diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 587 |
1 files changed, 302 insertions, 285 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index f3f196e4d66d..1f79667824eb 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -137,7 +137,7 @@ extern int mmap_rnd_compat_bits __read_mostly; * define their own version of this macro in <asm/pgtable.h> */ #if BITS_PER_LONG == 64 -/* This function must be updated when the size of struct page grows above 80 +/* This function must be updated when the size of struct page grows above 96 * or reduces below 56. The idea that compiler optimizes out switch() * statement, and only leaves move/store instructions. Also the compiler can * combine write statements if they are both assignments and can be reordered, @@ -148,12 +148,18 @@ static inline void __mm_zero_struct_page(struct page *page) { unsigned long *_pp = (void *)page; - /* Check that struct page is either 56, 64, 72, or 80 bytes */ + /* Check that struct page is either 56, 64, 72, 80, 88 or 96 bytes */ BUILD_BUG_ON(sizeof(struct page) & 7); BUILD_BUG_ON(sizeof(struct page) < 56); - BUILD_BUG_ON(sizeof(struct page) > 80); + BUILD_BUG_ON(sizeof(struct page) > 96); switch (sizeof(struct page)) { + case 96: + _pp[11] = 0; + fallthrough; + case 88: + _pp[10] = 0; + fallthrough; case 80: _pp[9] = 0; fallthrough; @@ -276,7 +282,12 @@ extern unsigned int kobjsize(const void *objp); #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ +#ifdef CONFIG_MMU #define VM_UFFD_MISSING 0x00000200 /* missing pages tracking */ +#else /* CONFIG_MMU */ +#define VM_MAYOVERLAY 0x00000200 /* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */ +#define VM_UFFD_MISSING 0 +#endif /* CONFIG_MMU */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_UFFD_WP 0x00001000 /* wrprotect pages tracking */ @@ -416,8 +427,8 @@ extern unsigned int kobjsize(const void *objp); /* This mask defines which mm->def_flags a process can inherit its parent */ #define VM_INIT_DEF_MASK VM_NOHUGEPAGE -/* This mask is used to clear all the VMA flags used by mlock */ -#define VM_LOCKED_CLEAR_MASK (~(VM_LOCKED | VM_LOCKONFAULT)) +/* This mask represents all the VMA flag bits used by mlock */ +#define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) /* Arch-specific flags to clear when updating VM flags on protection change */ #ifndef VM_ARCH_CLEAR @@ -622,6 +633,63 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) INIT_LIST_HEAD(&vma->anon_vma_chain); } +/* Use when VMA is not part of the VMA tree and needs no locking */ +static inline void vm_flags_init(struct vm_area_struct *vma, + vm_flags_t flags) +{ + ACCESS_PRIVATE(vma, __vm_flags) = flags; +} + +/* Use when VMA is part of the VMA tree and modifications need coordination */ +static inline void vm_flags_reset(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + vm_flags_init(vma, flags); +} + +static inline void vm_flags_reset_once(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags); +} + +static inline void vm_flags_set(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + ACCESS_PRIVATE(vma, __vm_flags) |= flags; +} + +static inline void vm_flags_clear(struct vm_area_struct *vma, + vm_flags_t flags) +{ + mmap_assert_write_locked(vma->vm_mm); + ACCESS_PRIVATE(vma, __vm_flags) &= ~flags; +} + +/* + * Use only if VMA is not part of the VMA tree or has no other users and + * therefore needs no locking. + */ +static inline void __vm_flags_mod(struct vm_area_struct *vma, + vm_flags_t set, vm_flags_t clear) +{ + vm_flags_init(vma, (vma->vm_flags | set) & ~clear); +} + +/* + * Use only when the order of set/clear operations is unimportant, otherwise + * use vm_flags_{set|clear} explicitly. + */ +static inline void vm_flags_mod(struct vm_area_struct *vma, + vm_flags_t set, vm_flags_t clear) +{ + mmap_assert_write_locked(vma->vm_mm); + __vm_flags_mod(vma, set, clear); +} + static inline void vma_set_anonymous(struct vm_area_struct *vma) { vma->vm_ops = NULL; @@ -665,16 +733,16 @@ static inline bool vma_is_accessible(struct vm_area_struct *vma) static inline struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max) { - return mas_find(&vmi->mas, max); + return mas_find(&vmi->mas, max - 1); } static inline struct vm_area_struct *vma_next(struct vma_iterator *vmi) { /* - * Uses vma_find() to get the first VMA when the iterator starts. + * Uses mas_find() to get