diff mbox series

[09/13] mm/gup: Cache *pudp in follow_pud_mask()

Message ID 20231219075538.414708-10-peterx@redhat.com
State New
Headers
Series mm/gup: Unify hugetlb, part 2 |

Commit Message

Peter Xu Dec. 19, 2023, 7:55 a.m. UTC 
  From: Peter Xu <peterx@redhat.com>

Introduce "pud_t pud" in the function, so the code won't dereference *pudp
multiple time.  Not only because that looks less straightforward, but also
because if the dereference really happened, it's not clear whether there
can be race to see different *pudp values if it's being modified at the
same time.

Signed-off-by: Peter Xu <peterx@redhat.com>
---
 mm/gup.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

Comments

James Houghton Dec. 19, 2023, 4:28 p.m. UTC | #1 
On Tue, Dec 19, 2023 at 2:57 AM <peterx@redhat.com> wrote:
>
> From: Peter Xu <peterx@redhat.com>
>
> Introduce "pud_t pud" in the function, so the code won't dereference *pudp
> multiple time.  Not only because that looks less straightforward, but also
> because if the dereference really happened, it's not clear whether there
> can be race to see different *pudp values if it's being modified at the
> same time.
>
> Signed-off-by: Peter Xu <peterx@redhat.com>
> ---
>  mm/gup.c | 17 +++++++++--------
>  1 file changed, 9 insertions(+), 8 deletions(-)
>
> diff --git a/mm/gup.c b/mm/gup.c
> index 6c0d82fa8cc7..97e87b7a15c3 100644
> --- a/mm/gup.c
> +++ b/mm/gup.c
> @@ -753,26 +753,27 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
>                                     unsigned int flags,
>                                     struct follow_page_context *ctx)
>  {
> -       pud_t *pud;
> +       pud_t *pudp, pud;
>         spinlock_t *ptl;
>         struct page *page;
>         struct mm_struct *mm = vma->vm_mm;
>
> -       pud = pud_offset(p4dp, address);
> -       if (pud_none(*pud))
> +       pudp = pud_offset(p4dp, address);
> +       pud = *pudp;

I think you might want a READ_ONCE() on this so that the compiler
doesn't actually read the pud multiple times.

> +       if (pud_none(pud))
>                 return no_page_table(vma, flags, address);
> -       if (pud_devmap(*pud)) {
> -               ptl = pud_lock(mm, pud);
> -               page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
> +       if (pud_devmap(pud)) {
> +               ptl = pud_lock(mm, pudp);
> +               page = follow_devmap_pud(vma, address, pudp, flags, &ctx->pgmap);
>                 spin_unlock(ptl);
>                 if (page)
>                         return page;
>                 return no_page_table(vma, flags, address);
>         }
> -       if (unlikely(pud_bad(*pud)))
> +       if (unlikely(pud_bad(pud)))
>                 return no_page_table(vma, flags, address);

Not your change, but reading this, it's not clear to me that
`pud_present(*pudp)` (and non-leaf) would necessarily be true at this
point -- like, I would prefer to see `!pud_present(pud)` instead of
`pud_bad()`. Thank you for adding that in the next patch. :)

Feel free to add:

