diff options
Diffstat (limited to 'include/linux/swapops.h')
| -rw-r--r-- | include/linux/swapops.h | 293 |
1 files changed, 263 insertions, 30 deletions
diff --git a/include/linux/swapops.h b/include/linux/swapops.h index d356ab4047f7..86b95ccb81bb 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -8,24 +8,69 @@ #ifdef CONFIG_MMU +#ifdef CONFIG_SWAP +#include <linux/swapfile.h> +#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 * the low-order bits. * - * We arrange the `type' and `offset' fields so that `type' is at the seven + * We arrange the `type' and `offset' fields so that `type' is at the six * high-order bits of the swp_entry_t and `offset' is right-aligned in the * remaining bits. Although `type' itself needs only five bits, we allow for - * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry(). + * shmem/tmpfs to shift it all up a further one bit: see swp_to_radix_entry(). * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ #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) { + if (pte_swp_exclusive(pte)) + pte = pte_swp_clear_exclusive(pte); if (pte_swp_soft_dirty(pte)) pte = pte_swp_clear_soft_dirty(pte); if (pte_swp_uffd_wp(pte)) @@ -62,6 +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) { @@ -106,6 +162,16 @@ 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) { @@ -194,6 +260,7 @@ static inline bool is_writable_device_exclusive_entry(swp_entry_t entry) static inline int is_migration_entry(swp_entry_t entry) { return unlikely(swp_type(entry) == SWP_MIGRATION_READ || + swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE || swp_type(entry) == SWP_MIGRATION_WRITE); } @@ -202,28 +269,96 @@ static inline int is_writable_migration_entry(swp_entry_t entry) return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE); } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ); +} + +static inline int is_readable_exclusive_migration_entry(swp_entry_t entry) +{ + return unlikely(swp_type(entry) == SWP_MIGRATION_READ_EXCLUSIVE); +} + static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(SWP_MIGRATION_READ, offset); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(SWP_MIGRATION_READ_EXCLUSIVE, offset); +} + 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, unsigned long address); -extern void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte); -#else +#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 /* CONFIG_HUGETLB_PAGE */ +#else /* CONFIG_MIGRATION */ static inline swp_entry_t make_readable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); } +static inline swp_entry_t make_readable_exclusive_migration_entry(pgoff_t offset) +{ + return swp_entry(0, 0); +} + static inline swp_entry_t make_writable_migration_entry(pgoff_t offset) { return swp_entry(0, 0); @@ -238,18 +373,122 @@ static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { } static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { } -static inline void migration_entry_wait_huge(struct vm_area_struct *vma, - struct mm_struct *mm, pte_t *pte) { } +#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 /* CONFIG_HUGETLB_PAGE */ static inline int is_writable_migration_entry(swp_entry_t entry) { return 0; } +static inline int is_readable_migration_entry(swp_entry_t entry) +{ + return 0; +} + +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; + +#define PTE_MARKER_UFFD_WP BIT(0) +#define PTE_MARKER_MASK (PTE_MARKER_UFFD_WP) + +#ifdef CONFIG_PTE_MARKER + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + return swp_entry(SWP_PTE_MARKER, marker); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return swp_type(entry) == SWP_PTE_MARKER; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return swp_offset(entry) & PTE_MARKER_MASK; +} + +static inline bool is_pte_marker(pte_t pte) +{ + return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte)); +} + +#else /* CONFIG_PTE_MARKER */ + +static inline swp_entry_t make_pte_marker_entry(pte_marker marker) +{ + /* This should never be called if !CONFIG_PTE_MARKER */ + WARN_ON_ONCE(1); + return swp_entry(0, 0); +} + +static inline bool is_pte_marker_entry(swp_entry_t entry) +{ + return false; +} + +static inline pte_marker pte_marker_get(swp_entry_t entry) +{ + return 0; +} -#endif +static inline bool is_pte_marker(pte_t pte) +{ + return false; +} + +#endif /* CONFIG_PTE_MARKER */ + +static inline pte_t make_pte_marker(pte_marker marker) +{ + return swp_entry_to_pte(make_pte_marker_entry(marker)); +} + +/* + * This is a special version to check pte_none() just to cover the case when + * the pte is a pte marker. It existed because in many cases the pte marker + * should be seen as a none pte; it's just that we have stored some information + * onto the none pte so it becomes not-none any more. + * + * It should be used when the pte is file-backed, ram-based and backing + * userspace pages, like shmem. It is not needed upon pgtables that do not + * support pte markers at all. For example, it's not needed on anonymous + * memory, kernel-only memory (including when the system is during-boot), + * non-ram based generic file-system. It's fine to be used even there, but the + * extra pte marker check will be pure overhead. + * + * For systems configured with !CONFIG_PTE_MARKER this will be automatically + * optimized to pte_none(). + */ +static inline int pte_none_mostly(pte_t pte) +{ + return pte_none(pte) || is_pte_marker(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 @@ -267,6 +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); } @@ -274,7 +516,7 @@ static inline bool is_pfn_swap_entry(swp_entry_t entry) struct page_vma_mapped_walk; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION -extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +extern int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page); extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, @@ -304,10 +546,10 @@ static inline pmd_t swp_entry_to_pmd(swp_entry_t entry) static inline int is_pmd_migration_entry(pmd_t pmd) { - return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); + return is_swap_pmd(pmd) && is_migration_entry(pmd_to_swp_entry(pmd)); } -#else -static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, +#else /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ +static inline int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { BUILD_BUG(); @@ -335,7 +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 @@ -355,22 +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) +static inline void num_poisoned_pages_sub(long i) { - atomic_long_dec(&num_poisoned_pages); + atomic_long_sub(i, &num_poisoned_pages); } -#else +#else /* CONFIG_MEMORY_FAILURE */ static inline swp_entry_t make_hwpoison_entry(struct page *page) { @@ -385,20 +622,16 @@ static inline int is_hwpoison_entry(swp_entry_t swp) static inline void num_poisoned_pages_inc(void) { } -#endif -#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION) || \ - defined(CONFIG_DEVICE_PRIVATE) -static inline int non_swap_entry(swp_entry_t entry) +static inline void num_poisoned_pages_sub(long i) { - return swp_type(entry) >= MAX_SWAPFILES; } -#else +#endif /* CONFIG_MEMORY_FAILURE */ + static inline int non_swap_entry(swp_entry_t entry) { - return 0; + return swp_type(entry) >= MAX_SWAPFILES; } -#endif #endif /* CONFIG_MMU */ #endif /* _LINUX_SWAPOPS_H */ |