Pick_next_task_fair() must be sure that here is at least one runnable
task before calling put_prev_task(), but put_prev_task() can expire
last remains of cfs quota and throttle all currently runnable tasks.
As a result pick_next_task_fair() cannot find next task and crashes.

This patch leaves 1 in ->runtime_remaining when current assignation
expires and tries to refill it right after that. In the worst case
task will be scheduled once and throttled at the end of slice.

Signed-off-by: Konstantin Khlebnikov <khlebni...@yandex-team.ru>
---
 kernel/sched/fair.c |   19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7ce18f3c097a..91785d077db4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3447,11 +3447,12 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
        struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 
-       /* if the deadline is ahead of our clock, nothing to do */
-       if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 
0))
+       /* nothing to expire */
+       if (cfs_rq->runtime_remaining <= 0)
                return;
 
-       if (cfs_rq->runtime_remaining < 0)
+       /* if the deadline is ahead of our clock, nothing to do */
+       if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 
0))
                return;
 
        /*
@@ -3469,8 +3470,14 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
                /* extend local deadline, drift is bounded above by 2 ticks */
                cfs_rq->runtime_expires += TICK_NSEC;
        } else {
-               /* global deadline is ahead, expiration has passed */
-               cfs_rq->runtime_remaining = 0;
+               /*
+                * Global deadline is ahead, expiration has passed.
+                *
+                * Do not expire runtime completely. Otherwise put_prev_task()
+                * can throttle all tasks when we already checked nr_running or
+                * put_prev_entity() can throttle already chosen next entity.
+                */
+               cfs_rq->runtime_remaining = 1;
        }
 }
 
@@ -3480,7 +3487,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq 
*cfs_rq, u64 delta_exec)
        cfs_rq->runtime_remaining -= delta_exec;
        expire_cfs_rq_runtime(cfs_rq);
 
-       if (likely(cfs_rq->runtime_remaining > 0))
+       if (likely(cfs_rq->runtime_remaining > 1))
                return;
 
        /*

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to