Merge branch 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler fixes from Ingo Molnar:
 "A deadline scheduler warning/race fix, and a cfs_period_us quota
  calculation workaround where the real fix looks too involved to merge
  immediately"

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Correctly handle active 0-lag timers
  sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup

2 files changed, 26 insertions, 2 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6a73e41a2016..43901fa3f269 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -252,7 +252,6 @@ static void task_non_contending(struct task_struct *p)
         if (dl_entity_is_special(dl_se))
                 return;
 
-        WARN_ON(hrtimer_active(&dl_se->inactive_timer));
         WARN_ON(dl_se->dl_non_contending);
 
         zerolag_time = dl_se->deadline -
@@ -269,7 +268,7 @@ static void task_non_contending(struct task_struct *p)
          * If the "0-lag time" already passed, decrease the active
          * utilization now, instead of starting a timer
          */
-        if (zerolag_time < 0) {
+        if ((zerolag_time < 0) || hrtimer_active(&dl_se->inactive_timer)) {
                 if (dl_task(p))
                         sub_running_bw(dl_se, dl_rq);
                 if (!dl_task(p) || p->state == TASK_DEAD) {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 40bd1e27b1b7..a4d9e14bf138 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4885,6 +4885,8 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
         return HRTIMER_NORESTART;
 }
 
+extern const u64 max_cfs_quota_period;
+
 static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 {
         struct cfs_bandwidth *cfs_b =
@@ -4892,6 +4894,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
         unsigned long flags;
         int overrun;
         int idle = 0;
+        int count = 0;
 
         raw_spin_lock_irqsave(&cfs_b->lock, flags);
         for (;;) {
@@ -4899,6 +4902,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
                 if (!overrun)
                         break;
 
+                if (++count > 3) {
+                        u64 new, old = ktime_to_ns(cfs_b->period);
+
+                        new = (old * 147) / 128; /* ~115% */
+                        new = min(new, max_cfs_quota_period);
+
+                        cfs_b->period = ns_to_ktime(new);
+
+                        /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
+                        cfs_b->quota *= new;
+                        cfs_b->quota = div64_u64(cfs_b->quota, old);
+
+                        pr_warn_ratelimited(
+        "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
+                                smp_processor_id(),
+                                div_u64(new, NSEC_PER_USEC),
+                                div_u64(cfs_b->quota, NSEC_PER_USEC));
+
+                        /* reset count so we don't come right back in here */
+                        count = 0;
+                }
+
                 idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
         }
         if (idle)