> > Fix threaded user page write memory ordering
>
> Thanks, I did see that, but I'm sure it must have been prompted by a
> discussion or another proposed patch from IBM. Maybe I'm wrong
> though.
Yes, my initial proposal iirc was to smp_wmb() in set_pte() but after a
discussion with Linus, we
> Fix threaded user page write memory ordering
>
> Make sure we order the writes to a newly created page
> with the page table update that potentially exposes the
> page to another CPU.
>
> This is a no-op on any architecture where getting the
> page table spinlock will already do the ordering
On Fri, Feb 09, 2007 at 12:41:51AM +, Hugh Dickins wrote:
> On Thu, 8 Feb 2007, Nick Piggin wrote:
> > Still no independent confirmation as to whether this is a problem or not.
>
> I'm trying to convince myself none of your patch is necessary. Probably
> shall fail. But how come we've
On Thu, 8 Feb 2007, Nick Piggin wrote:
> Still no independent confirmation as to whether this is a problem or not.
I'm trying to convince myself none of your patch is necessary. Probably
shall fail. But how come we've survived for years with such an issue?
> Updated some comments, added
On Thu, 2007-02-08 at 14:26 +0100, Nick Piggin wrote:
> Still no independent confirmation as to whether this is a problem or not.
> Updated some comments, added diffstats to patches, don't use __SetPageUptodate
> as an internal page-flags.h private function.
>
> I would like to eventually get an
Still no independent confirmation as to whether this is a problem or not.
Updated some comments, added diffstats to patches, don't use __SetPageUptodate
as an internal page-flags.h private function.
I would like to eventually get an ack from Hugh regarding the anon memory
and especially swap side
Still no independent confirmation as to whether this is a problem or not.
Updated some comments, added diffstats to patches, don't use __SetPageUptodate
as an internal page-flags.h private function.
I would like to eventually get an ack from Hugh regarding the anon memory
and especially swap side
On Thu, 2007-02-08 at 14:26 +0100, Nick Piggin wrote:
Still no independent confirmation as to whether this is a problem or not.
Updated some comments, added diffstats to patches, don't use __SetPageUptodate
as an internal page-flags.h private function.
I would like to eventually get an ack
On Thu, 8 Feb 2007, Nick Piggin wrote:
Still no independent confirmation as to whether this is a problem or not.
I'm trying to convince myself none of your patch is necessary. Probably
shall fail. But how come we've survived for years with such an issue?
Updated some comments, added
On Fri, Feb 09, 2007 at 12:41:51AM +, Hugh Dickins wrote:
On Thu, 8 Feb 2007, Nick Piggin wrote:
Still no independent confirmation as to whether this is a problem or not.
I'm trying to convince myself none of your patch is necessary. Probably
shall fail. But how come we've survived
Fix threaded user page write memory ordering
Make sure we order the writes to a newly created page
with the page table update that potentially exposes the
page to another CPU.
This is a no-op on any architecture where getting the
page table spinlock will already do the ordering (notably
Fix threaded user page write memory ordering
Thanks, I did see that, but I'm sure it must have been prompted by a
discussion or another proposed patch from IBM. Maybe I'm wrong
though.
Yes, my initial proposal iirc was to smp_wmb() in set_pte() but after a
discussion with Linus, we ended
12 matches
Mail list logo
