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 cycle were:

   - Add the SYSTEM_SCHEDULING bootup state to move various scheduler
     debug checks earlier into the bootup. This turns silent and
     sporadically deadly bugs into nice, deterministic splats. Fix some
     of the splats that triggered. (Thomas Gleixner)

   - A round of restructuring and refactoring of the load-balancing and
     topology code (Peter Zijlstra)

   - Another round of consolidating ~20 of incremental scheduler code
     history: this time in terms of wait-queue nomenclature. (I didn't
     get much feedback on these renaming patches, and we can still
     easily change any names I might have misplaced, so if anyone hates
     a new name, please holler and I'll fix it.) (Ingo Molnar)

   - sched/numa improvements, fixes and updates (Rik van Riel)

   - Another round of x86/tsc scheduler clock code improvements, in hope
     of making it more robust (Peter Zijlstra)

   - Improve NOHZ behavior (Frederic Weisbecker)

   - Deadline scheduler improvements and fixes (Luca Abeni, Daniel
     Bristot de Oliveira)

   - Simplify and optimize the topology setup code (Lauro Ramos
     Venancio)

   - Debloat and decouple scheduler code some more (Nicolas Pitre)

   - Simplify code by making better use of llist primitives (Byungchul
     Park)

   - ... plus other fixes and improvements"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (103 commits)
  sched/cputime: Refactor the cputime_adjust() code
  sched/debug: Expose the number of RT/DL tasks that can migrate
  sched/numa: Hide numa_wake_affine() from UP build
  sched/fair: Remove effective_load()
  sched/numa: Implement NUMA node level wake_affine()
  sched/fair: Simplify wake_affine() for the single socket case
  sched/numa: Override part of migrate_degrades_locality() when idle balancing
  sched/rt: Move RT related code from sched/core.c to sched/rt.c
  sched/deadline: Move DL related code from sched/core.c to sched/deadline.c
  sched/cpuset: Only offer CONFIG_CPUSETS if SMP is enabled
  sched/fair: Spare idle load balancing on nohz_full CPUs
  nohz: Move idle balancer registration to the idle path
  sched/loadavg: Generalize "_idle" naming to "_nohz"
  sched/core: Drop the unused try_get_task_struct() helper function
  sched/fair: WARN() and refuse to set buddy when !se->on_rq
  sched/debug: Fix SCHED_WARN_ON() to return a value on !CONFIG_SCHED_DEBUG as well
  sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
  sched/wait: Move bit_wait_table[] and related functionality from sched/core.c to sched/wait_bit.c
  sched/wait: Split out the wait_bit*() APIs from <linux/wait.h> into <linux/wait_bit.h>
  sched/wait: Re-adjust macro line continuation backslashes in <linux/wait.h>
  ...

25 files changed, 2413 insertions, 1585 deletions

diff --git a/kernel/async.c b/kernel/async.c
index d2edd6efec56..2cbd3dd5940d 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -114,14 +114,14 @@ static void async_run_entry_fn(struct work_struct *work)
 	ktime_t uninitialized_var(calltime), delta, rettime;
 
 	/* 1) run (and print duration) */
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		pr_debug("calling  %lli_%pF @ %i\n",
 			(long long)entry->cookie,
 			entry->func, task_pid_nr(current));
 		calltime = ktime_get();
 	}
 	entry->func(entry->data, entry->cookie);
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		rettime = ktime_get();
 		delta = ktime_sub(rettime, calltime);
 		pr_debug("initcall %lli_%pF returned 0 after %lld usecs\n",
@@ -284,14 +284,14 @@ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain
 {
 	ktime_t uninitialized_var(starttime), delta, endtime;
 
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		pr_debug("async_waiting @ %i\n", task_pid_nr(current));
 		starttime = ktime_get();
 	}
 
 	wait_event(async_done, lowest_in_progress(domain) >= cookie);
 
-	if (initcall_debug && system_state == SYSTEM_BOOTING) {
+	if (initcall_debug && system_state < SYSTEM_RUNNING) {
 		endtime = ktime_get();
 		delta = ktime_sub(endtime, starttime);
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 516acdb0e0ec..c63226283aef 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -318,19 +318,6 @@ void rcuwait_wake_up(struct rcuwait *w)
 	rcu_read_unlock();
 }
 
-struct task_struct *try_get_task_struct(struct task_struct **ptask)
-{
-	struct task_struct *task;
-
-	rcu_read_lock();
-	task = task_rcu_dereference(ptask);
-	if (task)
-		get_task_struct(task);
-	rcu_read_unlock();
-
-	return task;
-}
-
 /*
  * Determine if a process group is "orphaned", according to the POSIX
  * definition in 2.2.2.52.  Orphaned process groups are not to be affected
@@ -1004,7 +991,7 @@ struct wait_opts {
 	int __user		*wo_stat;
 	struct rusage __user	*wo_rusage;
 
-	wait_queue_t		child_wait;
+	wait_queue_entry_t		child_wait;
 	int			notask_error;
 };
 
@@ -1541,7 +1528,7 @@ static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
 	return 0;
 }
 
-static int child_wait_callback(wait_queue_t *wait, unsigned mode,
+static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode,
 				int sync, void *key)
 {
 	struct wait_opts *wo = container_of(wait, struct wait_opts,
diff --git a/kernel/extable.c b/kernel/extable.c
index 2676d7f8baf6..0fbdd8582f08 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -75,7 +75,7 @@ int core_kernel_text(unsigned long addr)
 	    addr < (unsigned long)_etext)
 		return 1;
 
-	if (system_state == SYSTEM_BOOTING &&
+	if (system_state < SYSTEM_RUNNING &&
 	    init_kernel_text(addr))
 		return 1;
 	return 0;
diff --git a/kernel/futex.c b/kernel/futex.c
index 357348a6cf6b..d6cf71d08f21 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -225,7 +225,7 @@ struct futex_pi_state {
  * @requeue_pi_key:	the requeue_pi target futex key
  * @bitset:		bitset for the optional bitmasked wakeup
  *
- * We use this hashed waitqueue, instead of a normal wait_queue_t, so
+ * We use this hashed waitqueue, instead of a normal wait_queue_entry_t, so
  * we can wake only the relevant ones (hashed queues may be shared).
  *
  * A futex_q has a woken state, just like tasks have TASK_RUNNING.
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a1db38abac5b..bd53ea579dc8 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1175,7 +1175,7 @@ static void boot_delay_msec(int level)
 	unsigned long long k;
 	unsigned long timeout;
 
-	if ((boot_delay == 0 || system_state != SYSTEM_BOOTING)
+	if ((boot_delay == 0 || system_state >= SYSTEM_RUNNING)
 		|| suppress_message_printing(level)) {
 		return;
 	}
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 89ab6758667b..53f0164ed362 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -16,9 +16,9 @@ CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
 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-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o
+obj-y += idle_task.o fair.o rt.o deadline.o
+obj-y += wait.o wait_bit.o swait.o completion.o idle.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 00a45c45beca..ca0f8fc945c6 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -64,6 +64,7 @@
 #include <linux/workqueue.h>
 #include <linux/compiler.h>
 #include <linux/tick.h>
+#include <linux/init.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -124,14 +125,27 @@ int sched_clock_stable(void)
 	return static_branch_likely(&__sched_clock_stable);
 }
 
+static void __scd_stamp(struct sched_clock_data *scd)
+{
+	scd->tick_gtod = ktime_get_ns();
+	scd->tick_raw = sched_clock();
+}
+
 static void __set_sched_clock_stable(void)
 {
-	struct sched_clock_data *scd = this_scd();
+	struct sched_clock_data *scd;
 
 	/*
+	 * Since we're still unstable and the tick is already running, we have
+	 * to disable IRQs in order to get a consistent scd->tick* reading.
+	 */
+	local_irq_disable();
+	scd = this_scd();
+	/*
 	 * Attempt to make the (initial) unstable->stable transition continuous.
 	 */
 	__sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw);
+	local_irq_enable();
 
 	printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n",
 			scd->tick_gtod, __gtod_offset,
@@ -141,8 +155,38 @@ static void __set_sched_clock_stable(void)
 	tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE);
 }
 
+/*
+ * If we ever get here, we're screwed, because we found out -- typically after
+ * the fact -- that TSC wasn't good. This means all our clocksources (including
+ * ktime) could have reported wrong values.
+ *
+ * What we do here is an attempt to fix up and continue sort of where we left
+ * off in a coherent manner.
+ *
+ * The only way to fully avoid random clock jumps is to boot with:
+ * "tsc=unstable".
+ */
 static void __sched_clock_work(struct work_struct *work)
 {
+	struct sched_clock_data *scd;
+	int cpu;
+
+	/* take a current timestamp and set 'now' */
+	preempt_disable();
+	scd = this_scd();
+	__scd_stamp(scd);
+	scd->clock = scd->tick_gtod + __gtod_offset;
+	preempt_enable();
+
+	/* clone to all CPUs */
+	for_each_possible_cpu(cpu)
+		per_cpu(sched_clock_data, cpu) = *scd;
+
+	printk(KERN_WARNING "TSC found unstable after boot, most likely due to broken BIOS. Use 'tsc=unstable'.\n");
+	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
+			scd->tick_gtod, __gtod_offset,
+			scd->tick_raw,  __sched_clock_offset);
+
 	static_branch_disable(&__sched_clock_stable);
 }
 
@@ -150,27 +194,11 @@ static DECLARE_WORK(sched_clock_work, __sched_clock_work);
 
 static void __clear_sched_clock_stable(void)
 {
-	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 + __sched_clock_offset) - (scd->tick_gtod);
-
-	printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n",
-			scd->tick_gtod, __gtod_offset,
-			scd->tick_raw,  __sched_clock_offset);
+	if (!sched_clock_stable())
+		return;
 
 	tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE);
-
-	if (sched_clock_stable())
-		schedule_work(&sched_clock_work);
+	schedule_work(&sched_clock_work);
 }
 
 void clear_sched_clock_stable(void)
@@ -183,7 +211,11 @@ void clear_sched_clock_stable(void)
 		__clear_sched_clock_stable();
 }
 
-void sched_clock_init_late(void)
+/*
+ * We run this as late_initcall() such that it runs after all built-in drivers,
+ * notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
+ */
+static int __init sched_clock_init_late(void)
 {
 	sched_clock_running = 2;
 	/*
@@ -197,7 +229,10 @@ void sched_clock_init_late(void)
 
 	if (__sched_clock_stable_early)
 		__set_sched_clock_stable();
+
+	return 0;
 }
+late_initcall(sched_clock_init_late);
 
 /*
  * min, max except they take wrapping into account
@@ -347,21 +382,38 @@ void sched_clock_tick(void)
 {
 	struct sched_clock_data *scd;
 
+	if (sched_clock_stable())
+		return;
+
+	if (unlikely(!sched_clock_running))
+		return;
+
 	WARN_ON_ONCE(!irqs_disabled());
 
+	scd = this_scd();
+	__scd_stamp(scd);
+	sched_clock_local(scd);
+}
+
+void sched_clock_tick_stable(void)
+{
+	u64 gtod, clock;
+
+	if (!sched_clock_stable())
+		return;
+
 	/*
-	 * 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.
+	 * Called under watchdog_lock.
 	 *
-	 * XXX arguably we can skip this if we expose tsc_clocksource_reliable
+	 * The watchdog just found this TSC to (still) be stable, so now is a
+	 * good moment to update our __gtod_offset. Because once we find the
+	 * TSC to be unstable, any computation will be computing crap.
 	 */
-	scd = this_scd();
-	scd->tick_raw  = sched_clock();
-	scd->tick_gtod = ktime_get_ns();
-
-	if (!sched_clock_stable() && likely(sched_clock_running))
-		sched_clock_local(scd);
+	local_irq_disable();
+	gtod = ktime_get_ns();
+	clock = sched_clock();
+	__gtod_offset = (clock + __sched_clock_offset) - gtod;
+	local_irq_enable();
 }
 
 /*
@@ -374,15 +426,21 @@ void sched_clock_idle_sleep_event(void)
 EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);
 
 /*
- * We just idled delta nanoseconds (called with irqs disabled):
+ * We just idled; resync with ktime.
  */
-void sched_clock_idle_wakeup_event(u64 delta_ns)
+void sched_clock_idle_wakeup_event(void)
 {
-	if (timekeeping_suspended)
+	unsigned long flags;
+
+	if (sched_clock_stable())
+		return;
+
+	if (unlikely(timekeeping_suspended))
 		return;
 
+	local_irq_save(flags);
 	sched_clock_tick();
-	touch_softlockup_watchdog_sched();
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index 53f9558fa925..13fc5ae9bf2f 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -66,7 +66,7 @@ do_wait_for_common(struct completion *x,
 	if (!x->done) {
 		DECLARE_WAITQUEUE(wait, current);
 
-		__add_wait_queue_tail_exclusive(&x->wait, &wait);
+		__add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
 		do {
 			if (signal_pending_state(state, current)) {
 				timeout = -ERESTARTSYS;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5b60f3a8343f..17c667b427b4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10,6 +10,7 @@
 #include <uapi/linux/sched/types.h>
 #include <linux/sched/loadavg.h>
 #include <linux/sched/hotplug.h>
+#include <linux/wait_bit.h>
 #include <linux/cpuset.h>
 #include <linux/delayacct.h>
 #include <linux/init_task.h>
@@ -788,36 +789,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 	dequeue_task(rq, p, flags);
 }
 
-void sched_set_stop_task(int cpu, struct task_struct *stop)
-{
-	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
-	struct task_struct *old_stop = cpu_rq(cpu)->stop;
-
-	if (stop) {
-		/*
-		 * Make it appear like a SCHED_FIFO task, its something
-		 * userspace knows about and won't get confused about.
-		 *
-		 * Also, it will make PI more or less work without too
-		 * much confusion -- but then, stop work should not
-		 * rely on PI working anyway.
-		 */
-		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
-
-		stop->sched_class = &stop_sched_class;
-	}
-
-	cpu_rq(cpu)->stop = stop;
-
-	if (old_stop) {
-		/*
-		 * Reset it back to a normal scheduling class so that
-		 * it can die in pieces.
-		 */
-		old_stop->sched_class = &rt_sched_class;
-	}
-}
-
 /*
  * __normal_prio - return the priority that is based on the static prio
  */
@@ -1588,6 +1559,36 @@ static void update_avg(u64 *avg, u64 sample)
 	*avg += diff >> 3;
 }
 
+void sched_set_stop_task(int cpu, struct task_struct *stop)
+{
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+	struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+	if (stop) {
+		/*
+		 * Make it appear like a SCHED_FIFO task, its something
+		 * userspace knows about and won't get confused about.
+		 *
+		 * Also, it will make PI more or less work without too
+		 * much confusion -- but then, stop work should not
+		 * rely on PI working anyway.
+		 */
+		sched_setscheduler_nocheck(stop, SCHED_FIFO, &param);
+
+		stop->sched_class = &stop_sched_class;
+	}
+
+	cpu_rq(cpu)->stop = stop;
+
+	if (old_stop) {
+		/*
+		 * Reset it back to a normal scheduling class so that
+		 * it can die in pieces.
+		 */
+		old_stop->sched_class = &rt_sched_class;
+	}
+}
+
 #else
 
 static inline int __set_cpus_allowed_ptr(struct task_struct *p,
@@ -1731,7 +1732,7 @@ void sched_ttwu_pending(void)
 {
 	struct rq *rq = this_rq();
 	struct llist_node *llist = llist_del_all(&rq->wake_list);
-	struct task_struct *p;
+	struct task_struct *p, *t;
 	struct rq_flags rf;
 
 	if (!llist)
@@ -1740,17 +1741,8 @@ void sched_ttwu_pending(void)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	while (llist) {
-		int wake_flags = 0;
-
-		p = llist_entry(llist, struct task_struct, wake_entry);
-		llist = llist_next(llist);
-
-		if (p->sched_remote_wakeup)
-			wake_flags = WF_MIGRATED;
-
-		ttwu_do_activate(rq, p, wake_flags, &rf);
-	}
+	llist_for_each_entry_safe(p, t, llist, wake_entry)
+		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
 
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -2148,23 +2140,6 @@ int wake_up_state(struct task_struct *p, unsigned int state)
 }
 
 /*
- * This function clears the sched_dl_entity static params.
- */
-void __dl_clear_params(struct task_struct *p)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	dl_se->dl_runtime = 0;
-	dl_se->dl_deadline = 0;
-	dl_se->dl_period = 0;
-	dl_se->flags = 0;
-	dl_se->dl_bw = 0;
-
-	dl_se->dl_throttled = 0;
-	dl_se->dl_yielded = 0;
-}
-
-/*
  * Perform scheduler related setup for a newly forked process p.
  * p is forked by current.
  *
@@ -2193,6 +2168,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
 	init_dl_task_timer(&p->dl);
+	init_dl_inactive_task_timer(&p->dl);
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -2430,7 +2406,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 unsigned long to_ratio(u64 period, u64 runtime)
 {
 	if (runtime == RUNTIME_INF)
-		return 1ULL << 20;
+		return BW_UNIT;
 
 	/*
 	 * Doing this here saves a lot of checks in all
@@ -2440,93 +2416,9 @@ unsigned long to_ratio(u64 period, u64 runtime)
 	if (period == 0)
 		return 0;
 
-	return div64_u64(runtime << 20, period);
+	return div64_u64(runtime << BW_SHIFT, period);
 }
 
-#ifdef CONFIG_SMP
-inline struct dl_bw *dl_bw_of(int i)
-{
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	return &cpu_rq(i)->rd->dl_bw;
-}
-
-static inline int dl_bw_cpus(int i)
-{
-	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus = 0;
-
-	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
-			 "sched RCU must be held");
-	for_each_cpu_and(i, rd->span, cpu_active_mask)
-		cpus++;
-
-	return cpus;
-}
-#else
-inline struct dl_bw *dl_bw_of(int i)
-{
-	return &cpu_rq(i)->dl.dl_bw;
-}
-
-static inline int dl_bw_cpus(int i)
-{
-	return 1;
-}
-#endif
-
-/*
- * We must be sure that accepting a new task (or allowing changing the
- * parameters of an existing one) is consistent with the bandwidth
- * constraints. If yes, this function also accordingly updates the currently
- * allocated bandwidth to reflect the new situation.
- *
- * This function is called while holding p's rq->lock.
- *
- * XXX we should delay bw change until the task's 0-lag point, see
- * __setparam_dl().
- */
-static int dl_overflow(struct task_struct *p, int policy,
-		       const struct sched_attr *attr)
-{
-
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-	u64 period = attr->sched_period ?: attr->sched_deadline;
-	u64 runtime = attr->sched_runtime;
-	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
-	int cpus, err = -1;
-
-	/* !deadline task may carry old deadline bandwidth */
-	if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
-		return 0;
-
-	/*
-	 * Either if a task, enters, leave, or stays -deadline but changes
-	 * its parameters, we may need to update accordingly the total
-	 * allocated bandwidth of the container.
-	 */
-	raw_spin_lock(&dl_b->lock);
-	cpus = dl_bw_cpus(task_cpu(p));
-	if (dl_policy(policy) && !task_has_dl_policy(p) &&
-	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
-		__dl_add(dl_b, new_bw);
-		err = 0;
-	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
-		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
-		__dl_clear(dl_b, p->dl.dl_bw);
-		__dl_add(dl_b, new_bw);
-		err = 0;
-	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
-		__dl_clear(dl_b, p->dl.dl_bw);
-		err = 0;
-	}
-	raw_spin_unlock(&dl_b->lock);
-
-	return err;
-}
-
-extern void init_dl_bw(struct dl_bw *dl_b);
-
 /*
  * wake_up_new_task - wake up a newly created task for the first time.
  *
@@ -3687,7 +3579,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void)
 	exception_exit(prev_state);
 }
 
-int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags,
+int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
 			  void *key)
 {
 	return try_to_wake_up(curr->private, mode, wake_flags);
@@ -4009,46 +3901,6 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 }
 
 /*
- * This function initializes the sched_dl_entity of a newly becoming
- * SCHED_DEADLINE task.
- *
- * Only the static values are considered here, the actual runtime and the
- * absolute deadline will be properly calculated when the task is enqueued
- * for the first time with its new policy.
- */
-static void
-__setparam_dl(struct task_struct *p, const struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	dl_se->dl_runtime = attr->sched_runtime;
-	dl_se->dl_deadline = attr->sched_deadline;
-	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
-	dl_se->flags = attr->sched_flags;
-	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-
-	/*
-	 * Changing the parameters of a task is 'tricky' and we're not doing
-	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
-	 *
-	 * What we SHOULD do is delay the bandwidth release until the 0-lag
-	 * point. This would include retaining the task_struct until that time
-	 * and change dl_overflow() to not immediately decrement the current
-	 * amount.
-	 *
-	 * Instead we retain the current runtime/deadline and let the new
-	 * parameters take effect after the current reservation period lapses.
-	 * This is safe (albeit pessimistic) because the 0-lag point is always
-	 * before the current scheduling deadline.
-	 *
-	 * We can still have temporary overloads because we do not delay the
-	 * change in bandwidth until that time; so admission control is
-	 * not on the safe side. It does however guarantee tasks will never
-	 * consume more than promised.
-	 */
-}
-
-/*
  * sched_setparam() passes in -1 for its policy, to let the functions
  * it calls know not to change it.
  */
@@ -4101,59 +3953,6 @@ static void __setscheduler(struct rq *rq, struct task_struct *p,
 		p->sched_class = &fair_sched_class;
 }
 
