sched: Bail out of yield_to when source and target runqueue has one task

In case of undercomitted scenarios, especially in large guests
yield_to overhead is significantly high. when run queue length of
source and target is one, take an opportunity to bail out and return
-ESRCH. This return condition can be further exploited to quickly come
out of PLE handler.

(History: Raghavendra initially worked on break out of kvm ple handler upon
 seeing source runqueue length = 1, but it had to export rq length).
 Peter came up with the elegant idea of return -ESRCH in scheduler core.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Raghavendra, Checking the rq length of target vcpu condition added.(thanks Avi)
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Acked-by: Andrew Jones <drjones@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0533496b6228cfde3afe20051006683da12e0ca5..01edad9b5d71f3603a0b1602e01272189e20301a 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4316,7 +4316,10 @@ EXPORT_SYMBOL(yield);
  * It's the caller's job to ensure that the target task struct
  * can't go away on us before we can do any checks.
  *
- * Returns true if we indeed boosted the target task.
+ * Returns:
+ *     true (>0) if we indeed boosted the target task.
+ *     false (0) if we failed to boost the target.
+ *     -ESRCH if there's no task to yield to.
  */
 bool __sched yield_to(struct task_struct *p, bool preempt)
 {
@@ -4330,6 +4333,15 @@ bool __sched yield_to(struct task_struct *p, bool preempt)
 
 again:
        p_rq = task_rq(p);
+       /*
+        * If we're the only runnable task on the rq and target rq also
+        * has only one task, there's absolutely no point in yielding.
+        */
+       if (rq->nr_running == 1 && p_rq->nr_running == 1) {
+               yielded = -ESRCH;
+               goto out_irq;
+       }
+
        double_rq_lock(rq, p_rq);
        while (task_rq(p) != p_rq) {
                double_rq_unlock(rq, p_rq);
@@ -4337,13 +4349,13 @@ again:
        }
 
        if (!curr->sched_class->yield_to_task)
-               goto out;
+               goto out_unlock;
 
        if (curr->sched_class != p->sched_class)
-               goto out;
+               goto out_unlock;
 
        if (task_running(p_rq, p) || p->state)
-               goto out;
+               goto out_unlock;
 
        yielded = curr->sched_class->yield_to_task(rq, p, preempt);
        if (yielded) {
@@ -4356,11 +4368,12 @@ again:
                        resched_task(p_rq->curr);
        }
 
-out:
+out_unlock:
        double_rq_unlock(rq, p_rq);
+out_irq:
        local_irq_restore(flags);
 
-       if (yielded)
+       if (yielded > 0)
                schedule();
 
        return yielded;