Re: [patch 2/4] mmu_notifier: Callbacks to invalidate address ranges

!MAILaRCHIVE_VOTE_RePLACE
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: Robin Holt <holt@...>
Cc: Christoph Lameter <clameter@...>, Avi Kivity <avi@...>, Izik Eidus <izike@...>, <kvm-devel@...>, Peter Zijlstra <a.p.zijlstra@...>, <steiner@...>, <linux-kernel@...>, <linux-mm@...>, <daniel.blueman@...>
Date: Saturday, February 2, 2008 - 10:23 pm

On Fri, Feb 01, 2008 at 05:35:28PM -0600, Robin Holt wrote:

I still hope I don't need to take any lock in _range_start and that
losing coherency (w/o risking global memory corruption but only
risking temporary userland data corruption thanks to the page pin) is
ok for KVM.

If I would have to take a lock in _range_start like XPMEM is forced to
do (GRU is by far not forced to it, if it would switch to my #v5) then
it would be a problem.
--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
Re: [patch 2/4] mmu_notifier: Callbacks to invalidate addres..., Andrea Arcangeli, (Sat Feb 2, 10:23 pm)