Re: [PATCH v6 1/4] rcu: Make call_rcu() lazy to save power

[Joel Fernandes]

> On Sep 26, 2022, at 6:37 PM, Paul E. McKenney <paulmck@xxxxxxxxxx> wrote:
> 
> On Mon, Sep 26, 2022 at 09:07:12PM +0000, Joel Fernandes wrote:
>> Hi Paul,
>> 
>> On Mon, Sep 26, 2022 at 10:42:40AM -0700, Paul E. McKenney wrote:
>> [..]
>>>>>>>> +        WRITE_ONCE(rdp->lazy_len, 0);
>>>>>>>> +    } else {
>>>>>>>> +        rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
>>>>>>>> +        WRITE_ONCE(rdp->lazy_len, 0);
>>>>>>> 
>>>>>>> This WRITE_ONCE() can be dropped out of the "if" statement, correct?
>>>>>> 
>>>>>> Yes will update.
>>>>> 
>>>>> Thank you!
>>>>> 
>>>>>>> If so, this could be an "if" statement with two statements in its "then"
>>>>>>> clause, no "else" clause, and two statements following the "if" statement.
>>>>>> 
>>>>>> I don’t think we can get rid of the else part but I’ll see what it looks like.
>>>>> 
>>>>> In the function header, s/rhp/rhp_in/, then:
>>>>> 
>>>>>    struct rcu_head *rhp = rhp_in;
>>>>> 
>>>>> And then:
>>>>> 
>>>>>    if (lazy && rhp) {
>>>>>        rcu_cblist_enqueue(&rdp->nocb_bypass, rhp);
>>>>>        rhp = NULL;
>>>> 
>>>> This enqueues on to the bypass list, where as if lazy && rhp, I want to queue
>>>> the new rhp on to the main cblist. So the pseudo code in my patch is:
>>>> 
>>>> if (lazy and rhp) then
>>>>    1. flush bypass CBs on to main list.
>>>>    2. queue new CB on to main list.
>>> 
>>> And the difference is here, correct?  I enqueue to the bypass list,
>>> which is then flushed (in order) to the main list.  In contrast, you
>>> flush the bypass list, then enqueue to the main list.  Either way,
>>> the callback referenced by rhp ends up at the end of ->cblist.
>>> 
>>> Or am I on the wrong branch of this "if" statement?
>> 
>> But we have to flush first, and then queue the new one. Otherwise wouldn't
>> the callbacks be invoked out of order? Or did I miss something?
> 
> I don't think so...
> 
> We want the new callback to be last, right?  One way to do that is to
> flush the bypass, then queue the new callback onto ->cblist.  Another way
> to do that is to enqueue the new callback onto the end of the bypass,
> then flush the bypass.  Why wouldn't these result in the same order?

Yes you are right, sorry. I was fixated on the main list. Both your snippet and my patch will be equivalent then. However I find your snippet a bit confusing, as in it is not immediately obvious - why would we queue something on to a list, if we were about to flush it. But any way, it does make it a clever piece of code in some sense and I am ok with doing it this way ;-)

Thanks,

  - Joel


> 
>>>> else
>>>>    1. flush bypass CBs on to main list
>>>>    2. queue new CB on to bypass list.
>>>> 
>>>>>    }
>>>>>    rcu_cblist_flush_enqueue(&rcl, &rdp->nocb_bypass, rhp);
>>>>>    WRITE_ONCE(rdp->lazy_len, 0);
>>>>> 
>>>>> Or did I mess something up?
>>>> 
>>>> So the rcu_cblist_flush_enqueue() has to happen before the
>>>> rcu_cblist_enqueue() to preserve the ordering of flushing into the main list,
>>>> and queuing on to the main list for the "if". Where as in your snip, the
>>>> order is reversed.
>>> 
>>> Did I pick the correct branch of the "if" statement above?  Or were you
>>> instead talking about the "else" clause?
>>> 
>>> I would have been more worried about getting cblist->len right.
>> 
>> Hmm, I think my concern was more the ordering of callbacks, and moving the
>> write to length should be Ok.
> 
> OK, sounds good to me!  ;-)
> 
>>>> If I consolidate it then, it looks like the following. However, it is a bit
>>>> more unreadable. I could instead just take the WRITE_ONCE out of both if/else
>>>> and move it to after the if/else, that would be cleanest. Does that sound
>>>> good to you? Thanks!
>>> 
>>> Let's first figure out whether or not we are talking past one another.  ;-)
>> 
>> Haha yeah :-)
> 
> So were we?  ;-)
> 
>                            Thanx, Paul