1 files changed, 214 insertions, 152 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e7c535eee0a6..e9866f86f304 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5,37 +5,14 @@
  *
  *  Copyright (C) 1991-2002  Linus Torvalds
  */
-#include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <uapi/linux/sched/types.h>
-#include <linux/sched/loadavg.h>
-#include <linux/sched/hotplug.h>
-#include <linux/wait_bit.h>
-#include <linux/cpuset.h>
-#include <linux/delayacct.h>
-#include <linux/init_task.h>
-#include <linux/context_tracking.h>
-#include <linux/rcupdate_wait.h>
-#include <linux/compat.h>
-
-#include <linux/blkdev.h>
-#include <linux/kprobes.h>
-#include <linux/mmu_context.h>
-#include <linux/module.h>
-#include <linux/nmi.h>
-#include <linux/prefetch.h>
-#include <linux/profile.h>
-#include <linux/security.h>
-#include <linux/syscalls.h>
-#include <linux/sched/isolation.h>
+#include "sched.h"
+
+#include <linux/kthread.h>
+#include <linux/nospec.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#endif
 
-#include "sched.h"
 #include "../workqueue_internal.h"
 #include "../smpboot.h"
 
@@ -135,7 +112,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 		 *					[L] ->on_rq
 		 *	RELEASE (rq->lock)
 		 *
-		 * If we observe the old cpu in task_rq_lock, the acquire of
+		 * If we observe the old CPU in task_rq_lock, the acquire of
 		 * the old rq->lock will fully serialize against the stores.
 		 *
 		 * If we observe the new CPU in task_rq_lock, the acquire will
@@ -333,7 +310,7 @@ void hrtick_start(struct rq *rq, u64 delay)
 }
 #endif /* CONFIG_SMP */
 
-static void init_rq_hrtick(struct rq *rq)
+static void hrtick_rq_init(struct rq *rq)
 {
 #ifdef CONFIG_SMP
 	rq->hrtick_csd_pending = 0;
@@ -351,7 +328,7 @@ static inline void hrtick_clear(struct rq *rq)
 {
 }
 
-static inline void init_rq_hrtick(struct rq *rq)
+static inline void hrtick_rq_init(struct rq *rq)
 {
 }
 #endif	/* CONFIG_SCHED_HRTICK */
@@ -609,7 +586,7 @@ static inline bool got_nohz_idle_kick(void)
 {
 	int cpu = smp_processor_id();
 
-	if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)))
+	if (!(atomic_read(nohz_flags(cpu)) & NOHZ_KICK_MASK))
 		return false;
 
 	if (idle_cpu(cpu) && !need_resched())
@@ -619,7 +596,7 @@ static inline bool got_nohz_idle_kick(void)
 	 * We can't run Idle Load Balance on this CPU for this time so we
 	 * cancel it and clear NOHZ_BALANCE_KICK
 	 */
-	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
+	atomic_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
 	return false;
 }
 
@@ -900,10 +877,37 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * this case, we can save a useless back to back clock update.
 	 */
 	if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr))
-		rq_clock_skip_update(rq, true);
+		rq_clock_skip_update(rq);
 }
 
 #ifdef CONFIG_SMP
+
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+	if (!(p->flags & PF_KTHREAD))
+		return false;
+
+	if (p->nr_cpus_allowed != 1)
+		return false;
+
+	return true;
+}
+
+/*
+ * Per-CPU kthreads are allowed to run on !actie && online CPUs, see
+ * __set_cpus_allowed_ptr() and select_fallback_rq().
+ */
+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
+{
+	if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+		return false;
+
+	if (is_per_cpu_kthread(p))
+		return cpu_online(cpu);
+
+	return cpu_active(cpu);
+}
+
 /*
  * This is how migration works:
  *
@@ -961,16 +965,8 @@ struct migration_arg {
 static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf,
 				 struct task_struct *p, int dest_cpu)
 {
-	if (p->flags & PF_KTHREAD) {
-		if (unlikely(!cpu_online(dest_cpu)))
-			return rq;
-	} else {
-		if (unlikely(!cpu_active(dest_cpu)))
-			return rq;
-	}
-
 	/* Affinity changed (again). */
-	if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+	if (!is_cpu_allowed(p, dest_cpu))
 		return rq;
 
