Re: [RFC PATCH v15 6/7] sched: Fix proxy/current (push,pull)ability

[K Prateek Nayak <kprateek.nayak@amd.com>]

Hello John, Peter,

On 3/17/2025 7:37 PM, Peter Zijlstra wrote:
> On Wed, Mar 12, 2025 at 03:11:36PM -0700, John Stultz wrote:
>> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
>> index b4f7b14f62a24..3596244f613f8 100644
>> --- a/kernel/sched/core.c
>> +++ b/kernel/sched/core.c
>> @@ -6722,6 +6722,23 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
>>   }
>>   #endif /* SCHED_PROXY_EXEC */
>>   
>> +static inline void proxy_tag_curr(struct rq *rq, struct task_struct *owner)
>> +{
>> +	if (!sched_proxy_exec())
>> +		return;
>> +	/*
>> +	 * pick_next_task() calls set_next_task() on the chosen task
>> +	 * at some point, which ensures it is not push/pullable.
>> +	 * However, the chosen/donor task *and* the mutex owner form an
>> +	 * atomic pair wrt push/pull.
>> +	 *
>> +	 * Make sure owner we run is not pushable. Unfortunately we can
>> +	 * only deal with that by means of a dequeue/enqueue cycle. :-/
>> +	 */
>> +	dequeue_task(rq, owner, DEQUEUE_NOCLOCK | DEQUEUE_SAVE);
>> +	enqueue_task(rq, owner, ENQUEUE_NOCLOCK | ENQUEUE_RESTORE);
>> +}
> 
> So this is probably fine at this point; but we should eventually look at
> fixing this.
> 
> We can probably look at (ab)using sched_class::set_cpus_allowed() for
> this.

Isn't the net result in this case just "dequeue_pushable_task()"?

Can it be defined as a class callback to avoid a full dequeue + requeue
overhead for the fair class during proxy?

-- 
Thanks and Regards,
Prateek