Re: [rfc][patch] mm: vmap rewrite
From: Jeremy Fitzhardinge
Date: Sat Jun 07 2008 - 13:39:27 EST
Nick Piggin wrote:
Hi. RFC.
Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a
fast, scalable percpu frontend for small vmaps.
XEN and PAT and such do not like deferred TLB flushing. They just need to call
vm_unmap_aliases() in order to flush any deferred mappings. That call is very
expensive (well, actually not a lot more expensive than a single vunmap under
the old scheme), however it should be OK if not called too often.
What are the performance characteristics? Can it be fast-pathed if
there are no outstanding aliases?
For Xen, I'd need to do the alias unmap each time it allocates a page
for use in a pagetable. For initial process construction that could be
deferred, but creating mappings on a live process could get fairly
expensive as a result. The ideal interface for me would be a way of
testing if a given page has vmap aliases, so that we need only do the
unmap if really necessary. I'm guessing that goes into "need a new page
flag" territory though...
J
--
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/