On Fri, 2018-07-13 at 11:26 -0700, Dave Hansen wrote:
> On 07/11/2018 10:05 AM, Yu-cheng Yu wrote:
> >
> > My understanding is that we don't want to follow write pte if the page
> > is shared as read-only. For a SHSTK page, that is (R/O + DIRTY_SW),
> > which means the SHSTK page has not been COW'ed. Is that right?
> Let's look at the code again:
>
> >
> > -static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
> > +static inline bool can_follow_write_pte(pte_t pte, unsigned int flags,
> > + bool shstk)
> > {
> > + bool pte_cowed = shstk ? is_shstk_pte(pte):pte_dirty(pte);
> > +
> > return pte_write(pte) ||
> > - ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
> > + ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_cowed);
> > }
> This is another case where the naming of pte_*() is biting us vs. the
> perversion of the PTE bits. The lack of comments and explanation inthe
> patch is compounding the confusion.
>
> We need to find a way to differentiate "someone can write to this PTE"
> from "the write bit is set in this PTE".
>
> In this particular hunk, we need to make it clear that pte_write() is
> *never* true for shadowstack PTEs. In other words, shadow stack VMAs
> will (should?) never even *see* a pte_write() PTE.
>
> I think this is a case where you just need to bite the bullet and
> bifurcate can_follow_write_pte(). Just separate the shadowstack and
> non-shadowstack parts.
In case I don't understand the exact issue.
What about the following.
diff --git a/mm/gup.c b/mm/gup.c
index fc5f98069f4e..45a0837b27f9 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -70,6 +70,12 @@ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags)
((flags & FOLL_FORCE) && (flags & FOLL_COW) && pte_dirty(pte));
}
+static inline bool can_follow_write_shstk_pte(pte_t pte, unsigned int flags)
+{
+ return ((flags & FOLL_FORCE) && (flags & FOLL_COW) &&
+ is_shstk_pte(pte));
+}
+
static struct page *follow_page_pte(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
@@ -105,9 +111,16 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
}
if ((flags & FOLL_NUMA) && pte_protnone(pte))
goto no_page;
- if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, flags)) {
- pte_unmap_unlock(ptep, ptl);
- return NULL;
+ if (flags & FOLL_WRITE) {
+ if (is_shstk_mapping(vma->vm_flags)) {
+ if (!can_follow_write_shstk_pte(pte, flags)) {
+ pte_unmap_unlock(ptep, ptl);
+ return NULL;
+ }
+ } else if (!can_follow_write_pte(pte, flags) {
+ pte_unmap_unlock(ptep, ptl);
+ return NULL;
+ }
}
page = vm_normal_page(vma, address, pte);
