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

Pull scheduler changes from Ingo Molnar:
 "Main changes:

   - scheduler side full-dynticks (user-space execution is undisturbed
     and receives no timer IRQs) preparation changes that convert the
     cputime accounting code to be full-dynticks ready, from Frederic
     Weisbecker.

   - Initial sched.h split-up changes, by Clark Williams

   - select_idle_sibling() performance improvement by Mike Galbraith:

        " 1 tbench pair (worst case) in a 10 core + SMT package:

          pre   15.22 MB/sec 1 procs
          post 252.01 MB/sec 1 procs "

  - sched_rr_get_interval() ABI fix/change.  We think this detail is not
    used by apps (so it's not an ABI in practice), but lets keep it
    under observation.

  - misc RT scheduling cleanups, optimizations"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  sched/rt: Add <linux/sched/rt.h> header to <linux/init_task.h>
  cputime: Remove irqsave from seqlock readers
  sched, powerpc: Fix sched.h split-up build failure
  cputime: Restore CPU_ACCOUNTING config defaults for PPC64
  sched/rt: Move rt specific bits into new header file
  sched/rt: Add a tuning knob to allow changing SCHED_RR timeslice
  sched: Move sched.h sysctl bits into separate header
  sched: Fix signedness bug in yield_to()
  sched: Fix select_idle_sibling() bouncing cow syndrome
  sched/rt: Further simplify pick_rt_task()
  sched/rt: Do not account zero delta_exec in update_curr_rt()
  cputime: Safely read cputime of full dynticks CPUs
  kvm: Prepare to add generic guest entry/exit callbacks
  cputime: Use accessors to read task cputime stats
  cputime: Allow dynamic switch between tick/virtual based cputime accounting
  cputime: Generic on-demand virtual cputime accounting
  cputime: Move default nsecs_to_cputime() to jiffies based cputime file
  cputime: Librarize per nsecs resolution cputime definitions
  cputime: Avoid multiplication overflow on utime scaling
  context_tracking: Export context state for generic vtime
  ...

Fix up conflict in kernel/context_tracking.c due to comment additions.

13 files changed, 524 insertions, 234 deletions

diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h
index 9a62937c56ca..51969436b8b8 100644
--- a/include/asm-generic/cputime.h
+++ b/include/asm-generic/cputime.h
@@ -4,66 +4,12 @@
 #include <linux/time.h>
 #include <linux/jiffies.h>
 
-typedef unsigned long __nocast cputime_t;
-
-#define cputime_one_jiffy		jiffies_to_cputime(1)
-#define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
-#define cputime_to_scaled(__ct)		(__ct)
-#define jiffies_to_cputime(__hz)	(__force cputime_t)(__hz)
-
-typedef u64 __nocast cputime64_t;
-
-#define cputime64_to_jiffies64(__ct)	(__force u64)(__ct)
-#define jiffies64_to_cputime64(__jif)	(__force cputime64_t)(__jif)
-
-#define nsecs_to_cputime64(__ct)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64(__ct))
-
-
-/*
- * Convert cputime to microseconds and back.
- */
-#define cputime_to_usecs(__ct)		\
-	jiffies_to_usecs(cputime_to_jiffies(__ct))
-#define usecs_to_cputime(__usec)	\
-	jiffies_to_cputime(usecs_to_jiffies(__usec))
-#define usecs_to_cputime64(__usec)	\
-	jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
-
-/*
- * Convert cputime to seconds and back.
- */
-#define cputime_to_secs(jif)		(cputime_to_jiffies(jif) / HZ)
-#define secs_to_cputime(sec)		jiffies_to_cputime((sec) * HZ)
-
-/*
- * Convert cputime to timespec and back.
- */
-#define timespec_to_cputime(__val)	\
-	jiffies_to_cputime(timespec_to_jiffies(__val))
-#define cputime_to_timespec(__ct,__val)	\
-	jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to timeval and back.
- */
-#define timeval_to_cputime(__val)	\
-	jiffies_to_cputime(timeval_to_jiffies(__val))
-#define cputime_to_timeval(__ct,__val)	\
-	jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
-
-/*
- * Convert cputime to clock and back.
- */
-#define cputime_to_clock_t(__ct)	\
-	jiffies_to_clock_t(cputime_to_jiffies(__ct))
-#define clock_t_to_cputime(__x)		\
-	jiffies_to_cputime(clock_t_to_jiffies(__x))
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+# include <asm-generic/cputime_jiffies.h>
+#endif
 
-/*
- * Convert cputime64 to clock.
- */
-#define cputime64_to_clock_t(__ct)	\
-	jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+# include <asm-generic/cputime_nsecs.h>
+#endif
 