 	update_rq_clock(rq);
@@ -1457,7 +1453,7 @@ EXPORT_SYMBOL_GPL(kick_process);
  *
  *  - cpu_active must be a subset of cpu_online
  *
- *  - on cpu-up we allow per-cpu kthreads on the online && !active cpu,
+ *  - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
  *    see __set_cpus_allowed_ptr(). At this point the newly online
  *    CPU isn't yet part of the sched domains, and balancing will not
  *    see it.
@@ -1499,10 +1495,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 	for (;;) {
 		/* Any allowed, online CPU? */
 		for_each_cpu(dest_cpu, &p->cpus_allowed) {
-			if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu))
-				continue;
-			if (!cpu_online(dest_cpu))
+			if (!is_cpu_allowed(p, dest_cpu))
 				continue;
+
 			goto out;
 		}
 
@@ -1565,8 +1560,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	 * [ this allows ->select_task() to simply return task_cpu(p) and
 	 *   not worry about this generic constraint ]
 	 */
-	if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) ||
-		     !cpu_online(cpu)))
+	if (unlikely(!is_cpu_allowed(p, cpu)))
 		cpu = select_fallback_rq(task_cpu(p), p);
 
 	return cpu;
@@ -2200,27 +2194,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
 
-#ifdef CONFIG_NUMA_BALANCING
-	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
-		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
-		p->mm->numa_scan_seq = 0;
-	}
-
-	if (clone_flags & CLONE_VM)
-		p->numa_preferred_nid = current->numa_preferred_nid;
-	else
-		p->numa_preferred_nid = -1;
-
-	p->node_stamp = 0ULL;
-	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
-	p->numa_work.next = &p->numa_work;
-	p->numa_faults = NULL;
-	p->last_task_numa_placement = 0;
-	p->last_sum_exec_runtime = 0;
-
-	p->numa_group = NULL;
-#endif /* CONFIG_NUMA_BALANCING */
+	init_numa_balancing(clone_flags, p);
 }
 
 DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
@@ -2488,17 +2462,17 @@ void wake_up_new_task(struct task_struct *p)
 
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
-static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE;
+static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
 
 void preempt_notifier_inc(void)
 {
-	static_key_slow_inc(&preempt_notifier_key);
+	static_branch_inc(&preempt_notifier_key);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_inc);
 
 void preempt_notifier_dec(void)
 {
-	static_key_slow_dec(&preempt_notifier_key);
+	static_branch_dec(&preempt_notifier_key);
 }
 EXPORT_SYMBOL_GPL(preempt_notifier_dec);
 
@@ -2508,7 +2482,7 @@ EXPORT_SYMBOL_GPL(preempt_notifier_dec);
  */
 void preempt_notifier_register(struct preempt_notifier *notifier)
 {
-	if (!static_key_false(&preempt_notifier_key))
+	if (!static_branch_unlikely(&preempt_notifier_key))
 		WARN(1, "registering preempt_notifier while notifiers disabled\n");
 
 	hlist_add_head(&notifier->link, &current->preempt_notifiers);
@@ -2537,7 +2511,7 @@ static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
 
 static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
 {
-	if (static_key_false(&preempt_notifier_key))
+	if (static_branch_unlikely(&preempt_notifier_key))
 		__fire_sched_in_preempt_notifiers(curr);
 }
 
@@ -2555,7 +2529,7 @@ static __always_inline void
 fire_sched_out_preempt_notifiers(struct task_struct *curr,
 				 struct task_struct *next)
 {
-	if (static_key_false(&preempt_notifier_key))
+	if (static_branch_unlikely(&preempt_notifier_key))
 		__fire_sched_out_preempt_notifiers(curr, next);
 }
 
