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:

   - Make nohz housekeeping processing more permissive and less
     intrusive to isolated CPUs

   - Decouple CPU-bound workqueue acconting from the scheduler and move
     it into the workqueue code.

   - Optimize topology building

   - Better handle quota and period overflows

   - Add more RCU annotations

   - Comment updates, misc cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  nohz_full: Allow the boot CPU to be nohz_full
  sched/isolation: Require a present CPU in housekeeping mask
  kernel/cpu: Allow non-zero CPU to be primary for suspend / kexec freeze
  power/suspend: Add function to disable secondaries for suspend
  sched/core: Allow the remote scheduler tick to be started on CPU0
  sched/nohz: Run NOHZ idle load balancer on HK_FLAG_MISC CPUs
  sched/debug: Fix spelling mistake "logaritmic" -> "logarithmic"
  sched/topology: Update init_sched_domains() comment
  cgroup/cpuset: Update stale generate_sched_domains() comments
  sched/core: Check quota and period overflow at usec to nsec conversion
  sched/core: Handle overflow in cpu_shares_write_u64
  sched/rt: Check integer overflow at usec to nsec conversion
  sched/core: Fix typo in comment
  sched/core: Make some functions static
  sched/core: Unify p->on_rq updates
  sched/core: Remove ttwu_activate()
  sched/core, workqueues: Distangle worker accounting from rq lock
  sched/fair: Remove unneeded prototype of capacity_of()
  sched/topology: Skip duplicate group rewrites in build_sched_groups()
  sched/topology: Fix build_sched_groups() comment
  ...

arch/powerpc/Kconfig

@@ -313,6 +313,10 @@ config ARCH_SUSPEND_POSSIBLE
 		   (PPC_85xx && !PPC_E500MC) || PPC_86xx || PPC_PSERIES \
 		   || 44x || 40x
 
+config ARCH_SUSPEND_NONZERO_CPU
+	def_bool y
+	depends on PPC_POWERNV || PPC_PSERIES
+
 config PPC_DCR_NATIVE
 	bool
 

include/linux/cpu.h

@@ -137,9 +137,26 @@ static inline int disable_nonboot_cpus(void)
 	return freeze_secondary_cpus(0);
 }
 extern void enable_nonboot_cpus(void);
+
+static inline int suspend_disable_secondary_cpus(void)
+{
+	int cpu = 0;
+
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU))
+		cpu = -1;
+
+	return freeze_secondary_cpus(cpu);
+}
+static inline void suspend_enable_secondary_cpus(void)
+{
+	return enable_nonboot_cpus();
+}
+
 #else /* !CONFIG_PM_SLEEP_SMP */
 static inline int disable_nonboot_cpus(void) { return 0; }
 static inline void enable_nonboot_cpus(void) {}
+static inline int suspend_disable_secondary_cpus(void) { return 0; }
+static inline void suspend_enable_secondary_cpus(void) { }
 #endif /* !CONFIG_PM_SLEEP_SMP */
 
 void cpu_startup_entry(enum cpuhp_state state);

include/linux/rcuwait.h

@@ -18,7 +18,7 @@
  * awoken.
  */
 struct rcuwait {
-	struct task_struct *task;
+	struct task_struct __rcu *task;
 };
 
 #define __RCUWAIT_INITIALIZER(name)		\

include/linux/sched/topology.h

@@ -76,8 +76,8 @@ struct sched_domain_shared {
 
 struct sched_domain {
 	/* These fields must be setup */
-	struct sched_domain *parent;	/* top domain must be null terminated */
-	struct sched_domain *child;	/* bottom domain must be null terminated */
+	struct sched_domain __rcu *parent;	/* top domain must be null terminated */
+	struct sched_domain __rcu *child;	/* bottom domain must be null terminated */
 	struct sched_group *groups;	/* the balancing groups of the domain */
 	unsigned long min_interval;	/* Minimum balance interval ms */
 	unsigned long max_interval;	/* Maximum balance interval ms */

