Re: [PATCH v2 1/2] mm/migrate_device.c: Copy pte dirty bit to page

[Alistair Popple]

huang ying <huang.ying.caritas@xxxxxxxxx> writes:

> On Tue, Aug 16, 2022 at 3:39 PM Alistair Popple <apopple@xxxxxxxxxx> wrote:
>>
>> migrate_vma_setup() has a fast path in migrate_vma_collect_pmd() that
>> installs migration entries directly if it can lock the migrating page.
>> When removing a dirty pte the dirty bit is supposed to be carried over
>> to the underlying page to prevent it being lost.
>>
>> Currently migrate_vma_*() can only be used for private anonymous
>> mappings. That means loss of the dirty bit usually doesn't result in
>> data loss because these pages are typically not file-backed. However
>> pages may be backed by swap storage which can result in data loss if an
>> attempt is made to migrate a dirty page that doesn't yet have the
>> PageDirty flag set.
>>
>> In this case migration will fail due to unexpected references but the
>> dirty pte bit will be lost. If the page is subsequently reclaimed data
>> won't be written back to swap storage as it is considered uptodate,
>> resulting in data loss if the page is subsequently accessed.
>>
>> Prevent this by copying the dirty bit to the page when removing the pte
>> to match what try_to_migrate_one() does.
>>
>> Signed-off-by: Alistair Popple <apopple@xxxxxxxxxx>
>> Acked-by: Peter Xu <peterx@xxxxxxxxxx>
>> Reported-by: Huang Ying <ying.huang@xxxxxxxxx>
>> Fixes: 8c3328f1f36a ("mm/migrate: migrate_vma() unmap page from vma while collecting pages")
>> Cc: stable@xxxxxxxxxxxxxxx
>>
>> ---
>>
>> Changes for v2:
>>
>>  - Fixed up Reported-by tag.
>>  - Added Peter's Acked-by.
>>  - Atomically read and clear the pte to prevent the dirty bit getting
>>    set after reading it.
>>  - Added fixes tag
>> ---
>>  mm/migrate_device.c | 21 ++++++++-------------
>>  1 file changed, 8 insertions(+), 13 deletions(-)
>>
>> diff --git a/mm/migrate_device.c b/mm/migrate_device.c
>> index 27fb37d..e2d09e5 100644
>> --- a/mm/migrate_device.c
>> +++ b/mm/migrate_device.c
>> @@ -7,6 +7,7 @@
>>  #include <linux/export.h>
>>  #include <linux/memremap.h>
>>  #include <linux/migrate.h>
>> +#include <linux/mm.h>
>>  #include <linux/mm_inline.h>
>>  #include <linux/mmu_notifier.h>
>>  #include <linux/oom.h>
>> @@ -61,7 +62,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
>>         struct migrate_vma *migrate = walk->private;
>>         struct vm_area_struct *vma = walk->vma;
>>         struct mm_struct *mm = vma->vm_mm;
>> -       unsigned long addr = start, unmapped = 0;
>> +       unsigned long addr = start;
>>         spinlock_t *ptl;
>>         pte_t *ptep;
>>
>> @@ -193,11 +194,10 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
>>                         bool anon_exclusive;
>>                         pte_t swp_pte;
>>
>> +                       flush_cache_page(vma, addr, pte_pfn(*ptep));
>> +                       pte = ptep_clear_flush(vma, addr, ptep);
>
> Although I think it's possible to batch the TLB flushing just before
> unlocking PTL.  The current code looks correct.

I think you might be right but I'd rather deal with batch TLB flushing
as a separate change that implements it for normal migration as well
given we don't seem to do it there either.

> Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>

Thanks.

> Best Regards,
> Huang, Ying
>
>>                         anon_exclusive = PageAnon(page) && PageAnonExclusive(page);
>>                         if (anon_exclusive) {
>> -                               flush_cache_page(vma, addr, pte_pfn(*ptep));
>> -                               ptep_clear_flush(vma, addr, ptep);
>> -
>>                                 if (page_try_share_anon_rmap(page)) {
>>                                         set_pte_at(mm, addr, ptep, pte);
>>                                         unlock_page(page);
>> @@ -205,12 +205,14 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
>>                                         mpfn = 0;
>>                                         goto next;
>>                                 }
>> -                       } else {
>> -                               ptep_get_and_clear(mm, addr, ptep);
>>                         }
>>
>>                         migrate->cpages++;
>>
>> +                       /* Set the dirty flag on the folio now the pte is gone. */
>> +                       if (pte_dirty(pte))
>> +                               folio_mark_dirty(page_folio(page));
>> +
>>                         /* Setup special migration page table entry */
>>                         if (mpfn & MIGRATE_PFN_WRITE)
>>                                 entry = make_writable_migration_entry(
>> @@ -242,9 +244,6 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
>>                          */
>>                         page_remove_rmap(page, vma, false);
>>                         put_page(page);
>> -
>> -                       if (pte_present(pte))
>> -                               unmapped++;
>>                 } else {
>>                         put_page(page);
>>                         mpfn = 0;
>> @@ -257,10 +256,6 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp,
>>         arch_leave_lazy_mmu_mode();
>>         pte_unmap_unlock(ptep - 1, ptl);
>>
>> -       /* Only flush the TLB if we actually modified any entries */
>> -       if (unmapped)
>> -               flush_tlb_range(walk->vma, start, end);
>> -
>>         return 0;
>>  }
>>
>>
>> base-commit: ffcf9c5700e49c0aee42dcba9a12ba21338e8136
>> --
>> git-series 0.9.1
>>