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

Pull scheduler updates from Thomas Gleixner:

 - Cleanup and improvement of NUMA balancing

 - Refactoring and improvements to the PELT (Per Entity Load Tracking)
   code

 - Watchdog simplification and related cleanups

 - The usual pile of small incremental fixes and improvements

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  watchdog: Reduce message verbosity
  stop_machine: Reflow cpu_stop_queue_two_works()
  sched/numa: Move task_numa_placement() closer to numa_migrate_preferred()
  sched/numa: Use group_weights to identify if migration degrades locality
  sched/numa: Update the scan period without holding the numa_group lock
  sched/numa: Remove numa_has_capacity()
  sched/numa: Modify migrate_swap() to accept additional parameters
  sched/numa: Remove unused task_capacity from 'struct numa_stats'
  sched/numa: Skip nodes that are at 'hoplimit'
  sched/debug: Reverse the order of printing faults
  sched/numa: Use task faults only if numa_group is not yet set up
  sched/numa: Set preferred_node based on best_cpu
  sched/numa: Simplify load_too_imbalanced()
  sched/numa: Evaluate move once per node
  sched/numa: Remove redundant field
  sched/debug: Show the sum wait time of a task group
  sched/fair: Remove #ifdefs from scale_rt_capacity()
  sched/core: Remove get_cpu() from sched_fork()
  sched/cpufreq: Clarify sugov_get_util()
  sched/sysctl: Remove unused sched_time_avg_ms sysctl
  ...

arch/mips/kvm/mips.c

@@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 	dvcpu->arch.wait = 0;
 
 	if (swq_has_sleeper(&dvcpu->wq))
-		swake_up(&dvcpu->wq);
+		swake_up_one(&dvcpu->wq);
 
 	return 0;
 }
@@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data)
 
 	vcpu->arch.wait = 0;
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 }
 
 /* low level hrtimer wake routine */

arch/powerpc/kvm/book3s_hv.c

@@ -216,7 +216,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -3188,7 +3188,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 		}
 	}
 
-	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	if (kvmppc_vcore_check_block(vc)) {
 		finish_swait(&vc->wq, &wait);
@@ -3311,7 +3311,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			swake_up(&vc->wq);
+			swake_up_one(&vc->wq);
 		}
 
 	}

arch/s390/kvm/interrupt.c

@@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 	/*

arch/x86/kernel/kvm.c

@@ -154,7 +154,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
 
 	for (;;) {
 		if (!n.halted)
-			prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+			prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
 		if (hlist_unhashed(&n.link))
 			break;
 
@@ -188,7 +188,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (swq_has_sleeper(&n->wq))
-		swake_up(&n->wq);
+		swake_up_one(&n->wq);
 }
 
 static void apf_task_wake_all(void)

arch/x86/kvm/lapic.c

@@ -1379,7 +1379,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	 * using swait_active() is safe.
 	 */
 	if (swait_active(q))
-		swake_up(q);
+		swake_up_one(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;

include/linux/cpuhotplug.h

@@ -164,6 +164,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
+	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
 	CPUHP_AP_ONLINE_DYN,

include/linux/nmi.h

@@ -45,12 +45,18 @@ extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern unsigned int  softlockup_panic;
-#else
+
+extern int lockup_detector_online_cpu(unsigned int cpu);
+extern int lockup_detector_offline_cpu(unsigned int cpu);
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
 static inline void touch_softlockup_watchdog_sched(void) { }
 static inline void touch_softlockup_watchdog(void) { }
 static inline void touch_softlockup_watchdog_sync(void) { }
 static inline void touch_all_softlockup_watchdogs(void) { }
-#endif
+
+#define lockup_detector_online_cpu	NULL
+#define lockup_detector_offline_cpu	NULL
+#endif /* CONFIG_SOFTLOCKUP_DETECTOR */
 
 #ifdef CONFIG_DETECT_HUNG_TASK
 void reset_hung_task_detector(void);

include/linux/sched.h

@@ -1017,7 +1017,6 @@ struct task_struct {
 	u64				last_sum_exec_runtime;
 	struct callback_head		numa_work;
 
-	struct list_head		numa_entry;
 	struct numa_group		*numa_group;
 
 	/*

include/linux/sched/sysctl.h

@@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 #ifdef CONFIG_SCHED_DEBUG
 extern __read_mostly unsigned int sysctl_sched_migration_cost;
 extern __read_mostly unsigned int sysctl_sched_nr_migrate;
-extern __read_mostly unsigned int sysctl_sched_time_avg;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,

include/linux/smpboot.h

@@ -25,8 +25,6 @@ struct smpboot_thread_data;
  *			parked (cpu offline)
  * @unpark:		Optional unpark function, called when the thread is
  *			unparked (cpu online)
- * @cpumask:		Internal state.  To update which threads are unparked,
- *			call smpboot_update_cpumask_percpu_thread().
  * @selfparking:	Thread is not parked by the park function.
  * @thread_comm:	The base name of the thread
  */
@@ -40,23 +38,12 @@ struct smp_hotplug_thread {
 	void				(*cleanup)(unsigned int cpu, bool online);
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
-	cpumask_var_t			cpumask;
 	bool				selfparking;
 	const char			*thread_comm;
 };
 
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask);
-
-static inline int
-smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
-{
-	return smpboot_register_percpu_thread_cpumask(plug_thread,
-						      cpu_possible_mask);
-}
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
 
 void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *);
 