kernel/cgroup/cpuset.c

@@ -740,11 +740,10 @@ static inline int nr_cpusets(void)
  * Must be called with cpuset_mutex held.
  *
  * The three key local variables below are:
- *    q  - a linked-list queue of cpuset pointers, used to implement a
- *	   top-down scan of all cpusets.  This scan loads a pointer
- *	   to each cpuset marked is_sched_load_balance into the
- *	   array 'csa'.  For our purposes, rebuilding the schedulers
- *	   sched domains, we can ignore !is_sched_load_balance cpusets.
+ *    cp - cpuset pointer, used (together with pos_css) to perform a
+ *	   top-down scan of all cpusets. For our purposes, rebuilding
+ *	   the schedulers sched domains, we can ignore !is_sched_load_
+ *	   balance cpusets.
  *  csa  - (for CpuSet Array) Array of pointers to all the cpusets
  *	   that need to be load balanced, for convenient iterative
  *	   access by the subsequent code that finds the best partition,
@@ -775,7 +774,7 @@ static inline int nr_cpusets(void)
 static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
-	struct cpuset *cp;	/* scans q */
+	struct cpuset *cp;	/* top-down scan of cpusets */
 	struct cpuset **csa;	/* array of all cpuset ptrs */
 	int csn;		/* how many cpuset ptrs in csa so far */
 	int i, j, k;		/* indices for partition finding loops */

kernel/cpu.c

@@ -9,6 +9,7 @@
 #include <linux/notifier.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
 #include <linux/sched/task.h>
 #include <linux/sched/smt.h>
 #include <linux/unistd.h>
@@ -1199,8 +1200,15 @@ int freeze_secondary_cpus(int primary)
 	int cpu, error = 0;
 
 	cpu_maps_update_begin();
+	if (primary == -1) {
+		primary = cpumask_first(cpu_online_mask);
+		if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
+			primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+	} else {
 		if (!cpu_online(primary))
 			primary = cpumask_first(cpu_online_mask);
+	}
+
 	/*
 	 * We take down all of the non-boot CPUs in one shot to avoid races
 	 * with the userspace trying to use the CPU hotplug at the same time

kernel/kexec_core.c

@@ -1150,7 +1150,7 @@ int kernel_kexec(void)
 		error = dpm_suspend_end(PMSG_FREEZE);
 		if (error)
 			goto Resume_devices;
-		error = disable_nonboot_cpus();
+		error = suspend_disable_secondary_cpus();
 		if (error)
 			goto Enable_cpus;
 		local_irq_disable();
@@ -1183,7 +1183,7 @@ int kernel_kexec(void)
  Enable_irqs:
 		local_irq_enable();
  Enable_cpus:
-		enable_nonboot_cpus();
+		suspend_enable_secondary_cpus();
 		dpm_resume_start(PMSG_RESTORE);
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);

kernel/power/Kconfig

@@ -114,6 +114,15 @@ config PM_SLEEP_SMP
 	depends on PM_SLEEP
 	select HOTPLUG_CPU
 
+config PM_SLEEP_SMP_NONZERO_CPU
+	def_bool y
+	depends on PM_SLEEP_SMP
+	depends on ARCH_SUSPEND_NONZERO_CPU
+	---help---
+	If an arch can suspend (for suspend, hibernate, kexec, etc) on a
+	non-zero numbered CPU, it may define ARCH_SUSPEND_NONZERO_CPU. This
+	will allow nohz_full mask to include CPU0.
+
 config PM_AUTOSLEEP
 	bool "Opportunistic sleep"
 	depends on PM_SLEEP

kernel/power/hibernate.c

@@ -281,7 +281,7 @@ static int create_image(int platform_mode)
 	if (error || hibernation_test(TEST_PLATFORM))
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || hibernation_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -323,7 +323,7 @@ static int create_image(int platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	platform_finish(platform_mode);
@@ -417,7 +417,7 @@ int hibernation_snapshot(int platform_mode)
 
 int __weak hibernate_resume_nonboot_cpu_disable(void)
 {
-	return disable_nonboot_cpus();
+	return suspend_disable_secondary_cpus();
 }
 
 /**
@@ -486,7 +486,7 @@ static int resume_target_kernel(bool platform_mode)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Cleanup:
 	platform_restore_cleanup(platform_mode);
@@ -564,7 +564,7 @@ int hibernation_platform_enter(void)
 	if (error)
 		goto Platform_finish;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error)
 		goto Enable_cpus;
 
@@ -586,7 +586,7 @@ int hibernation_platform_enter(void)
 	local_irq_enable();
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_finish:
 	hibernation_ops->finish();

kernel/power/suspend.c

@@ -428,7 +428,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	if (suspend_test(TEST_PLATFORM))
 		goto Platform_wake;
 
