diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 0795028f017c..35e9a468d13e 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -245,7 +245,7 @@ static inline struct folio *hugetlb_swap_entry_to_folio(swp_entry_t entry) { VM_BUG_ON(!is_migration_entry(entry) && !is_hwpoison_entry(entry)); - return page_folio(pfn_to_page(swp_offset(entry))); + return page_folio(pfn_to_page(swp_offset_pfn(entry))); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index e896ebef8c24..28421a887209 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -256,10 +256,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS) -#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) -#define __swp_type(x) (((x).val) & 0x1f) -#define __swp_offset(x) ((x).val >> 5) -#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << 5}) +#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) +#define __swp_type(x) (((x).val) & ((1UL << SWP_TYPE_BITS) - 1)) +#define __swp_offset(x) ((x).val >> SWP_TYPE_BITS) +#define __swp_entry(type, offset) ((swp_entry_t){(type) | (offset) << SWP_TYPE_BITS}) /* * Normally, __swp_entry() converts from arch-independent swp_entry_t to diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 82a042c03824..9121bc1b9453 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -1054,7 +1054,7 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache) } #ifdef CONFIG_SWAP -unsigned long max_swapfile_size(void) +unsigned long arch_max_swapfile_size(void) { unsigned long pages; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 482f91577f8c..db2f3a2946a0 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1418,9 +1418,19 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, if (pte_swp_uffd_wp(pte)) flags |= PM_UFFD_WP; entry = pte_to_swp_entry(pte); - if (pm->show_pfn) + if (pm->show_pfn) { + pgoff_t offset; + /* + * For PFN swap offsets, keeping the offset field + * to be PFN only to be compatible with old smaps. + */ + if (is_pfn_swap_entry(entry)) + offset = swp_offset_pfn(entry); + else + offset = swp_offset(entry); frame = swp_type(entry) | - (swp_offset(entry) << MAX_SWAPFILES_SHIFT); + (offset << MAX_SWAPFILES_SHIFT); + } flags |= PM_SWAP; migration = is_migration_entry(entry); if (is_pfn_swap_entry(entry)) @@ -1477,7 +1487,11 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned long offset; if (pm->show_pfn) { - offset = swp_offset(entry) + + if (is_pfn_swap_entry(entry)) + offset = swp_offset_pfn(entry); + else + offset = swp_offset(entry); + offset = offset + ((addr & ~PMD_MASK) >> PAGE_SHIFT); frame = swp_type(entry) | (offset << MAX_SWAPFILES_SHIFT); diff --git a/include/linux/mm.h b/include/linux/mm.h index e98ef2cb1176..8a5ad9d050bf 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2999,8 +2999,8 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * PageAnonExclusive() has to protect against concurrent GUP: * * Ordinary GUP: Using the PT lock * * GUP-fast and fork(): mm->write_protect_seq - * * GUP-fast and KSM or temporary unmapping (swap, migration): - * clear/invalidate+flush of the page table entry + * * GUP-fast and KSM or temporary unmapping (swap, migration): see + * page_try_share_anon_rmap() * * Must be called with the (sub)page that's actually referenced via the * page table entry, which might not necessarily be the head page for a @@ -3021,6 +3021,11 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) */ if (!PageAnon(page)) return false; + + /* Paired with a memory barrier in page_try_share_anon_rmap(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_rmb(); + /* * Note that PageKsm() pages cannot be exclusive, and consequently, * cannot get pinned. diff --git a/include/linux/rmap.h b/include/linux/rmap.h index b89b4b86951f..4a6865e795c7 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -270,7 +270,7 @@ static inline int page_try_dup_anon_rmap(struct page *page, bool compound, * @page: the exclusive anonymous page to try marking possibly shared * * The caller needs to hold the PT lock and has to have the page table entry - * cleared/invalidated+flushed, to properly sync against GUP-fast. + * cleared/invalidated. * * This is similar to page_try_dup_anon_rmap(), however, not used during fork() * to duplicate a mapping, but instead to prepare for KSM or temporarily @@ -286,12 +286,68 @@ static inline int page_try_share_anon_rmap(struct page *page) { VM_BUG_ON_PAGE(!PageAnon(page) || !PageAnonExclusive(page), page); - /* See page_try_dup_anon_rmap(). */ - if (likely(!is_device_private_page(page) && - unlikely(page_maybe_dma_pinned(page)))) - return -EBUSY; + /* device private pages cannot get pinned via GUP. */ + if (unlikely(is_device_private_page(page))) { + ClearPageAnonExclusive(page); + return 0; + } + /* + * We have to make sure that when we clear PageAnonExclusive, that + * the page is not pinned and that concurrent GUP-fast won't succeed in + * concurrently pinning the page. + * + * Conceptually, PageAnonExclusive clearing consists of: + * (A1) Clear PTE + * (A2) Check if the page is pinned; back off if so. + * (A3) Clear PageAnonExclusive + * (A4) Restore PTE (optional, but certainly not writable) + * + * When clearing PageAnonExclusive, we cannot possibly map the page + * writable again, because anon pages that may be shared must never + * be writable. So in any case, if the PTE was writable it cannot + * be writable anymore afterwards and there would be a PTE change. Only + * if the PTE wasn't writable, there might not be a PTE change. + * + * Conceptually, GUP-fast pinning of an anon page consists of: + * (B1) Read the PTE + * (B2) FOLL_WRITE: check if the PTE is not writable; back off if so. + * (B3) Pin the mapped page + * (B4) Check if the PTE changed by re-reading it; back off if so. + * (B5) If the original PTE is not writable, check if + * PageAnonExclusive is not set; back off if so. + * + * If the PTE was writable, we only have to make sure that GUP-fast + * observes a PTE change and properly backs off. + * + * If the PTE was not writable, we have to make sure that GUP-fast either + * detects a (temporary) PTE change or that PageAnonExclusive is cleared + * and properly backs off. + * + * Consequently, when clearing PageAnonExclusive(), we have to make + * sure that (A1), (A2)/(A3) and (A4) happen in the right memory + * order. In GUP-fast pinning code, we have to make sure that (B3),(B4) + * and (B5) happen in the right memory order. + * + * We assume that there might not be a memory barrier after + * clearing/invalidating the PTE (A1) and before restoring the PTE (A4), + * so we use explicit ones here. + */ + + /* Paired with the memory barrier in try_grab_folio(). */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb(); + + if (unlikely(page_maybe_dma_pinned(page))) + return -EBUSY; ClearPageAnonExclusive(page); + + /* + * This is conceptually a smp_wmb() paired with the smp_rmb() in + * gup_must_unshare(). + */ + if (IS_ENABLED(CONFIG_HAVE_FAST_GUP)) + smp_mb__after_atomic(); return 0; } diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h index 54078542134c..7ed529a77c5b 100644 --- a/include/linux/swapfile.h +++ b/include/linux/swapfile.h @@ -8,6 +8,11 @@ */ extern struct swap_info_struct *swap_info[]; extern unsigned long generic_max_swapfile_size(void); -extern unsigned long max_swapfile_size(void); +unsigned long arch_max_swapfile_size(void); + +/* Maximum swapfile size supported for the arch (not inclusive). */ +extern unsigned long swapfile_maximum_size; +/* Whether swap migration entry supports storing A/D bits for the arch */ +extern bool swap_migration_ad_supported; #endif /* _LINUX_SWAPFILE_H */ diff --git a/include/linux/swapops.h b/include/linux/swapops.h index a3d435bf9f97..86b95ccb81bb 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -8,6 +8,10 @@ #ifdef CONFIG_MMU +#ifdef CONFIG_SWAP +#include +#endif /* CONFIG_SWAP */ + /* * swapcache pages are stored in the swapper_space radix tree. We want to * get good packing density in that tree, so the index should be dense in @@ -23,6 +27,45 @@ #define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) #define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) +/* + * Definitions only for PFN swap entries (see is_pfn_swap_entry()). To + * store PFN, we only need SWP_PFN_BITS bits. Each of the pfn swap entries + * can use the extra bits to store other information besides PFN. + */ +#ifdef MAX_PHYSMEM_BITS +#define SWP_PFN_BITS (MAX_PHYSMEM_BITS - PAGE_SHIFT) +#else /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_BITS (BITS_PER_LONG - PAGE_SHIFT) +#endif /* MAX_PHYSMEM_BITS */ +#define SWP_PFN_MASK (BIT(SWP_PFN_BITS) - 1) + +/** + * Migration swap entry specific bitfield definitions. Layout: + * + * |----------+--------------------| + * | swp_type | swp_offset | + * |----------+--------+-+-+-------| + * | | resv |D|A| PFN | + * |----------+--------+-+-+-------| + * + * @SWP_MIG_YOUNG_BIT: Whether the page used to have young bit set (bit A) + * @SWP_MIG_DIRTY_BIT: Whether the page used to have dirty bit set (bit D) + * + * Note: A/D bits will be stored in migration entries iff there're enough + * free bits in arch specific swp offset. By default we'll ignore A/D bits + * when migrating a page. Please refer to migration_entry_supports_ad() + * for more information. If there're more bits besides PFN and A/D bits, + * they should be reserved and always be zeros. + */ +#define SWP_MIG_YOUNG_BIT (SWP_PFN_BITS) +#define SWP_MIG_DIRTY_BIT (SWP_PFN_BITS + 1) +#define SWP_MIG_TOTAL_BITS (SWP_PFN_BITS + 2) + +#define SWP_MIG_YOUNG BIT(SWP_MIG_YOUNG_BIT) +#define SWP_MIG_DIRTY BIT(SWP_MIG_DIRTY_BIT) + +static inline bool is_pfn_swap_entry(swp_entry_t entry); + /* Clear all flags but only keep swp_entry_t related information */ static inline pte_t pte_swp_clear_flags(pte_t pte) { @@ -64,6 +107,17 @@ static inline pgoff_t swp_offset(swp_entry_t entry) return entry.val & SWP_OFFSET_MASK; } +/* + * This should only be called upon a pfn swap entry to get the PFN stored + * in the swap entry. Please refers to is_pfn_swap_entry() for definition + * of pfn swap entry. + */ +static inline unsigned long swp_offset_pfn(swp_entry_t entry) +{ + VM_BUG_ON(!is_pfn_swap_entry(entry)); + return swp_offset(entry) & SWP_PFN_MASK; +} + /* check whether a pte points to a swap entry */ static inline int is_swap_pte(pte_t pte) { @@ -240,6 +294,52 @@ static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) return swp_entry(SWP_MIGRATION_WRITE, offset); } +/* + * Returns whether the host has large enough swap offset field to support + * carrying over pgtable A/D bits for page migrations. The result is + * pretty much arch specific. + */ +static inline bool migration_entry_supports_ad(void) +{ +#ifdef CONFIG_SWAP + return swap_migration_ad_supported; +#else /* CONFIG_SWAP */ + return false; +#endif /* CONFIG_SWAP */ +} + +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_YOUNG); + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_YOUNG; + /* Keep the old behavior of aging page after migration */ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_entry(swp_type(entry), + swp_offset(entry) | SWP_MIG_DIRTY); + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + if (migration_entry_supports_ad()) + return swp_offset(entry) & SWP_MIG_DIRTY; + /* Keep the old behavior of clean page after migration */ + return false; +} + extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, @@ -247,8 +347,8 @@ extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, #ifdef CONFIG_HUGETLB_PAGE extern void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl); extern void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte); -#endif -#else +#endif /* CONFIG_HUGETLB_PAGE */ +#else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -276,7 +376,7 @@ static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, #ifdef CONFIG_HUGETLB_PAGE static inline void __migration_entry_wait_huge(pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait_huge(struct vm_area_struct *vma, pte_t *pte) { } -#endif +#endif /* CONFIG_HUGETLB_PAGE */ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; @@ -286,7 +386,26 @@ static inline int is_readable_migration_entry(swp_entry_t entry) return 0; } -#endif +static inline swp_entry_t make_migration_entry_young(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_young(swp_entry_t entry) +{ + return false; +} + +static inline swp_entry_t make_migration_entry_dirty(swp_entry_t entry) +{ + return entry; +} + +static inline bool is_migration_entry_dirty(swp_entry_t entry) +{ + return false; +} +#endif /* CONFIG_MIGRATION */ typedef unsigned long pte_marker; @@ -369,7 +488,7 @@ static inline int pte_none_mostly(pte_t pte) static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) { - struct page *p = pfn_to_page(swp_offset(entry)); + struct page *p = pfn_to_page(swp_offset_pfn(entry)); /* * Any use of migration entries may only occur while the @@ -387,6 +506,9 @@ static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry) */ static inline bool is_pfn_swap_entry(swp_entry_t entry) { + /* Make sure the swp offset can always store the needed fields */ + BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS); + return is_migration_entry(entry) || is_device_private_entry(entry) || is_device_exclusive_entry(entry); } @@ -426,7 +548,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) { return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } -#else +#else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { @@ -455,7 +577,7 @@ static inline int is_pmd_migration_entry(pmd_t pmd) { return 0; } -#endif +#endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ #ifdef CONFIG_MEMORY_FAILURE @@ -475,27 +597,17 @@ static inline int is_hwpoison_entry(swp_entry_t entry) return swp_type(entry) == SWP_HWPOISON; } -static inline unsigned long hwpoison_entry_to_pfn(swp_entry_t entry) -{ - return swp_offset(entry); -} - static inline void num_poisoned_pages_inc(void) { atomic_long_inc(&num_poisoned_pages); } -static inline void num_poisoned_pages_dec(void) -{ - atomic_long_dec(&num_poisoned_pages); -} - static inline void num_poisoned_pages_sub(long i) { atomic_long_sub(i, &num_poisoned_pages); } -#else +#else /* CONFIG_MEMORY_FAILURE */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { @@ -514,7 +626,7 @@ static inline void num_poisoned_pages_inc(void) static inline void num_poisoned_pages_sub(long i) { } -#endif +#endif /* CONFIG_MEMORY_FAILURE */ static inline int non_swap_entry(swp_entry_t entry) { diff --git a/mm/gup.c b/mm/gup.c index 9e9b17c42f3a..d4f706dc245f 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -158,6 +158,13 @@ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) else folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1)); + /* + * Adjust the pincount before re-checking the PTE for changes. + * This is essentially a smp_mb() and is paired with a memory + * barrier in page_try_share_anon_rmap(). + */ + smp_mb__after_atomic(); + node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); return folio; diff --git a/mm/hmm.c b/mm/hmm.c index f2aa63b94d9b..3850fb625dda 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -253,7 +253,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, cpu_flags = HMM_PFN_VALID; if (is_writable_device_private_entry(entry)) cpu_flags |= HMM_PFN_WRITE; - *hmm_pfn = swp_offset(entry) | cpu_flags; + *hmm_pfn = swp_offset_pfn(entry) | cpu_flags; return 0; } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ce025f95aa8c..f4a656b279b1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2037,7 +2037,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pgtable_t pgtable; pmd_t old_pmd, _pmd; bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false; - bool anon_exclusive = false; + bool anon_exclusive = false, dirty = false; unsigned long addr; int i; @@ -2121,13 +2121,16 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, write = is_writable_migration_entry(entry); if (PageAnon(page)) anon_exclusive = is_readable_exclusive_migration_entry(entry); - young = false; + young = is_migration_entry_young(entry); + dirty = is_migration_entry_dirty(entry); soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { page = pmd_page(old_pmd); - if (pmd_dirty(old_pmd)) + if (pmd_dirty(old_pmd)) { + dirty = true; SetPageDirty(page); + } write = pmd_write(old_pmd); young = pmd_young(old_pmd); soft_dirty = pmd_soft_dirty(old_pmd); @@ -2148,6 +2151,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, * * In case we cannot clear PageAnonExclusive(), split the PMD * only and let try_to_migrate_one() fail later. + * + * See page_try_share_anon_rmap(): invalidate PMD first. */ anon_exclusive = PageAnon(page) && PageAnonExclusive(page); if (freeze && anon_exclusive && page_try_share_anon_rmap(page)) @@ -2179,6 +2184,10 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, else swp_entry = make_readable_migration_entry( page_to_pfn(page + i)); + if (young) + swp_entry = make_migration_entry_young(swp_entry); + if (dirty) + swp_entry = make_migration_entry_dirty(swp_entry); entry = swp_entry_to_pte(swp_entry); if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); @@ -2193,6 +2202,9 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, entry = pte_wrprotect(entry); if (!young) entry = pte_mkold(entry); + /* NOTE: this may set soft-dirty too on some archs */ + if (dirty) + entry = pte_mkdirty(entry); if (soft_dirty) entry = pte_mksoft_dirty(entry); if (uffd_wp) @@ -3179,6 +3191,7 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = pmdp_invalidate(vma, address, pvmw->pmd); + /* See page_try_share_anon_rmap(): invalidate PMD first. */ anon_exclusive = PageAnon(page) && PageAnonExclusive(page); if (anon_exclusive && page_try_share_anon_rmap(page)) { set_pmd_at(mm, address, pvmw->pmd, pmdval); @@ -3193,6 +3206,10 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); else entry = make_readable_migration_entry(page_to_pfn(page)); + if (pmd_young(pmdval)) + entry = make_migration_entry_young(entry); + if (pmd_dirty(pmdval)) + entry = make_migration_entry_dirty(entry); pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); @@ -3218,13 +3235,18 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) entry = pmd_to_swp_entry(*pvmw->pmd); get_page(new); - pmde = pmd_mkold(mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot))); + pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (is_writable_migration_entry(entry)) pmde = maybe_pmd_mkwrite(pmde, vma); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); + if (!is_migration_entry_young(entry)) + pmde = pmd_mkold(pmde); + /* NOTE: this may contain setting soft-dirty on some archs */ + if (PageDirty(new) && is_migration_entry_dirty(entry)) + pmde = pmd_mkdirty(pmde); if (PageAnon(new)) { rmap_t rmap_flags = RMAP_COMPOUND; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 28448e2234cc..d3533a1a0b46 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -2438,6 +2438,8 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, last_fail = result; goto out_nolock; } + + hend = vma->vm_end & HPAGE_PMD_MASK; } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 1eddc0132f7f..37af2dc8dac9 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -604,9 +604,8 @@ static int __save_stack_trace(unsigned long *trace) * memory block and add it to the object_list and object_tree_root (or * object_phys_tree_root). */ -static struct kmemleak_object *__create_object(unsigned long ptr, size_t size, - int min_count, gfp_t gfp, - bool is_phys) +static void __create_object(unsigned long ptr, size_t size, + int min_count, gfp_t gfp, bool is_phys) { unsigned long flags; struct kmemleak_object *object, *parent; @@ -618,7 +617,7 @@ static struct kmemleak_object *__create_object(unsigned long ptr, size_t size, if (!object) { pr_warn("Cannot allocate a kmemleak_object structure\n"); kmemleak_disable(); - return NULL; + return; } INIT_LIST_HEAD(&object->object_list); @@ -687,7 +686,6 @@ static struct kmemleak_object *__create_object(unsigned long ptr, size_t size, */ dump_object_info(parent); kmem_cache_free(object_cache, object); - object = NULL; goto out; } } @@ -698,21 +696,20 @@ static struct kmemleak_object *__create_object(unsigned long ptr, size_t size, list_add_tail_rcu(&object->object_list, &object_list); out: raw_spin_unlock_irqrestore(&kmemleak_lock, flags); - return object; } /* Create kmemleak object which allocated with virtual address. */ -static struct kmemleak_object *create_object(unsigned long ptr, size_t size, - int min_count, gfp_t gfp) +static void create_object(unsigned long ptr, size_t size, + int min_count, gfp_t gfp) { - return __create_object(ptr, size, min_count, gfp, false); + __create_object(ptr, size, min_count, gfp, false); } /* Create kmemleak object which allocated with physical address. */ -static struct kmemleak_object *create_object_phys(unsigned long ptr, size_t size, - int min_count, gfp_t gfp) +static void create_object_phys(unsigned long ptr, size_t size, + int min_count, gfp_t gfp) { - return __create_object(ptr, size, min_count, gfp, true); + __create_object(ptr, size, min_count, gfp, true); } /* diff --git a/mm/ksm.c b/mm/ksm.c index 2f315c69fa2c..fd6d03cb0463 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -1095,6 +1095,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page, goto out_unlock; } + /* See page_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && page_try_share_anon_rmap(page)) { set_pte_at(mm, pvmw.address, pvmw.pte, entry); goto out_unlock; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 265378237c22..e554f9f583ca 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -277,7 +277,7 @@ static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags) * to SIG_IGN, but hopefully no one will do that? */ ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr, - addr_lsb, t); /* synchronous? */ + addr_lsb, t); if (ret < 0) pr_info("Error sending signal to %s:%d: %d\n", t->comm, t->pid, ret); @@ -521,11 +521,11 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill, anon_vma_interval_tree_foreach(vmac, &av->rb_root, pgoff, pgoff) { vma = vmac->vma; + if (vma->vm_mm != t->mm) + continue; if (!page_mapped_in_vma(page, vma)) continue; - if (vma->vm_mm == t->mm) - add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, - to_kill); + add_to_kill(t, page, FSDAX_INVALID_PGOFF, vma, to_kill); } } read_unlock(&tasklist_lock); @@ -635,7 +635,7 @@ static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, swp_entry_t swp = pte_to_swp_entry(pte); if (is_hwpoison_entry(swp)) - pfn = hwpoison_entry_to_pfn(swp); + pfn = swp_offset_pfn(swp); } if (!pfn || pfn != poisoned_pfn) @@ -1249,9 +1249,9 @@ static int __get_hwpoison_page(struct page *page, unsigned long flags) return ret; /* - * This check prevents from calling get_hwpoison_unless_zero() - * for any unsupported type of page in order to reduce the risk of - * unexpected races caused by taking a page refcount. + * This check prevents from calling get_page_unless_zero() for any + * unsupported type of page in order to reduce the risk of unexpected + * races caused by taking a page refcount. */ if (!HWPoisonHandlable(head, flags)) return -EBUSY; @@ -1409,7 +1409,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * Here we are interested only in user-mapped pages, so skip any * other types of pages. */ - if (PageReserved(p) || PageSlab(p)) + if (PageReserved(p) || PageSlab(p) || PageTable(p)) return true; if (!(PageLRU(hpage) || PageHuge(p))) return true; @@ -2028,7 +2028,7 @@ int memory_failure(unsigned long pfn, int flags) /* * We need/can do nothing about count=0 pages. * 1) it's a free page, and therefore in safe hand: - * prep_new_page() will be the gate keeper. + * check_new_page() will be the gate keeper. * 2) it's part of a non-compound high order page. * Implies some kernel user: cannot stop them from * R/W the page; let's pray that the page has been @@ -2131,7 +2131,7 @@ int memory_failure(unsigned long pfn, int flags) page_flags = p->flags; if (hwpoison_filter(p)) { - TestClearPageHWPoison(p); + ClearPageHWPoison(p); unlock_page(p); put_page(p); res = -EOPNOTSUPP; @@ -2407,24 +2407,26 @@ EXPORT_SYMBOL(unpoison_memory); static bool isolate_page(struct page *page, struct list_head *pagelist) { bool isolated = false; - bool lru = PageLRU(page); if (PageHuge(page)) { isolated = !isolate_hugetlb(page, pagelist); } else { + bool lru = !