 #endif

include/linux/swait.h

@@ -16,7 +16,7 @@
  * wait-queues, but the semantics are actually completely different, and
  * every single user we have ever had has been buggy (or pointless).
  *
- * A "swake_up()" only wakes up _one_ waiter, which is not at all what
+ * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what
  * "wake_up()" does, and has led to problems. In other cases, it has
  * been fine, because there's only ever one waiter (kvm), but in that
  * case gthe whole "simple" wait-queue is just pointless to begin with,
@@ -38,8 +38,8 @@
  *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
  *    sleeper state.
  *
- *  - the exclusive mode; because this requires preserving the list order
- *    and this is hard.
+ *  - the !exclusive mode; because that leads to O(n) wakeups, everything is
+ *    exclusive.
  *
  *  - custom wake callback functions; because you cannot give any guarantees
  *    about random code. This also allows swait to be used in RT, such that
@@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name
  *      CPU0 - waker                    CPU1 - waiter
  *
  *                                      for (;;) {
- *      @cond = true;                     prepare_to_swait(&wq_head, &wait, state);
+ *      @cond = true;                     prepare_to_swait_exclusive(&wq_head, &wait, state);
  *      smp_mb();                         // smp_mb() from set_current_state()
  *      if (swait_active(wq_head))        if (@cond)
  *        wake_up(wq_head);                      break;
@@ -157,20 +157,20 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq)
 	return swait_active(wq);
 }
 
-extern void swake_up(struct swait_queue_head *q);
+extern void swake_up_one(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
 
-extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
-extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
+extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state);
 extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
 
 extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 
-/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+/* as per ___wait_event() but for swait, therefore "exclusive == 1" */
 #define ___swait_event(wq, condition, state, ret, cmd)			\
 ({									\
+	__label__ __out;						\
 	struct swait_queue __wait;					\
 	long __ret = ret;						\
 									\
@@ -183,20 +183,20 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 									\
 		if (___wait_is_interruptible(state) && __int) {		\
 			__ret = __int;					\
-			break;						\
+			goto __out;					\
 		}							\
 									\
 		cmd;							\
 	}								\
 	finish_swait(&wq, &__wait);					\
-	__ret;								\
+__out:	__ret;								\
 })
 
 #define __swait_event(wq, condition)					\
 	(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,	\
 			    schedule())
 
-#define swait_event(wq, condition)					\
+#define swait_event_exclusive(wq, condition)				\
 do {									\
 	if (condition)							\
 		break;							\
@@ -208,7 +208,7 @@ do {									\
 		      TASK_UNINTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_timeout(wq, condition, timeout)			\
+#define swait_event_timeout_exclusive(wq, condition, timeout)		\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -220,7 +220,7 @@ do {									\
 	___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0,		\
 		      schedule())
 
-#define swait_event_interruptible(wq, condition)			\
+#define swait_event_interruptible_exclusive(wq, condition)		\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
@@ -233,7 +233,7 @@ do {									\
 		      TASK_INTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_interruptible_timeout(wq, condition, timeout)	\
+#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -246,7 +246,7 @@ do {									\
 	(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
 
 /**
- * swait_event_idle - wait without system load contribution
+ * swait_event_idle_exclusive - wait without system load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
@@ -257,7 +257,7 @@ do {									\
  * condition and doesn't want to contribute to system load. Signals are
  * ignored.
  */
-#define swait_event_idle(wq, condition)					\
+#define swait_event_idle_exclusive(wq, condition)			\
 do {									\
 	if (condition)							\
 		break;							\
@@ -270,7 +270,7 @@ do {									\
 		       __ret = schedule_timeout(__ret))
 
 /**
- * swait_event_idle_timeout - wait up to timeout without load contribution
+ * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout at which we'll give up in jiffies
@@ -288,7 +288,7 @@ do {									\
  * or the remaining jiffies (at least 1) if the @condition evaluated
  * to %true before the @timeout elapsed.
  */
-#define swait_event_idle_timeout(wq, condition, timeout)		\
+#define swait_event_idle_timeout_exclusive(wq, condition, timeout)	\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\

kernel/cpu.c

@@ -1344,6 +1344,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= perf_event_init_cpu,
 		.teardown.single	= perf_event_exit_cpu,
 	},
+	[CPUHP_AP_WATCHDOG_ONLINE] = {
+		.name			= "lockup_detector:online",
+		.startup.single		= lockup_detector_online_cpu,
+		.teardown.single	= lockup_detector_offline_cpu,
+	},
 	[CPUHP_AP_WORKQUEUE_ONLINE] = {
 		.name			= "workqueue:online",
 		.startup.single		= workqueue_online_cpu,

kernel/kthread.c

@@ -190,7 +190,7 @@ static void __kthread_parkme(struct kthread *self)
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
 
-		complete_all(&self->parked);
+		complete(&self->parked);
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -471,7 +471,6 @@ void kthread_unpark(struct task_struct *k)
 	if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
 		__kthread_bind(k, kthread->cpu, TASK_PARKED);
 
-	reinit_completion(&kthread->parked);
 	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	/*
 	 * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
@@ -499,6 +498,9 @@ int kthread_park(struct task_struct *k)
 	if (WARN_ON(k->flags & PF_EXITING))
 		return -ENOSYS;
 