-	error = disable_nonboot_cpus();
+	error = suspend_disable_secondary_cpus();
 	if (error || suspend_test(TEST_CPUS))
 		goto Enable_cpus;
 
@@ -458,7 +458,7 @@ static int suspend_enter(suspend_state_t state, bool *wakeup)
 	BUG_ON(irqs_disabled());
 
  Enable_cpus:
-	enable_nonboot_cpus();
+	suspend_enable_secondary_cpus();
 
  Platform_wake:
 	platform_resume_noirq(state);

kernel/sched/core.c

@@ -792,10 +792,14 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 		rq->nr_uninterruptible--;
 
 	enqueue_task(rq, p, flags);
+
+	p->on_rq = TASK_ON_RQ_QUEUED;
 }
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING;
+
 	if (task_contributes_to_load(p))
 		rq->nr_uninterruptible++;
 
@@ -920,7 +924,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 }
 
 /*
- * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
@@ -1236,11 +1240,9 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		rq_pin_lock(src_rq, &srf);
 		rq_pin_lock(dst_rq, &drf);
 
-		p->on_rq = TASK_ON_RQ_MIGRATING;
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
-		p->on_rq = TASK_ON_RQ_QUEUED;
 		check_preempt_curr(dst_rq, p, 0);
 
 		rq_unpin_lock(dst_rq, &drf);
@@ -1680,16 +1682,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
 }
 
-static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags)
-{
-	activate_task(rq, p, en_flags);
-	p->on_rq = TASK_ON_RQ_QUEUED;
-
-	/* If a worker is waking up, notify the workqueue: */
-	if (p->flags & PF_WQ_WORKER)
-		wq_worker_waking_up(p, cpu_of(rq));
-}
-
 /*
  * Mark the task runnable and perform wakeup-preemption.
  */
@@ -1741,7 +1733,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
 
-	ttwu_activate(rq, p, en_flags);
+	activate_task(rq, p, en_flags);
 	ttwu_do_wakeup(rq, p, wake_flags, rf);
 }
 
@@ -2105,56 +2097,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	return success;
 }
 
-/**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- * @rf: request-queue flags for pinning
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf)
-{
-	struct rq *rq = task_rq(p);
-
-	if (WARN_ON_ONCE(rq != this_rq()) ||
-	    WARN_ON_ONCE(p == current))
-		return;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (!raw_spin_trylock(&p->pi_lock)) {
-		/*
-		 * This is OK, because current is on_cpu, which avoids it being
-		 * picked for load-balance and preemption/IRQs are still
-		 * disabled avoiding further scheduler activity on it and we've
-		 * not yet picked a replacement task.
-		 */
-		rq_unlock(rq, rf);
-		raw_spin_lock(&p->pi_lock);
-		rq_relock(rq, rf);
-	}
-
-	if (!(p->state & TASK_NORMAL))
-		goto out;
-
-	trace_sched_waking(p);
-
-	if (!task_on_rq_queued(p)) {
-		if (p->in_iowait) {
-			delayacct_blkio_end(p);
-			atomic_dec(&rq->nr_iowait);
-		}
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK);
-	}
-
-	ttwu_do_wakeup(rq, p, 0, rf);
-	ttwu_stat(p, smp_processor_id(), 0);
-out:
-	raw_spin_unlock(&p->pi_lock);
-}
-
 /**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
@@ -2466,7 +2408,6 @@ void wake_up_new_task(struct task_struct *p)
 	post_init_entity_util_avg(p);
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
@@ -3465,25 +3406,11 @@ static void __sched notrace __schedule(bool preempt)
 			prev->state = TASK_RUNNING;
 		} else {
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
-			prev->on_rq = 0;
 
