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

Pull RCU updates from Ingo Molnar:
 "This cycle's RCU changes were:

   - A few more RCU flavor consolidation cleanups.

   - Updates to RCU's list-traversal macros improving lockdep usability.

   - Forward-progress improvements for no-CBs CPUs: Avoid ignoring
     incoming callbacks during grace-period waits.

   - Forward-progress improvements for no-CBs CPUs: Use ->cblist
     structure to take advantage of others' grace periods.

   - Also added a small commit that avoids needlessly inflicting
     scheduler-clock ticks on callback-offloaded CPUs.

   - Forward-progress improvements for no-CBs CPUs: Reduce contention on
     ->nocb_lock guarding ->cblist.

   - Forward-progress improvements for no-CBs CPUs: Add ->nocb_bypass
     list to further reduce contention on ->nocb_lock guarding ->cblist.

   - Miscellaneous fixes.

   - Torture-test updates.

   - minor LKMM updates"

* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (86 commits)
  MAINTAINERS: Update from paulmck@linux.ibm.com to paulmck@kernel.org
  rcu: Don't include <linux/ktime.h> in rcutiny.h
  rcu: Allow rcu_do_batch() to dynamically adjust batch sizes
  rcu/nocb: Don't wake no-CBs GP kthread if timer posted under overload
  rcu/nocb: Reduce __call_rcu_nocb_wake() leaf rcu_node ->lock contention
  rcu/nocb: Reduce nocb_cb_wait() leaf rcu_node ->lock contention
  rcu/nocb: Advance CBs after merge in rcutree_migrate_callbacks()
  rcu/nocb: Avoid synchronous wakeup in __call_rcu_nocb_wake()
  rcu/nocb: Print no-CBs diagnostics when rcutorture writer unduly delayed
  rcu/nocb: EXP Check use and usefulness of ->nocb_lock_contended
  rcu/nocb: Add bypass callback queueing
  rcu/nocb: Atomic ->len field in rcu_segcblist structure
  rcu/nocb: Unconditionally advance and wake for excessive CBs
  rcu/nocb: Reduce ->nocb_lock contention with separate ->nocb_gp_lock
  rcu/nocb: Reduce contention at no-CBs invocation-done time
  rcu/nocb: Reduce contention at no-CBs registry-time CB advancement
  rcu/nocb: Round down for number of no-CBs grace-period kthreads
  rcu/nocb: Avoid ->nocb_lock capture by corresponding CPU
  rcu/nocb: Avoid needless wakeups of no-CBs grace-period kthread
  rcu/nocb: Make __call_rcu_nocb_wake() safe for many callbacks
  ...

2 files changed, 52 insertions, 10 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index df9f1fe5689b..7fa8e74ad2ab 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3486,8 +3486,36 @@ void scheduler_tick(void)
 
 struct tick_work {
 	int			cpu;
+	atomic_t		state;
 	struct delayed_work	work;
 };
+/* Values for ->state, see diagram below. */
+#define TICK_SCHED_REMOTE_OFFLINE	0
+#define TICK_SCHED_REMOTE_OFFLINING	1
+#define TICK_SCHED_REMOTE_RUNNING	2
+
+/*
+ * State diagram for ->state:
+ *
+ *
+ *          TICK_SCHED_REMOTE_OFFLINE
+ *                    |   ^
+ *                    |   |
+ *                    |   | sched_tick_remote()
+ *                    |   |
+ *                    |   |
+ *                    +--TICK_SCHED_REMOTE_OFFLINING
+ *                    |   ^
+ *                    |   |
+ * sched_tick_start() |   | sched_tick_stop()
+ *                    |   |
+ *                    V   |
+ *          TICK_SCHED_REMOTE_RUNNING
+ *
+ *
+ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
+ * and sched_tick_start() are happy to leave the state in RUNNING.
+ */
 
 static struct tick_work __percpu *tick_work_cpu;
 
@@ -3500,6 +3528,7 @@ static void sched_tick_remote(struct work_struct *work)
 	struct task_struct *curr;
 	struct rq_flags rf;
 	u64 delta;
+	int os;
 
 	/*
 	 * Handle the tick only if it appears the remote CPU is running in full
@@ -3513,7 +3542,7 @@ static void sched_tick_remote(struct work_struct *work)
 
 	rq_lock_irq(rq, &rf);
 	curr = rq->curr;
-	if (is_idle_task(curr))
+	if (is_idle_task(curr) || cpu_is_offline(cpu))
 		goto out_unlock;
 
 	update_rq_clock(rq);
@@ -3533,13 +3562,18 @@ 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.
+	 * to keep scheduler internal stats reasonably up to date.  But
+	 * first update state to reflect hotplug activity if required.
 	 */
-	queue_delayed_work(system_unbound_wq, dwork, HZ);
+	os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
+	WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
+	if (os == TICK_SCHED_REMOTE_RUNNING)
+		queue_delayed_work(system_unbound_wq, dwork, HZ);
 }
 
 static void sched_tick_start(int cpu)
 {
+	int os;
 	struct tick_work *twork;
 
 	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
@@ -3548,15 +3582,20 @@ static void sched_tick_start(int cpu)
 	WARN_ON_ONCE(!tick_work_cpu);
 
 	twork = per_cpu_ptr(tick_work_cpu, cpu);
-	twork->cpu = cpu;
-	INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
-	queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+	os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
+	WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
+	if (os == TICK_SCHED_REMOTE_OFFLINE) {
+		twork->cpu = cpu;
+		INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
+		queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+	}
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
 static void sched_tick_stop(int cpu)
 {
 	struct tick_work *twork;
+	int os;
 
 	if (housekeeping_cpu(cpu, HK_FLAG_TICK))
 		return;
@@ -3564,7 +3603,10 @@ static void sched_tick_stop(int cpu)
 	WARN_ON_ONCE(!tick_work_cpu);
 
 	twork = per_cpu_ptr(tick_work_cpu, cpu);
-	cancel_delayed_work_sync(&twork->work);
+	/* There cannot be competing actions, but don't rely on stop-machine. */
+	os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
+	WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
+	/* Don't cancel, as this would mess up the state machine. */
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
@@ -3572,7 +3614,6 @@ int __init sched_tick_offload_init(void)
 {
 	tick_work_cpu = alloc_percpu(struct tick_work);
 	BUG_ON(!tick_work_cpu);
-
 	return 0;
 }
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 80940939b733..e4bc4aa739b8 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -241,13 +241,14 @@ static void do_idle(void)
 		check_pgt_cache();
 		rmb();
 
+		local_irq_disable();
+
 		if (cpu_is_offline(cpu)) {
-			tick_nohz_idle_stop_tick_protected();
+			tick_nohz_idle_stop_tick();
 			cpuhp_report_idle_dead();
 			arch_cpu_idle_dead();
 		}
 
-		local_irq_disable();
 		arch_cpu_idle_enter();
 
 		/*