Re: [PATCH, RFC, tip/core/rcu] v3 scalable classic RCUimplementation

[Paul E. McKenney]

On Sun, Aug 31, 2008 at 08:18:42PM +0200, Manfred Spraul wrote:
> Paul E. McKenney wrote:
>> On Sun, Aug 31, 2008 at 07:45:02PM +0200, Manfred Spraul wrote:
>>   
>>> Paul E. McKenney wrote:
>>>     
>>>> Assuming that the ordering of processing pending irqs and marking the
>>>> CPU offline in cpu_online_mask can be resolved as noted above, it should
>>>> work fine -- if a CPU's bit is clear, we can safely ignore it.  The race
>>>> can be resolved by checking the CPU's bit in force_quiescent_state().
>>>>
>>>> Or am I missing something?
>>>>         
>>> Yes, that would work:
>>> Rule 1: after CPU_DEAD, a cpu is gone. The cpu is quiet, rcu callbacks 
>>> must be moved to other cpus, ...
>>> Rule 2: if a cpu is not listed in cpu_online_mask, then it can be 
>>> considered as outside a read-side critical section.
>>>
>>> The problem with rule 2 is that it means someone 
>>> [force_quiescent_state()] must poll the cpu_online_mask and look for 
>>> changes.
>>> I'd really prefer a notifier. CPU_DYING is nearly the correct thing, it 
>>> only has to be moved down 3 lines ;-)
>>> (I want to kill the bitmaps, not add a hierarchical bitmap polling 
>>> system!)
>>>     
>>
>> But some later CPU_DYING notifier might decide that the CPU cannot be
>> removed after all, which would mean bringing the CPU back.  And then
>> whatever the CPU was needed for might have actually happened in the
>> meantime, which does not sound good to me...
>>   
> CPU_DYING must not fail, the current code doesn't support that.

Good point!

							Thanx, Paul
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/