 			if (prev->in_iowait) {
 				atomic_inc(&rq->nr_iowait);
 				delayacct_blkio_start();
 			}
-
-			/*
-			 * If a worker went to sleep, notify and ask workqueue
-			 * whether it wants to wake up a task to maintain
-			 * concurrency.
-			 */
-			if (prev->flags & PF_WQ_WORKER) {
-				struct task_struct *to_wakeup;
-
-				to_wakeup = wq_worker_sleeping(prev);
-				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup, &rf);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -3543,6 +3470,20 @@ static inline void sched_submit_work(struct task_struct *tsk)
 {
 	if (!tsk->state || tsk_is_pi_blocked(tsk))
 		return;
+
+	/*
+	 * If a worker went to sleep, notify and ask workqueue whether
+	 * it wants to wake up a task to maintain concurrency.
+	 * As this function is called inside the schedule() context,
+	 * we disable preemption to avoid it calling schedule() again
+	 * in the possible wakeup of a kworker.
+	 */
+	if (tsk->flags & PF_WQ_WORKER) {
+		preempt_disable();
+		wq_worker_sleeping(tsk);
+		preempt_enable_no_resched();
+	}
+
 	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
@@ -3551,6 +3492,12 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
+static void sched_update_worker(struct task_struct *tsk)
+{
+	if (tsk->flags & PF_WQ_WORKER)
+		wq_worker_running(tsk);
+}
+
 asmlinkage __visible void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
@@ -3561,6 +3508,7 @@ asmlinkage __visible void __sched schedule(void)
 		__schedule(false);
 		sched_preempt_enable_no_resched();
 	} while (need_resched());
+	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
 
@@ -5917,7 +5865,7 @@ void __init sched_init_smp(void)
 
 static int __init migration_init(void)
 {
-	sched_rq_cpu_starting(smp_processor_id());
+	sched_cpu_starting(smp_processor_id());
 	return 0;
 }
 early_initcall(migration_init);
@@ -6558,6 +6506,8 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cftype, u64 shareval)
 {
+	if (shareval > scale_load_down(ULONG_MAX))
+		shareval = MAX_SHARES;
 	return sched_group_set_shares(css_tg(css), scale_load(shareval));
 }
 
@@ -6573,7 +6523,7 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
 static DEFINE_MUTEX(cfs_constraints_mutex);
 
 const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
-const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
 
@@ -6653,20 +6603,22 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
 	return ret;
 }
 
-int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
+static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
 {
 	u64 quota, period;
 
 	period = ktime_to_ns(tg->cfs_bandwidth.period);
 	if (cfs_quota_us < 0)
 		quota = RUNTIME_INF;
-	else
+	else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC)
 		quota = (u64)cfs_quota_us * NSEC_PER_USEC;
+	else
+		return -EINVAL;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_quota(struct task_group *tg)
+static long tg_get_cfs_quota(struct task_group *tg)
 {
 	u64 quota_us;
 
@@ -6679,17 +6631,20 @@ long tg_get_cfs_quota(struct task_group *tg)
 	return quota_us;
 }
 
-int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
+static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
 {
 	u64 quota, period;
 
+	if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	period = (u64)cfs_period_us * NSEC_PER_USEC;
 	quota = tg->cfs_bandwidth.quota;
 
 	return tg_set_cfs_bandwidth(tg, period, quota);
 }
 
-long tg_get_cfs_period(struct task_group *tg)
+static long tg_get_cfs_period(struct task_group *tg)
 {
 	u64 cfs_period_us;
 

kernel/sched/cpufreq.c

@@ -7,7 +7,7 @@
  */
 #include "sched.h"
 
-DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 
 /**
  * cpufreq_add_update_util_hook - Populate the CPU's update_util_data pointer.

kernel/sched/debug.c

@@ -702,7 +702,7 @@ do {									\
 
 static const char *sched_tunable_scaling_names[] = {
 	"none",
-	"logaritmic",
+	"logarithmic",
 	"linear"
 };
 

kernel/sched/fair.c

@@ -2597,7 +2597,7 @@ void task_numa_work(struct callback_head *work)
 /*
  * Drive the periodic memory faults..
  */
-void task_tick_numa(struct rq *rq, struct task_struct *curr)
+static void task_tick_numa(struct rq *rq, struct task_struct *curr)
 {
 	struct callback_head *work = &curr->numa_work;
 	u64 period, now;
@@ -3571,7 +3571,7 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq)
  * Synchronize entity load avg of dequeued entity without locking
  * the previous rq.
  */
-void sync_entity_load_avg(struct sched_entity *se)
+static void sync_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	u64 last_update_time;
@@ -3584,7 +3584,7 @@ void sync_entity_load_avg(struct sched_entity *se)
  * Task first catches up with cfs_rq, and then subtract
  * itself from the cfs_rq (task must be off the queue now).
  */
-void remove_entity_load_avg(struct sched_entity *se)
+static void remove_entity_load_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	unsigned long flags;
@@ -5145,7 +5145,6 @@ static inline void hrtick_update(struct rq *rq)
 
