1 files changed, 104 insertions, 141 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78d8facba456..625bc9897f62 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,7 +7,6 @@
  */
 #include "sched.h"
 
-#include <linux/kthread.h>
 #include <linux/nospec.h>
 
 #include <linux/kcov.h>
@@ -18,6 +17,8 @@
 #include "../workqueue_internal.h"
 #include "../smpboot.h"
 
+#include "pelt.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
@@ -46,14 +47,6 @@ 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
  */
@@ -184,9 +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
 }
 
@@ -413,8 +406,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() implies a full barrier, which pairs with the write
-	 * barrier implied by the wakeup in wake_up_q().
+	 * This cmpxchg() executes a full barrier, which pairs with the full
+	 * barrier executed by the wakeup in wake_up_q().
 	 */
 	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
 		return;
@@ -442,8 +435,8 @@ void wake_up_q(struct wake_q_head *head)
 		task->wake_q.next = NULL;
 
 		/*
-		 * wake_up_process() implies a wmb() to pair with the queueing
-		 * in wake_q_add() so as not to miss wakeups.
+		 * wake_up_process() executes a full barrier, which pairs with
+		 * the queueing in wake_q_add() so as not to miss wakeups.
 		 */
 		wake_up_process(task);
 		put_task_struct(task);
@@ -650,23 +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) && \
@@ -1200,6 +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)) {
@@ -1281,16 +1258,17 @@ unlock:
 /*
  * 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)
@@ -1315,6 +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.
@@ -1880,8 +1859,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *     rq(c1)->lock (if not at the same time, then in that order).
  *  C) LOCK of the rq(c1)->lock scheduling in task
  *
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
  * Note: the CPU doing B need not be c0 or c1
  *
  * Example:
@@ -1943,16 +1921,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *   UNLOCK rq(0)->lock
  *
  *
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
  */
 
 /**
@@ -1968,6 +1939,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * Atomic against schedule() which would dequeue a task, also see
  * set_current_state().
  *
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
  */
@@ -1999,21 +1973,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
 	 * in smp_cond_load_acquire() below.
 	 *
-	 * sched_ttwu_pending()                 try_to_wake_up()
-	 *   [S] p->on_rq = 1;                  [L] P->state
-	 *       UNLOCK rq->lock  -----.
-	 *                              \
-	 *				 +---   RMB
-	 * schedule()                   /
-	 *       LOCK rq->lock    -----'
-	 *       UNLOCK rq->lock
+	 * sched_ttwu_pending()			try_to_wake_up()
+	 *   STORE p->on_rq = 1			  LOAD p->state
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   UNLOCK rq->lock
 	 *
 	 * [task p]
-	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *   STORE p->state = UNINTERRUPTIBLE	  LOAD p->on_rq
 	 *
-	 * Pairs with the UNLOCK+LOCK on rq->lock from the
-	 * last wakeup of our task and the schedule that got our task
-	 * current.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2027,15 +2000,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * One must be running (->on_cpu == 1) in order to remove oneself
 	 * from the runqueue.
 	 *
-	 *  [S] ->on_cpu = 1;	[L] ->on_rq
-	 *      UNLOCK rq->lock
-	 *			RMB
-	 *      LOCK   rq->lock
-	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 * __schedule() (switch to task 'p')	try_to_wake_up()
+	 *   STORE p->on_cpu = 1		  LOAD p->on_rq
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (put 'p' to sleep)
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   STORE p->on_rq = 0			  LOAD p->on_cpu
 	 *
-	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
-	 * from the consecutive calls to schedule(); the first switching to our
-	 * task, the second putting it to sleep.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 
@@ -2141,8 +2116,7 @@ out:
  *
  * Return: 1 if the process was woken up, 0 if it was already running.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
  */
 int wake_up_process(struct task_struct *p)
 {
@@ -2318,7 +2292,6 @@ 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);
 	/*
@@ -2354,14 +2327,12 @@ 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);
 
