Merge tag 'sched_urgent_for_v5.11_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Borislav Petkov:

 - Correct the marking of kthreads which are supposed to run on a
   specific, single CPU vs such which are affine to only one CPU, mark
   per-cpu workqueue threads as such and make sure that marking
   "survives" CPU hotplug. Fix CPU hotplug issues with such kthreads.

 - A fix to not push away tasks on CPUs coming online.

 - Have workqueue CPU hotplug code use cpu_possible_mask when breaking
   affinity on CPU offlining so that pending workers can finish on newly
   arrived onlined CPUs too.

 - Dump tasks which haven't vacated a CPU which is currently being
   unplugged.

 - Register a special scale invariance callback which gets called on
   resume from RAM to read out APERF/MPERF after resume and thus make
   the schedutil scaling governor more precise.

* tag 'sched_urgent_for_v5.11_rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Relax the set_cpus_allowed_ptr() semantics
  sched: Fix CPU hotplug / tighten is_per_cpu_kthread()
  sched: Prepare to use balance_push in ttwu()
  workqueue: Restrict affinity change to rescuer
  workqueue: Tag bound workers with KTHREAD_IS_PER_CPU
  kthread: Extract KTHREAD_IS_PER_CPU
  sched: Don't run cpu-online with balance_push() enabled
  workqueue: Use cpu_possible_mask instead of cpu_active_mask to break affinity
  sched/core: Print out straggler tasks in sched_cpu_dying()
  x86: PM: Register syscore_ops for scale invariance

7 files changed, 151 insertions, 33 deletions

diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8ca66af96a54..117e24fbfd8a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -56,6 +56,7 @@
 #include <linux/numa.h>
 #include <linux/pgtable.h>
 #include <linux/overflow.h>
+#include <linux/syscore_ops.h>
 
 #include <asm/acpi.h>
 #include <asm/desc.h>
@@ -2083,6 +2084,23 @@ static void init_counter_refs(void)
 	this_cpu_write(arch_prev_mperf, mperf);
 }
 
+#ifdef CONFIG_PM_SLEEP
+static struct syscore_ops freq_invariance_syscore_ops = {
+	.resume = init_counter_refs,
+};
+
+static void register_freq_invariance_syscore_ops(void)
+{
+	/* Bail out if registered already. */
+	if (freq_invariance_syscore_ops.node.prev)
+		return;
+
+	register_syscore_ops(&freq_invariance_syscore_ops);
+}
+#else
+static inline void register_freq_invariance_syscore_ops(void) {}
+#endif
+
 static void init_freq_invariance(bool secondary, bool cppc_ready)
 {
 	bool ret = false;
@@ -2109,6 +2127,7 @@ static void init_freq_invariance(bool secondary, bool cppc_ready)
 	if (ret) {
 		init_counter_refs();
 		static_branch_enable(&arch_scale_freq_key);
+		register_freq_invariance_syscore_ops();
 		pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio);
 	} else {
 		pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n");
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 65b81e0c494d..2484ed97e72f 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -33,6 +33,9 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 					  unsigned int cpu,
 					  const char *namefmt);
 
+void kthread_set_per_cpu(struct task_struct *k, int cpu);
+bool kthread_is_per_cpu(struct task_struct *k);
+
 /**
  * kthread_run - create and wake a thread.
  * @threadfn: the function to run until signal_pending(current).
diff --git a/kernel/kthread.c b/kernel/kthread.c
index fb9c3dcbb68d..1578973c5740 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -493,11 +493,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
 		return p;
 	kthread_bind(p, cpu);
 	/* CPU hotplug need to bind once again when unparking the thread. */
-	set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags);
 	to_kthread(p)->cpu = cpu;
 	return p;
 }
 
+void kthread_set_per_cpu(struct task_struct *k, int cpu)
+{
+	struct kthread *kthread = to_kthread(k);
+	if (!kthread)
+		return;
+
+	WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY));
+
+	if (cpu < 0) {
+		clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+		return;
+	}
+
+	kthread->cpu = cpu;
+	set_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+}
+
+bool kthread_is_per_cpu(struct task_struct *k)
+{
+	struct kthread *kthread = to_kthread(k);
+	if (!kthread)
+		return false;
+
+	return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
+}
+
 /**
  * kthread_unpark - unpark a thread created by kthread_create().
  * @k:		thread created by kthread_create().
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 15d2562118d1..ff74fca39ed2 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.
 	 */
@@ -7276,8 +7290,14 @@ 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
@@ -7309,7 +7329,7 @@ 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);
 }
@@ -7320,10 +7340,13 @@ 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);
 }
 
@@ -7441,6 +7464,10 @@ 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
@@ -7483,17 +7510,27 @@ int sched_cpu_deactivate(unsigned int cpu)
 	int ret;
 
 	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);
@@ -7574,6 +7611,25 @@ 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);
@@ -7583,9 +7639,18 @@ 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();
 	nohz_balance_exit_idle(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 12ada79d40f3..bb09988451a0 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;
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 2efe1e206167..f25208e8df83 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -188,6 +188,7 @@ __smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
 		kfree(td);
 		return PTR_ERR(tsk);
 	}
+	kthread_set_per_cpu(tsk, cpu);
 	/*
 	 * Park the thread so that it could start right on the CPU
 	 * when it is available.
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 9880b6c0e272..894bb885b40b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1849,18 +1849,17 @@ static void worker_attach_to_pool(struct worker *worker,
 	mutex_lock(&wq_pool_attach_mutex);
 
 	/*
-	 * set_cpus_allowed_ptr() will fail if the cpumask doesn't have any
-	 * online CPUs.  It'll be re-applied when any of the CPUs come up.
-	 */
-	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
-
-	/*
 	 * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains
 	 * stable across this function.  See the comments above the flag
 	 * definition for details.
 	 */
 	if (pool->flags & POOL_DISASSOCIATED)
 		worker->flags |= WORKER_UNBOUND;
+	else
+		kthread_set_per_cpu(worker->task, pool->cpu);
+
+	if (worker->rescue_wq)
+		set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
 
 	list_add_tail(&worker->node, &pool->workers);
 	worker->pool = pool;
@@ -1883,6 +1882,7 @@ static void worker_detach_from_pool(struct worker *worker)
 
 	mutex_lock(&wq_pool_attach_mutex);
 
+	kthread_set_per_cpu(worker->task, -1);
 	list_del(&worker->node);
 	worker->pool = NULL;
 
@@ -4919,8 +4919,10 @@ static void unbind_workers(int cpu)
 
 		raw_spin_unlock_irq(&pool->lock);
 
-		for_each_pool_worker(worker, pool)
-			WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_active_mask) < 0);
+		for_each_pool_worker(worker, pool) {
+			kthread_set_per_cpu(worker->task, -1);
+			WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0);
+		}
 
 		mutex_unlock(&wq_pool_attach_mutex);
 
@@ -4972,9 +4974,11 @@ static void rebind_workers(struct worker_pool *pool)
 	 * of all workers first and then clear UNBOUND.  As we're called
 	 * from CPU_ONLINE, the following shouldn't fail.
 	 */
-	for_each_pool_worker(worker, pool)
+	for_each_pool_worker(worker, pool) {
+		kthread_set_per_cpu(worker->task, pool->cpu);
 		WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task,
 						  pool->attrs->cpumask) < 0);
+	}
 
 	raw_spin_lock_irq(&pool->lock);