From 854e5ff8b3ce2a776586cabebaeae645c992345b Mon Sep 17 00:00:00 2001 From: Kyle Zeng Date: Tue, 6 Oct 2026 21:10:01 -0700 Subject: [PATCH] mm/khugepaged: flush deferred unmaps before dropping a failed folio collapse_file() can fail its reference-count or dirty-folio check after unmapping with TTU_BATCH_FLUSH. Both paths put back the isolated folio, then unlock it and drop the lookup reference before reaching the common try_to_unmap_flush(). The page-cache reference does not keep the folio stable once the lock is released. Another collapse can replace and free it. With its PTEs already gone, that collapse cannot flush the first task's per-task TLB batch, and retract_page_tables() skips short or unaligned VMAs. A CPU can therefore retain a user translation to the freed folio. This has been reproduced with unprivileged MADV_COLLAPSE on a memfd. Flush at out_unlock while the lookup reference and folio lock are still held. The common flush continues to cover the accumulated pagelist on both success and rollback, preserving batching on successful collapses. Link: https://lore.kernel.org/20261007041001.43181-1-kylebot@openai.com Fixes: 6d9df8a5889c ("mm/thp: collapse_file() do try_to_unmap(TTU_BATCH_FLUSH)") Signed-off-by: Kyle Zeng Signed-off-by: Andrew Morton Acked-by: David Hildenbrand (Arm) Reviewed-by: Zi Yan Reviewed-by: Baolin Wang Acked-by: Hugh Dickins Assisted-by: LLM Cc: Barry Song Cc: Dev Jain Cc: Kiryl Shutsemau Cc: Lance Yang Cc: "Liam R. Howlett" Cc: Nico Pache Cc: Ryan Roberts Cc: Usama Arif Cc: Matthew Wilcox (Oracle) Cc: --- mm/khugepaged.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 4b71d010b2af..da91762f6358 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2467,6 +2467,11 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, index += folio_nr_pages(folio); continue; out_unlock: + /* + * The folio may have been unmapped with TTU_BATCH_FLUSH. + * Flush before releasing the lock and our last reference. + */ + try_to_unmap_flush(); folio_unlock(folio); folio_put(folio); goto xa_unlocked; @@ -2477,9 +2482,8 @@ static enum scan_result collapse_file(struct mm_struct *mm, unsigned long addr, xa_unlocked: /* - * If collapse is successful, flush must be done now before copying. - * If collapse is unsuccessful, does flush actually need to be done? - * Do it anyway, to clear the state. + * Flush before copying the folios, or releasing them in rollback. + * This is a no-op if out_unlock already flushed the batch. */ try_to_unmap_flush();