Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Move the nohz kick code out of the scheduler tick to a dedicated IPI,
   from Frederic Weisbecker.

  This necessiated quite some background infrastructure rework,
  including:

   * Clean up some irq-work internals
   * Implement remote irq-work
   * Implement nohz kick on top of remote irq-work
   * Move full dynticks timer enqueue notification to new kick
   * Move multi-task notification to new kick
   * Remove unecessary barriers on multi-task notification

 - Remove proliferation of wait_on_bit() action functions and allow
   wait_on_bit_action() functions to support a timeout.  (Neil Brown)

 - Another round of sched/numa improvements, cleanups and fixes.  (Rik
   van Riel)

 - Implement fast idling of CPUs when the system is partially loaded,
   for better scalability.  (Tim Chen)

 - Restructure and fix the CPU hotplug handling code that may leave
   cfs_rq and rt_rq's throttled when tasks are migrated away from a dead
   cpu.  (Kirill Tkhai)

 - Robustify the sched topology setup code.  (Peterz Zijlstra)

 - Improve sched_feat() handling wrt.  static_keys (Jason Baron)

 - Misc fixes.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (37 commits)
  sched/fair: Fix 'make xmldocs' warning caused by missing description
  sched: Use macro for magic number of -1 for setparam
  sched: Robustify topology setup
  sched: Fix sched_setparam() policy == -1 logic
  sched: Allow wait_on_bit_action() functions to support a timeout
  sched: Remove proliferation of wait_on_bit() action functions
  sched/numa: Revert "Use effective_load() to balance NUMA loads"
  sched: Fix static_key race with sched_feat()
  sched: Remove extra static_key*() function indirection
  sched/rt: Fix replenish_dl_entity() comments to match the current upstream code
  sched: Transform resched_task() into resched_curr()
  sched/deadline: Kill task_struct->pi_top_task
  sched: Rework check_for_tasks()
  sched/rt: Enqueue just unthrottled rt_rq back on the stack in __disable_runtime()
  sched/fair: Disable runtime_enabled on dying rq
  sched/numa: Change scan period code to match intent
  sched/numa: Rework best node setting in task_numa_migrate()
  sched/numa: Examine a task move when examining a task swap
  sched/numa: Simplify task_numa_compare()
  sched/numa: Use effective_load() to balance NUMA loads
  ...

1 files changed, 45 insertions, 65 deletions

diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index a82170e..e6bcbe7 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -16,11 +16,12 @@
 #include <linux/tick.h>
 #include <linux/cpu.h>
 #include <linux/notifier.h>
+#include <linux/smp.h>
 #include <asm/processor.h>
 
 
-static DEFINE_PER_CPU(struct llist_head, irq_work_list);
-static DEFINE_PER_CPU(int, irq_work_raised);
+static DEFINE_PER_CPU(struct llist_head, raised_list);
+static DEFINE_PER_CPU(struct llist_head, lazy_list);
 
 /*
  * Claim the entry so that no one else will poke at it.
@@ -55,12 +56,34 @@ void __weak arch_irq_work_raise(void)
 	 */
 }
 