 #endif
diff --git a/include/asm-generic/cputime_jiffies.h b/include/asm-generic/cputime_jiffies.h
new file mode 100644
index 000000000000..272ecba9f588
--- /dev/null
+++ b/include/asm-generic/cputime_jiffies.h
@@ -0,0 +1,72 @@
+#ifndef _ASM_GENERIC_CPUTIME_JIFFIES_H
+#define _ASM_GENERIC_CPUTIME_JIFFIES_H
+
+typedef unsigned long __nocast cputime_t;
+
+#define cputime_one_jiffy		jiffies_to_cputime(1)
+#define cputime_to_jiffies(__ct)	(__force unsigned long)(__ct)
+#define cputime_to_scaled(__ct)		(__ct)
+#define jiffies_to_cputime(__hz)	(__force cputime_t)(__hz)
+
+typedef u64 __nocast cputime64_t;
+
+#define cputime64_to_jiffies64(__ct)	(__force u64)(__ct)
+#define jiffies64_to_cputime64(__jif)	(__force cputime64_t)(__jif)
+
+
+/*
+ * Convert nanoseconds to cputime
+ */
+#define nsecs_to_cputime64(__nsec)	\
+	jiffies64_to_cputime64(nsecs_to_jiffies64(__nsec))
+#define nsecs_to_cputime(__nsec)	\
+	jiffies_to_cputime(nsecs_to_jiffies(__nsec))
+
+
+/*
+ * Convert cputime to microseconds and back.
+ */
+#define cputime_to_usecs(__ct)		\
+	jiffies_to_usecs(cputime_to_jiffies(__ct))
+#define usecs_to_cputime(__usec)	\
+	jiffies_to_cputime(usecs_to_jiffies(__usec))
+#define usecs_to_cputime64(__usec)	\
+	jiffies64_to_cputime64(nsecs_to_jiffies64((__usec) * 1000))
+
+/*
+ * Convert cputime to seconds and back.
+ */
+#define cputime_to_secs(jif)		(cputime_to_jiffies(jif) / HZ)
+#define secs_to_cputime(sec)		jiffies_to_cputime((sec) * HZ)
+
+/*
+ * Convert cputime to timespec and back.
+ */
+#define timespec_to_cputime(__val)	\
+	jiffies_to_cputime(timespec_to_jiffies(__val))
+#define cputime_to_timespec(__ct,__val)	\
+	jiffies_to_timespec(cputime_to_jiffies(__ct),__val)
+
+/*
+ * Convert cputime to timeval and back.
+ */
+#define timeval_to_cputime(__val)	\
+	jiffies_to_cputime(timeval_to_jiffies(__val))
+#define cputime_to_timeval(__ct,__val)	\
+	jiffies_to_timeval(cputime_to_jiffies(__ct),__val)
+
+/*
+ * Convert cputime to clock and back.
+ */
+#define cputime_to_clock_t(__ct)	\
+	jiffies_to_clock_t(cputime_to_jiffies(__ct))
+#define clock_t_to_cputime(__x)		\
+	jiffies_to_cputime(clock_t_to_jiffies(__x))
+
+/*
+ * Convert cputime64 to clock.
+ */
+#define cputime64_to_clock_t(__ct)	\
+	jiffies_64_to_clock_t(cputime64_to_jiffies64(__ct))
+
+#endif
diff --git a/include/asm-generic/cputime_nsecs.h b/include/asm-generic/cputime_nsecs.h
new file mode 100644
index 000000000000..b6485cafb7bd
--- /dev/null
+++ b/include/asm-generic/cputime_nsecs.h
@@ -0,0 +1,104 @@
+/*
+ * Definitions for measuring cputime in nsecs resolution.
+ *
+ * Based on <arch/ia64/include/asm/cputime.h>
+ *
+ * Copyright (C) 2007 FUJITSU LIMITED
+ * Copyright (C) 2007 Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#ifndef _ASM_GENERIC_CPUTIME_NSECS_H
+#define _ASM_GENERIC_CPUTIME_NSECS_H
+
+typedef u64 __nocast cputime_t;
+typedef u64 __nocast cputime64_t;
+
+#define cputime_one_jiffy		jiffies_to_cputime(1)
+
+/*
+ * Convert cputime <-> jiffies (HZ)
+ */
+#define cputime_to_jiffies(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
+#define cputime_to_scaled(__ct)		(__ct)
+#define jiffies_to_cputime(__jif)	\
+	(__force cputime_t)((__jif) * (NSEC_PER_SEC / HZ))
+#define cputime64_to_jiffies64(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / HZ))
+#define jiffies64_to_cputime64(__jif)	\
+	(__force cputime64_t)((__jif) * (NSEC_PER_SEC / HZ))
+
+
+/*
+ * Convert cputime <-> nanoseconds
+ */
+#define nsecs_to_cputime(__nsecs)	((__force u64)(__nsecs))
+
+
+/*
+ * Convert cputime <-> microseconds
+ */
+#define cputime_to_usecs(__ct)		\
+	((__force u64)(__ct) / NSEC_PER_USEC)
+#define usecs_to_cputime(__usecs)	\
+	(__force cputime_t)((__usecs) * NSEC_PER_USEC)
+#define usecs_to_cputime64(__usecs)	\
+	(__force cputime64_t)((__usecs) * NSEC_PER_USEC)
+
+/*
+ * Convert cputime <-> seconds
+ */
+#define cputime_to_secs(__ct)		\
+	((__force u64)(__ct) / NSEC_PER_SEC)
+#define secs_to_cputime(__secs)		\
+	(__force cputime_t)((__secs) * NSEC_PER_SEC)
+
+/*
+ * Convert cputime <-> timespec (nsec)
+ */
+static inline cputime_t timespec_to_cputime(const struct timespec *val)
+{
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_nsec;
+	return (__force cputime_t) ret;
+}
+static inline void cputime_to_timespec(const cputime_t ct, struct timespec *val)
+{
+	val->tv_sec  = (__force u64) ct / NSEC_PER_SEC;
+	val->tv_nsec = (__force u64) ct % NSEC_PER_SEC;
+}
+
+/*
+ * Convert cputime <-> timeval (msec)
+ */
+static inline cputime_t timeval_to_cputime(struct timeval *val)
+{
+	u64 ret = val->tv_sec * NSEC_PER_SEC + val->tv_usec * NSEC_PER_USEC;
+	return (__force cputime_t) ret;
+}
+static inline void cputime_to_timeval(const cputime_t ct, struct timeval *val)
+{
+	val->tv_sec = (__force u64) ct / NSEC_PER_SEC;
+	val->tv_usec = ((__force u64) ct % NSEC_PER_SEC) / NSEC_PER_USEC;
+}
+
+/*
+ * Convert cputime <-> clock (USER_HZ)
+ */
+#define cputime_to_clock_t(__ct)	\
+	((__force u64)(__ct) / (NSEC_PER_SEC / USER_HZ))
+#define clock_t_to_cputime(__x)		\
+	(__force cputime_t)((__x) * (NSEC_PER_SEC / USER_HZ))
+
+/*
+ * Convert cputime64 to clock.
+ */
+#define cputime64_to_clock_t(__ct)	\
+	cputime_to_clock_t((__force cputime_t)__ct)
+
+#endif
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index e24339ccb7f0..b28d161c1091 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -3,12 +3,40 @@
 