 #ifdef CONFIG_SMP
 static inline unsigned long cpu_util(int cpu);
-static unsigned long capacity_of(int cpu);
 
 static inline bool cpu_overutilized(int cpu)
 {
@@ -7521,7 +7520,6 @@ static void detach_task(struct task_struct *p, struct lb_env *env)
 {
 	lockdep_assert_held(&env->src_rq->lock);
 
-	p->on_rq = TASK_ON_RQ_MIGRATING;
 	deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, env->dst_cpu);
 }
@@ -7657,7 +7655,6 @@ static void attach_task(struct rq *rq, struct task_struct *p)
 
 	BUG_ON(task_rq(p) != rq);
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
-	p->on_rq = TASK_ON_RQ_QUEUED;
 	check_preempt_curr(rq, p, 0);
 }
 
@@ -9551,22 +9548,26 @@ static inline int on_null_domain(struct rq *rq)
  * - When one of the busy CPUs notice that there may be an idle rebalancing
  *   needed, they will kick the idle load balancer, which then does idle
  *   load balancing for all the idle CPUs.
+ * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set
+ *   anywhere yet.
  */
 
 static inline int find_new_ilb(void)
 {
-	int ilb = cpumask_first(nohz.idle_cpus_mask);
+	int ilb;
 
-	if (ilb < nr_cpu_ids && idle_cpu(ilb))
+	for_each_cpu_and(ilb, nohz.idle_cpus_mask,
+			      housekeeping_cpumask(HK_FLAG_MISC)) {
+		if (idle_cpu(ilb))
 			return ilb;
+	}
 
 	return nr_cpu_ids;
 }
 
 /*
- * Kick a CPU to do the nohz balancing, if it is time for it. We pick the
- * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle
- * CPU (if there is one).
+ * Kick a CPU to do the nohz balancing, if it is time for it. We pick any
+ * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one).
  */
 static void kick_ilb(unsigned int flags)
 {

kernel/sched/isolation.c

@@ -65,6 +65,7 @@ void __init housekeeping_init(void)
 static int __init housekeeping_setup(char *str, enum hk_flags flags)
 {
 	cpumask_var_t non_housekeeping_mask;
+	cpumask_var_t tmp;
 	int err;
 
 	alloc_bootmem_cpumask_var(&non_housekeeping_mask);
@@ -75,16 +76,23 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 		return 0;
 	}
 
+	alloc_bootmem_cpumask_var(&tmp);
 	if (!housekeeping_flags) {
 		alloc_bootmem_cpumask_var(&housekeeping_mask);
 		cpumask_andnot(housekeeping_mask,
 			       cpu_possible_mask, non_housekeeping_mask);
-		if (cpumask_empty(housekeeping_mask))
+
+		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+		if (cpumask_empty(tmp)) {
+			pr_warn("Housekeeping: must include one present CPU, "
+				"using boot CPU:%d\n", smp_processor_id());
 			__cpumask_set_cpu(smp_processor_id(), housekeeping_mask);
+			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
+		}
 	} else {
-		cpumask_var_t tmp;
-
-		alloc_bootmem_cpumask_var(&tmp);
+		cpumask_andnot(tmp, cpu_present_mask, non_housekeeping_mask);
+		if (cpumask_empty(tmp))
+			__cpumask_clear_cpu(smp_processor_id(), non_housekeeping_mask);
 		cpumask_andnot(tmp, cpu_possible_mask, non_housekeeping_mask);
 		if (!cpumask_equal(tmp, housekeeping_mask)) {
 			pr_warn("Housekeeping: nohz_full= must match isolcpus=\n");
@@ -92,8 +100,8 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags)
 			free_bootmem_cpumask_var(non_housekeeping_mask);
 			return 0;
 		}
-		free_bootmem_cpumask_var(tmp);
 	}
+	free_bootmem_cpumask_var(tmp);
 
 	if ((flags & HK_FLAG_TICK) && !(housekeeping_flags & HK_FLAG_TICK)) {
 		if (IS_ENABLED(CONFIG_NO_HZ_FULL)) {

kernel/sched/rt.c

@@ -2555,6 +2555,8 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us)
 	rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC;
 	if (rt_runtime_us < 0)
 		rt_runtime = RUNTIME_INF;
+	else if ((u64)rt_runtime_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
 
 	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
 }
@@ -2575,6 +2577,9 @@ int sched_group_set_rt_period(struct task_group *tg, u64 rt_period_us)
 {
 	u64 rt_runtime, rt_period;
 
+	if (rt_period_us > U64_MAX / NSEC_PER_USEC)
+		return -EINVAL;
+
 	rt_period = rt_period_us * NSEC_PER_USEC;
 	rt_runtime = tg->rt_bandwidth.rt_runtime;
 

kernel/sched/sched.h

@@ -780,7 +780,7 @@ struct root_domain {
 	 * NULL-terminated list of performance domains intersecting with the
 	 * CPUs of the rd. Protected by RCU.
 	 */
-	struct perf_domain	*pd;
+	struct perf_domain __rcu *pd;
 };
 
 extern struct root_domain def_root_domain;
@@ -870,7 +870,7 @@ struct rq {
 
 #ifdef CONFIG_SMP
 	struct root_domain		*rd;
-	struct sched_domain	*sd;
+	struct sched_domain __rcu	*sd;
 
 	unsigned long		cpu_capacity;
 	unsigned long		cpu_capacity_orig;
@@ -1324,13 +1324,13 @@ static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
 	return sd;
 }
 
-DECLARE_PER_CPU(struct sched_domain *, sd_llc);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DECLARE_PER_CPU(int, sd_llc_size);
 DECLARE_PER_CPU(int, sd_llc_id);
-DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DECLARE_PER_CPU(struct sched_domain *, sd_numa);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DECLARE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DECLARE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 extern struct static_key_false sched_asym_cpucapacity;
 
 struct sched_group_capacity {
@@ -2185,7 +2185,7 @@ static inline u64 irq_time_read(int cpu)
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #ifdef CONFIG_CPU_FREQ
-DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data);
+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
 
 /**
  * cpufreq_update_util - Take a note about CPU utilization changes.

kernel/sched/topology.c

@@ -615,13 +615,13 @@ static void destroy_sched_domains(struct sched_domain *sd)
  * the cpumask of the domain), this allows us to quickly tell if
  * two CPUs are in the same cache domain, see cpus_share_cache().
  */
-DEFINE_PER_CPU(struct sched_domain *, sd_llc);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc);
 DEFINE_PER_CPU(int, sd_llc_size);
 DEFINE_PER_CPU(int, sd_llc_id);
-DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared);
-DEFINE_PER_CPU(struct sched_domain *, sd_numa);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing);
-DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity);
+DEFINE_PER_CPU(struct sched_domain_shared __rcu *, sd_llc_shared);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_numa);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_packing);
+DEFINE_PER_CPU(struct sched_domain __rcu *, sd_asym_cpucapacity);
 DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
 
 static void update_top_cache_domain(int cpu)
@@ -1059,6 +1059,7 @@ 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;
+	bool already_visited;
 
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
@@ -1066,9 +1067,14 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 	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);
+	/* Increase refcounts for claim_allocations: */
+	already_visited = atomic_inc_return(&sg->ref) > 1;
+	/* sgc visits should follow a similar trend as sg */
+	WARN_ON(already_visited != (atomic_inc_return(&sg->sgc->ref) > 1));
+
+	/* If we have already visited that group, it's already initialized. */
+	if (already_visited)
+		return sg;
 
 	if (child) {
 		cpumask_copy(sched_group_span(sg), sched_domain_span(child));
@@ -1087,8 +1093,8 @@ static struct sched_group *get_group(int cpu, struct sd_data *sdd)
 
 /*
  * build_sched_groups will build a circular linked list of the groups
- * covered by the given span, and will set each group's ->cpumask correctly,
- * and ->cpu_capacity to 0.
+ * covered by the given span, will set each group's ->cpumask correctly,
+ * and will initialize their ->sgc.
  *
  * Assumes the sched_domain tree is fully constructed
  */
@@ -2075,9 +2081,8 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
 }
 