+#ifdef CONFIG_SMP
 /*
- * Enqueue the irq_work @entry unless it's already pending
+ * Enqueue the irq_work @work on @cpu unless it's already pending
  * somewhere.
  *
  * Can be re-enqueued while the callback is still in progress.
  */
+bool irq_work_queue_on(struct irq_work *work, int cpu)
+{
+	/* All work should have been flushed before going offline */
+	WARN_ON_ONCE(cpu_is_offline(cpu));
+
+	/* Arch remote IPI send/receive backend aren't NMI safe */
+	WARN_ON_ONCE(in_nmi());
+
+	/* Only queue if not already pending */
+	if (!irq_work_claim(work))
+		return false;
+
+	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+		arch_send_call_function_single_ipi(cpu);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(irq_work_queue_on);
+#endif
+
+/* Enqueue the irq work @work on the current CPU */
 bool irq_work_queue(struct irq_work *work)
 {
 	/* Only queue if not already pending */
@@ -70,15 +93,13 @@ bool irq_work_queue(struct irq_work *work)
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 
-	llist_add(&work->llnode, &__get_cpu_var(irq_work_list));
-
-	/*
-	 * If the work is not "lazy" or the tick is stopped, raise the irq
-	 * work interrupt (if supported by the arch), otherwise, just wait
-	 * for the next tick.
-	 */
-	if (!(work->flags & IRQ_WORK_LAZY) || tick_nohz_tick_stopped()) {
-		if (!this_cpu_cmpxchg(irq_work_raised, 0, 1))
+	/* If the work is "lazy", handle it from next tick if any */
+	if (work->flags & IRQ_WORK_LAZY) {
+		if (llist_add(&work->llnode, &__get_cpu_var(lazy_list)) &&
+		    tick_nohz_tick_stopped())
+			arch_irq_work_raise();
+	} else {
+		if (llist_add(&work->llnode, &__get_cpu_var(raised_list)))
 			arch_irq_work_raise();
 	}
 
@@ -90,10 +111,11 @@ EXPORT_SYMBOL_GPL(irq_work_queue);
 
 bool irq_work_needs_cpu(void)
 {
-	struct llist_head *this_list;
+	struct llist_head *raised, *lazy;
 
-	this_list = &__get_cpu_var(irq_work_list);
-	if (llist_empty(this_list))
+	raised = &__get_cpu_var(raised_list);
+	lazy = &__get_cpu_var(lazy_list);
+	if (llist_empty(raised) && llist_empty(lazy))
 		return false;
 
 	/* All work should have been flushed before going offline */
@@ -102,28 +124,18 @@ bool irq_work_needs_cpu(void)
 	return true;
 }
 
-static void __irq_work_run(void)
+static void irq_work_run_list(struct llist_head *list)
 {
 	unsigned long flags;
 	struct irq_work *work;
-	struct llist_head *this_list;
 	struct llist_node *llnode;
 
+	BUG_ON(!irqs_disabled());
 
-	/*
-	 * Reset the "raised" state right before we check the list because
-	 * an NMI may enqueue after we find the list empty from the runner.
-	 */
-	__this_cpu_write(irq_work_raised, 0);
-	barrier();
-
-	this_list = &__get_cpu_var(irq_work_list);
-	if (llist_empty(this_list))
+	if (llist_empty(list))
 		return;
 
-	BUG_ON(!irqs_disabled());
-
-	llnode = llist_del_all(this_list);
+	llnode = llist_del_all(list);
 	while (llnode != NULL) {
 		work = llist_entry(llnode, struct irq_work, llnode);
 
@@ -149,13 +161,13 @@ static void __irq_work_run(void)
 }
 
 /*
- * Run the irq_work entries on this cpu. Requires to be ran from hardirq
- * context with local IRQs disabled.
+ * hotplug calls this through:
+ *  hotplug_cfd() -> flush_smp_call_function_queue()
  */
 void irq_work_run(void)
 {
-	BUG_ON(!in_irq());
-	__irq_work_run();
+	irq_work_run_list(&__get_cpu_var(raised_list));
+	irq_work_run_list(&__get_cpu_var(lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
@@ -171,35 +183,3 @@ void irq_work_sync(struct irq_work *work)
 		cpu_relax();
 }
 EXPORT_SYMBOL_GPL(irq_work_sync);
-
-#ifdef CONFIG_HOTPLUG_CPU
-static int irq_work_cpu_notify(struct notifier_block *self,
-			       unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_DYING:
-		/* Called from stop_machine */
-		if (WARN_ON_ONCE(cpu != smp_processor_id()))
-			break;
-		__irq_work_run();
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpu_notify;
-
-static __init int irq_work_init_cpu_notifier(void)
-{
-	cpu_notify.notifier_call = irq_work_cpu_notify;
-	cpu_notify.priority = 0;
-	register_cpu_notifier(&cpu_notify);
-	return 0;
-}
-device_initcall(irq_work_init_cpu_notifier);
-
-#endif /* CONFIG_HOTPLUG_CPU */