Messages in this thread | | | Date | Wed, 27 Feb 2008 14:33:00 +0100 | From | Andi Kleen <> | Subject | Re: [rfc][patch] x86-64 new smp_call_function design |
| |
> *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
| |