-static void
-__getparam_dl(struct task_struct *p, struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	attr->sched_priority = p->rt_priority;
-	attr->sched_runtime = dl_se->dl_runtime;
-	attr->sched_deadline = dl_se->dl_deadline;
-	attr->sched_period = dl_se->dl_period;
-	attr->sched_flags = dl_se->flags;
-}
-
-/*
- * This function validates the new parameters of a -deadline task.
- * We ask for the deadline not being zero, and greater or equal
- * than the runtime, as well as the period of being zero or
- * greater than deadline. Furthermore, we have to be sure that
- * user parameters are above the internal resolution of 1us (we
- * check sched_runtime only since it is always the smaller one) and
- * below 2^63 ns (we have to check both sched_deadline and
- * sched_period, as the latter can be zero).
- */
-static bool
-__checkparam_dl(const struct sched_attr *attr)
-{
-	/* deadline != 0 */
-	if (attr->sched_deadline == 0)
-		return false;
-
-	/*
-	 * Since we truncate DL_SCALE bits, make sure we're at least
-	 * that big.
-	 */
-	if (attr->sched_runtime < (1ULL << DL_SCALE))
-		return false;
-
-	/*
-	 * Since we use the MSB for wrap-around and sign issues, make
-	 * sure it's not set (mind that period can be equal to zero).
-	 */
-	if (attr->sched_deadline & (1ULL << 63) ||
-	    attr->sched_period & (1ULL << 63))
-		return false;
-
-	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
-	    attr->sched_deadline < attr->sched_runtime)
-		return false;
-
-	return true;
-}
-
 /*
  * Check the target process has a UID that matches the current process's:
  */
@@ -4170,19 +3969,6 @@ static bool check_same_owner(struct task_struct *p)
 	return match;
 }
 
-static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
-{
-	struct sched_dl_entity *dl_se = &p->dl;
-
-	if (dl_se->dl_runtime != attr->sched_runtime ||
-		dl_se->dl_deadline != attr->sched_deadline ||
-		dl_se->dl_period != attr->sched_period ||
-		dl_se->flags != attr->sched_flags)
-		return true;
-
-	return false;
-}
-
 static int __sched_setscheduler(struct task_struct *p,
 				const struct sched_attr *attr,
 				bool user, bool pi)
@@ -4197,8 +3983,8 @@ static int __sched_setscheduler(struct task_struct *p,
 	int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct rq *rq;
 
-	/* May grab non-irq protected spin_locks: */
-	BUG_ON(in_interrupt());
+	/* The pi code expects interrupts enabled */
+	BUG_ON(pi && in_interrupt());
 recheck:
 	/* Double check policy once rq lock held: */
 	if (policy < 0) {
@@ -4211,7 +3997,8 @@ recheck:
 			return -EINVAL;
 	}
 
-	if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK))
+	if (attr->sched_flags &
+		~(SCHED_FLAG_RESET_ON_FORK | SCHED_FLAG_RECLAIM))
 		return -EINVAL;
 
 	/*
@@ -4362,7 +4149,7 @@ change:
 	 * of a SCHED_DEADLINE task) we need to check if enough bandwidth
 	 * is available.
 	 */
-	if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) {
+	if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
 		task_rq_unlock(rq, p, &rf);
 		return -EBUSY;
 	}
@@ -5463,26 +5250,17 @@ void init_idle(struct task_struct *idle, int cpu)
 #endif
 }
 
+#ifdef CONFIG_SMP
+
 int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 			      const struct cpumask *trial)
 {
-	int ret = 1, trial_cpus;
-	struct dl_bw *cur_dl_b;
-	unsigned long flags;
+	int ret = 1;
 
 	if (!cpumask_weight(cur))
 		return ret;
 
-	rcu_read_lock_sched();
-	cur_dl_b = dl_bw_of(cpumask_any(cur));
-	trial_cpus = cpumask_weight(trial);
-
-	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
-	if (cur_dl_b->bw != -1 &&
-	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
-		ret = 0;
-	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
-	rcu_read_unlock_sched();
+	ret = dl_cpuset_cpumask_can_shrink(cur, trial);
 
 	return ret;
 }
@@ -5506,43 +5284,14 @@ int task_can_attach(struct task_struct *p,
 		goto out;
 	}
 
-#ifdef CONFIG_SMP
 	if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span,
-					      cs_cpus_allowed)) {
-		unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
-							cs_cpus_allowed);
-		struct dl_bw *dl_b;
-		bool overflow;
-		int cpus;
-		unsigned long flags;
-
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(dest_cpu);
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		cpus = dl_bw_cpus(dest_cpu);
-		overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
-		if (overflow)
-			ret = -EBUSY;
-		else {
-			/*
-			 * We reserve space for this task in the destination
-			 * root_domain, as we can't fail after this point.
-			 * We will free resources in the source root_domain
-			 * later on (see set_cpus_allowed_dl()).
-			 */
-			__dl_add(dl_b, p->dl.dl_bw);
-		}
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-		rcu_read_unlock_sched();
+					      cs_cpus_allowed))
+		ret = dl_task_can_attach(p, cs_cpus_allowed);
 
-	}
-#endif
 out:
 	return ret;
 }
 
-#ifdef CONFIG_SMP
-
 bool sched_smp_initialized __read_mostly;
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -5805,23 +5554,8 @@ static void cpuset_cpu_active(void)
 
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
-	unsigned long flags;
-	struct dl_bw *dl_b;
-	bool overflow;
-	int cpus;
-
 	if (!cpuhp_tasks_frozen) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		cpus = dl_bw_cpus(cpu);
-		overflow = __dl_overflow(dl_b, cpus, 0, 0);
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-
-		if (overflow)
+		if (dl_cpu_busy(cpu))
 			return -EBUSY;
 		cpuset_update_active_cpus();
 	} else {
@@ -5952,7 +5686,6 @@ void __init sched_init_smp(void)
 	cpumask_var_t non_isolated_cpus;
 
 	alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
-	alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
 
 	sched_init_numa();
 
@@ -5962,7 +5695,7 @@ void __init sched_init_smp(void)
 	 * happen.
 	 */
 	mutex_lock(&sched_domains_mutex);
-	init_sched_domains(cpu_active_mask);
+	sched_init_domains(cpu_active_mask);
 	cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
 	if (cpumask_empty(non_isolated_cpus))
 		cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
@@ -5978,7 +5711,6 @@ void __init sched_init_smp(void)
 	init_sched_dl_class();
 
 	sched_init_smt();
-	sched_clock_init_late();
 
 	sched_smp_initialized = true;
 }
@@ -5994,7 +5726,6 @@ early_initcall(migration_init);
 void __init sched_init_smp(void)
 {
 	sched_init_granularity();
-	sched_clock_init_late();
 }
 #endif /* CONFIG_SMP */
 
@@ -6020,28 +5751,13 @@ static struct kmem_cache *task_group_cache __read_mostly;
 DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
 DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
-#define WAIT_TABLE_BITS 8
-#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
-static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
-
-wait_queue_head_t *bit_waitqueue(void *word, int bit)
-{
-	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
-	unsigned long val = (unsigned long)word << shift | bit;
-
-	return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
-}
-EXPORT_SYMBOL(bit_waitqueue);
-
 void __init sched_init(void)
 {
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
 	sched_clock_init();
-
-	for (i = 0; i < WAIT_TABLE_SIZE; i++)
-		init_waitqueue_head(bit_wait_table + i);
+	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
@@ -6193,7 +5909,6 @@ void __init sched_init(void)
 	calc_load_update = jiffies + LOAD_FREQ;
 
 #ifdef CONFIG_SMP
-	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT);
 	/* May be allocated at isolcpus cmdline parse time */
 	if (cpu_isolated_map == NULL)
 		zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
@@ -6245,8 +5960,10 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
 	     !is_idle_task(current)) ||
-	    system_state != SYSTEM_RUNNING || oops_in_progress)
+	    system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
+	    oops_in_progress)
 		return;
+
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
 		return;
 	prev_jiffy = jiffies;
@@ -6501,385 +6218,6 @@ void sched_move_task(struct task_struct *tsk)
 
 	task_rq_unlock(rq, tsk, &rf);
 }
-#endif /* CONFIG_CGROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-/*
- * Ensure that the real time constraints are schedulable.
- */
-static DEFINE_MUTEX(rt_constraints_mutex);
-
-/* Must be called with tasklist_lock held */
-static inline int tg_has_rt_tasks(struct task_group *tg)
-{
-	struct task_struct *g, *p;
-
-	/*
-	 * Autogroups do not have RT tasks; see autogroup_create().
-	 */
-	if (task_group_is_autogroup(tg))
-		return 0;
-
-	for_each_process_thread(g, p) {
-		if (rt_task(p) && task_group(p) == tg)
-			return 1;
-	}
-
-	return 0;
-}
-
-struct rt_schedulable_data {
-	struct task_group *tg;
-	u64 rt_period;
-	u64 rt_runtime;
-};
-
-static int tg_rt_schedulable(struct task_group *tg, void *data)
-{
-	struct rt_schedulable_data *d = data;
-	struct task_group *child;
-	unsigned long total, sum = 0;
-	u64 period, runtime;
-
-	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	runtime = tg->rt_bandwidth.rt_runtime;
-
-	if (tg == d->tg) {
-		period = d->rt_period;
-		runtime = d->rt_runtime;
-	}
-
-	/*
-	 * Cannot have more runtime than the period.
-	 */
-	if (runtime > period && runtime != RUNTIME_INF)
-		return -EINVAL;
-
-	/*
-	 * Ensure we don't starve existing RT tasks.
-	 */
-	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
-		return -EBUSY;
-
-	total = to_ratio(period, runtime);
-
-	/*
-	 * Nobody can have more than the global setting allows.
-	 */
-	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
-		return -EINVAL;
-
-	/*
-	 * The sum of our children's runtime should not exceed our own.
-	 */
-	list_for_each_entry_rcu(child, &tg->children, siblings) {
-		period = ktime_to_ns(child->rt_bandwidth.rt_period);
-		runtime = child->rt_bandwidth.rt_runtime;
-
-		if (child == d->tg) {
-			period = d->rt_period;
-			runtime = d->rt_runtime;
-		}
-
-		sum += to_ratio(period, runtime);
-	}
-
-	if (sum > total)
-		return -EINVAL;
-
-	return 0;
-}
-
-static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
-{
-	int ret;
-
-	struct rt_schedulable_data data = {
-		.tg = tg,
-		.rt_period = period,
-		.rt_runtime = runtime,
-	};
-
-	rcu_read_lock();
-	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
-	rcu_read_unlock();
-
-	return ret;
-}
-
-static int tg_set_rt_bandwidth(struct task_group *tg,
-		u64 rt_period, u64 rt_runtime)
-{
-	int i, err = 0;
-
-	/*
-	 * Disallowing the root group RT runtime is BAD, it would disallow the
-	 * kernel creating (and or operating) RT threads.
-	 */
-	if (tg == &root_task_group && rt_runtime == 0)
-		return -EINVAL;
-
-	/* No period doesn't make any sense. */
-	if (rt_period == 0)
-		return -EINVAL;
-
-	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
-	err = __rt_schedulable(tg, rt_period, rt_runtime);
-	if (err)
-		goto unlock;
-
-	raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
-	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
-	tg->rt_bandwidth.rt_runtime = rt_runtime;
-
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = tg->rt_rq[i];
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = rt_runtime;
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
-unlock:
-	read_unlock(&tasklist_lock);
-	mutex_unlock(&rt_constraints_mutex);
-
-	return err;
-}
-
-static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
-{
-	u64 rt_runtime, rt_period;
-
-	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
-	if (rt_runtime_us < 0)
-		rt_runtime = RUNTIME_INF;
-
-	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-static long sched_group_rt_runtime(struct task_group *tg)
-{
-	u64 rt_runtime_us;
-
-	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
-		return -1;
-
-	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
-	do_div(rt_runtime_us, NSEC_PER_USEC);
-	return rt_runtime_us;
-}
-
-static int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
-{
-	u64 rt_runtime, rt_period;
-
-	rt_period = rt_period_us * NSEC_PER_USEC;
-	rt_runtime = tg->rt_bandwidth.rt_runtime;
-
-	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
-}
-
-static long sched_group_rt_period(struct task_group *tg)
-{
-	u64 rt_period_us;
-
-	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
-	do_div(rt_period_us, NSEC_PER_USEC);
-	return rt_period_us;
-}
-#endif /* CONFIG_RT_GROUP_SCHED */
-
-#ifdef CONFIG_RT_GROUP_SCHED
-static int sched_rt_global_constraints(void)
-{
-	int ret = 0;
-
-	mutex_lock(&rt_constraints_mutex);
-	read_lock(&tasklist_lock);
-	ret = __rt_schedulable(NULL, 0, 0);
-	read_unlock(&tasklist_lock);
-	mutex_unlock(&rt_constraints_mutex);
-
-	return ret;
-}
-
-static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
-{
-	/* Don't accept realtime tasks when there is no way for them to run */
-	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
-		return 0;
-
-	return 1;
-}
-
-#else /* !CONFIG_RT_GROUP_SCHED */
-static int sched_rt_global_constraints(void)
-{
-	unsigned long flags;
-	int i;
-
-	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
-	for_each_possible_cpu(i) {
-		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
-
-		raw_spin_lock(&rt_rq->rt_runtime_lock);
-		rt_rq->rt_runtime = global_rt_runtime();
-		raw_spin_unlock(&rt_rq->rt_runtime_lock);
-	}
-	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
-
-	return 0;
-}
-#endif /* CONFIG_RT_GROUP_SCHED */
-
-static int sched_dl_global_validate(void)
-{
-	u64 runtime = global_rt_runtime();
-	u64 period = global_rt_period();
-	u64 new_bw = to_ratio(period, runtime);
-	struct dl_bw *dl_b;
-	int cpu, ret = 0;
-	unsigned long flags;
-
-	/*
-	 * Here we want to check the bandwidth not being set to some
-	 * value smaller than the currently allocated bandwidth in
-	 * any of the root_domains.
-	 *
-	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
-	 * cycling on root_domains... Discussion on different/better
-	 * solutions is welcome!
-	 */
-	for_each_possible_cpu(cpu) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		if (new_bw < dl_b->total_bw)
-			ret = -EBUSY;
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-
-		if (ret)
-			break;
-	}
-
-	return ret;
-}
-
-static void sched_dl_do_global(void)
-{
-	u64 new_bw = -1;
-	struct dl_bw *dl_b;
-	int cpu;
-	unsigned long flags;
-
-	def_dl_bandwidth.dl_period = global_rt_period();
-	def_dl_bandwidth.dl_runtime = global_rt_runtime();
-
-	if (global_rt_runtime() != RUNTIME_INF)
-		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
-
-	/*
-	 * FIXME: As above...
-	 */
-	for_each_possible_cpu(cpu) {
-		rcu_read_lock_sched();
-		dl_b = dl_bw_of(cpu);
-
-		raw_spin_lock_irqsave(&dl_b->lock, flags);
-		dl_b->bw = new_bw;
-		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
-
-		rcu_read_unlock_sched();
-	}
-}
-
-static int sched_rt_global_validate(void)
-{
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
-	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
-		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
-		return -EINVAL;
-
-	return 0;
-}
-
-static void sched_rt_do_global(void)
-{
-	def_rt_bandwidth.rt_runtime = global_rt_runtime();
-	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
-}
-
-int sched_rt_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
-{
-	int old_period, old_runtime;
-	static DEFINE_MUTEX(mutex);
-	int ret;
-
-	mutex_lock(&mutex);
-	old_period = sysctl_sched_rt_period;
-	old_runtime = sysctl_sched_rt_runtime;
-
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-
-	if (!ret && write) {
-		ret = sched_rt_global_validate();
-		if (ret)
-			goto undo;
-
-		ret = sched_dl_global_validate();
-		if (ret)
-			goto undo;
-
-		ret = sched_rt_global_constraints();
-		if (ret)
-			goto undo;
-
-		sched_rt_do_global();
-		sched_dl_do_global();
-	}
-	if (0) {
-undo:
-		sysctl_sched_rt_period = old_period;
-		sysctl_sched_rt_runtime = old_runtime;
-	}
-	mutex_unlock(&mutex);
-
-	return ret;
-}
-
-int sched_rr_handler(struct ctl_table *table, int write,
-		void __user *buffer, size_t *lenp,
-		loff_t *ppos)
-{
-	int ret;
-	static DEFINE_MUTEX(mutex);
-
-	mutex_lock(&mutex);
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
-	/*
-	 * Make sure that internally we keep jiffies.
-	 * Also, writing zero resets the timeslice to default:
-	 */
-	if (!ret && write) {
-		sched_rr_timeslice =
-			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
-			msecs_to_jiffies(sysctl_sched_rr_timeslice);
-	}
-	mutex_unlock(&mutex);
-	return ret;
-}
-
-#ifdef CONFIG_CGROUP_SCHED
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
 {
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index aea3135c5d90..67c70e287647 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -615,19 +615,13 @@ static void cputime_adjust(struct task_cputime *curr,
 	 * userspace. Once a task gets some ticks, the monotonicy code at
 	 * 'update' will ensure things converge to the observed ratio.
 	 */
-	if (stime == 0) {
-		utime = rtime;
-		goto update;
+	if (stime != 0) {
+		if (utime == 0)
+			stime = rtime;
+		else
+			stime = scale_stime(stime, rtime, stime + utime);
 	}
 
-	if (utime == 0) {
-		stime = rtime;
-		goto update;
-	}
-
-	stime = scale_stime(stime, rtime, stime + utime);
-
-update:
 	/*
 	 * Make sure stime doesn't go backwards; this preserves monotonicity
 	 * for utime because rtime is monotonic.
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a2ce59015642..a84299f44b5d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -17,6 +17,7 @@
 #include "sched.h"
 
 #include <linux/slab.h>
+#include <uapi/linux/sched/types.h>
 
 struct dl_bandwidth def_dl_bandwidth;
 
@@ -43,6 +44,254 @@ static inline int on_dl_rq(struct sched_dl_entity *dl_se)
 	return !RB_EMPTY_NODE(&dl_se->rb_node);
 }
 
