On Tue, Apr 02, 2019 at 10:28:12AM +0200, Peter Zijlstra wrote:
> Another approach would be something like the below:
>
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -87,7 +87,7 @@ static inline int __task_prio(struct tas
> */
>
> /* real prio, less is less */
> -static inline bool __prio_less(struct task_struct *a, struct task_struct *b,
> bool runtime)
> +static inline bool __prio_less(struct task_struct *a, struct task_struct *b,
> u64 vruntime)
> {
> int pa = __task_prio(a), pb = __task_prio(b);
>
> @@ -104,21 +104,25 @@ static inline bool __prio_less(struct ta
> if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
> return !dl_time_before(a->dl.deadline, b->dl.deadline);
>
> - if (pa == MAX_RT_PRIO + MAX_NICE && runtime) /* fair */
> - return !((s64)(a->se.vruntime - b->se.vruntime) < 0);
> + if (pa == MAX_RT_PRIO + MAX_NICE) /* fair */
> + return !((s64)(a->se.vruntime - vruntime) < 0);
>
> return false;
> }
>
> static inline bool cpu_prio_less(struct task_struct *a, struct task_struct
> *b)
> {
> - return __prio_less(a, b, true);
> + return __prio_less(a, b, b->se.vruntime);
> }
>
> static inline bool core_prio_less(struct task_struct *a, struct task_struct
> *b)
> {
> - /* cannot compare vruntime across CPUs */
> - return __prio_less(a, b, false);
> + u64 vruntime = b->se.vruntime;
> +
> + vruntime -= task_rq(b)->cfs.min_vruntime;
> + vruntime += task_rq(a)->cfs.min_vruntime
> +
> + return __prio_less(a, b, vruntime);
> }
>
> static inline bool __sched_core_less(struct task_struct *a, struct
> task_struct *b)
Brilliant, I like this approach, it makes core_prio_less() work across
CPUs. So I tested this, together with changing
cpu_prio_less(max, class_pick) to core_prio_less(max, class_pick) in
pick_task(), this problem is gone :-)
I verified with below debug code:
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cb24a0141e57..50658e79363f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3832,6 +3832,14 @@ next_class:;
WARN_ON_ONCE(!rq_i->core_pick);
+ if (rq->core->core_cookie && rq_i->core_pick->core_cookie &&
+ rq->core->core_cookie != rq_i->core_pick->core_cookie) {
+ trace_printk("expect 0x%lx, cpu%d got 0x%lx\n",
+ rq->core->core_cookie, i,
+ rq_i->core_pick->core_cookie);
+ WARN_ON_ONCE(1);
+ }
+
rq_i->core_pick->core_occupation = occ;
if (i == cpu)
--
2.19.1.3.ge56e4f7