 /*
- * Set up scheduler domains and groups. Callers must hold the hotplug lock.
- * For now this just excludes isolated CPUs, but could be used to
- * exclude other special cases in the future.
+ * Set up scheduler domains and groups.  For now this just excludes isolated
+ * CPUs, but could be used to exclude other special cases in the future.
  */
 int sched_init_domains(const struct cpumask *cpu_map)
 {

kernel/time/tick-common.c

@@ -46,6 +46,14 @@ ktime_t tick_period;
  *    procedure also covers cpu hotplug.
  */
 int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
+ * tick_do_timer_cpu and it should be taken over by an eligible secondary
+ * when one comes online.
+ */
+static int tick_do_timer_boot_cpu __read_mostly = -1;
+#endif
 
 /*
  * Debugging: see timer_list.c
@@ -167,6 +175,26 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
 	}
 }
 
+#ifdef CONFIG_NO_HZ_FULL
+static void giveup_do_timer(void *info)
+{
+	int cpu = *(unsigned int *)info;
+
+	WARN_ON(tick_do_timer_cpu != smp_processor_id());
+
+	tick_do_timer_cpu = cpu;
+}
+
+static void tick_take_do_timer_from_boot(void)
+{
+	int cpu = smp_processor_id();
+	int from = tick_do_timer_boot_cpu;
+
+	if (from >= 0 && from != cpu)
+		smp_call_function_single(from, giveup_do_timer, &cpu, 1);
+}
+#endif
+
 /*
  * Setup the tick device
  */
@@ -186,12 +214,26 @@ static void tick_setup_device(struct tick_device *td,
 		 * this cpu:
 		 */
 		if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
-			if (!tick_nohz_full_cpu(cpu))
 			tick_do_timer_cpu = cpu;
-			else
-				tick_do_timer_cpu = TICK_DO_TIMER_NONE;
+
 			tick_next_period = ktime_get();
 			tick_period = NSEC_PER_SEC / HZ;
+#ifdef CONFIG_NO_HZ_FULL
+			/*
+			 * The boot CPU may be nohz_full, in which case set
+			 * tick_do_timer_boot_cpu so the first housekeeping
+			 * secondary that comes up will take do_timer from
+			 * us.
+			 */
+			if (tick_nohz_full_cpu(cpu))
+				tick_do_timer_boot_cpu = cpu;
+
+		} else if (tick_do_timer_boot_cpu != -1 &&
+						!tick_nohz_full_cpu(cpu)) {
+			tick_take_do_timer_from_boot();
+			tick_do_timer_boot_cpu = -1;
+			WARN_ON(tick_do_timer_cpu != cpu);
+#endif
 		}
 
 		/*

kernel/time/tick-sched.c

@@ -121,10 +121,16 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
 	 * into a long sleep. If two CPUs happen to assign themselves to
 	 * this duty, then the jiffies update is still serialized by
 	 * jiffies_lock.
+	 *
+	 * If nohz_full is enabled, this should not happen because the
+	 * tick_do_timer_cpu never relinquishes.
 	 */
-	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
-	    && !tick_nohz_full_cpu(cpu))
+	if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
+#ifdef CONFIG_NO_HZ_FULL
+		WARN_ON(tick_nohz_full_running);
+#endif
 		tick_do_timer_cpu = cpu;
+	}
 #endif
 
 	/* Check, if the jiffies need an update */
@@ -395,8 +401,8 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask)
 static int tick_nohz_cpu_down(unsigned int cpu)
 {
 	/*
-	 * The boot CPU handles housekeeping duty (unbound timers,
-	 * workqueues, timekeeping, ...) on behalf of full dynticks
+	 * The tick_do_timer_cpu CPU handles housekeeping duty (unbound
+	 * timers, workqueues, timekeeping, ...) on behalf of full dynticks
 	 * CPUs. It must remain online when nohz full is enabled.
 	 */
 	if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
@@ -423,13 +429,16 @@ void __init tick_nohz_init(void)
 		return;
 	}
 
+	if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
+			!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
 		cpu = smp_processor_id();
 
 		if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
-		pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n",
-			cpu);
+			pr_warn("NO_HZ: Clearing %d from nohz_full range "
+				"for timekeeping\n", cpu);
 			cpumask_clear_cpu(cpu, tick_nohz_full_mask);
 		}
+	}
 
 	for_each_cpu(cpu, tick_nohz_full_mask)
 		context_tracking_cpu_set(cpu);
@@ -904,8 +913,13 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
 		/*
 		 * Boot safety: make sure the timekeeping duty has been
 		 * assigned before entering dyntick-idle mode,
+		 * tick_do_timer_cpu is TICK_DO_TIMER_BOOT
 		 */
-		if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+		if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT))
+			return false;
+
+		/* Should not happen for nohz-full */
+		if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
 			return false;
 	}
 

kernel/workqueue.c

@@ -841,43 +841,32 @@ static void wake_up_worker(struct worker_pool *pool)
 }
 
 /**
- * wq_worker_waking_up - a worker is waking up
+ * wq_worker_running - a worker is running again
  * @task: task waking up
- * @cpu: CPU @task is waking up to
  *
- * This function is called during try_to_wake_up() when a worker is
- * being awoken.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * This function is called when a worker returns from schedule()
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu)
+void wq_worker_running(struct task_struct *task)
 {
 	struct worker *worker = kthread_data(task);
 
-	if (!(worker->flags & WORKER_NOT_RUNNING)) {
-		WARN_ON_ONCE(worker->pool->cpu != cpu);
+	if (!worker->sleeping)
+		return;
+	if (!(worker->flags & WORKER_NOT_RUNNING))
 		atomic_inc(&worker->pool->nr_running);
-	}
+	worker->sleeping = 0;
 }
 
 /**
  * wq_worker_sleeping - a worker is going to sleep
  * @task: task going to sleep
  *
- * This function is called during schedule() when a busy worker is
- * going to sleep.  Worker on the same cpu can be woken up by
- * returning pointer to its task.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
- *
- * Return:
- * Worker task on @cpu to wake up, %NULL if none.
+ * This function is called from schedule() when a busy worker is
+ * going to sleep.
  */
-struct task_struct *wq_worker_sleeping(struct task_struct *task)
+void wq_worker_sleeping(struct task_struct *task)
 {
-	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
+	struct worker *next, *worker = kthread_data(task);
 	struct worker_pool *pool;
 
 	/*
@@ -886,13 +875,15 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
 	 * checking NOT_RUNNING.
 	 */
 	if (worker->flags & WORKER_NOT_RUNNING)
-		return NULL;
+		return;
 
 	pool = worker->pool;
 
-	/* this can only happen on the local cpu */
-	if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id()))
-		return NULL;
+	if (WARN_ON_ONCE(worker->sleeping))
+		return;
+
+	worker->sleeping = 1;
+	spin_lock_irq(&pool->lock);
 
 	/*
 	 * The counterpart of the following dec_and_test, implied mb,
@@ -906,9 +897,12 @@ struct task_struct *wq_worker_sleeping(struct task_struct *task)
 	 * lock is safe.
 	 */
 	if (atomic_dec_and_test(&pool->nr_running) &&
-	    !list_empty(&pool->worklist))
-		to_wakeup = first_idle_worker(pool);
-	return to_wakeup ? to_wakeup->task : NULL;
+	    !list_empty(&pool->worklist)) {
+		next = first_idle_worker(pool);
+		if (next)
+			wake_up_process(next->task);
+	}
+	spin_unlock_irq(&pool->lock);
 }
 
 /**
@@ -4929,7 +4923,7 @@ static void rebind_workers(struct worker_pool *pool)
 		 *
 		 * WRITE_ONCE() is necessary because @worker->flags may be
 		 * tested without holding any lock in
-		 * wq_worker_waking_up().  Without it, NOT_RUNNING test may
+		 * wq_worker_running().  Without it, NOT_RUNNING test may
 		 * fail incorrectly leading to premature concurrency
 		 * management operations.
 		 */

kernel/workqueue_internal.h

@@ -44,6 +44,7 @@ struct worker {
 	unsigned long		last_active;	/* L: last active timestamp */
 	unsigned int		flags;		/* X: flags */
 	int			id;		/* I: worker id */
+	int			sleeping;	/* None */
 
 	/*
 	 * Opaque string set with work_set_desc().  Printed out with task
@@ -72,8 +73,8 @@ static inline struct worker *current_wq_worker(void)
  * Scheduler hooks for concurrency managed workqueue.  Only to be used from
  * sched/ and workqueue.c.
  */
-void wq_worker_waking_up(struct task_struct *task, int cpu);
-struct task_struct *wq_worker_sleeping(struct task_struct *task);
+void wq_worker_running(struct task_struct *task);
+void wq_worker_sleeping(struct task_struct *task);
 work_func_t wq_worker_last_func(struct task_struct *task);
 
 #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */