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

Pull scheduler changes from Ingo Molnar:
 "The main changes in this development cycle were:

   - full dynticks preparatory work by Frederic Weisbecker

   - factor out the cpu time accounting code better, by Li Zefan

   - multi-CPU load balancer cleanups and improvements by Joonsoo Kim

   - various smaller fixes and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (45 commits)
  sched: Fix init NOHZ_IDLE flag
  sched: Prevent to re-select dst-cpu in load_balance()
  sched: Rename load_balance_tmpmask to load_balance_mask
  sched: Move up affinity check to mitigate useless redoing overhead
  sched: Don't consider other cpus in our group in case of NEWLY_IDLE
  sched: Explicitly cpu_idle_type checking in rebalance_domains()
  sched: Change position of resched_cpu() in load_balance()
  sched: Fix wrong rq's runnable_avg update with rt tasks
  sched: Document task_struct::personality field
  sched/cpuacct/UML: Fix header file dependency bug on the UML build
  cgroup: Kill subsys.active flag
  sched/cpuacct: No need to check subsys active state
  sched/cpuacct: Initialize cpuacct subsystem earlier
  sched/cpuacct: Initialize root cpuacct earlier
  sched/cpuacct: Allocate per_cpu cpuusage for root cpuacct statically
  sched/cpuacct: Clean up cpuacct.h
  sched/cpuacct: Remove redundant NULL checks in cpuacct_acount_field()
  sched/cpuacct: Remove redundant NULL checks in cpuacct_charge()
  sched/cpuacct: Add cpuacct_acount_field()
  sched/cpuacct: Add cpuacct_init()
  ...

4 files changed, 49 insertions, 199 deletions

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index d86e215ca2b..646ab9d15e4 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -586,7 +586,6 @@ struct cgroup_subsys {
 	void (*bind)(struct cgroup *root);
 
 	int subsys_id;
-	int active;
 	int disabled;
 	int early_init;
 	/*
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index b28d161c109..365f4a61bf0 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -1,9 +1,9 @@
 #ifndef _LINUX_CONTEXT_TRACKING_H
 #define _LINUX_CONTEXT_TRACKING_H
 
-#ifdef CONFIG_CONTEXT_TRACKING
 #include <linux/sched.h>
 #include <linux/percpu.h>
+#include <asm/ptrace.h>
 
 struct context_tracking {
 	/*
@@ -13,12 +13,13 @@ struct context_tracking {
 	 * may be further optimized using static keys.
 	 */
 	bool active;
-	enum {
+	enum ctx_state {
 		IN_KERNEL = 0,
 		IN_USER,
 	} state;
 };
 
+#ifdef CONFIG_CONTEXT_TRACKING
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
 static inline bool context_tracking_in_user(void)
@@ -33,12 +34,31 @@ static inline bool context_tracking_active(void)
 
 extern void user_enter(void);
 extern void user_exit(void);
+
+static inline enum ctx_state exception_enter(void)
+{
+	enum ctx_state prev_ctx;
+
+	prev_ctx = this_cpu_read(context_tracking.state);
+	user_exit();
+
+	return prev_ctx;
+}
+
+static inline void exception_exit(enum ctx_state prev_ctx)
+{
+	if (prev_ctx == IN_USER)
+		user_enter();
+}
+
 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 enum ctx_state exception_enter(void) { return 0; }
+static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
 						struct task_struct *next) { }
 #endif /* !CONFIG_CONTEXT_TRACKING */
diff --git a/include/linux/math64.h b/include/linux/math64.h
index b8ba8554472..931a619407b 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -30,6 +30,15 @@ static inline s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder)
 }
 
 /**
+ * div64_u64_rem - unsigned 64bit divide with 64bit divisor
+ */
+static inline u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder)
+{
+	*remainder = dividend % divisor;
+	return dividend / divisor;
+}
+
+/**
  * div64_u64 - unsigned 64bit divide with 64bit divisor
  */
 static inline u64 div64_u64(u64 dividend, u64 divisor)
@@ -61,8 +70,16 @@ static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
 extern s64 div_s64_rem(s64 dividend, s32 divisor, s32 *remainder);
 #endif
 
