Re: [PATCH] tmpfs: fix regressions from wider use of ZERO_PAGE

From: Christoph Hellwig
Date: Wed Apr 13 2022 - 12:41:37 EST


On Tue, Apr 12, 2022 at 04:22:21PM -0700, Andrew Morton wrote:
> On Fri, 8 Apr 2022 23:08:29 -0700 (PDT) Hugh Dickins <hughd@xxxxxxxxxx> wrote:
>
> > >
> > > Either way I'd rather do this optimization in iov_iter_zero rather
> > > than hiding it in tmpfs.
> >
> > Let's see what others say. I think we would all prefer clear_user() to be
> > enhanced, and hack around it neither here in tmpfs nor in iov_iter_zero().
> > But that careful work won't get done by magic, nor by me.
> >
> > And iov_iter_zero() has to deal with a wider range of possibilities,
> > when pulling in cache lines of ZERO_PAGE(0) will be less advantageous,
> > than in tmpfs doing a large dd - the case I'm aiming not to regress here
> > (tmpfs has been copying ZERO_PAGE(0) like this for years).
>
> We do need something to get 5.18 fixed. Christoph, do you think we
> should proceed with this patch for 5.18?

Well, let's queue it up then.