Re: [rfc][patch] x86-64 new smp_call_function design

[Andi Kleen <ak@suse.de>]

> *vmalloc* TLB flushing. 
> 
> void flush_tlb_all(void)
> {
>         on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
> }
> 
> Of course we could use a new vector for it and speed it up a lot more,
> but after my vmalloc improvements I think that would be a waste of a
> vector at this point.

Ah I see sorry. If you want to just speed up vmalloc flushing I think
the easier way would be to just extend the normal TLB flusher for
vmalloc. So alone for this it probably wouldn't be worth it.

But I think it'll be useful for a couple of other things.

>>> As far as I understand, calling a subset of online CPUs that is not all or
>>> one, is used quite infrequently, so this might be OK.
>> With cpusets and isolation etc. it is the normal case.
> 
> Oh really? Coming from what callers?

The isolation work is not merged yet, but it will essentially need
to turn a lot of the _call_function()s into _call_function_mask()

-Andi