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

Pull scheduler updates from Ingo Molnar:

 - massive CPU hotplug rework (Thomas Gleixner)

 - improve migration fairness (Peter Zijlstra)

 - CPU load calculation updates/cleanups (Yuyang Du)

 - cpufreq updates (Steve Muckle)

 - nohz optimizations (Frederic Weisbecker)

 - switch_mm() micro-optimization on x86 (Andy Lutomirski)

 - ... lots of other enhancements, fixes and cleanups.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (66 commits)
  ARM: Hide finish_arch_post_lock_switch() from modules
  sched/core: Provide a tsk_nr_cpus_allowed() helper
  sched/core: Use tsk_cpus_allowed() instead of accessing ->cpus_allowed
  sched/loadavg: Fix loadavg artifacts on fully idle and on fully loaded systems
  sched/fair: Correct unit of load_above_capacity
  sched/fair: Clean up scale confusion
  sched/nohz: Fix affine unpinned timers mess
  sched/fair: Fix fairness issue on migration
  sched/core: Kill sched_class::task_waking to clean up the migration logic
  sched/fair: Prepare to fix fairness problems on migration
  sched/fair: Move record_wakee()
  sched/core: Fix comment typo in wake_q_add()
  sched/core: Remove unused variable
  sched: Make hrtick_notifier an explicit call
  sched/fair: Make ilb_notifier an explicit call
  sched/hotplug: Make activate() the last hotplug step
  sched/hotplug: Move migration CPU_DYING to sched_cpu_dying()
  sched/migration: Move CPU_ONLINE into scheduler state
  sched/migration: Move calc_load_migrate() into CPU_DYING
  sched/migration: Move prepare transition to SCHED_STARTING state
  ...

31 files changed, 1329 insertions, 927 deletions

diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index f52f297cb406..9857606dd7b7 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -1562,12 +1562,12 @@ Doing the same with chrt -r 5 and function-trace set.
   <idle>-0       3dN.1   12us : menu_hrtimer_cancel <-tick_nohz_idle_exit
   <idle>-0       3dN.1   12us : ktime_get <-tick_nohz_idle_exit
   <idle>-0       3dN.1   12us : tick_do_update_jiffies64 <-tick_nohz_idle_exit
-  <idle>-0       3dN.1   13us : update_cpu_load_nohz <-tick_nohz_idle_exit
-  <idle>-0       3dN.1   13us : _raw_spin_lock <-update_cpu_load_nohz
+  <idle>-0       3dN.1   13us : cpu_load_update_nohz <-tick_nohz_idle_exit
+  <idle>-0       3dN.1   13us : _raw_spin_lock <-cpu_load_update_nohz
   <idle>-0       3dN.1   13us : add_preempt_count <-_raw_spin_lock
-  <idle>-0       3dN.2   13us : __update_cpu_load <-update_cpu_load_nohz
-  <idle>-0       3dN.2   14us : sched_avg_update <-__update_cpu_load
-  <idle>-0       3dN.2   14us : _raw_spin_unlock <-update_cpu_load_nohz
+  <idle>-0       3dN.2   13us : __cpu_load_update <-cpu_load_update_nohz
+  <idle>-0       3dN.2   14us : sched_avg_update <-__cpu_load_update
+  <idle>-0       3dN.2   14us : _raw_spin_unlock <-cpu_load_update_nohz
   <idle>-0       3dN.2   14us : sub_preempt_count <-_raw_spin_unlock
   <idle>-0       3dN.1   15us : calc_load_exit_idle <-tick_nohz_idle_exit
   <idle>-0       3dN.1   15us : touch_softlockup_watchdog <-tick_nohz_idle_exit
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index fa5b42d44985..3cc14dd8587c 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/arch/arm/include/asm/mmu_context.h
@@ -15,6 +15,7 @@
 
 #include <linux/compiler.h>
 #include <linux/sched.h>
+#include <linux/preempt.h>
 #include <asm/cacheflush.h>
 #include <asm/cachetype.h>
 #include <asm/proc-fns.h>
@@ -66,6 +67,7 @@ static inline void check_and_switch_context(struct mm_struct *mm,
 		cpu_switch_mm(mm->pgd, mm);
 }
 
+#ifndef MODULE
 #define finish_arch_post_lock_switch \
 	finish_arch_post_lock_switch
 static inline void finish_arch_post_lock_switch(void)
@@ -87,6 +89,7 @@ static inline void finish_arch_post_lock_switch(void)
 		preempt_enable_no_resched();
 	}
 }
+#endif /* !MODULE */
 
 #endif	/* CONFIG_MMU */
 
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 8cac1eb41466..55c924b65f71 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -565,7 +565,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 		smp_ops->give_timebase();
 
 	/* Wait until cpu puts itself in the online & active maps */
-	while (!cpu_online(cpu) || !cpu_active(cpu))
+	while (!cpu_online(cpu))
 		cpu_relax();
 
 	return 0;
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 40a6b4f9c36c..7b89a7572100 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -832,7 +832,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 	pcpu_attach_task(pcpu, tidle);
 	pcpu_start_fn(pcpu, smp_start_secondary, NULL);
 	/* Wait until cpu puts itself in the online & active maps */
-	while (!cpu_online(cpu) || !cpu_active(cpu))
+	while (!cpu_online(cpu))
 		cpu_relax();
 	return 0;
 }
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 5e5e76a52f58..b7080bef9137 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2183,7 +2183,7 @@ void arch_perf_update_userpage(struct perf_event *event,
 	 * cap_user_time_zero doesn't make sense when we're using a different
 	 * time base for the records.
 	 */
-	if (event->clock == &local_clock) {
+	if (!event->attr.use_clockid) {
 		userpg->cap_user_time_zero = 1;
 		userpg->time_zero = data->cyc2ns_offset;
 	}
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 84280029cafd..396348196aa7 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -115,103 +115,12 @@ static inline void destroy_context(struct mm_struct *mm)
 	destroy_context_ldt(mm);
 }
 
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
+extern void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+		      struct task_struct *tsk);
 
-	if (likely(prev != next)) {
-#ifdef CONFIG_SMP
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		this_cpu_write(cpu_tlbstate.active_mm, next);
-#endif
-		cpumask_set_cpu(cpu, mm_cpumask(next));
-
-		/*
-		 * Re-load page tables.
-		 *
-		 * This logic has an ordering constraint:
-		 *
-		 *  CPU 0: Write to a PTE for 'next'
-		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
-		 *  CPU 1: set bit 1 in next's mm_cpumask
-		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
-		 *
-		 * We need to prevent an outcome in which CPU 1 observes
-		 * the new PTE value and CPU 0 observes bit 1 clear in
-		 * mm_cpumask.  (If that occurs, then the IPI will never
-		 * be sent, and CPU 0's TLB will contain a stale entry.)
-		 *
-		 * The bad outcome can occur if either CPU's load is
-		 * reordered before that CPU's store, so both CPUs must
-		 * execute full barriers to prevent this from happening.
-		 *
-		 * Thus, switch_mm needs a full barrier between the
-		 * store to mm_cpumask and any operation that could load
-		 * from next->pgd.  TLB fills are special and can happen
-		 * due to instruction fetches or for no reason at all,
-		 * and neither LOCK nor MFENCE orders them.
-		 * Fortunately, load_cr3() is serializing and gives the
-		 * ordering guarantee we need.
-		 *
-		 */
-		load_cr3(next->pgd);
-
-		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-
-		/* Stop flush ipis for the previous mm */
-		cpumask_clear_cpu(cpu, mm_cpumask(prev));
-
-		/* Load per-mm CR4 state */
-		load_mm_cr4(next);
-
-#ifdef CONFIG_MODIFY_LDT_SYSCALL
-		/*
-		 * Load the LDT, if the LDT is different.
-		 *
-		 * It's possible that prev->context.ldt doesn't match
-		 * the LDT register.  This can happen if leave_mm(prev)
-		 * was called and then modify_ldt changed
-		 * prev->context.ldt but suppressed an IPI to this CPU.
-		 * In this case, prev->context.ldt != NULL, because we
-		 * never set context.ldt to NULL while the mm still
-		 * exists.  That means that next->context.ldt !=
-		 * prev->context.ldt, because mms never share an LDT.
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_mm_ldt(next);
-#endif
-	}
-#ifdef CONFIG_SMP
-	  else {
-		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
-
-		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
-			/*
-			 * On established mms, the mm_cpumask is only changed
-			 * from irq context, from ptep_clear_flush() while in
-			 * lazy tlb mode, and here. Irqs are blocked during
-			 * schedule, protecting us from simultaneous changes.
-			 */
-			cpumask_set_cpu(cpu, mm_cpumask(next));
-
-			/*
-			 * We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 *
-			 * As above, load_cr3() is serializing and orders TLB
-			 * fills with respect to the mm_cpumask write.
-			 */
-			load_cr3(next->pgd);
-			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-			load_mm_cr4(next);
-			load_mm_ldt(next);
-		}
-	}
-#endif
-}
+extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			       struct task_struct *tsk);
+#define switch_mm_irqs_off switch_mm_irqs_off
 
 #define activate_mm(prev, next)			\
 do {						\
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index f98913258c63..62c0043a5fd5 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -2,7 +2,7 @@
 KCOV_INSTRUMENT_tlb.o	:= n
 
 obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
-	    pat.o pgtable.o physaddr.o gup.o setup_nx.o
+	    pat.o pgtable.o physaddr.o gup.o setup_nx.o tlb.o
 
 # Make sure __phys_addr has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
@@ -12,7 +12,6 @@ CFLAGS_setup_nx.o		:= $(nostackp)
 CFLAGS_fault.o := -I$(src)/../include/asm/trace
 
 obj-$(CONFIG_X86_PAT)		+= pat_rbtree.o
-obj-$(CONFIG_SMP)		+= tlb.o
 
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index fe9b9f776361..5643fd0b1a7d 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -28,6 +28,8 @@
  *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
+#ifdef CONFIG_SMP
+
 struct flush_tlb_info {
 	struct mm_struct *flush_mm;
 	unsigned long flush_start;
@@ -57,6 +59,118 @@ void leave_mm(int cpu)
 }
 EXPORT_SYMBOL_GPL(leave_mm);
 
+#endif /* CONFIG_SMP */
+
+void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	       struct task_struct *tsk)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	switch_mm_irqs_off(prev, next, tsk);
+	local_irq_restore(flags);
+}
+
+void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
+			struct task_struct *tsk)
+{
+	unsigned cpu = smp_processor_id();
+
+	if (likely(prev != next)) {
+#ifdef CONFIG_SMP
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		this_cpu_write(cpu_tlbstate.active_mm, next);
+#endif
+		cpumask_set_cpu(cpu, mm_cpumask(next));
+
+		/*
+		 * Re-load page tables.
+		 *
+		 * This logic has an ordering constraint:
+		 *
+		 *  CPU 0: Write to a PTE for 'next'
+		 *  CPU 0: load bit 1 in mm_cpumask.  if nonzero, send IPI.
+		 *  CPU 1: set bit 1 in next's mm_cpumask
+		 *  CPU 1: load from the PTE that CPU 0 writes (implicit)
+		 *
+		 * We need to prevent an outcome in which CPU 1 observes
+		 * the new PTE value and CPU 0 observes bit 1 clear in
+		 * mm_cpumask.  (If that occurs, then the IPI will never
+		 * be sent, and CPU 0's TLB will contain a stale entry.)
+		 *
+		 * The bad outcome can occur if either CPU's load is
+		 * reordered before that CPU's store, so both CPUs must
+		 * execute full barriers to prevent this from happening.
+		 *
+		 * Thus, switch_mm needs a full barrier between the
+		 * store to mm_cpumask and any operation that could load
+		 * from next->pgd.  TLB fills are special and can happen
+		 * due to instruction fetches or for no reason at all,
+		 * and neither LOCK nor MFENCE orders them.
+		 * Fortunately, load_cr3() is serializing and gives the
+		 * ordering guarantee we need.
+		 *
+		 */
+		load_cr3(next->pgd);
+
+		trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+
+		/* Stop flush ipis for the previous mm */
+		cpumask_clear_cpu(cpu, mm_cpumask(prev));
+
+		/* Load per-mm CR4 state */
+		load_mm_cr4(next);
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+		/*
+		 * Load the LDT, if the LDT is different.
+		 *
+		 * It's possible that prev->context.ldt doesn't match
+		 * the LDT register.  This can happen if leave_mm(prev)
+		 * was called and then modify_ldt changed
+		 * prev->context.ldt but suppressed an IPI to this CPU.
+		 * In this case, prev->context.ldt != NULL, because we
+		 * never set context.ldt to NULL while the mm still
+		 * exists.  That means that next->context.ldt !=
+		 * prev->context.ldt, because mms never share an LDT.
+		 */
+		if (unlikely(prev->context.ldt != next->context.ldt))
+			load_mm_ldt(next);
+#endif
+	}
+#ifdef CONFIG_SMP
+	  else {
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
+
+		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+			/*
+			 * On established mms, the mm_cpumask is only changed
+			 * from irq context, from ptep_clear_flush() while in
+			 * lazy tlb mode, and here. Irqs are blocked during
+			 * schedule, protecting us from simultaneous changes.
+			 */
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+
+			/*
+			 * We were in lazy tlb mode and leave_mm disabled
+			 * tlb flush IPI delivery. We must reload CR3
+			 * to make sure to use no freed page tables.
+			 *
+			 * As above, load_cr3() is serializing and orders TLB
+			 * fills with respect to the mm_cpumask write.
+			 */
+			load_cr3(next->pgd);
+			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+			load_mm_cr4(next);
+			load_mm_ldt(next);
+		}
+	}
+#endif
+}
+
+#ifdef CONFIG_SMP
+
 /*
  * The flush IPI assumes that a thread switch happens in this order:
  * [cpu0: the cpu that switches]
@@ -353,3 +467,5 @@ static int __init create_tlb_single_page_flush_ceiling(void)
 	return 0;
 }
 late_initcall(create_tlb_single_page_flush_ceiling);
+
+#endif /* CONFIG_SMP */
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index f9b1fab4388a..21597dcac0e2 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -59,25 +59,7 @@ struct notifier_block;
  * CPU notifier priorities.
  */
 enum {
-	/*
-	 * SCHED_ACTIVE marks a cpu which is coming up active during
-	 * CPU_ONLINE and CPU_DOWN_FAILED and must be the first
-	 * notifier.  CPUSET_ACTIVE adjusts cpuset according to
-	 * cpu_active mask right after SCHED_ACTIVE.  During
-	 * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are
-	 * ordered in the similar way.
-	 *
-	 * This ordering guarantees consistent cpu_active mask and
-	 * migration behavior to all cpu notifiers.
-	 */
-	CPU_PRI_SCHED_ACTIVE	= INT_MAX,
-	CPU_PRI_CPUSET_ACTIVE	= INT_MAX - 1,
-	CPU_PRI_SCHED_INACTIVE	= INT_MIN + 1,
-	CPU_PRI_CPUSET_INACTIVE	= INT_MIN,
-
-	/* migration should happen before other stuff but after perf */
 	CPU_PRI_PERF		= 20,
-	CPU_PRI_MIGRATION	= 10,
 
 	/* bring up workqueues before normal notifiers and down after */
 	CPU_PRI_WORKQUEUE_UP	= 5,
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 5d68e15e46b7..386374d19987 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -8,6 +8,7 @@ enum cpuhp_state {
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
 	CPUHP_AP_OFFLINE,
+	CPUHP_AP_SCHED_STARTING,
 	CPUHP_AP_NOTIFY_STARTING,
 	CPUHP_AP_ONLINE,
 	CPUHP_TEARDOWN_CPU,
@@ -16,6 +17,7 @@ enum cpuhp_state {
 	CPUHP_AP_NOTIFY_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
+	CPUHP_AP_ACTIVE,
 	CPUHP_ONLINE,
 };
 
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 40cee6b77a93..e828cf65d7df 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -743,12 +743,10 @@ set_cpu_present(unsigned int cpu, bool present)
 static inline void
 set_cpu_online(unsigned int cpu, bool online)
 {
-	if (online) {
+	if (online)
 		cpumask_set_cpu(cpu, &__cpu_online_mask);
-		cpumask_set_cpu(cpu, &__cpu_active_mask);
-	} else {
+	else
 		cpumask_clear_cpu(cpu, &__cpu_online_mask);
-	}
 }
 
 static inline void
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index f75222ea7f16..eabe0138eb06 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -356,8 +356,13 @@ extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask);
 extern void lockdep_clear_current_reclaim_state(void);
 extern void lockdep_trace_alloc(gfp_t mask);
 
-extern void lock_pin_lock(struct lockdep_map *lock);
-extern void lock_unpin_lock(struct lockdep_map *lock);
+struct pin_cookie { unsigned int val; };
+
+#define NIL_COOKIE (struct pin_cookie){ .val = 0U, }
+
+extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock);
+extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie);
+extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 
 # define INIT_LOCKDEP				.lockdep_recursion = 0, .lockdep_reclaim_gfp = 0,
 
@@ -373,8 +378,9 @@ extern void lock_unpin_lock(struct lockdep_map *lock);
 
 #define lockdep_recursing(tsk)	((tsk)->lockdep_recursion)
 
-#define lockdep_pin_lock(l)		lock_pin_lock(&(l)->dep_map)
-#define lockdep_unpin_lock(l)	lock_unpin_lock(&(l)->dep_map)
+#define lockdep_pin_lock(l)	lock_pin_lock(&(l)->dep_map)
+#define lockdep_repin_lock(l,c)	lock_repin_lock(&(l)->dep_map, (c))
+#define lockdep_unpin_lock(l,c)	lock_unpin_lock(&(l)->dep_map, (c))
 
 #else /* !CONFIG_LOCKDEP */
 
@@ -427,8 +433,13 @@ struct lock_class_key { };
 
 #define lockdep_recursing(tsk)			(0)
 
-#define lockdep_pin_lock(l)				do { (void)(l); } while (0)
-#define lockdep_unpin_lock(l)			do { (void)(l); } while (0)
+struct pin_cookie { };
+
+#define NIL_COOKIE (struct pin_cookie){ }
+
+#define lockdep_pin_lock(l)			({ struct pin_cookie cookie; cookie; })
+#define lockdep_repin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
+#define lockdep_unpin_lock(l, c)		do { (void)(l); (void)(c); } while (0)
 
 #endif /* !LOCKDEP */
 
diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h
index 70fffeba7495..a4441784503b 100644
--- a/include/linux/mmu_context.h
+++ b/include/linux/mmu_context.h
@@ -1,9 +1,16 @@
 #ifndef _LINUX_MMU_CONTEXT_H
 #define _LINUX_MMU_CONTEXT_H
 
+#include <asm/mmu_context.h>
+
 struct mm_struct;
 
 void use_mm(struct mm_struct *mm);
 void unuse_mm(struct mm_struct *mm);
 
+/* Architectures that care about IRQ state in switch_mm can override this. */
+#ifndef switch_mm_irqs_off
+# define switch_mm_irqs_off switch_mm
+#endif
+
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e8dfa6f0d843..6cc0df970f1a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -177,9 +177,11 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load);
 extern void calc_global_load(unsigned long ticks);
 
 #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
-extern void update_cpu_load_nohz(int active);
+extern void cpu_load_update_nohz_start(void);
+extern void cpu_load_update_nohz_stop(void);
 #else
-static inline void update_cpu_load_nohz(int active) { }
+static inline void cpu_load_update_nohz_start(void) { }
+static inline void cpu_load_update_nohz_stop(void) { }
 #endif
 
 extern void dump_cpu_task(int cpu);
@@ -371,6 +373,15 @@ extern void cpu_init (void);
 extern void trap_init(void);
 extern void update_process_times(int user);
 extern void scheduler_tick(void);
+extern int sched_cpu_starting(unsigned int cpu);
+extern int sched_cpu_activate(unsigned int cpu);
+extern int sched_cpu_deactivate(unsigned int cpu);
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern int sched_cpu_dying(unsigned int cpu);
+#else
+# define sched_cpu_dying	NULL
+#endif
 
 extern void sched_show_task(struct task_struct *p);
 
@@ -934,9 +945,19 @@ enum cpu_idle_type {
 };
 
 /*
+ * Integer metrics need fixed point arithmetic, e.g., sched/fair
+ * has a few: load, load_avg, util_avg, freq, and capacity.
+ *
+ * We define a basic fixed point arithmetic range, and then formalize
+ * all these metrics based on that basic range.
+ */
+# define SCHED_FIXEDPOINT_SHIFT	10
+# define SCHED_FIXEDPOINT_SCALE	(1L << SCHED_FIXEDPOINT_SHIFT)
+
+/*
  * Increase resolution of cpu_capacity calculations
  */
-#define SCHED_CAPACITY_SHIFT	10
+#define SCHED_CAPACITY_SHIFT	SCHED_FIXEDPOINT_SHIFT
 #define SCHED_CAPACITY_SCALE	(1L << SCHED_CAPACITY_SHIFT)
 
 /*
@@ -1198,18 +1219,56 @@ struct load_weight {
 };
 
 /*
- * The load_avg/util_avg accumulates an infinite geometric series.
- * 1) load_avg factors frequency scaling into 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 and cpu 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
+ * The load_avg/util_avg accumulates an infinite geometric series
+ * (see __update_load_avg() in kernel/sched/fair.c).
+ *
+ * [load_avg definition]
+ *
+ *   load_avg = runnable% * scale_load_down(load)
+ *
+ * where runnable% is the time ratio that a sched_entity is runnable.
+ * For cfs_rq, it is the aggregated load_avg 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
+ *
+ * load_avg may also take frequency scaling into account:
+ *
+ *   load_avg = runnable% * scale_load_down(load) * freq%
+ *
+ * where freq% is the CPU frequency normalized to the highest frequency.
+ *
+ * [util_avg definition]
+ *
+ *   util_avg = running% * SCHED_CAPACITY_SCALE
+ *
+ * where running% is the time ratio that a sched_entity is running on
+ * a CPU. For cfs_rq, it is the aggregated util_avg of all runnable
+ * and blocked sched_entities.
+ *
+ * util_avg may also factor frequency scaling and CPU capacity scaling:
+ *
+ *   util_avg = running% * SCHED_CAPACITY_SCALE * freq% * capacity%
+ *
+ * where freq% is the same as above, and capacity% is the CPU capacity
+ * normalized to the greatest capacity (due to uarch differences, etc).
+ *
+ * N.B., the above ratios (runnable%, running%, freq%, and capacity%)
+ * themselves are in the range of [0, 1]. To do fixed point arithmetics,
+ * we therefore scale them to as large a range as necessary. This is for
+ * example reflected by util_avg's SCHED_CAPACITY_SCALE.
+ *
+ * [Overflow issue]
+ *
+ * The 64-bit load_sum can have 4353082796 (=2^64/47742/88761) entities
+ * with the highest load (=88761), always runnable on a single cfs_rq,
+ * and should not overflow as the number already hits PID_MAX_LIMIT.
+ *
+ * For all other cases (including 32-bit kernels), struct load_weight's
+ * weight will overflow first before we do, because:
+ *
+ *    Max(load_avg) <= Max(load.weight)
+ *
+ * Then it is the load_weight's responsibility to consider overflow
+ * issues.
  */
 struct sched_avg {
 	u64 last_update_time, load_sum;
@@ -1871,6 +1930,11 @@ extern int arch_task_struct_size __read_mostly;
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
+static inline int tsk_nr_cpus_allowed(struct task_struct *p)
+{
+	return p->nr_cpus_allowed;
+}
+
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
 #define TNF_SHARED	0x04
@@ -2303,8 +2367,6 @@ extern unsigned long long notrace sched_clock(void);
 /*
  * See the comment in kernel/sched/clock.c
  */
-extern u64 cpu_clock(int cpu);
-extern u64 local_clock(void);
 extern u64 running_clock(void);
 extern u64 sched_clock_cpu(int cpu);
 
