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

Pull scheduler updates from Ingo Molnar:
 "The biggest change in this cycle is the rewrite of the main SMP load
  balancing metric: the CPU load/utilization.  The main goal was to make
  the metric more precise and more representative - see the changelog of
  this commit for the gory details:

    9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking")

  It is done in a way that significantly reduces complexity of the code:

    5 files changed, 249 insertions(+), 494 deletions(-)

  and the performance testing results are encouraging.  Nevertheless we
  need to keep an eye on potential regressions, since this potentially
  affects every SMP workload in existence.

  This work comes from Yuyang Du.

  Other changes:

   - SCHED_DL updates.  (Andrea Parri)

   - Simplify architecture callbacks by removing finish_arch_switch().
     (Peter Zijlstra et al)

   - cputime accounting: guarantee stime + utime == rtime.  (Peter
     Zijlstra)

   - optimize idle CPU wakeups some more - inspired by Facebook server
     loads.  (Mike Galbraith)

   - stop_machine fixes and updates.  (Oleg Nesterov)

   - Introduce the 'trace_sched_waking' tracepoint.  (Peter Zijlstra)

   - sched/numa tweaks.  (Srikar Dronamraju)

   - misc fixes and small cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  sched/deadline: Fix comment in enqueue_task_dl()
  sched/deadline: Fix comment in push_dl_tasks()
  sched: Change the sched_class::set_cpus_allowed() calling context
  sched: Make sched_class::set_cpus_allowed() unconditional
  sched: Fix a race between __kthread_bind() and sched_setaffinity()
  sched: Ensure a task has a non-normalized vruntime when returning back to CFS
  sched/numa: Fix NUMA_DIRECT topology identification
  tile: Reorganize _switch_to()
  sched, sparc32: Update scheduler comments in copy_thread()
  sched: Remove finish_arch_switch()
  sched, tile: Remove finish_arch_switch
  sched, sh: Fold finish_arch_switch() into switch_to()
  sched, score: Remove finish_arch_switch()
  sched, avr32: Remove finish_arch_switch()
  sched, MIPS: Get rid of finish_arch_switch()
  sched, arm: Remove finish_arch_switch()
  sched/fair: Clean up load average references
  sched/fair: Provide runnable_load_avg back to cfs_rq
  sched/fair: Remove task and group entity load when they are dead
  sched/fair: Init cfs_rq's sched_entity load average
  ...

7 files changed, 97 insertions, 94 deletions

diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index d0a7a47..0bec580 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -71,9 +71,10 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!preempt_count() && tif_need_resched());
+	return unlikely(preempt_count() == preempt_offset &&
+			tif_need_resched());
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e8493fe..d0b380e 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -32,6 +32,14 @@ extern struct fs_struct init_fs;
 #define INIT_CPUSET_SEQ(tsk)
 #endif
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+#define INIT_PREV_CPUTIME(x)	.prev_cputime = {			\
+	.lock = __RAW_SPIN_LOCK_UNLOCKED(x.prev_cputime.lock),		\
+},
+#else
+#define INIT_PREV_CPUTIME(x)
+#endif
+
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
 	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\
@@ -46,6 +54,7 @@ extern struct fs_struct init_fs;
 		.cputime_atomic	= INIT_CPUTIME_ATOMIC,			\
 		.running	= 0,					\
 	},								\
+	INIT_PREV_CPUTIME(sig)						\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
 }
@@ -246,6 +255,7 @@ extern struct task_group root_task_group;
 	INIT_TASK_RCU_TASKS(tsk)					\
 	INIT_CPUSET_SEQ(tsk)						\
 	INIT_RT_MUTEXES(tsk)						\
+	INIT_PREV_CPUTIME(tsk)						\
 	INIT_VTIME(tsk)							\
 	INIT_NUMA_BALANCING(tsk)					\
 	INIT_KASAN(tsk)							\
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 13d5520..869b21d 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -38,6 +38,7 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 })
 
 void kthread_bind(struct task_struct *k, unsigned int cpu);
+void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask);
 int kthread_stop(struct task_struct *k);
 bool kthread_should_stop(void);
 bool kthread_should_park(void);
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 84991f1..bea8dd8 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -84,13 +84,21 @@
  */
 #define in_nmi()	(preempt_count() & NMI_MASK)
 
+/*
+ * The preempt_count offset after preempt_disable();
+ */
 #if defined(CONFIG_PREEMPT_COUNT)
-# define PREEMPT_DISABLE_OFFSET 1
+# define PREEMPT_DISABLE_OFFSET	PREEMPT_OFFSET
 #else
-# define PREEMPT_DISABLE_OFFSET 0
+# define PREEMPT_DISABLE_OFFSET	0
 #endif
 
