Re: [PATCH 2.5.66-mm2] Fix page_convert_anon locking issues

[Andrew Morton <akpm@digeo.com>]

Andrew Morton <akpm@digeo.com> wrote:
>
> page_referenced() has the same problem, so refill_inactive_zone() will need
> to lock pages too.

Complete bollocks.  As long as the pte chains are consistent while
refill_inactive_zone holds pte_chain_lock (they darn well should be),
concurrent page_referenced() and page_convert_anon() is fine.

It could be that page_referenced() returns an inappropriate answer, but it's
so rare we don't care.

Which is good.  We really don't want to lock pages in refill_inactive_zone()
to keep the extremely rare page_convert_anon() away.  refill_inactive_zone()
is more a bath-temperature path than a hotpath, but still...

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart@kvack.org">aart@kvack.org</a>