member cpus from any other cpuset. Whenever a new
+ * exclusive cpuset is created, we also create and attach a new root-domain
+ * object.
+ *
+ */
+struct root_domain {
+	atomic_t refcount;
+	atomic_t rto_count;
+	struct rcu_head rcu;
+	cpumask_var_t span;
+	cpumask_var_t online;
+
+	/*
+	 * The "RT overload" flag: it gets set if a CPU has more than
+	 * one runnable RT task.
+	 */
+	cpumask_var_t rto_mask;
+	struct cpupri cpupri;
+};
+
+/*
+ * By default the system creates a single root-domain with all cpus as
+ * members (mimicking the global state we have today).
+ */
+static struct root_domain def_root_domain;
+
+#endif /* CONFIG_SMP */
+
+/* There can be only one */
+static struct global_rq grq;
+
+/*
+ * This is the main, per-CPU runqueue data structure.
+ * This data should only be modified by the local cpu.
+ */
+struct rq {
+	struct task_struct *curr, *idle, *stop;
+	struct mm_struct *prev_mm;
+
+	unsigned int rq_sched_round;
+	unsigned int rq_policy;
+	u64 rq_last_ran;
+	int rq_prio;
+	bool rq_preempt;
+	bool rq_running; /* There is a task running */
+
+	/* Accurate timekeeping data */
+	u64 timekeep_clock;
+	unsigned long user_pc, nice_pc, irq_pc, softirq_pc, system_pc,
+		iowait_pc, idle_pc;
+	long account_pc;
+	atomic_t nr_iowait;
+
+#ifdef CONFIG_SMP
+	int cpu;		/* cpu of this runqueue */
+	bool online;
+	bool scaling; /* This CPU is managed by a scaling CPU freq governor */
+	struct task_struct *sticky_task;
+
+	struct root_domain *rd;
+	struct sched_domain *sd;
+	int *cpu_locality; /* CPU relative cache distance */
+#ifdef CONFIG_SCHED_SMT
+	bool (*siblings_idle)(int cpu);
+	/* See if all smt siblings are idle */
+	cpumask_t smt_siblings;
+#endif
+#ifdef CONFIG_SCHED_MC
+	bool (*cache_idle)(int cpu);
+	/* See if all cache siblings are idle */
+	cpumask_t cache_siblings;
+#endif
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	u64 prev_irq_time;
+#endif
+
+	u64 clock;
+	u64 clock_task;
+};
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+static DEFINE_MUTEX(sched_hotcpu_mutex);
+
+#ifdef CONFIG_SMP
+/*
+ * sched_domains_mutex serialises calls to init_sched_domains,
+ * detach_destroy_domains and partition_sched_domains.
+ */
+static DEFINE_MUTEX(sched_domains_mutex);
+
+/*
+ * By default the system creates a single root-domain with all cpus as
+ * members (mimicking the global state we have today).
+ */
+static struct root_domain def_root_domain;
+
+int __weak arch_sd_sibling_asym_packing(void)
+{
+	   return 0*SD_ASYM_PACKING;
+}
+#endif
+
+#define rcu_dereference_check_sched_domain(p) \
+	rcu_dereference_check((p), \
+				  lockdep_is_held(&sched_domains_mutex))
+
+/*
+ * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
+ * See detach_destroy_domains: synchronize_sched for details.
+ *
+ * The domain tree of any CPU may only be accessed from within
+ * preempt-disabled sections.
+ */
+#define for_each_domain(cpu, __sd) \
+	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent)
+
+static inline void update_rq_clock(struct rq *rq);
+
+/*
+ * Sanity check should sched_clock return bogus values. We make sure it does
+ * not appear to go backwards, and use jiffies to determine the maximum and
+ * minimum it could possibly have increased, and round down to the nearest
+ * jiffy when it falls outside this.
+ */
+static inline void niffy_diff(s64 *niff_diff, int jiff_diff)
+{
+	unsigned long min_diff, max_diff;
+
+	if (jiff_diff > 1)
+		min_diff = JIFFIES_TO_NS(jiff_diff - 1);
+	else
+		min_diff = 1;
+	/*  Round up to the nearest tick for maximum */
+	max_diff = JIFFIES_TO_NS(jiff_diff + 1);
+
+	if (unlikely(*niff_diff < min_diff || *niff_diff > max_diff))
+		*niff_diff = min_diff;
+}
+
+#ifdef CONFIG_SMP
+#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
+#define this_rq()		(&__get_cpu_var(runqueues))
+#define task_rq(p)		cpu_rq(task_cpu(p))
+#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
+static inline int cpu_of(struct rq *rq)
+{
+	return rq->cpu;
+}
+
+#else /* CONFIG_SMP */
+static struct rq *uprq;
+#define cpu_rq(cpu)	(uprq)
+#define this_rq()	(uprq)
+#define task_rq(p)	(uprq)
+#define cpu_curr(cpu)	((uprq)->curr)
+static inline int cpu_of(struct rq *rq)
+{
+	return 0;
+}
+
+#endif
+#define raw_rq()	(&__raw_get_cpu_var(runqueues))
+
+#ifndef prepare_arch_switch
+# define prepare_arch_switch(next)	do { } while (0)
+#endif
+#ifndef finish_arch_switch
+# define finish_arch_switch(prev)	do { } while (0)
+#endif
+
+/*
+ * All common locking functions performed on grq.lock. rq->clock is local to
+ * the CPU accessing it so it can be modified just with interrupts disabled
+ * when we're not updating the time.
+ * Looking up task_rq must be done under grq.lock to be safe.
+ */
+static void update_rq_clock_task(struct rq *rq, s64 delta);
+
+static inline void update_rq_clock(struct rq *rq)
+{
+	s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+
+	rq->clock += delta;
+	update_rq_clock_task(rq, delta);
+}
+
+static inline bool task_running(struct task_struct *p)
+{
+	return p->on_cpu;
+}
+
+static inline void grq_lock(void)
+	__acquires(grq.lock)
+{
+	raw_spin_lock(&grq.lock);
+}
+
+static inline void grq_unlock(void)
+	__releases(grq.lock)
+{
+	raw_spin_unlock(&grq.lock);
+}
+
+static inline void grq_lock_irq(void)
+	__acquires(grq.lock)
+{
+	raw_spin_lock_irq(&grq.lock);
+}
+
+static inline void time_lock_grq(struct rq *rq)
+	__acquires(grq.lock)
+{
+	grq_lock();
+}
+
+static inline void grq_unlock_irq(void)
+	__releases(grq.lock)
+{
+	raw_spin_unlock_irq(&grq.lock);
+}
+
+static inline void grq_lock_irqsave(unsigned long *flags)
+	__acquires(grq.lock)
+{
+	raw_spin_lock_irqsave(&grq.lock, *flags);
+}
+
+static inline void grq_unlock_irqrestore(unsigned long *flags)
+	__releases(grq.lock)
+{
+	raw_spin_unlock_irqrestore(&grq.lock, *flags);
+}
+
+static inline struct rq
+*task_grq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(grq.lock)
+{
+	grq_lock_irqsave(flags);
+	return task_rq(p);
+}
+
+static inline struct rq
+*time_task_grq_lock(struct task_struct *p, unsigned long *flags)
+	__acquires(grq.lock)
+{
+	struct rq *rq = task_grq_lock(p, flags);
+	return rq;
+}
+
+static inline struct rq *task_grq_lock_irq(struct task_struct *p)
+	__acquires(grq.lock)
+{
+	grq_lock_irq();
+	return task_rq(p);
+}
+
+static inline void task_grq_unlock_irq(void)
+	__releases(grq.lock)
+{
+	grq_unlock_irq();
+}
+
+static inline void task_grq_unlock(unsigned long *flags)
+	__releases(grq.lock)
+{
+	grq_unlock_irqrestore(flags);
+}
+
+/**
+ * grunqueue_is_locked
+ *
+ * Returns true if the global runqueue is locked.
+ * This interface allows printk to be called with the runqueue lock
+ * held and know whether or not it is OK to wake up the klogd.
+ */
+bool grunqueue_is_locked(void)
+{
+	return raw_spin_is_locked(&grq.lock);
+}
+
+void grq_unlock_wait(void)
+	__releases(grq.lock)
+{
+	smp_mb(); /* spin-unlock-wait is not a full memory barrier */
+	raw_spin_unlock_wait(&grq.lock);
+}
+
+static inline void time_grq_lock(struct rq *rq, unsigned long *flags)
+	__acquires(grq.lock)
+{
+	local_irq_save(*flags);
+	time_lock_grq(rq);
+}
+
+static inline struct rq *__task_grq_lock(struct task_struct *p)
+	__acquires(grq.lock)
+{
+	grq_lock();
+	return task_rq(p);
+}
+
+static inline void __task_grq_unlock(void)
+	__releases(grq.lock)
+{
+	grq_unlock();
+}
+
+/*
+ * Look for any tasks *anywhere* that are running nice 0 or better. We do
+ * this lockless for overhead reasons since the occasional wrong result
+ * is harmless.
+ */
+bool above_background_load(void)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		struct task_struct *cpu_curr = cpu_rq(cpu)->curr;
+
+		if (unlikely(!cpu_curr))
+			continue;
+		if (PRIO_TO_NICE(cpu_curr->static_prio) < 1) {
+			return true;
+		}
+	}
+	return false;
+}
+
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
+{
+}
+
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
+{
+#ifdef CONFIG_DEBUG_SPINLOCK
+	/* this is a valid case when another task releases the spinlock */
+	grq.lock.owner = current;
+#endif
+	/*
+	 * If we are tracking spinlock dependencies then we have to
+	 * fix up the runqueue lock - which gets 'carried over' from
+	 * prev into current:
+	 */
+	spin_acquire(&grq.lock.dep_map, 0, 0, _THIS_IP_);
+
+	grq_unlock_irq();
+}
+
+#else /* __ARCH_WANT_UNLOCKED_CTXSW */
+
+static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
+{
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	grq_unlock_irq();
+#else
+	grq_unlock();
+#endif
+}
+
+static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
+{
+	smp_wmb();
+#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_enable();
+#endif
+}
+#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
+
+/*
+ * A task that is queued but not running will be on the grq run list.
+ * A task that is not running or queued will not be on the grq run list.
+ * A task that is currently running will have ->on_cpu set but not on the
+ * grq run list.
+ */
+static inline bool task_queued(struct task_struct *p)
+{
+	return (!list_empty(&p->run_list));
+}
+
+static inline bool deadline_before(u64 deadline, u64 time)
+{
+	return (deadline < time);
+}
+
+static inline bool deadline_after(u64 deadline, u64 time)
+{
+	return (deadline > time);
+}
+
+/*
+ * Removing from the global runqueue. Enter with grq locked.
+ */
+static void dequeue_task(struct task_struct *p)
+{
+	int prio = p->prio;
+	list_del_init(&p->run_list);
+	if (list_empty(grq.queue + prio))
+		__clear_bit(prio, grq.prio_bitmap);
+}
+
+/*
+ * Adding to the global runqueue. Enter with grq locked.
+ */
+static void enqueue_task(struct task_struct *p)
+{
+	__set_bit(p->prio, grq.prio_bitmap);
+	list_add_tail(&p->run_list, grq.queue + p->prio);
+}
+
+/* Only idle task does this as a real time task*/
+static inline void enqueue_task_head(struct task_struct *p)
+{
+	int prio = p->prio;
+	struct list_head *queue = grq.queue + prio;
+
+	__set_bit(prio, grq.prio_bitmap);
+	list_add(&p->run_list, queue);
+}
+
+static inline void requeue_task(struct task_struct *p)
+{
+}
+
+#ifdef CONFIG_SMP
+/*
+ * qnr is the "queued but not running" count which is the total number of
+ * tasks on the global runqueue list waiting for cpu time but not actually
+ * currently running on a cpu.
+ */
+static inline void inc_qnr(void)
+{
+	grq.qnr++;
+}
+
+static inline void dec_qnr(void)
+{
+	grq.qnr--;
+}
+
+static inline int queued_notrunning(void)
+{
+	return grq.qnr;
+}
+
+/*
+ * The cpu_idle_map stores a bitmap of all the CPUs currently idle to
+ * allow easy lookup of whether any suitable idle CPUs are available.
+ * It's cheaper to maintain a binary yes/no if there are any idle CPUs on the
+ * idle_cpus variable than to do a full bitmask check when we are busy.
+ */
+static inline void set_cpuidle_map(int cpu)
+{
+	if (likely(cpu_online(cpu))) {
+		cpu_set(cpu, grq.cpu_idle_map);
+		grq.idle_cpus = true;
+	}
+}
+
+static inline void clear_cpuidle_map(int cpu)
+{
+	cpu_clear(cpu, grq.cpu_idle_map);
+	if (cpus_empty(grq.cpu_idle_map))
+		grq.idle_cpus = false;
+}
+
+static bool suitable_idle_cpus(struct task_struct *p)
+{
+	if (!grq.idle_cpus)
+		return false;
+	return (cpus_intersects(p->cpus_allowed, grq.cpu_idle_map));
+}
+
+#define CPUIDLE_DIFF_THREAD	(1)
+#define CPUIDLE_DIFF_CORE	(2)
+#define CPUIDLE_CACHE_BUSY	(4)
+#define CPUIDLE_DIFF_CPU	(8)
+#define CPUIDLE_THREAD_BUSY	(16)
+#define CPUIDLE_DIFF_NODE	(32)
+
+static void resched_task(struct task_struct *p);
+
+/*
+ * The best idle CPU is chosen according to the CPUIDLE ranking above where the
+ * lowest value would give the most suitable CPU to schedule p onto next. The
+ * order works out to be the following:
+ *
+ * Same core, idle or busy cache, idle or busy threads
+ * Other core, same cache, idle or busy cache, idle threads.
+ * Same node, other CPU, idle cache, idle threads.
+ * Same node, other CPU, busy cache, idle threads.
+ * Other core, same cache, busy threads.
+ * Same node, other CPU, busy threads.
+ * Other node, other CPU, idle cache, idle threads.
+ * Other node, other CPU, busy cache, idle threads.
+ * Other node, other CPU, busy threads.
+ */
+static void
+resched_best_mask(int best_cpu, struct rq *rq, cpumask_t *tmpmask)
+{
+	unsigned int best_ranking = CPUIDLE_DIFF_NODE | CPUIDLE_THREAD_BUSY |
+		CPUIDLE_DIFF_CPU | CPUIDLE_CACHE_BUSY | CPUIDLE_DIFF_CORE |
+		CPUIDLE_DIFF_THREAD;
+	int cpu_tmp;
+
+	if (cpu_isset(best_cpu, *tmpmask))
+		goto out;
+
+	for_each_cpu_mask(cpu_tmp, *tmpmask) {
+		unsigned int ranking;
+		struct rq *tmp_rq;
+
+		ranking = 0;
+		tmp_rq = cpu_rq(cpu_tmp);
+
+#ifdef CONFIG_NUMA
+		if (rq->cpu_locality[cpu_tmp] > 3)
+			ranking |= CPUIDLE_DIFF_NODE;
+		else
+#endif
+		if (rq->cpu_locality[cpu_tmp] > 2)
+			ranking |= CPUIDLE_DIFF_CPU;
+#ifdef CONFIG_SCHED_MC
+		if (rq->cpu_locality[cpu_tmp] == 2)
+			ranking |= CPUIDLE_DIFF_CORE;
+		if (!(tmp_rq->cache_idle(cpu_tmp)))
+			ranking |= CPUIDLE_CACHE_BUSY;
+#endif
+#ifdef CONFIG_SCHED_SMT
+		if (rq->cpu_locality[cpu_tmp] == 1)
+			ranking |= CPUIDLE_DIFF_THREAD;
+		if (!(tmp_rq->siblings_idle(cpu_tmp)))
+			ranking |= CPUIDLE_THREAD_BUSY;
+#endif
+		if (ranking < best_ranking) {
+			best_cpu = cpu_tmp;
+			best_ranking = ranking;
+		}
+	}
+out:
+	resched_task(cpu_rq(best_cpu)->curr);
+}
+
+bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+	struct rq *this_rq = cpu_rq(this_cpu);
+
+	return (this_rq->cpu_locality[that_cpu] < 2);
+}
+EXPORT_SYMBOL(cpus_share_cache);
+
+static void resched_best_idle(struct task_struct *p)
+{
+	cpumask_t tmpmask;
+
+	cpus_and(tmpmask, p->cpus_allowed, grq.cpu_idle_map);
+	resched_best_mask(task_cpu(p), task_rq(p), &tmpmask);
+}
+
+static inline void resched_suitable_idle(struct task_struct *p)
+{
+	if (suitable_idle_cpus(p))
+		resched_best_idle(p);
+}
+/*
+ * Flags to tell us whether this CPU is running a CPU frequency governor that
+ * has slowed its speed or not. No locking required as the very rare wrongly
+ * read value would be harmless.
+ */
+void cpu_scaling(int cpu)
+{
+	cpu_rq(cpu)->scaling = true;
+}
+
+void cpu_nonscaling(int cpu)
+{
+	cpu_rq(cpu)->scaling = false;
+}
+
+static inline bool scaling_rq(struct rq *rq)
+{
+	return rq->scaling;
+}
+
+static inline int locality_diff(struct task_struct *p, struct rq *rq)
+{
+	return rq->cpu_locality[task_cpu(p)];
+}
+#else /* CONFIG_SMP */
+static inline void inc_qnr(void)
+{
+}
+
+static inline void dec_qnr(void)
+{
+}
+
+static inline int queued_notrunning(void)
+{
+	return grq.nr_running;
+}
+
+static inline void set_cpuidle_map(int cpu)
+{
+}
+
+static inline void clear_cpuidle_map(int cpu)
+{
+}
+
+static inline bool suitable_idle_cpus(struct task_struct *p)
+{
+	return current == uprq->idle;
+}
+
+static inline void resched_suitable_idle(struct task_struct *p)
+{
+}
+
+void cpu_scaling(int __unused)
+{
+}
+
+void cpu_nonscaling(int __unused)
+{
+}
+
+/*
+ * Although CPUs can scale in UP, there is nowhere else for tasks to go so this
+ * always returns 0.
+ */
+static inline bool scaling_rq(struct rq *rq)
+{
+	return false;
+}
+
+static inline int locality_diff(struct task_struct *p, struct rq *rq)
+{
+	return 0;
+}
+#endif /* CONFIG_SMP */
+EXPORT_SYMBOL_GPL(cpu_scaling);
+EXPORT_SYMBOL_GPL(cpu_nonscaling);
+
+/*
+ * activate_idle_task - move idle task to the _front_ of runqueue.
+ */
+static inline void activate_idle_task(struct task_struct *p)
+{
+	enqueue_task_head(p);
+	grq.nr_running++;
+	inc_qnr();
+}
+
+/*
+ * activate_task - move a task to the runqueue. Enter with grq locked.
+ */
+static void activate_task(struct task_struct *p, struct rq *rq)
+{
+	/*
+	 * Sleep time is in units of nanosecs, so shift by 20 to get a
+	 * milliseconds-range estimation of the amount of time that the task
+	 * spent sleeping:
+	 */
+	if (unlikely(prof_on == SLEEP_PROFILING)) {
+		if (p->state == TASK_UNINTERRUPTIBLE)
+			profile_hits(SLEEP_PROFILING, (void *)get_wchan(p),
+					 (rq->clock - p->last_ran) >> 20);
+		
+	}
+
+	if (task_contributes_to_load(p))
+		grq.nr_uninterruptible--;
+	if(!rt_task(p)) {
+		if (sched_method)
+			p->prio = p->resched_tick + p->prio - jiffies_64;
+		else
+			p->prio--;
+		if(p->prio < p->static_prio)
+			p->prio = p->static_prio;
+	}
+	enqueue_task_head(p);
+	grq.nr_running++;
+	inc_qnr();
+}
+
+static inline void clear_sticky(struct task_struct *p);
+
+/*
+ * deactivate_task - If it's running, it's not on the grq and we can just
+ * decrement the nr_running. Enter with grq locked.
+ */
+static inline void deactivate_task(struct task_struct *p)
+{
+	if (task_contributes_to_load(p))
+		grq.nr_uninterruptible++;
+	grq.nr_running--;
+	clear_sticky(p);
+}
+
+#ifdef CONFIG_SMP
+void set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+#ifdef CONFIG_LOCKDEP
+	/*
+	 * The caller should hold grq lock.
+	 */
+	WARN_ON_ONCE(debug_locks && !lockdep_is_held(&grq.lock));
+#endif
+	trace_sched_migrate_task(p, cpu);
+	if (task_cpu(p) != cpu)
+		perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0);
+
+	/*
+	 * After ->cpu is set up to a new value, task_grq_lock(p, ...) can be
+	 * successfully executed on another CPU. We must ensure that updates of
+	 * per-task data have been completed by this moment.
+	 */
+	smp_wmb();
+	task_thread_info(p)->cpu = cpu;
+}
+
+static inline void clear_sticky(struct task_struct *p)
+{
+	p->sticky = false;
+}
+
+static inline bool task_sticky(struct task_struct *p)
+{
+	return p->sticky;
+}
+
+/* Reschedule the best idle CPU that is not this one. */
+static void
+resched_closest_idle(struct rq *rq, int cpu, struct task_struct *p)
+{
+	cpumask_t tmpmask;
+
+	cpus_and(tmpmask, p->cpus_allowed, grq.cpu_idle_map);
+	cpu_clear(cpu, tmpmask);
+	if (cpus_empty(tmpmask))
+		return;
+	resched_best_mask(cpu, rq, &tmpmask);
+}
+
+/*
+ * We set the sticky flag on a task that is descheduled involuntarily meaning
+ * it is awaiting further CPU time. If the last sticky task is still sticky
+ * but unlucky enough to not be the next task scheduled, we unstick it and try
+ * to find it an idle CPU. Realtime tasks do not stick to minimise their
+ * latency at all times.
+ */
+static inline void
+swap_sticky(struct rq *rq, int cpu, struct task_struct *p)
+{
+	if (rq->sticky_task) {
+		if (rq->sticky_task == p) {
+			p->sticky = true;
+			return;
+		}
+		if (task_sticky(rq->sticky_task)) {
+			clear_sticky(rq->sticky_task);
+			resched_closest_idle(rq, cpu, rq->sticky_task);
+		}
+	}
+	if (!rt_task(p)) {
+		p->sticky = true;
+		rq->sticky_task = p;
+	} else {
+		resched_closest_idle(rq, cpu, p);
+		rq->sticky_task = NULL;
+	}
+}
+
+static inline void unstick_task(struct rq *rq, struct task_struct *p)
+{
+	rq->sticky_task = NULL;
+	clear_sticky(p);
+}
+#else
+static inline void clear_sticky(struct task_struct *p)
+{
+}
+
+static inline bool task_sticky(struct task_struct *p)
+{
+	return false;
+}
+
+static inline void
+swap_sticky(struct rq *rq, int cpu, struct task_struct *p)
+{
+}
+
+static inline void unstick_task(struct rq *rq, struct task_struct *p)
+{
+}
+#endif
+
+
+/*
+ * resched_task - mark a task 'to be rescheduled now'.
