Re: [PATCH 2/5] mm: migrate: simplify the logic for handling permanent failure

[Yang Shi <shy828301@gmail.com>]

On Fri, Nov 6, 2020 at 12:03 PM Zi Yan <ziy@nvidia.com> wrote:
>
> On 3 Nov 2020, at 8:03, Yang Shi wrote:
>
> > When unmap_and_move{_huge_page}() returns !-EAGAIN and !MIGRATEPAGE_SUCCESS,
> > the page would be put back to LRU or proper list if it is non-LRU movable
> > page.  But, the callers always call putback_movable_pages() to put the
> > failed pages back later on, so it seems not very efficient to put every
> > single page back immediately, and the code looks convoluted.
> >
> > Put the failed page on a separate list, then splice the list to migrate
> > list when all pages are tried.  It is the caller's responsibility to
> > call putback_movable_pages() to handle failures.  This also makes the
> > code simpler and more readable.
> >
> > After the change the rules are:
> >     * Success: non hugetlb page will be freed, hugetlb page will be put
> >                back
> >     * -EAGAIN: stay on the from list
> >     * -ENOMEM: stay on the from list
> >     * Other errno: put on ret_pages list then splice to from list
>
> Can you put this before the switch case in the migrate_pages? That will
> be very helpful to understand the code.

Sure, I agree the switch case deserves some comments.

> >
> > The from list would be empty iff all pages are migrated successfully, it
>
> s/iff/if unless you really mean if and only if. :)

Yes, I mean if and only if.

>
>
> Everything else looks good to me. Thanks for making the code cleaner.
> With the changes above, you can add Reviewed-by: Zi Yan <ziy@nvidia.com>.

Thanks.

