[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <878r8090tu.fsf@yhuang6-desk2.ccr.corp.intel.com>
Date: Wed, 18 Oct 2023 09:27:41 +0800
From: "Huang, Ying" <ying.huang@...el.com>
To: Zi Yan <zi.yan@...t.com>
Cc: linux-mm@...ck.org, linux-kernel@...r.kernel.org,
Zi Yan <ziy@...dia.com>,
Andrew Morton <akpm@...ux-foundation.org>,
"Matthew Wilcox (Oracle)" <willy@...radead.org>,
David Hildenbrand <david@...hat.com>,
Baolin Wang <baolin.wang@...ux.alibaba.com>
Subject: Re: [PATCH v3 1/2] mm/migrate: correct nr_failed in
migrate_pages_sync()
Zi Yan <zi.yan@...t.com> writes:
> From: Zi Yan <ziy@...dia.com>
>
> nr_failed was missing the large folio splits from migrate_pages_batch()
> and can cause a mismatch between migrate_pages() return value and the
> number of not migrated pages, i.e., when the return value of
> migrate_pages() is 0, there are still pages left in the from page list.
> It will happen when a non-PMD THP large folio fails to migrate due to
> -ENOMEM and is split successfully but not all the split pages are not
> migrated, migrate_pages_batch() would return non-zero, but
> astats.nr_thp_split = 0. nr_failed would be 0 and returned to the caller
> of migrate_pages(), but the not migrated pages are left in the from page
> list without being added back to LRU lists.
>
> Fix it by adding a new nr_split counter for large folio splits and adding
> it to nr_failed in migrate_page_sync() after migrate_pages_batch() is
> done.
>
> Fixes: 2ef7dbb26990 ("migrate_pages: try migrate in batch asynchronously firstly")
> Signed-off-by: Zi Yan <ziy@...dia.com>
> Cc: Baolin Wang <baolin.wang@...ux.alibaba.com>
> Cc: David Hildenbrand <david@...hat.com>
> Cc: Huang Ying <ying.huang@...el.com>
> Cc: Matthew Wilcox <willy@...radead.org>
LGTM except a trivial issue below, not a big deal. Thanks!
Reviewed-by: "Huang, Ying" <ying.huang@...el.com>
> ---
> mm/migrate.c | 16 +++++++++++++---
> 1 file changed, 13 insertions(+), 3 deletions(-)
>
> diff --git a/mm/migrate.c b/mm/migrate.c
> index c602bf6dec97..fc2e70b17704 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -1495,6 +1495,7 @@ struct migrate_pages_stats {
> int nr_thp_succeeded; /* THP migrated successfully */
> int nr_thp_failed; /* THP failed to be migrated */
> int nr_thp_split; /* THP split before migrating */
> + int nr_split; /* Large folio (include THP) split before migrating */
> };
>
> /*
> @@ -1614,6 +1615,7 @@ static int migrate_pages_batch(struct list_head *from,
> int nr_retry_pages = 0;
> int pass = 0;
> bool is_thp = false;
> + bool is_large = false;
> struct folio *folio, *folio2, *dst = NULL, *dst2;
> int rc, rc_saved = 0, nr_pages;
> LIST_HEAD(unmap_folios);
> @@ -1629,7 +1631,8 @@ static int migrate_pages_batch(struct list_head *from,
> nr_retry_pages = 0;
>
> list_for_each_entry_safe(folio, folio2, from, lru) {
> - is_thp = folio_test_large(folio) && folio_test_pmd_mappable(folio);
> + is_large = folio_test_large(folio);
> + is_thp = is_large && folio_test_pmd_mappable(folio);
> nr_pages = folio_nr_pages(folio);
>
> cond_resched();
> @@ -1649,6 +1652,7 @@ static int migrate_pages_batch(struct list_head *from,
> stats->nr_thp_failed++;
> if (!try_split_folio(folio, split_folios)) {
> stats->nr_thp_split++;
> + stats->nr_split++;
> continue;
> }
> stats->nr_failed_pages += nr_pages;
> @@ -1677,11 +1681,12 @@ static int migrate_pages_batch(struct list_head *from,
> nr_failed++;
> stats->nr_thp_failed += is_thp;
> /* Large folio NUMA faulting doesn't split to retry. */
> - if (folio_test_large(folio) && !nosplit) {
> + if (is_large && !nosplit) {
> int ret = try_split_folio(folio, split_folios);
>
> if (!ret) {
> stats->nr_thp_split += is_thp;
> + stats->nr_split += is_large;
We have tested is_large above, so, "++" is enough here. Not a big deal,
only change it if you think it's necessary.
> break;
> } else if (reason == MR_LONGTERM_PIN &&
> ret == -EAGAIN) {
> @@ -1827,6 +1832,7 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio,
> stats->nr_succeeded += astats.nr_succeeded;
> stats->nr_thp_succeeded += astats.nr_thp_succeeded;
> stats->nr_thp_split += astats.nr_thp_split;
> + stats->nr_split += astats.nr_split;
> if (rc < 0) {
> stats->nr_failed_pages += astats.nr_failed_pages;
> stats->nr_thp_failed += astats.nr_thp_failed;
> @@ -1834,7 +1840,11 @@ static int migrate_pages_sync(struct list_head *from, new_folio_t get_new_folio,
> return rc;
> }
> stats->nr_thp_failed += astats.nr_thp_split;
> - nr_failed += astats.nr_thp_split;
> + /*
> + * Do not count rc, as pages will be retried below.
> + * Count nr_split only, since it includes nr_thp_split.
> + */
> + nr_failed += astats.nr_split;
> /*
> * Fall back to migrate all failed folios one by one synchronously. All
> * failed folios except split THPs will be retried, so their failure
--
Best Regards,
Huang, Ying
Powered by blists - more mailing lists