mm: fix deferred split queue races during migration

migrate_folio_move() records the deferred split queue state from src and
replays it on dst.  Replaying it after remove_migration_ptes(src, dst, 0)
makes dst visible before it is requeued, so a concurrent rmap-removal path
can mark dst partially mapped and trip the WARN in deferred_split_folio().

Move the requeue before remove_migration_ptes() so dst is back on the
deferred split queue before it becomes visible again.

Because migration still holds dst locked at that point, teach
deferred_split_scan() to requeue a folio when folio_trylock() fails.
Otherwise a fully mapped underused folio can be dequeued by the shrinker
and silently lost from split_queue.

[ziy@nvidia.com: move the comment]
Link: https://lkml.kernel.org/r/FB71A764-0F10-4E5A-B4A0-BA4C7F138408@nvidia.com
Link: https://syzkaller.appspot.com/bug?extid=a7067a757858ac8eb085
Link: https://lkml.kernel.org/r/20260401131032.13011-1-lance.yang@linux.dev
Fixes: 8a8ca142a488 ("mm: migrate: requeue destination folio on deferred split queue")
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: syzbot+a7067a757858ac8eb085@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-mm/69ccb65b.050a0220.183828.003a.GAE@google.com/
Suggested-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Acked-by: Zi Yan <ziy@nvidia.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Byungchul Park <byungchul@sk.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: Deepanshu Kartikey <kartikey406@gmail.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Nico Pache <npache@redhat.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Ying Huang <ying.huang@linux.alibaba.com>
Cc: Usama Arif <usama.arif@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 745eb3d0d4a7867ece9e0d31879a17119f17e9b9..42c983821c03116464ce2872f7c67ef13b47730b 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -4542,7 +4542,7 @@ retry:
                                goto next;
                }
                if (!folio_trylock(folio))
-                       goto next;
+                       goto requeue;
                if (!split_folio(folio)) {
                        did_split = true;
                        if (underused)
@@ -4551,13 +4551,18 @@ retry:
                }
                folio_unlock(folio);
 next:
+               /*
+                * If thp_underused() returns false, or if split_folio()
+                * succeeds, or if split_folio() fails in the case it was
+                * underused, then consider it used and don't add it back to
+                * split_queue.
+                */
                if (did_split || !folio_test_partially_mapped(folio))
                        continue;
+requeue:
                /*
-                * Only add back to the queue if folio is partially mapped.
-                * If thp_underused returns false, or if split_folio fails
-                * in the case it was underused, then consider it used and
-                * don't add it back to split_queue.
+                * Add back partially mapped folios, or underused folios that
+                * we could not lock this round.
                 */
                fqueue = folio_split_queue_lock_irqsave(folio, &flags);
                if (list_empty(&folio->_deferred_list)) {

diff --git a/mm/migrate.c b/mm/migrate.c
index 4241eb6eca00fcd8e9ae7801d2f1b285ad1de918..76142a02192b2909fdc1fdcb3f2bca05b9f5f0dc 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1383,6 +1383,15 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
        if (rc)
                goto out;
 
+       /*
+        * Requeue the destination folio on the deferred split queue if
+        * the source was on the queue.  The source is unqueued in
+        * __folio_migrate_mapping(), so we recorded the state from
+        * before move_to_new_folio().
+        */
+       if (src_deferred_split)
+               deferred_split_folio(dst, src_partially_mapped);
+
        /*
         * When successful, push dst to LRU immediately: so that if it
         * turns out to be an mlocked page, remove_migration_ptes() will
@@ -1399,15 +1408,6 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
        if (old_page_state & PAGE_WAS_MAPPED)
                remove_migration_ptes(src, dst, 0);
 
-       /*
-        * Requeue the destination folio on the deferred split queue if
-        * the source was on the queue.  The source is unqueued in
-        * __folio_migrate_mapping(), so we recorded the state from
-        * before move_to_new_folio().
-        */
-       if (src_deferred_split)
-               deferred_split_folio(dst, src_partially_mapped);
-
 out_unlock_both:
        folio_unlock(dst);
        folio_set_owner_migrate_reason(dst, reason);