Re: [PATCH] task_work: allow TWA_SIGNAL without a rescheduling IPI

[Jens Axboe]

On 4/28/22 4:28 PM, Thomas Gleixner wrote:
> On Thu, Apr 28 2022 at 06:21, Jens Axboe wrote:
>> On 4/28/22 3:08 AM, Peter Zijlstra wrote:
>>> On Mon, Apr 25, 2022 at 07:52:31PM -0600, Jens Axboe wrote:
>>>> On 4/22/22 8:34 AM, Jens Axboe wrote:
>>>>> Some use cases don't always need an IPI when sending a TWA_SIGNAL
>>>>> notification. Add TWA_SIGNAL_NO_IPI, which is just like TWA_SIGNAL,
>>>>> except it doesn't send an IPI to the target task. It merely sets
>>>>> TIF_NOTIFY_SIGNAL and wakes up the task.
>>>
>>> Could you perphaps elaborate on those use-cases? How do they guarantee
>>> the task_work is ran before userspace?
>>
>> The task is still marked as having task_work, so there should be no
>> differences in how it's run before returning to userspace. That would
>> not have delivered an IPI before, if it was in the kernel.
>>
>> The difference would be in the task currently running in userspace, and
>> whether we force a reschedule to ensure the task_work gets run now.
>> Without the forced reschedule, running of the task_work (from io_uring)
>> becomes more cooperative - it'll happen when the task transitions to the
>> kernel anyway (eg to wait for events).
> 
> I can see why you want that, but that needs to be part of the change log
> and it also needs a comprehensive comment for TWA_SIGNAL_NO_IPI.
> 
> @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL.... does not really explain
> much.

Agree, it should be better. I'll send out a new one with an improved
commit message and also with a better comment in the code for the NO_IPI
variant.

Thanks!

-- 
Jens Axboe