+#ifdef CONFIG_SMP
+static inline struct dl_bw *dl_bw_of(int i)
+{
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	return &cpu_rq(i)->rd->dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	int cpus = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cpus++;
+
+	return cpus;
+}
+#else
+static inline struct dl_bw *dl_bw_of(int i)
+{
+	return &cpu_rq(i)->dl.dl_bw;
+}
+
+static inline int dl_bw_cpus(int i)
+{
+	return 1;
+}
+#endif
+
+static inline
+void add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->running_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->running_bw += dl_bw;
+	SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
+	SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
+}
+
+static inline
+void sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->running_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->running_bw -= dl_bw;
+	SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
+	if (dl_rq->running_bw > old)
+		dl_rq->running_bw = 0;
+}
+
+static inline
+void add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->this_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->this_bw += dl_bw;
+	SCHED_WARN_ON(dl_rq->this_bw < old); /* overflow */
+}
+
+static inline
+void sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
+{
+	u64 old = dl_rq->this_bw;
+
+	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	dl_rq->this_bw -= dl_bw;
+	SCHED_WARN_ON(dl_rq->this_bw > old); /* underflow */
+	if (dl_rq->this_bw > old)
+		dl_rq->this_bw = 0;
+	SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
+}
+
+void dl_change_utilization(struct task_struct *p, u64 new_bw)
+{
+	struct rq *rq;
+
+	if (task_on_rq_queued(p))
+		return;
+
+	rq = task_rq(p);
+	if (p->dl.dl_non_contending) {
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
+		p->dl.dl_non_contending = 0;
+		/*
+		 * If the timer handler is currently running and the
+		 * timer cannot be cancelled, inactive_task_timer()
+		 * will see that dl_not_contending is not set, and
+		 * will not touch the rq's active utilization,
+		 * so we are still safe.
+		 */
+		if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
+			put_task_struct(p);
+	}
+	sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	add_rq_bw(new_bw, &rq->dl);
+}
+
+/*
+ * The utilization of a task cannot be immediately removed from
+ * the rq active utilization (running_bw) when the task blocks.
+ * Instead, we have to wait for the so called "0-lag time".
+ *
+ * If a task blocks before the "0-lag time", a timer (the inactive
+ * timer) is armed, and running_bw is decreased when the timer
+ * fires.
+ *
+ * If the task wakes up again before the inactive timer fires,
+ * the timer is cancelled, whereas if the task wakes up after the
+ * inactive timer fired (and running_bw has been decreased) the
+ * task's utilization has to be added to running_bw again.
+ * A flag in the deadline scheduling entity (dl_non_contending)
+ * is used to avoid race conditions between the inactive timer handler
+ * and task wakeups.
+ *
+ * The following diagram shows how running_bw is updated. A task is
+ * "ACTIVE" when its utilization contributes to running_bw; an
+ * "ACTIVE contending" task is in the TASK_RUNNING state, while an
+ * "ACTIVE non contending" task is a blocked task for which the "0-lag time"
+ * has not passed yet. An "INACTIVE" task is a task for which the "0-lag"
+ * time already passed, which does not contribute to running_bw anymore.
+ *                              +------------------+
+ *             wakeup           |    ACTIVE        |
+ *          +------------------>+   contending     |
+ *          | add_running_bw    |                  |
+ *          |                   +----+------+------+
+ *          |                        |      ^
+ *          |                dequeue |      |
+ * +--------+-------+                |      |
+ * |                |   t >= 0-lag   |      | wakeup
+ * |    INACTIVE    |<---------------+      |
+ * |                | sub_running_bw |      |
+ * +--------+-------+                |      |
+ *          ^                        |      |
+ *          |              t < 0-lag |      |
+ *          |                        |      |
+ *          |                        V      |
+ *          |                   +----+------+------+
+ *          | sub_running_bw    |    ACTIVE        |
+ *          +-------------------+                  |
+ *            inactive timer    |  non contending  |
+ *            fired             +------------------+
+ *
+ * The task_non_contending() function is invoked when a task
+ * blocks, and checks if the 0-lag time already passed or
+ * not (in the first case, it directly updates running_bw;
+ * in the second case, it arms the inactive timer).
+ *
+ * The task_contending() function is invoked when a task wakes
+ * up, and checks if the task is still in the "ACTIVE non contending"
+ * state or not (in the second case, it updates running_bw).
+ */
+static void task_non_contending(struct task_struct *p)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+	struct hrtimer *timer = &dl_se->inactive_timer;
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+	struct rq *rq = rq_of_dl_rq(dl_rq);
+	s64 zerolag_time;
+
+	/*
+	 * If this is a non-deadline task that has been boosted,
+	 * do nothing
+	 */
+	if (dl_se->dl_runtime == 0)
+		return;
+
+	WARN_ON(hrtimer_active(&dl_se->inactive_timer));
+	WARN_ON(dl_se->dl_non_contending);
+
+	zerolag_time = dl_se->deadline -
+		 div64_long((dl_se->runtime * dl_se->dl_period),
+			dl_se->dl_runtime);
+
+	/*
+	 * Using relative times instead of the absolute "0-lag time"
+	 * allows to simplify the code
+	 */
+	zerolag_time -= rq_clock(rq);
+
+	/*
+	 * If the "0-lag time" already passed, decrease the active
+	 * utilization now, instead of starting a timer
+	 */
+	if (zerolag_time < 0) {
+		if (dl_task(p))
+			sub_running_bw(dl_se->dl_bw, dl_rq);
+		if (!dl_task(p) || p->state == TASK_DEAD) {
+			struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+			if (p->state == TASK_DEAD)
+				sub_rq_bw(p->dl.dl_bw, &rq->dl);
+			raw_spin_lock(&dl_b->lock);
+			__dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
+			__dl_clear_params(p);
+			raw_spin_unlock(&dl_b->lock);
+		}
+
+		return;
+	}
+
+	dl_se->dl_non_contending = 1;
+	get_task_struct(p);
+	hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
+}
+
+static void task_contending(struct sched_dl_entity *dl_se, int flags)
+{
+	struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
+
+	/*
+	 * If this is a non-deadline task that has been boosted,
+	 * do nothing
+	 */
+	if (dl_se->dl_runtime == 0)
+		return;
+
+	if (flags & ENQUEUE_MIGRATED)
+		add_rq_bw(dl_se->dl_bw, dl_rq);
+
+	if (dl_se->dl_non_contending) {
+		dl_se->dl_non_contending = 0;
+		/*
+		 * If the timer handler is currently running and the
+		 * timer cannot be cancelled, inactive_task_timer()
+		 * will see that dl_not_contending is not set, and
+		 * will not touch the rq's active utilization,
+		 * so we are still safe.
+		 */
+		if (hrtimer_try_to_cancel(&dl_se->inactive_timer) == 1)
+			put_task_struct(dl_task_of(dl_se));
+	} else {
+		/*
+		 * Since "dl_non_contending" is not set, the
+		 * task's utilization has already been removed from
+		 * active utilization (either when the task blocked,
+		 * when the "inactive timer" fired).
+		 * So, add it back.
+		 */
+		add_running_bw(dl_se->dl_bw, dl_rq);
+	}
+}
+
 static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 {
 	struct sched_dl_entity *dl_se = &p->dl;
@@ -83,6 +332,10 @@ void init_dl_rq(struct dl_rq *dl_rq)
 #else
 	init_dl_bw(&dl_rq->dl_bw);
 #endif
+
+	dl_rq->running_bw = 0;
+	dl_rq->this_bw = 0;
+	init_dl_rq_bw_ratio(dl_rq);
 }
 
 #ifdef CONFIG_SMP
@@ -484,13 +737,84 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se,
 }
 
 /*
- * When a -deadline entity is queued back on the runqueue, its runtime and
- * deadline might need updating.
+ * Revised wakeup rule [1]: For self-suspending tasks, rather then
+ * re-initializing task's runtime and deadline, the revised wakeup
+ * rule adjusts the task's runtime to avoid the task to overrun its
+ * density.
+ *
+ * Reasoning: a task may overrun the density if:
+ *    runtime / (deadline - t) > dl_runtime / dl_deadline
+ *
+ * Therefore, runtime can be adjusted to:
+ *     runtime = (dl_runtime / dl_deadline) * (deadline - t)
+ *
+ * In such way that runtime will be equal to the maximum density
+ * the task can use without breaking any rule.
+ *
+ * [1] Luca Abeni, Giuseppe Lipari, and Juri Lelli. 2015. Constant
+ * bandwidth server revisited. SIGBED Rev. 11, 4 (January 2015), 19-24.
+ */
+static void
+update_dl_revised_wakeup(struct sched_dl_entity *dl_se, struct rq *rq)
+{
+	u64 laxity = dl_se->deadline - rq_clock(rq);
+
+	/*
+	 * If the task has deadline < period, and the deadline is in the past,
+	 * it should already be throttled before this check.
+	 *
+	 * See update_dl_entity() comments for further details.
+	 */
+	WARN_ON(dl_time_before(dl_se->deadline, rq_clock(rq)));
+
+	dl_se->runtime = (dl_se->dl_density * laxity) >> BW_SHIFT;
+}
+
+/*
+ * Regarding the deadline, a task with implicit deadline has a relative
+ * deadline == relative period. A task with constrained deadline has a
+ * relative deadline <= relative period.
+ *
+ * We support constrained deadline tasks. However, there are some restrictions
+ * applied only for tasks which do not have an implicit deadline. See
+ * update_dl_entity() to know more about such restrictions.
+ *
+ * The dl_is_implicit() returns true if the task has an implicit deadline.
+ */
+static inline bool dl_is_implicit(struct sched_dl_entity *dl_se)
+{
+	return dl_se->dl_deadline == dl_se->dl_period;
+}
+
+/*
+ * When a deadline entity is placed in the runqueue, its runtime and deadline
+ * might need to be updated. This is done by a CBS wake up rule. There are two
+ * different rules: 1) the original CBS; and 2) the Revisited CBS.
+ *
+ * When the task is starting a new period, the Original CBS is used. In this
+ * case, the runtime is replenished and a new absolute deadline is set.
+ *
+ * When a task is queued before the begin of the next period, using the
+ * remaining runtime and deadline could make the entity to overflow, see
+ * dl_entity_overflow() to find more about runtime overflow. When such case
+ * is detected, the runtime and deadline need to be updated.
+ *
+ * If the task has an implicit deadline, i.e., deadline == period, the Original
+ * CBS is applied. the runtime is replenished and a new absolute deadline is
+ * set, as in the previous cases.
+ *
+ * However, the Original CBS does not work properly for tasks with
+ * deadline < period, which are said to have a constrained deadline. By
+ * applying the Original CBS, a constrained deadline task would be able to run
+ * runtime/deadline in a period. With deadline < period, the task would
+ * overrun the runtime/period allowed bandwidth, breaking the admission test.
  *
- * The policy here is that we update the deadline of the entity only if:
- *  - the current deadline is in the past,
- *  - using the remaining runtime with the current deadline would make
- *    the entity exceed its bandwidth.
+ * In order to prevent this misbehave, the Revisited CBS is used for
+ * constrained deadline tasks when a runtime overflow is detected. In the
+ * Revisited CBS, rather than replenishing & setting a new absolute deadline,
+ * the remaining runtime of the task is reduced to avoid runtime overflow.
+ * Please refer to the comments update_dl_revised_wakeup() function to find
+ * more about the Revised CBS rule.
  */
 static void update_dl_entity(struct sched_dl_entity *dl_se,
 			     struct sched_dl_entity *pi_se)
@@ -500,6 +824,14 @@ static void update_dl_entity(struct sched_dl_entity *dl_se,
 
 	if (dl_time_before(dl_se->deadline, rq_clock(rq)) ||
 	    dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) {
+
+		if (unlikely(!dl_is_implicit(dl_se) &&
+			     !dl_time_before(dl_se->deadline, rq_clock(rq)) &&
+			     !dl_se->dl_boosted)){
+			update_dl_revised_wakeup(dl_se, rq);
+			return;
+		}
+
 		dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
 		dl_se->runtime = pi_se->dl_runtime;
 	}
@@ -593,10 +925,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 	 * The task might have changed its scheduling policy to something
 	 * different than SCHED_DEADLINE (through switched_from_dl()).
 	 */
-	if (!dl_task(p)) {
-		__dl_clear_params(p);
+	if (!dl_task(p))
 		goto unlock;
-	}
 
 	/*
 	 * The task might have been boosted by someone else and might be in the
@@ -723,6 +1053,8 @@ static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se)
 		if (unlikely(dl_se->dl_boosted || !start_dl_timer(p)))
 			return;
 		dl_se->dl_throttled = 1;
+		if (dl_se->runtime > 0)
+			dl_se->runtime = 0;
 	}
 }
 
@@ -735,6 +1067,47 @@ int dl_runtime_exceeded(struct sched_dl_entity *dl_se)
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
 
 /*
+ * This function implements the GRUB accounting rule:
+ * according to the GRUB reclaiming algorithm, the runtime is
+ * not decreased as "dq = -dt", but as
+ * "dq = -max{u / Umax, (1 - Uinact - Uextra)} dt",
+ * where u is the utilization of the task, Umax is the maximum reclaimable
+ * utilization, Uinact is the (per-runqueue) inactive utilization, computed
+ * as the difference between the "total runqueue utilization" and the
+ * runqueue active utilization, and Uextra is the (per runqueue) extra
+ * reclaimable utilization.
+ * Since rq->dl.running_bw and rq->dl.this_bw contain utilizations
+ * multiplied by 2^BW_SHIFT, the result has to be shifted right by
+ * BW_SHIFT.
+ * Since rq->dl.bw_ratio contains 1 / Umax multipled by 2^RATIO_SHIFT,
+ * dl_bw is multiped by rq->dl.bw_ratio and shifted right by RATIO_SHIFT.
+ * Since delta is a 64 bit variable, to have an overflow its value
+ * should be larger than 2^(64 - 20 - 8), which is more than 64 seconds.
+ * So, overflow is not an issue here.
+ */
+u64 grub_reclaim(u64 delta, struct rq *rq, struct sched_dl_entity *dl_se)
+{
+	u64 u_inact = rq->dl.this_bw - rq->dl.running_bw; /* Utot - Uact */
+	u64 u_act;
+	u64 u_act_min = (dl_se->dl_bw * rq->dl.bw_ratio) >> RATIO_SHIFT;
+
+	/*
+	 * Instead of computing max{u * bw_ratio, (1 - u_inact - u_extra)},
+	 * we compare u_inact + rq->dl.extra_bw with
+	 * 1 - (u * rq->dl.bw_ratio >> RATIO_SHIFT), because
+	 * u_inact + rq->dl.extra_bw can be larger than
+	 * 1 * (so, 1 - u_inact - rq->dl.extra_bw would be negative
+	 * leading to wrong results)
+	 */
+	if (u_inact + rq->dl.extra_bw > BW_UNIT - u_act_min)
+		u_act = u_act_min;
+	else
+		u_act = BW_UNIT - u_inact - rq->dl.extra_bw;
+
+	return (delta * u_act) >> BW_SHIFT;
+}
+
+/*
  * Update the current task's runtime statistics (provided it is still
  * a -deadline task and has not been removed from the dl_rq).
  */
@@ -776,6 +1149,8 @@ static void update_curr_dl(struct rq *rq)
 
 	sched_rt_avg_update(rq, delta_exec);
 
+	if (unlikely(dl_se->flags & SCHED_FLAG_RECLAIM))
+		delta_exec = grub_reclaim(delta_exec, rq, &curr->dl);
 	dl_se->runtime -= delta_exec;
 
 throttle:
@@ -815,6 +1190,56 @@ throttle:
 	}
 }
 
+static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer)
+{
+	struct sched_dl_entity *dl_se = container_of(timer,
+						     struct sched_dl_entity,
+						     inactive_timer);
+	struct task_struct *p = dl_task_of(dl_se);
+	struct rq_flags rf;
+	struct rq *rq;
+
+	rq = task_rq_lock(p, &rf);
+
+	if (!dl_task(p) || p->state == TASK_DEAD) {
+		struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+
+		if (p->state == TASK_DEAD && dl_se->dl_non_contending) {
+			sub_running_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl));
+			sub_rq_bw(p->dl.dl_bw, dl_rq_of_se(&p->dl));
+			dl_se->dl_non_contending = 0;
+		}
+
+		raw_spin_lock(&dl_b->lock);
+		__dl_clear(dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
+		raw_spin_unlock(&dl_b->lock);
+		__dl_clear_params(p);
+
+		goto unlock;
+	}
+	if (dl_se->dl_non_contending == 0)
+		goto unlock;
+
+	sched_clock_tick();
+	update_rq_clock(rq);
+
+	sub_running_bw(dl_se->dl_bw, &rq->dl);
+	dl_se->dl_non_contending = 0;
+unlock:
+	task_rq_unlock(rq, p, &rf);
+	put_task_struct(p);
+
+	return HRTIMER_NORESTART;
+}
+
+void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
+{
+	struct hrtimer *timer = &dl_se->inactive_timer;
+
+	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	timer->function = inactive_task_timer;
+}
+
 #ifdef CONFIG_SMP
 
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
@@ -946,10 +1371,12 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
 	 * parameters of the task might need updating. Otherwise,
 	 * we want a replenishment of its runtime.
 	 */
-	if (flags & ENQUEUE_WAKEUP)
+	if (flags & ENQUEUE_WAKEUP) {
+		task_contending(dl_se, flags);
 		update_dl_entity(dl_se, pi_se);
-	else if (flags & ENQUEUE_REPLENISH)
+	} else if (flags & ENQUEUE_REPLENISH) {
 		replenish_dl_entity(dl_se, pi_se);
+	}
 
 	__enqueue_dl_entity(dl_se);
 }
@@ -959,11 +1386,6 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se)
 	__dequeue_dl_entity(dl_se);
 }
 
-static inline bool dl_is_constrained(struct sched_dl_entity *dl_se)
-{
-	return dl_se->dl_deadline < dl_se->dl_period;
-}
-
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct task_struct *pi_task = rt_mutex_get_top_task(p);
@@ -995,17 +1417,32 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 	 * If that is the case, the task will be throttled and
 	 * the replenishment timer will be set to the next period.
 	 */
-	if (!p->dl.dl_throttled && dl_is_constrained(&p->dl))
+	if (!p->dl.dl_throttled && !dl_is_implicit(&p->dl))
 		dl_check_constrained_dl(&p->dl);
 
+	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & ENQUEUE_RESTORE) {
+		add_rq_bw(p->dl.dl_bw, &rq->dl);
+		add_running_bw(p->dl.dl_bw, &rq->dl);
+	}
+
 	/*
-	 * If p is throttled, we do nothing. In fact, if it exhausted
+	 * If p is throttled, we do not enqueue it. In fact, if it exhausted
 	 * its budget it needs a replenishment and, since it now is on
 	 * its rq, the bandwidth timer callback (which clearly has not
 	 * run yet) will take care of this.
+	 * However, the active utilization does not depend on the fact
+	 * that the task is on the runqueue or not (but depends on the
+	 * task's state - in GRUB parlance, "inactive" vs "active contending").
+	 * In other words, even if a task is throttled its utilization must
+	 * be counted in the active utilization; hence, we need to call
+	 * add_running_bw().
 	 */
-	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH))
+	if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) {
+		if (flags & ENQUEUE_WAKEUP)
+			task_contending(&p->dl, flags);
+
 		return;
+	}
 
 	enqueue_dl_entity(&p->dl, pi_se, flags);
 
@@ -1023,6 +1460,23 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
 	update_curr_dl(rq);
 	__dequeue_task_dl(rq, p, flags);
+
+	if (p->on_rq == TASK_ON_RQ_MIGRATING || flags & DEQUEUE_SAVE) {
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
+		sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	}
+
+	/*
+	 * This check allows to start the inactive timer (or to immediately
+	 * decrease the active utilization, if needed) in two cases:
+	 * when the task blocks and when it is terminating
+	 * (p->state == TASK_DEAD). We can handle the two cases in the same
+	 * way, because from GRUB's point of view the same thing is happening
+	 * (the task moves from "active contending" to "active non contending"
+	 * or "inactive")
+	 */
+	if (flags & DEQUEUE_SLEEP)
+		task_non_contending(p);
 }
 
 /*
@@ -1100,6 +1554,37 @@ out:
 	return cpu;
 }
 
+static void migrate_task_rq_dl(struct task_struct *p)
+{
+	struct rq *rq;
+
+	if (p->state != TASK_WAKING)
+		return;
+
+	rq = task_rq(p);
+	/*
+	 * Since p->state == TASK_WAKING, set_task_cpu() has been called
+	 * from try_to_wake_up(). Hence, p->pi_lock is locked, but
+	 * rq->lock is not... So, lock it
+	 */
+	raw_spin_lock(&rq->lock);
+	if (p->dl.dl_non_contending) {
+		sub_running_bw(p->dl.dl_bw, &rq->dl);
+		p->dl.dl_non_contending = 0;
+		/*
+		 * If the timer handler is currently running and the
+		 * timer cannot be cancelled, inactive_task_timer()
+		 * will see that dl_not_contending is not set, and
+		 * will not touch the rq's active utilization,
+		 * so we are still safe.
+		 */
+		if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
+			put_task_struct(p);
+	}
+	sub_rq_bw(p->dl.dl_bw, &rq->dl);
+	raw_spin_unlock(&rq->lock);
+}
+
 static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
 {
 	/*
@@ -1255,19 +1740,6 @@ static void task_fork_dl(struct task_struct *p)
 	 */
 }
 
-static void task_dead_dl(struct task_struct *p)
-{
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
-
-	/*
-	 * Since we are TASK_DEAD we won't slip out of the domain!
-	 */
-	raw_spin_lock_irq(&dl_b->lock);
-	/* XXX we should retain the bw until 0-lag */
-	dl_b->total_bw -= p->dl.dl_bw;
-	raw_spin_unlock_irq(&dl_b->lock);
-}
-
 static void set_curr_task_dl(struct rq *rq)
 {
 	struct task_struct *p = rq->curr;
@@ -1533,7 +2005,7 @@ retry:
 		 * then possible that next_task has migrated.
 		 */
 		task = pick_next_pushable_dl_task(rq);
-		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+		if (task == next_task) {
 			/*
 			 * The task is still there. We don't try
 			 * again, some other cpu will pull it when ready.
@@ -1551,7 +2023,11 @@ retry:
 	}
 
 	deactivate_task(rq, next_task, 0);
+	sub_running_bw(next_task->dl.dl_bw, &rq->dl);
+	sub_rq_bw(next_task->dl.dl_bw, &rq->dl);
 	set_task_cpu(next_task, later_rq->cpu);
+	add_rq_bw(next_task->dl.dl_bw, &later_rq->dl);
+	add_running_bw(next_task->dl.dl_bw, &later_rq->dl);
 	activate_task(later_rq, next_task, 0);
 	ret = 1;
 
@@ -1639,7 +2115,11 @@ static void pull_dl_task(struct rq *this_rq)
 			resched = true;
 
 			deactivate_task(src_rq, p, 0);
+			sub_running_bw(p->dl.dl_bw, &src_rq->dl);
+			sub_rq_bw(p->dl.dl_bw, &src_rq->dl);
 			set_task_cpu(p, this_cpu);
+			add_rq_bw(p->dl.dl_bw, &this_rq->dl);
+			add_running_bw(p->dl.dl_bw, &this_rq->dl);
 			activate_task(this_rq, p, 0);
 			dmin = p->dl.deadline;
 
@@ -1695,7 +2175,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 		 * until we complete the update.
 		 */
 		raw_spin_lock(&src_dl_b->lock);
-		__dl_clear(src_dl_b, p->dl.dl_bw);
+		__dl_clear(src_dl_b, p->dl.dl_bw, dl_bw_cpus(task_cpu(p)));
 		raw_spin_unlock(&src_dl_b->lock);
 	}
 
@@ -1737,13 +2217,26 @@ void __init init_sched_dl_class(void)
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
 	/*
-	 * Start the deadline timer; if we switch back to dl before this we'll
-	 * continue consuming our current CBS slice. If we stay outside of
-	 * SCHED_DEADLINE until the deadline passes, the timer will reset the
-	 * task.
+	 * task_non_contending() can start the "inactive timer" (if the 0-lag
+	 * time is in the future). If the task switches back to dl before
+	 * the "inactive timer" fires, it can continue to consume its current
+	 * runtime using its current deadline. If it stays outside of
+	 * SCHED_DEADLINE until the 0-lag time passes, inactive_task_timer()
+	 * will reset the task parameters.
 	 */
-	if (!start_dl_timer(p))
-		__dl_clear_params(p);
+	if (task_on_rq_queued(p) && p->dl.dl_runtime)
+		task_non_contending(p);
+
+	if (!task_on_rq_queued(p))
+		sub_rq_bw(p->dl.dl_bw, &rq->dl);
+
+	/*
+	 * We cannot use inactive_task_timer() to invoke sub_running_bw()
+	 * at the 0-lag time, because the task could have been migrated
+	 * while SCHED_OTHER in the meanwhile.
+	 */
+	if (p->dl.dl_non_contending)
+		p->dl.dl_non_contending = 0;
 