 #ifdef CONFIG_CONTEXT_TRACKING
 #include <linux/sched.h>
+#include <linux/percpu.h>
+
+struct context_tracking {
+	/*
+	 * When active is false, probes are unset in order
+	 * to minimize overhead: TIF flags are cleared
+	 * and calls to user_enter/exit are ignored. This
+	 * may be further optimized using static keys.
+	 */
+	bool active;
+	enum {
+		IN_KERNEL = 0,
+		IN_USER,
+	} state;
+};
+
+DECLARE_PER_CPU(struct context_tracking, context_tracking);
+
+static inline bool context_tracking_in_user(void)
+{
+	return __this_cpu_read(context_tracking.state) == IN_USER;
+}
+
+static inline bool context_tracking_active(void)
+{
+	return __this_cpu_read(context_tracking.active);
+}
 
 extern void user_enter(void);
 extern void user_exit(void);
 extern void context_tracking_task_switch(struct task_struct *prev,
 					 struct task_struct *next);
 #else
+static inline bool context_tracking_in_user(void) { return false; }
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 57bfdce8fb90..29eb805ea4a6 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -153,7 +153,7 @@ extern void rcu_nmi_exit(void);
  */
 #define __irq_enter()					\
 	do {						\
-		vtime_account_irq_enter(current);	\
+		account_irq_enter_time(current);	\
 		add_preempt_count(HARDIRQ_OFFSET);	\
 		trace_hardirq_enter();			\
 	} while (0)
@@ -169,7 +169,7 @@ extern void irq_enter(void);
 #define __irq_exit()					\
 	do {						\
 		trace_hardirq_exit();			\
-		vtime_account_irq_exit(current);	\
+		account_irq_exit_time(current);		\
 		sub_preempt_count(HARDIRQ_OFFSET);	\
 	} while (0)
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 6d087c5f57f7..5cd0f0949927 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -10,7 +10,9 @@
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/securebits.h>
+#include <linux/seqlock.h>
 #include <net/net_namespace.h>
+#include <linux/sched/rt.h>
 