Acked-by: James Houghton <jthoughton@google.com>
Peter Xu Dec. 20, 2023, 1:43 a.m. UTC | #2 
On Tue, Dec 19, 2023 at 11:28:54AM -0500, James Houghton wrote:
> On Tue, Dec 19, 2023 at 2:57 AM <peterx@redhat.com> wrote:
> >
> > From: Peter Xu <peterx@redhat.com>
> >
> > Introduce "pud_t pud" in the function, so the code won't dereference *pudp
> > multiple time.  Not only because that looks less straightforward, but also
> > because if the dereference really happened, it's not clear whether there
> > can be race to see different *pudp values if it's being modified at the
> > same time.
> >
> > Signed-off-by: Peter Xu <peterx@redhat.com>
> > ---
> >  mm/gup.c | 17 +++++++++--------
> >  1 file changed, 9 insertions(+), 8 deletions(-)
> >
> > diff --git a/mm/gup.c b/mm/gup.c
> > index 6c0d82fa8cc7..97e87b7a15c3 100644
> > --- a/mm/gup.c
> > +++ b/mm/gup.c
> > @@ -753,26 +753,27 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
> >                                     unsigned int flags,
> >                                     struct follow_page_context *ctx)
> >  {
> > -       pud_t *pud;
> > +       pud_t *pudp, pud;
> >         spinlock_t *ptl;
> >         struct page *page;
> >         struct mm_struct *mm = vma->vm_mm;
> >
> > -       pud = pud_offset(p4dp, address);
> > -       if (pud_none(*pud))
> > +       pudp = pud_offset(p4dp, address);
> > +       pud = *pudp;
> 
> I think you might want a READ_ONCE() on this so that the compiler
> doesn't actually read the pud multiple times.

Makes sense.  I probably only did the "split" part which Christoph
requested, without thinking futher than that. :)

> 
> > +       if (pud_none(pud))
> >                 return no_page_table(vma, flags, address);
> > -       if (pud_devmap(*pud)) {
> > -               ptl = pud_lock(mm, pud);
> > -               page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
> > +       if (pud_devmap(pud)) {
> > +               ptl = pud_lock(mm, pudp);
> > +               page = follow_devmap_pud(vma, address, pudp, flags, &ctx->pgmap);
> >                 spin_unlock(ptl);
> >                 if (page)
> >                         return page;
> >                 return no_page_table(vma, flags, address);
> >         }
> > -       if (unlikely(pud_bad(*pud)))
> > +       if (unlikely(pud_bad(pud)))
> >                 return no_page_table(vma, flags, address);
> 
> Not your change, but reading this, it's not clear to me that
> `pud_present(*pudp)` (and non-leaf) would necessarily be true at this
> point -- like, I would prefer to see `!pud_present(pud)` instead of
> `pud_bad()`. Thank you for adding that in the next patch. :)

I think the assumption here is it is expected to be a directory entry when
reaching here, and for a valid directory entry pud_present() should always
return true (a side note: pud_present() may not mean "PRESENT bit set", see
m68k's implementation for example).

Yeah I added that in the next patch, my intention was to check
!pud_present() for all cases without the need to take pgtable lock, though.

> 
> Feel free to add:
> 
> Acked-by: James Houghton <jthoughton@google.com>

Thanks,
diff mbox series

Patch

diff --git a/mm/gup.c b/mm/gup.c
index 6c0d82fa8cc7..97e87b7a15c3 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -753,26 +753,27 @@  static struct page *follow_pud_mask(struct vm_area_struct *vma,
 				    unsigned int flags,
 				    struct follow_page_context *ctx)
 {
-	pud_t *pud;
+	pud_t *pudp, pud;
 	spinlock_t *ptl;
 	struct page *page;
 	struct mm_struct *mm = vma->vm_mm;
 
-	pud = pud_offset(p4dp, address);
-	if (pud_none(*pud))
+	pudp = pud_offset(p4dp, address);
+	pud = *pudp;
+	if (pud_none(pud))
 		return no_page_table(vma, flags, address);
-	if (pud_devmap(*pud)) {
-		ptl = pud_lock(mm, pud);
-		page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap);
+	if (pud_devmap(pud)) {
+		ptl = pud_lock(mm, pudp);
+		page = follow_devmap_pud(vma, address, pudp, flags, &ctx->pgmap);
 		spin_unlock(ptl);
 		if (page)
 			return page;
 		return no_page_table(vma, flags, address);
 	}
-	if (unlikely(pud_bad(*pud)))
+	if (unlikely(pud_bad(pud)))
 		return no_page_table(vma, flags, address);
 
-	return follow_pmd_mask(vma, address, pud, flags, ctx);
+	return follow_pmd_mask(vma, address, pudp, flags, ctx);
 }
 
 static struct page *follow_p4d_mask(struct vm_area_struct *vma,