 	/*
 	 * Since this might be the only -deadline task on the rq,
@@ -1762,11 +2255,15 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
  */
 static void switched_to_dl(struct rq *rq, struct task_struct *p)
 {
+	if (hrtimer_try_to_cancel(&p->dl.inactive_timer) == 1)
+		put_task_struct(p);
 
 	/* If p is not queued we will update its parameters at next wakeup. */
-	if (!task_on_rq_queued(p))
-		return;
+	if (!task_on_rq_queued(p)) {
+		add_rq_bw(p->dl.dl_bw, &rq->dl);
 
+		return;
+	}
 	/*
 	 * If p is boosted we already updated its params in
 	 * rt_mutex_setprio()->enqueue_task(..., ENQUEUE_REPLENISH),
@@ -1836,6 +2333,7 @@ const struct sched_class dl_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_dl,
+	.migrate_task_rq	= migrate_task_rq_dl,
 	.set_cpus_allowed       = set_cpus_allowed_dl,
 	.rq_online              = rq_online_dl,
 	.rq_offline             = rq_offline_dl,
@@ -1845,7 +2343,6 @@ const struct sched_class dl_sched_class = {
 	.set_curr_task		= set_curr_task_dl,
 	.task_tick		= task_tick_dl,
 	.task_fork              = task_fork_dl,
-	.task_dead		= task_dead_dl,
 
 	.prio_changed           = prio_changed_dl,
 	.switched_from		= switched_from_dl,
@@ -1854,6 +2351,317 @@ const struct sched_class dl_sched_class = {
 	.update_curr		= update_curr_dl,
 };
 
+int sched_dl_global_validate(void)
+{
+	u64 runtime = global_rt_runtime();
+	u64 period = global_rt_period();
+	u64 new_bw = to_ratio(period, runtime);
+	struct dl_bw *dl_b;
+	int cpu, ret = 0;
+	unsigned long flags;
+
+	/*
+	 * Here we want to check the bandwidth not being set to some
+	 * value smaller than the currently allocated bandwidth in
+	 * any of the root_domains.
+	 *
+	 * FIXME: Cycling on all the CPUs is overdoing, but simpler than
+	 * cycling on root_domains... Discussion on different/better
+	 * solutions is welcome!
+	 */
+	for_each_possible_cpu(cpu) {
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		if (new_bw < dl_b->total_bw)
+			ret = -EBUSY;
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+		rcu_read_unlock_sched();
+
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+void init_dl_rq_bw_ratio(struct dl_rq *dl_rq)
+{
+	if (global_rt_runtime() == RUNTIME_INF) {
+		dl_rq->bw_ratio = 1 << RATIO_SHIFT;
+		dl_rq->extra_bw = 1 << BW_SHIFT;
+	} else {
+		dl_rq->bw_ratio = to_ratio(global_rt_runtime(),
+			  global_rt_period()) >> (BW_SHIFT - RATIO_SHIFT);
+		dl_rq->extra_bw = to_ratio(global_rt_period(),
+						    global_rt_runtime());
+	}
+}
+
+void sched_dl_do_global(void)
+{
+	u64 new_bw = -1;
+	struct dl_bw *dl_b;
+	int cpu;
+	unsigned long flags;
+
+	def_dl_bandwidth.dl_period = global_rt_period();
+	def_dl_bandwidth.dl_runtime = global_rt_runtime();
+
+	if (global_rt_runtime() != RUNTIME_INF)
+		new_bw = to_ratio(global_rt_period(), global_rt_runtime());
+
+	/*
+	 * FIXME: As above...
+	 */
+	for_each_possible_cpu(cpu) {
+		rcu_read_lock_sched();
+		dl_b = dl_bw_of(cpu);
+
+		raw_spin_lock_irqsave(&dl_b->lock, flags);
+		dl_b->bw = new_bw;
+		raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+
+		rcu_read_unlock_sched();
+		init_dl_rq_bw_ratio(&cpu_rq(cpu)->dl);
+	}
+}
+
+/*
+ * We must be sure that accepting a new task (or allowing changing the
+ * parameters of an existing one) is consistent with the bandwidth
+ * constraints. If yes, this function also accordingly updates the currently
+ * allocated bandwidth to reflect the new situation.
+ *
+ * This function is called while holding p's rq->lock.
+ */
+int sched_dl_overflow(struct task_struct *p, int policy,
+		      const struct sched_attr *attr)
+{
+	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
+	u64 period = attr->sched_period ?: attr->sched_deadline;
+	u64 runtime = attr->sched_runtime;
+	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
+	int cpus, err = -1;
+
+	/* !deadline task may carry old deadline bandwidth */
+	if (new_bw == p->dl.dl_bw && task_has_dl_policy(p))
+		return 0;
+
+	/*
+	 * Either if a task, enters, leave, or stays -deadline but changes
+	 * its parameters, we may need to update accordingly the total
+	 * allocated bandwidth of the container.
+	 */
+	raw_spin_lock(&dl_b->lock);
+	cpus = dl_bw_cpus(task_cpu(p));
+	if (dl_policy(policy) && !task_has_dl_policy(p) &&
+	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+		if (hrtimer_active(&p->dl.inactive_timer))
+			__dl_clear(dl_b, p->dl.dl_bw, cpus);
+		__dl_add(dl_b, new_bw, cpus);
+		err = 0;
+	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
+		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		/*
+		 * XXX this is slightly incorrect: when the task
+		 * utilization decreases, we should delay the total
+		 * utilization change until the task's 0-lag point.
+		 * But this would require to set the task's "inactive
+		 * timer" when the task is not inactive.
+		 */
+		__dl_clear(dl_b, p->dl.dl_bw, cpus);
+		__dl_add(dl_b, new_bw, cpus);
+		dl_change_utilization(p, new_bw);
+		err = 0;
+	} else if (!dl_policy(policy) && task_has_dl_policy(p)) {
+		/*
+		 * Do not decrease the total deadline utilization here,
+		 * switched_from_dl() will take care to do it at the correct
+		 * (0-lag) time.
+		 */
+		err = 0;
+	}
+	raw_spin_unlock(&dl_b->lock);
+
+	return err;
+}
+
+/*
+ * This function initializes the sched_dl_entity of a newly becoming
+ * SCHED_DEADLINE task.
+ *
+ * Only the static values are considered here, the actual runtime and the
+ * absolute deadline will be properly calculated when the task is enqueued
+ * for the first time with its new policy.
+ */
+void __setparam_dl(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	dl_se->dl_runtime = attr->sched_runtime;
+	dl_se->dl_deadline = attr->sched_deadline;
+	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
+	dl_se->flags = attr->sched_flags;
+	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
+	dl_se->dl_density = to_ratio(dl_se->dl_deadline, dl_se->dl_runtime);
+}
+
+void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	attr->sched_priority = p->rt_priority;
+	attr->sched_runtime = dl_se->dl_runtime;
+	attr->sched_deadline = dl_se->dl_deadline;
+	attr->sched_period = dl_se->dl_period;
+	attr->sched_flags = dl_se->flags;
+}
+
+/*
+ * This function validates the new parameters of a -deadline task.
+ * We ask for the deadline not being zero, and greater or equal
+ * than the runtime, as well as the period of being zero or
+ * greater than deadline. Furthermore, we have to be sure that
+ * user parameters are above the internal resolution of 1us (we
+ * check sched_runtime only since it is always the smaller one) and
+ * below 2^63 ns (we have to check both sched_deadline and
+ * sched_period, as the latter can be zero).
+ */
+bool __checkparam_dl(const struct sched_attr *attr)
+{
+	/* deadline != 0 */
+	if (attr->sched_deadline == 0)
+		return false;
+
+	/*
+	 * Since we truncate DL_SCALE bits, make sure we're at least
+	 * that big.
+	 */
+	if (attr->sched_runtime < (1ULL << DL_SCALE))
+		return false;
+
+	/*
+	 * Since we use the MSB for wrap-around and sign issues, make
+	 * sure it's not set (mind that period can be equal to zero).
+	 */
+	if (attr->sched_deadline & (1ULL << 63) ||
+	    attr->sched_period & (1ULL << 63))
+		return false;
+
+	/* runtime <= deadline <= period (if period != 0) */
+	if ((attr->sched_period != 0 &&
+	     attr->sched_period < attr->sched_deadline) ||
+	    attr->sched_deadline < attr->sched_runtime)
+		return false;
+
+	return true;
+}
+
+/*
+ * This function clears the sched_dl_entity static params.
+ */
+void __dl_clear_params(struct task_struct *p)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	dl_se->dl_runtime = 0;
+	dl_se->dl_deadline = 0;
+	dl_se->dl_period = 0;
+	dl_se->flags = 0;
+	dl_se->dl_bw = 0;
+	dl_se->dl_density = 0;
+
+	dl_se->dl_throttled = 0;
+	dl_se->dl_yielded = 0;
+	dl_se->dl_non_contending = 0;
+}
+
+bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
+{
+	struct sched_dl_entity *dl_se = &p->dl;
+
+	if (dl_se->dl_runtime != attr->sched_runtime ||
+	    dl_se->dl_deadline != attr->sched_deadline ||
+	    dl_se->dl_period != attr->sched_period ||
+	    dl_se->flags != attr->sched_flags)
+		return true;
+
+	return false;
+}
+
+#ifdef CONFIG_SMP
+int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
+{
+	unsigned int dest_cpu = cpumask_any_and(cpu_active_mask,
+							cs_cpus_allowed);
+	struct dl_bw *dl_b;
+	bool overflow;
+	int cpus, ret;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	dl_b = dl_bw_of(dest_cpu);
+	raw_spin_lock_irqsave(&dl_b->lock, flags);
+	cpus = dl_bw_cpus(dest_cpu);
+	overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+	if (overflow)
+		ret = -EBUSY;
+	else {
+		/*
+		 * We reserve space for this task in the destination
+		 * root_domain, as we can't fail after this point.
+		 * We will free resources in the source root_domain
+		 * later on (see set_cpus_allowed_dl()).
+		 */
+		__dl_add(dl_b, p->dl.dl_bw, cpus);
+		ret = 0;
+	}
+	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return ret;
+}
+
+int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
+				 const struct cpumask *trial)
+{
+	int ret = 1, trial_cpus;
+	struct dl_bw *cur_dl_b;
+	unsigned long flags;
+
+	rcu_read_lock_sched();
+	cur_dl_b = dl_bw_of(cpumask_any(cur));
+	trial_cpus = cpumask_weight(trial);
+
+	raw_spin_lock_irqsave(&cur_dl_b->lock, flags);
+	if (cur_dl_b->bw != -1 &&
+	    cur_dl_b->bw * trial_cpus < cur_dl_b->total_bw)
+		ret = 0;
+	raw_spin_unlock_irqrestore(&cur_dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return ret;
+}
+
+bool dl_cpu_busy(unsigned int cpu)
+{
+	unsigned long flags;
+	struct dl_bw *dl_b;
+	bool overflow;
+	int cpus;
+
+	rcu_read_lock_sched();
+	dl_b = dl_bw_of(cpu);
+	raw_spin_lock_irqsave(&dl_b->lock, flags);
+	cpus = dl_bw_cpus(cpu);
+	overflow = __dl_overflow(dl_b, cpus, 0, 0);
+	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
+	rcu_read_unlock_sched();
+	return overflow;
+}
+#endif
+
 #ifdef CONFIG_SCHED_DEBUG
 extern void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq);
 
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 38f019324f1a..4fa66de52bd6 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -552,15 +552,21 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq)
 
 #define P(x) \
 	SEQ_printf(m, "  .%-30s: %Ld\n", #x, (long long)(rt_rq->x))
+#define PU(x) \
+	SEQ_printf(m, "  .%-30s: %lu\n", #x, (unsigned long)(rt_rq->x))
 #define PN(x) \
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x))
 
-	P(rt_nr_running);
+	PU(rt_nr_running);
+#ifdef CONFIG_SMP
+	PU(rt_nr_migratory);
+#endif
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
 
 #undef PN
+#undef PU
 #undef P
 }
 
@@ -569,14 +575,21 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 	struct dl_bw *dl_bw;
 
 	SEQ_printf(m, "\ndl_rq[%d]:\n", cpu);
-	SEQ_printf(m, "  .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running);
+
+#define PU(x) \
+	SEQ_printf(m, "  .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x))
+
+	PU(dl_nr_running);
 #ifdef CONFIG_SMP
+	PU(dl_nr_migratory);
 	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
 #else
 	dl_bw = &dl_rq->dl_bw;
 #endif
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
+
+#undef PU
 }
 
 extern __read_mostly int sched_clock_running;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c77e4b1d51c0..008c514dc241 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -369,8 +369,9 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 }
 
 /* Iterate thr' all leaf cfs_rq's on a runqueue */
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-	list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)			\
+	list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list,	\
+				 leaf_cfs_rq_list)
 
 /* Do the two (enqueued) entities belong to the same group ? */
 static inline struct cfs_rq *
@@ -463,8 +464,8 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
 {
 }
 
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
-		for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos)	\
+		for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
 
 static inline struct sched_entity *parent_entity(struct sched_entity *se)
 {
@@ -1381,7 +1382,6 @@ static unsigned long weighted_cpuload(const int cpu);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
 static unsigned long capacity_of(int cpu);
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
@@ -2469,7 +2469,8 @@ void task_numa_work(struct callback_head *work)
 		return;
 
 
-	down_read(&mm->mmap_sem);
+	if (!down_read_trylock(&mm->mmap_sem))
+		return;
 	vma = find_vma(mm, start);
 	if (!vma) {
 		reset_ptenuma_scan(p);
@@ -2584,6 +2585,60 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr)
 		}
 	}
 }
+
+/*
+ * Can a task be moved from prev_cpu to this_cpu without causing a load
+ * imbalance that would trigger the load balancer?
+ */
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	struct numa_stats prev_load, this_load;
+	s64 this_eff_load, prev_eff_load;
+
+	update_numa_stats(&prev_load, cpu_to_node(prev_cpu));
+	update_numa_stats(&this_load, cpu_to_node(this_cpu));
+
+	/*
+	 * If sync wakeup then subtract the (maximum possible)
+	 * effect of the currently running task from the load
+	 * of the current CPU:
+	 */
+	if (sync) {
+		unsigned long current_load = task_h_load(current);
+
+		if (this_load.load > current_load)
+			this_load.load -= current_load;
+		else
+			this_load.load = 0;
+	}
+
+	/*
+	 * In low-load situations, where this_cpu's node is idle due to the
+	 * sync cause above having dropped this_load.load to 0, move the task.
+	 * Moving to an idle socket will not create a bad imbalance.
+	 *
+	 * Otherwise check if the nodes are near enough in load to allow this
+	 * task to be woken on this_cpu's node.
+	 */
+	if (this_load.load > 0) {
+		unsigned long task_load = task_h_load(p);
+
+		this_eff_load = 100;
+		this_eff_load *= prev_load.compute_capacity;
+
+		prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
+		prev_eff_load *= this_load.compute_capacity;
+
+		this_eff_load *= this_load.load + task_load;
+		prev_eff_load *= prev_load.load - task_load;
+
+		return this_eff_load <= prev_eff_load;
+	}
+
+	return true;
+}
 #else
 static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
@@ -2596,6 +2651,15 @@ static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p)
 {
 }
+
+#ifdef CONFIG_SMP
+static inline bool numa_wake_affine(struct sched_domain *sd,
+				    struct task_struct *p, int this_cpu,
+				    int prev_cpu, int sync)
+{
+	return true;
+}
+#endif /* !SMP */
 #endif /* CONFIG_NUMA_BALANCING */
 
 static void
@@ -2916,12 +2980,12 @@ ___update_load_avg(u64 now, int cpu, struct sched_avg *sa,
 	/*
 	 * Step 2: update *_avg.
 	 */
-	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX);
+	sa->load_avg = div_u64(sa->load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	if (cfs_rq) {
 		cfs_rq->runnable_load_avg =
-			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX);
+			div_u64(cfs_rq->runnable_load_sum, LOAD_AVG_MAX - 1024 + sa->period_contrib);
 	}
-	sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
+	sa->util_avg = sa->util_sum / (LOAD_AVG_MAX - 1024 + sa->period_contrib);
 
 	return 1;
 }
@@ -2982,8 +3046,7 @@ __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
  * differential update where we store the last value we propagated. This in
  * turn allows skipping updates if the differential is 'small'.
  *
- * Updating tg's load_avg is necessary before update_cfs_share() (which is
- * done) and effective_load() (which is not done because it is too costly).
+ * Updating tg's load_avg is necessary before update_cfs_share().
  */
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
 {
@@ -4642,24 +4705,43 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	hrtimer_cancel(&cfs_b->slack_timer);
 }
 
+/*
+ * Both these cpu hotplug callbacks race against unregister_fair_sched_group()
+ *
+ * The race is harmless, since modifying bandwidth settings of unhooked group
+ * bits doesn't do much.
+ */
+
+/* cpu online calback */
 static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
-		struct cfs_bandwidth *cfs_b = &cfs_rq->tg->cfs_bandwidth;
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
 		raw_spin_lock(&cfs_b->lock);
 		cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF;
 		raw_spin_unlock(&cfs_b->lock);
 	}
+	rcu_read_unlock();
 }
 
+/* cpu offline callback */
 static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
-	struct cfs_rq *cfs_rq;
+	struct task_group *tg;
+
+	lockdep_assert_held(&rq->lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(tg, &task_groups, list) {
+		struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
 		if (!cfs_rq->runtime_enabled)
 			continue;
 
@@ -4677,6 +4759,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 		if (cfs_rq_throttled(cfs_rq))
 			unthrottle_cfs_rq(cfs_rq);
 	}
+	rcu_read_unlock();
 }
 
 #else /* CONFIG_CFS_BANDWIDTH */
@@ -5215,126 +5298,6 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 	return 0;
 }
 
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
- * effective_load() calculates the load change as seen from the root_task_group
- *
- * Adding load to a group doesn't make a group heavier, but can cause movement
- * of group shares between cpus. Assuming the shares were perfectly aligned one
- * can calculate the shift in shares.
- *
- * Calculate the effective load difference if @wl is added (subtracted) to @tg
- * on this @cpu and results in a total addition (subtraction) of @wg to the
- * total group weight.
- *
- * Given a runqueue weight distribution (rw_i) we can compute a shares
- * distribution (s_i) using:
- *
- *   s_i = rw_i / \Sum rw_j						(1)
- *
- * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
- * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
- * shares distribution (s_i):
- *
- *   rw_i = {   2,   4,   1,   0 }
- *   s_i  = { 2/7, 4/7, 1/7,   0 }
- *
- * As per wake_affine() we're interested in the load of two CPUs (the CPU the
- * task used to run on and the CPU the waker is running on), we need to
- * compute the effect of waking a task on either CPU and, in case of a sync
- * wakeup, compute the effect of the current task going to sleep.
- *
- * So for a change of @wl to the local @cpu with an overall group weight change
- * of @wl we can compute the new shares distribution (s'_i) using:
- *
- *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)				(2)
- *
- * Suppose we're interested in CPUs 0 and 1, and want to compute the load
- * differences in waking a task to CPU 0. The additional task changes the
- * weight and shares distributions like:
- *
- *   rw'_i = {   3,   4,   1,   0 }
- *   s'_i  = { 3/8, 4/8, 1/8,   0 }
- *
- * We can then compute the difference in effective weight by using:
- *
- *   dw_i = S * (s'_i - s_i)						(3)
- *
- * Where 'S' is the group weight as seen by its parent.
- *
- * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
- * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
- * 4/7) times the weight of the group.
- */
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	struct sched_entity *se = tg->se[cpu];
-
-	if (!tg->parent)	/* the trivial, non-cgroup case */
-		return wl;
-
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = se->my_q;
-		long W, w = cfs_rq_load_avg(cfs_rq);
-
-		tg = cfs_rq->tg;
-
-		/*
-		 * W = @wg + \Sum rw_j
-		 */
-		W = wg + atomic_long_read(&tg->load_avg);
-
-		/* Ensure \Sum rw_j >= rw_i */
-		W -= cfs_rq->tg_load_avg_contrib;
-		W += w;
-
-		/*
-		 * w = rw_i + @wl
-		 */
-		w += wl;
-
-		/*
-		 * wl = S * s'_i; see (2)
-		 */
-		if (W > 0 && w < W)
-			wl = (w * (long)scale_load_down(tg->shares)) / W;
-		else
-			wl = scale_load_down(tg->shares);
-
-		/*
-		 * Per the above, wl is the new se->load.weight value; since
-		 * those are clipped to [MIN_SHARES, ...) do so now. See
-		 * calc_cfs_shares().
-		 */
-		if (wl < MIN_SHARES)
-			wl = MIN_SHARES;
-
-		/*
-		 * wl = dw_i = S * (s'_i - s_i); see (3)
-		 */
-		wl -= se->avg.load_avg;
-
-		/*
-		 * Recursively apply this logic to all parent groups to compute
-		 * the final effective load change on the root group. Since
-		 * only the @tg group gets extra weight, all parent groups can
-		 * only redistribute existing shares. @wl is the shift in shares
-		 * resulting from this level per the above.
-		 */
-		wg = 0;
-	}
-
-	return wl;
-}
-#else
-
-static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
-{
-	return wl;
-}
-
-#endif
-
 static void record_wakee(struct task_struct *p)
 {
 	/*
@@ -5385,67 +5348,25 @@ static int wake_wide(struct task_struct *p)
 static int wake_affine(struct sched_domain *sd, struct task_struct *p,
 		       int prev_cpu, int sync)
 {
-	s64 this_load, load;
-	s64 this_eff_load, prev_eff_load;
-	int idx, this_cpu;
-	struct task_group *tg;
-	unsigned long weight;
-	int balanced;
-
-	idx	  = sd->wake_idx;
-	this_cpu  = smp_processor_id();
-	load	  = source_load(prev_cpu, idx);
-	this_load = target_load(this_cpu, idx);
-
-	/*
-	 * If sync wakeup then subtract the (maximum possible)
-	 * effect of the currently running task from the load
-	 * of the current CPU:
-	 */
-	if (sync) {
-		tg = task_group(current);
-		weight = current->se.avg.load_avg;
-
-		this_load += effective_load(tg, this_cpu, -weight, -weight);
-		load += effective_load(tg, prev_cpu, 0, -weight);
-	}
-
-	tg = task_group(p);
-	weight = p->se.avg.load_avg;
+	int this_cpu = smp_processor_id();
+	bool affine = false;
 