+ *
+ * On UP this means the setting of the need_resched flag, on SMP it
+ * might also involve a cross-CPU call to trigger the scheduler on
+ * the target CPU.
+ */
+#ifdef CONFIG_SMP
+
+#ifndef tsk_is_polling
+#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG)
+#endif
+
+static void resched_task(struct task_struct *p)
+{
+	int cpu;
+
+	assert_raw_spin_locked(&grq.lock);
+
+	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
+		return;
+
+	set_tsk_thread_flag(p, TIF_NEED_RESCHED);
+
+	cpu = task_cpu(p);
+	if (cpu == smp_processor_id())
+		return;
+
+	/* NEED_RESCHED must be visible before we test polling */
+	smp_mb();
+	if (!tsk_is_polling(p))
+		smp_send_reschedule(cpu);
+}
+
+#else
+static inline void resched_task(struct task_struct *p)
+{
+	assert_raw_spin_locked(&grq.lock);
+	set_tsk_need_resched(p);
+}
+#endif
+
+/**
+ * task_curr - is this task currently executing on a CPU?
+ * @p: the task in question.
+ */
+inline int task_curr(const struct task_struct *p)
+{
+	return cpu_curr(task_cpu(p)) == p;
+}
+
+#ifdef CONFIG_SMP
+struct migration_req {
+	struct task_struct *task;
+	int dest_cpu;
+};
+
+/*
+ * wait_task_inactive - wait for a thread to unschedule.
+ *
+ * If @match_state is nonzero, it's the @p->state value just checked and
+ * not expected to change.  If it changes, i.e. @p might have woken up,
+ * then return zero.  When we succeed in waiting for @p to be off its CPU,
+ * we return a positive number (its total switch count).  If a second call
+ * a short while later returns the same number, the caller can be sure that
+ * @p has remained unscheduled the whole time.
+ *
+ * The caller must ensure that the task *will* unschedule sometime soon,
+ * else this function might spin for a *long* time. This function can't
+ * be called with interrupts off, or it may introduce deadlock with
+ * smp_call_function() if an IPI is sent by the same process we are
+ * waiting to become inactive.
+ */
+unsigned long wait_task_inactive(struct task_struct *p, long match_state)
+{
+	unsigned long flags;
+	bool running, on_rq;
+	unsigned long ncsw;
+	struct rq *rq;
+
+	for (;;) {
+		/*
+		 * We do the initial early heuristics without holding
+		 * any task-queue locks at all. We'll only try to get
+		 * the runqueue lock when things look like they will
+		 * work out! In the unlikely event rq is dereferenced
+		 * since we're lockless, grab it again.
+		 */
+#ifdef CONFIG_SMP
+retry_rq:
+		rq = task_rq(p);
+		if (unlikely(!rq))
+			goto retry_rq;
+#else /* CONFIG_SMP */
+		rq = task_rq(p);
+#endif
+		/*
+		 * If the task is actively running on another CPU
+		 * still, just relax and busy-wait without holding
+		 * any locks.
+		 *
+		 * NOTE! Since we don't hold any locks, it's not
+		 * even sure that "rq" stays as the right runqueue!
+		 * But we don't care, since this will return false
+		 * if the runqueue has changed and p is actually now
+		 * running somewhere else!
+		 */
+		while (task_running(p) && p == rq->curr) {
+			if (match_state && unlikely(p->state != match_state))
+				return 0;
+			cpu_relax();
+		}
+
+		/*
+		 * Ok, time to look more closely! We need the grq
+		 * lock now, to be *sure*. If we're wrong, we'll
+		 * just go back and repeat.
+		 */
+		rq = task_grq_lock(p, &flags);
+		trace_sched_wait_task(p);
+		running = task_running(p);
+		on_rq = task_queued(p);
+		ncsw = 0;
+		if (!match_state || p->state == match_state)
+			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
+		task_grq_unlock(&flags);
+
+		/*
+		 * If it changed from the expected state, bail out now.
+		 */
+		if (unlikely(!ncsw))
+			break;
+
+		/*
+		 * Was it really running after all now that we
+		 * checked with the proper locks actually held?
+		 *
+		 * Oops. Go back and try again..
+		 */
+		if (unlikely(running)) {
+			cpu_relax();
+			continue;
+		}
+
+		/*
+		 * It's not enough that it's not actively running,
+		 * it must be off the runqueue _entirely_, and not
+		 * preempted!
+		 *
+		 * So if it was still runnable (but just not actively
+		 * running right now), it's preempted, and we should
+		 * yield - it could be a while.
+		 */
+		if (unlikely(on_rq)) {
+			ktime_t to = ktime_set(0, NSEC_PER_SEC / HZ);
+
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
+			continue;
+		}
+
+		/*
+		 * Ahh, all good. It wasn't running, and it wasn't
+		 * runnable, which means that it will never become
+		 * running in the future either. We're all done!
+		 */
+		break;
+	}
+
+	return ncsw;
+}
+
+/***
+ * kick_process - kick a running thread to enter/exit the kernel
+ * @p: the to-be-kicked thread
+ *
+ * Cause a process which is running on another CPU to enter
+ * kernel-mode, without any delay. (to get signals handled.)
+ *
+ * NOTE: this function doesn't have to take the runqueue lock,
+ * because all it wants to ensure is that the remote task enters
+ * the kernel. If the IPI races and the task has been migrated
+ * to another CPU then no harm is done and the purpose has been
+ * achieved as well.
+ */
+void kick_process(struct task_struct *p)
+{
+	int cpu;
+
+	preempt_disable();
+	cpu = task_cpu(p);
+	if ((cpu != smp_processor_id()) && task_curr(p))
+		smp_send_reschedule(cpu);
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(kick_process);
+#endif
+
+#define rq_idle(rq)	((rq)->rq_prio == PRIO_LIMIT)
+
+/*
+ * RT tasks preempt on priority.
+ * NORMAL tasks preempt on sleep time length.
+ * SCHED_IDLEPRIO don't preempt anything else or
+ * between themselves, they cooperatively multitask. An idle rq scores as
+ * prio PRIO_LIMIT so it is always preempted.
+ */
+static inline bool
+can_preempt(struct task_struct *p, int prio)
+{
+#if 0
+	u64 dl = p->deadline;
+	/* Better static priority RT task or better policy preemption */
+	if ((p->prio < prio) && rt_task(p))
+		return true;
+	if (p->prio > MAX_PRIO)
+		return false;
+
+	/* SCHED_NORMAL, BATCH and ISO will preempt based on deadline */
+	if (deadline_before(dl, deadline))
+		return true;
+	return false;
+#else
+	if (p->prio <= prio) {
+		return true;
+	}
+	return false;
+#endif
+}
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Check to see if there is a task that is affined only to offline CPUs but
+ * still wants runtime. This happens to kernel threads during suspend/halt and
+ * disabling of CPUs.
+ */
+#define cpu_online_map		(*(cpumask_t *)cpu_online_mask)
+static inline bool online_cpus(struct task_struct *p)
+{
+	return (likely(cpus_intersects(cpu_online_map, p->cpus_allowed)));
+}
+#else /* CONFIG_HOTPLUG_CPU */
+/* All available CPUs are always online without hotplug. */
+static inline bool online_cpus(struct task_struct *p)
+{
+	return true;
+}
+#endif
+
+/*
+ * Check to see if p can run on cpu, and if not, whether there are any online
+ * CPUs it can run on instead.
+ */
+static inline bool needs_other_cpu(struct task_struct *p, int cpu)
+{
+	if (unlikely(!cpu_isset(cpu, p->cpus_allowed)))
+		return true;
+	return false;
+}
+
+/*
+ * When all else is equal, still prefer this_rq.
+ */
+static void try_preempt(struct task_struct *p, struct rq *this_rq)
+{
+	struct rq *highest_prio_rq = NULL;
+	int cpu, highest_prio = 0;
+	cpumask_t tmp;
+
+	/*
+	 * We clear the sticky flag here because for a task to have called
+	 * try_preempt with the sticky flag enabled means some complicated
+	 * re-scheduling has occurred and we should ignore the sticky flag.
+	 */
+	clear_sticky(p);
+
+	if (suitable_idle_cpus(p)) {
+		resched_best_idle(p);
+		return;
+	}
+
+	/* IDLEPRIO tasks never preempt anything but idle */
+	if (p->policy == SCHED_IDLEPRIO)
+		return;
+
+	if (likely(online_cpus(p)))
+		cpus_and(tmp, cpu_online_map, p->cpus_allowed);
+	else
+		return;
+
+	for_each_cpu_mask(cpu, tmp) {
+		struct rq *rq;
+		int rq_prio;
+
+		rq = cpu_rq(cpu);
+		rq_prio = rq->rq_prio;
+		if (rq_prio < highest_prio)
+			continue;
+		
+		if (rq_prio > highest_prio) {
+			highest_prio = rq_prio;
+			highest_prio_rq = rq;
+		}
+	}
+
+	if (likely(highest_prio_rq)) {
+		if (can_preempt(p, highest_prio)) {
+			highest_prio_rq->rq_preempt = true;
+			resched_task(highest_prio_rq->curr);
+		}
+	}
+}
+#else /* CONFIG_SMP */
+static inline bool needs_other_cpu(struct task_struct *p, int cpu)
+{
+	return false;
+}
+
+static void try_preempt(struct task_struct *p, struct rq *this_rq)
+{
+	if (p->policy == SCHED_IDLEPRIO)
+		return;
+	if (can_preempt(p, uprq->rq_prio)) 
+		resched_task(current);
+}
+#endif /* CONFIG_SMP */
+
+static void
+ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
+{
+}
+
+static inline void ttwu_activate(struct task_struct *p, struct rq *rq,
+				 bool is_sync)
+{
+	activate_task(p, rq);
+
+	/*
+	 * Sync wakeups (i.e. those types of wakeups where the waker
+	 * has indicated that it will leave the CPU in short order)
+	 * don't trigger a preemption if there are no idle cpus,
+	 * instead waiting for current to deschedule.
+	 */
+	if (!is_sync || suitable_idle_cpus(p)) {
+		try_preempt(p, rq);
+	}
+}
+
+static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq,
+					bool success)
+{
+	trace_sched_wakeup(p, success);
+	p->state = TASK_RUNNING;
+
+	/*
+	 * if a worker is waking up, notify workqueue. Note that on BFS, we
+	 * don't really know what cpu it will be, so we fake it for
+	 * wq_worker_waking_up :/
+	 */
+	if ((p->flags & PF_WQ_WORKER) && success)
+		wq_worker_waking_up(p, cpu_of(rq));
+}
+
+#ifdef CONFIG_SMP
+void scheduler_ipi(void)
+{
+}
+#endif /* CONFIG_SMP */
+
+/***
+ * try_to_wake_up - wake up a thread
+ * @p: the thread to be awakened
+ * @state: the mask of task states that can be woken
+ * @wake_flags: wake modifier flags (WF_*)
+ *
+ * Put it on the run-queue if it's not already there. The "current"
+ * thread is always on the run-queue (except when the actual
+ * re-schedule is in progress), and as such you're allowed to do
+ * the simpler "current->state = TASK_RUNNING" to mark yourself
+ * runnable without the overhead of this.
+ *
+ * Returns %true if @p was woken up, %false if it was already running
+ * or @state didn't match @p's state.
+ */
+static bool try_to_wake_up(struct task_struct *p, unsigned int state,
+			  int wake_flags)
+{
+	bool success = false;
+	unsigned long flags;
+	struct rq *rq;
+	int cpu;
+
+	get_cpu();
+
+	/* This barrier is undocumented, probably for p->state? くそ */
+	smp_wmb();
+
+	/*
+	 * No need to do time_lock_grq as we only need to update the rq clock
+	 * if we activate the task
+	 */
+	rq = task_grq_lock(p, &flags);
+	cpu = task_cpu(p);
+
+	/* state is a volatile long, どうして、分からない */
+	if (!((unsigned int)p->state & state))
+		goto out_unlock;
+
+	if (task_queued(p) || task_running(p))
+		goto out_running;
+
+	ttwu_activate(p, rq, wake_flags & WF_SYNC);
+	success = true;
+
+out_running:
+	ttwu_post_activation(p, rq, success);
+out_unlock:
+	task_grq_unlock(&flags);
+
+	ttwu_stat(p, cpu, wake_flags);
+
+	put_cpu();
+
+	return success;
+}
+
+/**
+ * try_to_wake_up_local - try to wake up a local task with grq lock held
+ * @p: the thread to be awakened
+ *
+ * Put @p on the run-queue if it's not already there. The caller must
+ * ensure that grq is locked and, @p is not the current task.
+ * grq stays locked over invocation.
+ */
+static void try_to_wake_up_local(struct task_struct *p)
+{
+	struct rq *rq = task_rq(p);
+	bool success = false;
+
+	lockdep_assert_held(&grq.lock);
+
+	if (!(p->state & TASK_NORMAL))
+		return;
+
+	if (!task_queued(p)) {
+		ttwu_activate(p, rq, false);
+		ttwu_stat(p, smp_processor_id(), 0);
+		success = true;
+	}
+	ttwu_post_activation(p, rq, success);
+}
+
+/**
+ * wake_up_process - Wake up a specific process
+ * @p: The process to be woken up.
+ *
+ * Attempt to wake up the nominated process and move it to the set of runnable
+ * processes.  Returns 1 if the process was woken up, 0 if it was already
+ * running.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+int wake_up_process(struct task_struct *p)
+{
+	return try_to_wake_up(p, TASK_ALL, 0);
+}
+EXPORT_SYMBOL(wake_up_process);
+
+int wake_up_state(struct task_struct *p, unsigned int state)
+{
+	return try_to_wake_up(p, state, 0);
+}
+
+/*
+ * Perform scheduler related setup for a newly forked process p.
+ * p is forked by current.
+ */
+void sched_fork(struct task_struct *p)
+{
+	struct task_struct *curr;
+	int cpu = get_cpu();
+	struct rq *rq;
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+	INIT_HLIST_HEAD(&p->preempt_notifiers);
+#endif
+	/*
+	 * We mark the process as running here. This guarantees that
+	 * nobody will actually run it, and a signal or other external
+	 * event cannot wake it up and insert it on the runqueue either.
+	 */
+	p->state = TASK_RUNNING;
+	set_task_cpu(p, cpu);
+
+	p->sched_time = p->stime_pc = p->utime_pc = 0;
+
+	/*
+	 * Revert to default priority/policy on fork if requested.
+	 */
+	if (unlikely(p->sched_reset_on_fork)) {
+		if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
+			p->policy = SCHED_NORMAL;
+		}
+
+		if (PRIO_TO_NICE(p->static_prio) < 0) {
+			p->static_prio = NICE_TO_PRIO(0);
+		}
+
+		/*
+		 * We don't need the reset flag anymore after the fork. It has
+		 * fulfilled its duty:
+		 */
+		p->sched_reset_on_fork = 0;
+	}
+
+	curr = current;
+	/*
+	 * Make sure we do not leak PI boosting priority to the child.
+	 */
+	p->prio = curr->static_prio;
+
+	INIT_LIST_HEAD(&p->run_list);
+#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
+	if (unlikely(sched_info_on()))
+		memset(&p->sched_info, 0, sizeof(p->sched_info));
+#endif
+
+	p->on_cpu = false;
+	clear_sticky(p);
+
+#ifdef CONFIG_PREEMPT_COUNT
+	/* Want to start with kernel preemption disabled. */
+	task_thread_info(p)->preempt_count = 1;
+#endif
+	if (unlikely(p->policy == SCHED_FIFO))
+		goto out;
+	rq = task_grq_lock_irq(curr);
+	set_tsk_need_resched(curr);
+	p->last_ran = rq->rq_last_ran;
+	task_grq_unlock_irq();
+out:
+	put_cpu();
+}
+
+/*
+ * wake_up_new_task - wake up a newly created task for the first time.
+ *
+ * This function will do some initial scheduler statistics housekeeping
+ * that must be done for every newly created context, then puts the task
+ * on the runqueue and wakes it.
+ */
+void wake_up_new_task(struct task_struct *p)
+{
+	struct task_struct *parent;
+	unsigned long flags;
+	struct rq *rq;
+
+	rq = task_grq_lock(p, &flags);
+	p->state = TASK_RUNNING;
+	p->resched_tick = jiffies_64;
+	p->prio = NICE_TO_PRIO(19);
+	parent = p->parent;
+	/* Unnecessary but small chance that the parent changed CPU */
+	set_task_cpu(p, task_cpu(parent));
+	activate_task(p, rq);
+	trace_sched_wakeup_new(p, 1);
+	if (rq->curr == parent && !suitable_idle_cpus(p)) {
+		/*
+		 * The VM isn't cloned, so we're in a good position to
+		 * do child-runs-first in anticipation of an exec. This
+		 * usually avoids a lot of COW overhead.
+		 */
+		resched_task(parent);
+	} else
+		try_preempt(p, rq);
+	task_grq_unlock(&flags);
+}
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+
+/**
+ * preempt_notifier_register - tell me when current is being preempted & rescheduled
+ * @notifier: notifier struct to register
+ */
+void preempt_notifier_register(struct preempt_notifier *notifier)
+{
+	hlist_add_head(&notifier->link, &current->preempt_notifiers);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_register);
+
+/**
+ * preempt_notifier_unregister - no longer interested in preemption notifications
+ * @notifier: notifier struct to unregister
+ *
+ * This is safe to call from within a preemption notifier.
+ */
+void preempt_notifier_unregister(struct preempt_notifier *notifier)
+{
+	hlist_del(&notifier->link);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+	struct preempt_notifier *notifier;
+	struct hlist_node *node;
+
+	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+		notifier->ops->sched_in(notifier, raw_smp_processor_id());
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+	struct preempt_notifier *notifier;
+	struct hlist_node *node;
+
+	hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link)
+		notifier->ops->sched_out(notifier, next);
+}
+
+#else /* !CONFIG_PREEMPT_NOTIFIERS */
+
+static void fire_sched_in_preempt_notifiers(struct task_struct *curr)
+{
+}
+
+static void
+fire_sched_out_preempt_notifiers(struct task_struct *curr,
+				 struct task_struct *next)
+{
+}
+
+#endif /* CONFIG_PREEMPT_NOTIFIERS */
+
+/**
+ * prepare_task_switch - prepare to switch tasks
+ * @rq: the runqueue preparing to switch
+ * @next: the task we are going to switch to.
+ *
+ * This is called with the rq lock held and interrupts off. It must
+ * be paired with a subsequent finish_task_switch after the context
+ * switch.
+ *
+ * prepare_task_switch sets up locking and calls architecture specific
+ * hooks.
+ */
+static inline void
+prepare_task_switch(struct rq *rq, struct task_struct *prev,
+			struct task_struct *next)
+{
+	perf_event_task_sched_out(prev, next);
+	fire_sched_out_preempt_notifiers(prev, next);
+	prepare_lock_switch(rq, next);
+	prepare_arch_switch(next);
+	trace_sched_switch(prev, next);
+}
+
+/**
+ * finish_task_switch - clean up after a task-switch
+ * @rq: runqueue associated with task-switch
+ * @prev: the thread we just switched away from.
+ *
+ * finish_task_switch must be called after the context switch, paired
+ * with a prepare_task_switch call before the context switch.
+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
+ * and do any other architecture-specific cleanup actions.
+ *
+ * Note that we may have delayed dropping an mm in context_switch(). If
+ * so, we finish that here outside of the runqueue lock.  (Doing it
+ * with the lock held can cause deadlocks; see schedule() for
+ * details.)
+ */
+static inline void finish_task_switch(struct rq *rq, struct task_struct *prev)
+	__releases(grq.lock)
+{
+	struct mm_struct *mm = rq->prev_mm;
+	long prev_state;
+
+	rq->prev_mm = NULL;
+
+	/*
+	 * A task struct has one reference for the use as "current".
+	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
+	 * schedule one last time. The schedule call will never return, and
+	 * the scheduled task must drop that reference.
+	 * The test for TASK_DEAD must occur while the runqueue locks are
+	 * still held, otherwise prev could be scheduled on another cpu, die
+	 * there before we look at prev->state, and then the reference would
+	 * be dropped twice.
+	 *		Manfred Spraul <manfred@colorfullife.com>
+	 */
+	prev_state = prev->state;
+	finish_arch_switch(prev);
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_disable();
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+	perf_event_task_sched_in(prev, current);
+#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
+	local_irq_enable();
+#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
+	finish_lock_switch(rq, prev);
+
+	fire_sched_in_preempt_notifiers(current);
+	if (mm)
+		mmdrop(mm);
+	if (unlikely(prev_state == TASK_DEAD)) {
+		/*
+		 * Remove function-return probe instances associated with this
+		 * task and put them back on the free list.
+		 */
+		kprobe_flush_task(prev);
+		put_task_struct(prev);
+	}
+}
+
+/**
+ * schedule_tail - first thing a freshly forked thread must call.
+ * @prev: the thread we just switched away from.
+ */
+asmlinkage void schedule_tail(struct task_struct *prev)
+	__releases(grq.lock)
+{
+	struct rq *rq = this_rq();
+
+	finish_task_switch(rq, prev);
+#ifdef __ARCH_WANT_UNLOCKED_CTXSW
+	/* In this case, finish_task_switch does not reenable preemption */
+	preempt_enable();
+#endif
+	if (current->set_child_tid)
+		put_user(current->pid, current->set_child_tid);
+}
+
+/*
+ * context_switch - switch to the new MM and the new
+ * thread's register state.
+ */
+static inline void
+context_switch(struct rq *rq, struct task_struct *prev,
+		   struct task_struct *next)
+{
+	struct mm_struct *mm, *oldmm;
+	
+	prepare_task_switch(rq, prev, next);
+
+	mm = next->mm;
+	oldmm = prev->active_mm;
+	/*
+	 * For paravirt, this is coupled with an exit in switch_to to
+	 * combine the page table reload and the switch backend into
+	 * one hypercall.