 /*
+ * The preempt_count offset after spin_lock()
+ */
+#define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+
+/*
  * The preempt_count offset needed for things like:
  *
  *  spin_lock_bh()
@@ -103,7 +111,7 @@
  *
  * Work as expected.
  */
-#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET)
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET)
 
 /*
  * Are we running in atomic context?  WARNING: this macro cannot
@@ -124,7 +132,8 @@
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
 extern void preempt_count_sub(int val);
-#define preempt_count_dec_and_test() ({ preempt_count_sub(1); should_resched(); })
+#define preempt_count_dec_and_test() \
+	({ preempt_count_sub(1); should_resched(0); })
 #else
 #define preempt_count_add(val)	__preempt_count_add(val)
 #define preempt_count_sub(val)	__preempt_count_sub(val)
@@ -184,7 +193,7 @@ do { \
 
 #define preempt_check_resched() \
 do { \
-	if (should_resched()) \
+	if (should_resched(0)) \
 		__preempt_schedule(); \
 } while (0)
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 04b5ada..119823d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -530,39 +530,49 @@ struct cpu_itimer {
 };
 
 /**
- * struct cputime - snaphsot of system and user cputime
+ * struct prev_cputime - snaphsot of system and user cputime
  * @utime: time spent in user mode
  * @stime: time spent in system mode
+ * @lock: protects the above two fields
  *
- * Gathers a generic snapshot of user and system time.
+ * Stores previous user/system time values such that we can guarantee
+ * monotonicity.
  */
-struct cputime {
+struct prev_cputime {
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 	cputime_t utime;
 	cputime_t stime;
+	raw_spinlock_t lock;
+#endif
 };
 
+static inline void prev_cputime_init(struct prev_cputime *prev)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	prev->utime = prev->stime = 0;
+	raw_spin_lock_init(&prev->lock);
+#endif
+}
+
 /**
  * struct task_cputime - collected CPU time counts
  * @utime:		time spent in user mode, in &cputime_t units
  * @stime:		time spent in kernel mode, in &cputime_t units
  * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
  *
- * This is an extension of struct cputime that includes the total runtime
- * spent by the task from the scheduler point of view.
- *
- * As a result, this structure groups together three kinds of CPU time
- * that are tracked for threads and thread groups.  Most things considering
- * CPU time want to group these counts together and treat all three
- * of them in parallel.
+ * This structure groups together three kinds of CPU time that are tracked for
+ * threads and thread groups.  Most things considering CPU time want to group
+ * these counts together and treat all three of them in parallel.
  */
 struct task_cputime {
 	cputime_t utime;
 	cputime_t stime;
 	unsigned long long sum_exec_runtime;
 };
+
 /* Alternate field names when used to cache expirations. */
-#define prof_exp	stime
 #define virt_exp	utime
+#define prof_exp	stime
 #define sched_exp	sum_exec_runtime
 
 #define INIT_CPUTIME	\
@@ -715,9 +725,7 @@ struct signal_struct {
 	cputime_t utime, stime, cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	struct cputime prev_cputime;
-#endif
+	struct prev_cputime prev_cputime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
 	unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
 	unsigned long inblock, oublock, cinblock, coublock;
@@ -1167,29 +1175,24 @@ struct load_weight {
 	u32 inv_weight;
 };
 
+/*
+ * The load_avg/util_avg accumulates an infinite geometric series.
+ * 1) load_avg factors the amount of time that a sched_entity is
+ * runnable on a rq into its weight. For cfs_rq, it is the aggregated
+ * such weights of all runnable and blocked sched_entities.
+ * 2) util_avg factors frequency scaling into the amount of time
+ * that a sched_entity is running on a CPU, in the range [0..SCHED_LOAD_SCALE].
+ * For cfs_rq, it is the aggregated such times of all runnable and
+ * blocked sched_entities.
+ * The 64 bit load_sum can:
+ * 1) for cfs_rq, afford 4353082796 (=2^64/47742/88761) entities with
+ * the highest weight (=88761) always runnable, we should not overflow
+ * 2) for entity, support any load.weight always runnable
+ */
 struct sched_avg {
-	u64 last_runnable_update;
-	s64 decay_count;
-	/*
-	 * utilization_avg_contrib describes the amount of time that a
-	 * sched_entity is running on a CPU. It is based on running_avg_sum
-	 * and is scaled in the range [0..SCHED_LOAD_SCALE].
-	 * load_avg_contrib described the amount of time that a sched_entity
-	 * is runnable on a rq. It is based on both runnable_avg_sum and the
-	 * weight of the task.
-	 */
-	unsigned long load_avg_contrib, utilization_avg_contrib;
-	/*
-	 * These sums represent an infinite geometric series and so are bound
-	 * above by 1024/(1-y).  Thus we only need a u32 to store them for all
-	 * choices of y < 1-2^(-32)*1024.
-	 * running_avg_sum reflects the time that the sched_entity is
-	 * effectively running on the CPU.
-	 * runnable_avg_sum represents the amount of time a sched_entity is on
-	 * a runqueue which includes the running time that is monitored by
-	 * running_avg_sum.
-	 */
-	u32 runnable_avg_sum, avg_period, running_avg_sum;
+	u64 last_update_time, load_sum;
+	u32 util_sum, period_contrib;
+	unsigned long load_avg, util_avg;
 };
 
 #ifdef CONFIG_SCHEDSTATS
@@ -1255,7 +1258,7 @@ struct sched_entity {
 #endif
 
 #ifdef CONFIG_SMP
-	/* Per-entity load-tracking */
+	/* Per entity load average tracking */
 	struct sched_avg	avg;
 #endif
 };
@@ -1351,9 +1354,9 @@ struct task_struct {
 #ifdef CONFIG_SMP
 	struct llist_node wake_entry;
 	int on_cpu;
-	struct task_struct *last_wakee;
-	unsigned long wakee_flips;
+	unsigned int wakee_flips;
 	unsigned long wakee_flip_decay_ts;
+	struct task_struct *last_wakee;
 
 	int wake_cpu;
 #endif
@@ -1481,9 +1484,7 @@ struct task_struct {
 
 	cputime_t utime, stime, utimescaled, stimescaled;
 	cputime_t gtime;
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-	struct cputime prev_cputime;
-#endif
+	struct prev_cputime prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 	seqlock_t vtime_seqlock;
 	unsigned long long vtime_snap;
@@ -2214,13 +2215,6 @@ static inline void calc_load_enter_idle(void) { }
 static inline void calc_load_exit_idle(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
-#ifndef CONFIG_CPUMASK_OFFSTACK
-static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
-{
-	return set_cpus_allowed_ptr(p, &new_mask);
-}
-#endif
-
 /*
  * Do not use outside of architecture code which knows its limitations.
  *
@@ -2897,12 +2891,6 @@ extern int _cond_resched(void);
 
 extern int __cond_resched_lock(spinlock_t *lock);
 
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
-#else
-#define PREEMPT_LOCK_OFFSET	0
-#endif
-
 #define cond_resched_lock(lock) ({				\
 	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
 	__cond_resched_lock(lock);				\
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index d2abbdb..414d924 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -112,25 +112,13 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  *
  * This can be thought of as a very heavy write lock, equivalent to
  * grabbing every spinlock in the kernel. */
-int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
+int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
-/**
- * __stop_machine: freeze the machine on all CPUs and run this function
- * @fn: the function to run
- * @data: the data ptr for the @fn
- * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
- *
- * Description: This is a special version of the above, which assumes cpus
- * won't come or go while it's being called.  Used by hotplug cpu.
- */
-int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus);
-
-int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
+int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
-
 #else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
 
-static inline int __stop_machine(int (*fn)(void *), void *data,
+static inline int stop_machine(cpu_stop_fn_t fn, void *data,
 				 const struct cpumask *cpus)
 {
 	unsigned long flags;
@@ -141,16 +129,10 @@ static inline int __stop_machine(int (*fn)(void *), void *data,
 	return ret;
 }
 
-static inline int stop_machine(int (*fn)(void *), void *data,
-			       const struct cpumask *cpus)
-{
-	return __stop_machine(fn, data, cpus);
-}
-
-static inline int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
+static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 						 const struct cpumask *cpus)
 {
-	return __stop_machine(fn, data, cpus);
+	return stop_machine(fn, data, cpus);
 }
 
 #endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index d57a575..539d6bc 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -55,9 +55,9 @@ TRACE_EVENT(sched_kthread_stop_ret,
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-	TP_PROTO(struct task_struct *p, int success),
+	TP_PROTO(struct task_struct *p),
 
-	TP_ARGS(__perf_task(p), success),
+	TP_ARGS(__perf_task(p)),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -71,25 +71,37 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->success	= success;
+		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
 
-	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
+	TP_printk("comm=%s pid=%d prio=%d target_cpu=%03d",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success, __entry->target_cpu)
+		  __entry->target_cpu)
 );
 
+/*
+ * Tracepoint called when waking a task; this tracepoint is guaranteed to be
+ * called from the waking context.
+ */
+DEFINE_EVENT(sched_wakeup_template, sched_waking,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
+
+/*
+ * Tracepoint called when the task is actually woken; p->state == TASK_RUNNNG.
+ * It it not always called from the waking context.
+ */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 /*
  * Tracepoint for waking up a new task:
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-	     TP_PROTO(struct task_struct *p, int success),
-	     TP_ARGS(p, success));
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
 static inline long __trace_sched_switch_state(struct task_struct *p)