Merge branch 'sched/urgent'

5 files changed, 101 insertions, 32 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0a08d0c235d4..15c980af63db 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1313,9 +1313,6 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 
 void activate_task(struct rq *rq, struct task_struct *p, int flags)
 {
-	if (task_contributes_to_load(p))
-		rq->nr_uninterruptible--;
-
 	enqueue_task(rq, p, flags);
 
 	p->on_rq = TASK_ON_RQ_QUEUED;
@@ -1325,9 +1322,6 @@ 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++;
-
 	dequeue_task(rq, p, flags);
 }
 
@@ -1629,7 +1623,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(p->cpus_ptr, new_mask))
+	if (cpumask_equal(&p->cpus_mask, new_mask))
 		goto out;
 
 	/*
@@ -2228,10 +2222,10 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 	lockdep_assert_held(&rq->lock);
 
-#ifdef CONFIG_SMP
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
+#ifdef CONFIG_SMP
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 #endif
@@ -2285,8 +2279,15 @@ void sched_ttwu_pending(void *arg)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 
-	llist_for_each_entry_safe(p, t, llist, wake_entry)
+	llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
+		if (WARN_ON_ONCE(p->on_cpu))
+			smp_cond_load_acquire(&p->on_cpu, !VAL);
+
+		if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
+			set_task_cpu(p, cpu_of(rq));
+
 		ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
+	}
 
 	rq_unlock_irqrestore(rq, &rf);
 }
@@ -2314,7 +2315,7 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
 	WRITE_ONCE(rq->ttwu_pending, 1);
-	__smp_call_single_queue(cpu, &p->wake_entry);
+	__smp_call_single_queue(cpu, &p->wake_entry.llist);
 }
 
 void wake_up_if_idle(int cpu)
@@ -2361,7 +2362,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 	 * the soon-to-be-idle CPU as the current CPU is likely busy.
 	 * nr_running is checked to avoid unnecessary task stacking.
 	 */
-	if ((wake_flags & WF_ON_RQ) && cpu_rq(cpu)->nr_running <= 1)
+	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
 		return true;
 
 	return false;
@@ -2370,6 +2371,9 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 {
 	if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) {
+		if (WARN_ON_ONCE(cpu == smp_processor_id()))
+			return false;
+
 		sched_clock_cpu(cpu); /* Sync clocks across CPUs */
 		__ttwu_queue_wakelist(p, cpu, wake_flags);
 		return true;
@@ -2520,7 +2524,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 			goto out;
 
 		success = 1;
-		cpu = task_cpu(p);
 		trace_sched_waking(p);
 		p->state = TASK_RUNNING;
 		trace_sched_wakeup(p);
@@ -2542,7 +2545,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 
 	/* We're going to change ->state: */
 	success = 1;
-	cpu = task_cpu(p);
 
 	/*
 	 * Ensure we load p->on_rq _after_ p->state, otherwise it would
@@ -2567,7 +2569,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
 	 */
 	smp_rmb();
-	if (p->on_rq && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq) && ttwu_remote(p, wake_flags))
 		goto unlock;
 
 	if (p->in_iowait) {
@@ -2576,9 +2578,6 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	}
 
 #ifdef CONFIG_SMP
-	p->sched_contributes_to_load = !!task_contributes_to_load(p);
-	p->state = TASK_WAKING;
-
 	/*
 	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
 	 * possible to, falsely, observe p->on_cpu == 0.
@@ -2597,8 +2596,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 *
 	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 	 * __schedule().  See the comment for smp_mb__after_spinlock().
+	 *
+	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
+	 * schedule()'s deactivate_task() has 'happened' and p will no longer
+	 * care about it's own p->state. See the comment in __schedule().
 	 */
-	smp_rmb();
+	smp_acquire__after_ctrl_dep();
+
+	/*
+	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
+	 * == 0), which means we need to do an enqueue, change p->state to
+	 * TASK_WAKING such that we can unlock p->pi_lock before doing the
+	 * enqueue, such as ttwu_queue_wakelist().
+	 */
+	p->state = TASK_WAKING;
 