+	 */
+	arch_start_context_switch(prev);
+
+	if (!mm) {
+		next->active_mm = oldmm;
+		atomic_inc(&oldmm->mm_count);
+		enter_lazy_tlb(oldmm, next);
+	} else
+		switch_mm(oldmm, mm, next);
+
+	if (!prev->mm) {
+		prev->active_mm = NULL;
+		rq->prev_mm = oldmm;
+	}
+	/*
+	 * Since the runqueue lock will be released by the next
+	 * task (which is an invalid locking op but in the case
+	 * of the scheduler it's an obvious special-case), so we
+	 * do an early lockdep release here:
+	 */
+#ifndef __ARCH_WANT_UNLOCKED_CTXSW
+	spin_release(&grq.lock.dep_map, 1, _THIS_IP_);
+#endif
+
+	/* Here we just switch the register state and the stack. */
+	switch_to(prev, next, prev);
+
+	barrier();
+	/*
+	 * this_rq must be evaluated again because prev may have moved
+	 * CPUs since it called schedule(), thus the 'rq' on its stack
+	 * frame will be invalid.
+	 */
+	finish_task_switch(this_rq(), prev);
+}
+
+/*
+ * nr_running, nr_uninterruptible and nr_context_switches:
+ *
+ * externally visible scheduler statistics: current number of runnable
+ * threads, current number of uninterruptible-sleeping threads, total
+ * number of context switches performed since bootup. All are measured
+ * without grabbing the grq lock but the occasional inaccurate result
+ * doesn't matter so long as it's positive.
+ */
+unsigned long nr_running(void)
+{
+	long nr = grq.nr_running;
+
+	if (unlikely(nr < 0))
+		nr = 0;
+	return (unsigned long)nr;
+}
+
+unsigned long nr_uninterruptible(void)
+{
+	long nu = grq.nr_uninterruptible;
+
+	if (unlikely(nu < 0))
+		nu = 0;
+	return nu;
+}
+
+unsigned long long nr_context_switches(void)
+{
+	long long ns = grq.nr_switches;
+
+	/* This is of course impossible */
+	if (unlikely(ns < 0))
+		ns = 1;
+	return (unsigned long long)ns;
+}
+
+unsigned long nr_iowait(void)
+{
+	unsigned long i, sum = 0;
+
+	for_each_possible_cpu(i)
+		sum += atomic_read(&cpu_rq(i)->nr_iowait);
+
+	return sum;
+}
+
+unsigned long nr_iowait_cpu(int cpu)
+{
+	struct rq *this = cpu_rq(cpu);
+	return atomic_read(&this->nr_iowait);
+}
+
+unsigned long nr_active(void)
+{
+	return nr_running() + nr_uninterruptible();
+}
+
+/* Beyond a task running on this CPU, load is equal everywhere on BFS */
+unsigned long this_cpu_load(void)
+{
+	return this_rq()->rq_running +
+		((queued_notrunning() + nr_uninterruptible()) / grq.noc);
+}
+
+/* Variables and functions for calc_load */
+static unsigned long calc_load_update;
+unsigned long avenrun[3];
+EXPORT_SYMBOL(avenrun);
+
+/**
+ * get_avenrun - get the load average array
+ * @loads:	pointer to dest load array
+ * @offset:	offset to add
+ * @shift:	shift count to shift the result left
+ *
+ * These values are estimates at best, so no need for locking.
+ */
+void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
+{
+	loads[0] = (avenrun[0] + offset) << shift;
+	loads[1] = (avenrun[1] + offset) << shift;
+	loads[2] = (avenrun[2] + offset) << shift;
+}
+
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	return load >> FSHIFT;
+}
+
+/*
+ * calc_load - update the avenrun load estimates every LOAD_FREQ seconds.
+ */
+void calc_global_load(unsigned long ticks)
+{
+	long active;
+
+	if (time_before(jiffies, calc_load_update))
+		return;
+	active = nr_active() * FIXED_1;
+
+	avenrun[0] = calc_load(avenrun[0], EXP_1, active);
+	avenrun[1] = calc_load(avenrun[1], EXP_5, active);
+	avenrun[2] = calc_load(avenrun[2], EXP_15, active);
+
+	calc_load_update = jiffies + LOAD_FREQ;
+}
+
+DEFINE_PER_CPU(struct kernel_stat, kstat);
+DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
+
+EXPORT_PER_CPU_SYMBOL(kstat);
+EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+/*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in account_system_vtime, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/account_system_vtime on this CPU. We would either get old
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
+ */
+static DEFINE_PER_CPU(u64, cpu_hardirq_time);
+static DEFINE_PER_CPU(u64, cpu_softirq_time);
+
+static DEFINE_PER_CPU(u64, irq_start_time);
+static int sched_clock_irqtime;
+
+void enable_sched_clock_irqtime(void)
+{
+	sched_clock_irqtime = 1;
+}
+
+void disable_sched_clock_irqtime(void)
+{
+	sched_clock_irqtime = 0;
+}
+
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
+{
+	__this_cpu_inc(irq_time_seq.sequence);
+	smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+	smp_wmb();
+	__this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+	u64 irq_time;
+	unsigned seq;
+
+	do {
+		seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+		irq_time = per_cpu(cpu_softirq_time, cpu) +
+			   per_cpu(cpu_hardirq_time, cpu);
+	} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+	return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+}
+#endif /* CONFIG_64BIT */
+
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
+void account_system_vtime(struct task_struct *curr)
+{
+	unsigned long flags;
+	s64 delta;
+	int cpu;
+
+	if (!sched_clock_irqtime)
+		return;
+
+	local_irq_save(flags);
+
+	cpu = smp_processor_id();
+	delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+	__this_cpu_add(irq_start_time, delta);
+
+	irq_time_write_begin();
+	/*
+	 * We do not account for softirq time from ksoftirqd here.
+	 * We want to continue accounting softirq time to ksoftirqd thread
+	 * in that case, so as not to confuse scheduler with a special task
+	 * that do not consume any time, but still wants to run.
+	 */
+	if (hardirq_count())
+		__this_cpu_add(cpu_hardirq_time, delta);
+	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+		__this_cpu_add(cpu_softirq_time, delta);
+
+	irq_time_write_end();
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(account_system_vtime);
+
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+static void update_rq_clock_task(struct rq *rq, s64 delta)
+{
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	s64 irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+	/*
+	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
+	 * this case when a previous update_rq_clock() happened inside a
+	 * {soft,}irq region.
+	 *
+	 * When this happens, we stop ->clock_task and only update the
+	 * prev_irq_time stamp to account for the part that fit, so that a next
+	 * update will consume the rest. This ensures ->clock_task is
+	 * monotonic.
+	 *
+	 * It does however cause some slight miss-attribution of {soft,}irq
+	 * time, a more accurate solution would be to update the irq_time using
+	 * the current rq->clock timestamp, except that would require using
+	 * atomic ops.
+	 */
+	if (irq_delta > delta)
+		irq_delta = delta;
+
+	rq->prev_irq_time += irq_delta;
+	delta -= irq_delta;
+#endif
+	rq->clock_task += delta;
+}
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs)	nsecs_to_jiffies(__nsecs)
+#endif
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+static void irqtime_account_hi_si(void)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+	u64 latest_ns;
+
+	latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_hardirq_time));
+	if (latest_ns > cpustat[CPUTIME_IRQ])
+		cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy;
+
+	latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_softirq_time));
+	if (latest_ns > cpustat[CPUTIME_SOFTIRQ])
+		cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy;
+}
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#define sched_clock_irqtime	(0)
+
+static inline void irqtime_account_hi_si(void)
+{
+}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+/*
+ * On each tick, see what percentage of that tick was attributed to each
+ * component and add the percentage to the _pc values. Once a _pc value has
+ * accumulated one tick's worth, account for that. This means the total
+ * percentage of load components will always be 128 (pseudo 100) per tick.
+ */
+static void pc_idle_time(struct rq *rq, unsigned long pc)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+	if (atomic_read(&rq->nr_iowait) > 0) {
+		rq->iowait_pc += pc;
+		if (rq->iowait_pc >= 128) {
+			rq->iowait_pc %= 128;
+			cpustat[CPUTIME_IOWAIT] += (__force u64)cputime_one_jiffy;
+		}
+	} else {
+		rq->idle_pc += pc;
+		if (rq->idle_pc >= 128) {
+			rq->idle_pc %= 128;
+			cpustat[CPUTIME_IDLE] += (__force u64)cputime_one_jiffy;
+		}
+	}
+}
+
+static void
+pc_system_time(struct rq *rq, struct task_struct *p, int hardirq_offset,
+		   unsigned long pc, unsigned long ns)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+
+	p->stime_pc += pc;
+	if (p->stime_pc >= 128) {
+		p->stime_pc %= 128;
+		p->stime += (__force u64)cputime_one_jiffy;
+		p->stimescaled += one_jiffy_scaled;
+		acct_update_integrals(p);
+	}
+	p->sched_time += ns;
+
+	if (hardirq_count() - hardirq_offset) {
+		rq->irq_pc += pc;
+		if (rq->irq_pc >= 128) {
+			rq->irq_pc %= 128;
+			cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy;
+		}
+	} else if (in_serving_softirq()) {
+		rq->softirq_pc += pc;
+		if (rq->softirq_pc >= 128) {
+			rq->softirq_pc %= 128;
+			cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy;
+		}
+	} else {
+		rq->system_pc += pc;
+		if (rq->system_pc >= 128) {
+			rq->system_pc %= 128;
+			cpustat[CPUTIME_SYSTEM] += (__force u64)cputime_one_jiffy;
+		}
+	}
+}
+
+static void pc_user_time(struct rq *rq, struct task_struct *p,
+			 unsigned long pc, unsigned long ns)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+	cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+
+	p->utime_pc += pc;
+	if (p->utime_pc >= 128) {
+		p->utime_pc %= 128;
+		p->utime += (__force u64)cputime_one_jiffy;
+		p->utimescaled += one_jiffy_scaled;
+		acct_update_integrals(p);
+	}
+	p->sched_time += ns;
+
+	if (this_cpu_ksoftirqd() == p) {
+		/*
+		 * ksoftirqd time do not get accounted in cpu_softirq_time.
+		 * So, we have to handle it separately here.
+		 */
+		rq->softirq_pc += pc;
+		if (rq->softirq_pc >= 128) {
+			rq->softirq_pc %= 128;
+			cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy;
+		}
+	}
+
+	if (TASK_NICE(p) > 0 || idleprio_task(p)) {
+		rq->nice_pc += pc;
+		if (rq->nice_pc >= 128) {
+			rq->nice_pc %= 128;
+			cpustat[CPUTIME_NICE] += (__force u64)cputime_one_jiffy;
+		}
+	} else {
+		rq->user_pc += pc;
+		if (rq->user_pc >= 128) {
+			rq->user_pc %= 128;
+			cpustat[CPUTIME_USER] += (__force u64)cputime_one_jiffy;
+		}
+	}
+}
+
+/*
+ * Convert nanoseconds to pseudo percentage of one tick. Use 128 for fast
+ * shifts instead of 100
+ */
+#define NS_TO_PC(NS)	(NS * 128 / JIFFY_NS)
+
+/*
+ * This is called on clock ticks and on context switches.
+ * Bank in p->sched_time the ns elapsed since the last tick or switch.
+ * CPU scheduler quota accounting is also performed here in microseconds.
+ */
+static void
+update_cpu_clock(struct rq *rq, struct task_struct *p)
+{
+	long account_ns = rq->clock - rq->timekeep_clock;
+	struct task_struct *idle = rq->idle;
+	unsigned long account_pc;
+	int user_tick;
+
+	p->last_ran = rq->clock;
+
+	if (unlikely(account_ns < 0))
+		account_ns = 0;
+
+	account_pc = NS_TO_PC(account_ns);
+
+	/* Accurate tick timekeeping */
+	rq->account_pc += account_pc - 128;
+	if (rq->account_pc < 0) {
+		/*
+		 * Small errors in micro accounting may not make the
+		 * accounting add up to 128 each tick so we keep track
+		 * of the percentage and round it up when less than 128
+		 */
+		account_pc += -rq->account_pc;
+		rq->account_pc = 0;
+	}
+
+	user_tick = user_mode(get_irq_regs());
+
+	if (user_tick)
+		pc_user_time(rq, p, account_pc, account_ns);
+	else if (p != idle || (irq_count() != HARDIRQ_OFFSET))
+		pc_system_time(rq, p, HARDIRQ_OFFSET,
+				   account_pc, account_ns);
+	else
+		pc_idle_time(rq, account_pc);
+
+	if (sched_clock_irqtime)
+		irqtime_account_hi_si();
+
+	if (rq->rq_policy != SCHED_FIFO && p != idle) {
+		s64 time_diff = rq->clock - rq->rq_last_ran;
+
+		niffy_diff(&time_diff, 1);
+		if(p->prio < NICE_TO_PRIO(19))
+			p->prio++;
+		rq->rq_sched_round--;
+	}
+	rq->rq_last_ran = rq->timekeep_clock = rq->clock;
+}
+
+/*
+ * Return any ns on the sched_clock that have not yet been accounted in
+ * @p in case that task is currently running.
+ *
+ * Called with task_grq_lock() held.
+ */
+static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
+{
+	u64 ns = 0;
+
+	if (p == rq->curr) {
+		ns = rq->clock_task - rq->rq_last_ran;
+		if (unlikely((s64)ns < 0))
+			ns = 0;
+	}
+
+	return ns;
+}
+
+unsigned long long task_delta_exec(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns;
+
+	rq = task_grq_lock(p, &flags);
+	ns = do_task_delta_exec(p, rq);
+	task_grq_unlock(&flags);
+
+	return ns;
+}
+
+/*
+ * Return accounted runtime for the task.
+ * In case the task is currently running, return the runtime plus current's
+ * pending runtime that have not been accounted yet.
+ */
+unsigned long long task_sched_runtime(struct task_struct *p)
+{
+	unsigned long flags;
+	struct rq *rq;
+	u64 ns;
+
+	rq = task_grq_lock(p, &flags);
+	ns = p->sched_time + do_task_delta_exec(p, rq);
+	task_grq_unlock(&flags);
+
+	return ns;
+}
+
+/* Compatibility crap for removal */
+void account_user_time(struct task_struct *p, cputime_t cputime,
+			   cputime_t cputime_scaled)
+{
+}
+
+void account_idle_time(cputime_t cputime)
+{
+}
+
+/*
+ * Account guest cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+				   cputime_t cputime_scaled)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+	/* Add guest time to process. */
+	p->utime += (__force u64)cputime;
+	p->utimescaled += (__force u64)cputime_scaled;
+	p->gtime += (__force u64)cputime;
+
+	/* Add guest time to cpustat. */
+	if (TASK_NICE(p) > 0) {
+		cpustat[CPUTIME_NICE] += (__force u64)cputime;
+		cpustat[CPUTIME_GUEST_NICE] += (__force u64)cputime;
+	} else {
+		cpustat[CPUTIME_USER] += (__force u64)cputime;
+		cpustat[CPUTIME_GUEST] += (__force u64)cputime;
+	}
+}
+
+/*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+			cputime_t cputime_scaled, cputime64_t *target_cputime64)
+{
+	/* Add system time to process. */
+	p->stime += (__force u64)cputime;
+	p->stimescaled += (__force u64)cputime_scaled;
+
+	/* Add system time to cpustat. */
+	*target_cputime64 += (__force u64)cputime;
+
+	/* Account for system time used */
+	acct_update_integrals(p);
+}
+
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * This is for guest only now.
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+			 cputime_t cputime, cputime_t cputime_scaled)
+{
+
+	if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0))
+		account_guest_time(p, cputime, cputime_scaled);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @steal: the cpu time spent in involuntary wait
+ */
+void account_steal_time(cputime_t cputime)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+	cpustat[CPUTIME_STEAL] += (__force u64)cputime;
+}
+
+/*
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
+ */
+static void account_idle_times(cputime_t cputime)
+{
+	u64 *cpustat = kcpustat_this_cpu->cpustat;
+	struct rq *rq = this_rq();
+
+	if (atomic_read(&rq->nr_iowait) > 0)
+		cpustat[CPUTIME_IOWAIT] += (__force u64)cputime;
+	else
+		cpustat[CPUTIME_IDLE] += (__force u64)cputime;
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+void account_process_tick(struct task_struct *p, int user_tick)
+{
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+	account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen ticks
+ */
+void account_idle_ticks(unsigned long ticks)
+{
+	account_idle_times(jiffies_to_cputime(ticks));
+}
+#endif
+
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+/*
+ * 最低位查找,查找最高优先级开始。
+ * Find the lowest bit set in the bitmap.We would find the highest priority first/
+ */
+static inline unsigned long
+get_prio_bit(unsigned long *addr, unsigned long offset)
+{
+	unsigned long *from = addr + (offset / BITS_PER_LONG);
+	unsigned long *limit = addr + PRIO_LIMIT / BITS_PER_LONG;
+	int i = offset % BITS_PER_LONG;
+	
+	if (offset >=  PRIO_LIMIT)
+		return PRIO_LIMIT;
+
+	for(;from != (limit);from++) {
+		for(;i < BITS_PER_LONG;i++, offset++) {
+			if(((*from >> i) & 0x1)) {
+				goto out;
+			}
+		}
+		
+		/*
+		 *  This can make sure to generate the best machine code.
+		 */
+		i = 0;
+	}
+out:
+	return offset;
+}
+
+/* This manages tasks that have run out of timeslice during a scheduler_tick */
+/* 当前队列时钟的控制 */
+static void task_running_tick(struct rq *rq)
+{
+	struct task_struct *p;
+	p = rq->curr;
+
+	/* SCHED_FIFO tasks never run out of timeslice. */
+	if (rq->rq_policy == SCHED_FIFO)
+		return;
+	if (rq->rq_sched_round)
+		return;
+	if (p->prio <= get_prio_bit(grq.prio_bitmap, 0))
+		return;
+	p->resched_tick = jiffies_64;
+	grq_lock();
+	requeue_task(p);
+	set_tsk_need_resched(p);
+	grq_unlock();
+}
+
+void wake_up_idle_cpu(int cpu);
+
+/*
+ * This function gets called by the timer code, with HZ frequency.
+ * We call it with interrupts disabled. The data modified is all
+ * local to struct rq so we don't need to grab grq lock.
+ */
+void scheduler_tick(void)
+{
+	int cpu __maybe_unused = smp_processor_id();
+	struct rq *rq = cpu_rq(cpu);
+
+	sched_clock_tick();
+	/* grq lock not grabbed, so only update rq clock */
+	update_rq_clock(rq);
+	update_cpu_clock(rq, rq->curr);
+	if (!rq_idle(rq))
+		task_running_tick(rq);
+	perf_event_task_tick();
+}
+
+notrace unsigned long get_parent_ip(unsigned long addr)
+{
+	if (in_lock_functions(addr)) {
+		addr = CALLER_ADDR2;
+		if (in_lock_functions(addr))
+			addr = CALLER_ADDR3;
+	}
+	return addr;
+}
+
+#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+				defined(CONFIG_PREEMPT_TRACER))
+void __kprobes add_preempt_count(int val)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Underflow?
+	 */
+	if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
+		return;
+#endif
+	preempt_count() += val;
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Spinlock count overflowing soon?
+	 */
+	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
+				PREEMPT_MASK - 10);
+#endif
+	if (preempt_count() == val)
+		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+}
+EXPORT_SYMBOL(add_preempt_count);
+
+void __kprobes sub_preempt_count(int val)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+	/*
+	 * Underflow?
+	 */
+	if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
+		return;
+	/*
+	 * Is the spinlock portion underflowing?
+	 */
+	if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
+			!(preempt_count() & PREEMPT_MASK)))
+		return;
+#endif
+
+	if (preempt_count() == val)
+		trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+	preempt_count() -= val;
+}
+EXPORT_SYMBOL(sub_preempt_count);
+#endif
+
+/*
+ * The currently running task's information is all stored in rq local data
+ * which is only modified by the local CPU, thereby allowing the data to be
+ * changed without grabbing the grq lock.
+ */
+static inline void set_rq_task(struct rq *rq, struct task_struct *p)
+{
+	rq->rq_last_ran = p->last_ran = rq->clock;
+	rq->rq_policy = p->policy;
+	rq->rq_prio = p->prio;
+	rq->rq_sched_round = sched_round;
+	if (p != rq->idle)
+		rq->rq_running = true;
+	else
+		rq->rq_running = false;
+}
+
+static void reset_rq_task(struct rq *rq, struct task_struct *p)
+{
+	rq->rq_policy = p->policy;
+	rq->rq_prio = p->prio;
+}
+
+static inline void operate_blk_needs_flush_plug(struct task_struct *p)
+{
+	grq_unlock_irq();
+	sched_preempt_enable_no_resched();
+	blk_schedule_flush_plug(p);
+}
+
+static inline void task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next)
+{
+	/*
+	 * Don't stick tasks when a real time task is going to run as
+	 * they may literally get stuck.
+	 */
+	if (rt_task(next))
+		unstick_task(rq, prev);
+	set_rq_task(rq, next);
+	grq.nr_switches++;
+	prev->on_cpu = false;
+	next->on_cpu = true;
+	rq->curr = next;
+
+	/*
+	 * The context switch have flipped the stack from under us
+	 * and restored the local variables which were saved when
+	 * this task called schedule() in the past. prev == current
+	 * is still correct, but it can be moved to another cpu/rq.
+	 */
+	context_switch(rq, prev, next); /* unlocks the grq */
+}
+
+
+/*
+ * Move a task off the global queue and take it to a cpu for it will
+ * become the running task.
+ */
+static inline void take_task(int cpu, struct task_struct *p)
+{
+	set_task_cpu(p, cpu);
+	dequeue_task(p);
+	clear_sticky(p);
+	dec_qnr();
+}
+
+/*
+ * Put the descheduling task back to grq.
+ */
+static inline void put_prev_task(struct rq *rq, struct task_struct *p, bool deactivate, bool preempt)
+{
+	if(deactivate) {
+		deactivate_task(p);
+	} else {
+		inc_qnr();
+		if(preempt)
+			enqueue_task_head(p);
+		else
+			enqueue_task(p);
+	}
+}
+
+/*
+ * Task picking for next time to run.
+ */
+static inline struct
+task_struct *get_runnable_task(struct rq *rq, int cpu, struct task_struct *idle)
+{
+	struct task_struct *edt = NULL;
+	unsigned long idx = -1;
+
+	do {
+		struct list_head *queue;
+		struct task_struct *p;
+
+		idx = get_prio_bit(grq.prio_bitmap, ++idx);
+		if (idx >= PRIO_LIMIT) {
+			return idle;
+		}
+		queue = grq.queue + idx;
+
+		list_for_each_entry(p, queue, run_list) {
+			/* Make sure cpu affinity is ok */
+			if (needs_other_cpu(p, cpu)) {
+				continue;
+			}
+			edt = p;
+			goto out_take;
+		}
+	} while (1);
+
+out_take:
+	take_task(cpu, edt);
+	return edt;
+}
+
+#define SCHED_RESCHED -1
+
+/*
+ * schedule() is the main scheduler function.
