In the next commit we want to rearrange struct slab fields to allow a larger rcu_head. Afterwards, the page->mapping field will overlap with SLUB's "struct list_head slab_list", where the value of prev pointer can become LIST_POISON2, which is 0x122 + POISON_POINTER_DELTA. Unfortunately the bit 1 being set can confuse PageMovable() to be a false positive and cause a GPF as reported by lkp [1]. To fix this, make isolate_movable_page() skip pages with the PageSlab flag set. This is a bit tricky as we need to add memory barriers to SLAB and SLUB's page allocation and freeing, and their counterparts to isolate_movable_page(). Based on my RFC from [2]. Added a comment update from Matthew's variant in [3] and, as done there, moved the PageSlab checks to happen before trying to take the page lock. [1] https://lore.kernel.org/all/208c1757-5edd-fd42-67d4-1940cc43b50f@xxxxxxxxx/ [2] https://lore.kernel.org/all/aec59f53-0e53-1736-5932-25407125d4d4@xxxxxxx/ [3] https://lore.kernel.org/all/YzsVM8eToHUeTP75@xxxxxxxxxxxxxxxxxxxx/ Reported-by: kernel test robot <yujie.liu@xxxxxxxxx> Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx> --- mm/migrate.c | 15 ++++++++++++--- mm/slab.c | 6 +++++- mm/slub.c | 6 +++++- 3 files changed, 22 insertions(+), 5 deletions(-) diff --git a/mm/migrate.c b/mm/migrate.c index 1379e1912772..959c99cff814 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -74,13 +74,22 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode) if (unlikely(!get_page_unless_zero(page))) goto out; + if (unlikely(PageSlab(page))) + goto out_putpage; + /* Pairs with smp_wmb() in slab freeing, e.g. SLUB's __free_slab() */ + smp_rmb(); /* - * Check PageMovable before holding a PG_lock because page's owner - * assumes anybody doesn't touch PG_lock of newly allocated page - * so unconditionally grabbing the lock ruins page's owner side. + * Check movable flag before taking the page lock because + * we use non-atomic bitops on newly allocated page flags so + * unconditionally grabbing the lock ruins page's owner side. */ if (unlikely(!__PageMovable(page))) goto out_putpage; + /* Pairs with smp_wmb() in slab allocation, e.g. SLUB's alloc_slab_page() */ + smp_rmb(); + if (unlikely(PageSlab(page))) + goto out_putpage; + /* * As movable pages are not isolated from LRU lists, concurrent * compaction threads can race against page migration functions diff --git a/mm/slab.c b/mm/slab.c index 59c8e28f7b6a..219beb48588e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1370,6 +1370,8 @@ static struct slab *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, account_slab(slab, cachep->gfporder, cachep, flags); __folio_set_slab(folio); + /* Make the flag visible before any changes to folio->mapping */ + smp_wmb(); /* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */ if (sk_memalloc_socks() && page_is_pfmemalloc(folio_page(folio, 0))) slab_set_pfmemalloc(slab); @@ -1387,9 +1389,11 @@ static void kmem_freepages(struct kmem_cache *cachep, struct slab *slab) BUG_ON(!folio_test_slab(folio)); __slab_clear_pfmemalloc(slab); - __folio_clear_slab(folio); page_mapcount_reset(folio_page(folio, 0)); folio->mapping = NULL; + /* Make the mapping reset visible before clearing the flag */ + smp_wmb(); + __folio_clear_slab(folio); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += 1 << order; diff --git a/mm/slub.c b/mm/slub.c index 99ba865afc4a..5e6519d5169c 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1800,6 +1800,8 @@ static inline struct slab *alloc_slab_page(gfp_t flags, int node, slab = folio_slab(folio); __folio_set_slab(folio); + /* Make the flag visible before any changes to folio->mapping */ + smp_wmb(); if (page_is_pfmemalloc(folio_page(folio, 0))) slab_set_pfmemalloc(slab); @@ -2000,8 +2002,10 @@ static void __free_slab(struct kmem_cache *s, struct slab *slab) int pages = 1 << order; __slab_clear_pfmemalloc(slab); - __folio_clear_slab(folio); folio->mapping = NULL; + /* Make the mapping reset visible before clearing the flag */ + smp_wmb(); + __folio_clear_slab(folio); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += pages; unaccount_slab(slab, order, s); -- 2.38.0
