Huang Ying <ying.huang@xxxxxxxxx> writes:
> This is a preparation patch to batch the folio unmapping and moving
> for the non-hugetlb folios. Based on that we can batch the TLB
> shootdown during the folio migration and make it possible to use some
> hardware accelerator for the folio copying.
>
> In this patch the hugetlb folios and non-hugetlb folios migration is
> separated in migrate_pages() to make it easy to change the non-hugetlb
> folios migration implementation.
>
> Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
> Cc: Zi Yan <ziy@xxxxxxxxxx>
> Cc: Yang Shi <shy828301@xxxxxxxxx>
> Cc: Baolin Wang <baolin.wang@xxxxxxxxxxxxxxxxx>
> Cc: Oscar Salvador <osalvador@xxxxxxx>
> Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
> Cc: Bharata B Rao <bharata@xxxxxxx>
> Cc: Alistair Popple <apopple@xxxxxxxxxx>
> Cc: haoxin <xhao@xxxxxxxxxxxxxxxxx>
> ---
> mm/migrate.c | 114 ++++++++++++++++++++++++++++++++++++++++++++-------
> 1 file changed, 99 insertions(+), 15 deletions(-)
>
> diff --git a/mm/migrate.c b/mm/migrate.c
> index ec9263a33d38..bdbe73fe2eb7 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -1404,6 +1404,87 @@ struct migrate_pages_stats {
> int nr_thp_split;
> };
>
> +static int migrate_hugetlbs(struct list_head *from, new_page_t get_new_page,
> + free_page_t put_new_page, unsigned long private,
> + enum migrate_mode mode, int reason,
> + struct migrate_pages_stats *stats,
> + struct list_head *ret_folios)
> +{
> + int retry = 1;
> + int nr_failed = 0;
> + int nr_retry_pages = 0;
> + int pass = 0;
> + struct folio *folio, *folio2;
> + int rc = 0, nr_pages;
> +
> + for (pass = 0; pass < 10 && retry; pass++) {
> + retry = 0;
> + nr_retry_pages = 0;
> +
> + list_for_each_entry_safe(folio, folio2, from, lru) {
> + if (!folio_test_hugetlb(folio))
> + continue;
> +
> + nr_pages = folio_nr_pages(folio);
> +
> + cond_resched();
> +
> + rc = unmap_and_move_huge_page(get_new_page,
> + put_new_page, private,
> + &folio->page, pass > 2, mode,
> + reason, ret_folios);
> + /*
> + * The rules are:
> + * Success: hugetlb folio will be put back
> + * -EAGAIN: stay on the from list
> + * -ENOMEM: stay on the from list
> + * -ENOSYS: stay on the from list
> + * Other errno: put on ret_folios list
> + */
> + switch(rc) {
> + case -ENOSYS:
> + /* Hugetlb migration is unsupported */
> + nr_failed++;
> + stats->nr_failed_pages += nr_pages;
> + list_move_tail(&folio->lru, ret_folios);
> + break;
> + case -ENOMEM:
> + /*
> + * When memory is low, don't bother to try to migrate
> + * other folios, just exit.
> + */
> + nr_failed++;
This currently isn't relevant for -ENOMEM and I think it would be
clearer if it was dropped.
> + stats->nr_failed_pages += nr_pages;
Makes sense not to continue migration with low memory, but shouldn't we
add the remaining unmigrated hugetlb folios to stats->nr_failed_pages as
well? Ie. don't we still have to continue the iteration to to find and
account for these?
> + goto out;
Given this is the only use of the out label, and that there is a special
case for -ENOMEM there anyway I think it would be clearer to return
directly.
> + case -EAGAIN:
> + retry++;
> + nr_retry_pages += nr_pages;
> + break;
> + case MIGRATEPAGE_SUCCESS:
> + stats->nr_succeeded += nr_pages;
> + break;
> + default:
> + /*
> + * Permanent failure (-EBUSY, etc.):
> + * unlike -EAGAIN case, the failed folio is
> + * removed from migration folio list and not
> + * retried in the next outer loop.
> + */
> + nr_failed++;
> + stats->nr_failed_pages += nr_pages;
> + break;
> + }
> + }
> + }
> +out:
> + nr_failed += retry;
> + stats->nr_failed_pages += nr_retry_pages;
> + if (rc != -ENOMEM)
> + rc = nr_failed;
> +
> + return rc;
> +}
> +
> /*
> * migrate_pages - migrate the folios specified in a list, to the free folios
> * supplied as the target for the page migration
> @@ -1437,7 +1518,7 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> int retry = 1;
> int large_retry = 1;
> int thp_retry = 1;
> - int nr_failed = 0;
> + int nr_failed;
> int nr_retry_pages = 0;
> int nr_large_failed = 0;
> int pass = 0;
> @@ -1454,6 +1535,12 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> trace_mm_migrate_pages_start(mode, reason);
>
> memset(&stats, 0, sizeof(stats));
> + rc = migrate_hugetlbs(from, get_new_page, put_new_page, private, mode, reason,
> + &stats, &ret_folios);
> + if (rc < 0)
> + goto out;
> + nr_failed = rc;
> +
> split_folio_migration:
> for (pass = 0; pass < 10 && (retry || large_retry); pass++) {
> retry = 0;
> @@ -1462,30 +1549,28 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> nr_retry_pages = 0;
>
> list_for_each_entry_safe(folio, folio2, from, lru) {
> + if (folio_test_hugetlb(folio)) {
How do we hit this case? Shouldn't migrate_hugetlbs() have already moved
any hugetlb folios off the from list?
> + list_move_tail(&folio->lru, &ret_folios);
> + continue;
> + }
> +
> /*
> * Large folio statistics is based on the source large
> * folio. Capture required information that might get
> * lost during migration.
> */
> - is_large = folio_test_large(folio) && !folio_test_hugetlb(folio);
> + is_large = folio_test_large(folio);
> is_thp = is_large && folio_test_pmd_mappable(folio);
> nr_pages = folio_nr_pages(folio);
> +
> cond_resched();
>
> - if (folio_test_hugetlb(folio))
> - rc = unmap_and_move_huge_page(get_new_page,
> - put_new_page, private,
> - &folio->page, pass > 2, mode,
> - reason,
> - &ret_folios);
> - else
> - rc = unmap_and_move(get_new_page, put_new_page,
> - private, folio, pass > 2, mode,
> - reason, &ret_folios);
> + rc = unmap_and_move(get_new_page, put_new_page,
> + private, folio, pass > 2, mode,
> + reason, &ret_folios);
> /*
> * The rules are:
> - * Success: non hugetlb folio will be freed, hugetlb
> - * folio will be put back
> + * Success: folio will be freed
> * -EAGAIN: stay on the from list
> * -ENOMEM: stay on the from list
> * -ENOSYS: stay on the from list
> @@ -1512,7 +1597,6 @@ int migrate_pages(struct list_head *from, new_page_t get_new_page,
> stats.nr_thp_split += is_thp;
> break;
> }
> - /* Hugetlb migration is unsupported */
> } else if (!no_split_folio_counting) {
> nr_failed++;
> }