+#ifndef div64_u64_rem
+extern u64 div64_u64_rem(u64 dividend, u64 divisor, u64 *remainder);
+#endif
+
 #ifndef div64_u64
-extern u64 div64_u64(u64 dividend, u64 divisor);
+static inline u64 div64_u64(u64 dividend, u64 divisor)
+{
+	u64 remainder;
+	return div64_u64_rem(dividend, divisor, &remainder);
+}
 #endif
 
 #ifndef div64_s64
diff --git a/include/linux/sched.h b/include/linux/sched.h
index bcbc30397f2..01c7d85bcaa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -127,18 +127,6 @@ extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
 extern void proc_sched_set_task(struct task_struct *p);
 extern void
 print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
-#else
-static inline void
-proc_sched_show_task(struct task_struct *p, struct seq_file *m)
-{
-}
-static inline void proc_sched_set_task(struct task_struct *p)
-{
-}
-static inline void
-print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
-{
-}
 #endif
 
 /*
@@ -570,7 +558,7 @@ struct signal_struct {
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	struct cputime prev_cputime;
 #endif
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
@@ -768,31 +756,6 @@ enum cpu_idle_type {
 };
 
 /*
- * Increase resolution of nice-level calculations for 64-bit architectures.
- * The extra resolution improves shares distribution and load balancing of
- * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
- * hierarchies, especially on larger systems. This is not a user-visible change
- * and does not change the user-interface for setting shares/weights.
- *
- * We increase resolution only if we have enough bits to allow this increased
- * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
- * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
- * increased costs.
- */
-#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load  */
-# define SCHED_LOAD_RESOLUTION	10
-# define scale_load(w)		((w) << SCHED_LOAD_RESOLUTION)
-# define scale_load_down(w)	((w) >> SCHED_LOAD_RESOLUTION)
-#else
-# define SCHED_LOAD_RESOLUTION	0
-# define scale_load(w)		(w)
-# define scale_load_down(w)	(w)
-#endif
-
-#define SCHED_LOAD_SHIFT	(10 + SCHED_LOAD_RESOLUTION)
-#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)
-
-/*
  * Increase resolution of cpu_power calculations
  */
 #define SCHED_POWER_SHIFT	10
@@ -817,62 +780,6 @@ enum cpu_idle_type {
 
 extern int __weak arch_sd_sibiling_asym_packing(void);
 
-struct sched_group_power {
-	atomic_t ref;
-	/*
-	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
-	 * single CPU.
-	 */
-	unsigned int power, power_orig;
-	unsigned long next_update;
-	/*
-	 * Number of busy cpus in this group.
-	 */
-	atomic_t nr_busy_cpus;
-
-	unsigned long cpumask[0]; /* iteration mask */
-};
-
-struct sched_group {
-	struct sched_group *next;	/* Must be a circular list */
-	atomic_t ref;
-
-	unsigned int group_weight;
-	struct sched_group_power *sgp;
-
-	/*
-	 * The CPUs this group covers.
-	 *
-	 * NOTE: this field is variable length. (Allocated dynamically
-	 * by attaching extra space to the end of the structure,
-	 * depending on how many CPUs the kernel has booted up with)
-	 */
-	unsigned long cpumask[0];
-};
-
-static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
-{
-	return to_cpumask(sg->cpumask);
-}
-
-/*
- * cpumask masking which cpus in the group are allowed to iterate up the domain
- * tree.
- */
-static inline struct cpumask *sched_group_mask(struct sched_group *sg)
-{
-	return to_cpumask(sg->sgp->cpumask);
-}
-
-/**
- * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
- * @group: The group whose first cpu is to be returned.
- */
-static inline unsigned int group_first_cpu(struct sched_group *group)
-{
-	return cpumask_first(sched_group_cpus(group));
-}
-
 struct sched_domain_attr {
 	int relax_domain_level;
 };
@@ -883,6 +790,8 @@ struct sched_domain_attr {
 
 extern int sched_domain_level_max;
 
+struct sched_group;
+
 struct sched_domain {
 	/* These fields must be setup */
 	struct sched_domain *parent;	/* top domain must be null terminated */
@@ -899,6 +808,8 @@ struct sched_domain {
 	unsigned int wake_idx;
 	unsigned int forkexec_idx;
 	unsigned int smt_gain;
+
+	int nohz_idle;			/* NOHZ IDLE status */
 	int flags;			/* See SD_* */
 	int level;
 
@@ -971,18 +882,6 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
-/* Test a flag in parent sched domain */
-static inline int test_sd_parent(struct sched_domain *sd, int flag)
-{
-	if (sd->parent && (sd->parent->flags & flag))
-		return 1;
-
-	return 0;
-}
-
-unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
-unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
-
 bool cpus_share_cache(int this_cpu, int that_cpu);
 
 #else /* CONFIG_SMP */
@@ -1017,72 +916,6 @@ struct mempolicy;
 struct pipe_inode_info;
 struct uts_namespace;
 
-struct rq;
-struct sched_domain;
-
-/*
- * wake flags
- */
-#define WF_SYNC		0x01		/* waker goes to sleep after wakup */
-#define WF_FORK		0x02		/* child wakeup after fork */
-#define WF_MIGRATED	0x04		/* internal use, task got migrated */
-
-#define ENQUEUE_WAKEUP		1
-#define ENQUEUE_HEAD		2
-#ifdef CONFIG_SMP
-#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
-#else
-#define ENQUEUE_WAKING		0
-#endif
-
-#define DEQUEUE_SLEEP		1
-
-struct sched_class {
-	const struct sched_class *next;
-
-	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
-	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
-	void (*yield_task) (struct rq *rq);
-	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);
-
-	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
-
-	struct task_struct * (*pick_next_task) (struct rq *rq);
-	void (*put_prev_task) (struct rq *rq, struct task_struct *p);
-
-#ifdef CONFIG_SMP
-	int  (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
-	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);
-
-	void (*pre_schedule) (struct rq *this_rq, struct task_struct *task);
-	void (*post_schedule) (struct rq *this_rq);
-	void (*task_waking) (struct task_struct *task);
-	void (*task_woken) (struct rq *this_rq, struct task_struct *task);
-
-	void (*set_cpus_allowed)(struct task_struct *p,
-				 const struct cpumask *newmask);
-
-	void (*rq_online)(struct rq *rq);
-	void (*rq_offline)(struct rq *rq);
-#endif
-
-	void (*set_curr_task) (struct rq *rq);
-	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
-	void (*task_fork) (struct task_struct *p);
-
-	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
-	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
-	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
-			     int oldprio);
-
-	unsigned int (*get_rr_interval) (struct rq *rq,
-					 struct task_struct *task);
-
-#ifdef CONFIG_FAIR_GROUP_SCHED
-	void (*task_move_group) (struct task_struct *p, int on_rq);
-#endif
-};
-
 struct load_weight {
 	unsigned long weight, inv_weight;
 };
@@ -1274,8 +1107,10 @@ struct task_struct {
 	int exit_code, exit_signal;
 	int pdeath_signal;  /*  The signal sent when the parent dies  */
 	unsigned int jobctl;	/* JOBCTL_*, siglock protected */
-	/* ??? */
+
+	/* Used for emulating ABI behavior of previous Linux versions */
 	unsigned int personality;
+
 	unsigned did_exec:1;
 	unsigned in_execve:1;	/* Tell the LSMs that the process is doing an
 				 * execve */
@@ -1327,7 +1162,7 @@ struct task_struct {
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	struct cputime prev_cputime;
 #endif
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
@@ -2681,28 +2516,7 @@ extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
 #ifdef CONFIG_CGROUP_SCHED
-
 extern struct task_group root_task_group;
-
-extern struct task_group *sched_create_group(struct task_group *parent);
-extern void sched_online_group(struct task_group *tg,
-			       struct task_group *parent);
-extern void sched_destroy_group(struct task_group *tg);
-extern void sched_offline_group(struct task_group *tg);
-extern void sched_move_task(struct task_struct *tsk);
-#ifdef CONFIG_FAIR_GROUP_SCHED
-extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
-extern unsigned long sched_group_shares(struct task_group *tg);
-#endif
-#ifdef CONFIG_RT_GROUP_SCHED
-extern int sched_group_set_rt_runtime(struct task_group *tg,
-				      long rt_runtime_us);
-extern long sched_group_rt_runtime(struct task_group *tg);
-extern int sched_group_set_rt_period(struct task_group *tg,
-				      long rt_period_us);
-extern long sched_group_rt_period(struct task_group *tg);
-extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
-#endif
 #endif /* CONFIG_CGROUP_SCHED */
 
 extern int task_can_switch_user(struct user_struct *up,