Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed,  6 Nov 2019 14:14:48 -0800
In-Reply-To: <CAKfTPtDeMevgn0JFxjzUWhp4dS10T2MQSA9P82nOGX73xUjXoA@mail.gmail.com>
Message-Id: <20191106221448.225183-1-joshdon@google.com>
Mime-Version: 1.0
References: <CAKfTPtDeMevgn0JFxjzUWhp4dS10T2MQSA9P82nOGX73xUjXoA@mail.gmail.com>
Subject: [PATCH v2] sched/fair: Do not set skip buddy up the sched hierarchy
From:   Josh Don <joshdon@google.com>
To:     Ingo Molnar <mingo@redhat.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>
Cc:     Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        linux-kernel@vger.kernel.org, Paul Turner <pjt@google.com>,
        Josh Don <joshdon@google.com>
Content-Type: text/plain; charset="UTF-8"
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

From: Venkatesh Pallipadi <venki@google.com>

Setting skip buddy all the way up the hierarchy does not play well
with intra-cgroup yield. One typical usecase of yield is when a
thread in a cgroup wants to yield CPU to another thread within the
same cgroup. For such a case, setting the skip buddy all the way up
the hierarchy is counter-productive, as that results in CPU being
yielded to a task in some other cgroup.

So, limit the skip effect only to the task requesting it.

Signed-off-by: Josh Don <joshdon@google.com>
---
Changelog since v1:
- As an optimization, skip clearing the skip buddy up the hierarchy
- Due to the above, it makes sense to inline __clear_buddies_skip; while
  we're at it, inline the other __clear_buddies* functions as well.

 kernel/sched/fair.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 682a754ea3e1..dbac30e3cc08 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4010,7 +4010,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	}
 }
 
-static void __clear_buddies_last(struct sched_entity *se)
+static inline void __clear_buddies_last(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -4021,7 +4021,7 @@ static void __clear_buddies_last(struct sched_entity *se)
 	}
 }
 
-static void __clear_buddies_next(struct sched_entity *se)
+static inline void __clear_buddies_next(struct sched_entity *se)
 {
 	for_each_sched_entity(se) {
 		struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -4032,15 +4032,12 @@ static void __clear_buddies_next(struct sched_entity *se)
 	}
 }
 
-static void __clear_buddies_skip(struct sched_entity *se)
+static inline void __clear_buddies_skip(struct sched_entity *se)
 {
-	for_each_sched_entity(se) {
-		struct cfs_rq *cfs_rq = cfs_rq_of(se);
-		if (cfs_rq->skip != se)
-			break;
+	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
+	if (cfs_rq->skip == se)
 		cfs_rq->skip = NULL;
-	}
 }
 
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -4051,8 +4048,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (cfs_rq->next == se)
 		__clear_buddies_next(se);
 
-	if (cfs_rq->skip == se)
-		__clear_buddies_skip(se);
+	__clear_buddies_skip(se);
 }
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
@@ -6647,8 +6643,15 @@ static void set_next_buddy(struct sched_entity *se)
 
 static void set_skip_buddy(struct sched_entity *se)
 {
-	for_each_sched_entity(se)
-		cfs_rq_of(se)->skip = se;
+	/*
+	 * One typical usecase of yield is when a thread in a cgroup
+	 * wants to yield CPU to another thread within the same cgroup.
+	 * For such a case, setting the skip buddy all the way up the
+	 * hierarchy is counter-productive, as that results in CPU being
+	 * yielded to a task in some other cgroup. So, only set skip
+	 * for the task requesting it.
+	 */
+	cfs_rq_of(se)->skip = se;
 }
 
 /*
-- 
2.24.0.rc1.363.gb1bccd3e3d-goog