the first VMA when the iterator starts. * Calling mas_next() could skip the first entry. */ - return vma_find(vmi, ULONG_MAX); + return mas_find(&vmi->mas, ULONG_MAX); } static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi) @@ -687,12 +755,50 @@ static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) return vmi->mas.index; } +static inline unsigned long vma_iter_end(struct vma_iterator *vmi) +{ + return vmi->mas.last + 1; +} +static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi, + unsigned long count) +{ + return mas_expected_entries(&vmi->mas, count); +} + +/* Free any unused preallocations */ +static inline void vma_iter_free(struct vma_iterator *vmi) +{ + mas_destroy(&vmi->mas); +} + +static inline int vma_iter_bulk_store(struct vma_iterator *vmi, + struct vm_area_struct *vma) +{ + vmi->mas.index = vma->vm_start; + vmi->mas.last = vma->vm_end - 1; + mas_store(&vmi->mas, vma); + if (unlikely(mas_is_err(&vmi->mas))) + return -ENOMEM; + + return 0; +} + +static inline void vma_iter_invalidate(struct vma_iterator *vmi) +{ + mas_pause(&vmi->mas); +} + +static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr) +{ + mas_set(&vmi->mas, addr); +} + #define for_each_vma(__vmi, __vma) \ while (((__vma) = vma_next(&(__vmi))) != NULL) /* The MM code likes to work with exclusive end addresses */ #define for_each_vma_range(__vmi, __vma, __end) \ - while (((__vma) = vma_find(&(__vmi), (__end) - 1)) != NULL) + while (((__vma) = vma_find(&(__vmi), (__end))) != NULL) #ifdef CONFIG_SHMEM /* @@ -714,11 +820,20 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; +/* + * compound_order() can be called without holding a reference, which means + * that niceties like page_folio() don't work. These callers should be + * prepared to handle wild return values. For example, PG_head may be + * set before _folio_order is initialised, or this may be a tail page. + * See compaction.c for some good examples. + */ static inline unsigned int compound_order(struct page *page) { - if (!PageHead(page)) + struct folio *folio = (struct folio *)page; + + if (!test_bit(PG_head, &folio->flags)) return 0; - return page[1].compound_order; + return folio->_folio_order; } /** @@ -777,6 +892,13 @@ static inline bool get_page_unless_zero(struct page *page) return page_ref_add_unless(page, 1, 0); } +static inline struct folio *folio_get_nontail_page(struct page *page) +{ + if (unlikely(!get_page_unless_zero(page))) + return NULL; + return (struct folio *)page; +} + extern int page_is_ram(unsigned long pfn); enum { @@ -826,34 +948,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) static inline int folio_entire_mapcount(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); - return atomic_read(folio_mapcount_ptr(folio)) + 1; -} - -/* - * Mapcount of compound page as a whole, does not include mapped sub-pages. - * Must be called only on head of compound page. - */ -static inline int head_compound_mapcount(struct page *head) -{ - return atomic_read(compound_mapcount_ptr(head)) + 1; -} - -/* - * If a 16GB hugetlb page were mapped by PTEs of all of its 4kB sub-pages, - * its subpages_mapcount would be 0x400000: choose the COMPOUND_MAPPED bit - * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently - * leaves subpages_mapcount at 0, but avoid surprise if it participates later. - */ -#define COMPOUND_MAPPED 0x800000 -#define SUBPAGES_MAPPED (COMPOUND_MAPPED - 1) - -/* - * Number of sub-pages mapped by PTE, does not include compound mapcount. - * Must be called only on head of compound page. - */ -static inline int head_subpages_mapcount(struct page *head) -{ - return atomic_read(subpages_mapcount_ptr(head)) & SUBPAGES_MAPPED; + return atomic_read(&folio->_entire_mapcount) + 1; } /* @@ -866,25 +961,29 @@ static inline void page_mapcount_reset(struct page *page) atomic_set(&(page)->_mapcount, -1); } -/* - * Mapcount of 0-order page; when compound sub-page, includes - * compound_mapcount of compound_head of page. +/** + * page_mapcount() - Number of times this precise page is mapped. + * @page: The page. + * + * The number of times this page is mapped. If this page is part of + * a large folio, it includes the number of times this page is mapped + * as part of that folio. * - * Result is undefined for pages which cannot be mapped into userspace. + * The result is undefined for pages which cannot be mapped