[RFC 1/6] sched: Add nice value change notifier

[Tvrtko Ursulin]

Hi Peter,

On 30/09/2021 19:33, Peter Zijlstra wrote:
> On Thu, Sep 30, 2021 at 06:15:47PM +0100, Tvrtko Ursulin wrote:
>>   void set_user_nice(struct task_struct *p, long nice)
>>   {
>>   	bool queued, running;
>> -	int old_prio;
>> +	int old_prio, ret;
>>   	struct rq_flags rf;
>>   	struct rq *rq;
>>   
>> @@ -6913,6 +6945,9 @@ void set_user_nice(struct task_struct *p, long nice)
>>   	 */
>>   	p->sched_class->prio_changed(rq, p, old_prio);
>>   
>> +	ret = atomic_notifier_call_chain(&user_nice_notifier_list, nice, p);
>> +	WARN_ON_ONCE(ret != NOTIFY_DONE);
>> +
>>   out_unlock:
>>   	task_rq_unlock(rq, p, &rf);
>>   }
> 
> No, we're not going to call out to exported, and potentially unbounded,
> functions under scheduler locks.

Agreed, that's another good point why it is even more hairy, as I have 
generally alluded in the cover letter.

Do you have any immediate thoughts on possible alternatives?

Like for instance if I did a queue_work from set_user_nice and then ran 
a notifier chain async from a worker? I haven't looked at yet what 
repercussion would that have in terms of having to cancel the pending 
workers when tasks exit. I can try and prototype that and see how it 
would look.

There is of course an example ioprio which solves the runtime 
adjustments via a dedicated system call. But I don't currently feel that 
a third one would be a good solution. At least I don't see a case for 
being able to decouple the priority of CPU and GPU and computations.

Have I opened a large can of worms? :)

Regards,

Tvrtko