>
> > was not so before.  This has no impact to current existing callsites.
> >
> > Signed-off-by: Yang Shi <shy828301@gmail.com>
> > ---
> >  mm/migrate.c | 58 ++++++++++++++++++++++++++--------------------------
> >  1 file changed, 29 insertions(+), 29 deletions(-)
> >
> > diff --git a/mm/migrate.c b/mm/migrate.c
> > index 8a2e7e19e27b..c33c92495ead 100644
> > --- a/mm/migrate.c
> > +++ b/mm/migrate.c
> > @@ -1169,7 +1169,8 @@ static int unmap_and_move(new_page_t get_new_page,
> >                                  free_page_t put_new_page,
> >                                  unsigned long private, struct page *page,
> >                                  int force, enum migrate_mode mode,
> > -                                enum migrate_reason reason)
> > +                                enum migrate_reason reason,
> > +                                struct list_head *ret)
> >  {
> >       int rc = MIGRATEPAGE_SUCCESS;
> >       struct page *newpage = NULL;
> > @@ -1206,7 +1207,14 @@ static int unmap_and_move(new_page_t get_new_page,
> >                * migrated will have kept its references and be restored.
> >                */
> >               list_del(&page->lru);
> > +     }
> >
> > +     /*
> > +      * If migration is successful, releases reference grabbed during
> > +      * isolation. Otherwise, restore the page to right list unless
> > +      * we want to retry.
> > +      */
> > +     if (rc == MIGRATEPAGE_SUCCESS) {
> >               /*
> >                * Compaction can migrate also non-LRU pages which are
> >                * not accounted to NR_ISOLATED_*. They can be recognized
> > @@ -1215,35 +1223,16 @@ static int unmap_and_move(new_page_t get_new_page,
> >               if (likely(!__PageMovable(page)))
> >                       mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
> >                                       page_is_file_lru(page), -thp_nr_pages(page));
> > -     }
> >
> > -     /*
> > -      * If migration is successful, releases reference grabbed during
> > -      * isolation. Otherwise, restore the page to right list unless
> > -      * we want to retry.
> > -      */
> > -     if (rc == MIGRATEPAGE_SUCCESS) {
> >               if (reason != MR_MEMORY_FAILURE)
> >                       /*
> >                        * We release the page in page_handle_poison.
> >                        */
> >                       put_page(page);
> >       } else {
> > -             if (rc != -EAGAIN) {
> > -                     if (likely(!__PageMovable(page))) {
> > -                             putback_lru_page(page);
> > -                             goto put_new;
> > -                     }
> > +             if (rc != -EAGAIN)
> > +                     list_add_tail(&page->lru, ret);
> >
> > -                     lock_page(page);
> > -                     if (PageMovable(page))
> > -                             putback_movable_page(page);
> > -                     else
> > -                             __ClearPageIsolated(page);
> > -                     unlock_page(page);
> > -                     put_page(page);
> > -             }
> > -put_new:
> >               if (put_new_page)
> >                       put_new_page(newpage, private);
> >               else
> > @@ -1274,7 +1263,8 @@ static int unmap_and_move(new_page_t get_new_page,
> >  static int unmap_and_move_huge_page(new_page_t get_new_page,
> >                               free_page_t put_new_page, unsigned long private,
> >                               struct page *hpage, int force,
> > -                             enum migrate_mode mode, int reason)
> > +                             enum migrate_mode mode, int reason,
> > +                             struct list_head *ret)
> >  {
> >       int rc = -EAGAIN;
> >       int page_was_mapped = 0;
> > @@ -1290,7 +1280,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
> >        * kicking migration.
> >        */
> >       if (!hugepage_migration_supported(page_hstate(hpage))) {
> > -             putback_active_hugepage(hpage);
> > +             list_move_tail(&hpage->lru, ret);
> >               return -ENOSYS;
> >       }
> >
> > @@ -1372,8 +1362,10 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
> >  out_unlock:
> >       unlock_page(hpage);
> >  out:
> > -     if (rc != -EAGAIN)
> > +     if (rc == MIGRATEPAGE_SUCCESS)
> >               putback_active_hugepage(hpage);
> > +     else if (rc != -EAGAIN && rc != MIGRATEPAGE_SUCCESS)
> > +             list_move_tail(&hpage->lru, ret);
> >
> >       /*
> >        * If migration was not successful and there's a freeing callback, use
> > @@ -1404,8 +1396,8 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
> >   *
> >   * The function returns after 10 attempts or if no pages are movable any more
> >   * because the list has become empty or no retryable pages exist any more.
> > - * The caller should call putback_movable_pages() to return pages to the LRU
> > - * or free list only if ret != 0.
> > + * It is caller's responsibility to call putback_movable_pages() to return pages
> > + * to the LRU or free list only if ret != 0.
> >   *
> >   * Returns the number of pages that were not migrated, or an error code.
> >   */
> > @@ -1426,6 +1418,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> >       struct page *page2;
> >       int swapwrite = current->flags & PF_SWAPWRITE;
> >       int rc, nr_subpages;
> > +     LIST_HEAD(ret_pages);
> >
> >       if (!swapwrite)
> >               current->flags |= PF_SWAPWRITE;
> > @@ -1448,11 +1441,12 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> >                       if (PageHuge(page))
> >                               rc = unmap_and_move_huge_page(get_new_page,
> >                                               put_new_page, private, page,
> > -                                             pass > 2, mode, reason);
> > +                                             pass > 2, mode, reason,
> > +                                             &ret_pages);
> >                       else
> >                               rc = unmap_and_move(get_new_page, put_new_page,
> >                                               private, page, pass > 2, mode,
> > -                                             reason);
> > +                                             reason, &ret_pages);
> >
> >                       switch(rc) {
> >                       case -ENOMEM:
> > @@ -1519,6 +1513,12 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> >       nr_thp_failed += thp_retry;
> >       rc = nr_failed;
> >  out:
> > +     /*
> > +      * Put the permanent failure page back to migration list, they
> > +      * will be put back to the right list by the caller.
> > +      */
> > +     list_splice(&ret_pages, from);
> > +
> >       count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
> >       count_vm_events(PGMIGRATE_FAIL, nr_failed);
> >       count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
> > --
> > 2.26.2
>
>
> —
> Best Regards,
> Yan Zi