+ */
+static inline int check_sleep_on_wq(int cpu, struct task_struct *p)
+{
+	int deactivate;
+	deactivate = 0;
+	if (sleep_task(p) && !(preempt_count() & PREEMPT_ACTIVE)) {
+		if (unlikely(signal_pending_state(p->state, p))) {
+			p->state = TASK_RUNNING;
+		} else {
+			deactivate = 1;
+			/*
+			 * If a worker is going to sleep, notify and
+			 * ask workqueue whether it wants to wake up a
+			 * task to maintain concurrency.  If so, wake
+			 * up the task.
+			 */
+			if (p->flags & PF_WQ_WORKER) {
+				struct task_struct *to_wakeup;
+
+				to_wakeup = wq_worker_sleeping(p, cpu);
+				if (to_wakeup) {
+					/* This shouldn't happen, but does */
+					if (unlikely(to_wakeup == p))
+						deactivate = 0;
+					else
+						try_to_wake_up_local(to_wakeup);
+				}
+			}
+
+			/*
+			 * If we are going to sleep and we have plugged IO queued, make
+			 * sure to submit it to avoid deadlocks.
+			 */
+			if (unlikely(deactivate && blk_needs_flush_plug(p))) {
+				operate_blk_needs_flush_plug(p);
+				deactivate = SCHED_RESCHED;
+				goto out;
+			}
+		}
+	}
+out:
+	return deactivate;
+}
+
+static inline int do_schedule(void)
+{
+	struct task_struct *prev, *next, *idle;
+	struct rq *rq;
+	int cpu;
+	int deactivate;
+
+	cpu = smp_processor_id();
+	rq = cpu_rq(cpu);
+	rcu_note_context_switch(cpu);
+	prev = rq->curr;
+
+	grq_lock_irq();
+
+	if((deactivate = check_sleep_on_wq(cpu, prev)) == SCHED_RESCHED) {
+		goto out;
+	}
+
+	clear_tsk_need_resched(prev);
+
+	idle = rq->idle;
+	if (idle != prev) {
+		/* Task changed affinity off this CPU */
+		if (needs_other_cpu(prev, cpu))
+			resched_suitable_idle(prev);
+		else if (!deactivate) {
+			if (!queued_notrunning()) {
+				/*
+				* Rerun the prev task again.
+				*/
+				set_rq_task(rq, prev);
+				grq_unlock_irq();
+				goto out;
+			} else
+				swap_sticky(rq, cpu, prev);
+		}
+
+		put_prev_task(rq, prev, deactivate, rq->rq_preempt);
+		rq->rq_preempt = false;
+	}
+
+	if (unlikely(!queued_notrunning())) {
+		/*
+		 * This CPU is now truly idle as opposed to when idle is
+		 * scheduled as a high priority task in its own right.
+		 */
+		next = idle;
+		set_cpuidle_map(cpu);
+	} else {
+		next = get_runnable_task(rq, cpu, idle);
+	}
+
+	if (likely(prev != next)) {
+		prev->nvcsw++;
+		grq.nr_switches++;
+
+		task_switch(rq, prev, next);
+		idle = rq->idle;
+	} else
+		grq_unlock_irq();
+
+out:
+	return deactivate;
+}
+
+asmlinkage void __sched schedule(void)
+{
+reschedule:
+		preempt_disable();
+		
+		if(do_schedule() == SCHED_RESCHED)
+			goto reschedule;
+		
+		sched_preempt_enable_no_resched();
+		if(unlikely(need_resched()))
+			goto reschedule;
+}
+EXPORT_SYMBOL(schedule);
+
+/**
+ * schedule_preempt_disabled - called with preemption disabled
+ *
+ * Returns with preemption disabled. Note: preempt_count must be 1
+ */
+void __sched schedule_preempt_disabled(void)
+{
+	sched_preempt_enable_no_resched();
+	schedule();
+	preempt_disable();
+}
+
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+
+static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
+{
+	if (lock->owner != owner)
+		return false;
+
+	/*
+	 * Ensure we emit the owner->on_cpu, dereference _after_ checking
+	 * lock->owner still matches owner, if that fails, owner might
+	 * point to free()d memory, if it still matches, the rcu_read_lock()
+	 * ensures the memory stays valid.
+	 */
+	barrier();
+
+	return owner->on_cpu;
+}
+
+/*
+ * Look out! "owner" is an entirely speculative pointer
+ * access and not reliable.
+ */
+int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
+{
+	rcu_read_lock();
+	while (owner_running(lock, owner)) {
+		if (need_resched())
+			break;
+
+		arch_mutex_cpu_relax();
+	}
+	rcu_read_unlock();
+
+	/*
+	 * We break out the loop above on need_resched() and when the
+	 * owner changed, which is a sign for heavy contention. Return
+	 * success only when lock->owner is NULL.
+	 */
+	return lock->owner == NULL;
+}
+#endif
+
+#ifdef CONFIG_PREEMPT
+/*
+ * this is the entry point to schedule() from in-kernel preemption
+ * off of preempt_enable. Kernel preemptions off return from interrupt
+ * occur there and call schedule directly.
+ */
+asmlinkage void __sched notrace preempt_schedule(void)
+{
+	struct thread_info *ti = current_thread_info();
+
+	/*
+	 * If there is a non-zero preempt_count or interrupts are disabled,
+	 * we do not want to preempt the current task. Just return..
+	 */
+	if (likely(ti->preempt_count || irqs_disabled()))
+		return;
+
+	do {
+		add_preempt_count_notrace(PREEMPT_ACTIVE);
+		schedule();
+		sub_preempt_count_notrace(PREEMPT_ACTIVE);
+
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (need_resched());
+}
+EXPORT_SYMBOL(preempt_schedule);
+
+/*
+ * this is the entry point to schedule() from kernel preemption
+ * off of irq context.
+ * Note, that this is called and return with irqs disabled. This will
+ * protect us against recursive calling from irq.
+ */
+asmlinkage void __sched preempt_schedule_irq(void)
+{
+	struct thread_info *ti = current_thread_info();
+
+	/* Catch callers which need to be fixed */
+	BUG_ON(ti->preempt_count || !irqs_disabled());
+
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		local_irq_enable();
+		schedule();
+		local_irq_disable();
+		sub_preempt_count(PREEMPT_ACTIVE);
+
+		/*
+		 * Check again in case we missed a preemption opportunity
+		 * between schedule and now.
+		 */
+		barrier();
+	} while (need_resched());
+}
+
+#endif /* CONFIG_PREEMPT */
+
+int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
+			  void *key)
+{
+	return try_to_wake_up(curr->private, mode, wake_flags);
+}
+EXPORT_SYMBOL(default_wake_function);
+
+/*
+ * The core wakeup function.  Non-exclusive wakeups (nr_exclusive == 0) just
+ * wake everything up.  If it's an exclusive wakeup (nr_exclusive == small +ve
+ * number) then we wake all the non-exclusive tasks and one exclusive task.
+ *
+ * There are circumstances in which we can try to wake a task which has already
+ * started to run but is not in state TASK_RUNNING.  try_to_wake_up() returns
+ * zero in this (rare) case, and we handle it by continuing to scan the queue.
+ */
+static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, int wake_flags, void *key)
+{
+	struct list_head *tmp, *next;
+
+	list_for_each_safe(tmp, next, &q->task_list) {
+		wait_queue_t *curr = list_entry(tmp, wait_queue_t, task_list);
+		unsigned int flags = curr->flags;
+
+		if (curr->func(curr, mode, wake_flags, key) &&
+				(flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
+			break;
+	}
+}
+
+/**
+ * __wake_up - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: is directly passed to the wakeup function
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, 0, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL(__wake_up);
+
+/*
+ * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
+ */
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
+{
+	__wake_up_common(q, mode, nr, 0, NULL);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked);
+
+void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+{
+	__wake_up_common(q, mode, 1, 0, key);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked_key);
+
+/**
+ * __wake_up_sync_key - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ * @key: opaque value to be passed to wakeup targets
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronised'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+			int nr_exclusive, void *key)
+{
+	unsigned long flags;
+	int wake_flags = WF_SYNC;
+
+	if (unlikely(!q))
+		return;
+
+	if (unlikely(!nr_exclusive))
+		wake_flags = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, wake_flags, key);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync_key);
+
+/**
+ * __wake_up_sync - wake up threads blocked on a waitqueue.
+ * @q: the waitqueue
+ * @mode: which threads
+ * @nr_exclusive: how many wake-one or wake-many threads to wake up
+ *
+ * The sync wakeup differs that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronised'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ */
+void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+{
+	unsigned long flags;
+	int sync = 1;
+
+	if (unlikely(!q))
+		return;
+
+	if (unlikely(!nr_exclusive))
+		sync = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
+
+/**
+ * complete: - signals a single thread waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up a single thread waiting on this completion. Threads will be
+ * awakened in the same order in which they were queued.
+ *
+ * See also complete_all(), wait_for_completion() and related routines.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done++;
+	__wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete);
+
+/**
+ * complete_all: - signals all threads waiting on this completion
+ * @x:  holds the state of this particular completion
+ *
+ * This will wake up all threads waiting on this particular completion event.
+ *
+ * It may be assumed that this function implies a write memory barrier before
+ * changing the task state if and only if any tasks are woken up.
+ */
+void complete_all(struct completion *x)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	x->done += UINT_MAX/2;
+	__wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL);
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+}
+EXPORT_SYMBOL(complete_all);
+
+static inline long __sched
+do_wait_for_common(struct completion *x, long timeout, int state)
+{
+	if (!x->done) {
+		DECLARE_WAITQUEUE(wait, current);
+
+		__add_wait_queue_tail_exclusive(&x->wait, &wait);
+		do {
+			if (signal_pending_state(state, current)) {
+				timeout = -ERESTARTSYS;
+				break;
+			}
+			__set_current_state(state);
+			spin_unlock_irq(&x->wait.lock);
+			timeout = schedule_timeout(timeout);
+			spin_lock_irq(&x->wait.lock);
+		} while (!x->done && timeout);
+		__remove_wait_queue(&x->wait, &wait);
+		if (!x->done)
+			return timeout;
+	}
+	x->done--;
+	return timeout ?: 1;
+}
+
+static long __sched
+wait_for_common(struct completion *x, long timeout, int state)
+{
+	might_sleep();
+
+	spin_lock_irq(&x->wait.lock);
+	timeout = do_wait_for_common(x, timeout, state);
+	spin_unlock_irq(&x->wait.lock);
+	return timeout;
+}
+
+/**
+ * wait_for_completion: - waits for completion of a task
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It is NOT
+ * interruptible and there is no timeout.
+ *
+ * See also similar routines (i.e. wait_for_completion_timeout()) with timeout
+ * and interrupt capability. Also see complete().
+ */
+void __sched wait_for_completion(struct completion *x)
+{
+	wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion);
+
+/**
+ * wait_for_completion_timeout: - waits for completion of a task (w/timeout)
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. The timeout is in jiffies. It is not
+ * interruptible.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
+ */
+unsigned long __sched
+wait_for_completion_timeout(struct completion *x, unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_timeout);
+
+/**
+ * wait_for_completion_interruptible: - waits for completion of a task (w/intr)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits for completion of a specific task to be signaled. It is
+ * interruptible.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
+ */
+int __sched wait_for_completion_interruptible(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible);
+
+/**
+ * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be signaled or for a
+ * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
+ */
+long __sched
+wait_for_completion_interruptible_timeout(struct completion *x,
+					  unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_INTERRUPTIBLE);
+}
+EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
+
+/**
+ * wait_for_completion_killable: - waits for completion of a task (killable)
+ * @x:  holds the state of this particular completion
+ *
+ * This waits to be signaled for completion of a specific task. It can be
+ * interrupted by a kill signal.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
+ */
+int __sched wait_for_completion_killable(struct completion *x)
+{
+	long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE);
+	if (t == -ERESTARTSYS)
+		return t;
+	return 0;
+}
+EXPORT_SYMBOL(wait_for_completion_killable);
+
+/**
+ * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable))
+ * @x:  holds the state of this particular completion
+ * @timeout:  timeout value in jiffies
+ *
+ * This waits for either a completion of a specific task to be
+ * signaled or for a specified timeout to expire. It can be
+ * interrupted by a kill signal. The timeout is in jiffies.
+ */
+long __sched
+wait_for_completion_killable_timeout(struct completion *x,
+					 unsigned long timeout)
+{
+	return wait_for_common(x, timeout, TASK_KILLABLE);
+}
+EXPORT_SYMBOL(wait_for_completion_killable_timeout);
+
+/**
+ *	try_wait_for_completion - try to decrement a completion without blocking
+ *	@x:	completion structure
+ *
+ *	Returns: 0 if a decrement cannot be done without blocking
+ *		 1 if a decrement succeeded.
+ *
+ *	If a completion is being used as a counting completion,
+ *	attempt to decrement the counter without blocking. This
+ *	enables us to avoid waiting if the resource the completion
+ *	is protecting is not available.
+ */
+bool try_wait_for_completion(struct completion *x)
+{
+	unsigned long flags;
+	int ret = 1;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	if (!x->done)
+		ret = 0;
+	else
+		x->done--;
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(try_wait_for_completion);
+
+/**
+ *	completion_done - Test to see if a completion has any waiters
+ *	@x:	completion structure
+ *
+ *	Returns: 0 if there are waiters (wait_for_completion() in progress)
+ *		 1 if there are no waiters.
+ *
+ */
+bool completion_done(struct completion *x)
+{
+	unsigned long flags;
+	int ret = 1;
+
+	spin_lock_irqsave(&x->wait.lock, flags);
+	if (!x->done)
+		ret = 0;
+	spin_unlock_irqrestore(&x->wait.lock, flags);
+	return ret;
+}
+EXPORT_SYMBOL(completion_done);
+
+static long __sched
+sleep_on_common(wait_queue_head_t *q, int state, long timeout)
+{
+	unsigned long flags;
+	wait_queue_t wait;
+
+	init_waitqueue_entry(&wait, current);
+
+	__set_current_state(state);
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, &wait);
+	spin_unlock(&q->lock);
+	timeout = schedule_timeout(timeout);
+	spin_lock_irq(&q->lock);
+	__remove_wait_queue(q, &wait);
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return timeout;
+}
+
+void __sched interruptible_sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+EXPORT_SYMBOL(interruptible_sleep_on);
+
+long __sched
+interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout);
+}
+EXPORT_SYMBOL(interruptible_sleep_on_timeout);
+
+void __sched sleep_on(wait_queue_head_t *q)
+{
+	sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+EXPORT_SYMBOL(sleep_on);
+
+long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
+{
+	return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout);
+}
+EXPORT_SYMBOL(sleep_on_timeout);
+
+#ifdef CONFIG_RT_MUTEXES
+
+/*
+ * rt_mutex_setprio - set the current priority of a task
+ * @p: task
+ * @prio: prio value (kernel-internal form)
+ *
+ * This function changes the 'effective' priority of a task. It does
+ * not touch ->prio like __setscheduler().
+ *
+ * Used by the rt_mutex code to implement priority inheritance logic.
+ */
+void rt_mutex_setprio(struct task_struct *p, int prio)
+{
+	unsigned long flags;
+	int queued, oldprio;
+	struct rq *rq;
+
+	BUG_ON(prio < 0 || prio > MAX_PRIO);
+
+	rq = task_grq_lock(p, &flags);
+
+	trace_sched_pi_setprio(p, prio);
+	oldprio = p->prio;
+	queued = task_queued(p);
+	p->prio = prio;
+	if (task_running(p) && prio > oldprio)
+		resched_task(p);
+	if (queued) {
+		try_preempt(p, rq);
+	}
+
+	task_grq_unlock(&flags);
+}
+
+#endif
+
+void set_user_nice(struct task_struct *p, long nice)
+{
+	int queued, new_static, old_static;
+	unsigned long flags;
+	struct rq *rq;
+
+	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
+		return;
+	new_static = NICE_TO_PRIO(nice);
+	/*
+	 * We have to be careful, if called from sys_setpriority(),
+	 * the task might be in the middle of scheduling on another CPU.
+	 */
+	rq = time_task_grq_lock(p, &flags);
+	/*
+	 * The RT priorities are set via sched_setscheduler(), but we still
+	 * allow the 'normal' nice value to be set - but as expected
+	 * it wont have any effect on scheduling until the task is
+	 * not SCHED_NORMAL/SCHED_BATCH:
+	 */
+	if (has_rt_policy(p)) {
+		p->static_prio = new_static;
+		goto out_unlock;
+	}
+	queued = task_queued(p);
+
+	old_static = p->static_prio;
+	p->static_prio = new_static;
+	p->prio = p->static_prio;
+
+	if (queued) {
+		if (new_static < old_static)
+			try_preempt(p, rq);
+	} else if (task_running(p)) {
+		reset_rq_task(rq, p);
+		if (old_static < new_static)
+			resched_task(p);
+	}
+out_unlock:
+	task_grq_unlock(&flags);
+}
+EXPORT_SYMBOL(set_user_nice);
+
+/*
+ * can_nice - check if a task can reduce its nice value
+ * @p: task
+ * @nice: nice value
+ */
+int can_nice(const struct task_struct *p, const int nice)
+{
+	/* convert nice value [19,-20] to rlimit style value [1,40] */
+	int nice_rlim = 20 - nice;
+
+	return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) ||
+		capable(CAP_SYS_NICE));
+}
+
+#ifdef __ARCH_WANT_SYS_NICE
+
+/*
+ * sys_nice - change the priority of the current process.
+ * @increment: priority increment
+ *
+ * sys_setpriority is a more generic, but much slower function that
+ * does similar things.
+ */
+SYSCALL_DEFINE1(nice, int, increment)
+{
+	long nice, retval;
+
+	/*
+	 * Setpriority might change our priority at the same moment.
+	 * We don't have to worry. Conceptually one call occurs first
+	 * and we have a single winner.
+	 */
+	if (increment < -40)
+		increment = -40;
+	if (increment > 40)
+		increment = 40;
+
+	nice = TASK_NICE(current) + increment;
+	if (nice < -20)
+		nice = -20;
+	if (nice > 19)
+		nice = 19;
+
+	if (increment < 0 && !can_nice(current, nice))
+		return -EPERM;
+
+	retval = security_task_setnice(current, nice);
+	if (retval)
+		return retval;
+
+	set_user_nice(current, nice);
+	return 0;
+}
+
+#endif
+
+/**
+ * task_prio - return the priority value of a given task.
+ * @p: the task in question.
+ *
+ * This is the priority value as seen by users in /proc.
+ * RT tasks are offset by -100. Normal tasks are centered around 1.
+ */
+int task_prio(const struct task_struct *p)
+{
+	return p->prio - NORMAL_PRIO;
+}
+
+/**
+ * task_nice - return the nice value of a given task.
+ * @p: the task in question.
+ */
+int task_nice(const struct task_struct *p)
+{
+	return TASK_NICE(p);
+}
+EXPORT_SYMBOL_GPL(task_nice);
+
+/**
+ * idle_cpu - is a given cpu idle currently?
+ * @cpu: the processor in question.
+ */
+int idle_cpu(int cpu)
+{
+	return cpu_curr(cpu) == cpu_rq(cpu)->idle;
+}
+
+/**
+ * idle_task - return the idle task for a given cpu.
+ * @cpu: the processor in question.
+ */
+struct task_struct *idle_task(int cpu)
+{
+	return cpu_rq(cpu)->idle;
+}
+
+/**
+ * find_process_by_pid - find a process with a matching PID value.
+ * @pid: the pid in question.
+ */
+static inline struct task_struct *find_process_by_pid(pid_t pid)
+{
+	return pid ? find_task_by_vpid(pid) : current;
+}
+
+/* Actually do priority change: must hold grq lock. */
+static void
+__setscheduler(struct task_struct *p, struct rq *rq, int policy, int prio)
+{
+	int oldrtprio, oldprio;
+
+	p->policy = policy;
+	oldrtprio = p->rt_priority;
+	p->rt_priority = prio;
+	oldprio = p->prio;
+	/* we are holding p->pi_lock already */
+	p->prio = rt_mutex_getprio(p);
+	if (task_running(p)) {
+		reset_rq_task(rq, p);
+		/* Resched only if we might now be preempted */
+		if (p->prio > oldprio || p->rt_priority > oldrtprio)
+			resched_task(p);
+	}
+}
+
+/*
+ * check the target process has a UID that matches the current process's
+ */
+static bool check_same_owner(struct task_struct *p)
+{
+	const struct cred *cred = current_cred(), *pcred;
+	bool match;
+
+	rcu_read_lock();
+	pcred = __task_cred(p);
+	if (cred->user->user_ns == pcred->user->user_ns)
+		match = (cred->euid == pcred->euid ||
+			 cred->euid == pcred->uid);
+	else
+		match = false;
+	rcu_read_unlock();
+	return match;
+}
+
+static int __sched_setscheduler(struct task_struct *p, int policy,
+				const struct sched_param *param, bool user)
+{
+	struct sched_param zero_param = { .sched_priority = 0 };
+	int queued, retval, oldpolicy = -1;
+	unsigned long flags, rlim_rtprio = 0;
+	int reset_on_fork;
+	struct rq *rq;
+
+	/* may grab non-irq protected spin_locks */
+	BUG_ON(in_interrupt());
+
+	if (is_rt_policy(policy) && !capable(CAP_SYS_NICE)) {
+		unsigned long lflags;
+
+		if (!lock_task_sighand(p, &lflags))
+			return -ESRCH;
+		rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
+		unlock_task_sighand(p, &lflags);
+		if (rlim_rtprio)
+			goto recheck;
+		param = &zero_param;
+	}
+recheck:
+	/* double check policy once rq lock held */
+	if (policy < 0) {
+		reset_on_fork = p->sched_reset_on_fork;
+		policy = oldpolicy = p->policy;
+	} else {
+		reset_on_fork = !!(policy & SCHED_RESET_ON_FORK);
+		policy &= ~SCHED_RESET_ON_FORK;
+
+		if (!SCHED_RANGE(policy))
+			return -EINVAL;
+	}
+
+	/*
+	 * Valid priorities for SCHED_FIFO and SCHED_RR are
+	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and
+	 * SCHED_BATCH is 0.