 	/*
-	 * In low-load situations, where prev_cpu is idle and this_cpu is idle
-	 * due to the sync cause above having dropped this_load to 0, we'll
-	 * always have an imbalance, but there's really nothing you can do
-	 * about that, so that's good too.
-	 *
-	 * Otherwise check if either cpus are near enough in load to allow this
-	 * task to be woken on this_cpu.
+	 * Common case: CPUs are in the same socket, and select_idle_sibling()
+	 * will do its thing regardless of what we return:
 	 */
-	this_eff_load = 100;
-	this_eff_load *= capacity_of(prev_cpu);
-
-	prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2;
-	prev_eff_load *= capacity_of(this_cpu);
-
-	if (this_load > 0) {
-		this_eff_load *= this_load +
-			effective_load(tg, this_cpu, weight, weight);
-
-		prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight);
-	}
-
-	balanced = this_eff_load <= prev_eff_load;
+	if (cpus_share_cache(prev_cpu, this_cpu))
+		affine = true;
+	else
+		affine = numa_wake_affine(sd, p, this_cpu, prev_cpu, sync);
 
 	schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts);
+	if (affine) {
+		schedstat_inc(sd->ttwu_move_affine);
+		schedstat_inc(p->se.statistics.nr_wakeups_affine);
+	}
 
-	if (!balanced)
-		return 0;
-
-	schedstat_inc(sd->ttwu_move_affine);
-	schedstat_inc(p->se.statistics.nr_wakeups_affine);
-
-	return 1;
+	return affine;
 }
 
 static inline int task_util(struct task_struct *p);
@@ -5484,12 +5405,12 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		int i;
 
 		/* Skip over this group if it has no CPUs allowed */
-		if (!cpumask_intersects(sched_group_cpus(group),
+		if (!cpumask_intersects(sched_group_span(group),
 					&p->cpus_allowed))
 			continue;
 
 		local_group = cpumask_test_cpu(this_cpu,
-					       sched_group_cpus(group));
+					       sched_group_span(group));
 
 		/*
 		 * Tally up the load of all CPUs in the group and find
@@ -5499,7 +5420,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		runnable_load = 0;
 		max_spare_cap = 0;
 
-		for_each_cpu(i, sched_group_cpus(group)) {
+		for_each_cpu(i, sched_group_span(group)) {
 			/* Bias balancing toward cpus of our domain */
 			if (local_group)
 				load = source_load(i, load_idx);
@@ -5602,10 +5523,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 
 	/* Check if we have any choice: */
 	if (group->group_weight == 1)
-		return cpumask_first(sched_group_cpus(group));
+		return cpumask_first(sched_group_span(group));
 
 	/* Traverse only the allowed CPUs */
-	for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
+	for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
 		if (idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
@@ -5640,43 +5561,6 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 	return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu;
 }
 
-/*
- * Implement a for_each_cpu() variant that starts the scan at a given cpu
- * (@start), and wraps around.
- *
- * This is used to scan for idle CPUs; such that not all CPUs looking for an
- * idle CPU find the same CPU. The down-side is that tasks tend to cycle
- * through the LLC domain.
- *
- * Especially tbench is found sensitive to this.
- */
-
-static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped)
-{
-	int next;
-
-again:
-	next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1);
-
-	if (*wrapped) {
-		if (next >= start)
-			return nr_cpumask_bits;
-	} else {
-		if (next >= nr_cpumask_bits) {
-			*wrapped = 1;
-			n = -1;
-			goto again;
-		}
-	}
-
-	return next;
-}
-
-#define for_each_cpu_wrap(cpu, mask, start, wrap)				\
-	for ((wrap) = 0, (cpu) = (start)-1;					\
-		(cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)),	\
-		(cpu) < nr_cpumask_bits; )
-
 #ifdef CONFIG_SCHED_SMT
 
 static inline void set_idle_cores(int cpu, int val)
@@ -5736,7 +5620,7 @@ unlock:
 static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
-	int core, cpu, wrap;
+	int core, cpu;
 
 	if (!static_branch_likely(&sched_smt_present))
 		return -1;
@@ -5746,7 +5630,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
 	cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
 
-	for_each_cpu_wrap(core, cpus, target, wrap) {
+	for_each_cpu_wrap(core, cpus, target) {
 		bool idle = true;
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
@@ -5809,27 +5693,38 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd
 static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	struct sched_domain *this_sd;
-	u64 avg_cost, avg_idle = this_rq()->avg_idle;
+	u64 avg_cost, avg_idle;
 	u64 time, cost;
 	s64 delta;
-	int cpu, wrap;
+	int cpu, nr = INT_MAX;
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
 		return -1;
 
-	avg_cost = this_sd->avg_scan_cost;
-
 	/*
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
 	 */
-	if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
+	avg_idle = this_rq()->avg_idle / 512;
+	avg_cost = this_sd->avg_scan_cost + 1;
+
+	if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost)
 		return -1;
 
+	if (sched_feat(SIS_PROP)) {
+		u64 span_avg = sd->span_weight * avg_idle;
+		if (span_avg > 4*avg_cost)
+			nr = div_u64(span_avg, avg_cost);
+		else
+			nr = 4;
+	}
+
 	time = local_clock();
 
-	for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) {
+	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+		if (!--nr)
+			return -1;
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
 		if (idle_cpu(cpu))
@@ -6011,11 +5906,15 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 
 	if (affine_sd) {
 		sd = NULL; /* Prefer wake_affine over balance flags */
-		if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync))
+		if (cpu == prev_cpu)
+			goto pick_cpu;
+
+		if (wake_affine(affine_sd, p, prev_cpu, sync))
 			new_cpu = cpu;
 	}
 
 	if (!sd) {
+ pick_cpu:
 		if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */
 			new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
@@ -6168,8 +6067,11 @@ static void set_last_buddy(struct sched_entity *se)
 	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
 		return;
 
-	for_each_sched_entity(se)
+	for_each_sched_entity(se) {
+		if (SCHED_WARN_ON(!se->on_rq))
+			return;
 		cfs_rq_of(se)->last = se;
+	}
 }
 
 static void set_next_buddy(struct sched_entity *se)
@@ -6177,8 +6079,11 @@ static void set_next_buddy(struct sched_entity *se)
 	if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE))
 		return;
 
-	for_each_sched_entity(se)
+	for_each_sched_entity(se) {
+		if (SCHED_WARN_ON(!se->on_rq))
+			return;
 		cfs_rq_of(se)->next = se;
+	}
 }
 
 static void set_skip_buddy(struct sched_entity *se)
@@ -6686,6 +6591,10 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 	if (dst_nid == p->numa_preferred_nid)
 		return 0;
 
+	/* Leaving a core idle is often worse than degrading locality. */
+	if (env->idle != CPU_NOT_IDLE)
+		return -1;
+
 	if (numa_group) {
 		src_faults = group_faults(p, src_nid);
 		dst_faults = group_faults(p, dst_nid);
@@ -6970,10 +6879,28 @@ static void attach_tasks(struct lb_env *env)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+
+static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
+{
+	if (cfs_rq->load.weight)
+		return false;
+
+	if (cfs_rq->avg.load_sum)
+		return false;
+
+	if (cfs_rq->avg.util_sum)
+		return false;
+
+	if (cfs_rq->runnable_load_sum)
+		return false;
+
+	return true;
+}
+
 static void update_blocked_averages(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
@@ -6983,7 +6910,7 @@ static void update_blocked_averages(int cpu)
 	 * Iterates the task_group tree in a bottom up fashion, see
 	 * list_add_leaf_cfs_rq() for details.
 	 */
-	for_each_leaf_cfs_rq(rq, cfs_rq) {
+	for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
 		struct sched_entity *se;
 
 		/* throttled entities do not contribute to load */
@@ -6997,6 +6924,13 @@ static void update_blocked_averages(int cpu)
 		se = cfs_rq->tg->se[cpu];
 		if (se && !skip_blocked_update(se))
 			update_load_avg(se, 0);
+
+		/*
+		 * There can be a lot of idle CPU cgroups.  Don't let fully
+		 * decayed cfs_rqs linger on the list.
+		 */
+		if (cfs_rq_is_decayed(cfs_rq))
+			list_del_leaf_cfs_rq(cfs_rq);
 	}
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -7229,7 +7163,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 		 * span the current group.
 		 */
 
-		for_each_cpu(cpu, sched_group_cpus(sdg)) {
+		for_each_cpu(cpu, sched_group_span(sdg)) {
 			struct sched_group_capacity *sgc;
 			struct rq *rq = cpu_rq(cpu);
 
@@ -7408,7 +7342,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
 	memset(sgs, 0, sizeof(*sgs));
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		struct rq *rq = cpu_rq(i);
 
 		/* Bias balancing toward cpus of our domain */
@@ -7572,7 +7506,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		struct sg_lb_stats *sgs = &tmp_sgs;
 		int local_group;
 
-		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
+		local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg));
 		if (local_group) {
 			sds->local = sg;
 			sgs = local;
@@ -7927,7 +7861,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
 	unsigned long busiest_load = 0, busiest_capacity = 1;
 	int i;
 
-	for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
+	for_each_cpu_and(i, sched_group_span(group), env->cpus) {
 		unsigned long capacity, wl;
 		enum fbq_type rt;
 
@@ -8033,7 +7967,6 @@ static int active_load_balance_cpu_stop(void *data);
 static int should_we_balance(struct lb_env *env)
 {
 	struct sched_group *sg = env->sd->groups;
-	struct cpumask *sg_cpus, *sg_mask;
 	int cpu, balance_cpu = -1;
 
 	/*
@@ -8043,11 +7976,9 @@ static int should_we_balance(struct lb_env *env)
 	if (env->idle == CPU_NEWLY_IDLE)
 		return 1;
 
-	sg_cpus = sched_group_cpus(sg);
-	sg_mask = sched_group_mask(sg);
 	/* Try to find first idle cpu */
-	for_each_cpu_and(cpu, sg_cpus, env->cpus) {
-		if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu))
+	for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) {
+		if (!idle_cpu(cpu))
 			continue;
 
 		balance_cpu = cpu;
@@ -8083,7 +8014,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		.sd		= sd,
 		.dst_cpu	= this_cpu,
 		.dst_rq		= this_rq,
-		.dst_grpmask    = sched_group_cpus(sd->groups),
+		.dst_grpmask    = sched_group_span(sd->groups),
 		.idle		= idle,
 		.loop_break	= sched_nr_migrate_break,
 		.cpus		= cpus,
@@ -8659,6 +8590,10 @@ void nohz_balance_enter_idle(int cpu)
 	if (!cpu_active(cpu))
 		return;
 
+	/* Spare idle load balancing on CPUs that don't want to be disturbed: */
+	if (!is_housekeeping_cpu(cpu))
+		return;
+
 	if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
 		return;
 
@@ -9523,10 +9458,10 @@ const struct sched_class fair_sched_class = {
 #ifdef CONFIG_SCHED_DEBUG
 void print_cfs_stats(struct seq_file *m, int cpu)
 {
-	struct cfs_rq *cfs_rq;
+	struct cfs_rq *cfs_rq, *pos;
 
 	rcu_read_lock();
-	for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
+	for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
 		print_cfs_rq(m, cpu, cfs_rq);
 	rcu_read_unlock();
 }
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 11192e0cb122..d3fb15555291 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -55,6 +55,7 @@ SCHED_FEAT(TTWU_QUEUE, true)
  * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
  */
 SCHED_FEAT(SIS_AVG_CPU, false)
+SCHED_FEAT(SIS_PROP, true)
 
 /*
  * Issue a WARN when we do multiple update_rq_clock() calls
@@ -76,7 +77,6 @@ SCHED_FEAT(WARN_DOUBLE_CLOCK, false)
 SCHED_FEAT(RT_PUSH_IPI, true)
 #endif
 
-SCHED_FEAT(FORCE_SD_OVERLAP, false)
 SCHED_FEAT(RT_RUNTIME_SHARE, true)
 SCHED_FEAT(LB_MIN, false)
 SCHED_FEAT(ATTACH_AGE_LOAD, true)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index ef63adce0c9c..6c23e30c0e5c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -219,6 +219,7 @@ static void do_idle(void)
 	 */
 
 	__current_set_polling();
+	quiet_vmstat();
 	tick_nohz_idle_enter();
 
 	while (!need_resched()) {
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index f15fb2bdbc0d..f14716a3522f 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -117,7 +117,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active)
  * load-average relies on per-cpu sampling from the tick, it is affected by
  * NO_HZ.
  *
- * The basic idea is to fold the nr_active delta into a global idle-delta upon
+ * The basic idea is to fold the nr_active delta into a global NO_HZ-delta upon
  * entering NO_HZ state such that we can include this as an 'extra' cpu delta
  * when we read the global state.
  *
@@ -126,7 +126,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active)
  *  - When we go NO_HZ idle during the window, we can negate our sample
  *    contribution, causing under-accounting.
  *
- *    We avoid this by keeping two idle-delta counters and flipping them
+ *    We avoid this by keeping two NO_HZ-delta counters and flipping them
  *    when the window starts, thus separating old and new NO_HZ load.
  *
  *    The only trick is the slight shift in index flip for read vs write.
@@ -137,22 +137,22 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active)
  *    r:0 0 1           1 0           0 1           1 0
  *    w:0 1 1           0 0           1 1           0 0
  *
- *    This ensures we'll fold the old idle contribution in this window while
+ *    This ensures we'll fold the old NO_HZ contribution in this window while
  *    accumlating the new one.
  *
- *  - When we wake up from NO_HZ idle during the window, we push up our
+ *  - When we wake up from NO_HZ during the window, we push up our
  *    contribution, since we effectively move our sample point to a known
  *    busy state.
  *
  *    This is solved by pushing the window forward, and thus skipping the
- *    sample, for this cpu (effectively using the idle-delta for this cpu which
+ *    sample, for this cpu (effectively using the NO_HZ-delta for this cpu which
  *    was in effect at the time the window opened). This also solves the issue
- *    of having to deal with a cpu having been in NOHZ idle for multiple
- *    LOAD_FREQ intervals.
+ *    of having to deal with a cpu having been in NO_HZ for multiple LOAD_FREQ
+ *    intervals.
  *
  * When making the ILB scale, we should try to pull this in as well.
  */
-static atomic_long_t calc_load_idle[2];
+static atomic_long_t calc_load_nohz[2];
 static int calc_load_idx;
 
 static inline int calc_load_write_idx(void)
@@ -167,7 +167,7 @@ static inline int calc_load_write_idx(void)
 
 	/*
 	 * If the folding window started, make sure we start writing in the
-	 * next idle-delta.
+	 * next NO_HZ-delta.
 	 */
 	if (!time_before(jiffies, READ_ONCE(calc_load_update)))
 		idx++;
@@ -180,24 +180,24 @@ static inline int calc_load_read_idx(void)
 	return calc_load_idx & 1;
 }
 
-void calc_load_enter_idle(void)
+void calc_load_nohz_start(void)
 {
 	struct rq *this_rq = this_rq();
 	long delta;
 
 	/*
-	 * We're going into NOHZ mode, if there's any pending delta, fold it
-	 * into the pending idle delta.
+	 * We're going into NO_HZ mode, if there's any pending delta, fold it
+	 * into the pending NO_HZ delta.
 	 */
 	delta = calc_load_fold_active(this_rq, 0);
 	if (delta) {
 		int idx = calc_load_write_idx();
 
-		atomic_long_add(delta, &calc_load_idle[idx]);
+		atomic_long_add(delta, &calc_load_nohz[idx]);
 	}
 }
 
-void calc_load_exit_idle(void)
+void calc_load_nohz_stop(void)
 {
 	struct rq *this_rq = this_rq();
 
@@ -217,13 +217,13 @@ void calc_load_exit_idle(void)
 		this_rq->calc_load_update += LOAD_FREQ;
 }
 
-static long calc_load_fold_idle(void)
+static long calc_load_nohz_fold(void)
 {
 	int idx = calc_load_read_idx();
 	long delta = 0;
 
-	if (atomic_long_read(&calc_load_idle[idx]))
-		delta = atomic_long_xchg(&calc_load_idle[idx], 0);
+	if (atomic_long_read(&calc_load_nohz[idx]))
+		delta = atomic_long_xchg(&calc_load_nohz[idx], 0);
 
 	return delta;
 }
@@ -299,9 +299,9 @@ calc_load_n(unsigned long load, unsigned long exp,
 
 /*
  * NO_HZ can leave us missing all per-cpu ticks calling
- * calc_load_account_active(), but since an idle CPU folds its delta into
- * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
- * in the pending idle delta if our idle period crossed a load cycle boundary.
+ * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into
+ * calc_load_nohz per calc_load_nohz_start(), all we need to do is fold
+ * in the pending NO_HZ delta if our NO_HZ period crossed a load cycle boundary.
  *
  * Once we've updated the global active value, we need to apply the exponential
  * weights adjusted to the number of cycles missed.
@@ -330,7 +330,7 @@ static void calc_global_nohz(void)
 	}
 
 	/*
-	 * Flip the idle index...
+	 * Flip the NO_HZ index...
 	 *
 	 * Make sure we first write the new time then flip the index, so that
 	 * calc_load_write_idx() will see the new time when it reads the new
@@ -341,7 +341,7 @@ static void calc_global_nohz(void)
 }
 #else /* !CONFIG_NO_HZ_COMMON */
 
-static inline long calc_load_fold_idle(void) { return 0; }
+static inline long calc_load_nohz_fold(void) { return 0; }
 static inline void calc_global_nohz(void) { }
 
 #endif /* CONFIG_NO_HZ_COMMON */
@@ -362,9 +362,9 @@ void calc_global_load(unsigned long ticks)
 		return;
 
 	/*
-	 * Fold the 'old' idle-delta to include all NO_HZ cpus.
+	 * Fold the 'old' NO_HZ-delta to include all NO_HZ cpus.
 	 */
-	delta = calc_load_fold_idle();
+	delta = calc_load_nohz_fold();
 	if (delta)
 		atomic_long_add(delta, &calc_load_tasks);
 
@@ -378,7 +378,8 @@ void calc_global_load(unsigned long ticks)
 	WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ);
 
 	/*
-	 * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk.
+	 * In case we went to NO_HZ for multiple LOAD_FREQ intervals
+	 * catch up in bulk.
 	 */
 	calc_global_nohz();
 }
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 979b7341008a..45caf937ef90 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -840,6 +840,17 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		int enqueue = 0;
 		struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i);
 		struct rq *rq = rq_of_rt_rq(rt_rq);
+		int skip;
+
+		/*
+		 * When span == cpu_online_mask, taking each rq->lock
+		 * can be time-consuming. Try to avoid it when possible.
+		 */
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+		if (skip)
+			continue;
 
 		raw_spin_lock(&rq->lock);
 		if (rt_rq->rt_time) {
@@ -1819,7 +1830,7 @@ retry:
 		 * pushing.
 		 */
 		task = pick_next_pushable_task(rq);
-		if (task_cpu(next_task) == rq->cpu && task == next_task) {
+		if (task == next_task) {
 			/*
 			 * The task hasn't migrated, and is still the next
 			 * eligible task, but we failed to find a run-queue
@@ -2438,6 +2449,316 @@ const struct sched_class rt_sched_class = {
 	.update_curr		= update_curr_rt,
 };
 