 #ifdef CONFIG_SMP
 # define INIT_PUSHABLE_TASKS(tsk)					\
@@ -141,6 +143,15 @@ extern struct task_group root_task_group;
 # define INIT_PERF_EVENTS(tsk)
 #endif
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+# define INIT_VTIME(tsk)						\
+	.vtime_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock),	\
+	.vtime_snap = 0,				\
+	.vtime_snap_whence = VTIME_SYS,
+#else
+# define INIT_VTIME(tsk)
+#endif
+
 #define INIT_TASK_COMM "swapper"
 
 /*
@@ -210,6 +221,7 @@ extern struct task_group root_task_group;
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
 	INIT_CPUSET_SEQ							\
+	INIT_VTIME(tsk)							\
 }
 
 
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 66b70780e910..ed5f6ed6eb77 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -127,7 +127,7 @@ extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t)
 extern void account_steal_time(cputime_t);
 extern void account_idle_time(cputime_t);
 
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static inline void account_process_tick(struct task_struct *tsk, int user)
 {
 	vtime_account_user(tsk);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2c497ab0d03d..b7996a768eb2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -22,6 +22,7 @@
 #include <linux/rcupdate.h>
 #include <linux/ratelimit.h>
 #include <linux/err.h>
+#include <linux/irqflags.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -740,15 +741,52 @@ static inline int kvm_deassign_device(struct kvm *kvm,
 }
 #endif /* CONFIG_IOMMU_API */
 
-static inline void kvm_guest_enter(void)
+static inline void __guest_enter(void)
 {
-	BUG_ON(preemptible());
 	/*
 	 * This is running in ioctl context so we can avoid
 	 * the call to vtime_account() with its unnecessary idle check.
 	 */
-	vtime_account_system_irqsafe(current);
+	vtime_account_system(current);
 	current->flags |= PF_VCPU;
+}
+
+static inline void __guest_exit(void)
+{
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
+	current->flags &= ~PF_VCPU;
+}
+
+#ifdef CONFIG_CONTEXT_TRACKING
+extern void guest_enter(void);
+extern void guest_exit(void);
+
+#else /* !CONFIG_CONTEXT_TRACKING */
+static inline void guest_enter(void)
+{
+	__guest_enter();
+}
+
+static inline void guest_exit(void)
+{
+	__guest_exit();
+}
+#endif /* !CONFIG_CONTEXT_TRACKING */
+
+static inline void kvm_guest_enter(void)
+{
+	unsigned long flags;
+
+	BUG_ON(preemptible());
+
+	local_irq_save(flags);
+	guest_enter();
+	local_irq_restore(flags);
+
 	/* KVM does not hold any references to rcu protected data when it
 	 * switches CPU into a guest mode. In fact switching to a guest mode
 	 * is very similar to exiting to userspase from rcu point of view. In
@@ -761,12 +799,11 @@ static inline void kvm_guest_enter(void)
 
 static inline void kvm_guest_exit(void)
 {
-	/*
-	 * This is running in ioctl context so we can avoid
-	 * the call to vtime_account() with its unnecessary idle check.
-	 */
-	vtime_account_system_irqsafe(current);
-	current->flags &= ~PF_VCPU;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	guest_exit();
+	local_irq_restore(flags);
 }
 
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d2112477ff5e..33cc42130371 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -304,19 +304,6 @@ static inline void lockup_detector_init(void)
 }
 #endif
 
-#ifdef CONFIG_DETECT_HUNG_TASK
-extern unsigned int  sysctl_hung_task_panic;
-extern unsigned long sysctl_hung_task_check_count;
-extern unsigned long sysctl_hung_task_timeout_secs;
-extern unsigned long sysctl_hung_task_warnings;
-extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
-					 void __user *buffer,
-					 size_t *lenp, loff_t *ppos);
-#else
-/* Avoid need for ifdefs elsewhere in the code */
-enum { sysctl_hung_task_timeout_secs = 0 };
-#endif
-
 /* Attach to any functions which should be ignored in wchan output. */
 #define __sched		__attribute__((__section__(".sched.text")))
 
@@ -338,23 +325,6 @@ extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 struct nsproxy;
 struct user_namespace;
 