+	 */
+	if (param->sched_priority < 0 ||
+		(p->mm && param->sched_priority > MAX_USER_RT_PRIO - 1) ||
+		(!p->mm && param->sched_priority > MAX_RT_PRIO - 1))
+		return -EINVAL;
+	if (is_rt_policy(policy) != (param->sched_priority != 0))
+		return -EINVAL;
+
+	/*
+	 * Allow unprivileged RT tasks to decrease priority:
+	 */
+	if (user && !capable(CAP_SYS_NICE)) {
+		if (is_rt_policy(policy)) {
+			unsigned long rlim_rtprio =
+					task_rlimit(p, RLIMIT_RTPRIO);
+
+			/* can't set/change the rt policy */
+			if (policy != p->policy && !rlim_rtprio)
+				return -EPERM;
+
+			/* can't increase priority */
+			if (param->sched_priority > p->rt_priority &&
+				param->sched_priority > rlim_rtprio)
+				return -EPERM;
+		} else {
+			switch (p->policy) {
+				case SCHED_BATCH:
+					if (policy == SCHED_BATCH)
+						goto out;
+					if (policy != SCHED_IDLEPRIO)
+						return -EPERM;
+					break;
+				case SCHED_IDLEPRIO:
+					if (policy == SCHED_IDLEPRIO)
+						goto out;
+					return -EPERM;
+				default:
+					break;
+			}
+		}
+
+		/* can't change other user's priorities */
+		if (!check_same_owner(p))
+			return -EPERM;
+
+		/* Normal users shall not reset the sched_reset_on_fork flag */
+		if (p->sched_reset_on_fork && !reset_on_fork)
+			return -EPERM;
+	}
+
+	if (user) {
+		retval = security_task_setscheduler(p);
+		if (retval)
+			return retval;
+	}
+
+	/*
+	 * make sure no PI-waiters arrive (or leave) while we are
+	 * changing the priority of the task:
+	 */
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	/*
+	 * To be able to change p->policy safely, the grunqueue lock must be
+	 * held.
+	 */
+	rq = __task_grq_lock(p);
+
+	/*
+	 * Changing the policy of the stop threads its a very bad idea
+	 */
+	if (p == rq->stop) {
+		__task_grq_unlock();
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		return -EINVAL;
+	}
+
+	/*
+	 * If not changing anything there's no need to proceed further:
+	 */
+	if (unlikely(policy == p->policy && (!is_rt_policy(policy) ||
+			param->sched_priority == p->rt_priority))) {
+
+		__task_grq_unlock();
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		return 0;
+	}
+
+	/* recheck policy now with rq lock held */
+	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
+		policy = oldpolicy = -1;
+		__task_grq_unlock();
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+		goto recheck;
+	}
+	p->sched_reset_on_fork = reset_on_fork;
+
+	queued = task_queued(p);
+	__setscheduler(p, rq, policy, param->sched_priority);
+	if (queued) {
+		try_preempt(p, rq);
+	}
+	__task_grq_unlock();
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+	rt_mutex_adjust_pi(p);
+out:
+	return 0;
+}
+
+/**
+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * NOTE that the task may be already dead.
+ */
+int sched_setscheduler(struct task_struct *p, int policy,
+			   const struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, true);
+}
+
+EXPORT_SYMBOL_GPL(sched_setscheduler);
+
+/**
+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
+ * @p: the task in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ *
+ * Just like sched_setscheduler, only don't bother checking if the
+ * current context has permission.  For example, this is needed in
+ * stop_machine(): we create temporary high priority worker threads,
+ * but our caller might not have that capability.
+ */
+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
+				   const struct sched_param *param)
+{
+	return __sched_setscheduler(p, policy, param, false);
+}
+
+static int
+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
+{
+	struct sched_param lparam;
+	struct task_struct *p;
+	int retval;
+
+	if (!param || pid < 0)
+		return -EINVAL;
+	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
+		return -EFAULT;
+
+	rcu_read_lock();
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (p != NULL)
+		retval = sched_setscheduler(p, policy, &lparam);
+	rcu_read_unlock();
+
+	return retval;
+}
+
+/**
+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
+ * @pid: the pid in question.
+ * @policy: new policy.
+ * @param: structure containing the new RT priority.
+ */
+asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
+					   struct sched_param __user *param)
+{
+	/* negative values for policy are not valid */
+	if (policy < 0)
+		return -EINVAL;
+
+	return do_sched_setscheduler(pid, policy, param);
+}
+
+/**
+ * sys_sched_setparam - set/change the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the new RT priority.
+ */
+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
+{
+	return do_sched_setscheduler(pid, -1, param);
+}
+
+/**
+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
+ * @pid: the pid in question.
+ */
+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
+{
+	struct task_struct *p;
+	int retval = -EINVAL;
+
+	if (pid < 0)
+		goto out_nounlock;
+
+	retval = -ESRCH;
+	rcu_read_lock();
+	p = find_process_by_pid(pid);
+	if (p) {
+		retval = security_task_getscheduler(p);
+		if (!retval)
+			retval = p->policy;
+	}
+	rcu_read_unlock();
+
+out_nounlock:
+	return retval;
+}
+
+/**
+ * sys_sched_getscheduler - get the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the RT priority.
+ */
+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
+{
+	struct sched_param lp;
+	struct task_struct *p;
+	int retval = -EINVAL;
+
+	if (!param || pid < 0)
+		goto out_nounlock;
+
+	rcu_read_lock();
+	p = find_process_by_pid(pid);
+	retval = -ESRCH;
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	lp.sched_priority = p->rt_priority;
+	rcu_read_unlock();
+
+	/*
+	 * This one might sleep, we cannot do it with a spinlock held ...
+	 */
+	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
+
+out_nounlock:
+	return retval;
+
+out_unlock:
+	rcu_read_unlock();
+	return retval;
+}
+
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+{
+	cpumask_var_t cpus_allowed, new_mask;
+	struct task_struct *p;
+	int retval;
+
+	get_online_cpus();
+	rcu_read_lock();
+
+	p = find_process_by_pid(pid);
+	if (!p) {
+		rcu_read_unlock();
+		put_online_cpus();
+		return -ESRCH;
+	}
+
+	/* Prevent p going away */
+	get_task_struct(p);
+	rcu_read_unlock();
+
+	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_put_task;
+	}
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
+		retval = -ENOMEM;
+		goto out_free_cpus_allowed;
+	}
+	retval = -EPERM;
+	if (!check_same_owner(p) && !ns_capable(task_user_ns(p), CAP_SYS_NICE))
+		goto out_unlock;
+
+	retval = security_task_setscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	cpuset_cpus_allowed(p, cpus_allowed);
+	cpumask_and(new_mask, in_mask, cpus_allowed);
+again:
+	retval = set_cpus_allowed_ptr(p, new_mask);
+
+	if (!retval) {
+		cpuset_cpus_allowed(p, cpus_allowed);
+		if (!cpumask_subset(new_mask, cpus_allowed)) {
+			/*
+			 * We must have raced with a concurrent cpuset
+			 * update. Just reset the cpus_allowed to the
+			 * cpuset's cpus_allowed
+			 */
+			cpumask_copy(new_mask, cpus_allowed);
+			goto again;
+		}
+	}
+out_unlock:
+	free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+	free_cpumask_var(cpus_allowed);
+out_put_task:
+	put_task_struct(p);
+	put_online_cpus();
+	return retval;
+}
+
+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
+				 cpumask_t *new_mask)
+{
+	if (len < sizeof(cpumask_t)) {
+		memset(new_mask, 0, sizeof(cpumask_t));
+	} else if (len > sizeof(cpumask_t)) {
+		len = sizeof(cpumask_t);
+	}
+	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
+}
+
+
+/**
+ * sys_sched_setaffinity - set the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to the new cpu mask
+ */
+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
+{
+	cpumask_var_t new_mask;
+	int retval;
+
+	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
+	if (retval == 0)
+		retval = sched_setaffinity(pid, new_mask);
+	free_cpumask_var(new_mask);
+	return retval;
+}
+
+long sched_getaffinity(pid_t pid, cpumask_t *mask)
+{
+	struct task_struct *p;
+	unsigned long flags;
+	int retval;
+
+	get_online_cpus();
+	rcu_read_lock();
+
+	retval = -ESRCH;
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	grq_lock_irqsave(&flags);
+	cpumask_and(mask, tsk_cpus_allowed(p), cpu_online_mask);
+	grq_unlock_irqrestore(&flags);
+
+out_unlock:
+	rcu_read_unlock();
+	put_online_cpus();
+
+	return retval;
+}
+
+/**
+ * sys_sched_getaffinity - get the cpu affinity of a process
+ * @pid: pid of the process
+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
+ * @user_mask_ptr: user-space pointer to hold the current cpu mask
+ */
+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
+		unsigned long __user *, user_mask_ptr)
+{
+	int ret;
+	cpumask_var_t mask;
+
+	if ((len * BITS_PER_BYTE) < nr_cpu_ids)
+		return -EINVAL;
+	if (len & (sizeof(unsigned long)-1))
+		return -EINVAL;
+
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	ret = sched_getaffinity(pid, mask);
+	if (ret == 0) {
+		size_t retlen = min_t(size_t, len, cpumask_size());
+
+		if (copy_to_user(user_mask_ptr, mask, retlen))
+			ret = -EFAULT;
+		else
+			ret = retlen;
+	}
+	free_cpumask_var(mask);
+
+	return ret;
+}
+
+/**
+ * sys_sched_yield - yield the current processor to other threads.
+ *
+ * This function yields the current CPU to other tasks. It does this by
+ * scheduling away the current task. 
+ */
+SYSCALL_DEFINE0(sched_yield)
+{
+	struct task_struct *p;
+
+	p = current;
+	grq_lock_irq();
+	requeue_task(p);
+
+	/*
+	 * Since we are going to call schedule() anyway, there's
+	 * no need to preempt or enable interrupts:
+	 */
+	__release(grq.lock);
+	spin_release(&grq.lock.dep_map, 1, _THIS_IP_);
+	do_raw_spin_unlock(&grq.lock);
+	sched_preempt_enable_no_resched();
+
+	schedule();
+
+	return 0;
+}
+
+static inline bool should_resched(void)
+{
+	return need_resched() && !(preempt_count() & PREEMPT_ACTIVE);
+}
+
+static void __cond_resched(void)
+{
+	/* NOT a real fix but will make voluntary preempt work. 馬鹿な事 */
+	if (unlikely(system_state != SYSTEM_RUNNING))
+		return;
+
+	add_preempt_count(PREEMPT_ACTIVE);
+	schedule();
+	sub_preempt_count(PREEMPT_ACTIVE);
+}
+
+int __sched _cond_resched(void)
+{
+	if (should_resched()) {
+		__cond_resched();
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(_cond_resched);
+
+/*
+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
+ * call schedule, and on return reacquire the lock.
+ *
+ * This works OK both with and without CONFIG_PREEMPT.  We do strange low-level
+ * operations here to prevent schedule() from being called twice (once via
+ * spin_unlock(), once by hand).
+ */
+int __cond_resched_lock(spinlock_t *lock)
+{
+	int resched = should_resched();
+	int ret = 0;
+
+	lockdep_assert_held(lock);
+
+	if (spin_needbreak(lock) || resched) {
+		spin_unlock(lock);
+		if (resched)
+			__cond_resched();
+		else
+			cpu_relax();
+		ret = 1;
+		spin_lock(lock);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(__cond_resched_lock);
+
+int __sched __cond_resched_softirq(void)
+{
+	BUG_ON(!in_softirq());
+
+	if (should_resched()) {
+		local_bh_enable();
+		__cond_resched();
+		local_bh_disable();
+		return 1;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(__cond_resched_softirq);
+
+/**
+ * yield - yield the current processor to other threads.
+ *
+ * This is a shortcut for kernel-space yielding - it marks the
+ * thread runnable and calls sys_sched_yield().
+ */
+void __sched yield(void)
+{
+	set_current_state(TASK_RUNNING);
+	sys_sched_yield();
+}
+EXPORT_SYMBOL(yield);
+
+/**
+ * yield_to - yield the current processor to another thread in
+ * your thread group, or accelerate that thread toward the
+ * processor it's on.
+ * @p: target task
+ * @preempt: whether task preemption is allowed or not
+ *
+ * It's the caller's job to ensure that the target task struct
+ * can't go away on us before we can do any checks.
+ *
+ * Returns true if we indeed boosted the target task.
+ */
+bool __sched yield_to(struct task_struct *p, bool preempt)
+{
+	unsigned long flags;
+	bool yielded = 0;
+	struct rq *rq;
+	struct task_struct *curr;
+
+	rq = this_rq();
+	grq_lock_irqsave(&flags);
+	if (task_running(p) || p->state)
+		goto out_unlock;
+	yielded = 1;
+	curr = rq->curr;
+	set_tsk_need_resched(curr);
+out_unlock:
+	grq_unlock_irqrestore(&flags);
+
+	if (yielded)
+		schedule();
+	return yielded;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
+/*
+ * This task is about to go to sleep on IO.  Increment rq->nr_iowait so
+ * that process accounting knows that this is a task in IO wait state.
+ *
+ * But don't do that if it is a deliberate, throttling IO wait (this task
+ * has set its backing_dev_info: the queue against which it should throttle)
+ */
+void __sched io_schedule(void)
+{
+	struct rq *rq = raw_rq();
+
+	delayacct_blkio_start();
+	atomic_inc(&rq->nr_iowait);
+	blk_flush_plug(current);
+	current->in_iowait = 1;
+	schedule();
+	current->in_iowait = 0;
+	atomic_dec(&rq->nr_iowait);
+	delayacct_blkio_end();
+}
+EXPORT_SYMBOL(io_schedule);
+
+long __sched io_schedule_timeout(long timeout)
+{
+	struct rq *rq = raw_rq();
+	long ret;
+
+	delayacct_blkio_start();
+	atomic_inc(&rq->nr_iowait);
+	blk_flush_plug(current);
+	current->in_iowait = 1;
+	ret = schedule_timeout(timeout);
+	current->in_iowait = 0;
+	atomic_dec(&rq->nr_iowait);
+	delayacct_blkio_end();
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_max - return maximum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the maximum rt_priority that can be used
+ * by a given scheduling class.
+ */
+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = MAX_USER_RT_PRIO-1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+	case SCHED_IDLEPRIO:
+		ret = 0;
+		break;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_get_priority_min - return minimum RT priority.
+ * @policy: scheduling class.
+ *
+ * this syscall returns the minimum rt_priority that can be used
+ * by a given scheduling class.
+ */
+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
+{
+	int ret = -EINVAL;
+
+	switch (policy) {
+	case SCHED_FIFO:
+	case SCHED_RR:
+		ret = 1;
+		break;
+	case SCHED_NORMAL:
+	case SCHED_BATCH:
+	case SCHED_IDLEPRIO:
+		ret = 0;
+		break;
+	}
+	return ret;
+}
+
+/**
+ * sys_sched_rr_get_interval - return the default timeslice of a process.
+ * @pid: pid of the process.
+ * @interval: userspace pointer to the timeslice value.
+ *
+ * this syscall writes the default timeslice value of a given process
+ * into the user-space timespec buffer. A value of '0' means infinity.
+ */
+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
+		struct timespec __user *, interval)
+{
+	struct task_struct *p;
+	unsigned long flags;
+	int retval;
+	struct timespec t;
+
+	if (pid < 0)
+		return -EINVAL;
+
+	retval = -ESRCH;
+	rcu_read_lock();
+	p = find_process_by_pid(pid);
+	if (!p)
+		goto out_unlock;
+
+	retval = security_task_getscheduler(p);
+	if (retval)
+		goto out_unlock;
+
+	grq_lock_irqsave(&flags);
+	grq_unlock_irqrestore(&flags);
+
+	rcu_read_unlock();
+	t = ns_to_timespec(MS_TO_NS(rr_interval));
+	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
+	return retval;
+
+out_unlock:
+	rcu_read_unlock();
+	return retval;
+}
+
+static const char stat_nam[] = TASK_STATE_TO_CHAR_STR;
+
+void sched_show_task(struct task_struct *p)
+{
+	unsigned long free = 0;
+	unsigned state;
+
+	state = p->state ? __ffs(p->state) + 1 : 0;
+	printk(KERN_INFO "%-15.15s %c", p->comm,
+		state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?');
+#if BITS_PER_LONG == 32
+	if (state == TASK_RUNNING)
+		printk(KERN_CONT " running  ");
+	else
+		printk(KERN_CONT " %08lx ", thread_saved_pc(p));
+#else
+	if (state == TASK_RUNNING)
+		printk(KERN_CONT "  running task	");
+	else
+		printk(KERN_CONT " %016lx ", thread_saved_pc(p));
+#endif
+#ifdef CONFIG_DEBUG_STACK_USAGE
+	free = stack_not_used(p);
+#endif
+	printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free,
+		task_pid_nr(p), task_pid_nr(p->real_parent),
+		(unsigned long)task_thread_info(p)->flags);
+
+	show_stack(p, NULL);
+}
+
+void show_state_filter(unsigned long state_filter)
+{
+	struct task_struct *g, *p;
+
+#if BITS_PER_LONG == 32
+	printk(KERN_INFO
+		"  task				PC stack   pid father\n");
+#else
+	printk(KERN_INFO
+		"  task						PC stack   pid father\n");
+#endif
+	rcu_read_lock();
+	do_each_thread(g, p) {
+		/*
+		 * reset the NMI-timeout, listing all files on a slow
+		 * console might take a lot of time:
+		 */
+		touch_nmi_watchdog();
+		if (!state_filter || (p->state & state_filter))
+			sched_show_task(p);
+	} while_each_thread(g, p);
+
+	touch_all_softlockup_watchdogs();
+
+	rcu_read_unlock();
+	/*
+	 * Only show locks if all tasks are dumped:
+	 */
+	if (!state_filter)
+		debug_show_all_locks();
+}
+
+#ifdef CONFIG_SMP
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+	cpumask_copy(tsk_cpus_allowed(p), new_mask);
+}
+#endif
+
+/**
+ * init_idle - set up an idle thread for a given CPU
+ * @idle: task in question
+ * @cpu: cpu the idle task belongs to
+ *
+ * NOTE: this function does not set the idle thread's NEED_RESCHED
+ * flag, to make booting more robust.
+ */
+void init_idle(struct task_struct *idle, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	unsigned long flags;
+
+	time_grq_lock(rq, &flags);
+	idle->last_ran = rq->clock;
+	idle->state = TASK_RUNNING;
+	/* Setting prio to illegal value shouldn't matter when never queued */
+	idle->prio = PRIO_LIMIT;
+	idle->policy = SCHED_IDLE;
+	set_rq_task(rq, idle);
+	do_set_cpus_allowed(idle, &cpumask_of_cpu(cpu));
+	/* Silence PROVE_RCU */
+	rcu_read_lock();
+	set_task_cpu(idle, cpu);
+	rcu_read_unlock();
+	rq->curr = rq->idle = idle;
+	idle->on_cpu = 1;
+	grq_unlock_irqrestore(&flags);
+
+	/* Set the preempt count _outside_ the spinlocks! */
+	task_thread_info(idle)->preempt_count = 0;
+
+	ftrace_graph_init_idle_task(idle, cpu);
+#if defined(CONFIG_SMP)
+	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
+#endif
+}
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_NO_HZ
+void select_nohz_load_balancer(int stop_tick)
+{
+}
+
+void set_cpu_sd_state_idle(void) {}
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+/**
+ * lowest_flag_domain - Return lowest sched_domain containing flag.
+ * @cpu:	The cpu whose lowest level of sched domain is to
+ *		be returned.
+ * @flag:	The flag to check for the lowest sched_domain
+ *		for the given cpu.
+ *
+ * Returns the lowest sched_domain of a cpu which contains the given flag.
+ */
+static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
+{
+	struct sched_domain *sd;
+
+	for_each_domain(cpu, sd)
+		if (sd && (sd->flags & flag))
+			break;
+
+	return sd;
+}
+
+/**
+ * for_each_flag_domain - Iterates over sched_domains containing the flag.
+ * @cpu:	The cpu whose domains we're iterating over.
+ * @sd:		variable holding the value of the power_savings_sd
+ *		for cpu.
+ * @flag:	The flag to filter the sched_domains to be iterated.
+ *
+ * Iterates over all the scheduler domains for a given cpu that has the 'flag'
+ * set, starting from the lowest sched_domain to the highest.
+ */
+#define for_each_flag_domain(cpu, sd, flag) \
+	for (sd = lowest_flag_domain(cpu, flag); \
+		(sd && (sd->flags & flag)); sd = sd->parent)
+
+#endif /*  (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
+
+static inline void resched_cpu(int cpu)
+{
+	unsigned long flags;
+
+	grq_lock_irqsave(&flags);
+	resched_task(cpu_curr(cpu));
+	grq_unlock_irqrestore(&flags);
+}
+
+/*
+ * 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
+ * which is scheduled to wake up that CPU. In case of a completely
+ * idle system the next event might even be infinite time into the
+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
+ * leaves the inner idle loop so the newly added timer is taken into
+ * account when the CPU goes back to idle and evaluates the timer
+ * wheel for the next timer event.
+ */
+void wake_up_idle_cpu(int cpu)
+{
+	struct task_struct *idle;
+	struct rq *rq;
+
+	if (cpu == smp_processor_id())
+		return;
+
+	rq = cpu_rq(cpu);
+	idle = rq->idle;
+
+	/*
+	 * This is safe, as this function is called with the timer
+	 * wheel base lock of (cpu) held. When the CPU is on the way
+	 * to idle and has not yet set rq->curr to idle then it will
+	 * be serialised on the timer wheel base lock and take the new
+	 * timer into account automatically.
+	 */
+	if (unlikely(rq->curr != idle))
+		return;
+
+	/*
+	 * We can set TIF_RESCHED on the idle task of the other CPU
+	 * lockless. The worst case is that the other CPU runs the
+	 * idle task through an additional NOOP schedule()
+	 */
+	set_tsk_need_resched(idle);
+
+	/* NEED_RESCHED must be visible before we test polling */
+	smp_mb();
+	if (!tsk_is_polling(idle))
+		smp_send_reschedule(cpu);
+}
+
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Change a given task's CPU affinity. Migrate the thread to a
+ * proper CPU and schedule it away if the CPU it's executing on
+ * is removed from the allowed bitmask.
+ *
+ * NOTE: the caller must have a valid reference to the task, the
+ * task must not exit() & deallocate itself prematurely. The
+ * call is not atomic; no spinlocks may be held.
