Merge tag 'v5.11' into sched/core, to pick up fixes & refresh the branch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 89 insertions, 23 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 06b449942adf..6c789dcb8e5a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1796,13 +1796,28 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 {
+	/* When not in the task's cpumask, no point in looking further. */
 	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 		return false;
 
-	if (is_per_cpu_kthread(p) || is_migration_disabled(p))
+	/* migrate_disabled() must be allowed to finish. */
+	if (is_migration_disabled(p))
 		return cpu_online(cpu);
 
-	return cpu_active(cpu);
+	/* Non kernel threads are not allowed during either online or offline. */
+	if (!(p->flags & PF_KTHREAD))
+		return cpu_active(cpu);
+
+	/* KTHREAD_IS_PER_CPU is always allowed. */
+	if (kthread_is_per_cpu(p))
+		return cpu_online(cpu);
+
+	/* Regular kernel threads don't get to stay during offline. */
+	if (cpu_rq(cpu)->balance_push)
+		return false;
+
+	/* But are allowed during online. */
+	return cpu_online(cpu);
 }
 
 /*
@@ -2327,7 +2342,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 
 	if (p->flags & PF_KTHREAD || is_migration_disabled(p)) {
 		/*
-		 * Kernel threads are allowed on online && !active CPUs.
+		 * Kernel threads are allowed on online && !active CPUs,
+		 * however, during cpu-hot-unplug, even these might get pushed
+		 * away if not KTHREAD_IS_PER_CPU.
 		 *
 		 * Specifically, migration_disabled() tasks must not fail the
 		 * cpumask_any_and_distribute() pick below, esp. so on
@@ -2371,16 +2388,6 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 
 	__do_set_cpus_allowed(p, new_mask, flags);
 
-	if (p->flags & PF_KTHREAD) {
-		/*
-		 * For kernel threads that do indeed end up on online &&
-		 * !active we want to ensure they are strict per-CPU threads.
-		 */
-		WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) &&
-			!cpumask_intersects(new_mask, cpu_active_mask) &&
-			p->nr_cpus_allowed != 1);
-	}
-
 	return affine_move_task(rq, p, &rf, dest_cpu, flags);
 
 out:
@@ -3122,6 +3129,13 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 static inline bool ttwu_queue_cond(int cpu, int wake_flags)
 {
 	/*
+	 * Do not complicate things with the async wake_list while the CPU is
+	 * in hotplug state.
+	 */
+	if (!cpu_active(cpu))
+		return false;
+
+	/*
 	 * If the CPU does not share cache, then queue the task on the
 	 * remote rqs wakelist to avoid accessing remote data.
 	 */
@@ -7390,8 +7404,14 @@ static void balance_push(struct rq *rq)
 	/*
 	 * Both the cpu-hotplug and stop task are in this case and are
 	 * required to complete the hotplug process.
+	 *
+	 * XXX: the idle task does not match kthread_is_per_cpu() due to
+	 * histerical raisins.
 	 */
-	if (is_per_cpu_kthread(push_task) || is_migration_disabled(push_task)) {
+	if (rq->idle == push_task ||
+	    ((push_task->flags & PF_KTHREAD) && kthread_is_per_cpu(push_task)) ||
+	    is_migration_disabled(push_task)) {
+
 		/*
 		 * If this is the idle task on the outgoing CPU try to wake
 		 * up the hotplug control thread which might wait for the
@@ -7423,7 +7443,7 @@ static void balance_push(struct rq *rq)
 	/*
 	 * At this point need_resched() is true and we'll take the loop in
 	 * schedule(). The next pick is obviously going to be the stop task
-	 * which is_per_cpu_kthread() and will push this task away.
+	 * which kthread_is_per_cpu() and will push this task away.
 	 */
 	raw_spin_lock(&rq->lock);
 }
@@ -7434,10 +7454,13 @@ static void balance_push_set(int cpu, bool on)
 	struct rq_flags rf;
 
 	rq_lock_irqsave(rq, &rf);
-	if (on)
+	rq->balance_push = on;
+	if (on) {
+		WARN_ON_ONCE(rq->balance_callback);
 		rq->balance_callback = &balance_push_callback;
-	else
+	} else if (rq->balance_callback == &balance_push_callback) {
 		rq->balance_callback = NULL;
+	}
 	rq_unlock_irqrestore(rq, &rf);
 }
 
@@ -7555,6 +7578,10 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+	/*
+	 * Make sure that when the hotplug state machine does a roll-back
+	 * we clear balance_push. Ideally that would happen earlier...
+	 */
 	balance_push_set(cpu, false);
 
 #ifdef CONFIG_SCHED_SMT
@@ -7603,17 +7630,27 @@ int sched_cpu_deactivate(unsigned int cpu)
 	nohz_balance_exit_idle(rq);
 
 	set_cpu_active(cpu, false);
+
+	/*
+	 * From this point forward, this CPU will refuse to run any task that
+	 * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively
+	 * push those tasks away until this gets cleared, see
+	 * sched_cpu_dying().
+	 */
+	balance_push_set(cpu, true);
+
 	/*
-	 * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
-	 * users of this state to go away such that all new such users will
-	 * observe it.
+	 * We've cleared cpu_active_mask / set balance_push, wait for all
+	 * preempt-disabled and RCU users of this state to go away such that
+	 * all new such users will observe it.
+	 *
+	 * Specifically, we rely on ttwu to no longer target this CPU, see
+	 * ttwu_queue_cond() and is_cpu_allowed().
 	 *
 	 * Do sync before park smpboot threads to take care the rcu boost case.
 	 */
 	synchronize_rcu();
 
-	balance_push_set(cpu, true);
-
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
 		update_rq_clock(rq);
@@ -7694,6 +7731,25 @@ static void calc_load_migrate(struct rq *rq)
 		atomic_long_add(delta, &calc_load_tasks);
 }
 
+static void dump_rq_tasks(struct rq *rq, const char *loglvl)
+{
+	struct task_struct *g, *p;
+	int cpu = cpu_of(rq);
+
+	lockdep_assert_held(&rq->lock);
+
+	printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
+	for_each_process_thread(g, p) {
+		if (task_cpu(p) != cpu)
+			continue;
+
+		if (!task_on_rq_queued(p))
+			continue;
+
+		printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm);
+	}
+}
+
 int sched_cpu_dying(unsigned int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -7703,9 +7759,18 @@ int sched_cpu_dying(unsigned int cpu)
 	sched_tick_stop(cpu);
 
 	rq_lock_irqsave(rq, &rf);
-	BUG_ON(rq->nr_running != 1 || rq_has_pinned_tasks(rq));
+	if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
+		WARN(true, "Dying CPU not properly vacated!");
+		dump_rq_tasks(rq, KERN_WARNING);
+	}
 	rq_unlock_irqrestore(rq, &rf);
 
+	/*
+	 * Now that the CPU is offline, make sure we're welcome
+	 * to new tasks once we come back up.
+	 */
+	balance_push_set(cpu, false);
+
 	calc_load_migrate(rq);
 	update_max_interval();
 	hrtick_clear(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 045b01064c1e..f519aba2c542 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -975,6 +975,7 @@ struct rq {
 	unsigned long		cpu_capacity_orig;
 
 	struct callback_head	*balance_callback;
+	unsigned char		balance_push;
 
 	unsigned char		nohz_idle_balance;
 	unsigned char		idle_balance;