into userspace. * For example SLAB or special types of pages. See function page_has_type(). - * They use this place in struct page differently. + * They use this field in struct page differently. */ static inline int page_mapcount(struct page *page) { int mapcount = atomic_read(&page->_mapcount) + 1; - if (likely(!PageCompound(page))) - return mapcount; - page = compound_head(page); - return head_compound_mapcount(page) + mapcount; + if (unlikely(PageCompound(page))) + mapcount += folio_entire_mapcount(page_folio(page)); + + return mapcount; } -int total_compound_mapcount(struct page *head); +int folio_total_mapcount(struct folio *folio); /** * folio_mapcount() - Calculate the number of mappings of this folio. @@ -901,24 +1000,24 @@ static inline int folio_mapcount(struct folio *folio) { if (likely(!folio_test_large(folio))) return atomic_read(&folio->_mapcount) + 1; - return total_compound_mapcount(&folio->page); + return folio_total_mapcount(folio); } static inline int total_mapcount(struct page *page) { if (likely(!PageCompound(page))) return atomic_read(&page->_mapcount) + 1; - return total_compound_mapcount(compound_head(page)); + return folio_total_mapcount(page_folio(page)); } static inline bool folio_large_is_mapped(struct folio *folio) { /* - * Reading folio_mapcount_ptr() below could be omitted if hugetlb - * participated in incrementing subpages_mapcount when compound mapped. + * Reading _entire_mapcount below could be omitted if hugetlb + * participated in incrementing nr_pages_mapped when compound mapped. */ - return atomic_read(folio_subpages_mapcount_ptr(folio)) > 0 || - atomic_read(folio_mapcount_ptr(folio)) >= 0; + return atomic_read(&folio->_nr_pages_mapped) > 0 || + atomic_read(&folio->_entire_mapcount) >= 0; } /** @@ -993,8 +1092,11 @@ extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS]; static inline void set_compound_page_dtor(struct page *page, enum compound_dtor_id compound_dtor) { + struct folio *folio = (struct folio *)page; + VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page); - page[1].compound_dtor = compound_dtor; + VM_BUG_ON_PAGE(!PageHead(page), page); + folio->_folio_dtor = compound_dtor; } static inline void folio_set_compound_dtor(struct folio *folio, @@ -1006,44 +1108,13 @@ static inline void folio_set_compound_dtor(struct folio *folio, void destroy_large_folio(struct folio *folio); -static inline int head_compound_pincount(struct page *head) -{ - return atomic_read(compound_pincount_ptr(head)); -} - static inline void set_compound_order(struct page *page, unsigned int order) { - page[1].compound_order = order; -#ifdef CONFIG_64BIT - page[1].compound_nr = 1U << order; -#endif -} - -/* - * folio_set_compound_order is generally passed a non-zero order to - * initialize a large folio. However, hugetlb code abuses this by - * passing in zero when 'dissolving' a large folio. - */ -static inline void folio_set_compound_order(struct folio *folio, - unsigned int order) -{ - VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); + struct folio *folio = (struct folio *)page; folio->_folio_order = order; #ifdef CONFIG_64BIT - folio->_folio_nr_pages = order ? 1U << order : 0; -#endif -} - -/* Returns the number of pages in this potentially compound page. */ -static inline unsigned long compound_nr(struct page *page) -{ - if (!PageHead(page)) - return 1; -#ifdef CONFIG_64BIT - return page[1].compound_nr; -#else - return 1UL << compound_order(page); + folio->_folio_nr_pages = 1U << order; #endif } @@ -1070,16 +1141,6 @@ static inline unsigned int thp_order(struct page *page) } /** - * thp_nr_pages - The number of regular pages in this huge page. - * @page: The head page of a huge page. - */ -static inline int thp_nr_pages(struct page *page) -{ - VM_BUG_ON_PGFLAGS(PageTail(page), page); - return compound_nr(page); -} - -/** * thp_size - Size of a transparent huge page. * @page: Head page of a transparent huge page. * @@ -1220,8 +1281,6 @@ static inline void get_page(struct page *page) folio_get(page_folio(page)); } -int __must_check try_grab_page(struct page *page, unsigned int flags); - static inline __must_check bool try_get_page(struct page *page) { page = compound_head(page); @@ -1270,10 +1329,10 @@ static inline void folio_put_refs(struct folio *folio, int refs) __folio_put(folio); } -/** - * release_pages - release an array of pages or folios +/* + * union release_pages_arg - an array of pages or folios * - * This just releases a simple array of multiple pages, and + * release_pages() releases a simple array of multiple pages, and * accepts various different forms of said page array: either * a regular old boring array of pages, an array of folios, or * an array of encoded page pointers. @@ -1363,6 +1422,21 @@ static inline bool is_cow_mapping(vm_flags_t flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +#ifndef CONFIG_MMU +static inline bool is_nommu_shared_mapping(vm_flags_t flags) +{ + /* + * NOMMU shared mappings are ordinary MAP_SHARED mappings and selected + * R/O MAP_PRIVATE file mappings that are an effective R/O overlay of + * a file mapping. R/O MAP_PRIVATE mappings might still modify + * underlying memory if ptrace is active, so this is only possible if + * ptrace does not apply. Note that there is no mprotect() to upgrade + * write permissions later. + */ + return flags & (VM_MAYSHARE | VM_MAYOVERLAY); +} +#endif + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -1637,11 +1711,6 @@ static inline struct folio *pfn_folio(unsigned long pfn) return page_folio(pfn_to_page(pfn)); } -static inline atomic_t *folio_pincount_ptr(struct folio *folio) -{ - return &folio_page(folio, 1)->compound_pincount; -} - /** * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA. * @folio: The folio. @@ -1659,7 +1728,7 @@ static inline atomic_t *folio_pincount_ptr(struct folio *folio) * expected to be able to deal gracefully with a false positive. * * For large folios, the result will be exactly correct. That's because - * we have more tracking data available: the compound_pincount is used + * we have more tracking data available: the _pincount field is used * instead of the GUP_PIN_COUNTING_BIAS scheme. * * For more information, please see Documentation/core-api/pin_user_pages.rst. @@ -1670,7 +1739,7 @@ static inline atomic_t *folio_pincount_ptr(struct folio *folio) static inline bool folio_maybe_dma_pinned(struct folio *folio) { if (folio_test_large(folio)) - return atomic_read(folio_pincount_ptr(folio)) > 0; + return atomic_read(&folio->_pincount) > 0; /* * folio_ref_count() is signed. If that refcount overflows, then @@ -1778,6 +1847,33 @@ static inline long folio_nr_pages(struct folio *folio) #endif } +/* + * compound_nr() returns the number of pages in this potentially compound + * page. compound_nr() can be called on a tail page, and is defined to + * return 1 in that case. + */ +static inline unsigned long compound_nr(struct page *page) +{ + struct folio *folio = (struct folio *)page; + + if (!test_bit(PG_head, &folio->flags)) + return 1; +#ifdef CONFIG_64BIT + return folio->_folio_nr_pages; +#else + return 1L << folio->_folio_order; +#endif +} + +/** + * thp_nr_pages - The number of regular pages in this huge page. + * @page: The head page of a huge page. + */ +static inline int thp_nr_pages(struct page *page) +{ + return folio_nr_pages((struct folio *)page); +} + /** * folio_next - Move to the next physical folio. * @folio: The folio we're currently operating on. @@ -1827,6 +1923,24 @@ static inline size_t folio_size(struct folio *folio) return PAGE_SIZE << folio_order(folio); } +/** + * folio_estimated_sharers - Estimate the number of sharers of a folio. + * @folio: The folio. + * + * folio_estimated_sharers() aims to serve as a function to efficiently + * estimate the number of processes sharing a folio. This is done by + * looking at the precise mapcount of the first subpage in the folio, and + * assuming the other subpages are the same. This may not be true for large + * folios. If you want exact mapcounts for exact calculations, look at + * page_mapcount() or folio_total_mapcount(). + * + * Return: The estimated number of processes sharing a folio. + */ +static inline int folio_estimated_sharers(struct folio *folio) +{ + return page_mapcount(folio_page(folio, 0)); +} + #ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE static inline int arch_make_page_accessible(struct page *page) { @@ -1923,6 +2037,21 @@ static inline bool page_is_pfmemalloc(const struct page *page) } /* + * Return true only if the folio has been allocated with + * ALLOC_NO_WATERMARKS and the low watermark was not + * met implying that the system is under some pressure. + */ +static inline bool folio_is_pfmemalloc(const struct folio *folio) +{ + /* + * lru.next has bit 1 set if the page is allocated from the + * pfmemalloc reserves. Callers may simply overwrite it if + * they do not need to preserve that information. + */ + return (uintptr_t)folio->lru.next & BIT(1); +} + +/* * Only to be called by the page allocator on a freshly allocated * page. */ @@ -1976,6 +2105,31 @@ struct zap_details { /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) +#ifdef CONFIG_SCHED_MM_CID +void sched_mm_cid_before_execve(struct task_struct *t); +void sched_mm_cid_after_execve(struct task_struct *t); +void sched_mm_cid_fork(struct task_struct *t); +void sched_mm_cid_exit_signals(struct task_struct *t); +static inline int task_mm_cid(struct task_struct *t) +{ + return t->mm_cid; +} +#else +static inline void sched_mm_cid_before_execve(struct task_struct *t) { } +static inline void sched_mm_cid_after_execve(struct task_struct *t) { } +static inline void sched_mm_cid_fork(struct task_struct *t) { } +static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } +static inline int task_mm_cid(struct task_struct *t) +{ + /* + * Use the processor id as a fall-back when the mm cid feature is + * disabled. This provides functional per-cpu data structure accesses + * in user-space, althrough it won't provide the memory usage benefits. + */ + return raw_smp_processor_id(); +} +#endif + #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else @@ -1984,6 +2138,8 @@ static inline bool can_do_mlock(void) { return false; } extern int user_shm_lock(size_t, struct ucounts *); extern void user_shm_unlock(size_t, struct ucounts *); +struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, @@ -1991,13 +2147,16 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); -void zap_page_range(struct vm_area_struct *vma, unsigned long address, - unsigned long size); void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details); +static inline void zap_vma_pages(struct vm_area_struct *vma) +{ + zap_page_range_single(vma, vma->vm_start, + vma->vm_end - vma->vm_start, NULL); +} void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt, struct vm_area_struct *start_vma, unsigned long start, - unsigned long end); + unsigned long end, bool mm_wr_locked); struct mmu_notifier_range; @@ -2095,8 +2254,6 @@ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim); struct kvec; -int get_kernel_pages(const struct kvec *iov, int nr_pages, int write, - struct page **pages); struct page *get_dump_page(unsigned long addr); bool folio_mark_dirty(struct folio *folio); @@ -2146,21 +2303,18 @@ static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma } bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr, pte_t pte); -extern unsigned long change_protection(struct mmu_gather *tlb, +extern long change_protection(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgprot_t newprot, - unsigned long cp_flags); -extern int mprotect_fixup(struct mmu_gather *tlb, struct vm_area_struct *vma, - struct vm_area_struct **pprev, unsigned long start, - unsigned long end, unsigned long newflags); + unsigned long end, unsigned long cp_flags); +extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb, + struct vm_area_struct *vma, struct vm_area_struct **pprev, + unsigned long start, unsigned long end, unsigned long newflags); /* * doesn't attempt to fault and will return short. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); -int pin_user_pages_fast_only(unsigned long start, int nr_pages, - unsigned int gup_flags, struct page **pages); static inline bool get_user_page_fast_only(unsigned long addr, unsigned int gup_flags, struct page **pagep) @@ -2784,23 +2938,21 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); /* mmap.c */ extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); -extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, - struct vm_area_struct *expand); -static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, - unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) -{ - return __vma_adjust(vma, start, end, pgoff, insert, NULL); -} -extern struct vm_area_struct *vma_merge(struct mm_struct *, - struct vm_area_struct *prev, unsigned long addr, unsigned long end, - unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx, struct anon_vma_name *); +extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff, + struct vm_area_struct *next); +extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, pgoff_t pgoff); +extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi, + struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, + unsigned long end, unsigned long vm_flags, struct anon_vma *, + struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx, + struct anon_vma_name *); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); -extern int __split_vma(struct mm_struct *, struct vm_area_struct *, - unsigned long addr, int new_below); -extern int split_vma(struct mm_struct *, struct vm_area_struct *, - unsigned long addr, int new_below); +extern int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *, + unsigned long addr, int new_below); +extern int split_vma(struct vma_iterator *vmi, struct vm_area_struct *, + unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, @@ -2808,9 +2960,6 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **, bool *need_rmap_locks); extern void exit_mmap(struct mm_struct *); -void vma_mas_store(struct vm_area_struct *vma, struct ma_state *mas); -void vma_mas_remove(struct vm_area_struct *vma, struct ma_state *mas); - static inline int check_data_rlimit(unsigned long rlim, unsigned long new, unsigned long start, @@ -2858,7 +3007,7 @@ extern unsigned long mmap_region(struct file *file, unsigned long addr, extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); -extern int do_mas_munmap(struct ma_state *mas, struct mm_struct *mm, +extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, @@ -2866,6 +3015,9 @@ extern int do_munmap(struct mm_struct *, unsigned long, size_t, extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior); #ifdef CONFIG_MMU +extern int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct list_head *uf, bool downgrade); extern int __mm_populate(unsigned long addr, unsigned long len, int ignore_errors); static inline void mm_populate(unsigned long addr, unsigned long len) @@ -3071,81 +3223,6 @@ static inline vm_fault_t vmf_error(int err) struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags); -#define FOLL_WRITE 0x01 /* check pte is writable */ -#define FOLL_TOUCH 0x02 /* mark page accessed */ -#define FOLL_GET 0x04 /* do get_page on page */ -#define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ -#define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ -#define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO - * and return without waiting upon it */ -#define FOLL_NOFAULT 0x80 /* do not fault in pages */ -#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ -#define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ -#define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ -#define FOLL_ANON 0x8000 /* don't do file mappings */ -#define FOLL_LONGTERM 0x10000 /* mapping lifetime is indefinite: see below */ -#define FOLL_SPLIT_PMD 0x20000 /* split huge pmd before returning */ -#define FOLL_PIN 0x40000 /* pages must be released via unpin_user_page */ -#define FOLL_FAST_ONLY 0x80000 /* gup_fast: prevent fall-back to slow gup */ -#define FOLL_PCI_P2PDMA 0x100000 /* allow returning PCI P2PDMA pages */ -#define FOLL_INTERRUPTIBLE 0x200000 /* allow interrupts from generic signals */ - -/* - * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each - * other. Here is what they mean, and how to use them: - * - * FOLL_LONGTERM indicates that the page will be held for an indefinite time - * period _often_ under userspace control. This is in contrast to - * iov_iter_get_pages(), whose usages are transient. - * - * FIXME: For pages which are part of a filesystem, mappings are subject to the - * lifetime enforced by the filesystem and we need guarantees that longterm - * users like RDMA and V4L2 only establish mappings which coordinate usage with - * the filesystem. Ideas for this coordination include revoking the longterm - * pin, delaying writeback, bounce buffer page writeback, etc. As FS DAX was - * added after the problem with filesystems was found FS DAX VMAs are - * specifically failed. Filesystem pages are still subject to bugs and use of - * FOLL_LONGTERM should be avoided on those pages. - * - * FIXME: Also NOTE that FOLL_LONGTERM is not supported in every GUP call. - * Currently only get_user_pages() and get_user_pages_fast() support this flag - * and calls to get_user_pages_[un]locked are specifically not allowed. This - * is due to an incompatibility with the FS DAX check and - * FAULT_FLAG_ALLOW_RETRY. - * - * In the CMA case: long term pins in a CMA region would unnecessarily fragment - * that region. And so, CMA attempts to migrate the page before pinning, when - * FOLL_LONGTERM is specified. - * - * FOLL_PIN indicates that a special kind of tracking (not just page->_refcount, - * but an additional pin counting system) will be invoked. This is intended for - * anything that gets a page reference and then touches page data (for example, - * Direct IO). This lets the filesystem know that some non-file-system entity is - * potentially changing the pages' data. In contrast to FOLL_GET (whose pages - * are released via put_page()), FOLL_PIN pages must be released, ultimately, by - * a call to unpin_user_page(). - * - * FOLL_PIN is similar to FOLL_GET: both of these pin pages. They use different - * and separate refcounting mechanisms, however, and that means that each has - * its own acquire and release mechanisms: - * - * FOLL_GET: get_user_pages*() to acquire, and put_page() to release. - * - * FOLL_PIN: pin_user_pages*() to acquire, and unpin_user_pages to release. - * - * FOLL_PIN and FOLL_GET are mutually exclusive for a given function call. - * (The underlying pages may experience both FOLL_GET-based and FOLL_PIN-based - * calls applied to them, and that's perfectly OK. This is a constraint on the - * callers, not on the pages.) - * - * FOLL_PIN should be set internally by the pin_user_pages*() APIs, never - * directly by the caller. That's in order to help avoid mismatches when - * releasing pages: get_user_pages*() pages must be released via put_page(), - * while pin_user_pages*() pages must be released via unpin_user_page(). - * - * Please see Documentation/core-api/pin_user_pages.rst for more information. - */ - static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { if (vm_fault & VM_FAULT_OOM) @@ -3158,71 +3235,6 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) } /* - * Indicates for which pages that are write-protected in the page table, - * whether GUP has to trigger unsharing via FAULT_FLAG_UNSHARE such that the - * GUP pin will remain consistent with the pages mapped into the page tables - * of the MM. - * - * Temporary unmapping of PageAnonExclusive() pages or clearing of - * 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): 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 - * PTE-mapped THP. - * - * If the vma is NULL, we're coming from the GUP-fast path and might have - * to fallback to the slow path just to lookup the vma. - */ -static inline bool gup_must_unshare(struct vm_area_struct *vma, - unsigned int flags, struct page *page) -{ - /* - * FOLL_WRITE is implicitly handled correctly as the page table entry - * has to be writable -- and if it references (part of) an anonymous - * folio, that part is required to be marked exclusive. - */ - if ((flags & (FOLL_WRITE | FOLL_PIN)) != FOLL_PIN) - return false; - /* - * Note: PageAnon(page) is stable until the page is actually getting - * freed. - */ - if (!PageAnon(page)) { - /* - * We only care about R/O long-term pining: R/O short-term - * pinning does not have the semantics to observe successive - * changes through the process page tables. - */ - if (!(flags & FOLL_LONGTERM)) - return false; - - /* We really need the vma ... */ - if (!vma) - return true; - - /* - * ... because we only care about writable private ("COW") - * mappings where we have to break COW early. - */ - return is_cow_mapping(vma->vm_flags); - } - - /* 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. - */ - return !PageAnonExclusive(page); -} - -/* * Indicates whether GUP can follow a PROT_NONE mapped page, or whether * a (NUMA hinting) fault is required. */ @@ -3521,6 +3533,11 @@ enum mf_action_page_type { MF_MSG_UNKNOWN, }; +/* + * Sysfs entries for memory failure handling statistics. + */ +extern const struct attribute_group memory_failure_attr_group; + #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) extern void clear_huge_page(struct page *page, unsigned long addr_hint, @@ -3638,7 +3655,7 @@ static inline int seal_check_future_write(int seals, struct vm_area_struct *vma) * VM_MAYWRITE as we still want them to be COW-writable. */ if (vma->vm_flags & VM_SHARED) - vma->vm_flags &= ~(VM_MAYWRITE); + vm_flags_clear(vma, VM_MAYWRITE); } return 0; |