sched/fair: Initialize throttle_count for new task-groups lazily

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@yandex-team.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: bsegall@google.com
Link: http://lkml.kernel.org/r/146608182119.21870.8439834428248129633.stgit@buzz
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2ae68f0e3bf5a4919c069c9ce1873d6a1817f89a..8c5d8c0c88273d7f5e03f1aeb4fbd3e97a2201f7 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4202,6 +4202,26 @@ 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 72f1f3087b04a72fc0afc9ff81d768018eb05391..7cbeb92a1cb9361102b8514f612ee81be87fef10 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -437,7 +437,7 @@ 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;
 #endif /* CONFIG_CFS_BANDWIDTH */
 #endif /* CONFIG_FAIR_GROUP_SCHED */