+ */
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+{
+	bool running_wrong = false;
+	bool queued = false;
+	unsigned long flags;
+	struct rq *rq;
+	int ret = 0;
+
+	rq = task_grq_lock(p, &flags);
+
+	if (cpumask_equal(tsk_cpus_allowed(p), new_mask))
+		goto out;
+
+	if (!cpumask_intersects(new_mask, cpu_active_mask)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	queued = task_queued(p);
+
+	do_set_cpus_allowed(p, new_mask);
+
+	/* Can the task run on the task's current CPU? If so, we're done */
+	if (cpumask_test_cpu(task_cpu(p), new_mask))
+		goto out;
+
+	if (task_running(p)) {
+		/* Task is running on the wrong cpu now, reschedule it. */
+		if (rq == this_rq()) {
+			set_tsk_need_resched(p);
+			running_wrong = true;
+		} else
+			resched_task(p);
+	} else
+		set_task_cpu(p, cpumask_any_and(cpu_active_mask, new_mask));
+
+out:
+	if (queued)
+		try_preempt(p, rq);
+	task_grq_unlock(&flags);
+
+	if (running_wrong)
+		_cond_resched();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
+
+#ifdef CONFIG_HOTPLUG_CPU
+/* Run through task list and find tasks affined to just the dead cpu, then
+ * allocate a new affinity */
+static void break_sole_affinity(int src_cpu, struct task_struct *idle)
+{
+	struct task_struct *p, *t;
+
+	do_each_thread(t, p) {
+		if (p != idle && !online_cpus(p)) {
+			cpumask_copy(tsk_cpus_allowed(p), cpu_possible_mask);
+			/*
+			 * Don't tell them about moving exiting tasks or
+			 * kernel threads (both mm NULL), since they never
+			 * leave kernel.
+			 */
+			if (p->mm && printk_ratelimit()) {
+				printk(KERN_INFO "process %d (%s) no "
+					   "longer affine to cpu %d\n",
+					   task_pid_nr(p), p->comm, src_cpu);
+			}
+		}
+		clear_sticky(p);
+	} while_each_thread(t, p);
+}
+
+/*
+ * Schedules idle task to be the next runnable task on current CPU.
+ * It does so by boosting its priority to highest possible.
+ * Used by CPU offline code.
+ */
+void sched_idle_next(struct rq *rq, int this_cpu, struct task_struct *idle)
+{
+	/* cpu has to be offline */
+	BUG_ON(cpu_online(this_cpu));
+
+	__setscheduler(idle, rq, SCHED_FIFO, STOP_PRIO);
+
+	activate_idle_task(idle);
+	set_tsk_need_resched(rq->curr);
+}
+
+/*
+ * Ensures that the idle task is using init_mm right before its cpu goes
+ * offline.
+ */
+void idle_task_exit(void)
+{
+	struct mm_struct *mm = current->active_mm;
+
+	BUG_ON(cpu_online(smp_processor_id()));
+
+	if (mm != &init_mm)
+		switch_mm(mm, &init_mm, current);
+	mmdrop(mm);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+	struct sched_param stop_param = { .sched_priority = STOP_PRIO };
+	struct sched_param start_param = { .sched_priority = MAX_USER_RT_PRIO - 1 };
+	struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+	if (stop) {
+		/*
+		 * Make it appear like a SCHED_FIFO task, its something
+		 * userspace knows about and won't get confused about.
+		 *
+		 * Also, it will make PI more or less work without too
+		 * much confusion -- but then, stop work should not
+		 * rely on PI working anyway.
+		 */
+		sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param);
+	}
+
+	cpu_rq(cpu)->stop = stop;
+
+	if (old_stop) {
+		/*
+		 * Reset it back to a normal rt scheduling prio so that
+		 * it can die in pieces.
+		 */
+		sched_setscheduler_nocheck(old_stop, SCHED_FIFO, &start_param);
+	}
+}
+
+
+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
+
+static struct ctl_table sd_ctl_dir[] = {
+	{
+		.procname	= "sched_domain",
+		.mode		= 0555,
+	},
+	{}
+};
+
+static struct ctl_table sd_ctl_root[] = {
+	{
+		.procname	= "kernel",
+		.mode		= 0555,
+		.child		= sd_ctl_dir,
+	},
+	{}
+};
+
+static struct ctl_table *sd_alloc_ctl_entry(int n)
+{
+	struct ctl_table *entry =
+		kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL);
+
+	return entry;
+}
+
+static void sd_free_ctl_entry(struct ctl_table **tablep)
+{
+	struct ctl_table *entry;
+
+	/*
+	 * In the intermediate directories, both the child directory and
+	 * procname are dynamically allocated and could fail but the mode
+	 * will always be set. In the lowest directory the names are
+	 * static strings and all have proc handlers.
+	 */
+	for (entry = *tablep; entry->mode; entry++) {
+		if (entry->child)
+			sd_free_ctl_entry(&entry->child);
+		if (entry->proc_handler == NULL)
+			kfree(entry->procname);
+	}
+
+	kfree(*tablep);
+	*tablep = NULL;
+}
+
+static void
+set_table_entry(struct ctl_table *entry,
+		const char *procname, void *data, int maxlen,
+		mode_t mode, proc_handler *proc_handler)
+{
+	entry->procname = procname;
+	entry->data = data;
+	entry->maxlen = maxlen;
+	entry->mode = mode;
+	entry->proc_handler = proc_handler;
+}
+
+static struct ctl_table *
+sd_alloc_ctl_domain_table(struct sched_domain *sd)
+{
+	struct ctl_table *table = sd_alloc_ctl_entry(13);
+
+	if (table == NULL)
+		return NULL;
+
+	set_table_entry(&table[0], "min_interval", &sd->min_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[1], "max_interval", &sd->max_interval,
+		sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[2], "busy_idx", &sd->busy_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[3], "idle_idx", &sd->idle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[5], "wake_idx", &sd->wake_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[7], "busy_factor", &sd->busy_factor,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[9], "cache_nice_tries",
+		&sd->cache_nice_tries,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[10], "flags", &sd->flags,
+		sizeof(int), 0644, proc_dointvec_minmax);
+	set_table_entry(&table[11], "name", sd->name,
+		CORENAME_MAX_SIZE, 0444, proc_dostring);
+	/* &table[12] is terminator */
+
+	return table;
+}
+
+static ctl_table *sd_alloc_ctl_cpu_table(int cpu)
+{
+	struct ctl_table *entry, *table;
+	struct sched_domain *sd;
+	int domain_num = 0, i;
+	char buf[32];
+
+	for_each_domain(cpu, sd)
+		domain_num++;
+	entry = table = sd_alloc_ctl_entry(domain_num + 1);
+	if (table == NULL)
+		return NULL;
+
+	i = 0;
+	for_each_domain(cpu, sd) {
+		snprintf(buf, 32, "domain%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_domain_table(sd);
+		entry++;
+		i++;
+	}
+	return table;
+}
+
+static struct ctl_table_header *sd_sysctl_header;
+static void register_sched_domain_sysctl(void)
+{
+	int i, cpu_num = num_possible_cpus();
+	struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
+	char buf[32];
+
+	WARN_ON(sd_ctl_dir[0].child);
+	sd_ctl_dir[0].child = entry;
+
+	if (entry == NULL)
+		return;
+
+	for_each_possible_cpu(i) {
+		snprintf(buf, 32, "cpu%d", i);
+		entry->procname = kstrdup(buf, GFP_KERNEL);
+		entry->mode = 0555;
+		entry->child = sd_alloc_ctl_cpu_table(i);
+		entry++;
+	}
+
+	WARN_ON(sd_sysctl_header);
+	sd_sysctl_header = register_sysctl_table(sd_ctl_root);
+}
+
+/* may be called multiple times per register */
+static void unregister_sched_domain_sysctl(void)
+{
+	if (sd_sysctl_header)
+		unregister_sysctl_table(sd_sysctl_header);
+	sd_sysctl_header = NULL;
+	if (sd_ctl_dir[0].child)
+		sd_free_ctl_entry(&sd_ctl_dir[0].child);
+}
+#else
+static void register_sched_domain_sysctl(void)
+{
+}
+static void unregister_sched_domain_sysctl(void)
+{
+}
+#endif
+
+static void set_rq_online(struct rq *rq)
+{
+	if (!rq->online) {
+		cpumask_set_cpu(cpu_of(rq), rq->rd->online);
+		rq->online = true;
+	}
+}
+
+static void set_rq_offline(struct rq *rq)
+{
+	if (rq->online) {
+		cpumask_clear_cpu(cpu_of(rq), rq->rd->online);
+		rq->online = false;
+	}
+}
+
+/*
+ * migration_call - callback that gets triggered when a CPU is added.
+ */
+static int __cpuinit
+migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	unsigned long flags;
+	struct rq *rq = cpu_rq(cpu);
+#ifdef CONFIG_HOTPLUG_CPU
+	struct task_struct *idle = rq->idle;
+#endif
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+
+	case CPU_UP_PREPARE:
+		break;
+
+	case CPU_ONLINE:
+		/* Update our root-domain */
+		grq_lock_irqsave(&flags);
+		if (rq->rd) {
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+
+			set_rq_online(rq);
+		}
+		grq.noc = num_online_cpus();
+		grq_unlock_irqrestore(&flags);
+		break;
+
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DEAD:
+		/* Idle task back to normal (off runqueue, low prio) */
+		grq_lock_irq();
+		put_prev_task(rq, idle, true, false);
+		idle->static_prio = MAX_PRIO;
+		__setscheduler(idle, rq, SCHED_NORMAL, 0);
+		idle->prio = PRIO_LIMIT;
+		set_rq_task(rq, idle);
+		grq_unlock_irq();
+		break;
+
+	case CPU_DYING:
+		/* Update our root-domain */
+		grq_lock_irqsave(&flags);
+		sched_idle_next(rq, cpu, idle);
+		if (rq->rd) {
+			BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+			set_rq_offline(rq);
+		}
+		break_sole_affinity(cpu, idle);
+		grq.noc = num_online_cpus();
+		grq_unlock_irqrestore(&flags);
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+/*
+ * Register at high priority so that task migration (migrate_all_tasks)
+ * happens before everything else.  This has to be lower priority than
+ * the notifier in the perf_counter subsystem, though.
+ */
+static struct notifier_block __cpuinitdata migration_notifier = {
+	.notifier_call = migration_call,
+	.priority = CPU_PRI_MIGRATION,
+};
+
+static int __cpuinit sched_cpu_active(struct notifier_block *nfb,
+					  unsigned long action, void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+	case CPU_DOWN_FAILED:
+		set_cpu_active((long)hcpu, true);
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb,
+					unsigned long action, void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DOWN_PREPARE:
+		set_cpu_active((long)hcpu, false);
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+int __init migration_init(void)
+{
+	void *cpu = (void *)(long)smp_processor_id();
+	int err;
+
+	/* Initialise migration for the boot CPU */
+	err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
+	BUG_ON(err == NOTIFY_BAD);
+	migration_call(&migration_notifier, CPU_ONLINE, cpu);
+	register_cpu_notifier(&migration_notifier);
+
+	/* Register cpu active notifiers */
+	cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE);
+	cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE);
+
+	return 0;
+}
+early_initcall(migration_init);
+#endif
+
+#ifdef CONFIG_SMP
+
+static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */
+
+#ifdef CONFIG_SCHED_DEBUG
+
+static __read_mostly int sched_domain_debug_enabled;
+
+static int __init sched_domain_debug_setup(char *str)
+{
+	sched_domain_debug_enabled = 1;
+
+	return 0;
+}
+early_param("sched_debug", sched_domain_debug_setup);
+
+static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
+				  struct cpumask *groupmask)
+{
+	struct sched_group *group = sd->groups;
+	char str[256];
+
+	cpulist_scnprintf(str, sizeof(str), sched_domain_span(sd));
+	cpumask_clear(groupmask);
+
+	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+
+	if (!(sd->flags & SD_LOAD_BALANCE)) {
+		printk("does not load-balance\n");
+		if (sd->parent)
+			printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain"
+					" has parent");
+		return -1;
+	}
+
+	printk(KERN_CONT "span %s level %s\n", str, sd->name);
+
+	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
+		printk(KERN_ERR "ERROR: domain->span does not contain "
+				"CPU%d\n", cpu);
+	}
+	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+		printk(KERN_ERR "ERROR: domain->groups does not contain"
+				" CPU%d\n", cpu);
+	}
+
+	printk(KERN_DEBUG "%*s groups:", level + 1, "");
+	do {
+		if (!group) {
+			printk("\n");
+			printk(KERN_ERR "ERROR: group is NULL\n");
+			break;
+		}
+
+		if (!group->sgp->power) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: domain->cpu_power not "
+					"set\n");
+			break;
+		}
+
+		if (!cpumask_weight(sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: empty group\n");
+			break;
+		}
+
+		if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
+			printk(KERN_CONT "\n");
+			printk(KERN_ERR "ERROR: repeated CPUs\n");
+			break;
+		}
+
+		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+
+		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
+
+		printk(KERN_CONT " %s", str);
+		if (group->sgp->power != SCHED_POWER_SCALE) {
+			printk(KERN_CONT " (cpu_power = %d)",
+				group->sgp->power);
+		}
+
+		group = group->next;
+	} while (group != sd->groups);
+	printk(KERN_CONT "\n");
+
+	if (!cpumask_equal(sched_domain_span(sd), groupmask))
+		printk(KERN_ERR "ERROR: groups don't span domain->span\n");
+
+	if (sd->parent &&
+		!cpumask_subset(groupmask, sched_domain_span(sd->parent)))
+		printk(KERN_ERR "ERROR: parent span is not a superset "
+			"of domain->span\n");
+	return 0;
+}
+
+static void sched_domain_debug(struct sched_domain *sd, int cpu)
+{
+	int level = 0;
+
+	if (!sched_domain_debug_enabled)
+		return;
+
+	if (!sd) {
+		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
+		return;
+	}
+
+	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+
+	for (;;) {
+		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
+			break;
+		level++;
+		sd = sd->parent;
+		if (!sd)
+			break;
+	}
+}
+#else /* !CONFIG_SCHED_DEBUG */
+# define sched_domain_debug(sd, cpu) do { } while (0)
+#endif /* CONFIG_SCHED_DEBUG */
+
+static int sd_degenerate(struct sched_domain *sd)
+{
+	if (cpumask_weight(sched_domain_span(sd)) == 1)
+		return 1;
+
+	/* Following flags need at least 2 groups */
+	if (sd->flags & (SD_LOAD_BALANCE |
+			 SD_BALANCE_NEWIDLE |
+			 SD_BALANCE_FORK |
+			 SD_BALANCE_EXEC |
+			 SD_SHARE_CPUPOWER |
+			 SD_SHARE_PKG_RESOURCES)) {
+		if (sd->groups != sd->groups->next)
+			return 0;
+	}
+
+	/* Following flags don't use groups */
+	if (sd->flags & (SD_WAKE_AFFINE))
+		return 0;
+
+	return 1;
+}
+
+static int
+sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
+{
+	unsigned long cflags = sd->flags, pflags = parent->flags;
+
+	if (sd_degenerate(parent))
+		return 1;
+
+	if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent)))
+		return 0;
+
+	/* Flags needing groups don't count if only 1 group in parent */
+	if (parent->groups == parent->groups->next) {
+		pflags &= ~(SD_LOAD_BALANCE |
+				SD_BALANCE_NEWIDLE |
+				SD_BALANCE_FORK |
+				SD_BALANCE_EXEC |
+				SD_SHARE_CPUPOWER |
+				SD_SHARE_PKG_RESOURCES);
+		if (nr_node_ids == 1)
+			pflags &= ~SD_SERIALIZE;
+	}
+	if (~cflags & pflags)
+		return 0;
+
+	return 1;
+}
+
+static void free_rootdomain(struct rcu_head *rcu)
+{
+	struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
+
+	cpupri_cleanup(&rd->cpupri);
+	free_cpumask_var(rd->rto_mask);
+	free_cpumask_var(rd->online);
+	free_cpumask_var(rd->span);
+	kfree(rd);
+}
+
+static void rq_attach_root(struct rq *rq, struct root_domain *rd)
+{
+	struct root_domain *old_rd = NULL;
+	unsigned long flags;
+
+	grq_lock_irqsave(&flags);
+
+	if (rq->rd) {
+		old_rd = rq->rd;
+
+		if (cpumask_test_cpu(rq->cpu, old_rd->online))
+			set_rq_offline(rq);
+
+		cpumask_clear_cpu(rq->cpu, old_rd->span);
+
+		/*
+		 * If we dont want to free the old_rt yet then
+		 * set old_rd to NULL to skip the freeing later
+		 * in this function:
+		 */
+		if (!atomic_dec_and_test(&old_rd->refcount))
+			old_rd = NULL;
+	}
+
+	atomic_inc(&rd->refcount);
+	rq->rd = rd;
+
+	cpumask_set_cpu(rq->cpu, rd->span);
+	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
+		set_rq_online(rq);
+
+	grq_unlock_irqrestore(&flags);
+
+	if (old_rd)
+		call_rcu_sched(&old_rd->rcu, free_rootdomain);
+}
+
+static int init_rootdomain(struct root_domain *rd)
+{
+	memset(rd, 0, sizeof(*rd));
+
+	if (!alloc_cpumask_var(&rd->span, GFP_KERNEL))
+		goto out;
+	if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
+		goto free_span;
+	if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+		goto free_online;
+
+	if (cpupri_init(&rd->cpupri) != 0)
+		goto free_rto_mask;
+	return 0;
+
+free_rto_mask:
+	free_cpumask_var(rd->rto_mask);
+free_online:
+	free_cpumask_var(rd->online);
+free_span:
+	free_cpumask_var(rd->span);
+out:
+	return -ENOMEM;
+}
+
+static void init_defrootdomain(void)
+{
+	init_rootdomain(&def_root_domain);
+
+	atomic_set(&def_root_domain.refcount, 1);
+}
+
+static struct root_domain *alloc_rootdomain(void)
+{
+	struct root_domain *rd;
+
+	rd = kmalloc(sizeof(*rd), GFP_KERNEL);
+	if (!rd)
+		return NULL;
+
+	if (init_rootdomain(rd) != 0) {
+		kfree(rd);
+		return NULL;
+	}
+
+	return rd;
+}
+
+static void free_sched_groups(struct sched_group *sg, int free_sgp)
+{
+	struct sched_group *tmp, *first;
+
+	if (!sg)
+		return;
+
+	first = sg;
+	do {
+		tmp = sg->next;
+
+		if (free_sgp && atomic_dec_and_test(&sg->sgp->ref))
+			kfree(sg->sgp);
+
+		kfree(sg);
+		sg = tmp;
+	} while (sg != first);
+}
+
+static void free_sched_domain(struct rcu_head *rcu)
+{
+	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
+
+	/*
+	 * If its an overlapping domain it has private groups, iterate and
+	 * nuke them all.
+	 */
+	if (sd->flags & SD_OVERLAP) {
+		free_sched_groups(sd->groups, 1);
+	} else if (atomic_dec_and_test(&sd->groups->ref)) {
+		kfree(sd->groups->sgp);
+		kfree(sd->groups);
+	}
+	kfree(sd);
+}
+
+static void destroy_sched_domain(struct sched_domain *sd, int cpu)
+{
+	call_rcu(&sd->rcu, free_sched_domain);
+}
+
+static void destroy_sched_domains(struct sched_domain *sd, int cpu)
+{
+	for (; sd; sd = sd->parent)
+		destroy_sched_domain(sd, cpu);
+}
+
+/*
+ * Attach the domain 'sd' to 'cpu' as its base domain. Callers must
+ * hold the hotplug lock.
+ */
+static void
+cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu)
+{
+	struct rq *rq = cpu_rq(cpu);
+	struct sched_domain *tmp;
+
+	/* Remove the sched domains which do not contribute to scheduling. */
+	for (tmp = sd; tmp; ) {
+		struct sched_domain *parent = tmp->parent;
+		if (!parent)
+			break;
+
+		if (sd_parent_degenerate(tmp, parent)) {
+			tmp->parent = parent->parent;
+			if (parent->parent)
+				parent->parent->child = tmp;
+			destroy_sched_domain(parent, cpu);
+		} else
+			tmp = tmp->parent;
+	}
+
+	if (sd && sd_degenerate(sd)) {
+		tmp = sd;
+		sd = sd->parent;
+		destroy_sched_domain(tmp, cpu);
+		if (sd)
+			sd->child = NULL;
+	}
+
+	sched_domain_debug(sd, cpu);
+
+	rq_attach_root(rq, rd);
+	tmp = rq->sd;
+	rcu_assign_pointer(rq->sd, sd);
+	destroy_sched_domains(tmp, cpu);
+}
+
+/* cpus with isolated domains */
+static cpumask_var_t cpu_isolated_map;
+
+/* Setup the mask of cpus configured for isolated domains */
+static int __init isolated_cpu_setup(char *str)
+{
+	alloc_bootmem_cpumask_var(&cpu_isolated_map);
+	cpulist_parse(str, cpu_isolated_map);
+	return 1;
+}
+
+__setup("isolcpus=", isolated_cpu_setup);
+
+#define SD_NODES_PER_DOMAIN 16
+
+#ifdef CONFIG_NUMA
+
+/**
+ * find_next_best_node - find the next node to include in a sched_domain
+ * @node: node whose sched_domain we're building
+ * @used_nodes: nodes already in the sched_domain
+ *
+ * Find the next node to include in a given scheduling domain. Simply
+ * finds the closest node not already in the @used_nodes map.
+ *
+ * Should use nodemask_t.
+ */
+static int find_next_best_node(int node, nodemask_t *used_nodes)
+{
+	int i, n, val, min_val, best_node = -1;
+
+	min_val = INT_MAX;
+
+	for (i = 0; i < nr_node_ids; i++) {
+		/* Start at @node */
+		n = (node + i) % nr_node_ids;
+
+		if (!nr_cpus_node(n))
+			continue;
+
+		/* Skip already used nodes */
+		if (node_isset(n, *used_nodes))
+			continue;
+
+		/* Simple min distance search */
+		val = node_distance(node, n);
+
+		if (val < min_val) {
+			min_val = val;
+			best_node = n;
+		}
+	}
+
+	if (best_node != -1)
+		node_set(best_node, *used_nodes);
+	return best_node;
+}
+
+/**
+ * sched_domain_node_span - get a cpumask for a node's sched_domain
+ * @node: node whose cpumask we're constructing
+ * @span: resulting cpumask
+ *
+ * Given a node, construct a good cpumask for its sched_domain to span. It
+ * should be one that prevents unnecessary balancing, but also spreads tasks
+ * out optimally.
