On Wed, Jan 12, 2022 at 7:37 PM Minchan Kim <minchan@xxxxxxxxxx> wrote:
>
> On Wed, Jan 12, 2022 at 06:53:07PM -0300, Mauricio Faria de Oliveira wrote:
> > Hi Minchan Kim,
> >
> > Thanks for handling the hard questions! :)
> >
> > On Wed, Jan 12, 2022 at 2:33 PM Minchan Kim <minchan@xxxxxxxxxx> wrote:
> > >
> > > On Wed, Jan 12, 2022 at 09:46:23AM +0800, Huang, Ying wrote:
> > > > Yu Zhao <yuzhao@xxxxxxxxxx> writes:
> > > >
> > > > > On Wed, Jan 05, 2022 at 08:34:40PM -0300, Mauricio Faria de Oliveira wrote:
> > > > >> diff --git a/mm/rmap.c b/mm/rmap.c
> > > > >> index 163ac4e6bcee..8671de473c25 100644
> > > > >> --- a/mm/rmap.c
> > > > >> +++ b/mm/rmap.c
> > > > >> @@ -1570,7 +1570,20 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> > > > >>
> > > > >> /* MADV_FREE page check */
> > > > >> if (!PageSwapBacked(page)) {
> > > > >> - if (!PageDirty(page)) {
> > > > >> + int ref_count = page_ref_count(page);
> > > > >> + int map_count = page_mapcount(page);
> > > > >> +
> > > > >> + /*
> > > > >> + * The only page refs must be from the isolation
> > > > >> + * (checked by the caller shrink_page_list() too)
> > > > >> + * and one or more rmap's (dropped by discard:).
> > > > >> + *
> > > > >> + * Check the reference count before dirty flag
> > > > >> + * with memory barrier; see __remove_mapping().
> > > > >> + */
> > > > >> + smp_rmb();
> > > > >> + if ((ref_count - 1 == map_count) &&
> > > > >> + !PageDirty(page)) {
> > > > >> /* Invalidate as we cleared the pte */
> > > > >> mmu_notifier_invalidate_range(mm,
> > > > >> address, address + PAGE_SIZE);
> > > > >
> > > > > Out of curiosity, how does it work with COW in terms of reordering?
> > > > > Specifically, it seems to me get_page() and page_dup_rmap() in
> > > > > copy_present_pte() can happen in any order, and if page_dup_rmap()
> > > > > is seen first, and direct io is holding a refcnt, this check can still
> > > > > pass?
> > > >
> > > > I think that you are correct.
> > > >
> > > > After more thoughts, it appears very tricky to compare page count and
> > > > map count. Even if we have added smp_rmb() between page_ref_count() and
> > > > page_mapcount(), an interrupt may happen between them. During the
> > > > interrupt, the page count and map count may be changed, for example,
> > > > unmapped, or do_swap_page().
> > >
> > > Yeah, it happens but what specific problem are you concerning from the
> > > count change under race? The fork case Yu pointed out was already known
> > > for breaking DIO so user should take care not to fork under DIO(Please
> > > look at O_DIRECT section in man 2 open). If you could give a specific
> > > example, it would be great to think over the issue.
> > >
> > > I agree it's little tricky but it seems to be way other place has used
> > > for a long time(Please look at write_protect_page in ksm.c).
> >
> > Ah, that's great to see it's being used elsewhere, for DIO particularly!
> >
> > > So, here what we missing is tlb flush before the checking.
> >
> > That shouldn't be required for this particular issue/case, IIUIC.
> > One of the things we checked early on was disabling deferred TLB flush
> > (similarly to what you've done), and it didn't help with the issue; also, the
> > issue happens on uniprocessor mode too (thus no remote CPU involved.)
>
> I guess you didn't try it with page_mapcount + 1 == page_count at tha
> time? Anyway, I agree we don't need TLB flush here like KSM.
Sorry, I fail to understand how the page (map) count and TLB flush
would be related.
(I realize you and Yu Zhao already confirmed the TLB flush is not
needed/expected
to fix the issue too; but just for my own education, if you have a chance.)
> I think the reason KSM is doing TLB flush before the check it to
> make sure trap trigger on the write from userprocess in other core.
> However, this MADV_FREE case, HW already gaurantees the trap.
Understood.
> Please see below.
>
> >
> >
> > >
> > > Something like this.
> > >
> > > diff --git a/mm/rmap.c b/mm/rmap.c
> > > index b0fd9dc19eba..b4ad9faa17b2 100644
> > > --- a/mm/rmap.c
> > > +++ b/mm/rmap.c
> > > @@ -1599,18 +1599,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
> > >
> > > /* MADV_FREE page check */
> > > if (!PageSwapBacked(page)) {
> > > - int refcount = page_ref_count(page);
> > > -
> > > - /*
> > > - * The only page refs must be from the isolation
> > > - * (checked by the caller shrink_page_list() too)
> > > - * and the (single) rmap (dropped by discard:).
> > > - *
> > > - * Check the reference count before dirty flag
> > > - * with memory barrier; see __remove_mapping().
> > > - */
> > > - smp_rmb();
> > > - if (refcount == 2 && !PageDirty(page)) {
> > > + if (!PageDirty(page) &&
> > > + page_mapcount(page) + 1 == page_count(page)) {
> >
> > In the interest of avoiding a different race/bug, it seemed worth following the
> > suggestion outlined in __remove_mapping(), i.e., checking PageDirty()
> > after the page's reference count, with a memory barrier in between.
>
> True so it means your patch as-is is good for me.
That's good news! Thanks for all your help, review, and discussion so
far; it's been very educational.
I see Yu Zhao mentioned a possible concern/suggestion with additional
memory barriers elsewhere.
I'll try and dig to understand/check that in more detail and follow up.
>
> >
> > I'm not familiar with the details of the original issue behind that code change,
> > but it seemed to be possible here too, particularly as writes from user-space
> > can happen asynchronously / after try_to_unmap_one() checked PTE clean
> > and didn't set PageDirty, and if the page's PTE is present, there's no fault?
>
> Yeah, it was discussed.
>
> For clean pte, CPU has to fetch and update the actual pte entry, not TLB
> so trap triggers for MADV_FREE page.
>
> https://lkml.org/lkml/2015/4/15/565
> https://lkml.org/lkml/2015/4/16/136
Thanks for the pointers; great reading.
cheers,
--
Mauricio Faria de Oliveira
