Re: [PATCH] mm/userfaultfd: fix memory corruption due to writeprotect

[Andy Lutomirski]

On Mon, Dec 21, 2020 at 10:04 AM Andrea Arcangeli <aarcange@xxxxxxxxxx> wrote:
>
> Hello,
>
> On Sat, Dec 19, 2020 at 09:08:55PM -0800, Andy Lutomirski wrote:
> > On Sat, Dec 19, 2020 at 6:49 PM Andrea Arcangeli <aarcange@xxxxxxxxxx> wrote:
> > > The ptes are changed always with the PT lock, in fact there's no
> > > problem with the PTE updates. The only difference with mprotect
> > > runtime is that the mmap_lock is taken for reading. And the effect
> > > contested for this change doesn't affect the PTE, but supposedly the
> > > tlb flushing deferral.
> >
> > Can you point me at where the lock ends up being taken in this path?
>
> pte_offset_map_lock in change_pte_range, as in mprotect, no difference.
>
> As I suspected on my follow up, the bug described wasn't there, but
> I'll look at the new theory posted.

Indeed.