+ */
+static void sched_domain_node_span(int node, struct cpumask *span)
+{
+	nodemask_t used_nodes;
+	int i;
+
+	cpumask_clear(span);
+	nodes_clear(used_nodes);
+
+	cpumask_or(span, span, cpumask_of_node(node));
+	node_set(node, used_nodes);
+
+	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
+		int next_node = find_next_best_node(node, &used_nodes);
+		if (next_node < 0)
+			break;
+		cpumask_or(span, span, cpumask_of_node(next_node));
+	}
+}
+
+static const struct cpumask *cpu_node_mask(int cpu)
+{
+	lockdep_assert_held(&sched_domains_mutex);
+
+	sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask);
+
+	return sched_domains_tmpmask;
+}
+
+static const struct cpumask *cpu_allnodes_mask(int cpu)
+{
+	return cpu_possible_mask;
+}
+#endif /* CONFIG_NUMA */
+
+static const struct cpumask *cpu_cpu_mask(int cpu)
+{
+	return cpumask_of_node(cpu_to_node(cpu));
+}
+
+int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
+
+struct sd_data {
+	struct sched_domain **__percpu sd;
+	struct sched_group **__percpu sg;
+	struct sched_group_power **__percpu sgp;
+};
+
+struct s_data {
+	struct sched_domain ** __percpu sd;
+	struct root_domain	*rd;
+};
+
+enum s_alloc {
+	sa_rootdomain,
+	sa_sd,
+	sa_sd_storage,
+	sa_none,
+};
+
+struct sched_domain_topology_level;
+
+typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
+typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
+
+#define SDTL_OVERLAP	0x01
+
+struct sched_domain_topology_level {
+	sched_domain_init_f init;
+	sched_domain_mask_f mask;
+	int			flags;
+	struct sd_data	  data;
+};
+
+static int
+build_overlap_sched_groups(struct sched_domain *sd, int cpu)
+{
+	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered = sched_domains_tmpmask;
+	struct sd_data *sdd = sd->private;
+	struct sched_domain *child;
+	int i;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct cpumask *sg_span;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				GFP_KERNEL, cpu_to_node(i));
+
+		if (!sg)
+			goto fail;
+
+		sg_span = sched_group_cpus(sg);
+
+		child = *per_cpu_ptr(sdd->sd, i);
+		if (child->child) {
+			child = child->child;
+			cpumask_copy(sg_span, sched_domain_span(child));
+		} else
+			cpumask_set_cpu(i, sg_span);
+
+		cpumask_or(covered, covered, sg_span);
+
+		sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
+		atomic_inc(&sg->sgp->ref);
+
+		if (cpumask_test_cpu(cpu, sg_span))
+			groups = sg;
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+		last->next = first;
+	}
+	sd->groups = groups;
+
+	return 0;
+
+fail:
+	free_sched_groups(first, 0);
+
+	return -ENOMEM;
+}
+
+static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
+{
+	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
+	struct sched_domain *child = sd->child;
+
+	if (child)
+		cpu = cpumask_first(sched_domain_span(child));
+
+	if (sg) {
+		*sg = *per_cpu_ptr(sdd->sg, cpu);
+		(*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu);
+		atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */
+	}
+
+	return cpu;
+}
+
+/*
+ * build_sched_groups will build a circular linked list of the groups
+ * covered by the given span, and will set each group's ->cpumask correctly,
+ * and ->cpu_power to 0.
+ *
+ * Assumes the sched_domain tree is fully constructed
+ */
+static int
+build_sched_groups(struct sched_domain *sd, int cpu)
+{
+	struct sched_group *first = NULL, *last = NULL;
+	struct sd_data *sdd = sd->private;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered;
+	int i;
+
+	get_group(cpu, sdd, &sd->groups);
+	atomic_inc(&sd->groups->ref);
+
+	if (cpu != cpumask_first(sched_domain_span(sd)))
+		return 0;
+
+	lockdep_assert_held(&sched_domains_mutex);
+	covered = sched_domains_tmpmask;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct sched_group *sg;
+		int group = get_group(i, sdd, &sg);
+		int j;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		cpumask_clear(sched_group_cpus(sg));
+		sg->sgp->power = 0;
+
+		for_each_cpu(j, span) {
+			if (get_group(j, sdd, NULL) != group)
+				continue;
+
+			cpumask_set_cpu(j, covered);
+			cpumask_set_cpu(j, sched_group_cpus(sg));
+		}
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+	}
+	last->next = first;
+
+	return 0;
+}
+
+/*
+ * Initializers for schedule domains
+ * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
+ */
+
+#ifdef CONFIG_SCHED_DEBUG
+# define SD_INIT_NAME(sd, type)		sd->name = #type
+#else
+# define SD_INIT_NAME(sd, type)		do { } while (0)
+#endif
+
+#define SD_INIT_FUNC(type)						\
+static noinline struct sched_domain *					\
+sd_init_##type(struct sched_domain_topology_level *tl, int cpu) 	\
+{									\
+	struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);	\
+	*sd = SD_##type##_INIT;						\
+	SD_INIT_NAME(sd, type);						\
+	sd->private = &tl->data;					\
+	return sd;							\
+}
+
+SD_INIT_FUNC(CPU)
+#ifdef CONFIG_NUMA
+ SD_INIT_FUNC(ALLNODES)
+ SD_INIT_FUNC(NODE)
+#endif
+#ifdef CONFIG_SCHED_SMT
+ SD_INIT_FUNC(SIBLING)
+#endif
+#ifdef CONFIG_SCHED_MC
+ SD_INIT_FUNC(MC)
+#endif
+#ifdef CONFIG_SCHED_BOOK
+ SD_INIT_FUNC(BOOK)
+#endif
+
+static int default_relax_domain_level = -1;
+int sched_domain_level_max;
+
+static int __init setup_relax_domain_level(char *str)
+{
+	unsigned long val;
+
+	val = simple_strtoul(str, NULL, 0);
+	if (val < sched_domain_level_max)
+		default_relax_domain_level = val;
+
+	return 1;
+}
+__setup("relax_domain_level=", setup_relax_domain_level);
+
+static void set_domain_attribute(struct sched_domain *sd,
+				 struct sched_domain_attr *attr)
+{
+	int request;
+
+	if (!attr || attr->relax_domain_level < 0) {
+		if (default_relax_domain_level < 0)
+			return;
+		else
+			request = default_relax_domain_level;
+	} else
+		request = attr->relax_domain_level;
+	if (request < sd->level) {
+		/* turn off idle balance on this domain */
+		sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
+	} else {
+		/* turn on idle balance on this domain */
+		sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE);
+	}
+}
+
+static void __sdt_free(const struct cpumask *cpu_map);
+static int __sdt_alloc(const struct cpumask *cpu_map);
+
+static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
+				 const struct cpumask *cpu_map)
+{
+	switch (what) {
+	case sa_rootdomain:
+		if (!atomic_read(&d->rd->refcount))
+			free_rootdomain(&d->rd->rcu); /* fall through */
+	case sa_sd:
+		free_percpu(d->sd); /* fall through */
+	case sa_sd_storage:
+		__sdt_free(cpu_map); /* fall through */
+	case sa_none:
+		break;
+	}
+}
+
+static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
+						   const struct cpumask *cpu_map)
+{
+	memset(d, 0, sizeof(*d));
+
+	if (__sdt_alloc(cpu_map))
+		return sa_sd_storage;
+	d->sd = alloc_percpu(struct sched_domain *);
+	if (!d->sd)
+		return sa_sd_storage;
+	d->rd = alloc_rootdomain();
+	if (!d->rd)
+		return sa_sd;
+	return sa_rootdomain;
+}
+
+/*
+ * NULL the sd_data elements we've used to build the sched_domain and
+ * sched_group structure so that the subsequent __free_domain_allocs()
+ * will not free the data we're using.
+ */
+static void claim_allocations(int cpu, struct sched_domain *sd)
+{
+	struct sd_data *sdd = sd->private;
+
+	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
+	*per_cpu_ptr(sdd->sd, cpu) = NULL;
+
+	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
+		*per_cpu_ptr(sdd->sg, cpu) = NULL;
+
+	if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref))
+		*per_cpu_ptr(sdd->sgp, cpu) = NULL;
+}
+
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *cpu_smt_mask(int cpu)
+{
+	return topology_thread_cpumask(cpu);
+}
+#endif
+
+/*
+ * Topology list, bottom-up.
+ */
+static struct sched_domain_topology_level default_topology[] = {
+#ifdef CONFIG_SCHED_SMT
+	{ sd_init_SIBLING, cpu_smt_mask, },
+#endif
+#ifdef CONFIG_SCHED_MC
+	{ sd_init_MC, cpu_coregroup_mask, },
+#endif
+#ifdef CONFIG_SCHED_BOOK
+	{ sd_init_BOOK, cpu_book_mask, },
+#endif
+	{ sd_init_CPU, cpu_cpu_mask, },
+#ifdef CONFIG_NUMA
+	{ sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, },
+	{ sd_init_ALLNODES, cpu_allnodes_mask, },
+#endif
+	{ NULL, },
+};
+
+static struct sched_domain_topology_level *sched_domain_topology = default_topology;
+
+static int __sdt_alloc(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for (tl = sched_domain_topology; tl->init; tl++) {
+		struct sd_data *sdd = &tl->data;
+
+		sdd->sd = alloc_percpu(struct sched_domain *);
+		if (!sdd->sd)
+			return -ENOMEM;
+
+		sdd->sg = alloc_percpu(struct sched_group *);
+		if (!sdd->sg)
+			return -ENOMEM;
+
+		sdd->sgp = alloc_percpu(struct sched_group_power *);
+		if (!sdd->sgp)
+			return -ENOMEM;
+
+		for_each_cpu(j, cpu_map) {
+			struct sched_domain *sd;
+			struct sched_group *sg;
+			struct sched_group_power *sgp;
+
+			   	sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sd)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sd, j) = sd;
+
+			sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sg)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sg, j) = sg;
+
+			sgp = kzalloc_node(sizeof(struct sched_group_power),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sgp)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sgp, j) = sgp;
+		}
+	}
+
+	return 0;
+}
+
+static void __sdt_free(const struct cpumask *cpu_map)
+{
+	struct sched_domain_topology_level *tl;
+	int j;
+
+	for (tl = sched_domain_topology; tl->init; tl++) {
+		struct sd_data *sdd = &tl->data;
+
+		for_each_cpu(j, cpu_map) {
+			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
+			if (sd && (sd->flags & SD_OVERLAP))
+				free_sched_groups(sd->groups, 0);
+			kfree(*per_cpu_ptr(sdd->sd, j));
+			kfree(*per_cpu_ptr(sdd->sg, j));
+			kfree(*per_cpu_ptr(sdd->sgp, j));
+		}
+		free_percpu(sdd->sd);
+		free_percpu(sdd->sg);
+		free_percpu(sdd->sgp);
+	}
+}
+
+struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl,
+		struct s_data *d, const struct cpumask *cpu_map,
+		struct sched_domain_attr *attr, struct sched_domain *child,
+		int cpu)
+{
+	struct sched_domain *sd = tl->init(tl, cpu);
+	if (!sd)
+		return child;
+
+	set_domain_attribute(sd, attr);
+	cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu));
+	if (child) {
+		sd->level = child->level + 1;
+		sched_domain_level_max = max(sched_domain_level_max, sd->level);
+		child->parent = sd;
+	}
+	sd->child = child;
+
+	return sd;
+}
+
+/*
+ * Build sched domains for a given set of cpus and attach the sched domains
+ * to the individual cpus
+ */
+static int build_sched_domains(const struct cpumask *cpu_map,
+				   struct sched_domain_attr *attr)
+{
+	enum s_alloc alloc_state = sa_none;
+	struct sched_domain *sd;
+	struct s_data d;
+	int i, ret = -ENOMEM;
+
+	alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
+	if (alloc_state != sa_rootdomain)
+		goto error;
+
+	/* Set up domains for cpus specified by the cpu_map. */
+	for_each_cpu(i, cpu_map) {
+		struct sched_domain_topology_level *tl;
+
+		sd = NULL;
+		for (tl = sched_domain_topology; tl->init; tl++) {
+			sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i);
+			if (tl->flags & SDTL_OVERLAP)
+				sd->flags |= SD_OVERLAP;
+			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
+				break;
+		}
+
+		while (sd->child)
+			sd = sd->child;
+
+		*per_cpu_ptr(d.sd, i) = sd;
+	}
+
+	/* Build the groups for the domains */
+	for_each_cpu(i, cpu_map) {
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			sd->span_weight = cpumask_weight(sched_domain_span(sd));
+			if (sd->flags & SD_OVERLAP) {
+				if (build_overlap_sched_groups(sd, i))
+					goto error;
+			} else {
+				if (build_sched_groups(sd, i))
+					goto error;
+			}
+		}
+	}
+
+	/* Calculate CPU power for physical packages and nodes */
+	for (i = nr_cpumask_bits-1; i >= 0; i--) {
+		if (!cpumask_test_cpu(i, cpu_map))
+			continue;
+
+		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
+			claim_allocations(i, sd);
+		}
+	}
+
+	/* Attach the domains */
+	rcu_read_lock();
+	for_each_cpu(i, cpu_map) {
+		sd = *per_cpu_ptr(d.sd, i);
+		cpu_attach_domain(sd, d.rd, i);
+	}
+	rcu_read_unlock();
+
+	ret = 0;
+error:
+	__free_domain_allocs(&d, alloc_state, cpu_map);
+	return ret;
+}
+
+static cpumask_var_t *doms_cur;	/* current sched domains */
+static int ndoms_cur;		/* number of sched domains in 'doms_cur' */
+static struct sched_domain_attr *dattr_cur;
+				/* attribues of custom domains in 'doms_cur' */
+
+/*
+ * Special case: If a kmalloc of a doms_cur partition (array of
+ * cpumask) fails, then fallback to a single sched domain,
+ * as determined by the single cpumask fallback_doms.
+ */
+static cpumask_var_t fallback_doms;
+
+/*
+ * arch_update_cpu_topology lets virtualized architectures update the
+ * cpu core maps. It is supposed to return 1 if the topology changed
+ * or 0 if it stayed the same.
+ */
+int __attribute__((weak)) arch_update_cpu_topology(void)
+{
+	return 0;
+}
+
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+	int i;
+	cpumask_var_t *doms;
+
+	doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+	if (!doms)
+		return NULL;
+	for (i = 0; i < ndoms; i++) {
+		if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+			free_sched_domains(doms, i);
+			return NULL;
+		}
+	}
+	return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+	unsigned int i;
+	for (i = 0; i < ndoms; i++)
+		free_cpumask_var(doms[i]);
+	kfree(doms);
+}
+
+/*
+ * Set up scheduler domains and groups. Callers must hold the hotplug lock.
+ * For now this just excludes isolated cpus, but could be used to
+ * exclude other special cases in the future.
+ */
+static int init_sched_domains(const struct cpumask *cpu_map)
+{
+	int err;
+
+	arch_update_cpu_topology();
+	ndoms_cur = 1;
+	doms_cur = alloc_sched_domains(ndoms_cur);
+	if (!doms_cur)
+		doms_cur = &fallback_doms;
+	cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
+	dattr_cur = NULL;
+	err = build_sched_domains(doms_cur[0], NULL);
+	register_sched_domain_sysctl();
+
+	return err;
+}
+
+/*
+ * Detach sched domains from a group of cpus specified in cpu_map
+ * These cpus will now be attached to the NULL domain
+ */
+static void detach_destroy_domains(const struct cpumask *cpu_map)
+{
+	int i;
+
+	rcu_read_lock();
+	for_each_cpu(i, cpu_map)
+		cpu_attach_domain(NULL, &def_root_domain, i);
+	rcu_read_unlock();
+}
+
+/* handle null as "default" */
+static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur,
+			struct sched_domain_attr *new, int idx_new)
+{
+	struct sched_domain_attr tmp;
+
+	/* fast path */
+	if (!new && !cur)
+		return 1;
+
+	tmp = SD_ATTR_INIT;
+	return !memcmp(cur ? (cur + idx_cur) : &tmp,
+			new ? (new + idx_new) : &tmp,
+			sizeof(struct sched_domain_attr));
+}
+
+/*
+ * Partition sched domains as specified by the 'ndoms_new'
+ * cpumasks in the array doms_new[] of cpumasks. This compares
+ * doms_new[] to the current sched domain partitioning, doms_cur[].
+ * It destroys each deleted domain and builds each new domain.
+ *
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
+ * The masks don't intersect (don't overlap.) We should setup one
+ * sched domain for each mask. CPUs not in any of the cpumasks will
+ * not be load balanced. If the same cpumask appears both in the
+ * current 'doms_cur' domains and in the new 'doms_new', we can leave
+ * it as it is.
+ *
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains.  This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
+ *
+ * If doms_new == NULL it will be replaced with cpu_online_mask.
+ * ndoms_new == 0 is a special case for destroying existing domains,
+ * and it will not create the default domain.
+ *
+ * Call with hotplug lock held
+ */
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+				 struct sched_domain_attr *dattr_new)
+{
+	int i, j, n;
+	int new_topology;
+
+	mutex_lock(&sched_domains_mutex);
+
+	/* always unregister in case we don't destroy any domains */
+	unregister_sched_domain_sysctl();
+
+	/* Let architecture update cpu core mappings. */
+	new_topology = arch_update_cpu_topology();
+
+	n = doms_new ? ndoms_new : 0;
+
+	/* Destroy deleted domains */
+	for (i = 0; i < ndoms_cur; i++) {
+		for (j = 0; j < n && !new_topology; j++) {
+			if (cpumask_equal(doms_cur[i], doms_new[j])
+				&& dattrs_equal(dattr_cur, i, dattr_new, j))
+				goto match1;
+		}
+		/* no match - a current sched domain not in new doms_new[] */
+		detach_destroy_domains(doms_cur[i]);
+match1:
+		;
+	}
+
+	if (doms_new == NULL) {
+		ndoms_cur = 0;
+		doms_new = &fallback_doms;
+		cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
+		WARN_ON_ONCE(dattr_new);
+	}
+
+	/* Build new domains */
+	for (i = 0; i < ndoms_new; i++) {
+		for (j = 0; j < ndoms_cur && !new_topology; j++) {
+			if (cpumask_equal(doms_new[i], doms_cur[j])
+				&& dattrs_equal(dattr_new, i, dattr_cur, j))
+				goto match2;
+		}
+		/* no match - add a new doms_new */
+		build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL);
+match2:
+		;
+	}
+
+	/* Remember the new sched domains */
+	if (doms_cur != &fallback_doms)
+		free_sched_domains(doms_cur, ndoms_cur);
+	kfree(dattr_cur);	/* kfree(NULL) is safe */
+	doms_cur = doms_new;
+	dattr_cur = dattr_new;
+	ndoms_cur = ndoms_new;
+
+	register_sched_domain_sysctl();
+
+	mutex_unlock(&sched_domains_mutex);
+}
+
+#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
+static void reinit_sched_domains(void)
+{
+	get_online_cpus();
+
+	/* Destroy domains first to force the rebuild */
+	partition_sched_domains(0, NULL, NULL);
+
+	rebuild_sched_domains();
+	put_online_cpus();
+}
+
+static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
+{
+	unsigned int level = 0;
+
+	if (sscanf(buf, "%u", &level) != 1)
+		return -EINVAL;
+
+	/*
+	 * level is always be positive so don't check for
+	 * level < POWERSAVINGS_BALANCE_NONE which is 0
+	 * What happens on 0 or 1 byte write,
+	 * need to check for count as well?
+	 */
+
+	if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
+		return -EINVAL;
+
+	if (smt)
+		sched_smt_power_savings = level;
+	else
+		sched_mc_power_savings = level;
+
+	reinit_sched_domains();
+
+	return count;
+}
+
+#ifdef CONFIG_SCHED_MC
+static ssize_t sched_mc_power_savings_show(struct device *dev,
+					   struct device_attribute *attr,
+					   char *buf)
+{
+	return sprintf(buf, "%u\n", sched_mc_power_savings);
+}
+static ssize_t sched_mc_power_savings_store(struct device *dev,
+						struct device_attribute *attr,
+						const char *buf, size_t count)
+{
+	return sched_power_savings_store(buf, count, 0);
+}
+static DEVICE_ATTR(sched_mc_power_savings, 0644,
+		   sched_mc_power_savings_show,
+		   sched_mc_power_savings_store);
+#endif
+
+#ifdef CONFIG_SCHED_SMT
+static ssize_t sched_smt_power_savings_show(struct device *dev,
+						struct device_attribute *attr,
+						char *buf)
+{
+	return sprintf(buf, "%u\n", sched_smt_power_savings);
+}
+static ssize_t sched_smt_power_savings_store(struct device *dev,
+						struct device_attribute *attr,
+						 const char *buf, size_t count)
+{
+	return sched_power_savings_store(buf, count, 1);
+}
+static DEVICE_ATTR(sched_smt_power_savings, 0644,
+		   sched_smt_power_savings_show,
+		   sched_smt_power_savings_store);
+#endif
+
+int __init sched_create_sysfs_power_savings_entries(struct device *dev)
+{
+	int err = 0;
+
+#ifdef CONFIG_SCHED_SMT
+	if (smt_capable())
+		err = device_create_file(dev, &dev_attr_sched_smt_power_savings);
+#endif
+#ifdef CONFIG_SCHED_MC
+	if (!err && mc_capable())
+		err = device_create_file(dev, &dev_attr_sched_mc_power_savings);
+#endif
+	return err;
+}
+#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
+
+/*
+ * Update cpusets according to cpu_active mask.  If cpusets are
+ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
+ * around partition_sched_domains().
+ */
+static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action,
+				 void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+	case CPU_STARTING:
+	case CPU_DOWN_FAILED:
+		cpuset_update_active_cpus();
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action,
+				   void *hcpu)
+{
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_DOWN_PREPARE:
+		cpuset_update_active_cpus();
+		return NOTIFY_OK;
+	default:
+		return NOTIFY_DONE;
+	}
+}
+
+#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC)
+/*
+ * Cheaper version of the below functions in case support for SMT and MC is
+ * compiled in but CPUs have no siblings.