@@ -2629,6 +2603,18 @@ static inline void finish_lock_switch(struct rq *rq)
 	raw_spin_unlock_irq(&rq->lock);
 }
 
+/*
+ * NOP if the arch has not defined these:
+ */
+
+#ifndef prepare_arch_switch
+# define prepare_arch_switch(next)	do { } while (0)
+#endif
+
+#ifndef finish_arch_post_lock_switch
+# define finish_arch_post_lock_switch()	do { } while (0)
+#endif
+
 /**
  * prepare_task_switch - prepare to switch tasks
  * @rq: the runqueue preparing to switch
@@ -2732,20 +2718,28 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 		membarrier_mm_sync_core_before_usermode(mm);
 		mmdrop(mm);
 	}
-	if (unlikely(prev_state == TASK_DEAD)) {
-		if (prev->sched_class->task_dead)
-			prev->sched_class->task_dead(prev);
+	if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
+		switch (prev_state) {
+		case TASK_DEAD:
+			if (prev->sched_class->task_dead)
+				prev->sched_class->task_dead(prev);
 
-		/*
-		 * Remove function-return probe instances associated with this
-		 * task and put them back on the free list.
-		 */
-		kprobe_flush_task(prev);
+			/*
+			 * Remove function-return probe instances associated with this
+			 * task and put them back on the free list.
+			 */
+			kprobe_flush_task(prev);
+
+			/* Task is done with its stack. */
+			put_task_stack(prev);
 
-		/* Task is done with its stack. */
-		put_task_stack(prev);
+			put_task_struct(prev);
+			break;
 
-		put_task_struct(prev);
+		case TASK_PARKED:
+			kthread_park_complete(prev);
+			break;
+		}
 	}
 
 	tick_nohz_task_switch();
@@ -3037,7 +3031,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
 	/*
-	 * 64-bit doesn't need locks to atomically read a 64bit value.
+	 * 64-bit doesn't need locks to atomically read a 64-bit value.
 	 * So we have a optimization chance when the task's delta_exec is 0.
 	 * Reading ->on_cpu is racy, but this is ok.
 	 *
@@ -3096,35 +3090,99 @@ void scheduler_tick(void)
 	rq->idle_balance = idle_cpu(cpu);
 	trigger_load_balance(rq);
 #endif
-	rq_last_tick_reset(rq);
 }
 
 #ifdef CONFIG_NO_HZ_FULL
-/**
- * scheduler_tick_max_deferment
- *
- * Keep at least one tick per second when a single
- * active task is running because the scheduler doesn't
- * yet completely support full dynticks environment.
- *
- * This makes sure that uptime, CFS vruntime, load
- * balancing, etc... continue to move forward, even
- * with a very low granularity.
- *
- * Return: Maximum deferment in nanoseconds.
- */
-u64 scheduler_tick_max_deferment(void)
+
+struct tick_work {
+	int			cpu;
+	struct delayed_work	work;
+};
+
+static struct tick_work __percpu *tick_work_cpu;
+
+static void sched_tick_remote(struct work_struct *work)
 {
-	struct rq *rq = this_rq();
-	unsigned long next, now = READ_ONCE(jiffies);
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct tick_work *twork = container_of(dwork, struct tick_work, work);
+	int cpu = twork->cpu;
+	struct rq *rq = cpu_rq(cpu);
+	struct rq_flags rf;
 
-	next = rq->last_sched_tick + HZ;
+	/*
+	 * Handle the tick only if it appears the remote CPU is running in full
+	 * dynticks mode. The check is racy by nature, but missing a tick or
+	 * having one too much is no big deal because the scheduler tick updates
+	 * statistics and checks timeslices in a time-independent way, regardless
+	 * of when exactly it is running.
+	 */
+	if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) {
+		struct task_struct *curr;
+		u64 delta;
 
-	if (time_before_eq(next, now))
-		return 0;
+		rq_lock_irq(rq, &rf);
+		update_rq_clock(rq);
+		curr = rq->curr;
+		delta = rq_clock_task(rq) - curr->se.exec_start;
 
