From 9f186f9e5fa9ebdaef909fd45f825a6ce281f13c Mon Sep 17 00:00:00 2001 From: Miaohe Lin Date: Thu, 19 May 2022 20:50:26 +0800 Subject: mm/swapfile: unuse_pte can map random data if swap read fails Patch series "A few fixup patches for mm", v4. This series contains a few patches to avoid mapping random data if swap read fails and fix lost swap bits in unuse_pte. Also we free hwpoison and swapin error entry in madvise_free_pte_range and so on. More details can be found in the respective changelogs. This patch (of 5): There is a bug in unuse_pte(): when swap page happens to be unreadable, page filled with random data is mapped into user address space. In case of error, a special swap entry indicating swap read fails is set to the page table. So the swapcache page can be freed and the user won't end up with a permanently mounted swap because a sector is bad. And if the page is accessed later, the user process will be killed so that corrupted data is never consumed. On the other hand, if the page is never accessed, the user won't even notice it. Link: https://lkml.kernel.org/r/20220519125030.21486-1-linmiaohe@huawei.com Link: https://lkml.kernel.org/r/20220519125030.21486-2-linmiaohe@huawei.com Signed-off-by: Miaohe Lin Acked-by: David Hildenbrand Cc: Hugh Dickins Cc: Matthew Wilcox (Oracle) Cc: Vlastimil Babka Cc: David Howells Cc: NeilBrown Cc: Alistair Popple Cc: Suren Baghdasaryan Cc: Peter Xu Cc: Ralph Campbell Cc: Naoya Horiguchi Signed-off-by: Andrew Morton --- include/linux/swap.h | 7 ++++++- include/linux/swapops.h | 10 ++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/swap.h b/include/linux/swap.h index f3ae17b43f20..0c0fed1b348f 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -55,6 +55,10 @@ static inline int current_is_kswapd(void) * actions on faults. */ +#define SWP_SWAPIN_ERROR_NUM 1 +#define SWP_SWAPIN_ERROR (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ + SWP_MIGRATION_NUM + SWP_DEVICE_NUM + \ + SWP_PTE_MARKER_NUM) /* * PTE markers are used to persist information onto PTEs that are mapped with * file-backed memories. As its name "PTE" hints, it should only be applied to @@ -120,7 +124,8 @@ static inline int current_is_kswapd(void) #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - SWP_PTE_MARKER_NUM) + SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ + SWP_PTE_MARKER_NUM - SWP_SWAPIN_ERROR_NUM) /* * Magic header for a swap area. The first part of the union is diff --git a/include/linux/swapops.h b/include/linux/swapops.h index fe220df499f1..f24775b41880 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -108,6 +108,16 @@ static inline void *swp_to_radix_entry(swp_entry_t entry) return xa_mk_value(entry.val); } +static inline swp_entry_t make_swapin_error_entry(struct page *page) +{ + return swp_entry(SWP_SWAPIN_ERROR, page_to_pfn(page)); +} + +static inline int is_swapin_error_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_SWAPIN_ERROR; +} + #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset) { -- cgit v1.2.3 From 1c563432588dbffa71e67ca6e37c826f9fa86e04 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Tue, 24 May 2022 10:15:25 -0700 Subject: mm: fix is_pinnable_page against a cma page Pages in the CMA area could have MIGRATE_ISOLATE as well as MIGRATE_CMA so the current is_pinnable_page() could miss CMA pages which have MIGRATE_ISOLATE. It ends up pinning CMA pages as longterm for the pin_user_pages() API so CMA allocations keep failing until the pin is released. CPU 0 CPU 1 - Task B cma_alloc alloc_contig_range pin_user_pages_fast(FOLL_LONGTERM) change pageblock as MIGRATE_ISOLATE internal_get_user_pages_fast lockless_pages_from_mm gup_pte_range try_grab_folio is_pinnable_page return true; So, pinned the page successfully. page migration failure with pinned page .. .. After 30 sec unpin_user_page(page) CMA allocation succeeded after 30 sec. The CMA allocation path protects the migration type change race using zone->lock but what GUP path need to know is just whether the page is on CMA area or not rather than exact migration type. Thus, we don't need zone->lock but just checks migration type in either of (MIGRATE_ISOLATE and MIGRATE_CMA). Adding the MIGRATE_ISOLATE check in is_pinnable_page could cause rejecting of pinning pages on MIGRATE_ISOLATE pageblocks even though it's neither CMA nor movable zone if the page is temporarily unmovable. However, such a migration failure by unexpected temporal refcount holding is general issue, not only come from MIGRATE_ISOLATE and the MIGRATE_ISOLATE is also transient state like other temporal elevated refcount problem. Link: https://lkml.kernel.org/r/20220524171525.976723-1-minchan@kernel.org Signed-off-by: Minchan Kim Reviewed-by: John Hubbard Acked-by: Paul E. McKenney Cc: David Hildenbrand Signed-off-by: Andrew Morton --- include/linux/mm.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index de32c0383387..93a46ff33dc2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1594,8 +1594,13 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma, #ifdef CONFIG_MIGRATION static inline bool is_pinnable_page(struct page *page) { - return !(is_zone_movable_page(page) || is_migrate_cma_page(page)) || - is_zero_pfn(page_to_pfn(page)); +#ifdef CONFIG_CMA + int mt = get_pageblock_migratetype(page); + + if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE) + return false; +#endif + return !(is_zone_movable_page(page) || is_zero_pfn(page_to_pfn(page))); } #else static inline bool is_pinnable_page(struct page *page) -- cgit v1.2.3