@@ -2377,7 +2348,7 @@ 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);
@@ -2394,8 +2365,6 @@ 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;
 }
 
@@ -2724,28 +2693,20 @@ 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|TASK_PARKED))) {
-		switch (prev_state) {
-		case TASK_DEAD:
-			if (prev->sched_class->task_dead)
-				prev->sched_class->task_dead(prev);
+	if (unlikely(prev_state == 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);
-
-			/* Task is done with its stack. */
-			put_task_stack(prev);
+		/*
+		 * Remove function-return probe instances associated with this
+		 * task and put them back on the free list.
+		 */
+		kprobe_flush_task(prev);
 
-			put_task_struct(prev);
-			break;
+		/* Task is done with its stack. */
+		put_task_stack(prev);
 
-		case TASK_PARKED:
-			kthread_park_complete(prev);
-			break;
-		}
+		put_task_struct(prev);
 	}
 
 	tick_nohz_task_switch();
@@ -2813,6 +2774,8 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 
 	if (current->set_child_tid)
 		put_user(task_pid_vnr(current), current->set_child_tid);
+
+	calculate_sigpending();
 }
 
 /*
@@ -3113,7 +3076,9 @@ static void sched_tick_remote(struct work_struct *work)
 	struct tick_work *twork = container_of(dwork, struct tick_work, work);
 	int cpu = twork->cpu;
 	struct rq *rq = cpu_rq(cpu);
+	struct task_struct *curr;
 	struct rq_flags rf;
+	u64 delta;
 
 	/*
 	 * Handle the tick only if it appears the remote CPU is running in full
@@ -3122,25 +3087,29 @@ static void sched_tick_remote(struct work_struct *work)
 	 * 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 (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+		goto out_requeue;
 
-		rq_lock_irq(rq, &rf);
-		update_rq_clock(rq);
-		curr = rq->curr;
-		delta = rq_clock_task(rq) - curr->se.exec_start;
+	rq_lock_irq(rq, &rf);
+	curr = rq->curr;
+	if (is_idle_task(curr))
+		goto out_unlock;
 
-		/*
-		 * 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);
-	}
+	update_rq_clock(rq);
+	delta = rq_clock_task(rq) - curr->se.exec_start;
 
 	/*
+	 * 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);
+
+out_unlock:
+	rq_unlock_irq(rq, &rf);
+
+out_requeue:
+	/*
 	 * 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.
@@ -3192,7 +3161,7 @@ static inline void sched_tick_stop(int cpu) { }
 #endif
 
 #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
-				defined(CONFIG_PREEMPT_TRACER))
+				defined(CONFIG_TRACE_PREEMPT_TOGGLE))
 /*
  * If the value passed in is equal to the current preempt count
  * then we just disabled preemption. Start timing the latency.
@@ -5717,13 +5686,6 @@ 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:
  */
@@ -5777,6 +5739,18 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * The sched_smt_present static key needs to be evaluated on every
+	 * hotplug event because at boot time SMT might be disabled when
+	 * the number of booted CPUs is limited.
+	 *
+	 * If then later a sibling gets hotplugged, then the key would stay
+	 * off and SMT scheduling would never be functional.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
+		static_branch_enable_cpuslocked(&sched_smt_present);
+#endif
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -5841,7 +5815,6 @@ 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;
@@ -5874,22 +5847,6 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
-	/*
-	 * We've enumerated all CPUs and will assume that if any CPU
-	 * has SMT siblings, CPU0 will too.
-	 */
-	if (cpumask_weight(cpu_smt_mask(0)) > 1)
-		static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
 void __init sched_init_smp(void)
 {
 	sched_init_numa();
@@ -5911,8 +5868,6 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
-	sched_init_smt();
-
 	sched_smp_initialized = true;
 }
 
@@ -5957,7 +5912,6 @@ void __init sched_init(void)
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
-	sched_clock_init();
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -6109,7 +6063,6 @@ 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();
 
@@ -6788,6 +6741,16 @@ 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 */