1 files changed, 107 insertions, 31 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index c32c3e643da..f61837ad336 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -822,6 +822,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 		 * re-elected due to buddy favours.
 		 */
 		clear_buddies(cfs_rq, curr);
+		return;
+	}
+
+	/*
+	 * Ensure that a task that missed wakeup preemption by a
+	 * narrow margin doesn't have to wait for a full slice.
+	 * This also mitigates buddy induced latencies under load.
+	 */
+	if (!sched_feat(WAKEUP_PREEMPT))
+		return;
+
+	if (delta_exec < sysctl_sched_min_granularity)
+		return;
+
+	if (cfs_rq->nr_running > 1) {
+		struct sched_entity *se = __pick_next_entity(cfs_rq);
+		s64 delta = curr->vruntime - se->vruntime;
+
+		if (delta > ideal_runtime)
+			resched_task(rq_of(cfs_rq)->curr);
 	}
 }
 
@@ -861,21 +881,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
 static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *se = __pick_next_entity(cfs_rq);
-	struct sched_entity *buddy;
+	struct sched_entity *left = se;
 
-	if (cfs_rq->next) {
-		buddy = cfs_rq->next;
-		cfs_rq->next = NULL;
-		if (wakeup_preempt_entity(buddy, se) < 1)
-			return buddy;
-	}
+	if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
+		se = cfs_rq->next;
 
-	if (cfs_rq->last) {
-		buddy = cfs_rq->last;
-		cfs_rq->last = NULL;
-		if (wakeup_preempt_entity(buddy, se) < 1)
-			return buddy;
-	}
+	/*
+	 * Prefer last buddy, try to return the CPU to a preempted task.
+	 */
+	if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
+		se = cfs_rq->last;
+
+	clear_buddies(cfs_rq, se);
 
 	return se;
 }
@@ -1328,6 +1345,37 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
 }
 
 /*
+ * Try and locate an idle CPU in the sched_domain.
+ */
+static int
+select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
+{
+	int cpu = smp_processor_id();
+	int prev_cpu = task_cpu(p);
+	int i;
+
+	/*
+	 * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
+	 * test in select_task_rq_fair) and the prev_cpu is idle then that's
+	 * always a better target than the current cpu.
+	 */
+	if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
+		return prev_cpu;
+
+	/*
+	 * Otherwise, iterate the domain and find an elegible idle cpu.
+	 */
+	for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
+		if (!cpu_rq(i)->cfs.nr_running) {
+			target = i;
+			break;
+		}
+	}
+
+	return target;
+}
+
+/*
  * sched_balance_self: balance the current task (running on cpu) in domains
  * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
  * SD_BALANCE_EXEC.
@@ -1381,11 +1429,35 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 				want_sd = 0;
 		}
 
-		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
-		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+		/*
+		 * While iterating the domains looking for a spanning
+		 * WAKE_AFFINE domain, adjust the affine target to any idle cpu
+		 * in cache sharing domains along the way.
+		 */
+		if (want_affine) {
+			int target = -1;
 
-			affine_sd = tmp;
-			want_affine = 0;
+			/*
+			 * If both cpu and prev_cpu are part of this domain,
+			 * cpu is a valid SD_WAKE_AFFINE target.
+			 */
+			if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+				target = cpu;
+
+			/*
+			 * If there's an idle sibling in this domain, make that
+			 * the wake_affine target instead of the current cpu.
+			 */
+			if (tmp->flags & SD_PREFER_SIBLING)
+				target = select_idle_sibling(p, tmp, target);
+
+			if (target >= 0) {
+				if (tmp->flags & SD_WAKE_AFFINE) {
+					affine_sd = tmp;
+					want_affine = 0;
+				}
+				cpu = target;
+			}
 		}
 
 		if (!want_sd && !want_affine)
@@ -1577,6 +1649,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	struct sched_entity *se = &curr->se, *pse = &p->se;
 	struct cfs_rq *cfs_rq = task_cfs_rq(curr);
 	int sync = wake_flags & WF_SYNC;
+	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
 	update_curr(cfs_rq);
 
@@ -1591,18 +1664,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	if (unlikely(se == pse))
 		return;
 
-	/*
-	 * Only set the backward buddy when the current task is still on the
-	 * rq. This can happen when a wakeup gets interleaved with schedule on
-	 * the ->pre_schedule() or idle_balance() point, either of which can
-	 * drop the rq lock.
-	 *
-	 * Also, during early boot the idle thread is in the fair class, for
-	 * obvious reasons its a bad idea to schedule back to the idle thread.
-	 */
-	if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
-		set_last_buddy(se);
-	if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+	if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
 		set_next_buddy(pse);
 
 	/*
@@ -1648,8 +1710,22 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 
 	BUG_ON(!pse);
 
-	if (wakeup_preempt_entity(se, pse) == 1)
+	if (wakeup_preempt_entity(se, pse) == 1) {
 		resched_task(curr);
+		/*
+		 * Only set the backward buddy when the current task is still
+		 * on the rq. This can happen when a wakeup gets interleaved
+		 * with schedule on the ->pre_schedule() or idle_balance()
+		 * point, either of which can * drop the rq lock.
+		 *
+		 * Also, during early boot the idle thread is in the fair class,
+		 * for obvious reasons its a bad idea to schedule back to it.
+		 */
+		if (unlikely(!se->on_rq || curr == rq->idle))
+			return;
+		if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
+			set_last_buddy(se);
+	}
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1658,7 +1734,7 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
 	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 
-	if (unlikely(!cfs_rq->nr_running))
+	if (!cfs_rq->nr_running)
 		return NULL;
 
 	do {