On Thu, 2010-04-01 at 18:51 +0300, Avi Kivity wrote:
On 04/01/2010 06:42 PM, Andrea Arcangeli wrote:I would much rather we make call_rcu_preempt() available at all times.
On Thu, Apr 01, 2010 at 01:43:14PM +0200, Peter Zijlstra wrote:Can we use srcu now instead?
On Thu, 2010-04-01 at 13:27 +0200, Peter Zijlstra wrote:You should have a look at my old patchset where Christoph already
I've almost got a patch done that converts those two, still need to lookOK, so the below builds and boots, only need to track down that
where that tasklist_lock muck happens.
tasklist_lock nesting, but I got to run an errand first.
implemented this (and not for decreasing latency but to allow
scheduling in mmu notifier handlers, only needed by XPMEM):
The ugliest part of it (that I think you missed below) is the breakage
of the RCU locking in the anon-vma which requires adding refcounting
to it. That was the worst part of the conversion as far as I can tell.