On Thu, 31 Jan 2008, Nick Piggin wrote:
> Sorry, way behind on email here. I'll get through it slowly...
You're certainly not the only one, and certainly not the worst offender.
> On Sat, Jan 26, 2008 at 10:03:56PM -0800, Andrew Morton wrote:
> >
> > So... it's two patches in one.
>
> I guess
Sorry, way behind on email here. I'll get through it slowly...
On Sat, Jan 26, 2008 at 10:03:56PM -0800, Andrew Morton wrote:
> > On Tue, 22 Jan 2008 05:01:14 +0100 Nick Piggin <[EMAIL PROTECTED]> wrote:
> >
> > After running SetPageUptodate, preceeding stores to the page contents to
> > actually
> On Tue, 22 Jan 2008 05:01:14 +0100 Nick Piggin <[EMAIL PROTECTED]> wrote:
>
> After running SetPageUptodate, preceeding stores to the page contents to
> actually bring it uptodate may not be ordered with the store to set the page
> uptodate.
>
> Therefore, another CPU which checks PageUptodate
After running SetPageUptodate, preceeding stores to the page contents to
actually bring it uptodate may not be ordered with the store to set the page
uptodate.
Therefore, another CPU which checks PageUptodate is true, then reads the
page contents can get stale data.
Fix this by having an smp_wmb
4 matches
Mail list logo