+ */
+static bool sole_cpu_idle(int cpu)
+{
+	return rq_idle(cpu_rq(cpu));
+}
+#endif
+#ifdef CONFIG_SCHED_SMT
+/* All this CPU's SMT siblings are idle */
+static bool siblings_cpu_idle(int cpu)
+{
+	return cpumask_subset(&(cpu_rq(cpu)->smt_siblings),
+				  &grq.cpu_idle_map);
+}
+#endif
+#ifdef CONFIG_SCHED_MC
+/* All this CPU's shared cache siblings are idle */
+static bool cache_cpu_idle(int cpu)
+{
+	return cpumask_subset(&(cpu_rq(cpu)->cache_siblings),
+				  &grq.cpu_idle_map);
+}
+#endif
+
+enum sched_domain_level {
+	SD_LV_NONE = 0,
+	SD_LV_SIBLING,
+	SD_LV_MC,
+	SD_LV_BOOK,
+	SD_LV_CPU,
+	SD_LV_NODE,
+	SD_LV_ALLNODES,
+	SD_LV_MAX
+};
+
+void __init sched_init_smp(void)
+{
+	struct sched_domain *sd;
+	int cpu;
+
+	cpumask_var_t non_isolated_cpus;
+
+	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
+	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+
+	get_online_cpus();
+	mutex_lock(&sched_domains_mutex);
+	init_sched_domains(cpu_active_mask);
+	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
+	if (cpumask_empty(non_isolated_cpus))
+		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
+	mutex_unlock(&sched_domains_mutex);
+	put_online_cpus();
+
+	hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE);
+	hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE);
+
+	/* Move init over to a non-isolated CPU */
+	if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0)
+		BUG();
+	free_cpumask_var(non_isolated_cpus);
+
+	grq_lock_irq();
+	/*
+	 * Set up the relative cache distance of each online cpu from each
+	 * other in a simple array for quick lookup. Locality is determined
+	 * by the closest sched_domain that CPUs are separated by. CPUs with
+	 * shared cache in SMT and MC are treated as local. Separate CPUs
+	 * (within the same package or physically) within the same node are
+	 * treated as not local. CPUs not even in the same domain (different
+	 * nodes) are treated as very distant.
+	 */
+	for_each_online_cpu(cpu) {
+		struct rq *rq = cpu_rq(cpu);
+		for_each_domain(cpu, sd) {
+			int locality, other_cpu;
+
+#ifdef CONFIG_SCHED_SMT
+			if (sd->level == SD_LV_SIBLING) {
+				for_each_cpu_mask(other_cpu, *sched_domain_span(sd))
+					cpumask_set_cpu(other_cpu, &rq->smt_siblings);
+			}
+#endif
+#ifdef CONFIG_SCHED_MC
+			if (sd->level == SD_LV_MC) {
+				for_each_cpu_mask(other_cpu, *sched_domain_span(sd))
+					cpumask_set_cpu(other_cpu, &rq->cache_siblings);
+			}
+#endif
+			if (sd->level <= SD_LV_SIBLING)
+				locality = 1;
+			else if (sd->level <= SD_LV_MC)
+				locality = 2;
+			else if (sd->level <= SD_LV_NODE)
+				locality = 3;
+			else
+				continue;
+
+			for_each_cpu_mask(other_cpu, *sched_domain_span(sd)) {
+				if (locality < rq->cpu_locality[other_cpu])
+					rq->cpu_locality[other_cpu] = locality;
+			}
+		}
+
+/*
+		 * Each runqueue has its own function in case it doesn't have
+		 * siblings of its own allowing mixed topologies.
+		 */
+#ifdef CONFIG_SCHED_SMT
+		if (cpus_weight(rq->smt_siblings) > 1)
+			rq->siblings_idle = siblings_cpu_idle;
+#endif
+#ifdef CONFIG_SCHED_MC
+		if (cpus_weight(rq->cache_siblings) > 1)
+			rq->cache_idle = cache_cpu_idle;
+#endif
+	}
+	grq_unlock_irq();
+}
+#else
+void __init sched_init_smp(void)
+{
+}
+#endif /* CONFIG_SMP */
+
+unsigned int sysctl_timer_migration = 1;
+
+int in_sched_functions(unsigned long addr)
+{
+	return in_lock_functions(addr) ||
+		(addr >= (unsigned long)__sched_text_start
+		&& addr < (unsigned long)__sched_text_end);
+}
+
+void __init sched_init(void)
+{
+	int i;
+	struct rq *rq;
+
+	print_scheduler_version();
+
+	raw_spin_lock_init(&grq.lock);
+	grq.nr_running = grq.nr_uninterruptible = grq.nr_switches = 0;
+	grq.noc = 1;
+#ifdef CONFIG_SMP
+	init_defrootdomain();
+	grq.qnr = grq.idle_cpus = 0;
+	cpumask_clear(&grq.cpu_idle_map);
+
+#else
+	uprq = &per_cpu(runqueues, 0);
+#endif
+	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+		rq->user_pc = rq->nice_pc = rq->softirq_pc = rq->system_pc =
+				  rq->iowait_pc = rq->idle_pc = 0;
+		rq->rq_preempt = false;
+#ifdef CONFIG_SMP
+		rq->sticky_task = NULL;
+		rq->sd = NULL;
+		rq->rd = NULL;
+		rq->online = false;
+		rq->cpu = i;
+		rq_attach_root(rq, &def_root_domain);
+#endif
+		atomic_set(&rq->nr_iowait, 0);
+	}
+
+#ifdef CONFIG_SMP
+	nr_cpu_ids = i;
+	/*
+	 * Set the base locality for cpu cache distance calculation to
+	 * "distant" (3). Make sure the distance from a CPU to itself is 0.
+	 */
+	for_each_possible_cpu(i) {
+		int j;
+
+		rq = cpu_rq(i);
+#ifdef CONFIG_SCHED_SMT
+		cpumask_clear(&rq->smt_siblings);
+		cpumask_set_cpu(i, &rq->smt_siblings);
+		rq->siblings_idle = sole_cpu_idle;
+		cpumask_set_cpu(i, &rq->smt_siblings);
+#endif
+#ifdef CONFIG_SCHED_MC
+		cpumask_clear(&rq->cache_siblings);
+		cpumask_set_cpu(i, &rq->cache_siblings);
+		rq->cache_idle = sole_cpu_idle;
+		cpumask_set_cpu(i, &rq->cache_siblings);
+#endif
+		rq->cpu_locality = kmalloc(nr_cpu_ids * sizeof(int *), GFP_ATOMIC);
+		for_each_possible_cpu(j) {
+			if (i == j)
+				rq->cpu_locality[j] = 0;
+			else
+				rq->cpu_locality[j] = 4;
+		}
+	}
+#endif
+
+	for (i = 0; i < PRIO_LIMIT; i++)
+		INIT_LIST_HEAD(grq.queue + i);
+	/* delimiter for bitsearch */
+	__set_bit(PRIO_LIMIT, grq.prio_bitmap);
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+	INIT_HLIST_HEAD(&init_task.preempt_notifiers);
+#endif
+
+#ifdef CONFIG_RT_MUTEXES
+	plist_head_init(&init_task.pi_waiters);
+#endif
+
+	/*
+	 * The boot idle thread does lazy MMU switching as well:
+	 */
+	atomic_inc(&init_mm.mm_count);
+	enter_lazy_tlb(&init_mm, current);
+
+	/*
+	 * Make us the idle thread. Technically, schedule() should not be
+	 * called from this thread, however somewhere below it might be,
+	 * but because we are the idle thread, we just pick up running again
+	 * when this runqueue becomes "idle".
+	 */
+	init_idle(current, smp_processor_id());
+
+#ifdef CONFIG_SMP
+	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
+	/* May be allocated at isolcpus cmdline parse time */
+	if (cpu_isolated_map == NULL)
+		zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+#endif /* SMP */
+}
+
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+static inline int preempt_count_equals(int preempt_offset)
+{
+	int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
+
+	return (nested == preempt_offset);
+}
+
+void __might_sleep(const char *file, int line, int preempt_offset)
+{
+	static unsigned long prev_jiffy;	/* ratelimiting */
+
+	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
+	if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+		system_state != SYSTEM_RUNNING || oops_in_progress)
+		return;
+	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+		return;
+	prev_jiffy = jiffies;
+
+	printk(KERN_ERR
+		"BUG: sleeping function called from invalid context at %s:%d\n",
+			file, line);
+	printk(KERN_ERR
+		"in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
+			in_atomic(), irqs_disabled(),
+			current->pid, current->comm);
+
+	debug_show_held_locks(current);
+	if (irqs_disabled())
+		print_irqtrace_events(current);
+	dump_stack();
+}
+EXPORT_SYMBOL(__might_sleep);
+#endif
+
+#ifdef CONFIG_MAGIC_SYSRQ
+void normalize_rt_tasks(void)
+{
+	struct task_struct *g, *p;
+	unsigned long flags;
+	struct rq *rq;
+	int queued;
+
+	read_lock_irq(&tasklist_lock);
+
+	do_each_thread(g, p) {
+		if (!rt_task(p))
+			continue;
+
+		raw_spin_lock_irqsave(&p->pi_lock, flags);
+		rq = __task_grq_lock(p);
+
+		queued = task_queued(p);
+		__setscheduler(p, rq, SCHED_NORMAL, 0);
+		if (queued) {
+			try_preempt(p, rq);
+		}
+
+		__task_grq_unlock();
+		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+	} while_each_thread(g, p);
+
+	read_unlock_irq(&tasklist_lock);
+}
+#endif /* CONFIG_MAGIC_SYSRQ */
+
+#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB)
+/*
+ * These functions are only useful for the IA64 MCA handling, or kdb.
+ *
+ * They can only be called when the whole system has been
+ * stopped - every CPU needs to be quiescent, and no scheduling
+ * activity can take place. Using them for anything else would
+ * be a serious bug, and as a result, they aren't even visible
+ * under any other configuration.
+ */
+
+/**
+ * curr_task - return the current task for a given cpu.
+ * @cpu: the processor in question.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+struct task_struct *curr_task(int cpu)
+{
+	return cpu_curr(cpu);
+}
+
+#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */
+
+#ifdef CONFIG_IA64
+/**
+ * set_curr_task - set the current task for a given cpu.
+ * @cpu: the processor in question.
+ * @p: the task pointer to set.
+ *
+ * Description: This function must only be used when non-maskable interrupts
+ * are serviced on a separate stack.  It allows the architecture to switch the
+ * notion of the current task on a cpu in a non-blocking manner.  This function
+ * must be called with all CPU's synchronised, and interrupts disabled, the
+ * and caller must save the original value of the current task (see
+ * curr_task() above) and restore that value before reenabling interrupts and
+ * re-starting the system.
+ *
+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
+ */
+void set_curr_task(int cpu, struct task_struct *p)
+{
+	cpu_curr(cpu) = p;
+}
+
+#endif
+
+/*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	*ut = p->utime;
+	*st = p->stime;
+}
+
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct task_cputime cputime;
+
+	thread_group_cputime(p, &cputime);
+
+	*ut = cputime.utime;
+	*st = cputime.stime;
+}
+#else
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	cputime_t rtime, utime = p->utime, total = utime + p->stime;
+
+	rtime = nsecs_to_cputime(p->sched_time);
+
+	if (total) {
+		u64 temp;
+
+		temp = (u64)(rtime * utime);
+		do_div(temp, total);
+		utime = (cputime_t)temp;
+	} else
+		utime = rtime;
+
+	/*
+	 * Compare with previous values, to keep monotonicity:
+	 */
+	p->prev_utime = max(p->prev_utime, utime);
+	p->prev_stime = max(p->prev_stime, (rtime - p->prev_utime));
+
+	*ut = p->prev_utime;
+	*st = p->prev_stime;
+}
+
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+	struct signal_struct *sig = p->signal;
+	struct task_cputime cputime;
+	cputime_t rtime, utime, total;
+
+	thread_group_cputime(p, &cputime);
+
+	total = cputime.utime + cputime.stime;
+	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
+
+	if (total) {
+		u64 temp;
+
+		temp = (u64)(rtime * cputime.utime);
+		do_div(temp, total);
+		utime = (cputime_t)temp;
+	} else
+		utime = rtime;
+
+	sig->prev_utime = max(sig->prev_utime, utime);
+	sig->prev_stime = max(sig->prev_stime, (rtime - sig->prev_utime));
+
+	*ut = sig->prev_utime;
+	*st = sig->prev_stime;
+}
+#endif
+
+inline cputime_t task_gtime(struct task_struct *p)
+{
+	return p->gtime;
+}
+
+void __cpuinit init_idle_bootup_task(struct task_struct *idle)
+{}
+
+#ifdef CONFIG_SCHED_DEBUG
+void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
+{}
+
+void proc_sched_set_task(struct task_struct *p)
+{}
+#endif
+
+#ifdef CONFIG_SMP
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return SCHED_LOAD_SCALE;
+}
+
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu)
+{
+	unsigned long weight = cpumask_weight(sched_domain_span(sd));
+	unsigned long smt_gain = sd->smt_gain;
+
+	smt_gain /= weight;
+
+	return smt_gain;
+}
+#endif
+
+static int zero = 0;
+static int ten_thousand = 10000;
+static int all = 0x7FFFFFFF;
+
+struct ctl_table rifs_table[] = {
+	{
+		.procname	= "rr_interval",
+		.data		= &rr_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0666,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &ten_thousand,
+	},
+	{
+		.procname	= "sched_method",
+		.data		= &sched_method,
+		.maxlen		= sizeof(int),
+		.mode		= 0666,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &all,
+	},
+	{
+		.procname	= "sched_round",
+		.data		= &sched_round,
+		.maxlen		= sizeof(int),
+		.mode		= 0666,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &all,
+	},
+	{
+		.procname	= "ts_percent",
+		.data		= &ts_percent,
+		.maxlen		= sizeof(int),
+		.mode		= 0666,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &ten_thousand,
+	},
+	{ }
+};
+EXPORT_SYMBOL(rifs_table);
diff -ruN linux-3.4.1/kernel/sched/stats.c linux-3.4.1-RIFS/kernel/sched/stats.c
--- linux-3.4.1/kernel/sched/stats.c	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/sched/stats.c	1970-01-01 08:00:00.000000000 +0800
@@ -1,111 +0,0 @@
-
-#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 0 %u %u %u %u %llu %llu %lu",
-		    cpu, rq->yld_count,
-		    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);
diff -ruN linux-3.4.1/kernel/sched/stats.h linux-3.4.1-RIFS/kernel/sched/stats.h
--- linux-3.4.1/kernel/sched/stats.h	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/sched/stats.h	2012-06-06 14:43:02.000000000 +0800
@@ -1,231 +0,0 @@
-
-#ifdef CONFIG_SCHEDSTATS
-
-/*
- * Expects runqueue lock to be held for atomicity of update
- */
-static inline void
-rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
-{
-	if (rq) {
-		rq->rq_sched_info.run_delay += delta;
-		rq->rq_sched_info.pcount++;
-	}
-}
-
-/*
- * Expects runqueue lock to be held for atomicity of update
- */
-static inline void
-rq_sched_info_depart(struct rq *rq, unsigned long long delta)
-{
-	if (rq)
-		rq->rq_cpu_time += delta;
-}
-
-static inline void
-rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
-{
-	if (rq)
-		rq->rq_sched_info.run_delay += delta;
-}
-# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
-# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
-# define schedstat_set(var, val)	do { var = (val); } while (0)
-#else /* !CONFIG_SCHEDSTATS */
-static inline void
-rq_sched_info_arrive(struct rq *rq, unsigned long long delta)
-{}
-static inline void
-rq_sched_info_dequeued(struct rq *rq, unsigned long long delta)
-{}
-static inline void
-rq_sched_info_depart(struct rq *rq, unsigned long long delta)
-{}
-# define schedstat_inc(rq, field)	do { } while (0)
-# define schedstat_add(rq, field, amt)	do { } while (0)
-# define schedstat_set(var, val)	do { } while (0)
-#endif
-
-#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
-static inline void sched_info_reset_dequeued(struct task_struct *t)
-{
-	t->sched_info.last_queued = 0;
-}
-
-/*
- * We are interested in knowing how long it was from the *first* time a
- * task was queued to the time that it finally hit a cpu, we call this routine
- * from dequeue_task() to account for possible rq->clock skew across cpus. The
- * delta taken on each cpu would annul the skew.
- */
-static inline void sched_info_dequeued(struct task_struct *t)
-{
-	unsigned long long now = task_rq(t)->clock, delta = 0;
-
-	if (unlikely(sched_info_on()))
-		if (t->sched_info.last_queued)
-			delta = now - t->sched_info.last_queued;
-	sched_info_reset_dequeued(t);
-	t->sched_info.run_delay += delta;
-
-	rq_sched_info_dequeued(task_rq(t), delta);
-}
-
-/*
- * Called when a task finally hits the cpu.  We can now calculate how
- * long it was waiting to run.  We also note when it began so that we
- * can keep stats on how long its timeslice is.
- */
-static void sched_info_arrive(struct task_struct *t)
-{
-	unsigned long long now = task_rq(t)->clock, delta = 0;
-
-	if (t->sched_info.last_queued)
-		delta = now - t->sched_info.last_queued;
-	sched_info_reset_dequeued(t);
-	t->sched_info.run_delay += delta;
-	t->sched_info.last_arrival = now;
-	t->sched_info.pcount++;
-
-	rq_sched_info_arrive(task_rq(t), delta);
-}
-
-/*
- * This function is only called from enqueue_task(), but also only updates
- * the timestamp if it is already not set.  It's assumed that
- * sched_info_dequeued() will clear that stamp when appropriate.
- */
-static inline void sched_info_queued(struct task_struct *t)
-{
-	if (unlikely(sched_info_on()))
-		if (!t->sched_info.last_queued)
-			t->sched_info.last_queued = task_rq(t)->clock;
-}
-
-/*
- * Called when a process ceases being the active-running process, either
- * voluntarily or involuntarily.  Now we can calculate how long we ran.
- * Also, if the process is still in the TASK_RUNNING state, call
- * sched_info_queued() to mark that it has now again started waiting on
- * the runqueue.
- */
-static inline void sched_info_depart(struct task_struct *t)
-{
-	unsigned long long delta = task_rq(t)->clock -
-					t->sched_info.last_arrival;
-
-	rq_sched_info_depart(task_rq(t), delta);
-
-	if (t->state == TASK_RUNNING)
-		sched_info_queued(t);
-}
-
-/*
- * Called when tasks are switched involuntarily due, typically, to expiring
- * their time slice.  (This may also be called when switching to or from
- * the idle task.)  We are only called when prev != next.
- */
-static inline void
-__sched_info_switch(struct task_struct *prev, struct task_struct *next)
-{
-	struct rq *rq = task_rq(prev);
-
-	/*
-	 * prev now departs the cpu.  It's not interesting to record
-	 * stats about how efficient we were at scheduling the idle
-	 * process, however.
-	 */
-	if (prev != rq->idle)
-		sched_info_depart(prev);
-
-	if (next != rq->idle)
-		sched_info_arrive(next);
-}
-static inline void
-sched_info_switch(struct task_struct *prev, struct task_struct *next)
-{
-	if (unlikely(sched_info_on()))
-		__sched_info_switch(prev, next);
-}
-#else
-#define sched_info_queued(t)			do { } while (0)
-#define sched_info_reset_dequeued(t)	do { } while (0)
-#define sched_info_dequeued(t)			do { } while (0)
-#define sched_info_switch(t, next)		do { } while (0)
-#endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
-
-/*
- * The following are functions that support scheduler-internal time accounting.
- * These functions are generally called at the timer tick.  None of this depends
- * on CONFIG_SCHEDSTATS.
- */
-
-/**
- * account_group_user_time - Maintain utime for a thread group.
- *
- * @tsk:	Pointer to task structure.
- * @cputime:	Time value by which to increment the utime field of the
- *		thread_group_cputime structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the utime field there.
- */
-static inline void account_group_user_time(struct task_struct *tsk,
-					   cputime_t cputime)
-{
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
-
-	if (!cputimer->running)
-		return;
-
-	raw_spin_lock(&cputimer->lock);
-	cputimer->cputime.utime += cputime;
-	raw_spin_unlock(&cputimer->lock);
-}
-
-/**
- * account_group_system_time - Maintain stime for a thread group.
- *
- * @tsk:	Pointer to task structure.
- * @cputime:	Time value by which to increment the stime field of the
- *		thread_group_cputime structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the stime field there.
- */
-static inline void account_group_system_time(struct task_struct *tsk,
-					     cputime_t cputime)
-{
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
-
-	if (!cputimer->running)
-		return;
-
-	raw_spin_lock(&cputimer->lock);
-	cputimer->cputime.stime += cputime;
-	raw_spin_unlock(&cputimer->lock);
-}
-
-/**
- * account_group_exec_runtime - Maintain exec runtime for a thread group.
- *
- * @tsk:	Pointer to task structure.
- * @ns:		Time value by which to increment the sum_exec_runtime field
- *		of the thread_group_cputime structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the sum_exec_runtime field there.
- */
-static inline void account_group_exec_runtime(struct task_struct *tsk,
-					      unsigned long long ns)
-{
-	struct thread_group_cputimer *cputimer = &tsk->signal->cputimer;
-
-	if (!cputimer->running)
-		return;
-
-	raw_spin_lock(&cputimer->lock);
-	cputimer->cputime.sum_exec_runtime += ns;
-	raw_spin_unlock(&cputimer->lock);
-}
diff -ruN linux-3.4.1/kernel/sysctl.c linux-3.4.1-RIFS/kernel/sysctl.c
--- linux-3.4.1/kernel/sysctl.c	2012-06-01 15:18:44.000000000 +0800
+++ linux-3.4.1-RIFS/kernel/sysctl.c	2012-06-24 00:46:40.000000000 +0800
@@ -89,6 +89,9 @@
 #include <linux/nmi.h>
 #endif
 
+#if defined(CONFIG_SCHED_RIFS)
+extern struct ctl_table rifs_table[];
+#endif
 
 #if defined(CONFIG_SYSCTL)
 
@@ -242,6 +245,7 @@
 };
 
 #ifdef CONFIG_SCHED_DEBUG
+#ifndef CONFIG_SCHED_RIFS
 static int min_sched_granularity_ns = 100000;		/* 100 usecs */
 static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 static int min_wakeup_granularity_ns;			/* 0 usecs */
@@ -249,6 +253,7 @@
 static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
 static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
 #endif
+#endif
 
 #ifdef CONFIG_COMPACTION
 static int min_extfrag_threshold;
@@ -256,14 +261,8 @@
 #endif
 
 static struct ctl_table kern_table[] = {
-	{
-		.procname	= "sched_child_runs_first",
-		.data		= &sysctl_sched_child_runs_first,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 #ifdef CONFIG_SCHED_DEBUG
+#ifndef CONFIG_SCHED_RIFS
 	{
 		.procname	= "sched_min_granularity_ns",
 		.data		= &sysctl_sched_min_granularity,
@@ -337,21 +336,14 @@
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-#endif
-	{
-		.procname	= "sched_rt_period_us",
-		.data		= &sysctl_sched_rt_period,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= sched_rt_handler,
-	},
+#else
 	{
-		.procname	= "sched_rt_runtime_us",
-		.data		= &sysctl_sched_rt_runtime,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= sched_rt_handler,
+		.procname	= "sched_rifs",
+		.mode		= 0555,
+		.child		= rifs_table,
 	},
+#endif
+#endif
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",


Copyright © 2012, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds