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 main changes in this (fairly busy) cycle were:

   - There was a class of scheduler bugs related to forgetting to update
     the rq-clock timestamp which can cause weird and hard to debug
     problems, so there's a new debug facility for this: which uncovered
     a whole lot of bugs which convinced us that we want to keep the
     debug facility.

     (Peter Zijlstra, Matt Fleming)

   - Various cputime related updates: eliminate cputime and use u64
     nanoseconds directly, simplify and improve the arch interfaces,
     implement delayed accounting more widely, etc. - (Frederic
     Weisbecker)

   - Move code around for better structure plus cleanups (Ingo Molnar)

   - Move IO schedule accounting deeper into the scheduler plus related
     changes to improve the situation (Tejun Heo)

   - ... plus a round of sched/rt and sched/deadline fixes, plus other
     fixes, updats and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (85 commits)
  sched/core: Remove unlikely() annotation from sched_move_task()
  sched/autogroup: Rename auto_group.[ch] to autogroup.[ch]
  sched/topology: Split out scheduler topology code from core.c into topology.c
  sched/core: Remove unnecessary #include headers
  sched/rq_clock: Consolidate the ordering of the rq_clock methods
  delayacct: Include <uapi/linux/taskstats.h>
  sched/core: Clean up comments
  sched/rt: Show the 'sched_rr_timeslice' SCHED_RR timeslice tuning knob in milliseconds
  sched/clock: Add dummy clear_sched_clock_stable() stub function
  sched/cputime: Remove generic asm headers
  sched/cputime: Remove unused nsec_to_cputime()
  s390, sched/cputime: Remove unused cputime definitions
  powerpc, sched/cputime: Remove unused cputime definitions
  s390, sched/cputime: Make arch_cpu_idle_time() to return nsecs
  ia64, sched/cputime: Remove unused cputime definitions
  ia64: Convert vtime to use nsec units directly
  ia64, sched/cputime: Move the nsecs based cputime headers to the last arch using it
  sched/cputime: Remove jiffies based cputime
  sched/cputime, vtime: Return nsecs instead of cputime_t to account
  sched/cputime: Complete nsec conversion of tick based accounting
  ...

17 files changed, 2406 insertions, 2203 deletions

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 5e59b832ae2b..89ab6758667b 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -18,8 +18,8 @@ endif
 obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o
 obj-y += wait.o swait.o completion.o idle.o
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o
-obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o
+obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
 obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
diff --git a/kernel/sched/auto_group.c b/kernel/sched/autogroup.c
index da39489d2d80..da39489d2d80 100644
--- a/kernel/sched/auto_group.c
+++ b/kernel/sched/autogroup.c
diff --git a/kernel/sched/auto_group.h b/kernel/sched/autogroup.h
index 890c95f2587a..890c95f2587a 100644
--- a/kernel/sched/auto_group.h
+++ b/kernel/sched/autogroup.h
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e85a725e5c34..ad64efe41722 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -77,41 +77,88 @@ EXPORT_SYMBOL_GPL(sched_clock);
 
 __read_mostly int sched_clock_running;
 
+void sched_clock_init(void)
+{
+	sched_clock_running = 1;
+}
+
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
-static struct static_key __sched_clock_stable = STATIC_KEY_INIT;
-static int __sched_clock_stable_early;
+/*
+ * We must start with !__sched_clock_stable because the unstable -> stable
+ * transition is accurate, while the stable -> unstable transition is not.
+ *
+ * Similarly we start with __sched_clock_stable_early, thereby assuming we
+ * will become stable, such that there's only a single 1 -> 0 transition.
+ */
+static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable);
+static int __sched_clock_stable_early = 1;
 
-int sched_clock_stable(void)
+/*
+ * We want: ktime_get_ns() + gtod_offset == sched_clock() + raw_offset
+ */
+static __read_mostly u64 raw_offset;
+static __read_mostly u64 gtod_offset;
+
+struct sched_clock_data {
+	u64			tick_raw;
+	u64			tick_gtod;
+	u64			clock;
+};
+
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
+
+static inline struct sched_clock_data *this_scd(void)
 {
-	return static_key_false(&__sched_clock_stable);
+	return this_cpu_ptr(&sched_clock_data);
 }
 
-static void __set_sched_clock_stable(void)
+static inline struct sched_clock_data *cpu_sdc(int cpu)
 {
-	if (!sched_clock_stable())
-		static_key_slow_inc(&__sched_clock_stable);
+	return &per_cpu(sched_clock_data, cpu);
+}
 
-	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
+int sched_clock_stable(void)
+{
+	return static_branch_likely(&__sched_clock_stable);
 }
 
-void set_sched_clock_stable(void)
+static void __set_sched_clock_stable(void)
 {
-	__sched_clock_stable_early = 1;
+	struct sched_clock_data *scd = this_scd();
 
-	smp_mb(); /* matches sched_clock_init() */
+	/*
+	 * Attempt to make the (initial) unstable->stable transition continuous.
+	 */
+	raw_offset = (scd->tick_gtod + gtod_offset) - (scd->tick_raw);
 
-	if (!sched_clock_running)
-		return;
+	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
+			scd->tick_gtod, gtod_offset,
+			scd->tick_raw,  raw_offset);
 
-	__set_sched_clock_stable();
+	static_branch_enable(&__sched_clock_stable);
+	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
 static void __clear_sched_clock_stable(struct work_struct *work)
 {
-	/* XXX worry about clock continuity */
-	if (sched_clock_stable())
-		static_key_slow_dec(&__sched_clock_stable);
+	struct sched_clock_data *scd = this_scd();
+
+	/*
+	 * Attempt to make the stable->unstable transition continuous.
+	 *
+	 * Trouble is, this is typically called from the TSC watchdog
+	 * timer, which is late per definition. This means the tick
+	 * values can already be screwy.
+	 *
+	 * Still do what we can.
+	 */
+	gtod_offset = (scd->tick_raw + raw_offset) - (scd->tick_gtod);
+
+	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+			scd->tick_gtod, gtod_offset,
+			scd->tick_raw,  raw_offset);
 
+	static_branch_disable(&__sched_clock_stable);
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
@@ -121,47 +168,15 @@ void clear_sched_clock_stable(void)
 {
 	__sched_clock_stable_early = 0;
 
-	smp_mb(); /* matches sched_clock_init() */
-
-	if (!sched_clock_running)
-		return;
+	smp_mb(); /* matches sched_clock_init_late() */
 
-	schedule_work(&sched_clock_work);
+	if (sched_clock_running == 2)
+		schedule_work(&sched_clock_work);
 }
 
-struct sched_clock_data {
-	u64			tick_raw;
-	u64			tick_gtod;
-	u64			clock;
-};
-
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
-
-static inline struct sched_clock_data *this_scd(void)
+void sched_clock_init_late(void)
 {
-	return this_cpu_ptr(&sched_clock_data);
-}
-
-static inline struct sched_clock_data *cpu_sdc(int cpu)
-{
-	return &per_cpu(sched_clock_data, cpu);
-}
-
-void sched_clock_init(void)
-{
-	u64 ktime_now = ktime_to_ns(ktime_get());
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct sched_clock_data *scd = cpu_sdc(cpu);
-
-		scd->tick_raw = 0;
-		scd->tick_gtod = ktime_now;
-		scd->clock = ktime_now;
-	}
-
-	sched_clock_running = 1;
-
+	sched_clock_running = 2;
 	/*
 	 * Ensure that it is impossible to not do a static_key update.
 	 *
@@ -173,8 +188,6 @@ void sched_clock_init(void)
 
 	if (__sched_clock_stable_early)
 		__set_sched_clock_stable();
-	else
-		__clear_sched_clock_stable(NULL);
 }
 
 /*
@@ -216,7 +229,7 @@ again:
 	 *		      scd->tick_gtod + TICK_NSEC);
 	 */
 
-	clock = scd->tick_gtod + delta;
+	clock = scd->tick_gtod + gtod_offset + delta;
 	min_clock = wrap_max(scd->tick_gtod, old_clock);
 	max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC);
 
@@ -302,7 +315,7 @@ u64 sched_clock_cpu(int cpu)
 	u64 clock;
 
 	if (sched_clock_stable())
-		return sched_clock();
+		return sched_clock() + raw_offset;
 
 	if (unlikely(!sched_clock_running))
 		return 0ull;
@@ -323,23 +336,22 @@ EXPORT_SYMBOL_GPL(sched_clock_cpu);
 void sched_clock_tick(void)
 {
 	struct sched_clock_data *scd;
-	u64 now, now_gtod;
-
-	if (sched_clock_stable())
-		return;
-
-	if (unlikely(!sched_clock_running))
-		return;
 
 	WARN_ON_ONCE(!irqs_disabled());
 
+	/*
+	 * Update these values even if sched_clock_stable(), because it can
+	 * become unstable at any point in time at which point we need some
+	 * values to fall back on.
+	 *
+	 * XXX arguably we can skip this if we expose tsc_clocksource_reliable
+	 */
 	scd = this_scd();
-	now_gtod = ktime_to_ns(ktime_get());
-	now = sched_clock();
+	scd->tick_raw  = sched_clock();
+	scd->tick_gtod = ktime_get_ns();
 
-	scd->tick_raw = now;
-	scd->tick_gtod = now_gtod;
-	sched_clock_local(scd);
+	if (!sched_clock_stable() && likely(sched_clock_running))
+		sched_clock_local(scd);
 }
 
 /*
@@ -366,11 +378,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
-void sched_clock_init(void)
-{
-	sched_clock_running = 1;
-}
-
 u64 sched_clock_cpu(int cpu)
 {
 	if (unlikely(!sched_clock_running))
@@ -378,6 +385,7 @@ u64 sched_clock_cpu(int cpu)
 
 	return sched_clock();
 }
+
 #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
 /*
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 8d0f35debf35..f063a25d4449 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -31,7 +31,8 @@ void complete(struct completion *x)
 	unsigned long flags;
 
 	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done++;
+	if (x->done != UINT_MAX)
+		x->done++;
 	__wake_up_locked(&x->wait, TASK_NORMAL, 1);
 	spin_unlock_irqrestore(&x->wait.lock, flags);
 }
@@ -51,7 +52,7 @@ void complete_all(struct completion *x)
 	unsigned long flags;
 
 	spin_lock_irqsave(&x->wait.lock, flags);
-	x->done += UINT_MAX/2;
+	x->done = UINT_MAX;
 	__wake_up_locked(&x->wait, TASK_NORMAL, 0);
 	spin_unlock_irqrestore(&x->wait.lock, flags);
 }
@@ -79,7 +80,8 @@ do_wait_for_common(struct completion *x,
 		if (!x->done)
 			return timeout;
 	}
-	x->done--;
+	if (x->done != UINT_MAX)
+		x->done--;
 	return timeout ?: 1;
 }
 
@@ -280,7 +282,7 @@ bool try_wait_for_completion(struct completion *x)
 	spin_lock_irqsave(&x->wait.lock, flags);
 	if (!x->done)
 		ret = 0;
-	else
+	else if (x->done != UINT_MAX)
 		x->done--;
 	spin_unlock_irqrestore(&x->wait.lock, flags);
 	return ret;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c56fb57f2991..34e2291a9a6c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1,88 +1,28 @@
 /*
  *  kernel/sched/core.c
  *
- *  Kernel scheduler and related syscalls
+ *  Core kernel scheduler code and related syscalls
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
- *
- *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
- *		make semaphores SMP safe
- *  1998-11-19	Implemented schedule_timeout() and related stuff
- *		by Andrea Arcangeli
- *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
- *		hybrid priority-list and round-robin design with
- *		an array-switch method of distributing timeslices
- *		and per-CPU runqueues.  Cleanups and useful suggestions
- *		by Davide Libenzi, preemptible kernel bits by Robert Love.
- *  2003-09-03	Interactivity tuning by Con Kolivas.
- *  2004-04-02	Scheduler domains code by Nick Piggin
- *  2007-04-15  Work begun on replacing all interactivity tuning with a
- *              fair scheduling design by Con Kolivas.
- *  2007-05-05  Load balancing (smp-nice) and other improvements
- *              by Peter Williams
- *  2007-05-06  Interactivity improvements to CFS by Mike Galbraith
- *  2007-07-01  Group scheduling enhancements by Srivatsa Vaddagiri
- *  2007-11-29  RT balancing improvements by Steven Rostedt, Gregory Haskins,
- *              Thomas Gleixner, Mike Kravetz
  */
-
-#include <linux/kasan.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/nmi.h>
-#include <linux/init.h>
-#include <linux/uaccess.h>
-#include <linux/highmem.h>
-#include <linux/mmu_context.h>
-#include <linux/interrupt.h>
-#include <linux/capability.h>
-#include <linux/completion.h>
-#include <linux/kernel_stat.h>
-#include <linux/debug_locks.h>
-#include <linux/perf_event.h>
-#include <linux/security.h>
-#include <linux/notifier.h>
-#include <linux/profile.h>
-#include <linux/freezer.h>
-#include <linux/vmalloc.h>
-#include <linux/blkdev.h>
-#include <linux/delay.h>
-#include <linux/pid_namespace.h>
-#include <linux/smp.h>
-#include <linux/threads.h>
-#include <linux/timer.h>
-#include <linux/rcupdate.h>
-#include <linux/cpu.h>
+#include <linux/sched.h>
 #include <linux/cpuset.h>
-#include <linux/percpu.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/sysctl.h>
-#include <linux/syscalls.h>
-#include <linux/times.h>
-#include <linux/tsacct_kern.h>
-#include <linux/kprobes.h>
 #include <linux/delayacct.h>
-#include <linux/unistd.h>
-#include <linux/pagemap.h>
-#include <linux/hrtimer.h>
-#include <linux/tick.h>
-#include <linux/ctype.h>
-#include <linux/ftrace.h>
-#include <linux/slab.h>
 #include <linux/init_task.h>
 #include <linux/context_tracking.h>
-#include <linux/compiler.h>
-#include <linux/frame.h>
+
+#include <linux/blkdev.h>
+#include <linux/kprobes.h>
+#include <linux/mmu_context.h>
+#include <linux/module.h>
+#include <linux/nmi.h>
 #include <linux/prefetch.h>
-#include <linux/mutex.h>
+#include <linux/profile.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
-#include <asm/irq_regs.h>
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#endif
 
 #include "sched.h"
 #include "../workqueue_internal.h"
@@ -91,27 +31,8 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
-DEFINE_MUTEX(sched_domains_mutex);
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
-static void update_rq_clock_task(struct rq *rq, s64 delta);
-
-void update_rq_clock(struct rq *rq)
-{
-	s64 delta;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (rq->clock_skip_update & RQCF_ACT_SKIP)
-		return;
-
-	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
-	if (delta < 0)
-		return;
-	rq->clock += delta;
-	update_rq_clock_task(rq, delta);
-}
-
 /*
  * Debugging: various feature bits
  */
@@ -140,7 +61,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32;
 const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
 
 /*
- * period over which we measure -rt task cpu usage in us.
+ * period over which we measure -rt task CPU usage in us.
  * default: 1s
  */
 unsigned int sysctl_sched_rt_period = 1000000;
@@ -153,7 +74,7 @@ __read_mostly int scheduler_running;
  */
 int sysctl_sched_rt_runtime = 950000;
 
-/* cpus with isolated domains */
+/* CPUs with isolated domains */
 cpumask_var_t cpu_isolated_map;
 
 /*
@@ -185,7 +106,7 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		rq = task_rq(p);
 		raw_spin_lock(&rq->lock);
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			rf->cookie = lockdep_pin_lock(&rq->lock);
+			rq_pin_lock(rq, rf);
 			return rq;
 		}
 		raw_spin_unlock(&rq->lock);
@@ -221,11 +142,11 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		 * If we observe the old cpu in task_rq_lock, the acquire of
 		 * the old rq->lock will fully serialize against the stores.
 		 *
-		 * If we observe the new cpu in task_rq_lock, the acquire will
+		 * If we observe the new CPU in task_rq_lock, the acquire will
 		 * pair with the WMB to ensure we must then also see migrating.
 		 */
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-			rf->cookie = lockdep_pin_lock(&rq->lock);
+			rq_pin_lock(rq, rf);
 			return rq;
 		}
 		raw_spin_unlock(&rq->lock);
@@ -236,6 +157,84 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	}
 }
 
+/*
+ * RQ-clock updating methods:
+ */
+
+static void update_rq_clock_task(struct rq *rq, s64 delta)
+{
+/*
+ * In theory, the compile should just see 0 here, and optimize out the call
+ * to sched_rt_avg_update. But I don't trust it...
+ */
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	s64 steal = 0, irq_delta = 0;
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+	/*
+	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
+	 * this case when a previous update_rq_clock() happened inside a
+	 * {soft,}irq region.
+	 *
+	 * When this happens, we stop ->clock_task and only update the
+	 * prev_irq_time stamp to account for the part that fit, so that a next
+	 * update will consume the rest. This ensures ->clock_task is
+	 * monotonic.
+	 *
+	 * It does however cause some slight miss-attribution of {soft,}irq
+	 * time, a more accurate solution would be to update the irq_time using
+	 * the current rq->clock timestamp, except that would require using
+	 * atomic ops.
+	 */
+	if (irq_delta > delta)
+		irq_delta = delta;
+
+	rq->prev_irq_time += irq_delta;
+	delta -= irq_delta;
+#endif
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	if (static_key_false((&paravirt_steal_rq_enabled))) {
+		steal = paravirt_steal_clock(cpu_of(rq));
+		steal -= rq->prev_steal_time_rq;
+
+		if (unlikely(steal > delta))
+			steal = delta;
+
+		rq->prev_steal_time_rq += steal;
+		delta -= steal;
+	}
+#endif
+
+	rq->clock_task += delta;
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
+		sched_rt_avg_update(rq, irq_delta + steal);
+#endif
+}
+
+void update_rq_clock(struct rq *rq)
+{
+	s64 delta;
+
+	lockdep_assert_held(&rq->lock);
+
+	if (rq->clock_update_flags & RQCF_ACT_SKIP)
+		return;
+
+#ifdef CONFIG_SCHED_DEBUG
+	rq->clock_update_flags |= RQCF_UPDATED;
+#endif
+	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+	if (delta < 0)
+		return;
+	rq->clock += delta;
+	update_rq_clock_task(rq, delta);
+}
+
+
 #ifdef CONFIG_SCHED_HRTICK
 /*
  * Use HR-timers to deliver accurate preemption points.
@@ -458,7 +457,7 @@ void wake_up_q(struct wake_q_head *head)
 
 		task = container_of(node, struct task_struct, wake_q);
 		BUG_ON(!task);
-		/* task can safely be re-inserted now */
+		/* Task can safely be re-inserted now: */
 		node = node->next;
 		task->wake_q.next = NULL;
 
@@ -516,12 +515,12 @@ void resched_cpu(int cpu)
 #ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ_COMMON
 /*
- * In the semi idle case, use the nearest busy cpu for migrating timers
- * from an idle cpu.  This is good for power-savings.
+ * In the semi idle case, use the nearest busy CPU for migrating timers
+ * from an idle CPU.  This is good for power-savings.
  *
  * We don't do similar optimization for completely idle system, as
- * selecting an idle cpu will add more delays to the timers than intended
- * (as that cpu's timer base may not be uptodate wrt jiffies etc).
+ * selecting an idle CPU will add more delays to the timers than intended
+ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
  */
 int get_nohz_timer_target(void)
 {
@@ -550,6 +549,7 @@ unlock:
 	rcu_read_unlock();
 	return cpu;
 }
+
 /*
  * When add_timer_on() enqueues a timer into the timer wheel of an
  * idle CPU then this timer might expire before the next timer event
@@ -784,60 +784,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_task(rq, p, flags);
 }
 
-static void update_rq_clock_task(struct rq *rq, s64 delta)
-{
-/*
- * In theory, the compile should just see 0 here, and optimize out the call
- * to sched_rt_avg_update. But I don't trust it...
- */
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	s64 steal = 0, irq_delta = 0;
-#endif
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
-
-	/*
-	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
-	 * this case when a previous update_rq_clock() happened inside a
-	 * {soft,}irq region.
-	 *
-	 * When this happens, we stop ->clock_task and only update the
-	 * prev_irq_time stamp to account for the part that fit, so that a next
-	 * update will consume the rest. This ensures ->clock_task is
-	 * monotonic.
-	 *
-	 * It does however cause some slight miss-attribution of {soft,}irq
-	 * time, a more accurate solution would be to update the irq_time using
-	 * the current rq->clock timestamp, except that would require using
-	 * atomic ops.
-	 */
-	if (irq_delta > delta)
-		irq_delta = delta;
-
-	rq->prev_irq_time += irq_delta;
-	delta -= irq_delta;
-#endif
-#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-	if (static_key_false((&paravirt_steal_rq_enabled))) {
-		steal = paravirt_steal_clock(cpu_of(rq));
-		steal -= rq->prev_steal_time_rq;
-
-		if (unlikely(steal > delta))
-			steal = delta;
-
-		rq->prev_steal_time_rq += steal;
-		delta -= steal;
-	}
-#endif
-
-	rq->clock_task += delta;
-
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
-		sched_rt_avg_update(rq, irq_delta + steal);
-#endif
-}
-
 void sched_set_stop_task(int cpu, struct task_struct *stop)
 {
 	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
@@ -1018,7 +964,7 @@ struct migration_arg {
 };
 
 /*
- * Move (not current) task off this cpu, onto dest cpu. We're doing
+ * Move (not current) task off this CPU, onto the destination CPU. We're doing
  * this because either it can't run here any more (set_cpus_allowed()
  * away from this CPU, or CPU going down), or because we're
  * attempting to rebalance this task on exec (sched_exec).
@@ -1052,8 +998,8 @@ static int migration_cpu_stop(void *data)
 	struct rq *rq = this_rq();
 
 	/*
-	 * The original target cpu might have gone down and we might
-	 * be on another cpu but it doesn't matter.
+	 * The original target CPU might have gone down and we might
+	 * be on another CPU but it doesn't matter.
 	 */
 	local_irq_disable();
 	/*
@@ -1171,7 +1117,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 	if (p->flags & PF_KTHREAD) {
 		/*
 		 * For kernel threads that do indeed end up on online &&
-		 * !active we want to ensure they are strict per-cpu threads.
+		 * !active we want to ensure they are strict per-CPU threads.
 		 */
 		WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
 			!cpumask_intersects(new_mask, cpu_active_mask) &&
@@ -1195,9 +1141,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		 * OK, since we're going to drop the lock immediately
 		 * afterwards anyway.
 		 */
-		lockdep_unpin_lock(&rq->lock, rf.cookie);
+		rq_unpin_lock(rq, &rf);
 		rq = move_queued_task(rq, p, dest_cpu);
-		lockdep_repin_lock(&rq->lock, rf.cookie);
+		rq_repin_lock(rq, &rf);
 	}
 out:
 	task_rq_unlock(rq, p, &rf);
@@ -1276,7 +1222,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		/*
 		 * Task isn't running anymore; make it appear like we migrated
 		 * it before it went to sleep. This means on wakeup we make the
-		 * previous cpu our target instead of where it really is.
+		 * previous CPU our target instead of where it really is.
 		 */
 		p->wake_cpu = cpu;
 	}
@@ -1508,12 +1454,12 @@ EXPORT_SYMBOL_GPL(kick_process);
  *
  *  - on cpu-up we allow per-cpu kthreads on the online && !active cpu,
  *    see __set_cpus_allowed_ptr(). At this point the newly online
- *    cpu isn't yet part of the sched domains, and balancing will not
+ *    CPU isn't yet part of the sched domains, and balancing will not
  *    see it.
  *
- *  - on cpu-down we clear cpu_active() to mask the sched domains and
+ *  - on CPU-down we clear cpu_active() to mask the sched domains and
  *    avoid the load balancer to place new tasks on the to be removed
- *    cpu. Existing tasks will remain running there and will be taken
+ *    CPU. Existing tasks will remain running there and will be taken
  *    off.
  *
  * This means that fallback selection must not select !active CPUs.
@@ -1529,9 +1475,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	int dest_cpu;
 
 	/*
-	 * If the node that the cpu is on has been offlined, cpu_to_node()
-	 * will return -1. There is no cpu on the node, and we should
-	 * select the cpu on the other node.
+	 * If the node that the CPU is on has been offlined, cpu_to_node()
+	 * will return -1. There is no CPU on the node, and we should
+	 * select the CPU on the other node.
 	 */
 	if (nid != -1) {
 		nodemask = cpumask_of_node(nid);
@@ -1563,7 +1509,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 				state = possible;
 				break;
 			}
-			/* fall-through */
+			/* Fall-through */
 		case possible:
 			do_set_cpus_allowed(p, cpu_possible_mask);
 			state = fail;
@@ -1607,7 +1553,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
 	 * to rely on ttwu() to place the task on a valid ->cpus_allowed
-	 * cpu.
+	 * CPU.
 	 *
 	 * Since this is common to all placement strategies, this lives here.
 	 *
@@ -1681,7 +1627,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
 	activate_task(rq, p, en_flags);
 	p->on_rq = TASK_ON_RQ_QUEUED;
 
-	/* if a worker is waking up, notify workqueue */
+	/* If a worker is waking up, notify the workqueue: */
 	if (p->flags & PF_WQ_WORKER)
 		wq_worker_waking_up(p, cpu_of(rq));
 }
@@ -1690,7 +1636,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl
  * Mark the task runnable and perform wakeup-preemption.
  */
 static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
-			   struct pin_cookie cookie)
+			   struct rq_flags *rf)
 {
 	check_preempt_curr(rq, p, wake_flags);
 	p->state = TASK_RUNNING;
@@ -1702,9 +1648,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 		 * Our task @p is fully woken up and running; so its safe to
 		 * drop the rq->lock, hereafter rq is only used for statistics.
 		 */
-		lockdep_unpin_lock(&rq->lock, cookie);
+		rq_unpin_lock(rq, rf);
 		p->sched_class->task_woken(rq, p);
-		lockdep_repin_lock(&rq->lock, cookie);
+		rq_repin_lock(rq, rf);
 	}
 
 	if (rq->idle_stamp) {
@@ -1723,7 +1669,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
 
 static void
 ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
-		 struct pin_cookie cookie)
+		 struct rq_flags *rf)
 {
 	int en_flags = ENQUEUE_WAKEUP;
 
@@ -1738,7 +1684,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 #endif
 
 	ttwu_activate(rq, p, en_flags);
-	ttwu_do_wakeup(rq, p, wake_flags, cookie);
+	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
 /*
@@ -1757,7 +1703,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 	if (task_on_rq_queued(p)) {
 		/* check_preempt_curr() may use rq clock */
 		update_rq_clock(rq);
-		ttwu_do_wakeup(rq, p, wake_flags, rf.cookie);
+		ttwu_do_wakeup(rq, p, wake_flags, &rf);
 		ret = 1;
 	}
 	__task_rq_unlock(rq, &rf);
@@ -1770,15 +1716,15 @@ void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
-	struct pin_cookie cookie;
 	struct task_struct *p;
 	unsigned long flags;
+	struct rq_flags rf;
 
 	if (!llist)
 		return;
 
 	raw_spin_lock_irqsave(&rq->lock, flags);
-	cookie = lockdep_pin_lock(&rq->lock);
+	rq_pin_lock(rq, &rf);
 
 	while (llist) {
 		int wake_flags = 0;
@@ -1789,10 +1735,10 @@ void sched_ttwu_pending(void)
 		if (p->sched_remote_wakeup)
 			wake_flags = WF_MIGRATED;
 
-		ttwu_do_activate(rq, p, wake_flags, cookie);
+		ttwu_do_activate(rq, p, wake_flags, &rf);
 	}
 
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_unpin_lock(rq, &rf);
 	raw_spin_unlock_irqrestore(&rq->lock, flags);
 }
 
@@ -1864,7 +1810,7 @@ void wake_up_if_idle(int cpu)
 		raw_spin_lock_irqsave(&rq->lock, flags);
 		if (is_idle_task(rq->curr))
 			smp_send_reschedule(cpu);
-		/* Else cpu is not in idle, do nothing here */
+		/* Else CPU is not idle, do nothing here: */
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}
 
@@ -1881,20 +1827,20 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct pin_cookie cookie;
+	struct rq_flags rf;
 
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) {
-		sched_clock_cpu(cpu); /* sync clocks x-cpu */
+		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		ttwu_queue_remote(p, cpu, wake_flags);
 		return;
 	}
 #endif
 
 	raw_spin_lock(&rq->lock);
-	cookie = lockdep_pin_lock(&rq->lock);
-	ttwu_do_activate(rq, p, wake_flags, cookie);
-	lockdep_unpin_lock(&rq->lock, cookie);
+	rq_pin_lock(rq, &rf);
+	ttwu_do_activate(rq, p, wake_flags, &rf);
+	rq_unpin_lock(rq, &rf);
 	raw_spin_unlock(&rq->lock);
 }
 
@@ -1904,8 +1850,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *  MIGRATION
  *
  * The basic program-order guarantee on SMP systems is that when a task [t]
- * migrates, all its activity on its old cpu [c0] happens-before any subsequent
- * execution on its new cpu [c1].
+ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
+ * execution on its new CPU [c1].
  *
  * For migration (of runnable tasks) this is provided by the following means:
  *
@@ -1916,7 +1862,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *
  * Transitivity guarantees that B happens after A and C after B.
  * Note: we only require RCpc transitivity.
- * Note: the cpu doing B need not be c0 or c1
+ * Note: the CPU doing B need not be c0 or c1
  *
  * Example:
  *
@@ -2024,7 +1970,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	trace_sched_waking(p);
 
-	success = 1; /* we're going to change ->state */
+	/* We're going to change ->state: */
+	success = 1;
 	cpu = task_cpu(p);