 	/*
 	 * If the owning (remote) CPU is still in the middle of schedule() with
@@ -2606,8 +2617,21 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * which potentially sends an IPI instead of spinning on p->on_cpu to
 	 * let the waker make forward progress. This is safe because IRQs are
 	 * disabled and the IPI will deliver after on_cpu is cleared.
+	 *
+	 * Ensure we load task_cpu(p) after p->on_cpu:
+	 *
+	 * set_task_cpu(p, cpu);
+	 *   STORE p->cpu = @cpu
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock
+	 *   smp_mb__after_spin_lock()		smp_cond_load_acquire(&p->on_cpu)
+	 *   STORE p->on_cpu = 1		LOAD p->cpu
+	 *
+	 * to ensure we observe the correct CPU on which the task is currently
+	 * scheduling.
 	 */
-	if (READ_ONCE(p->on_cpu) && ttwu_queue_wakelist(p, cpu, wake_flags | WF_ON_RQ))
+	if (smp_load_acquire(&p->on_cpu) &&
+	    ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU))
 		goto unlock;
 
 	/*
@@ -2627,6 +2651,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		psi_ttwu_dequeue(p);
 		set_task_cpu(p, cpu);
 	}
+#else
+	cpu = task_cpu(p);
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
@@ -2634,7 +2660,7 @@ unlock:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 out:
 	if (success)
-		ttwu_stat(p, cpu, wake_flags);
+		ttwu_stat(p, task_cpu(p), wake_flags);
 	preempt_enable();
 
 	return success;
@@ -2755,7 +2781,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 #endif
 	init_numa_balancing(clone_flags, p);
 #ifdef CONFIG_SMP
-	p->wake_entry_type = CSD_TYPE_TTWU;
+	p->wake_entry.u_flags = CSD_TYPE_TTWU;
 #endif
 }
 
@@ -2931,6 +2957,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	rseq_migrate(p);
 	/*
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
@@ -2995,6 +3022,7 @@ void wake_up_new_task(struct task_struct *p)
 	 * as we're not fully set-up yet.
 	 */
 	p->recent_used_cpu = task_cpu(p);
+	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
@@ -4065,6 +4093,7 @@ static void __sched notrace __schedule(bool preempt)
 {
 	struct task_struct *prev, *next;
 	unsigned long *switch_count;
+	unsigned long prev_state;
 	struct rq_flags rf;
 	struct rq *rq;
 	int cpu;
@@ -4081,12 +4110,22 @@ static void __sched notrace __schedule(bool preempt)
 	local_irq_disable();
 	rcu_note_context_switch(preempt);
 
+	/* See deactivate_task() below. */
+	prev_state = prev->state;
+
 	/*
 	 * Make sure that signal_pending_state()->signal_pending() below
 	 * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-	 * done by the caller to avoid the race with signal_wake_up().
+	 * done by the caller to avoid the race with signal_wake_up():
+	 *
+	 * __set_current_state(@state)		signal_wake_up()
+	 * schedule()				  set_tsk_thread_flag(p, TIF_SIGPENDING)
+	 *					  wake_up_state(p, state)
+	 *   LOCK rq->lock			    LOCK p->pi_state
+	 *   smp_mb__after_spinlock()		    smp_mb__after_spinlock()
+	 *     if (signal_pending_state())	    if (p->state & @state)
 	 *
-	 * The membarrier system call requires a full memory barrier
+	 * Also, the membarrier system call requires a full memory barrier
 	 * after coming from user-space, before storing to rq->curr.
 	 */
 	rq_lock(rq, &rf);
@@ -4097,10 +4136,31 @@ static void __sched notrace __schedule(bool preempt)
 	update_rq_clock(rq);
 
 	switch_count = &prev->nivcsw;
-	if (!preempt && prev->state) {
-		if (signal_pending_state(prev->state, prev)) {
+	/*
+	 * We must re-load prev->state in case ttwu_remote() changed it
+	 * before we acquired rq->lock.
+	 */
+	if (!preempt && prev_state && prev_state == prev->state) {
+		if (signal_pending_state(prev_state, prev)) {
 			prev->state = TASK_RUNNING;
 		} else {
+			prev->sched_contributes_to_load =
+				(prev_state & TASK_UNINTERRUPTIBLE) &&
+				!(prev_state & TASK_NOLOAD) &&
+				!(prev->flags & PF_FROZEN);
+
+			if (prev->sched_contributes_to_load)
+				rq->nr_uninterruptible++;
+
+			/*
+			 * __schedule()			ttwu()
+			 *   prev_state = prev->state;	  if (READ_ONCE(p->on_rq) && ...)
+			 *   LOCK rq->lock		    goto out;
+			 *   smp_mb__after_spinlock();	  smp_acquire__after_ctrl_dep();
+			 *   p->on_rq = 0;		  p->state = TASK_WAKING;
+			 *
+			 * After this, schedule() must not care about p->state any more.
+			 */
 			deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);
 
 			if (prev->in_iowait) {
@@ -4524,7 +4584,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	 */
 	if (dl_prio(prio)) {
 		if (!dl_prio(p->normal_prio) ||
-		    (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+		    (pi_task && dl_prio(pi_task->prio) &&
+		     dl_entity_preempt(&pi_task->dl, &p->dl))) {
 			p->dl.dl_boosted = 1;
 			queue_flag |= ENQUEUE_REPLENISH;
 		} else
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index c9cc1d6fa363..3862a28cd05d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2763,6 +2763,7 @@ void __dl_clear_params(struct task_struct *p)
 	dl_se->dl_bw			= 0;
 	dl_se->dl_density		= 0;
 
+	dl_se->dl_boosted		= 0;
 	dl_se->dl_throttled		= 0;
 	dl_se->dl_yielded		= 0;
 	dl_se->dl_non_contending	= 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b9b9f19e80c1..6fab1d17c575 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -806,7 +806,7 @@ void post_init_entity_util_avg(struct task_struct *p)
 		}
 	}
 
-	sa->runnable_avg = cpu_scale;
+	sa->runnable_avg = sa->util_avg;
 
 	if (p->sched_class != &fair_sched_class) {
 		/*
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 336d478bddc8..6bf34986f45c 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -96,6 +96,15 @@ void __cpuidle default_idle_call(void)
 	}
 }
 
+static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
+			       struct cpuidle_device *dev)
+{
+	if (current_clr_polling_and_test())
+		return -EBUSY;
+
+	return cpuidle_enter_s2idle(drv, dev);
+}
+
 static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		      int next_state)
 {
@@ -171,11 +180,9 @@ static void cpuidle_idle_call(void)
 		if (idle_should_enter_s2idle()) {
 			rcu_idle_enter();
 
-			entered_state = cpuidle_enter_s2idle(drv, dev);
-			if (entered_state > 0) {
-				local_irq_enable();
+			entered_state = call_cpuidle_s2idle(drv, dev);
+			if (entered_state > 0)
 				goto exit_idle;
-			}
 
 			rcu_idle_exit();
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 549e7e6e0a66..5aa6661ecaf1 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1697,7 +1697,7 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #define WF_SYNC			0x01		/* Waker goes to sleep after wakeup */
 #define WF_FORK			0x02		/* Child wakeup after fork */
 #define WF_MIGRATED		0x04		/* Internal use, task got migrated */
-#define WF_ON_RQ		0x08		/* Wakee is on_rq */
+#define WF_ON_CPU		0x08		/* Wakee is on_cpu */
 
 /*
  * To aid in avoiding the subversion of "niceness" due to uneven distribution