-/*
- * Default maximum number of active map areas, this limits the number of vmas
- * per mm struct. Users can overwrite this number by sysctl but there is a
- * problem.
- *
- * When a program's coredump is generated as ELF format, a section is created
- * per a vma. In ELF, the number of sections is represented in unsigned short.
- * This means the number of sections should be smaller than 65535 at coredump.
- * Because the kernel adds some informative sections to a image of program at
- * generating coredump, we need some margin. The number of extra sections is
- * 1-3 now and depends on arch. We use "5" as safe margin, here.
- */
-#define MAPCOUNT_ELF_CORE_MARGIN	(5)
-#define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
-
-extern int sysctl_max_map_count;
-
 #include <linux/aio.h>
 
 #ifdef CONFIG_MMU
@@ -1194,6 +1164,7 @@ struct sched_entity {
 	/* rq "owned" by this entity/group: */
 	struct cfs_rq		*my_q;
 #endif
+
 /*
  * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
  * removed when useful for applications beyond shares distribution (e.g.
@@ -1208,6 +1179,7 @@ struct sched_entity {
 struct sched_rt_entity {
 	struct list_head run_list;
 	unsigned long timeout;
+	unsigned long watchdog_stamp;
 	unsigned int time_slice;
 
 	struct sched_rt_entity *back;
@@ -1220,11 +1192,6 @@ struct sched_rt_entity {
 #endif
 };
 
-/*
- * default timeslice is 100 msecs (used only for SCHED_RR tasks).
- * Timeslices get refilled after they expire.
- */
-#define RR_TIMESLICE		(100 * HZ / 1000)
 
 struct rcu_node;
 
@@ -1368,6 +1335,15 @@ struct task_struct {
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	struct cputime prev_cputime;
 #endif
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+	seqlock_t vtime_seqlock;
+	unsigned long long vtime_snap;
+	enum {
+		VTIME_SLEEPING = 0,
+		VTIME_USER,
+		VTIME_SYS,
+	} vtime_snap_whence;
+#endif
 	unsigned long nvcsw, nivcsw; /* context switch counts */
 	struct timespec start_time; 		/* monotonic time */
 	struct timespec real_start_time;	/* boot based time */
@@ -1622,37 +1598,6 @@ static inline void set_numabalancing_state(bool enabled)
 }
 #endif
 
-/*
- * Priority of a process goes from 0..MAX_PRIO-1, valid RT
- * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
- * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
- * values are inverted: lower p->prio value means higher priority.
- *
- * The MAX_USER_RT_PRIO value allows the actual maximum
- * RT priority to be separate from the value exported to
- * user-space.  This allows kernel threads to set their
- * priority to a value higher than any user task. Note:
- * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
- */
-
-#define MAX_USER_RT_PRIO	100
-#define MAX_RT_PRIO		MAX_USER_RT_PRIO
-
-#define MAX_PRIO		(MAX_RT_PRIO + 40)
-#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
-
-static inline int rt_prio(int prio)
-{
-	if (unlikely(prio < MAX_RT_PRIO))
-		return 1;
-	return 0;
-}
-
-static inline int rt_task(struct task_struct *p)
-{
-	return rt_prio(p->prio);
-}
-
 static inline struct pid *task_pid(struct task_struct *task)
 {
 	return task->pids[PIDTYPE_PID].pid;
@@ -1792,6 +1737,37 @@ static inline void put_task_struct(struct task_struct *t)
 		__put_task_struct(t);
 }
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern void task_cputime(struct task_struct *t,
+			 cputime_t *utime, cputime_t *stime);
+extern void task_cputime_scaled(struct task_struct *t,
+				cputime_t *utimescaled, cputime_t *stimescaled);
+extern cputime_t task_gtime(struct task_struct *t);
+#else
+static inline void task_cputime(struct task_struct *t,
+				cputime_t *utime, cputime_t *stime)
+{
+	if (utime)
+		*utime = t->utime;
+	if (stime)
+		*stime = t->stime;
+}
+
+static inline void task_cputime_scaled(struct task_struct *t,
+				       cputime_t *utimescaled,
+				       cputime_t *stimescaled)
+{
+	if (utimescaled)
+		*utimescaled = t->utimescaled;
+	if (stimescaled)
+		*stimescaled = t->stimescaled;
+}
+
+static inline cputime_t task_gtime(struct task_struct *t)
+{
+	return t->gtime;
+}
+#endif
 extern void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st);
 
@@ -2033,58 +2009,7 @@ extern void wake_up_idle_cpu(int cpu);
 static inline void wake_up_idle_cpu(int cpu) { }
 #endif
 
-extern unsigned int sysctl_sched_latency;
-extern unsigned int sysctl_sched_min_granularity;
-extern unsigned int sysctl_sched_wakeup_granularity;
-extern unsigned int sysctl_sched_child_runs_first;
-
-enum sched_tunable_scaling {
-	SCHED_TUNABLESCALING_NONE,
-	SCHED_TUNABLESCALING_LOG,
-	SCHED_TUNABLESCALING_LINEAR,
-	SCHED_TUNABLESCALING_END,
-};
-extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
-
-extern unsigned int sysctl_numa_balancing_scan_delay;
-extern unsigned int sysctl_numa_balancing_scan_period_min;
-extern unsigned int sysctl_numa_balancing_scan_period_max;
-extern unsigned int sysctl_numa_balancing_scan_period_reset;
-extern unsigned int sysctl_numa_balancing_scan_size;
-extern unsigned int sysctl_numa_balancing_settle_count;
-
-#ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_migration_cost;
-extern unsigned int sysctl_sched_nr_migrate;
-extern unsigned int sysctl_sched_time_avg;
-extern unsigned int sysctl_timer_migration;
-extern unsigned int sysctl_sched_shares_window;
-
-int sched_proc_update_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *length,
-		loff_t *ppos);
-#endif
-#ifdef CONFIG_SCHED_DEBUG
-static inline unsigned int get_sysctl_timer_migration(void)
-{
-	return sysctl_timer_migration;
-}
-#else
-static inline unsigned int get_sysctl_timer_migration(void)
-{
-	return 1;
-}
-#endif
-extern unsigned int sysctl_sched_rt_period;
-extern int sysctl_sched_rt_runtime;
-
-int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos);
-
 #ifdef CONFIG_SCHED_AUTOGROUP
-extern unsigned int sysctl_sched_autogroup_enabled;
-
 extern void sched_autogroup_create_attach(struct task_struct *p);
 extern void sched_autogroup_detach(struct task_struct *p);
 extern void sched_autogroup_fork(struct signal_struct *sig);
@@ -2100,30 +2025,6 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { }
 static inline void sched_autogroup_exit(struct signal_struct *sig) { }
 #endif
 
-#ifdef CONFIG_CFS_BANDWIDTH
-extern unsigned int sysctl_sched_cfs_bandwidth_slice;
-#endif
-
-#ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern void rt_mutex_adjust_pi(struct task_struct *p);
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return tsk->pi_blocked_on != NULL;
-}
-#else
-static inline int rt_mutex_getprio(struct task_struct *p)
-{
-	return p->normal_prio;
-}
-# define rt_mutex_adjust_pi(p)		do { } while (0)
-static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
-{
-	return false;
-}
-#endif
-
 extern bool yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
 extern int task_prio(const struct task_struct *p);
@@ -2753,8 +2654,6 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
-extern void normalize_rt_tasks(void);
-
 #ifdef CONFIG_CGROUP_SCHED
 
 extern struct task_group root_task_group;
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
new file mode 100644
index 000000000000..94e19ea28fc3
--- /dev/null
+++ b/include/linux/sched/rt.h
@@ -0,0 +1,58 @@
+#ifndef _SCHED_RT_H
+#define _SCHED_RT_H
+
+/*
+ * Priority of a process goes from 0..MAX_PRIO-1, valid RT
+ * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
+ * tasks are in the range MAX_RT_PRIO..MAX_PRIO-1. Priority
+ * values are inverted: lower p->prio value means higher priority.
+ *
+ * The MAX_USER_RT_PRIO value allows the actual maximum
+ * RT priority to be separate from the value exported to
+ * user-space.  This allows kernel threads to set their
+ * priority to a value higher than any user task. Note:
+ * MAX_RT_PRIO must not be smaller than MAX_USER_RT_PRIO.
+ */
+
+#define MAX_USER_RT_PRIO	100
+#define MAX_RT_PRIO		MAX_USER_RT_PRIO
+
+#define MAX_PRIO		(MAX_RT_PRIO + 40)
+#define DEFAULT_PRIO		(MAX_RT_PRIO + 20)
+
+static inline int rt_prio(int prio)
+{
+	if (unlikely(prio < MAX_RT_PRIO))
+		return 1;
+	return 0;
+}
+
+static inline int rt_task(struct task_struct *p)
+{
+	return rt_prio(p->prio);
+}
+
+#ifdef CONFIG_RT_MUTEXES
+extern int rt_mutex_getprio(struct task_struct *p);
+extern void rt_mutex_setprio(struct task_struct *p, int prio);
+extern void rt_mutex_adjust_pi(struct task_struct *p);
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+	return tsk->pi_blocked_on != NULL;
+}
+#else
+static inline int rt_mutex_getprio(struct task_struct *p)
+{
+	return p->normal_prio;
+}
+# define rt_mutex_adjust_pi(p)		do { } while (0)
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+	return false;
+}
+#endif
+
+extern void normalize_rt_tasks(void);
+
+
+#endif /* _SCHED_RT_H */
diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
new file mode 100644
index 000000000000..d2bb0ae979d0
--- /dev/null
+++ b/include/linux/sched/sysctl.h
@@ -0,0 +1,110 @@
+#ifndef _SCHED_SYSCTL_H
+#define _SCHED_SYSCTL_H
+
+#ifdef CONFIG_DETECT_HUNG_TASK
+extern unsigned int  sysctl_hung_task_panic;
+extern unsigned long sysctl_hung_task_check_count;
+extern unsigned long sysctl_hung_task_timeout_secs;
+extern unsigned long sysctl_hung_task_warnings;
+extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+					 void __user *buffer,
+					 size_t *lenp, loff_t *ppos);
+#else
+/* Avoid need for ifdefs elsewhere in the code */
+enum { sysctl_hung_task_timeout_secs = 0 };
+#endif
+
+/*
+ * Default maximum number of active map areas, this limits the number of vmas
+ * per mm struct. Users can overwrite this number by sysctl but there is a
+ * problem.
+ *
+ * When a program's coredump is generated as ELF format, a section is created
+ * per a vma. In ELF, the number of sections is represented in unsigned short.
+ * This means the number of sections should be smaller than 65535 at coredump.
+ * Because the kernel adds some informative sections to a image of program at
+ * generating coredump, we need some margin. The number of extra sections is
+ * 1-3 now and depends on arch. We use "5" as safe margin, here.
+ */
+#define MAPCOUNT_ELF_CORE_MARGIN	(5)
+#define DEFAULT_MAX_MAP_COUNT	(USHRT_MAX - MAPCOUNT_ELF_CORE_MARGIN)
+
+extern int sysctl_max_map_count;
+
+extern unsigned int sysctl_sched_latency;
+extern unsigned int sysctl_sched_min_granularity;
+extern unsigned int sysctl_sched_wakeup_granularity;
+extern unsigned int sysctl_sched_child_runs_first;
+
+enum sched_tunable_scaling {
+	SCHED_TUNABLESCALING_NONE,
+	SCHED_TUNABLESCALING_LOG,
+	SCHED_TUNABLESCALING_LINEAR,
+	SCHED_TUNABLESCALING_END,
+};
+extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
+
+extern unsigned int sysctl_numa_balancing_scan_delay;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_period_reset;
+extern unsigned int sysctl_numa_balancing_scan_size;
+extern unsigned int sysctl_numa_balancing_settle_count;
+
+#ifdef CONFIG_SCHED_DEBUG
+extern unsigned int sysctl_sched_migration_cost;
+extern unsigned int sysctl_sched_nr_migrate;
+extern unsigned int sysctl_sched_time_avg;
+extern unsigned int sysctl_timer_migration;
+extern unsigned int sysctl_sched_shares_window;
+
+int sched_proc_update_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *length,
+		loff_t *ppos);
+#endif
+#ifdef CONFIG_SCHED_DEBUG
+static inline unsigned int get_sysctl_timer_migration(void)
+{
+	return sysctl_timer_migration;
+}
+#else
+static inline unsigned int get_sysctl_timer_migration(void)
+{
+	return 1;
+}
+#endif
+
+/*
+ *  control realtime throttling:
+ *
+ *  /proc/sys/kernel/sched_rt_period_us
+ *  /proc/sys/kernel/sched_rt_runtime_us
+ */
+extern unsigned int sysctl_sched_rt_period;
+extern int sysctl_sched_rt_runtime;
+
+#ifdef CONFIG_CFS_BANDWIDTH
+extern unsigned int sysctl_sched_cfs_bandwidth_slice;
+#endif
+
+#ifdef CONFIG_SCHED_AUTOGROUP
+extern unsigned int sysctl_sched_autogroup_enabled;
