tick/nohz: Only wake up a single target cpu when kicking a task

When adding a tick dependency to a task, its necessary to
wake up the CPU where the task resides to reevaluate tick
dependencies on that CPU.

However the current code wakes up all nohz_full CPUs, which
is unnecessary.

Switch to waking up a single CPU, by using ordering of writes
to task->cpu and task->tick_dep_mask.

[ mingo: Minor readability edit. ]

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210512232924.150322-7-frederic@kernel.org

Author: Frederic Weisbecker

kernel/time/tick-sched.c

@@ -322,6 +322,31 @@ void tick_nohz_full_kick_cpu(int cpu)
 	irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
 }
 
+static void tick_nohz_kick_task(struct task_struct *tsk)
+{
+	int cpu = task_cpu(tsk);
+
+	/*
+	 * If the task concurrently migrates to another CPU,
+	 * we guarantee it sees the new tick dependency upon
+	 * schedule.
+	 *
+	 *
+	 * set_task_cpu(p, cpu);
+	 *   STORE p->cpu = @cpu
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock
+	 *   smp_mb__after_spin_lock()          STORE p->tick_dep_mask
+	 *   tick_nohz_task_switch()            smp_mb() (atomic_fetch_or())
+	 *      LOAD p->tick_dep_mask           LOAD p->cpu
+	 */
+
+	preempt_disable();
+	if (cpu_online(cpu))
+		tick_nohz_full_kick_cpu(cpu);
+	preempt_enable();
+}
+
 /*
  * Kick all full dynticks CPUs in order to force these to re-evaluate
  * their dependency on the tick and restart it if necessary.
@@ -404,19 +429,8 @@ EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
  */
 void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
 {
-	if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask)) {
-		if (tsk == current) {
-			preempt_disable();
-			tick_nohz_full_kick();
-			preempt_enable();
-		} else {
-			/*
-			 * Some future tick_nohz_full_kick_task()
-			 * should optimize this.
-			 */
-			tick_nohz_full_kick_all();
-		}
-	}
+	if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask))
+		tick_nohz_kick_task(tsk);
 }
 EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);