+	if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
+		return -EBUSY;
+
 	set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	if (k != current) {
 		wake_up_process(k);

kernel/power/suspend.c

@@ -92,7 +92,7 @@ static void s2idle_enter(void)
 	/* Push all the CPUs into the idle loop. */
 	wake_up_all_idle_cpus();
 	/* Make the current CPU wait so it can enter the idle loop too. */
-	swait_event(s2idle_wait_head,
+	swait_event_exclusive(s2idle_wait_head,
 		    s2idle_state == S2IDLE_STATE_WAKE);
 
 	cpuidle_pause();
@@ -160,7 +160,7 @@ void s2idle_wake(void)
 	raw_spin_lock_irqsave(&s2idle_lock, flags);
 	if (s2idle_state > S2IDLE_STATE_NONE) {
 		s2idle_state = S2IDLE_STATE_WAKE;
-		swake_up(&s2idle_wait_head);
+		swake_up_one(&s2idle_wait_head);
 	}
 	raw_spin_unlock_irqrestore(&s2idle_lock, flags);
 }

kernel/rcu/srcutiny.c

@@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 
 	WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
 	if (!newval && READ_ONCE(sp->srcu_gp_waiting))
-		swake_up(&sp->srcu_wq);
+		swake_up_one(&sp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	idx = sp->srcu_idx;
 	WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
 	WRITE_ONCE(sp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
-	swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+	swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
 	WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
 
 	/* Invoke the callbacks we removed above. */

kernel/rcu/tree.c

@@ -1701,7 +1701,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
-	swake_up(&rsp->gp_wq);
+	swake_up_one(&rsp->gp_wq);
 }
 
 /*
@@ -2015,7 +2015,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 }
 
 /*
- * Helper function for swait_event_idle() wakeup at force-quiescent-state
+ * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
  * time.
  */
 static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
@@ -2163,7 +2163,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gp_seq),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
-			swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
+			swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
 						     RCU_GP_FLAG_INIT);
 			rsp->gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
@@ -2191,7 +2191,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gp_seq),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
-			ret = swait_event_idle_timeout(rsp->gp_wq,
+			ret = swait_event_idle_timeout_exclusive(rsp->gp_wq,
 					rcu_gp_fqs_check_wake(rsp, &gf), j);
 			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */

kernel/rcu/tree_exp.h

@@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				swake_up(&rsp->expedited_wq);
+				swake_up_one(&rsp->expedited_wq);
 			}
 			break;
 		}
@@ -526,7 +526,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	jiffies_start = jiffies;
 
 	for (;;) {
-		ret = swait_event_timeout(
+		ret = swait_event_timeout_exclusive(
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done_unlocked(rnp_root),
 				jiffies_stall);

kernel/rcu/tree_plugin.h

@@ -1926,8 +1926,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force,
 		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
 		del_timer(&rdp->nocb_timer);
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
-		smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
-		swake_up(&rdp_leader->nocb_wq);
+		smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */
+		swake_up_one(&rdp_leader->nocb_wq);
 	} else {
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 	}
@@ -2159,7 +2159,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	 */
 	trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
 	for (;;) {
-		swait_event_interruptible(
+		swait_event_interruptible_exclusive(
 			rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1],
 			(d = rcu_seq_done(&rnp->gp_seq, c)));
 		if (likely(d))
@@ -2188,7 +2188,7 @@ static void nocb_leader_wait(struct rcu_data *my_rdp)
 	/* Wait for callbacks to appear. */
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep"));
-		swait_event_interruptible(my_rdp->nocb_wq,
+		swait_event_interruptible_exclusive(my_rdp->nocb_wq,
 				!READ_ONCE(my_rdp->nocb_leader_sleep));
 		raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
 		my_rdp->nocb_leader_sleep = true;
@@ -2253,7 +2253,7 @@ static void nocb_leader_wait(struct rcu_data *my_rdp)
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
 			/* List was empty, so wake up the follower.  */
-			swake_up(&rdp->nocb_wq);
+			swake_up_one(&rdp->nocb_wq);
 		}
 	}
 
@@ -2270,7 +2270,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 {
 	for (;;) {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep"));
-		swait_event_interruptible(rdp->nocb_wq,
+		swait_event_interruptible_exclusive(rdp->nocb_wq,
 					 READ_ONCE(rdp->nocb_follower_head));
 		if (smp_load_acquire(&rdp->nocb_follower_head)) {
 			/* ^^^ Ensure CB invocation follows _head test. */

kernel/sched/Makefile

@@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle.o fair.o rt.o deadline.o
 obj-y += wait.o wait_bit.o swait.o completion.o
 
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o

kernel/sched/core.c

@@ -17,6 +17,8 @@
 #include "../workqueue_internal.h"
 #include "../smpboot.h"
 
+#include "pelt.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
@@ -44,14 +46,6 @@ const_debug unsigned int sysctl_sched_features =
  */
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
-/*
- * period over which we average the RT time consumption, measured
- * in ms.
- *
- * default: 1s
- */
-const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
-
 /*
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
@@ -183,9 +177,9 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->clock_task += delta;
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef HAVE_SCHED_AVG_IRQ
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
-		sched_rt_avg_update(rq, irq_delta + steal);
+		update_irq_load_avg(rq, irq_delta + steal);
 #endif
 }
 
@@ -649,23 +643,6 @@ bool sched_can_stop_tick(struct rq *rq)
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
-
-void sched_avg_update(struct rq *rq)
-{
-	s64 period = sched_avg_period();
-
-	while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
-		/*
-		 * Inline assembly required to prevent the compiler
-		 * optimising this loop into a divmod call.
-		 * See __iter_div_u64_rem() for another example of this.
-		 */
-		asm("" : "+rm" (rq->age_stamp));
-		rq->age_stamp += period;
-		rq->rt_avg /= 2;
-	}
-}
-
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -1199,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
 	if (task_on_rq_queued(p)) {
@@ -1280,16 +1258,17 @@ static int migrate_swap_stop(void *data)
 /*
  * Cross migrate two tasks
  */
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+		int target_cpu, int curr_cpu)
 {
 	struct migration_swap_arg arg;
 	int ret = -EINVAL;
 
 	arg = (struct migration_swap_arg){
 		.src_task = cur,
-		.src_cpu = task_cpu(cur),
+		.src_cpu = curr_cpu,
 		.dst_task = p,
-		.dst_cpu = task_cpu(p),
+		.dst_cpu = target_cpu,
 	};
 
 	if (arg.src_cpu == arg.dst_cpu)
@@ -1314,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
 out:
 	return ret;
 }
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * wait_task_inactive - wait for a thread to unschedule.
@@ -2317,7 +2297,6 @@ static inline void init_schedstats(void) {}
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
-	int cpu = get_cpu();
 
 	__sched_fork(clone_flags, p);
 	/*
@@ -2353,14 +2332,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	if (dl_prio(p->prio)) {
-		put_cpu();
+	if (dl_prio(p->prio))
 		return -EAGAIN;
-	} else if (rt_prio(p->prio)) {
+	else if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
-	} else {
+	else
 		p->sched_class = &fair_sched_class;
-	}
 
 	init_entity_runnable_average(&p->se);
 
@@ -2376,7 +2353,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
 	 */
-	__set_task_cpu(p, cpu);
+	__set_task_cpu(p, smp_processor_id());
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
@@ -2393,8 +2370,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
-
-	put_cpu();
 	return 0;
 }
 
@@ -5714,13 +5689,6 @@ void set_rq_offline(struct rq *rq)
 	}
 }
 
-static void set_cpu_rq_start_time(unsigned int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-
-	rq->age_stamp = sched_clock_cpu(cpu);
-}
-
 /*
  * used to mark begin/end of suspend/resume:
  */
@@ -5838,7 +5806,6 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 
 int sched_cpu_starting(unsigned int cpu)
 {
-	set_cpu_rq_start_time(cpu);
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -6106,7 +6073,6 @@ void __init sched_init(void)
 
 #ifdef CONFIG_SMP
 	idle_thread_set_boot_cpu();
-	set_cpu_rq_start_time(smp_processor_id());
 #endif
 	init_sched_fair_class();
 
@@ -6785,6 +6751,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
 	seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
 	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
 
+	if (schedstat_enabled() && tg != &root_task_group) {
+		u64 ws = 0;
+		int i;
+
+		for_each_possible_cpu(i)
+			ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+
+		seq_printf(sf, "wait_sum %llu\n", ws);
+	}
+
 	return 0;
 }
 #endif /* CONFIG_CFS_BANDWIDTH */

kernel/sched/cpufreq_schedutil.c

@@ -53,9 +53,7 @@ struct sugov_cpu {
 	unsigned int		iowait_boost_max;
 	u64			last_update;
 
-	/* The fields below are only needed when sharing a policy: */
-	unsigned long		util_cfs;
-	unsigned long		util_dl;
+	unsigned long		bw_dl;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -179,33 +177,90 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ *   cpu_util_{cfs,rt,dl,irq}()
+ *   cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util, irq, max;
 
-	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
-	sg_cpu->util_cfs = cpu_util_cfs(rq);
-	sg_cpu->util_dl  = cpu_util_dl(rq);
-}
-
-static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
-{
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+	sg_cpu->bw_dl = cpu_bw_dl(rq);
 
 	if (rt_rq_is_runnable(&rq->rt))
-		return sg_cpu->max;
+		return max;
+
+	/*
+	 * Early check to see if IRQ/steal time saturates the CPU, can be
+	 * because of inaccuracies in how we track these -- see
+	 * update_irq_load_avg().
+	 */
+	irq = cpu_util_irq(rq);
+	if (unlikely(irq >= max))
+		return max;
+
+	/*
+	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
+	 * CFS tasks and we use the same metric to track the effective
+	 * utilization (PELT windows are synchronized) we can directly add them
+	 * to obtain the CPU's actual utilization.
+	 */
+	util = cpu_util_cfs(rq);
+	util += cpu_util_rt(rq);
+
+	/*
+	 * We do not make cpu_util_dl() a permanent part of this sum because we
+	 * want to use cpu_bw_dl() later on, but we need to check if the
+	 * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+	 * f_max when there is no idle time.
+	 *
+	 * NOTE: numerical errors or stop class might cause us to not quite hit
+	 * saturation when we should -- something for later.
+	 */
+	if ((util + cpu_util_dl(rq)) >= max)
+		return max;
+
+	/*
+	 * There is still idle time; further improve the number by using the
+	 * irq metric. Because IRQ/steal time is hidden from the task clock we
+	 * need to scale the task numbers:
+	 *
+	 *              1 - irq
+	 *   U' = irq + ------- * U
+	 *                max
+	 */
+	util = scale_irq_capacity(util, irq, max);
+	util += irq;
 
 	/*
-	 * Utilization required by DEADLINE must always be granted while, for
-	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
-	 * gracefully reduce the frequency when no tasks show up for longer
+	 * Bandwidth required by DEADLINE must always be granted while, for
+	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+	 * to gracefully reduce the frequency when no tasks show up for longer
 	 * periods of time.
 	 *
-	 * Ideally we would like to set util_dl as min/guaranteed freq and
-	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
-	 * ready for such an interface. So, we only do the latter for now.
+	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
+	 * an interface. So, we only do the latter for now.
 	 */
-	return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
+	return min(max, util + sg_cpu->bw_dl);
 }
 