+#endif
+
+/*
+ * default timeslice is 100 msecs (used only for SCHED_RR tasks).
+ * Timeslices get refilled after they expire.
+ */
+#define RR_TIMESLICE		(100 * HZ / 1000)
+
+extern int sched_rr_timeslice;
+
+extern int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
+extern int sched_rt_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos);
+
+#endif /* _SCHED_SYSCTL_H */
diff --git a/include/linux/tsacct_kern.h b/include/linux/tsacct_kern.h
index 44893e5ec8f7..3251965bf4cc 100644
--- a/include/linux/tsacct_kern.h
+++ b/include/linux/tsacct_kern.h
@@ -23,12 +23,15 @@ static inline void bacct_add_tsk(struct user_namespace *user_ns,
 #ifdef CONFIG_TASK_XACCT
 extern void xacct_add_tsk(struct taskstats *stats, struct task_struct *p);
 extern void acct_update_integrals(struct task_struct *tsk);
+extern void acct_account_cputime(struct task_struct *tsk);
 extern void acct_clear_integrals(struct task_struct *tsk);
 #else
 static inline void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
 {}
 static inline void acct_update_integrals(struct task_struct *tsk)
 {}
+static inline void acct_account_cputime(struct task_struct *tsk)
+{}
 static inline void acct_clear_integrals(struct task_struct *tsk)
 {}
 #endif /* CONFIG_TASK_XACCT */
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index ae30ab58431a..71a5782d8c59 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -6,15 +6,46 @@ struct task_struct;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 extern void vtime_task_switch(struct task_struct *prev);
 extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_system_irqsafe(struct task_struct *tsk);
 extern void vtime_account_idle(struct task_struct *tsk);
 extern void vtime_account_user(struct task_struct *tsk);
-extern void vtime_account(struct task_struct *tsk);
-#else
+extern void vtime_account_irq_enter(struct task_struct *tsk);
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+static inline bool vtime_accounting_enabled(void) { return true; }
+#endif
+
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
+
 static inline void vtime_task_switch(struct task_struct *prev) { }
 static inline void vtime_account_system(struct task_struct *tsk) { }
-static inline void vtime_account_system_irqsafe(struct task_struct *tsk) { }
-static inline void vtime_account(struct task_struct *tsk) { }
+static inline void vtime_account_user(struct task_struct *tsk) { }
+static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
+static inline bool vtime_accounting_enabled(void) { return false; }
+#endif
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern void arch_vtime_task_switch(struct task_struct *tsk);
+extern void vtime_account_irq_exit(struct task_struct *tsk);
+extern bool vtime_accounting_enabled(void);
+extern void vtime_user_enter(struct task_struct *tsk);
+static inline void vtime_user_exit(struct task_struct *tsk)
+{
+	vtime_account_user(tsk);
+}
+extern void vtime_guest_enter(struct task_struct *tsk);
+extern void vtime_guest_exit(struct task_struct *tsk);
+extern void vtime_init_idle(struct task_struct *tsk);
+#else
+static inline void vtime_account_irq_exit(struct task_struct *tsk)
+{
+	/* On hard|softirq exit we always account to hard|softirq cputime */
+	vtime_account_system(tsk);
+}
+static inline void vtime_user_enter(struct task_struct *tsk) { }
+static inline void vtime_user_exit(struct task_struct *tsk) { }
+static inline void vtime_guest_enter(struct task_struct *tsk) { }
+static inline void vtime_guest_exit(struct task_struct *tsk) { }
+static inline void vtime_init_idle(struct task_struct *tsk) { }
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
@@ -23,25 +54,15 @@ extern void irqtime_account_irq(struct task_struct *tsk);
 static inline void irqtime_account_irq(struct task_struct *tsk) { }
 #endif
 
-static inline void vtime_account_irq_enter(struct task_struct *tsk)
+static inline void account_irq_enter_time(struct task_struct *tsk)
 {
-	/*
-	 * Hardirq can interrupt idle task anytime. So we need vtime_account()
-	 * that performs the idle check in CONFIG_VIRT_CPU_ACCOUNTING.
-	 * Softirq can also interrupt idle task directly if it calls
-	 * local_bh_enable(). Such case probably don't exist but we never know.
-	 * Ksoftirqd is not concerned because idle time is flushed on context
-	 * switch. Softirqs in the end of hardirqs are also not a problem because
-	 * the idle time is flushed on hardirq time already.
-	 */
-	vtime_account(tsk);
+	vtime_account_irq_enter(tsk);
 	irqtime_account_irq(tsk);
 }
 
-static inline void vtime_account_irq_exit(struct task_struct *tsk)
+static inline void account_irq_exit_time(struct task_struct *tsk)
 {
-	/* On hard|softirq exit we always account to hard|softirq cputime */
-	vtime_account_system(tsk);
+	vtime_account_irq_exit(tsk);
 	irqtime_account_irq(tsk);
 }