From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Fri, 14 Dec 2012 15:20:43 +0000 (-0800)
Subject: Revert "sched: Update_cfs_shares at period edge"
X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=17bc14b7;p=linux-beck.git

Revert "sched: Update_cfs_shares at period edge"

This reverts commit f269ae0469fc882332bdfb5db15d3c1315fe2a10.

It turns out it causes a very noticeable interactivity regression with
CONFIG_SCHED_AUTOGROUP (test-case: "make -j32" of the kernel in a
terminal window, while scrolling in a browser - the autogrouping means
that the two end up in separate cgroups, and the browser should be
smooth as silk despite the high load).

Says Paul Turner:
 "It seems that the update-throttling on the wake-side is reducing the
  interactive tasks' ability to preempt.  While I suspect the right
  longer term answer here is force these updates only in the
  cross-cgroup case; this is less trivial.  For this release I believe
  the right answer is either going to be a revert or restore the updates
  on the enqueue-side."

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Bisected-by: Mike Galbraith <efault@gmx.de>
Acked-by: Paul Turner <pjt@google.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 59e072b2db97..756f9f9e8542 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1265,7 +1265,6 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 	}
 
 	__update_cfs_rq_tg_load_contrib(cfs_rq, force_update);
-	update_cfs_shares(cfs_rq);
 }
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
@@ -1475,8 +1474,9 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
-	account_entity_enqueue(cfs_rq, se);
 	enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
+	account_entity_enqueue(cfs_rq, se);
+	update_cfs_shares(cfs_rq);
 
 	if (flags & ENQUEUE_WAKEUP) {
 		place_entity(cfs_rq, se, 0);
@@ -1549,6 +1549,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	 * Update run-time statistics of the 'current'.
 	 */
 	update_curr(cfs_rq);
+	dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);
 
 	update_stats_dequeue(cfs_rq, se);
 	if (flags & DEQUEUE_SLEEP) {
@@ -1568,8 +1569,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 
 	if (se != cfs_rq->curr)
 		__dequeue_entity(cfs_rq, se);
+	se->on_rq = 0;
 	account_entity_dequeue(cfs_rq, se);
-	dequeue_entity_load_avg(cfs_rq, se, flags & DEQUEUE_SLEEP);
 
 	/*
 	 * Normalize the entity after updating the min_vruntime because the
@@ -1583,7 +1584,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	return_cfs_rq_runtime(cfs_rq);
 
 	update_min_vruntime(cfs_rq);
-	se->on_rq = 0;
+	update_cfs_shares(cfs_rq);
 }
 
 /*
@@ -2595,8 +2596,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 
+		update_cfs_shares(cfs_rq);
 		update_entity_load_avg(se, 1);
-		update_cfs_rq_blocked_load(cfs_rq, 0);
 	}
 
 	if (!se) {
@@ -2656,8 +2657,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 
+		update_cfs_shares(cfs_rq);
 		update_entity_load_avg(se, 1);
-		update_cfs_rq_blocked_load(cfs_rq, 0);
 	}
 
 	if (!se) {
@@ -5837,11 +5838,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		se = tg->se[i];
 		/* Propagate contribution to hierarchy */
 		raw_spin_lock_irqsave(&rq->lock, flags);
-		for_each_sched_entity(se) {
+		for_each_sched_entity(se)
 			update_cfs_shares(group_cfs_rq(se));
-			/* update contribution to parent */
-			update_entity_load_avg(se, 1);
-		}
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
 	}