__PageMovable(page); + if (lru) isolated = !isolate_lru_page(page); else - isolated = !isolate_movable_page(page, ISOLATE_UNEVICTABLE); + isolated = !isolate_movable_page(page, + ISOLATE_UNEVICTABLE); - if (isolated) + if (isolated) { list_add(&page->lru, pagelist); + if (lru) + inc_node_page_state(page, NR_ISOLATED_ANON + + page_is_file_lru(page)); + } } - if (isolated && lru) - inc_node_page_state(page, NR_ISOLATED_ANON + - page_is_file_lru(page)); - /* * If we succeed to isolate the page, we grabbed another refcount on * the page, so we can safely drop the one we got from get_any_pages(). @@ -2600,7 +2602,7 @@ int soft_offline_page(unsigned long pfn, int flags) void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) { - int i; + int i, total = 0; /* * A further optimization is to have per section refcounted @@ -2613,8 +2615,10 @@ void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) for (i = 0; i < nr_pages; i++) { if (PageHWPoison(&memmap[i])) { - num_poisoned_pages_dec(); + total++; ClearPageHWPoison(&memmap[i]); } } + if (total) + num_poisoned_pages_sub(total); } diff --git a/mm/memremap.c b/mm/memremap.c index 58b20c3c300b..25029a474d30 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -454,7 +454,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, /* fall back to slow path lookup */ rcu_read_lock(); pgmap = xa_load(&pgmap_array, PHYS_PFN(phys)); - if (pgmap && !percpu_ref_tryget_live(&pgmap->ref)) + if (pgmap && !percpu_ref_tryget_live_rcu(&pgmap->ref)) pgmap = NULL; rcu_read_unlock(); diff --git a/mm/migrate.c b/mm/migrate.c index ce6a58f3b21f..a35eba462e61 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -198,7 +198,7 @@ static bool remove_migration_pte(struct folio *folio, #endif folio_get(folio); - pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot))); + pte = mk_pte(new, READ_ONCE(vma->vm_page_prot)); if (pte_swp_soft_dirty(*pvmw.pte)) pte = pte_mksoft_dirty(pte); @@ -206,6 +206,10 @@ static bool remove_migration_pte(struct folio *folio, * Recheck VMA as permissions can change since migration started */ entry = pte_to_swp_entry(*pvmw.pte); + if (!is_migration_entry_young(entry)) + pte = pte_mkold(pte); + if (folio_test_dirty(folio) && is_migration_entry_dirty(entry)) + pte = pte_mkdirty(pte); if (is_writable_migration_entry(entry)) pte = maybe_mkwrite(pte, vma); else if (pte_swp_uffd_wp(*pvmw.pte)) diff --git a/mm/migrate_device.c b/mm/migrate_device.c index d8efd5a0eb40..5ab6ab9d2ed8 100644 --- a/mm/migrate_device.c +++ b/mm/migrate_device.c @@ -233,6 +233,12 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, else entry = make_readable_migration_entry( page_to_pfn(page)); + if (pte_present(pte)) { + if (pte_young(pte)) + entry = make_migration_entry_young(entry); + if (pte_dirty(pte)) + entry = make_migration_entry_dirty(entry); + } swp_pte = swp_entry_to_pte(entry); if (pte_present(pte)) { if (pte_soft_dirty(pte)) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 65fba92d6676..3062a0342021 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3600,16 +3600,11 @@ EXPORT_SYMBOL_GPL(split_page); int __isolate_free_page(struct page *page, unsigned int order) { - unsigned long watermark; - struct zone *zone; - int mt; - - BUG_ON(!PageBuddy(page)); - - zone = page_zone(page); - mt = get_pageblock_migratetype(page); + struct zone *zone = page_zone(page); + int mt = get_pageblock_migratetype(page); if (!is_migrate_isolate(mt)) { + unsigned long watermark; /* * Obey watermarks as if the page was being allocated. We can * emulate a high-order watermark check with a raised order-0 @@ -3623,8 +3618,6 @@ int __isolate_free_page(struct page *page, unsigned int order) __mod_zone_freepage_state(zone, -(1UL << order), mt); } - /* Remove page from free list */ - del_page_from_free_list(page, zone, order); /* @@ -3645,7 +3638,6 @@ int __isolate_free_page(struct page *page, unsigned int order) } } - return 1UL << order; } diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index 8e9e574d535a..93e13fc17d3c 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -86,7 +86,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) !is_device_exclusive_entry(entry)) return false; - pfn = swp_offset(entry); + pfn = swp_offset_pfn(entry); } else if (is_swap_pte(*pvmw->pte)) { swp_entry_t entry; @@ -96,7 +96,7 @@ static bool check_pte(struct page_vma_mapped_walk *pvmw) !is_device_exclusive_entry(entry)) return false; - pfn = swp_offset(entry); + pfn = swp_offset_pfn(entry); } else { if (!pte_present(*pvmw->pte)) return false; @@ -221,7 +221,7 @@ bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw) return not_found(pvmw); entry = pmd_to_swp_entry(pmde); if (!is_migration_entry(entry) || - !check_pmd(swp_offset(entry), pvmw)) + !check_pmd(swp_offset_pfn(entry), pvmw)) return not_found(pvmw); return true; } diff --git a/mm/rmap.c b/mm/rmap.c index 9af08343ce55..98ecdb96fc94 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1577,11 +1577,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); } else { flush_cache_page(vma, address, pte_pfn(*pvmw.pte)); - /* - * Nuke the page table entry. When having to clear - * PageAnonExclusive(), we always have to flush. - */ - if (should_defer_flush(mm, flags) && !anon_exclusive) { + /* Nuke the page table entry. */ + if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. @@ -1712,6 +1709,8 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, page_vma_mapped_walk_done(&pvmw); break; } + + /* See page_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && page_try_share_anon_rmap(subpage)) { swap_free(entry); @@ -2043,6 +2042,8 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, } VM_BUG_ON_PAGE(pte_write(pteval) && folio_test_anon(folio) && !anon_exclusive, subpage); + + /* See page_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && page_try_share_anon_rmap(subpage)) { if (folio_test_hugetlb(folio)) @@ -2068,7 +2069,10 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, else entry = make_readable_migration_entry( page_to_pfn(subpage)); - + if (pte_young(pteval)) + entry = make_migration_entry_young(entry); + if (pte_dirty(pteval)) + entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); diff --git a/mm/swapfile.c b/mm/swapfile.c index 82e62007881d..194d398febb3 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -63,6 +63,10 @@ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; +unsigned long swapfile_maximum_size; +#ifdef CONFIG_MIGRATION +bool swap_migration_ad_supported; +#endif /* CONFIG_MIGRATION */ static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; @@ -2816,7 +2820,7 @@ unsigned long generic_max_swapfile_size(void) } /* Can be overridden by an architecture for additional checks. */ -__weak unsigned long max_swapfile_size(void) +__weak unsigned long arch_max_swapfile_size(void) { return generic_max_swapfile_size(); } @@ -2856,7 +2860,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p, p->cluster_next = 1; p->cluster_nr = 0; - maxpages = max_swapfile_size(); + maxpages = swapfile_maximum_size; last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); @@ -3677,6 +3681,13 @@ static int __init swapfile_init(void) for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); + swapfile_maximum_size = arch_max_swapfile_size(); + +#ifdef CONFIG_MIGRATION + if (swapfile_maximum_size >= (1UL << SWP_MIG_TOTAL_BITS)) + swap_migration_ad_supported = true; +#endif /* CONFIG_MIGRATION */ + return 0; } subsys_initcall(swapfile_init); diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index 31e5eea2a9b9..7b9dc2426f18 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -30,7 +30,6 @@ map_fixed_noreplace write_to_hugetlbfs hmm-tests memfd_secret -local_config.* soft-dirty split_huge_page_test ksm_tests