@@ -2323,6 +2385,16 @@ static inline void sched_clock_idle_sleep_event(void)
 static inline void sched_clock_idle_wakeup_event(u64 delta_ns)
 {
 }
+
+static inline u64 cpu_clock(int cpu)
+{
+	return sched_clock();
+}
+
+static inline u64 local_clock(void)
+{
+	return sched_clock();
+}
 #else
 /*
  * Architectures can set this to 1 if they have specified
@@ -2337,6 +2409,26 @@ extern void clear_sched_clock_stable(void);
 extern void sched_clock_tick(void);
 extern void sched_clock_idle_sleep_event(void);
 extern void sched_clock_idle_wakeup_event(u64 delta_ns);
+
+/*
+ * As outlined in clock.c, provides a fast, high resolution, nanosecond
+ * time source that is monotonic per cpu argument and has bounded drift
+ * between cpus.
+ *
+ * ######################### BIG FAT WARNING ##########################
+ * # when comparing cpu_clock(i) to cpu_clock(j) for i != j, time can #
+ * # go backwards !!                                                  #
+ * ####################################################################
+ */
+static inline u64 cpu_clock(int cpu)
+{
+	return sched_clock_cpu(cpu);
+}
+
+static inline u64 local_clock(void)
+{
+	return sched_clock_cpu(raw_smp_processor_id());
+}
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 3e3f6e49eabb..d948e44c471e 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -703,21 +703,6 @@ static int takedown_cpu(unsigned int cpu)
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	int err;
 
-	/*
-	 * By now we've cleared cpu_active_mask, wait for all preempt-disabled
-	 * and RCU users of this state to go away such that all new such users
-	 * will observe it.
-	 *
-	 * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
-	 * not imply sync_sched(), so wait for both.
-	 *
-	 * Do sync before park smpboot threads to take care the rcu boost case.
-	 */
-	if (IS_ENABLED(CONFIG_PREEMPT))
-		synchronize_rcu_mult(call_rcu, call_rcu_sched);
-	else
-		synchronize_rcu();
-
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
 	smpboot_park_threads(cpu);
@@ -923,8 +908,6 @@ void cpuhp_online_idle(enum cpuhp_state state)
 
 	st->state = CPUHP_AP_ONLINE_IDLE;
 
-	/* The cpu is marked online, set it active now */
-	set_cpu_active(cpu, true);
 	/* Unpark the stopper thread and the hotplug thread of this cpu */
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
@@ -1236,6 +1219,12 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 		.name			= "ap:offline",
 		.cant_stop		= true,
 	},
+	/* First state is scheduler control. Interrupts are disabled */
+	[CPUHP_AP_SCHED_STARTING] = {
+		.name			= "sched:starting",
+		.startup		= sched_cpu_starting,
+		.teardown		= sched_cpu_dying,
+	},
 	/*</