Merge branch 'timers/nohz' into sched/core

Merge these two, because upcoming patches will touch both areas.

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

2 files changed, 22 insertions, 12 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3bdf01b494fe..7f3063c153d8 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -684,10 +684,16 @@ static void wake_up_idle_cpu(int cpu)
 
 static bool wake_up_full_nohz_cpu(int cpu)
 {
+        /*
+         * We just need the target to call irq_exit() and re-evaluate
+         * the next tick. The nohz full kick at least implies that.
+         * If needed we can still optimize that later with an
+         * empty IRQ.
+         */
         if (tick_nohz_full_cpu(cpu)) {
                 if (cpu != smp_processor_id() ||
                     tick_nohz_tick_stopped())
-                        smp_send_reschedule(cpu);
+                        tick_nohz_full_kick_cpu(cpu);
                 return true;
         }
 
@@ -734,10 +740,11 @@ bool sched_can_stop_tick(void)
 
        rq = this_rq();
 
-       /* Make sure rq->nr_running update is visible after the IPI */
-       smp_rmb();
-
-       /* More than one running task need preemption */
+        /*
+         * More than one running task need preemption.
+         * nr_running update is assumed to be visible
+         * after IPI is sent from wakers.
+         */
        if (rq->nr_running > 1)
                return false;
 
@@ -1568,9 +1575,7 @@ void scheduler_ipi(void)
          */
         preempt_fold_need_resched();
 
-        if (llist_empty(&this_rq()->wake_list)
-                        && !tick_nohz_full_cpu(smp_processor_id())
-                        && !got_nohz_idle_kick())
+        if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick())
                 return;
 
         /*
@@ -1587,7 +1592,6 @@ void scheduler_ipi(void)
          * somewhat pessimize the simple resched case.
          */
         irq_enter();
-        tick_nohz_full_check();
         sched_ttwu_pending();
 
         /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 31cc02ebc54e..eb8567610295 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1221,9 +1221,15 @@ static inline void add_nr_running(struct rq *rq, unsigned count)
 #ifdef CONFIG_NO_HZ_FULL
         if (prev_nr < 2 && rq->nr_running >= 2) {
                 if (tick_nohz_full_cpu(rq->cpu)) {
-                        /* Order rq->nr_running write against the IPI */
-                        smp_wmb();
-                        smp_send_reschedule(rq->cpu);
+                        /*
+                         * Tick is needed if more than one task runs on a CPU.
+                         * Send the target an IPI to kick it out of nohz mode.
+                         *
+                         * We assume that IPI implies full memory barrier and the
+                         * new value of rq->nr_running is visible on reception
+                         * from the target.
+                         */
+                        tick_nohz_full_kick_cpu(rq->cpu);
                 }
        }
 #endif