Re: [PATCH v3] sched/fair: remove dead code on enqueue_task_fair()

[Christian Loehle <christian.loehle@arm.com>]

On 10/13/26 12:58, Peter Zijlstra wrote:
> On Mon, Oct 12, 2026 at 03:59:40PM +0100, Christian Loehle wrote:
>> On 10/12/26 15:02, Peter Zijlstra wrote:
> 
>>> Anyway, this is different from the initial use-case, where a
>>> sched_entity would get dequeue and re-enqueued while walking the cgroup
>>> hierarchy, and thus had to appear like nothing happened in between.
>>>
>>> In this case we're fine to advance time.
>>>
>>> Anyway... the normal block/wakeup paths are >< close to also hitting
>>> this in the case where balancing drops the rq->lock after dequeue. The
>>> only reason ttwu can't tickle this is because it has that ->on_cpu
>>> stuff. However, we cannot use that on the unthrottle path :/
>>>
>>> Bah.
>>>
>>> Does this work?
>>>
>>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>>> index 5c98d8dfce5d..0edd8bfb6363 100644
>>> --- a/kernel/sched/fair.c
>>> +++ b/kernel/sched/fair.c
>>> @@ -8250,7 +8250,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
>>>  	weight = enqueue_hierarchy(p, flags);
>>>  	reweight_eevdf(cfs_rq, se, weight, false);
>>>  	place_entity(cfs_rq, se, flags | ENQUEUE_QUEUED);
>>> -	__enqueue_entity(cfs_rq, se);
>>> +
>>> +	/*
>>> +	 * This can actually happen with CFS_BANDWIDTH, in that case a task
>>> +	 * can get throttled, dequeued and then unthrottled, woken *before* it
>>> +	 * schedules out and does put_prev_task().
>>> +	 */
>>> +	if (cfs_rq->curr != se)
>>> +		__enqueue_entity(cfs_rq, se);
>>>  
>>>  	if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
>>>  		dl_server_start(&rq->fair_server);
>>
>> Tested-by: Christian Loehle <christian.loehle@arm.com>
>> for my reproducer, that being said, and indeed the failure is:
>> throttle -> dequeue (not put_prev_task()'d yet) -> (from remote CPU) unthrottle -> enqueue()
>>
>> The dequeue()->enqueue() also lets place_entity()
>> 'double-account' the entity's (on dequeue() saved) lag, right?
>> After dequeue:       curr == se, on_rq == 0 -> excl from average
>> enqueue_hierarchy(): curr == se, on_rq == 1 -> incl again
>> place_entity():      calculate placement assuming se is excl
> 
> I'm not entirely sure I follow. With the above fix there is still only
> one place_entity(), which is after enqueue_hierarchy() and has
> ENQUEUE_QUEUED on.

Exactly.

> 
> Here enqueue_hierarchy() adds the entity to h_nr_queued, and
> ENQUEUE_QUEUED tells place_entity() exactly this, so it can adjust.

... but place_entity(ENQUEUE_QUEUED) still does:

    load = cfs_rq->sum_weight;
    if (curr && curr->on_rq) // <-- this is true after enqueue_hierarchy()
       load += avg_vruntime_weight(cfs_rq, curr->h_load.weight);
         
    weight = avg_vruntime_weight(cfs_rq, se->h_load.weight); // <- this assumes se isn't already part of cfs_rq weight, but it is (still)
    lag *= load + weight; 
    ...

(in this concrete enqueue()->dequeue() due to unthrottling case)