[Devel] [PATCH RHEL7 COMMIT] ms/sched/fair: Initialize throttle_count for new task-groups lazily

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-327.22.2.vz7.16.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-327.22.2.el7
------>
commit e2b27e0eb71646fac108ba71fc02e60de2c89ea6
Author: Konstantin Khlebnikov <khlebnikov at yandex-team.ru>
Date:   Wed Jul 27 17:05:48 2016 +0400

    ms/sched/fair: Initialize throttle_count for new task-groups lazily
    
    ms commit: 094f469172e00d6ab0a3130b0e01c83b3cf3a98d
    
    Cgroup created inside throttled group must inherit current throttle_count.
    Broken throttle_count allows to nominate throttled entries as a next buddy,
    later this leads to null pointer dereference in pick_next_task_fair().
    
    This patch initialize cfs_rq->throttle_count at first enqueue: laziness
    allows to skip locking all rq at group creation. Lazy approach also allows
    to skip full sub-tree scan at throttling hierarchy (not in this patch).
    
    Signed-off-by: Konstantin Khlebnikov <khlebnikov at yandex-team.ru>
    
    Signed-off-by: Peter Zijlstra (Intel) <peterz at infradead.org>
    Cc: Linus Torvalds <torvalds at linux-foundation.org>
    Cc: Peter Zijlstra <peterz at infradead.org>
    Cc: Thomas Gleixner <tglx at linutronix.de>
    Cc: bsegall at google.com
    Link: http://lkml.kernel.org/r/146608182119.21870.8439834428248129633.stgit@buzz
    Signed-off-by: Ingo Molnar <mingo at kernel.org>
    
    https://jira.sw.ru/browse/PSBM-50099
    
    Signed-off-by: Andrey Ryabinin <aryabinin at virtuozzo.com>
---
 kernel/sched/fair.c  | 20 ++++++++++++++++++++
 kernel/sched/sched.h |  2 +-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 515685f..b6f70a3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3850,6 +3850,26 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 	if (!cfs_bandwidth_used())
 		return;
 
+	/* Synchronize hierarchical throttle counter: */
+	if (unlikely(!cfs_rq->throttle_uptodate)) {
+		struct rq *rq = rq_of(cfs_rq);
+		struct cfs_rq *pcfs_rq;
+		struct task_group *tg;
+
+		cfs_rq->throttle_uptodate = 1;
+
+		/* Get closest up-to-date node, because leaves go first: */
+		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+			if (pcfs_rq->throttle_uptodate)
+				break;
+		}
+		if (tg) {
+			cfs_rq->throttle_count = pcfs_rq->throttle_count;
+			cfs_rq->throttled_clock_task = rq_clock_task(rq);
+		}
+	}
+
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2bdf80b..d9fe825 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -352,7 +352,7 @@ struct cfs_rq {
 
 	u64 throttled_clock, throttled_clock_task;
 	u64 throttled_clock_task_time;
-	int throttled, throttle_count;
+	int throttled, throttle_count, throttle_uptodate;
 	struct list_head throttled_list;
 
 	struct list_head boosted_entities;