From b9f962e3b5c1106c115c8795b932aec920f5fb30 Mon Sep 17 00:00:00 2001 From: "Matthew Wilcox (Oracle)" Date: Thu, 21 Mar 2024 14:24:39 +0000 Subject: [PATCH] mm: always initialise folio->_deferred_list BugLink: https://bugs.launchpad.net/bugs/2100894 commit b7b098cf00a2b65d5654a86dc8edf82f125289c1 upstream. Patch series "Various significant MM patches". These patches all interact in annoying ways which make it tricky to send them out in any way other than a big batch, even though there's not really an overarching theme to connect them. The big effects of this patch series are: - folio_test_hugetlb() becomes reliable, even when called without a page reference - We free up PG_slab, and we could always use more page flags - We no longer need to check PageSlab before calling page_mapcount() This patch (of 9): For compound pages which are at least order-2 (and hence have a deferred_list), initialise it and then we can check at free that the page is not part of a deferred list. We recently found this useful to rule out a source of corruption. [peterx@redhat.com: always initialise folio->_deferred_list] Link: https://lkml.kernel.org/r/20240417211836.2742593-2-peterx@redhat.com Link: https://lkml.kernel.org/r/20240321142448.1645400-1-willy@infradead.org Link: https://lkml.kernel.org/r/20240321142448.1645400-2-willy@infradead.org Signed-off-by: Matthew Wilcox (Oracle) Signed-off-by: Peter Xu Reviewed-by: David Hildenbrand Acked-by: Vlastimil Babka Cc: Miaohe Lin Cc: Muchun Song Cc: Oscar Salvador Signed-off-by: Andrew Morton [ Include three small changes from the upstream commit, for backport safety: replace list_del() by list_del_init() in split_huge_page_to_list(), like c010d47f107f ("mm: thp: split huge page to any lower order pages"); replace list_del() by list_del_init() in folio_undo_large_rmappable(), like 9bcef5973e31 ("mm: memcg: fix split queue list crash when large folio migration"); keep __free_pages() instead of folio_put() in __update_and_free_hugetlb_folio(). ] Signed-off-by: Hugh Dickins Signed-off-by: Greg Kroah-Hartman Signed-off-by: Manuel Diewald Signed-off-by: Stefan Bader --- mm/huge_memory.c | 4 +--- mm/hugetlb.c | 1 + mm/internal.h | 2 ++ mm/memcontrol.c | 3 +++ mm/page_alloc.c | 9 +++++---- 5 files changed, 12 insertions(+), 7 deletions(-) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1cc741aae1be..f95bf807d8e1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -796,8 +796,6 @@ void folio_prep_large_rmappable(struct folio *folio) { if (!folio || !folio_test_large(folio)) return; - if (folio_order(folio) > 1) - INIT_LIST_HEAD(&folio->_deferred_list); folio_set_large_rmappable(folio); } @@ -3092,7 +3090,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (folio_order(folio) > 1 && !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; - list_del(&folio->_deferred_list); + list_del_init(&folio->_deferred_list); } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f08c0194c5d9..3c8b88a362f7 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1795,6 +1795,7 @@ static void __update_and_free_hugetlb_folio(struct hstate *h, destroy_compound_gigantic_folio(folio, huge_page_order(h)); free_gigantic_folio(folio, huge_page_order(h)); } else { + INIT_LIST_HEAD(&folio->_deferred_list); __free_pages(&folio->page, huge_page_order(h)); } } diff --git a/mm/internal.h b/mm/internal.h index 4bea1ca039d1..b88688d0d6af 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -431,6 +431,8 @@ static inline void prep_compound_head(struct page *page, unsigned int order) atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); + if (order > 1) + INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 92b4b6dd2517..f5d120356694 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -7460,6 +7460,9 @@ static void uncharge_folio(struct folio *folio, struct uncharge_gather *ug) struct obj_cgroup *objcg; VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); + VM_BUG_ON_FOLIO(folio_order(folio) > 1 && + !folio_test_hugetlb(folio) && + !list_empty(&folio->_deferred_list), folio); /* * Nobody should be changing or seriously looking at diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5c9af04b1453..10f2009cbb96 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1010,10 +1010,11 @@ static int free_tail_page_prepare(struct page *head_page, struct page *page) } break; case 2: - /* - * the second tail page: ->mapping is - * deferred_list.next -- ignore value. - */ + /* the second tail page: deferred_list overlaps ->mapping */ + if (unlikely(!list_empty(&folio->_deferred_list))) { + bad_page(page, "on deferred list"); + goto out; + } break; default: if (page->mapping != TAIL_MAPPING) {