1 files changed, 37 insertions, 35 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ad97f3ba5ec5..091e089063be 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -135,9 +135,8 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
  * In theory, the compile should just see 0 here, and optimize out the call
  * to sched_rt_avg_update. But I don't trust it...
  */
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	s64 steal = 0, irq_delta = 0;
-#endif
+	s64 __maybe_unused steal = 0, irq_delta = 0;
+
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
 
@@ -177,7 +176,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->clock_task += delta;
 
-#ifdef HAVE_SCHED_AVG_IRQ
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		update_irq_load_avg(rq, irq_delta + steal);
 #endif
@@ -701,6 +700,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	if (idle_policy(p->policy)) {
 		load->weight = scale_load(WEIGHT_IDLEPRIO);
 		load->inv_weight = WMULT_IDLEPRIO;
+		p->se.runnable_weight = load->weight;
 		return;
 	}
 
@@ -713,6 +713,7 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	} else {
 		load->weight = scale_load(sched_prio_to_weight[prio]);
 		load->inv_weight = sched_prio_to_wmult[prio];
+		p->se.runnable_weight = load->weight;
 	}
 }
 
@@ -721,8 +722,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & ENQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	if (!(flags & ENQUEUE_RESTORE))
+	if (!(flags & ENQUEUE_RESTORE)) {
 		sched_info_queued(rq, p);
+		psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+	}
 
 	p->sched_class->enqueue_task(rq, p, flags);
 }
@@ -732,8 +735,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 	if (!(flags & DEQUEUE_NOCLOCK))
 		update_rq_clock(rq);
 
-	if (!(flags & DEQUEUE_SAVE))
+	if (!(flags & DEQUEUE_SAVE)) {
 		sched_info_dequeued(rq, p);
+		psi_dequeue(p, flags & DEQUEUE_SLEEP);
+	}
 
 	p->sched_class->dequeue_task(rq, p, flags);
 }
@@ -2036,6 +2041,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags);
 	if (task_cpu(p) != cpu) {
 		wake_flags |= WF_MIGRATED;
+		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
 
@@ -2875,6 +2881,18 @@ unsigned long long nr_context_switches(void)
 }
 
 /*
+ * Consumers of these two interfaces, like for example the cpuidle menu
+ * governor, are using nonsensical data. Preferring shallow idle state selection
+ * for a CPU that has IO-wait which might not even end up running the task when
+ * it does become runnable.
+ */
+
+unsigned long nr_iowait_cpu(int cpu)
+{
+	return atomic_read(&cpu_rq(cpu)->nr_iowait);
+}
+
+/*
  * IO-wait accounting, and how its mostly bollocks (on SMP).
  *
  * The idea behind IO-wait account is to account the idle time that we could
@@ -2909,31 +2927,11 @@ unsigned long nr_iowait(void)
 	unsigned long i, sum = 0;
 
 	for_each_possible_cpu(i)
-		sum += atomic_read(&cpu_rq(i)->nr_iowait);
+		sum += nr_iowait_cpu(i);
 
 	return sum;
 }
 
-/*
- * Consumers of these two interfaces, like for example the cpufreq menu
- * governor are using nonsensical data. Boosting frequency for a CPU that has
- * IO-wait which might not even end up running the task when it does become
- * runnable.
- */
-
-unsigned long nr_iowait_cpu(int cpu)
-{
-	struct rq *this = cpu_rq(cpu);
-	return atomic_read(&this->nr_iowait);
-}
-
-void get_iowait_load(unsigned long *nr_waiters, unsigned long *load)
-{
-	struct rq *rq = this_rq();
-	*nr_waiters = atomic_read(&rq->nr_iowait);
-	*load = rq->load.weight;
-}
-
 #ifdef CONFIG_SMP
 
 /*
@@ -3050,6 +3048,7 @@ void scheduler_tick(void)
 	curr->sched_class->task_tick(rq, curr, 0);
 	cpu_load_update_active(rq);
 	calc_global_load_tick(rq);
+	psi_task_tick(rq);
 
 	rq_unlock(rq, &rf);
 
@@ -4932,9 +4931,7 @@ static void do_sched_yield(void)
 	struct rq_flags rf;
 	struct rq *rq;
 
-	local_irq_disable();
-	rq = this_rq();
-	rq_lock(rq, &rf);
+	rq = this_rq_lock_irq(&rf);
 
 	schedstat_inc(rq->yld_count);
 	current->sched_class->yield_task(rq);
@@ -5243,7 +5240,7 @@ out_unlock:
  * an error code.
  */
 SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
-		struct timespec __user *, interval)
+		struct __kernel_timespec __user *, interval)
 {
 	struct timespec64 t;
 	int retval = sched_rr_get_interval(pid, &t);
@@ -5254,16 +5251,16 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
 	return retval;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval,
 		       compat_pid_t, pid,
-		       struct compat_timespec __user *, interval)
+		       struct old_timespec32 __user *, interval)
 {
 	struct timespec64 t;
 	int retval = sched_rr_get_interval(pid, &t);
 
 	if (retval == 0)
-		retval = compat_put_timespec64(&t, interval);
+		retval = put_old_timespec32(&t, interval);
 	return retval;
 }
 #endif
@@ -5854,11 +5851,14 @@ void __init sched_init_smp(void)
 	/*
 	 * There's no userspace yet to cause hotplug operations; hence all the
 	 * CPU masks are stable and all blatant races in the below code cannot
-	 * happen.
+	 * happen. The hotplug lock is nevertheless taken to satisfy lockdep,
+	 * but there won't be any contention on it.
 	 */
+	cpus_read_lock();
 	mutex_lock(&sched_domains_mutex);
 	sched_init_domains(cpu_active_mask);
 	mutex_unlock(&sched_domains_mutex);
+	cpus_read_unlock();
 
 	/* Move init over to a non-isolated CPU */
 	if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
@@ -6068,6 +6068,8 @@ void __init sched_init(void)
 
 	init_schedstats();
 
+	psi_init();
+
 	scheduler_running = 1;
 }