sched/core: Skip superfluous acquire barrier in ttwu

ttwu_remote() unconditionally locks the task's runqueue lock, which implies
a full barrier across the lock and unlock, so the acquire barrier after the
control dependency is only needed when the task isn't on the runqueue.

Signed-off-by: Sultan Alsawaf <sultan@kerneltoast.com>
Change-Id: Ibb988fe341ba3109d381682a8725fbd2e7a648e3

kernel/sched/core.c

@@ -2217,16 +2217,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags,
 	 * current.
 	 */
 	smp_rmb();
-	if (READ_ONCE(p->on_rq) && ttwu_remote(p, wake_flags))
+	if (READ_ONCE(p->on_rq)) {
+		if (ttwu_remote(p, wake_flags))
 			goto unlock;
-
+	} else {
 #ifdef CONFIG_SMP
 		/*
-	 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
-	 * possible to, falsely, observe p->on_cpu == 0.
+		 * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would
+		 * be possible to, falsely, observe p->on_cpu == 0.
 		 *
-	 * One must be running (->on_cpu == 1) in order to remove oneself
-	 * from the runqueue.
+		 * One must be running (->on_cpu == 1) in order to remove
+		 * oneself from the runqueue.
 		 *
 		 *  [S] ->on_cpu = 1;	[L] ->on_rq
 		 *      UNLOCK rq->lock
@@ -2234,16 +2235,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags,
 		 *      LOCK   rq->lock
 		 *  [S] ->on_rq = 0;    [L] ->on_cpu
 		 *
-	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
-	 * from the consecutive calls to schedule(); the first switching to our
-	 * task, the second putting it to sleep.
+		 * Pairs with the full barrier implied in the UNLOCK+LOCK on
+		 * rq->lock from the consecutive calls to schedule(); the first
+		 * switching to our task, the second putting it to sleep.
 		 *
-	 * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
-	 * schedule()'s deactivate_task() has 'happened' and p will no longer
-	 * care about it's own p->state. See the comment in __schedule().
+		 * Form a control-dep-acquire with p->on_rq == 0 above, to
+		 * ensure schedule()'s deactivate_task() has 'happened' and p
+		 * will no longer care about it's own p->state. See the comment
+		 * in __schedule().
 		 */
 		smp_acquire__after_ctrl_dep();
+#endif
+	}
 
+#ifdef CONFIG_SMP
 	/*
 	 * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
 	 * == 0), which means we need to do an enqueue, change p->state to