From 78b0ca26d00dfb585de60bdc79325d0c75c59b28 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Wed, 1 Jul 2026 07:06:38 -0700 Subject: [PATCH] mm/migrate_device: pin large folios before splitting migrate_vma_collect_pmd() can detect a large folio while holding the PTE lock, then drop the PTE lock before calling migrate_vma_split_folio(). The split helper took its own reference, but only after the lock had already been dropped. One way to hit this is device migration over a range that contains a large folio. The walker reads the PTE while holding the PTE lock and derives the folio either from a present PTE via vm_normal_page(), or from a non-present PTE that encodes a device-private softleaf entry. It then has to drop the PTE lock because split_folio() can block. Before migrate_vma_split_folio() gets a folio reference, concurrent reclaim, migration, or truncation can replace or clear the entry and drop the last reference to the folio. The split helper would then take a reference and lock on a stale folio pointer. Take a temporary reference before dropping the PTE lock and pass that reference into migrate_vma_split_folio(). The helper consumes the reference, so split_folio() still sees only the expected caller pin instead of an extra pin that could make the split fail. [usama.arif@linux.dev: condense comment about folio reference] Link: https://lore.kernel.org/87bbf335-648f-4065-abc8-3eaab5a3beeb@linux.dev Link: https://lore.kernel.org/20260701140638.840773-1-usama.arif@linux.dev Fixes: 022a12deda53 ("mm/migrate_device: handle partially mapped folios during collection") Signed-off-by: Usama Arif Reported-by: sashiko-bot Link: https://sashiko.dev/#/patchset/20260630164143.1595669-1-usama.arif%40linux.dev Acked-by: David Hildenbrand (Arm) Reviewed-by: Zi Yan Reviewed-by: Lance Yang Reviewed-by: SJ Park Cc: Alistair Popple Cc: Byungchul Park Cc: Gregory Price Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Joshua Hahn Cc: Matthew Brost Cc: Rakie Kim Cc: Shakeel Butt Signed-off-by: Andrew Morton --- mm/migrate_device.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/mm/migrate_device.c b/mm/migrate_device.c index e74fee90489a..2fffeb1f9969 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -77,6 +77,9 @@ static int migrate_vma_collect_hole(unsigned long start, * @folio: the folio to split * @fault_page: struct page associated with the fault if any * + * If @folio is not the folio containing @fault_page, the caller must hold a + * reference on @folio. The helper consumes that reference. + * * Returns 0 on success */ static int migrate_vma_split_folio(struct folio *folio, @@ -86,10 +89,8 @@ static int migrate_vma_split_folio(struct folio *folio, struct folio *fault_folio = fault_page ? page_folio(fault_page) : NULL; struct folio *new_fault_folio = NULL; - if (folio != fault_folio) { - folio_get(folio); + if (folio != fault_folio) folio_lock(folio); - } ret = split_folio(folio); if (ret) { @@ -310,6 +311,9 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, if (folio_test_large(folio)) { int ret; + /* migrate_vma_split_folio() consumes this reference */ + if (folio != fault_folio) + folio_get(folio); lazy_mmu_mode_disable(); pte_unmap_unlock(ptep, ptl); ret = migrate_vma_split_folio(folio, @@ -353,6 +357,9 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, if (folio && folio_test_large(folio)) { int ret; + /* migrate_vma_split_folio() consumes this reference */ + if (folio != fault_folio) + folio_get(folio); lazy_mmu_mode_disable(); pte_unmap_unlock(ptep, ptl); ret = migrate_vma_split_folio(folio,