+#ifdef CONFIG_RT_GROUP_SCHED
+/*
+ * Ensure that the real time constraints are schedulable.
+ */
+static DEFINE_MUTEX(rt_constraints_mutex);
+
+/* Must be called with tasklist_lock held */
+static inline int tg_has_rt_tasks(struct task_group *tg)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * Autogroups do not have RT tasks; see autogroup_create().
+	 */
+	if (task_group_is_autogroup(tg))
+		return 0;
+
+	for_each_process_thread(g, p) {
+		if (rt_task(p) && task_group(p) == tg)
+			return 1;
+	}
+
+	return 0;
+}
+
+struct rt_schedulable_data {
+	struct task_group *tg;
+	u64 rt_period;
+	u64 rt_runtime;
+};
+
+static int tg_rt_schedulable(struct task_group *tg, void *data)
+{
+	struct rt_schedulable_data *d = data;
+	struct task_group *child;
+	unsigned long total, sum = 0;
+	u64 period, runtime;
+
+	period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	runtime = tg->rt_bandwidth.rt_runtime;
+
+	if (tg == d->tg) {
+		period = d->rt_period;
+		runtime = d->rt_runtime;
+	}
+
+	/*
+	 * Cannot have more runtime than the period.
+	 */
+	if (runtime > period && runtime != RUNTIME_INF)
+		return -EINVAL;
+
+	/*
+	 * Ensure we don't starve existing RT tasks.
+	 */
+	if (rt_bandwidth_enabled() && !runtime && tg_has_rt_tasks(tg))
+		return -EBUSY;
+
+	total = to_ratio(period, runtime);
+
+	/*
+	 * Nobody can have more than the global setting allows.
+	 */
+	if (total > to_ratio(global_rt_period(), global_rt_runtime()))
+		return -EINVAL;
+
+	/*
+	 * The sum of our children's runtime should not exceed our own.
+	 */
+	list_for_each_entry_rcu(child, &tg->children, siblings) {
+		period = ktime_to_ns(child->rt_bandwidth.rt_period);
+		runtime = child->rt_bandwidth.rt_runtime;
+
+		if (child == d->tg) {
+			period = d->rt_period;
+			runtime = d->rt_runtime;
+		}
+
+		sum += to_ratio(period, runtime);
+	}
+
+	if (sum > total)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime)
+{
+	int ret;
+
+	struct rt_schedulable_data data = {
+		.tg = tg,
+		.rt_period = period,
+		.rt_runtime = runtime,
+	};
+
+	rcu_read_lock();
+	ret = walk_tg_tree(tg_rt_schedulable, tg_nop, &data);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int tg_set_rt_bandwidth(struct task_group *tg,
+		u64 rt_period, u64 rt_runtime)
+{
+	int i, err = 0;
+
+	/*
+	 * Disallowing the root group RT runtime is BAD, it would disallow the
+	 * kernel creating (and or operating) RT threads.
+	 */
+	if (tg == &root_task_group && rt_runtime == 0)
+		return -EINVAL;
+
+	/* No period doesn't make any sense. */
+	if (rt_period == 0)
+		return -EINVAL;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	err = __rt_schedulable(tg, rt_period, rt_runtime);
+	if (err)
+		goto unlock;
+
+	raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+	tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period);
+	tg->rt_bandwidth.rt_runtime = rt_runtime;
+
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = tg->rt_rq[i];
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = rt_runtime;
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
+unlock:
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return err;
+}
+
+int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
+	if (rt_runtime_us < 0)
+		rt_runtime = RUNTIME_INF;
+
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_runtime(struct task_group *tg)
+{
+	u64 rt_runtime_us;
+
+	if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF)
+		return -1;
+
+	rt_runtime_us = tg->rt_bandwidth.rt_runtime;
+	do_div(rt_runtime_us, NSEC_PER_USEC);
+	return rt_runtime_us;
+}
+
+int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
+{
+	u64 rt_runtime, rt_period;
+
+	rt_period = rt_period_us * NSEC_PER_USEC;
+	rt_runtime = tg->rt_bandwidth.rt_runtime;
+
+	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
+}
+
+long sched_group_rt_period(struct task_group *tg)
+{
+	u64 rt_period_us;
+
+	rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period);
+	do_div(rt_period_us, NSEC_PER_USEC);
+	return rt_period_us;
+}
+
+static int sched_rt_global_constraints(void)
+{
+	int ret = 0;
+
+	mutex_lock(&rt_constraints_mutex);
+	read_lock(&tasklist_lock);
+	ret = __rt_schedulable(NULL, 0, 0);
+	read_unlock(&tasklist_lock);
+	mutex_unlock(&rt_constraints_mutex);
+
+	return ret;
+}
+
+int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
+{
+	/* Don't accept realtime tasks when there is no way for them to run */
+	if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0)
+		return 0;
+
+	return 1;
+}
+
+#else /* !CONFIG_RT_GROUP_SCHED */
+static int sched_rt_global_constraints(void)
+{
+	unsigned long flags;
+	int i;
+
+	raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags);
+	for_each_possible_cpu(i) {
+		struct rt_rq *rt_rq = &cpu_rq(i)->rt;
+
+		raw_spin_lock(&rt_rq->rt_runtime_lock);
+		rt_rq->rt_runtime = global_rt_runtime();
+		raw_spin_unlock(&rt_rq->rt_runtime_lock);
+	}
+	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
+
+	return 0;
+}
+#endif /* CONFIG_RT_GROUP_SCHED */
+
+static int sched_rt_global_validate(void)
+{
+	if (sysctl_sched_rt_period <= 0)
+		return -EINVAL;
+
+	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
+		(sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void sched_rt_do_global(void)
+{
+	def_rt_bandwidth.rt_runtime = global_rt_runtime();
+	def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period());
+}
+
+int sched_rt_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int old_period, old_runtime;
+	static DEFINE_MUTEX(mutex);
+	int ret;
+
+	mutex_lock(&mutex);
+	old_period = sysctl_sched_rt_period;
+	old_runtime = sysctl_sched_rt_runtime;
+
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+
+	if (!ret && write) {
+		ret = sched_rt_global_validate();
+		if (ret)
+			goto undo;
+
+		ret = sched_dl_global_validate();
+		if (ret)
+			goto undo;
+
+		ret = sched_rt_global_constraints();
+		if (ret)
+			goto undo;
+
+		sched_rt_do_global();
+		sched_dl_do_global();
+	}
+	if (0) {
+undo:
+		sysctl_sched_rt_period = old_period;
+		sysctl_sched_rt_runtime = old_runtime;
+	}
+	mutex_unlock(&mutex);
+
+	return ret;
+}
+
+int sched_rr_handler(struct ctl_table *table, int write,
+		void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+	static DEFINE_MUTEX(mutex);
+
+	mutex_lock(&mutex);
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	/*
+	 * Make sure that internally we keep jiffies.
+	 * Also, writing zero resets the timeslice to default:
+	 */
+	if (!ret && write) {
+		sched_rr_timeslice =
+			sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE :
+			msecs_to_jiffies(sysctl_sched_rr_timeslice);
+	}
+	mutex_unlock(&mutex);
+	return ret;
+}
+
 #ifdef CONFIG_SCHED_DEBUG
 extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6dda2aab731e..eeef1a3086d1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -39,9 +39,9 @@
 #include "cpuacct.h"
 
 #ifdef CONFIG_SCHED_DEBUG
-#define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
+# define SCHED_WARN_ON(x)	WARN_ONCE(x, #x)
 #else
-#define SCHED_WARN_ON(x)	((void)(x))
+# define SCHED_WARN_ON(x)	({ (void)(x), 0; })
 #endif
 
 struct rq;
@@ -218,23 +218,25 @@ static inline int dl_bandwidth_enabled(void)
 	return sysctl_sched_rt_runtime >= 0;
 }
 
-extern struct dl_bw *dl_bw_of(int i);
-
 struct dl_bw {
 	raw_spinlock_t lock;
 	u64 bw, total_bw;
 };
 
+static inline void __dl_update(struct dl_bw *dl_b, s64 bw);
+
 static inline
-void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
+void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 {
 	dl_b->total_bw -= tsk_bw;
+	__dl_update(dl_b, (s32)tsk_bw / cpus);
 }
 
 static inline
-void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
+void __dl_add(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
 {
 	dl_b->total_bw += tsk_bw;
+	__dl_update(dl_b, -((s32)tsk_bw / cpus));
 }
 
 static inline
@@ -244,7 +246,22 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
 	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
 }
 
+void dl_change_utilization(struct task_struct *p, u64 new_bw);
 extern void init_dl_bw(struct dl_bw *dl_b);
+extern int sched_dl_global_validate(void);
+extern void sched_dl_do_global(void);
+extern int sched_dl_overflow(struct task_struct *p, int policy,
+			     const struct sched_attr *attr);
+extern void __setparam_dl(struct task_struct *p, const struct sched_attr *attr);
+extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
+extern bool __checkparam_dl(const struct sched_attr *attr);
+extern void __dl_clear_params(struct task_struct *p);
+extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
+extern int dl_task_can_attach(struct task_struct *p,
+			      const struct cpumask *cs_cpus_allowed);
+extern int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
+					const struct cpumask *trial);
+extern bool dl_cpu_busy(unsigned int cpu);
 
 #ifdef CONFIG_CGROUP_SCHED
 
@@ -366,6 +383,11 @@ extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent
 extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
 		struct sched_rt_entity *rt_se, int cpu,
 		struct sched_rt_entity *parent);
+extern int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us);
+extern int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us);
+extern long sched_group_rt_runtime(struct task_group *tg);
+extern long sched_group_rt_period(struct task_group *tg);
+extern int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk);
 
 extern struct task_group *sched_create_group(struct task_group *parent);
 extern void sched_online_group(struct task_group *tg,
@@ -558,6 +580,30 @@ struct dl_rq {
 #else
 	struct dl_bw dl_bw;
 #endif
+	/*
+	 * "Active utilization" for this runqueue: increased when a
+	 * task wakes up (becomes TASK_RUNNING) and decreased when a
+	 * task blocks
+	 */
+	u64 running_bw;
+
+	/*
+	 * Utilization of the tasks "assigned" to this runqueue (including
+	 * the tasks that are in runqueue and the tasks that executed on this
+	 * CPU and blocked). Increased when a task moves to this runqueue, and
+	 * decreased when the task moves away (migrates, changes scheduling
+	 * policy, or terminates).
+	 * This is needed to compute the "inactive utilization" for the
+	 * runqueue (inactive utilization = this_bw - running_bw).
+	 */
+	u64 this_bw;
+	u64 extra_bw;
+
+	/*
+	 * Inverse of the fraction of CPU utilization that can be reclaimed
+	 * by the GRUB algorithm.
+	 */
+	u64 bw_ratio;
 };
 
 #ifdef CONFIG_SMP
@@ -606,11 +652,9 @@ struct root_domain {
 
 extern struct root_domain def_root_domain;
 extern struct mutex sched_domains_mutex;
-extern cpumask_var_t fallback_doms;
-extern cpumask_var_t sched_domains_tmpmask;
 
 extern void init_defrootdomain(void);
-extern int init_sched_domains(const struct cpumask *cpu_map);
+extern int sched_init_domains(const struct cpumask *cpu_map);
 extern void rq_attach_root(struct rq *rq, struct root_domain *rd);
 
 #endif /* CONFIG_SMP */
@@ -1025,7 +1069,11 @@ struct sched_group_capacity {
 	unsigned long next_update;
 	int imbalance; /* XXX unrelated to capacity but shared group state */
 
-	unsigned long cpumask[0]; /* iteration mask */
+#ifdef CONFIG_SCHED_DEBUG
+	int id;
+#endif
+
+	unsigned long cpumask[0]; /* balance mask */
 };
 
 struct sched_group {
@@ -1046,16 +1094,15 @@ struct sched_group {
 	unsigned long cpumask[0];
 };
 
-static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
+static inline struct cpumask *sched_group_span(struct sched_group *sg)
 {
 	return to_cpumask(sg->cpumask);
 }
 
 /*
- * cpumask masking which cpus in the group are allowed to iterate up the domain
- * tree.
+ * See build_balance_mask().
  */
-static inline struct cpumask *sched_group_mask(struct sched_group *sg)
+static inline struct cpumask *group_balance_mask(struct sched_group *sg)
 {
 	return to_cpumask(sg->sgc->cpumask);
 }
@@ -1066,7 +1113,7 @@ static inline struct cpumask *sched_group_mask(struct sched_group *sg)
  */
 static inline unsigned int group_first_cpu(struct sched_group *group)
 {
-	return cpumask_first(sched_group_cpus(group));
+	return cpumask_first(sched_group_span(group));
 }
 
 extern int group_balance_cpu(struct sched_group *sg);
@@ -1422,7 +1469,11 @@ static inline void set_curr_task(struct rq *rq, struct task_struct *curr)
 	curr->sched_class->set_curr_task(rq);
 }
 
+#ifdef CONFIG_SMP
 #define sched_class_highest (&stop_sched_class)
+#else
+#define sched_class_highest (&dl_sched_class)
+#endif
 #define for_each_class(class) \
    for (class = sched_class_highest; class; class = class->next)
 
@@ -1486,7 +1537,12 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime
 extern struct dl_bandwidth def_dl_bandwidth;
 extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
 extern void init_dl_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se);
+extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
 
+#define BW_SHIFT	20
+#define BW_UNIT		(1 << BW_SHIFT)
+#define RATIO_SHIFT	8
 unsigned long to_ratio(u64 period, u64 runtime);
 
 extern void init_entity_runnable_average(struct sched_entity *se);
@@ -1928,6 +1984,33 @@ extern void nohz_balance_exit_idle(unsigned int cpu);
 static inline void nohz_balance_exit_idle(unsigned int cpu) { }
 #endif
 
+
+#ifdef CONFIG_SMP
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct root_domain *rd = container_of(dl_b, struct root_domain, dl_bw);
+	int i;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+	for_each_cpu_and(i, rd->span, cpu_active_mask) {
+		struct rq *rq = cpu_rq(i);
+
+		rq->dl.extra_bw += bw;
+	}
+}
+#else
+static inline
+void __dl_update(struct dl_bw *dl_b, s64 bw)
+{
+	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
+
+	dl->extra_bw += bw;
+}
+#endif
+
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 struct irqtime {
 	u64			total;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 1b0b4fb12837..79895aec281e 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -10,6 +10,7 @@ DEFINE_MUTEX(sched_domains_mutex);
 
 /* Protected by sched_domains_mutex: */
 cpumask_var_t sched_domains_tmpmask;
+cpumask_var_t sched_domains_tmpmask2;
 
 #ifdef CONFIG_SCHED_DEBUG
 
@@ -35,7 +36,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 
 	cpumask_clear(groupmask);
 
-	printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
+	printk(KERN_DEBUG "%*s domain-%d: ", level, "", level);
 
 	if (!(sd->flags & SD_LOAD_BALANCE)) {
 		printk("does not load-balance\n");
@@ -45,14 +46,14 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		return -1;
 	}
 
-	printk(KERN_CONT "span %*pbl level %s\n",
+	printk(KERN_CONT "span=%*pbl level=%s\n",
 	       cpumask_pr_args(sched_domain_span(sd)), sd->name);
 
 	if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
 		printk(KERN_ERR "ERROR: domain->span does not contain "
 				"CPU%d\n", cpu);
 	}
-	if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) {
+	if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
 		printk(KERN_ERR "ERROR: domain->groups does not contain"
 				" CPU%d\n", cpu);
 	}
@@ -65,29 +66,47 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!cpumask_weight(sched_group_cpus(group))) {
+		if (!cpumask_weight(sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: empty group\n");
 			break;
 		}
 
 		if (!(sd->flags & SD_OVERLAP) &&
-		    cpumask_intersects(groupmask, sched_group_cpus(group))) {
+		    cpumask_intersects(groupmask, sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
 			break;
 		}
 
-		cpumask_or(groupmask, groupmask, sched_group_cpus(group));
+		cpumask_or(groupmask, groupmask, sched_group_span(group));
 
-		printk(KERN_CONT " %*pbl",
-		       cpumask_pr_args(sched_group_cpus(group)));
-		if (group->sgc->capacity != SCHED_CAPACITY_SCALE) {
-			printk(KERN_CONT " (cpu_capacity = %lu)",
-				group->sgc->capacity);
+		printk(KERN_CONT " %d:{ span=%*pbl",
+				group->sgc->id,
+				cpumask_pr_args(sched_group_span(group)));
+
+		if ((sd->flags & SD_OVERLAP) &&
+		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
+			printk(KERN_CONT " mask=%*pbl",
+				cpumask_pr_args(group_balance_mask(group)));
+		}
+
+		if (group->sgc->capacity != SCHED_CAPACITY_SCALE)
+			printk(KERN_CONT " cap=%lu", group->sgc->capacity);
+
+		if (group == sd->groups && sd->child &&
+		    !cpumask_equal(sched_domain_span(sd->child),
+				   sched_group_span(group))) {
+			printk(KERN_ERR "ERROR: domain->groups does not match domain->child\n");
 		}
 
+		printk(KERN_CONT " }");
+
 		group = group->next;
+
+		if (group != sd->groups)
+			printk(KERN_CONT ",");
+
 	} while (group != sd->groups);
 	printk(KERN_CONT "\n");
 
@@ -113,7 +132,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
 		return;
 	}
 
-	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
+	printk(KERN_DEBUG "CPU%d attaching sched-domain(s):\n", cpu);
 
 	for (;;) {
 		if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask))
@@ -477,46 +496,214 @@ enum s_alloc {
 };
 
 /*
- * Build an iteration mask that can exclude certain CPUs from the upwards
- * domain traversal.
+ * Return the canonical balance CPU for this group, this is the first CPU
+ * of this group that's also in the balance mask.
  *
- * Asymmetric node setups can result in situations where the domain tree is of
- * unequal depth, make sure to skip domains that already cover the entire
- * range.
+ * The balance mask are all those CPUs that could actually end up at this
+ * group. See build_balance_mask().
  *
- * In that case build_sched_domains() will have terminated the iteration early
- * and our sibling sd spans will be empty. Domains should always include the
- * CPU they're built on, so check that.
+ * Also see should_we_balance().
  */
-static void build_group_mask(struct sched_domain *sd, struct sched_group *sg)
+int group_balance_cpu(struct sched_group *sg)
 {
-	const struct cpumask *span = sched_domain_span(sd);
+	return cpumask_first(group_balance_mask(sg));
+}
+
+
+/*
+ * NUMA topology (first read the regular topology blurb below)
+ *
+ * Given a node-distance table, for example:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  30  20
+ *     1:  20  10  20  30
+ *     2:  30  20  10  20
+ *     3:  20  30  20  10
+ *
+ * which represents a 4 node ring topology like:
+ *
+ *   0 ----- 1
+ *   |       |
+ *   |       |
+ *   |       |
+ *   3 ----- 2
+ *
+ * We want to construct domains and groups to represent this. The way we go
+ * about doing this is to build the domains on 'hops'. For each NUMA level we
+ * construct the mask of all nodes reachable in @level hops.
+ *
+ * For the above NUMA topology that gives 3 levels:
+ *
+ * NUMA-2	0-3		0-3		0-3		0-3
+ *  groups:	{0-1,3},{1-3}	{0-2},{0,2-3}	{1-3},{0-1,3}	{0,2-3},{0-2}
+ *
+ * NUMA-1	0-1,3		0-2		1-3		0,2-3
+ *  groups:	{0},{1},{3}	{0},{1},{2}	{1},{2},{3}	{0},{2},{3}
+ *
+ * NUMA-0	0		1		2		3
+ *
+ *
+ * As can be seen; things don't nicely line up as with the regular topology.
+ * When we iterate a domain in child domain chunks some nodes can be
+ * represented multiple times -- hence the "overlap" naming for this part of
+ * the topology.
+ *
+ * In order to minimize this overlap, we only build enough groups to cover the
+ * domain. For instance Node-0 NUMA-2 would only get groups: 0-1,3 and 1-3.
+ *
+ * Because:
+ *
+ *  - the first group of each domain is its child domain; this
+ *    gets us the first 0-1,3
+ *  - the only uncovered node is 2, who's child domain is 1-3.
+ *
+ * However, because of the overlap, computing a unique CPU for each group is
+ * more complicated. Consider for instance the groups of NODE-1 NUMA-2, both
+ * groups include the CPUs of Node-0, while those CPUs would not in fact ever
+ * end up at those groups (they would end up in group: 0-1,3).
+ *
+ * To correct this we have to introduce the group balance mask. This mask
+ * will contain those CPUs in the group that can reach this group given the
+ * (child) domain tree.
+ *
+ * With this we can once again compute balance_cpu and sched_group_capacity
+ * relations.
+ *
+ * XXX include words on how balance_cpu is unique and therefore can be
+ * used for sched_group_capacity links.
+ *
+ *
+ * Another 'interesting' topology is:
+ *
+ *   node   0   1   2   3
+ *     0:  10  20  20  30
+ *     1:  20  10  20  20
+ *     2:  20  20  10  20
+ *     3:  30  20  20  10
+ *
+ * Which looks a little like:
+ *
+ *   0 ----- 1
+ *   |     / |
+ *   |   /   |
+ *   | /     |
+ *   2 ----- 3
+ *
+ * This topology is asymmetric, nodes 1,2 are fully connected, but nodes 0,3
+ * are not.
+ *
+ * This leads to a few particularly weird cases where the sched_domain's are
+ * not of the same number for each cpu. Consider:
+ *
+ * NUMA-2	0-3						0-3
+ *  groups:	{0-2},{1-3}					{1-3},{0-2}
+ *
+ * NUMA-1	0-2		0-3		0-3		1-3
+ *
+ * NUMA-0	0		1		2		3
+ *
+ */
+
+
+/*
+ * Build the balance mask; it contains only those CPUs that can arrive at this
+ * group and should be considered to continue balancing.
+ *
+ * We do this during the group creation pass, therefore the group information
+ * isn't complete yet, however since each group represents a (child) domain we
+ * can fully construct this using the sched_domain bits (which are already
+ * complete).
+ */
+static void
+build_balance_mask(struct sched_domain *sd, struct sched_group *sg, struct cpumask *mask)
+{
+	const struct cpumask *sg_span = sched_group_span(sg);
 	struct sd_data *sdd = sd->private;
 	struct sched_domain *sibling;
 	int i;
 
-	for_each_cpu(i, span) {
+	cpumask_clear(mask);
+
+	for_each_cpu(i, sg_span) {
 		sibling = *per_cpu_ptr(sdd->sd, i);
-		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
+
+		/*
+		 * Can happen in the asymmetric case, where these siblings are
+		 * unused. The mask will not be empty because those CPUs that
+		 * do have the top domain _should_ span the domain.
+		 */
+		if (!sibling->child)
 			continue;
 
-		cpumask_set_cpu(i, sched_group_mask(sg));
+		/* If we would not end up here, we can't continue from here */
+		if (!cpumask_equal(sg_span, sched_domain_span(sibling->child)))
+			continue;
+
+		cpumask_set_cpu(i, mask);
 	}
+
+	/* We must not have empty masks here */
+	WARN_ON_ONCE(cpumask_empty(mask));
 }
 