-	return jiffies_to_nsecs(next - now);
+		/*
+		 * Make sure the next tick runs within a reasonable
+		 * amount of time.
+		 */
+		WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+		curr->sched_class->task_tick(rq, curr, 0);
+		rq_unlock_irq(rq, &rf);
+	}
+
+	/*
+	 * Run the remote tick once per second (1Hz). This arbitrary
+	 * frequency is large enough to avoid overload but short enough
+	 * to keep scheduler internal stats reasonably up to date.
+	 */
+	queue_delayed_work(system_unbound_wq, dwork, HZ);
 }
+
+static void sched_tick_start(int cpu)
+{
+	struct tick_work *twork;
+
+	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+		return;
+
+	WARN_ON_ONCE(!tick_work_cpu);
+
+	twork = per_cpu_ptr(tick_work_cpu, cpu);
+	twork->cpu = cpu;
+	INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
+	queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void sched_tick_stop(int cpu)
+{
+	struct tick_work *twork;
+
+	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+		return;
+
+	WARN_ON_ONCE(!tick_work_cpu);
+
+	twork = per_cpu_ptr(tick_work_cpu, cpu);
+	cancel_delayed_work_sync(&twork->work);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+int __init sched_tick_offload_init(void)
+{
+	tick_work_cpu = alloc_percpu(struct tick_work);
+	BUG_ON(!tick_work_cpu);
+
+	return 0;
+}
+
+#else /* !CONFIG_NO_HZ_FULL */
+static inline void sched_tick_start(int cpu) { }
+static inline void sched_tick_stop(int cpu) { }
 #endif
 
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
@@ -3448,23 +3506,8 @@ static void __sched notrace __schedule(bool preempt)
 
 void __noreturn do_task_dead(void)
 {
-	/*
-	 * The setting of TASK_RUNNING by try_to_wake_up() may be delayed
-	 * when the following two conditions become true.
-	 *   - There is race condition of mmap_sem (It is acquired by
-	 *     exit_mm()), and
-	 *   - SMI occurs before setting TASK_RUNINNG.
-	 *     (or hypervisor of virtual machine switches to other guest)
-	 *  As a result, we may become TASK_RUNNING after becoming TASK_DEAD
-	 *
-	 * To avoid it, we have to wait for releasing tsk->pi_lock which
-	 * is held by try_to_wake_up()
-	 */
-	raw_spin_lock_irq(&current->pi_lock);
-	raw_spin_unlock_irq(&current->pi_lock);
-
 	/* Causes final put_task_struct in finish_task_switch(): */
-	__set_current_state(TASK_DEAD);
+	set_special_state(TASK_DEAD);
 
 	/* Tell freezer to ignore us: */
 	current->flags |= PF_NOFREEZE;
@@ -3987,6 +4030,23 @@ int idle_cpu(int cpu)
 }
 
 /**
+ * available_idle_cpu - is a given CPU idle for enqueuing work.
+ * @cpu: the CPU in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
+ */
+int available_idle_cpu(int cpu)
+{
+	if (!idle_cpu(cpu))
+		return 0;
+
+	if (vcpu_is_preempted(cpu))
+		return 0;
+
+	return 1;
+}
+
+/**
  * idle_task - return the idle task for a given CPU.
  * @cpu: the processor in question.
  *
@@ -4892,7 +4952,7 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
  *
  * Return: 0.
  */
-SYSCALL_DEFINE0(sched_yield)
+static void do_sched_yield(void)
 {
 	struct rq_flags rf;
 	struct rq *rq;
@@ -4913,7 +4973,11 @@ SYSCALL_DEFINE0(sched_yield)
 	sched_preempt_enable_no_resched();
 
 	schedule();
+}
 
+SYSCALL_DEFINE0(sched_yield)
+{
+	do_sched_yield();
 	return 0;
 }
 
@@ -4958,20 +5022,6 @@ int __cond_resched_lock(spinlock_t *lock)
 }
 EXPORT_SYMBOL(__cond_resched_lock);
 
-int __sched __cond_resched_softirq(void)
-{
-	BUG_ON(!in_softirq());
-
-	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
-		local_bh_enable();
-		preempt_schedule_common();
-		local_bh_disable();
-		return 1;
-	}
-	return 0;
-}
-EXPORT_SYMBOL(__cond_resched_softirq);
-
 /**
  * yield - yield the current processor to other threads.
  *
@@ -4997,7 +5047,7 @@ EXPORT_SYMBOL(__cond_resched_softirq);
 void __sched yield(void)
 {
 	set_current_state(TASK_RUNNING);
-	sys_sched_yield();
+	do_sched_yield();
 }
 EXPORT_SYMBOL(yield);
 
@@ -5506,6 +5556,7 @@ void idle_task_exit(void)
 
 	if (mm != &init_mm) {
 		switch_mm(mm, &init_mm, current);
+		current->active_mm = &init_mm;
 		finish_arch_post_lock_switch();
 	}
 	mmdrop(mm);
@@ -5786,6 +5837,7 @@ int sched_cpu_starting(unsigned int cpu)
 {
 	set_cpu_rq_start_time(cpu);
 	sched_rq_cpu_starting(cpu);
+	sched_tick_start(cpu);
 	return 0;
 }
 
@@ -5797,6 +5849,7 @@ int sched_cpu_dying(unsigned int cpu)
 
 	/* Handle pending wakeups and then migrate everything off */
 	sched_ttwu_pending();
+	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
@@ -5809,7 +5862,7 @@ int sched_cpu_dying(unsigned int cpu)
 
 	calc_load_migrate(rq);
 	update_max_interval();
-	nohz_balance_exit_idle(cpu);
+	nohz_balance_exit_idle(rq);
 	hrtick_clear(rq);
 	return 0;
 }
@@ -6022,13 +6075,11 @@ void __init sched_init(void)
 		rq_attach_root(rq, &def_root_domain);
 #ifdef CONFIG_NO_HZ_COMMON
 		rq->last_load_update_tick = jiffies;
-		rq->nohz_flags = 0;
-#endif
-#ifdef CONFIG_NO_HZ_FULL
-		rq->last_sched_tick = 0;
+		rq->last_blocked_load_update_tick = jiffies;
+		atomic_set(&rq->nohz_flags, 0);
 #endif
 #endif /* CONFIG_SMP */
-		init_rq_hrtick(rq);
+		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
 	}
 
@@ -6683,13 +6734,18 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 		parent_quota = parent_b->hierarchical_quota;
 
 		/*
-		 * Ensure max(child_quota) <= parent_quota, inherit when no
+		 * Ensure max(child_quota) <= parent_quota.  On cgroup2,
+		 * always take the min.  On cgroup1, only inherit when no
 		 * limit is set:
 		 */
-		if (quota == RUNTIME_INF)
-			quota = parent_quota;
-		else if (parent_quota != RUNTIME_INF && quota > parent_quota)
-			return -EINVAL;
+		if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) {
+			quota = min(quota, parent_quota);
+		} else {
+			if (quota == RUNTIME_INF)
+				quota = parent_quota;
+			else if (parent_quota != RUNTIME_INF && quota > parent_quota)
+				return -EINVAL;
+		}
 	}
 	cfs_b->hierarchical_quota = quota;
 
@@ -6868,11 +6924,15 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
 				     struct cftype *cft, s64 nice)
 {
 	unsigned long weight;
+	int idx;
 
 	if (nice < MIN_NICE || nice > MAX_NICE)
 		return -ERANGE;
 
-	weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO];
+	idx = NICE_TO_PRIO(nice) - MAX_RT_PRIO;
+	idx = array_index_nospec(idx, 40);
+	weight = sched_prio_to_weight[idx];
+
 	return sched_group_set_shares(css_tg(css), scale_load(weight));
 }
 #endif
@@ -7022,3 +7082,5 @@ const u32 sched_prio_to_wmult[40] = {
  /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
  /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
 };
+
+#undef CREATE_TRACE_POINTS