 /**
@@ -360,7 +415,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
 {
-	if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl)
+	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
 		sg_policy->need_freq_update = true;
 }
 
@@ -383,9 +438,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
 	busy = sugov_cpu_is_busy(sg_cpu);
 
-	sugov_get_util(sg_cpu);
+	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
-	util = sugov_aggregate_util(sg_cpu);
 	sugov_iowait_apply(sg_cpu, time, &util, &max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
@@ -424,9 +478,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
 
-		sugov_get_util(j_sg_cpu);
+		j_util = sugov_get_util(j_sg_cpu);
 		j_max = j_sg_cpu->max;
-		j_util = sugov_aggregate_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
 
 		if (j_util * max > j_max * util) {

kernel/sched/deadline.c

@@ -16,6 +16,7 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 #include "sched.h"
+#include "pelt.h"
 
 struct dl_bandwidth def_dl_bandwidth;
 
@@ -1179,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
@@ -1761,6 +1760,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	deadline_queue_push_tasks(rq);
 
+	if (rq->curr->sched_class != &dl_sched_class)
+		update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1768,6 +1770,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
 }
@@ -1784,6 +1787,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	/*
 	 * Even when we have runtime, update_curr_dl() might have resulted in us
 	 * not being the leftmost task anymore. In that case NEED_RESCHED will

kernel/sched/debug.c

@@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp)
 		cmp += 3;
 	}
 
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
+	i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp);
+	if (i < 0)
+		return i;
+
+	if (neg) {
+		sysctl_sched_features &= ~(1UL << i);
+		sched_feat_disable(i);
+	} else {
+		sysctl_sched_features |= (1UL << i);
+		sched_feat_enable(i);
 	}
 
-	return i;
+	return 0;
 }
 
 static ssize_t
@@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 {
 	char buf[64];
 	char *cmp;
-	int i;
+	int ret;
 	struct inode *inode;
 
 	if (cnt > 63)
@@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	/* Ensure the static_key remains in a consistent state */
 	inode = file_inode(filp);
 	inode_lock(inode);
-	i = sched_feat_set(cmp);
+	ret = sched_feat_set(cmp);
 	inode_unlock(inode);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
@@ -843,8 +842,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
 		unsigned long tpf, unsigned long gsf, unsigned long gpf)
 {
 	SEQ_printf(m, "numa_faults node=%d ", node);
-	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
-	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf);
+	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf);
 }
 #endif
 

kernel/sched/pelt.h

+#ifdef CONFIG_SMP
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+int update_irq_load_avg(struct rq *rq, u64 running);
+#else
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
+#endif
+
+/*
+ * When a task is dequeued, its estimated utilization should not be update if
+ * its util_avg has not been updated at least once.
+ * This flag is used to synchronize util_avg updates with util_est updates.
+ * We map this information into the LSB bit of the utilization saved at
+ * dequeue time (i.e. util_est.dequeued).
+ */
+#define UTIL_AVG_UNCHANGED 0x1
+
+static inline void cfs_se_util_change(struct sched_avg *avg)
+{
+	unsigned int enqueued;
+
+	if (!sched_feat(UTIL_EST))
+		return;
+
+	/* Avoid store if the flag has been already set */
+	enqueued = avg->util_est.enqueued;
+	if (!(enqueued & UTIL_AVG_UNCHANGED))
+		return;
+
+	/* Reset flag to report util_avg has been updated */
+	enqueued &= ~UTIL_AVG_UNCHANGED;
+	WRITE_ONCE(avg->util_est.enqueued, enqueued);
+}
+
+#else
+
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+{
+	return 0;
+}
+
+static inline int
+update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
+
+static inline int
+update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
+
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
+#endif
+
+

kernel/sched/rt.c

@@ -5,6 +5,8 @@
  */
 #include "sched.h"
 
+#include "pelt.h"
+
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 
@@ -973,8 +975,6 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
@@ -1578,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	rt_queue_push_tasks(rq);
 
+	/*
+	 * If prev task was rt, put_prev_task() has already updated the
+	 * utilization. We only care of the case where we start to schedule a
+	 * rt task
+	 */
+	if (rq->curr->sched_class != &rt_sched_class)
+		update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1585,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
 	update_curr_rt(rq);
 
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
+
 	/*
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
@@ -2314,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	update_curr_rt(rq);
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
 
 	watchdog(rq, p);
 

kernel/sched/sched.h

@@ -594,6 +594,7 @@ struct rt_rq {
 	unsigned long		rt_nr_total;
 	int			overloaded;
 	struct plist_head	pushable_tasks;
+
 #endif /* CONFIG_SMP */
 	int			rt_queued;
 
@@ -673,7 +674,26 @@ struct dl_rq {
 	u64			bw_ratio;
 };
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* An entity is a task if it doesn't "own" a runqueue */
+#define entity_is_task(se)	(!se->my_q)
+#else
+#define entity_is_task(se)	1
+#endif
+
 #ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of these helpers and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+	return scale_load_down(se->load.weight);
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	return scale_load_down(se->runnable_weight);
+}
 
 static inline bool sched_asym_prefer(int a, int b)
 {
@@ -833,8 +853,12 @@ struct rq {
 
 	struct list_head cfs_tasks;
 
-	u64			rt_avg;
-	u64			age_stamp;
+	struct sched_avg	avg_rt;
+	struct sched_avg	avg_dl;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#define HAVE_SCHED_AVG_IRQ
+	struct sched_avg	avg_irq;
+#endif
 	u64			idle_stamp;
 	u64			avg_idle;
 
@@ -1075,7 +1099,8 @@ enum numa_faults_stats {
 };
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+			int cpu, int scpu);
 extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
 #else
 static inline void
@@ -1690,15 +1715,9 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
 extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
-extern const_debug unsigned int sysctl_sched_time_avg;
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
-static inline u64 sched_avg_period(void)
-{
-	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
-}
-
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
@@ -1735,8 +1754,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
 #endif
 
 #ifdef CONFIG_SMP
-extern void sched_avg_update(struct rq *rq);
-
 #ifndef arch_scale_cpu_capacity
 static __always_inline
 unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -1747,12 +1764,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
-{
-	rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq));
-	sched_avg_update(rq);
-}
 #else
 #ifndef arch_scale_cpu_capacity
 static __always_inline
@@ -1761,8 +1772,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
-static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
@@ -2177,11 +2186,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-static inline unsigned long cpu_util_dl(struct rq *rq)
+static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
 	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
 }
 
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_dl.util_avg);
+}
+
 static inline unsigned long cpu_util_cfs(struct rq *rq)
 {
 	unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
@@ -2193,4 +2207,37 @@ static inline unsigned long cpu_util_cfs(struct rq *rq)
 
 	return util;
 }
+
+static inline unsigned long cpu_util_rt(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_rt.util_avg);
+}
+#endif
+
+#ifdef HAVE_SCHED_AVG_IRQ
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return rq->avg_irq.util_avg;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	util *= (max - irq);
+	util /= max;
+
+	return util;
+
+}
+#else
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return 0;
+}
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	return util;
+}
 #endif

kernel/sched/swait.c

@@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_locked);
 
-void swake_up(struct swait_queue_head *q)
+void swake_up_one(struct swait_queue_head *q)
 {
 	unsigned long flags;
 
@@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q)
 	swake_up_locked(q);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(swake_up);
+EXPORT_SYMBOL(swake_up_one);
 
 /*
  * Does not allow usage from IRQ disabled, since we must be able to
@@ -69,14 +69,14 @@ void swake_up_all(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_all);
 
-void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
 {
 	wait->task = current;
 	if (list_empty(&wait->task_list))
-		list_add(&wait->task_list, &q->task_list);
+		list_add_tail(&wait->task_list, &q->task_list);
 }
 
-void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
 	unsigned long flags;
 
@@ -85,16 +85,28 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int
 	set_current_state(state);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(prepare_to_swait);
+EXPORT_SYMBOL(prepare_to_swait_exclusive);
 
 long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
-	if (signal_pending_state(state, current))
-		return -ERESTARTSYS;
+	unsigned long flags;
+	long ret = 0;
 
-	prepare_to_swait(q, wait, state);
+	raw_spin_lock_irqsave(&q->lock, flags);
+	if (unlikely(signal_pending_state(state, current))) {
+		/*
+		 * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one()
+		 * must not see us.
+		 */
+		list_del_init(&wait->task_list);
+		ret = -ERESTARTSYS;
+	} else {
+		__prepare_to_swait(q, wait);
+		set_current_state(state);
+	}
+	raw_spin_unlock_irqrestore(&q->lock, flags);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(prepare_to_swait_event);
 

kernel/smpboot.c

@@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu)
 
 	mutex_lock(&smpboot_threads_lock);
 	list_for_each_entry(cur, &hotplug_threads, list)
-		if (cpumask_test_cpu(cpu, cur->cpumask))
-			smpboot_unpark_thread(cur, cpu);
+		smpboot_unpark_thread(cur, cpu);
 	mutex_unlock(&smpboot_threads_lock);
 	return 0;
 }
@@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
 }
 
 /**
- * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related
+ * smpboot_register_percpu_thread - Register a per_cpu thread related
  * 					    to hotplug
  * @plug_thread:	Hotplug thread descriptor
- * @cpumask:		The cpumask where threads run
  *
  * Creates and starts the threads on all online cpus.
  */
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask)
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 {
 	unsigned int cpu;
 	int ret = 0;
 
-	if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
-		return -ENOMEM;
-	cpumask_copy(plug_thread->cpumask, cpumask);
-
 	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
 		ret = __smpboot_create_thread(plug_thread, cpu);
 		if (ret) {
 			smpboot_destroy_threads(plug_thread);
-			free_cpumask_var(plug_thread->cpumask);
 			goto out;
 		}
-		if (cpumask_test_cpu(cpu, cpumask))
-			smpboot_unpark_thread(plug_thread, cpu);
+		smpboot_unpark_thread(plug_thread, cpu);
 	}
 	list_add(&plug_thread->list, &hotplug_threads);
 out:
@@ -315,7 +306,7 @@ int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_threa
 	put_online_cpus();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask);
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
 
 /**
  * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
@@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	smpboot_destroy_threads(plug_thread);
 	mutex_unlock(&smpboot_threads_lock);
 	put_online_cpus();
-	free_cpumask_var(plug_thread->cpumask);
 }
 EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
 
-/**
- * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
- * @plug_thread:	Hotplug thread descriptor
- * @new:		Revised mask to use
- *
- * The cpumask field in the smp_hotplug_thread must not be updated directly
- * by the client, but only by calling this function.
- * This function can only be called on a registered smp_hotplug_thread.
- */
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *new)
-{
-	struct cpumask *old = plug_thread->cpumask;
-	static struct cpumask tmp;
-	unsigned int cpu;
-
-	lockdep_assert_cpus_held();
-	mutex_lock(&smpboot_threads_lock);
-
-	/* Park threads that were exclusively enabled on the old mask. */
-	cpumask_andnot(&tmp, old, new);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_park_thread(plug_thread, cpu);
-
-	/* Unpark threads that are exclusively enabled on the new mask. */
-	cpumask_andnot(&tmp, new, old);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_unpark_thread(plug_thread, cpu);
-
-	cpumask_copy(old, new);
-
-	mutex_unlock(&smpboot_threads_lock);
-}
-
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
 /*

kernel/stop_machine.c

@@ -238,13 +238,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
 	DEFINE_WAKE_Q(wakeq);
 	int err;
+
 retry:
+	/*
+	 * The waking up of stopper threads has to happen in the same
+	 * scheduling context as the queueing.  Otherwise, there is a
+	 * possibility of one of the above stoppers being woken up by another
+	 * CPU, and preempting us. This will cause us to not wake up the other
+	 * stopper forever.
+	 */
+	preempt_disable();
 	raw_spin_lock_irq(&stopper1->lock);
 	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
 
-	err = -ENOENT;
-	if (!stopper1->enabled || !stopper2->enabled)
+	if (!stopper1->enabled || !stopper2->enabled) {
+		err = -ENOENT;
 		goto unlock;
+	}
+
 	/*
 	 * Ensure that if we race with __stop_cpus() the stoppers won't get
 	 * queued up in reverse order leading to system deadlock.
@@ -255,36 +266,30 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 	 * It can be falsely true but it is safe to spin until it is cleared,
 	 * queue_stop_cpus_work() does everything under preempt_disable().
 	 */
-	err = -EDEADLK;
-	if (unlikely(stop_cpus_in_progress))
-			goto unlock;
+	if (unlikely(stop_cpus_in_progress)) {
+		err = -EDEADLK;
+		goto unlock;
+	}
 
 	err = 0;
 	__cpu_stop_queue_work(stopper1, work1, &wakeq);
 	__cpu_stop_queue_work(stopper2, work2, &wakeq);
-	/*
-	 * The waking up of stopper threads has to happen
-	 * in the same scheduling context as the queueing.
-	 * Otherwise, there is a possibility of one of the
-	 * above stoppers being woken up by another CPU,
-	 * and preempting us. This will cause us to n ot
-	 * wake up the other stopper forever.
-	 */
-	preempt_disable();
+
 unlock:
 	raw_spin_unlock(&stopper2->lock);
 	raw_spin_unlock_irq(&stopper1->lock);
 
 	if (unlikely(err == -EDEADLK)) {
+		preempt_enable();
+
 		while (stop_cpus_in_progress)
 			cpu_relax();
+
 		goto retry;
 	}
 
-	if (!err) {
-		wake_up_q(&wakeq);
-		preempt_enable();
-	}
+	wake_up_q(&wakeq);
+	preempt_enable();
 
 	return err;
 }

kernel/sysctl.c

@@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "sched_time_avg_ms",
-		.data		= &sysctl_sched_time_avg,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-	},
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname	= "sched_schedstats",

kernel/watchdog.c

@@ -18,18 +18,14 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
-#include <linux/smpboot.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
 #include <linux/tick.h>
-#include <linux/workqueue.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/isolation.h>
+#include <linux/stop_machine.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
-#include <linux/kthread.h>
 
 static DEFINE_MUTEX(watchdog_mutex);
 
@@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void)
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
-static bool softlockup_threads_initialized __read_mostly;
+static bool softlockup_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
 static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
@@ -335,6 +330,27 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
+static DEFINE_PER_CPU(struct completion, softlockup_completion);
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every sample_period seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static int softlockup_fn(void *data)
+{
+	__this_cpu_write(soft_lockup_hrtimer_cnt,
+			 __this_cpu_read(hrtimer_interrupts));
+	__touch_watchdog();
+	complete(this_cpu_ptr(&softlockup_completion));
+
+	return 0;
+}
+
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -350,7 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	watchdog_interrupt_count();
 
 	/* kick the softlockup detector */
-	wake_up_process(__this_cpu_read(softlockup_watchdog));
+	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
+		reinit_completion(this_cpu_ptr(&softlockup_completion));
+		stop_one_cpu_nowait(smp_processor_id(),
+				softlockup_fn, NULL,
+				this_cpu_ptr(&softlockup_stop_work));
+	}
 
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
@@ -448,16 +469,15 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static void watchdog_set_prio(unsigned int policy, unsigned int prio)
-{
-	struct sched_param param = { .sched_priority = prio };
-
-	sched_setscheduler(current, policy, &param);
-}
-
 static void watchdog_enable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
+	struct completion *done = this_cpu_ptr(&softlockup_completion);
+
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
+	init_completion(done);
+	complete(done);
 
 	/*
 	 * Start the timer first to prevent the NMI watchdog triggering
@@ -473,15 +493,14 @@ static void watchdog_enable(unsigned int cpu)
 	/* Enable the perf event */
 	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
 		watchdog_nmi_enable(cpu);
-
-	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
 
 static void watchdog_disable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
-	watchdog_set_prio(SCHED_NORMAL, 0);
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	/*
 	 * Disable the perf event first. That prevents that a large delay
 	 * between disabling the timer and disabling the perf event causes
@@ -489,79 +508,66 @@ static void watchdog_disable(unsigned int cpu)
 	 */
 	watchdog_nmi_disable(cpu);
 	hrtimer_cancel(hrtimer);
+	wait_for_completion(this_cpu_ptr(&softlockup_completion));
 }
 
-static void watchdog_cleanup(unsigned int cpu, bool online)
+static int softlockup_stop_fn(void *data)
 {
-	watchdog_disable(cpu);
+	watchdog_disable(smp_processor_id());
+	return 0;
 }
 
-static int watchdog_should_run(unsigned int cpu)
+static void softlockup_stop_all(void)
 {
-	return __this_cpu_read(hrtimer_interrupts) !=
-		__this_cpu_read(soft_lockup_hrtimer_cnt);
+	int cpu;
+
+	if (!softlockup_initialized)
+		return;
+
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);
+
+	cpumask_clear(&watchdog_allowed_mask);
 }
 
-/*
- * The watchdog thread function - touches the timestamp.
- *
- * It only runs once every sample_period seconds (4 seconds by
- * default) to reset the softlockup timestamp. If this gets delayed
- * for more than 2*watchdog_thresh seconds then the debug-printout
- * triggers in watchdog_timer_fn().
- */
-static void watchdog(unsigned int cpu)
+static int softlockup_start_fn(void *data)
 {
-	__this_cpu_write(soft_lockup_hrtimer_cnt,
-			 __this_cpu_read(hrtimer_interrupts));
-	__touch_watchdog();
+	watchdog_enable(smp_processor_id());
+	return 0;
 }
 
-static struct smp_hotplug_thread watchdog_threads = {
-	.store			= &softlockup_watchdog,
-	.thread_should_run	= watchdog_should_run,
-	.thread_fn		= watchdog,
-	.thread_comm		= "watchdog/%u",
-	.setup			= watchdog_enable,
-	.cleanup		= watchdog_cleanup,
-	.park			= watchdog_disable,
-	.unpark			= watchdog_enable,
-};
-
-static void softlockup_update_smpboot_threads(void)
+static void softlockup_start_all(void)
 {
-	lockdep_assert_held(&watchdog_mutex);
-
-	if (!softlockup_threads_initialized)
-		return;
+	int cpu;
 
-	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
-					     &watchdog_allowed_mask);
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
 }
 
-/* Temporarily park all watchdog threads */
-static void softlockup_park_all_threads(void)
+int lockup_detector_online_cpu(unsigned int cpu)
 {
-	cpumask_clear(&watchdog_allowed_mask);
-	softlockup_update_smpboot_threads();
+	watchdog_enable(cpu);
+	return 0;
 }
 
-/* Unpark enabled threads */
-static void softlockup_unpark_threads(void)
+int lockup_detector_offline_cpu(unsigned int cpu)
 {
-	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
-	softlockup_update_smpboot_threads();
+	watchdog_disable(cpu);
+	return 0;
 }
 
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
 	watchdog_nmi_stop();
-	softlockup_park_all_threads();
+
+	softlockup_stop_all();
 	set_sample_period();
 	lockup_detector_update_enable();
 	if (watchdog_enabled && watchdog_thresh)
-		softlockup_unpark_threads();
+		softlockup_start_all();
+
 	watchdog_nmi_start();
 	cpus_read_unlock();
 	/*
@@ -580,8 +586,6 @@ static void lockup_detector_reconfigure(void)
  */
 static __init void lockup_detector_setup(void)
 {
-	int ret;
-
 	/*
 	 * If sysctl is off and watchdog got disabled on the command line,
 	 * nothing to do here.
@@ -592,24 +596,13 @@ static __init void lockup_detector_setup(void)
 	    !(watchdog_enabled && watchdog_thresh))
 		return;
 
-	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-						     &watchdog_allowed_mask);
-	if (ret) {
-		pr_err("Failed to initialize soft lockup detector threads\n");
-		return;
-	}
-
 	mutex_lock(&watchdog_mutex);
-	softlockup_threads_initialized = true;
 	lockup_detector_reconfigure();
+	softlockup_initialized = true;
 	mutex_unlock(&watchdog_mutex);
 }
 
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static inline int watchdog_park_threads(void) { return 0; }
-static inline void watchdog_unpark_threads(void) { }
-static inline int watchdog_enable_all_cpus(void) { return 0; }
-static inline void watchdog_disable_all_cpus(void) { }
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();

kernel/watchdog_hld.c

@@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void)
 	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
 					       watchdog_overflow_callback, NULL);
 	if (IS_ERR(evt)) {
-		pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
-			PTR_ERR(evt));
+		pr_debug("Perf event create on CPU %d failed with %ld\n", cpu,
+			 PTR_ERR(evt));
 		return PTR_ERR(evt);
 	}
 	this_cpu_write(watchdog_ev, evt);

virt/kvm/arm/arm.c

@@ -604,7 +604,7 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu->arch.pause = false;
-		swake_up(kvm_arch_vcpu_wq(vcpu));
+		swake_up_one(kvm_arch_vcpu_wq(vcpu));
 	}
 }
 
@@ -612,7 +612,7 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
 	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
-	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+	swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
 
 	if (vcpu->arch.power_off || vcpu->arch.pause) {

virt/kvm/arm/psci.c

@@ -155,7 +155,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	swake_up(wq);
+	swake_up_one(wq);
 
 	return PSCI_RET_SUCCESS;
 }

virt/kvm/async_pf.c

@@ -107,7 +107,7 @@ static void async_pf_execute(struct work_struct *work)
 	trace_kvm_async_pf_completed(addr, gva);
 
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);

virt/kvm/kvm_main.c

@@ -2172,7 +2172,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	kvm_arch_vcpu_blocking(vcpu);
 
 	for (;;) {
-		prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2214,7 +2214,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 		return true;
 	}