 /*
- * Return the canonical balance CPU for this group, this is the first CPU
- * of this group that's also in the iteration mask.
+ * XXX: This creates per-node group entries; since the load-balancer will
+ * immediately access remote memory to construct this group's load-balance
+ * statistics having the groups node local is of dubious benefit.
  */
-int group_balance_cpu(struct sched_group *sg)
+static struct sched_group *
+build_group_from_child_sched_domain(struct sched_domain *sd, int cpu)
 {
-	return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg));
+	struct sched_group *sg;
+	struct cpumask *sg_span;
+
+	sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+			GFP_KERNEL, cpu_to_node(cpu));
+
+	if (!sg)
+		return NULL;
+
+	sg_span = sched_group_span(sg);
+	if (sd->child)
+		cpumask_copy(sg_span, sched_domain_span(sd->child));
+	else
+		cpumask_copy(sg_span, sched_domain_span(sd));
+
+	return sg;
+}
+
+static void init_overlap_sched_group(struct sched_domain *sd,
+				     struct sched_group *sg)
+{
+	struct cpumask *mask = sched_domains_tmpmask2;
+	struct sd_data *sdd = sd->private;
+	struct cpumask *sg_span;
+	int cpu;
+
+	build_balance_mask(sd, sg, mask);
+	cpu = cpumask_first_and(sched_group_span(sg), mask);
+
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	if (atomic_inc_return(&sg->sgc->ref) == 1)
+		cpumask_copy(group_balance_mask(sg), mask);
+	else
+		WARN_ON_ONCE(!cpumask_equal(group_balance_mask(sg), mask));
+
+	/*
+	 * Initialize sgc->capacity such that even if we mess up the
+	 * domains and no possible iteration will get us here, we won't
+	 * die on a /0 trap.
+	 */
+	sg_span = sched_group_span(sg);
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
 }
 
 static int
 build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 {
-	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	struct sched_group *first = NULL, *last = NULL, *sg;
 	const struct cpumask *span = sched_domain_span(sd);
 	struct cpumask *covered = sched_domains_tmpmask;
 	struct sd_data *sdd = sd->private;
@@ -525,7 +712,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct cpumask *sg_span;
 
 		if (cpumask_test_cpu(i, covered))
@@ -533,44 +720,27 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 
 		sibling = *per_cpu_ptr(sdd->sd, i);
 
-		/* See the comment near build_group_mask(). */
+		/*
+		 * Asymmetric node setups can result in situations where the
+		 * domain tree is of unequal depth, make sure to skip domains
+		 * that already cover the entire range.
+		 *
+		 * In that case build_sched_domains() will have terminated the
+		 * iteration early and our sibling sd spans will be empty.
+		 * Domains should always include the CPU they're built on, so
+		 * check that.
+		 */
 		if (!cpumask_test_cpu(i, sched_domain_span(sibling)))
 			continue;
 
-		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
-				GFP_KERNEL, cpu_to_node(cpu));
-
+		sg = build_group_from_child_sched_domain(sibling, cpu);
 		if (!sg)
 			goto fail;
 
-		sg_span = sched_group_cpus(sg);
-		if (sibling->child)
-			cpumask_copy(sg_span, sched_domain_span(sibling->child));
-		else
-			cpumask_set_cpu(i, sg_span);
-
+		sg_span = sched_group_span(sg);
 		cpumask_or(covered, covered, sg_span);
 
-		sg->sgc = *per_cpu_ptr(sdd->sgc, i);
-		if (atomic_inc_return(&sg->sgc->ref) == 1)
-			build_group_mask(sd, sg);
-
-		/*
-		 * Initialize sgc->capacity such that even if we mess up the
-		 * domains and no possible iteration will get us here, we won't
-		 * die on a /0 trap.
-		 */
-		sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span);
-		sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
-
-		/*
-		 * Make sure the first group of this domain contains the
-		 * canonical balance CPU. Otherwise the sched_domain iteration
-		 * breaks. See update_sg_lb_stats().
-		 */
-		if ((!groups && cpumask_test_cpu(cpu, sg_span)) ||
-		    group_balance_cpu(sg) == cpu)
-			groups = sg;
+		init_overlap_sched_group(sd, sg);
 
 		if (!first)
 			first = sg;
@@ -579,7 +749,7 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu)
 		last = sg;
 		last->next = first;
 	}
-	sd->groups = groups;
+	sd->groups = first;
 
 	return 0;
 
@@ -589,23 +759,106 @@ fail:
 	return -ENOMEM;
 }
 
-static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
+
+/*
+ * Package topology (also see the load-balance blurb in fair.c)
+ *
+ * The scheduler builds a tree structure to represent a number of important
+ * topology features. By default (default_topology[]) these include:
+ *
+ *  - Simultaneous multithreading (SMT)
+ *  - Multi-Core Cache (MC)
+ *  - Package (DIE)
+ *
+ * Where the last one more or less denotes everything up to a NUMA node.
+ *
+ * The tree consists of 3 primary data structures:
+ *
+ *	sched_domain -> sched_group -> sched_group_capacity
+ *	    ^ ^             ^ ^
+ *          `-'             `-'
+ *
+ * The sched_domains are per-cpu and have a two way link (parent & child) and
+ * denote the ever growing mask of CPUs belonging to that level of topology.
+ *
+ * Each sched_domain has a circular (double) linked list of sched_group's, each
+ * denoting the domains of the level below (or individual CPUs in case of the
+ * first domain level). The sched_group linked by a sched_domain includes the
+ * CPU of that sched_domain [*].
+ *
+ * Take for instance a 2 threaded, 2 core, 2 cache cluster part:
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * DIE  [                             ]
+ * MC   [             ] [             ]
+ * SMT  [     ] [     ] [     ] [     ]
+ *
+ *  - or -
+ *
+ * DIE  0-7 0-7 0-7 0-7 0-7 0-7 0-7 0-7
+ * MC	0-3 0-3 0-3 0-3 4-7 4-7 4-7 4-7
+ * SMT  0-1 0-1 2-3 2-3 4-5 4-5 6-7 6-7
+ *
+ * CPU   0   1   2   3   4   5   6   7
+ *
+ * One way to think about it is: sched_domain moves you up and down among these
+ * topology levels, while sched_group moves you sideways through it, at child
+ * domain granularity.
+ *
+ * sched_group_capacity ensures each unique sched_group has shared storage.
+ *
+ * There are two related construction problems, both require a CPU that
+ * uniquely identify each group (for a given domain):
+ *
+ *  - The first is the balance_cpu (see should_we_balance() and the
+ *    load-balance blub in fair.c); for each group we only want 1 CPU to
+ *    continue balancing at a higher domain.
+ *
+ *  - The second is the sched_group_capacity; we want all identical groups
+ *    to share a single sched_group_capacity.
+ *
+ * Since these topologies are exclusive by construction. That is, its
+ * impossible for an SMT thread to belong to multiple cores, and cores to
+ * be part of multiple caches. There is a very clear and unique location
+ * for each CPU in the hierarchy.
+ *
+ * Therefore computing a unique CPU for each group is trivial (the iteration
+ * mask is redundant and set all 1s; all CPUs in a group will end up at _that_
+ * group), we can simply pick the first CPU in each group.
+ *
+ *
+ * [*] in other words, the first group of each domain is its child domain.
+ */
+
+static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 {
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
 	struct sched_domain *child = sd->child;
+	struct sched_group *sg;
 
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
 
-	if (sg) {
-		*sg = *per_cpu_ptr(sdd->sg, cpu);
-		(*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+	sg = *per_cpu_ptr(sdd->sg, cpu);
+	sg->sgc = *per_cpu_ptr(sdd->sgc, cpu);
+
+	/* For claim_allocations: */
+	atomic_inc(&sg->ref);
+	atomic_inc(&sg->sgc->ref);
 
-		/* For claim_allocations: */
-		atomic_set(&(*sg)->sgc->ref, 1);
+	if (child) {
+		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
+		cpumask_copy(group_balance_mask(sg), sched_group_span(sg));
+	} else {
+		cpumask_set_cpu(cpu, sched_group_span(sg));
+		cpumask_set_cpu(cpu, group_balance_mask(sg));
 	}
 
-	return cpu;
+	sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sched_group_span(sg));
+	sg->sgc->min_capacity = SCHED_CAPACITY_SCALE;
+
+	return sg;
 }
 
 /*
@@ -624,34 +877,20 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 	struct cpumask *covered;
 	int i;
 
-	get_group(cpu, sdd, &sd->groups);
-	atomic_inc(&sd->groups->ref);
-
-	if (cpu != cpumask_first(span))
-		return 0;
-
 	lockdep_assert_held(&sched_domains_mutex);
 	covered = sched_domains_tmpmask;
 
 	cpumask_clear(covered);
 
-	for_each_cpu(i, span) {
+	for_each_cpu_wrap(i, span, cpu) {
 		struct sched_group *sg;
-		int group, j;
 
 		if (cpumask_test_cpu(i, covered))
 			continue;
 
-		group = get_group(i, sdd, &sg);
-		cpumask_setall(sched_group_mask(sg));
+		sg = get_group(i, sdd);
 
-		for_each_cpu(j, span) {
-			if (get_group(j, sdd, NULL) != group)
-				continue;
-
-			cpumask_set_cpu(j, covered);
-			cpumask_set_cpu(j, sched_group_cpus(sg));
-		}
+		cpumask_or(covered, covered, sched_group_span(sg));
 
 		if (!first)
 			first = sg;
@@ -660,6 +899,7 @@ build_sched_groups(struct sched_domain *sd, int cpu)
 		last = sg;
 	}
 	last->next = first;
+	sd->groups = first;
 
 	return 0;
 }
@@ -683,12 +923,12 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
 	do {
 		int cpu, max_cpu = -1;
 
-		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+		sg->group_weight = cpumask_weight(sched_group_span(sg));
 
 		if (!(sd->flags & SD_ASYM_PACKING))
 			goto next;
 
-		for_each_cpu(cpu, sched_group_cpus(sg)) {
+		for_each_cpu(cpu, sched_group_span(sg)) {
 			if (max_cpu < 0)
 				max_cpu = cpu;
 			else if (sched_asym_prefer(cpu, max_cpu))
@@ -1308,6 +1548,10 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 			if (!sgc)
 				return -ENOMEM;
 
+#ifdef CONFIG_SCHED_DEBUG
+			sgc->id = j;
+#endif
+
 			*per_cpu_ptr(sdd->sgc, j) = sgc;
 		}
 	}
@@ -1407,7 +1651,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 			sd = build_sched_domain(tl, cpu_map, attr, sd, i);
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+			if (tl->flags & SDTL_OVERLAP)
 				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
@@ -1478,7 +1722,7 @@ static struct sched_domain_attr		*dattr_cur;
  * cpumask) fails, then fallback to a single sched domain,
  * as determined by the single cpumask fallback_doms.
  */
-cpumask_var_t				fallback_doms;
+static cpumask_var_t			fallback_doms;
 
 /*
  * arch_update_cpu_topology lets virtualized architectures update the
@@ -1520,10 +1764,14 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
  * For now this just excludes isolated CPUs, but could be used to
  * exclude other special cases in the future.
  */
-int init_sched_domains(const struct cpumask *cpu_map)
+int sched_init_domains(const struct cpumask *cpu_map)
 {
 	int err;
 
+	zalloc_cpumask_var(&sched_domains_tmpmask, GFP_KERNEL);
+	zalloc_cpumask_var(&sched_domains_tmpmask2, GFP_KERNEL);
+	zalloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+
 	arch_update_cpu_topology();
 	ndoms_cur = 1;
 	doms_cur = alloc_sched_domains(ndoms_cur);
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index b8c84c6dee64..17f11c6b0a9f 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -12,44 +12,44 @@
 #include <linux/hash.h>
 #include <linux/kthread.h>
 
-void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key)
+void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
 {
-	spin_lock_init(&q->lock);
-	lockdep_set_class_and_name(&q->lock, key, name);
-	INIT_LIST_HEAD(&q->task_list);
+	spin_lock_init(&wq_head->lock);
+	lockdep_set_class_and_name(&wq_head->lock, key, name);
+	INIT_LIST_HEAD(&wq_head->head);
 }
 
 EXPORT_SYMBOL(__init_waitqueue_head);
 
-void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
-	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	__add_wait_queue(q, wait);
-	spin_unlock_irqrestore(&q->lock, flags);
+	wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__add_wait_queue_entry_tail(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(add_wait_queue);
 
-void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait)
+void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	__add_wait_queue_tail(q, wait);
-	spin_unlock_irqrestore(&q->lock, flags);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__add_wait_queue_entry_tail(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(add_wait_queue_exclusive);
 
-void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait)
+void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&q->lock, flags);
-	__remove_wait_queue(q, wait);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__remove_wait_queue(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(remove_wait_queue);
 
@@ -63,12 +63,12 @@ EXPORT_SYMBOL(remove_wait_queue);
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
-static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
+static void __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, int wake_flags, void *key)
 {
-	wait_queue_t *curr, *next;
+	wait_queue_entry_t *curr, *next;
 
-	list_for_each_entry_safe(curr, next, &q->task_list, task_list) {
+	list_for_each_entry_safe(curr, next, &wq_head->head, entry) {
 		unsigned flags = curr->flags;
 
 		if (curr->func(curr, mode, wake_flags, key) &&
@@ -79,7 +79,7 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
 
 /**
  * __wake_up - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
+ * @wq_head: the waitqueue
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
@@ -87,35 +87,35 @@ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
  * It may be assumed that this function implies a write memory barrier before
  * changing the task state if and only if any tasks are woken up.
  */
-void __wake_up(wait_queue_head_t *q, unsigned int mode,
+void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, 0, key);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__wake_up_common(wq_head, mode, nr_exclusive, 0, key);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(__wake_up);
 
 /*
  * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
  */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
+void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
 {
-	__wake_up_common(q, mode, nr, 0, NULL);
+	__wake_up_common(wq_head, mode, nr, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
-void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key)
+void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
 {
-	__wake_up_common(q, mode, 1, 0, key);
+	__wake_up_common(wq_head, mode, 1, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
 /**
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
- * @q: the waitqueue
+ * @wq_head: the waitqueue
  * @mode: which threads
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: opaque value to be passed to wakeup targets
@@ -130,30 +130,30 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key);
  * It may be assumed that this function implies a write memory barrier before
  * changing the task state if and only if any tasks are woken up.
  */
-void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode,
+void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
 {
 	unsigned long flags;
 	int wake_flags = 1; /* XXX WF_SYNC */
 
-	if (unlikely(!q))
+	if (unlikely(!wq_head))
 		return;
 
 	if (unlikely(nr_exclusive != 1))
 		wake_flags = 0;
 
-	spin_lock_irqsave(&q->lock, flags);
-	__wake_up_common(q, mode, nr_exclusive, wake_flags, key);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync_key);
 
 /*
  * __wake_up_sync - see __wake_up_sync_key()
  */
-void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
+void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive)
 {
-	__wake_up_sync_key(q, mode, nr_exclusive, NULL);
+	__wake_up_sync_key(wq_head, mode, nr_exclusive, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
@@ -170,48 +170,48 @@ EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
  * loads to move into the critical region).
  */
 void
-prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state)
+prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
 
-	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	if (list_empty(&wait->task_list))
-		__add_wait_queue(q, wait);
+	wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	if (list_empty(&wq_entry->entry))
+		__add_wait_queue(wq_head, wq_entry);
 	set_current_state(state);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait);
 
 void
-prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state)
+prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
 
-	wait->flags |= WQ_FLAG_EXCLUSIVE;
-	spin_lock_irqsave(&q->lock, flags);
-	if (list_empty(&wait->task_list))
-		__add_wait_queue_tail(q, wait);
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	if (list_empty(&wq_entry->entry))
+		__add_wait_queue_entry_tail(wq_head, wq_entry);
 	set_current_state(state);
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
-void init_wait_entry(wait_queue_t *wait, int flags)
+void init_wait_entry(struct wait_queue_entry *wq_entry, int flags)
 {
-	wait->flags = flags;
-	wait->private = current;
-	wait->func = autoremove_wake_function;
-	INIT_LIST_HEAD(&wait->task_list);
+	wq_entry->flags = flags;
+	wq_entry->private = current;
+	wq_entry->func = autoremove_wake_function;
+	INIT_LIST_HEAD(&wq_entry->entry);
 }
 EXPORT_SYMBOL(init_wait_entry);
 
-long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
+long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
 	long ret = 0;
 
-	spin_lock_irqsave(&q->lock, flags);
+	spin_lock_irqsave(&wq_head->lock, flags);
 	if (unlikely(signal_pending_state(state, current))) {
 		/*
 		 * Exclusive waiter must not fail if it was selected by wakeup,
@@ -219,24 +219,24 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
 		 *
 		 * The caller will recheck the condition and return success if
 		 * we were already woken up, we can not miss the event because
-		 * wakeup locks/unlocks the same q->lock.
+		 * wakeup locks/unlocks the same wq_head->lock.
 		 *
 		 * But we need to ensure that set-condition + wakeup after that
 		 * can't see us, it should wake up another exclusive waiter if
 		 * we fail.
 		 */
-		list_del_init(&wait->task_list);
+		list_del_init(&wq_entry->entry);
 		ret = -ERESTARTSYS;
 	} else {
-		if (list_empty(&wait->task_list)) {
-			if (wait->flags & WQ_FLAG_EXCLUSIVE)
-				__add_wait_queue_tail(q, wait);
+		if (list_empty(&wq_entry->entry)) {
+			if (wq_entry->flags & WQ_FLAG_EXCLUSIVE)
+				__add_wait_queue_entry_tail(wq_head, wq_entry);
 			else
-				__add_wait_queue(q, wait);
+				__add_wait_queue(wq_head, wq_entry);
 		}
 		set_current_state(state);
 	}
-	spin_unlock_irqrestore(&q->lock, flags);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 
 	return ret;
 }
@@ -249,10 +249,10 @@ EXPORT_SYMBOL(prepare_to_wait_event);
  * condition in the caller before they add the wait
  * entry to the wake queue.
  */
-int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
+int do_wait_intr(wait_queue_head_t *wq, wait_queue_entry_t *wait)
 {
-	if (likely(list_empty(&wait->task_list)))
-		__add_wait_queue_tail(wq, wait);
+	if (likely(list_empty(&wait->entry)))
+		__add_wait_queue_entry_tail(wq, wait);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	if (signal_pending(current))
@@ -265,10 +265,10 @@ int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait)
 }
 EXPORT_SYMBOL(do_wait_intr);
 
-int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait)
+int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_entry_t *wait)
 {
-	if (likely(list_empty(&wait->task_list)))
-		__add_wait_queue_tail(wq, wait);
+	if (likely(list_empty(&wait->entry)))
+		__add_wait_queue_entry_tail(wq, wait);
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	if (signal_pending(current))
@@ -283,14 +283,14 @@ EXPORT_SYMBOL(do_wait_intr_irq);
 
 /**
  * finish_wait - clean up after waiting in a queue
- * @q: waitqueue waited on
- * @wait: wait descriptor
+ * @wq_head: waitqueue waited on
+ * @wq_entry: wait descriptor
  *
  * Sets current thread back to running state and removes
  * the wait descriptor from the given waitqueue if still
  * queued.
  */
-void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
+void finish_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
 
@@ -308,20 +308,20 @@ void finish_wait(wait_queue_head_t *q, wait_queue_t *wait)
 	 *    have _one_ other CPU that looks at or modifies
 	 *    the list).
 	 */
-	if (!list_empty_careful(&wait->task_list)) {
-		spin_lock_irqsave(&q->lock, flags);
-		list_del_init(&wait->task_list);
-		spin_unlock_irqrestore(&q->lock, flags);
+	if (!list_empty_careful(&wq_entry->entry)) {
+		spin_lock_irqsave(&wq_head->lock, flags);
+		list_del_init(&wq_entry->entry);
+		spin_unlock_irqrestore(&wq_head->lock, flags);
 	}
 }
 EXPORT_SYMBOL(finish_wait);
 
-int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
-	int ret = default_wake_function(wait, mode, sync, key);
+	int ret = default_wake_function(wq_entry, mode, sync, key);
 
 	if (ret)
-		list_del_init(&wait->task_list);
+		list_del_init(&wq_entry->entry);
 	return ret;
 }
 EXPORT_SYMBOL(autoremove_wake_function);
@@ -334,24 +334,24 @@ static inline bool is_kthread_should_stop(void)
 /*
  * DEFINE_WAIT_FUNC(wait, woken_wake_func);
  *
- * add_wait_queue(&wq, &wait);
+ * add_wait_queue(&wq_head, &wait);
  * for (;;) {
  *     if (condition)
  *         break;
  *
  *     p->state = mode;				condition = true;
  *     smp_mb(); // A				smp_wmb(); // C
- *     if (!wait->flags & WQ_FLAG_WOKEN)	wait->flags |= WQ_FLAG_WOKEN;
+ *     if (!wq_entry->flags & WQ_FLAG_WOKEN)	wq_entry->flags |= WQ_FLAG_WOKEN;
  *         schedule()				try_to_wake_up();
  *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
- *     wait->flags &= ~WQ_FLAG_WOKEN;		condition = true;
+ *     wq_entry->flags &= ~WQ_FLAG_WOKEN;		condition = true;
  *     smp_mb() // B				smp_wmb(); // C
- *						wait->flags |= WQ_FLAG_WOKEN;
+ *						wq_entry->flags |= WQ_FLAG_WOKEN;
  * }
- * remove_wait_queue(&wq, &wait);
+ * remove_wait_queue(&wq_head, &wait);
  *
  */
-long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
+long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
 {
 	set_current_state(mode); /* A */
 	/*
@@ -359,7 +359,7 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
 	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
 	 * also observe all state before the wakeup.
 	 */
-	if (!(wait->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
+	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
 		timeout = schedule_timeout(timeout);
 	__set_current_state(TASK_RUNNING);
 
@@ -369,13 +369,13 @@ long wait_woken(wait_queue_t *wait, unsigned mode, long timeout)
 	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
 	 * an event.
 	 */
-	smp_store_mb(wait->flags, wait->flags & ~WQ_FLAG_WOKEN); /* B */
+	smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
 
 	return timeout;
 }
 EXPORT_SYMBOL(wait_woken);
 
-int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
+int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
 	/*
 	 * Although this function is called under waitqueue lock, LOCK
@@ -385,267 +385,8 @@ int woken_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key)
 	 * and is paired with smp_store_mb() in wait_woken().
 	 */
 	smp_wmb(); /* C */
-	wait->flags |= WQ_FLAG_WOKEN;
+	wq_entry->flags |= WQ_FLAG_WOKEN;
 
-	return default_wake_function(wait, mode, sync, key);
+	return default_wake_function(wq_entry, mode, sync, key);
 }
 EXPORT_SYMBOL(woken_wake_function);
-
-int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg)
-{
-	struct wait_bit_key *key = arg;
-	struct wait_bit_queue *wait_bit
-		= container_of(wait, struct wait_bit_queue, wait);
-
-	if (wait_bit->key.flags != key->flags ||
-			wait_bit->key.bit_nr != key->bit_nr ||
-			test_bit(key->bit_nr, key->flags))
-		return 0;
-	else
-		return autoremove_wake_function(wait, mode, sync, key);
-}
-EXPORT_SYMBOL(wake_bit_function);
-
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking)
- * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
- * permitted return codes. Nonzero return codes halt waiting and return.
- */
-int __sched
-__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q,
-	      wait_bit_action_f *action, unsigned mode)
-{
-	int ret = 0;
-
-	do {
-		prepare_to_wait(wq, &q->wait, mode);
-		if (test_bit(q->key.bit_nr, q->key.flags))
-			ret = (*action)(&q->key, mode);
-	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
-	finish_wait(wq, &q->wait);
-	return ret;
-}
-EXPORT_SYMBOL(__wait_on_bit);
-
-int __sched out_of_line_wait_on_bit(void *word, int bit,
-				    wait_bit_action_f *action, unsigned mode)
-{
-	wait_queue_head_t *wq = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wait, word, bit);
-
-	return __wait_on_bit(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_bit);
-
-int __sched out_of_line_wait_on_bit_timeout(
-	void *word, int bit, wait_bit_action_f *action,
-	unsigned mode, unsigned long timeout)
-{
-	wait_queue_head_t *wq = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wait, word, bit);
-
-	wait.key.timeout = jiffies + timeout;
-	return __wait_on_bit(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
-
-int __sched
-__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q,
-			wait_bit_action_f *action, unsigned mode)
-{
-	int ret = 0;
-
-	for (;;) {
-		prepare_to_wait_exclusive(wq, &q->wait, mode);
-		if (test_bit(q->key.bit_nr, q->key.flags)) {
-			ret = action(&q->key, mode);
-			/*
-			 * See the comment in prepare_to_wait_event().
-			 * finish_wait() does not necessarily takes wq->lock,
-			 * but test_and_set_bit() implies mb() which pairs with
-			 * smp_mb__after_atomic() before wake_up_page().
-			 */
-			if (ret)
-				finish_wait(wq, &q->wait);
-		}
-		if (!test_and_set_bit(q->key.bit_nr, q->key.flags)) {
-			if (!ret)
-				finish_wait(wq, &q->wait);
-			return 0;
-		} else if (ret) {
-			return ret;
-		}
-	}
-}
-EXPORT_SYMBOL(__wait_on_bit_lock);
-
-int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
-					 wait_bit_action_f *action, unsigned mode)
-{
-	wait_queue_head_t *wq = bit_waitqueue(word, bit);
-	DEFINE_WAIT_BIT(wait, word, bit);
-
-	return __wait_on_bit_lock(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
-
-void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit)
-{
-	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
-	if (waitqueue_active(wq))
-		__wake_up(wq, TASK_NORMAL, 1, &key);
-}
-EXPORT_SYMBOL(__wake_up_bit);
-
-/**
- * wake_up_bit - wake up a waiter on a bit
- * @word: the word being waited on, a kernel virtual address
- * @bit: the bit of the word being waited on
- *
- * There is a standard hashed waitqueue table for generic use. This
- * is the part of the hashtable's accessor API that wakes up waiters
- * on a bit. For instance, if one were to have waiters on a bitflag,
- * one would call wake_up_bit() after clearing the bit.
- *
- * In order for this to function properly, as it uses waitqueue_active()
- * internally, some kind of memory barrier must be done prior to calling
- * this. Typically, this will be smp_mb__after_atomic(), but in some
- * cases where bitflags are manipulated non-atomically under a lock, one
- * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
- * because spin_unlock() does not guarantee a memory barrier.
- */
-void wake_up_bit(void *word, int bit)
-{
-	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
-}
-EXPORT_SYMBOL(wake_up_bit);
-
-/*
- * Manipulate the atomic_t address to produce a better bit waitqueue table hash
- * index (we're keying off bit -1, but that would produce a horrible hash
- * value).
- */
-static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
-{
-	if (BITS_PER_LONG == 64) {
-		unsigned long q = (unsigned long)p;
-		return bit_waitqueue((void *)(q & ~1), q & 1);
-	}
-	return bit_waitqueue(p, 0);
-}
-
-static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync,
-				  void *arg)
-{
-	struct wait_bit_key *key = arg;
-	struct wait_bit_queue *wait_bit
-		= container_of(wait, struct wait_bit_queue, wait);
-	atomic_t *val = key->flags;
-
-	if (wait_bit->key.flags != key->flags ||
-	    wait_bit->key.bit_nr != key->bit_nr ||
-	    atomic_read(val) != 0)
-		return 0;
-	return autoremove_wake_function(wait, mode, sync, key);
-}
-
-/*
- * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
- * the actions of __wait_on_atomic_t() are permitted return codes.  Nonzero
- * return codes halt waiting and return.
- */
-static __sched
-int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q,
-		       int (*action)(atomic_t *), unsigned mode)
-{
-	atomic_t *val;
-	int ret = 0;
-
-	do {
-		prepare_to_wait(wq, &q->wait, mode);
-		val = q->key.flags;
-		if (atomic_read(val) == 0)
-			break;
-		ret = (*action)(val);
-	} while (!ret && atomic_read(val) != 0);
-	finish_wait(wq, &q->wait);
-	return ret;
-}
-
-#define DEFINE_WAIT_ATOMIC_T(name, p)					\
-	struct wait_bit_queue name = {					\
-		.key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p),		\
-		.wait	= {						\
-			.private	= current,			\
-			.func		= wake_atomic_t_function,	\
-			.task_list	=				\
-				LIST_HEAD_INIT((name).wait.task_list),	\
-		},							\
-	}
-
-__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
-					 unsigned mode)
-{
-	wait_queue_head_t *wq = atomic_t_waitqueue(p);
-	DEFINE_WAIT_ATOMIC_T(wait, p);
-
-	return __wait_on_atomic_t(wq, &wait, action, mode);
-}
-EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
-
-/**
- * wake_up_atomic_t - Wake up a waiter on a atomic_t
- * @p: The atomic_t being waited on, a kernel virtual address
- *
- * Wake up anyone waiting for the atomic_t to go to zero.
- *
- * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
- * check is done by the waiter's wake function, not the by the waker itself).
- */
-void wake_up_atomic_t(atomic_t *p)
-{
-	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
-}
-EXPORT_SYMBOL(wake_up_atomic_t);
-
-__sched int bit_wait(struct wait_bit_key *word, int mode)
-{
-	schedule();
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL(bit_wait);
-
-__sched int bit_wait_io(struct wait_bit_key *word, int mode)
-{
-	io_schedule();
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL(bit_wait_io);
-
-__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
-{
-	unsigned long now = READ_ONCE(jiffies);
-	if (time_after_eq(now, word->timeout))
-		return -EAGAIN;
-	schedule_timeout(word->timeout - now);
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bit_wait_timeout);
-
-__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
-{
-	unsigned long now = READ_ONCE(jiffies);
-	if (time_after_eq(now, word->timeout))
-		return -EAGAIN;
-	io_schedule_timeout(word->timeout - now);
-	if (signal_pending_state(mode, current))
-		return -EINTR;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bit_wait_io_timeout);
diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
new file mode 100644
index 000000000000..f8159698aa4d
--- /dev/null
+++ b/kernel/sched/wait_bit.c
@@ -0,0 +1,286 @@
+/*
+ * The implementation of the wait_bit*() and related waiting APIs:
+ */
+#include <linux/wait_bit.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/debug.h>
+#include <linux/hash.h>
+
+#define WAIT_TABLE_BITS 8
+#define WAIT_TABLE_SIZE (1 << WAIT_TABLE_BITS)
+
+static wait_queue_head_t bit_wait_table[WAIT_TABLE_SIZE] __cacheline_aligned;
+
+wait_queue_head_t *bit_waitqueue(void *word, int bit)
+{
+	const int shift = BITS_PER_LONG == 32 ? 5 : 6;
+	unsigned long val = (unsigned long)word << shift | bit;
+
+	return bit_wait_table + hash_long(val, WAIT_TABLE_BITS);
+}
+EXPORT_SYMBOL(bit_waitqueue);
+
+int wake_bit_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
+
+	if (wait_bit->key.flags != key->flags ||
+			wait_bit->key.bit_nr != key->bit_nr ||
+			test_bit(key->bit_nr, key->flags))
+		return 0;
+	else
+		return autoremove_wake_function(wq_entry, mode, sync, key);
+}
+EXPORT_SYMBOL(wake_bit_function);
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking)
+ * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are
+ * permitted return codes. Nonzero return codes halt waiting and return.
+ */
+int __sched
+__wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+	      wait_bit_action_f *action, unsigned mode)
+{
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
+		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
+			ret = (*action)(&wbq_entry->key, mode);
+	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	finish_wait(wq_head, &wbq_entry->wq_entry);
+	return ret;
+}
+EXPORT_SYMBOL(__wait_on_bit);
+
+int __sched out_of_line_wait_on_bit(void *word, int bit,
+				    wait_bit_action_f *action, unsigned mode)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	return __wait_on_bit(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit);
+
+int __sched out_of_line_wait_on_bit_timeout(
+	void *word, int bit, wait_bit_action_f *action,
+	unsigned mode, unsigned long timeout)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	wq_entry.key.timeout = jiffies + timeout;
+	return __wait_on_bit(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL_GPL(out_of_line_wait_on_bit_timeout);
+
+int __sched
+__wait_on_bit_lock(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+			wait_bit_action_f *action, unsigned mode)
+{
+	int ret = 0;
+
+	for (;;) {
+		prepare_to_wait_exclusive(wq_head, &wbq_entry->wq_entry, mode);
+		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
+			ret = action(&wbq_entry->key, mode);
+			/*
+			 * See the comment in prepare_to_wait_event().
+			 * finish_wait() does not necessarily takes wwq_head->lock,
+			 * but test_and_set_bit() implies mb() which pairs with
+			 * smp_mb__after_atomic() before wake_up_page().
+			 */
+			if (ret)
+				finish_wait(wq_head, &wbq_entry->wq_entry);
+		}
+		if (!test_and_set_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags)) {
+			if (!ret)
+				finish_wait(wq_head, &wbq_entry->wq_entry);
+			return 0;
+		} else if (ret) {
+			return ret;
+		}
+	}
+}
+EXPORT_SYMBOL(__wait_on_bit_lock);
+
+int __sched out_of_line_wait_on_bit_lock(void *word, int bit,
+					 wait_bit_action_f *action, unsigned mode)
+{
+	struct wait_queue_head *wq_head = bit_waitqueue(word, bit);
+	DEFINE_WAIT_BIT(wq_entry, word, bit);
+
+	return __wait_on_bit_lock(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_bit_lock);
+
+void __wake_up_bit(struct wait_queue_head *wq_head, void *word, int bit)
+{
+	struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit);
+	if (waitqueue_active(wq_head))
+		__wake_up(wq_head, TASK_NORMAL, 1, &key);
+}
+EXPORT_SYMBOL(__wake_up_bit);
+
+/**
+ * wake_up_bit - wake up a waiter on a bit
+ * @word: the word being waited on, a kernel virtual address
+ * @bit: the bit of the word being waited on
+ *
+ * There is a standard hashed waitqueue table for generic use. This
+ * is the part of the hashtable's accessor API that wakes up waiters
+ * on a bit. For instance, if one were to have waiters on a bitflag,
+ * one would call wake_up_bit() after clearing the bit.
+ *
+ * In order for this to function properly, as it uses waitqueue_active()
+ * internally, some kind of memory barrier must be done prior to calling
+ * this. Typically, this will be smp_mb__after_atomic(), but in some
+ * cases where bitflags are manipulated non-atomically under a lock, one
+ * may need to use a less regular barrier, such fs/inode.c's smp_mb(),
+ * because spin_unlock() does not guarantee a memory barrier.
+ */
+void wake_up_bit(void *word, int bit)
+{
+	__wake_up_bit(bit_waitqueue(word, bit), word, bit);
+}
+EXPORT_SYMBOL(wake_up_bit);
+
+/*
+ * Manipulate the atomic_t address to produce a better bit waitqueue table hash
+ * index (we're keying off bit -1, but that would produce a horrible hash
+ * value).
+ */
+static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p)
+{
+	if (BITS_PER_LONG == 64) {
+		unsigned long q = (unsigned long)p;
+		return bit_waitqueue((void *)(q & ~1), q & 1);
+	}
+	return bit_waitqueue(p, 0);
+}
+
+static int wake_atomic_t_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync,
+				  void *arg)
+{
+	struct wait_bit_key *key = arg;
+	struct wait_bit_queue_entry *wait_bit = container_of(wq_entry, struct wait_bit_queue_entry, wq_entry);
+	atomic_t *val = key->flags;
+
+	if (wait_bit->key.flags != key->flags ||
+	    wait_bit->key.bit_nr != key->bit_nr ||
+	    atomic_read(val) != 0)
+		return 0;
+	return autoremove_wake_function(wq_entry, mode, sync, key);
+}
+
+/*
+ * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting,
+ * the actions of __wait_on_atomic_t() are permitted return codes.  Nonzero
+ * return codes halt waiting and return.
+ */
+static __sched
+int __wait_on_atomic_t(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_entry,
+		       int (*action)(atomic_t *), unsigned mode)
+{
+	atomic_t *val;
+	int ret = 0;
+
+	do {
+		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
+		val = wbq_entry->key.flags;
+		if (atomic_read(val) == 0)
+			break;
+		ret = (*action)(val);
+	} while (!ret && atomic_read(val) != 0);
+	finish_wait(wq_head, &wbq_entry->wq_entry);
+	return ret;
+}
+
+#define DEFINE_WAIT_ATOMIC_T(name, p)					\
+	struct wait_bit_queue_entry name = {				\
+		.key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p),		\
+		.wq_entry = {						\
+			.private	= current,			\
+			.func		= wake_atomic_t_function,	\
+			.entry		=				\
+				LIST_HEAD_INIT((name).wq_entry.entry),	\
+		},							\
+	}
+
+__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *),
+					 unsigned mode)
+{
+	struct wait_queue_head *wq_head = atomic_t_waitqueue(p);
+	DEFINE_WAIT_ATOMIC_T(wq_entry, p);
+
+	return __wait_on_atomic_t(wq_head, &wq_entry, action, mode);
+}
+EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
+
+/**
+ * wake_up_atomic_t - Wake up a waiter on a atomic_t
+ * @p: The atomic_t being waited on, a kernel virtual address
+ *
+ * Wake up anyone waiting for the atomic_t to go to zero.
+ *
+ * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t
+ * check is done by the waiter's wake function, not the by the waker itself).
+ */
+void wake_up_atomic_t(atomic_t *p)
+{
+	__wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR);
+}
+EXPORT_SYMBOL(wake_up_atomic_t);
+
+__sched int bit_wait(struct wait_bit_key *word, int mode)
+{
+	schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait);
+
+__sched int bit_wait_io(struct wait_bit_key *word, int mode)
+{
+	io_schedule();
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL(bit_wait_io);
+
+__sched int bit_wait_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = READ_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_timeout);
+
+__sched int bit_wait_io_timeout(struct wait_bit_key *word, int mode)
+{
+	unsigned long now = READ_ONCE(jiffies);
+	if (time_after_eq(now, word->timeout))
+		return -EAGAIN;
+	io_schedule_timeout(word->timeout - now);
+	if (signal_pending_state(mode, current))
+		return -EINTR;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(bit_wait_io_timeout);
+
+void __init wait_bit_init(void)
+{
+	int i;
+
+	for (i = 0; i < WAIT_TABLE_SIZE; i++)
+		init_waitqueue_head(bit_wait_table + i);
+}
diff --git a/kernel/smp.c b/kernel/smp.c
index a817769b53c0..3061483cb3ad 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -30,6 +30,7 @@ enum {
 struct call_function_data {
 	struct call_single_data	__percpu *csd;
 	cpumask_var_t		cpumask;
+	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
@@ -45,9 +46,15 @@ int smpcfd_prepare_cpu(unsigned int cpu)
 	if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				     cpu_to_node(cpu)))
 		return -ENOMEM;
+	if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
+				     cpu_to_node(cpu))) {
+		free_cpumask_var(cfd->cpumask);
+		return -ENOMEM;
+	}
 	cfd->csd = alloc_percpu(struct call_single_data);
 	if (!cfd->csd) {
 		free_cpumask_var(cfd->cpumask);
+		free_cpumask_var(cfd->cpumask_ipi);
 		return -ENOMEM;
 	}
 
@@ -59,6 +66,7 @@ int smpcfd_dead_cpu(unsigned int cpu)
 	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
 
 	free_cpumask_var(cfd->cpumask);
+	free_cpumask_var(cfd->cpumask_ipi);
 	free_percpu(cfd->csd);
 	return 0;
 }
@@ -428,12 +436,13 @@ void smp_call_function_many(const struct cpumask *mask,
 	cfd = this_cpu_ptr(&cfd_data);
 
 	cpumask_and(cfd->cpumask, mask, cpu_online_mask);
-	cpumask_clear_cpu(this_cpu, cfd->cpumask);
+	__cpumask_clear_cpu(this_cpu, cfd->cpumask);
 
 	/* Some callers race with other cpus changing the passed mask */
 	if (unlikely(!cpumask_weight(cfd->cpumask)))
 		return;
 
+	cpumask_clear(cfd->cpumask_ipi);
 	for_each_cpu(cpu, cfd->cpumask) {
 		struct call_single_data *csd = per_cpu_ptr(cfd->csd, cpu);
 
@@ -442,11 +451,12 @@ void smp_call_function_many(const struct cpumask *mask,
 			csd->flags |= CSD_FLAG_SYNCHRONOUS;
 		csd->func = func;
 		csd->info = info;
-		llist_add(&csd->llist, &per_cpu(call_single_queue, cpu));
+		if (llist_add(&csd->llist, &per_cpu(call_single_queue, cpu)))
+			__cpumask_set_cpu(cpu, cfd->cpumask_ipi);
 	}
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(cfd->cpumask);
+	arch_send_call_function_ipi_mask(cfd->cpumask_ipi);
 
 	if (wait) {
 		for_each_cpu(cpu, cfd->cpumask) {
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 93621ae718d3..03918a19cf2d 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -233,6 +233,9 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 		}
 
+		if (cs == curr_clocksource && cs->tick_stable)
+			cs->tick_stable(cs);
+
 		if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) &&
 		    (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) &&
 		    (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) {
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 64c97fc130c4..db023e9cbb25 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -554,7 +554,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
 	update_ts_time_stats(smp_processor_id(), ts, now, NULL);
 	ts->idle_active = 0;
 
-	sched_clock_idle_wakeup_event(0);
+	sched_clock_idle_wakeup_event();
 }
 
 static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
@@ -782,8 +782,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
 	 * the scheduler tick in nohz_restart_sched_tick.
 	 */
 	if (!ts->tick_stopped) {
-		nohz_balance_enter_idle(cpu);
-		calc_load_enter_idle();
+		calc_load_nohz_start();
 		cpu_load_update_nohz_start();
 
 		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
@@ -823,7 +822,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 	 */
 	timer_clear_idle();
 
-	calc_load_exit_idle();
+	calc_load_nohz_stop();
 	touch_softlockup_watchdog_sched();
 	/*
 	 * Cancel the scheduled timer and restore the tick
@@ -923,8 +922,10 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
 			ts->idle_expires = expires;
 		}
 
-		if (!was_stopped && ts->tick_stopped)
+		if (!was_stopped && ts->tick_stopped) {
 			ts->idle_jiffies = ts->last_jiffies;
+			nohz_balance_enter_idle(cpu);
+		}
 	}
 }
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index c74bf39ef764..a86688fabc55 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2864,11 +2864,11 @@ bool flush_work(struct work_struct *work)
 EXPORT_SYMBOL_GPL(flush_work);
 
 struct cwt_wait {
-	wait_queue_t		wait;
+	wait_queue_entry_t		wait;
 	struct work_struct	*work;
 };
 
-static int cwt_wakefn(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait);