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 changes in this cycle were:

   - Make kcpustat vtime aware (Frederic Weisbecker)

   - Rework the CFS load_balance() logic (Vincent Guittot)

   - Misc cleanups, smaller enhancements, fixes.

  The load-balancing rework is the most intrusive change: it replaces
  the old heuristics that have become less meaningful after the
  introduction of the PELT metrics, with a grounds-up load-balancing
  algorithm.

  As such it's not really an iterative series, but replaces the old
  load-balancing logic with the new one. We hope there are no
  performance regressions left - but statistically it's highly probable
  that there *is* going to be some workload that is hurting from these
  chnages. If so then we'd prefer to have a look at that workload and
  fix its scheduling, instead of reverting the changes"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  rackmeter: Use vtime aware kcpustat accessor
  leds: Use all-in-one vtime aware kcpustat accessor
  cpufreq: Use vtime aware kcpustat accessors for user time
  procfs: Use all-in-one vtime aware kcpustat accessor
  sched/vtime: Bring up complete kcpustat accessor
  sched/cputime: Support other fields on kcpustat_field()
  sched/cpufreq: Move the cfs_rq_util_change() call to cpufreq_update_util()
  sched/fair: Add comments for group_type and balancing at SD_NUMA level
  sched/fair: Fix rework of find_idlest_group()
  sched/uclamp: Fix overzealous type replacement
  sched/Kconfig: Fix spelling mistake in user-visible help text
  sched/core: Further clarify sched_class::set_next_task()
  sched/fair: Use mul_u32_u32()
  sched/core: Simplify sched_class::pick_next_task()
  sched/core: Optimize pick_next_task()
  sched/core: Make pick_next_task_idle() more consistent
  sched/fair: Better document newidle_balance()
  leds: Use vtime aware kcpustat accessor to fetch CPUTIME_SYSTEM
  cpufreq: Use vtime aware kcpustat accessor to fetch CPUTIME_SYSTEM
  procfs: Use vtime aware kcpustat accessor to fetch CPUTIME_SYSTEM
  ...

6 files changed, 84 insertions, 55 deletions

diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index d05609ad329d..64ec82851aa3 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -22,26 +22,26 @@ extern void context_tracking_user_exit(void);
 
 static inline void user_enter(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		context_tracking_enter(CONTEXT_USER);
 
 }
 static inline void user_exit(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		context_tracking_exit(CONTEXT_USER);
 }
 
 /* Called with interrupts disabled.  */
 static inline void user_enter_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_enter(CONTEXT_USER);
 
 }
 static inline void user_exit_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_exit(CONTEXT_USER);
 }
 
@@ -49,7 +49,7 @@ static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
 
-	if (!context_tracking_is_enabled())
+	if (!context_tracking_enabled())
 		return 0;
 
 	prev_ctx = this_cpu_read(context_tracking.state);
@@ -61,7 +61,7 @@ static inline enum ctx_state exception_enter(void)
 
 static inline void exception_exit(enum ctx_state prev_ctx)
 {
-	if (context_tracking_is_enabled()) {
+	if (context_tracking_enabled()) {
 		if (prev_ctx != CONTEXT_KERNEL)
 			context_tracking_enter(prev_ctx);
 	}
@@ -77,7 +77,7 @@ static inline void exception_exit(enum ctx_state prev_ctx)
  */
 static inline enum ctx_state ct_state(void)
 {
-	return context_tracking_is_enabled() ?
+	return context_tracking_enabled() ?
 		this_cpu_read(context_tracking.state) : CONTEXT_DISABLED;
 }
 #else
@@ -90,7 +90,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline enum ctx_state ct_state(void) { return CONTEXT_DISABLED; }
 #endif /* !CONFIG_CONTEXT_TRACKING */
 
-#define CT_WARN_ON(cond) WARN_ON(context_tracking_is_enabled() && (cond))
+#define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
 
 #ifdef CONFIG_CONTEXT_TRACKING_FORCE
 extern void context_tracking_init(void);
@@ -103,12 +103,12 @@ static inline void context_tracking_init(void) { }
 /* must be called with irqs disabled */
 static inline void guest_enter_irqoff(void)
 {
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		vtime_guest_enter(current);
 	else
 		current->flags |= PF_VCPU;
 
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_enter(CONTEXT_GUEST);
 
 	/* KVM does not hold any references to rcu protected data when it
@@ -118,16 +118,16 @@ static inline void guest_enter_irqoff(void)
 	 * one time slice). Lets treat guest mode as quiescent state, just like
 	 * we do with user-mode execution.
 	 */
-	if (!context_tracking_cpu_is_enabled())
+	if (!context_tracking_enabled_this_cpu())
 		rcu_virt_note_context_switch(smp_processor_id());
 }
 
 static inline void guest_exit_irqoff(void)
 {
-	if (context_tracking_is_enabled())
+	if (context_tracking_enabled())
 		__context_tracking_exit(CONTEXT_GUEST);
 
-	if (vtime_accounting_cpu_enabled())
+	if (vtime_accounting_enabled_this_cpu())
 		vtime_guest_exit(current);
 	else
 		current->flags &= ~PF_VCPU;
@@ -141,7 +141,7 @@ static inline void guest_enter_irqoff(void)
 	 * to assume that it's the stime pending cputime
 	 * to flush.
 	 */
-	vtime_account_system(current);
+	vtime_account_kernel(current);
 	current->flags |= PF_VCPU;
 	rcu_virt_note_context_switch(smp_processor_id());
 }
@@ -149,7 +149,7 @@ static inline void guest_enter_irqoff(void)
 static inline void guest_exit_irqoff(void)
 {
 	/* Flush the guest cputime we spent on the guest */
-	vtime_account_system(current);
+	vtime_account_kernel(current);
 	current->flags &= ~PF_VCPU;
 }
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index f128dc3be0df..e7fe6678b7ad 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -23,17 +23,22 @@ struct context_tracking {
 };
 
 #ifdef CONFIG_CONTEXT_TRACKING
-extern struct static_key_false context_tracking_enabled;
+extern struct static_key_false context_tracking_key;
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
-static inline bool context_tracking_is_enabled(void)
+static inline bool context_tracking_enabled(void)
 {
-	return static_branch_unlikely(&context_tracking_enabled);
+	return static_branch_unlikely(&context_tracking_key);
 }
 
-static inline bool context_tracking_cpu_is_enabled(void)
+static inline bool context_tracking_enabled_cpu(int cpu)
 {
-	return __this_cpu_read(context_tracking.active);
+	return context_tracking_enabled() && per_cpu(context_tracking.active, cpu);
+}
+
+static inline bool context_tracking_enabled_this_cpu(void)
+{
+	return context_tracking_enabled() && __this_cpu_read(context_tracking.active);
 }
 
 static inline bool context_tracking_in_user(void)
@@ -42,9 +47,9 @@ static inline bool context_tracking_in_user(void)
 }
 #else
 static inline bool context_tracking_in_user(void) { return false; }
-static inline bool context_tracking_active(void) { return false; }
-static inline bool context_tracking_is_enabled(void) { return false; }
-static inline bool context_tracking_cpu_is_enabled(void) { return false; }
+static inline bool context_tracking_enabled(void) { return false; }
+static inline bool context_tracking_enabled_cpu(int cpu) { return false; }
+static inline bool context_tracking_enabled_this_cpu(void) { return false; }
 #endif /* CONFIG_CONTEXT_TRACKING */
 
 #endif
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 7ee2bb43b251..89f0745c096d 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -78,6 +78,24 @@ static inline unsigned int kstat_cpu_irqs_sum(unsigned int cpu)
 	return kstat_cpu(cpu).irqs_sum;
 }
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+extern u64 kcpustat_field(struct kernel_cpustat *kcpustat,
+			  enum cpu_usage_stat usage, int cpu);
+extern void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu);
+#else
+static inline u64 kcpustat_field(struct kernel_cpustat *kcpustat,
+				 enum cpu_usage_stat usage, int cpu)
+{
+	return kcpustat->cpustat[usage];
+}
+
+static inline void kcpustat_cpu_fetch(struct kernel_cpustat *dst, int cpu)
+{
+	*dst = kcpustat_cpu(cpu);
+}
+
+#endif
+
 extern void account_user_time(struct task_struct *, u64);
 extern void account_guest_time(struct task_struct *, u64);
 extern void account_system_time(struct task_struct *, int, u64);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6666e25606b7..f72984f94a5c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -250,16 +250,21 @@ struct prev_cputime {
 enum vtime_state {
 	/* Task is sleeping or running in a CPU with VTIME inactive: */
 	VTIME_INACTIVE = 0,
-	/* Task runs in userspace in a CPU with VTIME active: */
-	VTIME_USER,
+	/* Task is idle */
+	VTIME_IDLE,
 	/* Task runs in kernelspace in a CPU with VTIME active: */
 	VTIME_SYS,
+	/* Task runs in userspace in a CPU with VTIME active: */
+	VTIME_USER,
+	/* Task runs as guests in a CPU with VTIME active: */
+	VTIME_GUEST,
 };
 
 struct vtime {
 	seqcount_t		seqcount;
 	unsigned long long	starttime;
 	enum vtime_state	state;
+	unsigned int		cpu;
 	u64			utime;
 	u64			stime;
 	u64			gtime;
diff --git a/include/linux/tick.h b/include/linux/tick.h
index f92a10b5e112..7e050a356cc5 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -174,7 +174,7 @@ extern cpumask_var_t tick_nohz_full_mask;
 
 static inline bool tick_nohz_full_enabled(void)
 {
-	if (!context_tracking_is_enabled())
+	if (!context_tracking_enabled())
 		return false;
 
 	return tick_nohz_full_running;
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index a26ed10a4eac..2cdeca062db3 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -11,11 +11,15 @@
 struct task_struct;
 
 /*
- * vtime_accounting_cpu_enabled() definitions/declarations
+ * vtime_accounting_enabled_this_cpu() definitions/declarations
  */
 #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE)
-static inline bool vtime_accounting_cpu_enabled(void) { return true; }
+
+static inline bool vtime_accounting_enabled_this_cpu(void) { return true; }
+extern void vtime_task_switch(struct task_struct *prev);
+
 #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN)
+
 /*
  * Checks if vtime is enabled on some CPU. Cputime readers want to be careful
  * in that case and compute the tickless cputime.
@@ -24,46 +28,43 @@ static inline bool vtime_accounting_cpu_enabled(void) { return true; }
  */
 static inline bool vtime_accounting_enabled(void)
 {
-	return context_tracking_is_enabled();
+	return context_tracking_enabled();
 }
 
-static inline bool vtime_accounting_cpu_enabled(void)
+static inline bool vtime_accounting_enabled_cpu(int cpu)
 {
-	if (vtime_accounting_enabled()) {
-		if (context_tracking_cpu_is_enabled())
-			return true;
-	}
-
-	return false;
+	return context_tracking_enabled_cpu(cpu);
 }
-#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
-static inline bool vtime_accounting_cpu_enabled(void) { return false; }
-#endif
 
+static inline bool vtime_accounting_enabled_this_cpu(void)
+{
+	return context_tracking_enabled_this_cpu();
+}
 
-/*
- * Common vtime APIs
- */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void vtime_task_switch_generic(struct task_struct *prev);
 
-#ifdef __ARCH_HAS_VTIME_TASK_SWITCH
-extern void vtime_task_switch(struct task_struct *prev);
-#else
-extern void vtime_common_task_switch(struct task_struct *prev);
 static inline void vtime_task_switch(struct task_struct *prev)
 {
-	if (vtime_accounting_cpu_enabled())
-		vtime_common_task_switch(prev);
+	if (vtime_accounting_enabled_this_cpu())
+		vtime_task_switch_generic(prev);
 }
-#endif /* __ARCH_HAS_VTIME_TASK_SWITCH */
-
-extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
 
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
+static inline bool vtime_accounting_enabled_cpu(int cpu) {return false; }
+static inline bool vtime_accounting_enabled_this_cpu(void) { return false; }
 static inline void vtime_task_switch(struct task_struct *prev) { }
-static inline void vtime_account_system(struct task_struct *tsk) { }
+
+#endif
+
+/*
+ * Common vtime APIs
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void vtime_account_kernel(struct task_struct *tsk);
+extern void vtime_account_idle(struct task_struct *tsk);
+#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
+static inline void vtime_account_kernel(struct task_struct *tsk) { }
 #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
@@ -86,7 +87,7 @@ extern void vtime_account_irq_enter(struct task_struct *tsk);
 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);
+	vtime_account_kernel(tsk);
 }
 extern void vtime_flush(struct task_struct *tsk);
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */