diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 276 |
1 files changed, 221 insertions, 55 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 6a05a3bc0a28..8178fe894e2e 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -74,6 +74,7 @@ static inline void totalram_pages_add(long count) extern void * high_memory; extern int page_cluster; +extern const int page_cluster_max; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; @@ -549,7 +550,7 @@ struct vm_operations_struct { /* * Called by mprotect() to make driver-specific permission * checks before mprotect() is finalised. The VMA must not - * be modified. Returns 0 if eprotect() can proceed. + * be modified. Returns 0 if mprotect() can proceed. */ int (*mprotect)(struct vm_area_struct *vma, unsigned long start, unsigned long end, unsigned long newflags); @@ -699,8 +700,10 @@ static inline unsigned long vma_iter_addr(struct vma_iterator *vmi) * paths in userfault. */ bool vma_is_shmem(struct vm_area_struct *vma); +bool vma_is_anon_shmem(struct vm_area_struct *vma); #else static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } +static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; } #endif int vma_is_stack_for_current(struct vm_area_struct *vma); @@ -817,8 +820,8 @@ static inline int is_vmalloc_or_module_addr(const void *x) /* * How many times the entire folio is mapped as a single unit (eg by a * PMD or PUD entry). This is probably not what you want, except for - * debugging purposes; look at folio_mapcount() or page_mapcount() - * instead. + * debugging purposes - it does not include PTE-mapped sub-pages; look + * at folio_mapcount() or page_mapcount() or total_mapcount() instead. */ static inline int folio_entire_mapcount(struct folio *folio) { @@ -828,12 +831,29 @@ static inline int folio_entire_mapcount(struct folio *folio) /* * Mapcount of compound page as a whole, does not include mapped sub-pages. - * - * Must be called only for compound pages. + * Must be called only on head of compound page. */ -static inline int compound_mapcount(struct page *page) +static inline int head_compound_mapcount(struct page *head) { - return folio_entire_mapcount(page_folio(page)); + 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; } /* @@ -846,11 +866,9 @@ static inline void page_mapcount_reset(struct page *page) atomic_set(&(page)->_mapcount, -1); } -int __page_mapcount(struct page *page); - /* * Mapcount of 0-order page; when compound sub-page, includes - * compound_mapcount(). + * compound_mapcount of compound_head of page. * * Result is undefined for pages which cannot be mapped into userspace. * For example SLAB or special types of pages. See function page_has_type(). @@ -858,25 +876,75 @@ int __page_mapcount(struct page *page); */ static inline int page_mapcount(struct page *page) { - if (unlikely(PageCompound(page))) - return __page_mapcount(page); - return atomic_read(&page->_mapcount) + 1; + int mapcount = atomic_read(&page->_mapcount) + 1; + + if (likely(!PageCompound(page))) + return mapcount; + page = compound_head(page); + return head_compound_mapcount(page) + mapcount; } -int folio_mapcount(struct folio *folio); +int total_compound_mapcount(struct page *head); -#ifdef CONFIG_TRANSPARENT_HUGEPAGE -static inline int total_mapcount(struct page *page) +/** + * folio_mapcount() - Calculate the number of mappings of this folio. + * @folio: The folio. + * + * A large folio tracks both how many times the entire folio is mapped, + * and how many times each individual page in the folio is mapped. + * This function calculates the total number of times the folio is + * mapped. + * + * Return: The number of times this folio is mapped. + */ +static inline int folio_mapcount(struct folio *folio) { - return folio_mapcount(page_folio(page)); + if (likely(!folio_test_large(folio))) + return atomic_read(&folio->_mapcount) + 1; + return total_compound_mapcount(&folio->page); } -#else static inline int total_mapcount(struct page *page) { - return page_mapcount(page); + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) + 1; + return total_compound_mapcount(compound_head(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. + */ + return atomic_read(folio_subpages_mapcount_ptr(folio)) > 0 || + atomic_read(folio_mapcount_ptr(folio)) >= 0; +} + +/** + * folio_mapped - Is this folio mapped into userspace? + * @folio: The folio. + * + * Return: True if any page in this folio is referenced by user page tables. + */ +static inline bool folio_mapped(struct folio *folio) +{ + if (likely(!folio_test_large(folio))) + return atomic_read(&folio->_mapcount) >= 0; + return folio_large_is_mapped(folio); +} + +/* + * Return true if this page is mapped into pagetables. + * For compound page it returns true if any sub-page of compound page is mapped, + * even if this particular sub-page is not itself mapped by any PTE or PMD. + */ +static inline bool page_mapped(struct page *page) +{ + if (likely(!PageCompound(page))) + return atomic_read(&page->_mapcount) >= 0; + return folio_large_is_mapped(page_folio(page)); } -#endif static inline struct page *virt_to_head_page(const void *x) { @@ -929,6 +997,13 @@ static inline void set_compound_page_dtor(struct page *page, page[1].compound_dtor = compound_dtor; } +static inline void folio_set_compound_dtor(struct folio *folio, + enum compound_dtor_id compound_dtor) +{ + VM_BUG_ON_FOLIO(compound_dtor >= NR_COMPOUND_DTORS, folio); + folio->_folio_dtor = compound_dtor; +} + void destroy_large_folio(struct folio *folio); static inline int head_compound_pincount(struct page *head) @@ -944,6 +1019,22 @@ static inline void set_compound_order(struct page *page, unsigned int 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); + + 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) { @@ -1179,7 +1270,24 @@ static inline void folio_put_refs(struct folio *folio, int refs) __folio_put(folio); } -void release_pages(struct page **pages, int nr); +/** + * release_pages - release an array of pages or folios + * + * This just 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. + * + * The transparent union syntax for this kind of "any of these + * argument types" is all kinds of ugly, so look away. + */ +typedef union { + struct page **pages; + struct folio **folios; + struct encoded_page **encoded_pages; +} release_pages_arg __attribute__ ((__transparent_union__)); + +void release_pages(release_pages_arg, int nr); /** * folios_put - Decrement the reference count on an array of folios. @@ -1195,7 +1303,7 @@ void release_pages(struct page **pages, int nr); */ static inline void folios_put(struct folio **folios, unsigned int nr) { - release_pages((struct page **)folios, nr); + release_pages(folios, nr); } static inline void put_page(struct page *page) @@ -1799,9 +1907,6 @@ static inline pgoff_t page_index(struct page *page) return page->index; } -bool page_mapped(struct page *page); -bool folio_mapped(struct folio *folio); - /* * Return true only if the page has been allocated with * ALLOC_NO_WATERMARKS and the low watermark was not @@ -2025,6 +2130,22 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma, #define MM_CP_UFFD_WP_ALL (MM_CP_UFFD_WP | \ MM_CP_UFFD_WP_RESOLVE) +int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); +static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) +{ + /* + * We want to check manually if we can change individual PTEs writable + * if we can't do that automatically for all PTEs in a mapping. For + * private mappings, that's always the case when we have write + * permissions as we properly have to handle COW. + */ + if (vma->vm_flags & VM_SHARED) + return vma_wants_writenotify(vma, vma->vm_page_prot); + return !!(vma->vm_flags & VM_WRITE); + +} +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, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgprot_t newprot, @@ -2051,40 +2172,30 @@ static inline bool get_user_page_fast_only(unsigned long addr, */ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) { - long val = atomic_long_read(&mm->rss_stat.count[member]); - -#ifdef SPLIT_RSS_COUNTING - /* - * counter is updated in asynchronous manner and may go to minus. - * But it's never be expected number for users. - */ - if (val < 0) - val = 0; -#endif - return (unsigned long)val; + return percpu_counter_read_positive(&mm->rss_stat[member]); } -void mm_trace_rss_stat(struct mm_struct *mm, int member, long count); +void mm_trace_rss_stat(struct mm_struct *mm, int member); static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { - long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); + percpu_counter_add(&mm->rss_stat[member], value); - mm_trace_rss_stat(mm, member, count); + mm_trace_rss_stat(mm, member); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { - long count = atomic_long_inc_return(&mm->rss_stat.count[member]); + percpu_counter_inc(&mm->rss_stat[member]); - mm_trace_rss_stat(mm, member, count); + mm_trace_rss_stat(mm, member); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { - long count = atomic_long_dec_return(&mm->rss_stat.count[member]); + percpu_counter_dec(&mm->rss_stat[member]); - mm_trace_rss_stat(mm, member, count); + mm_trace_rss_stat(mm, member); } /* Optimized variant when page is already known not to be PageAnon */ @@ -2174,8 +2285,6 @@ static inline int pte_devmap(pte_t pte) } #endif -int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); - extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, @@ -2424,7 +2533,7 @@ static inline void pgtable_pte_page_dtor(struct page *page) #if USE_SPLIT_PMD_PTLOCKS -static struct page *pmd_to_page(pmd_t *pmd) +static inline struct page *pmd_pgtable_page(pmd_t *pmd) { unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1); return virt_to_page((void *)((unsigned long) pmd & mask)); @@ -2432,7 +2541,7 @@ static struct page *pmd_to_page(pmd_t *pmd) static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd) { - return ptlock_ptr(pmd_to_page(pmd)); + return ptlock_ptr(pmd_pgtable_page(pmd)); } static inline bool pmd_ptlock_init(struct page *page) @@ -2451,7 +2560,7 @@ static inline void pmd_ptlock_free(struct page *page) ptlock_free(page); } -#define pmd_huge_pte(mm, pmd) (pmd_to_page(pmd)->pmd_huge_pte) +#define pmd_huge_pte(mm, pmd) (pmd_pgtable_page(pmd)->pmd_huge_pte) #else @@ -2971,7 +3080,6 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * 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_MIGRATION 0x400 /* wait for page to replace migration entry */ #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 */ @@ -3064,8 +3172,12 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) * 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(unsigned int flags, struct page *page) +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 @@ -3078,8 +3190,25 @@ static inline bool gup_must_unshare(unsigned int flags, struct page *page) * Note: PageAnon(page) is stable until the page is actually getting * freed. */ - if (!PageAnon(page)) - return false; + 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)) @@ -3255,6 +3384,8 @@ void *sparse_buffer_alloc(unsigned long size); struct page * __populate_section_memmap(unsigned long pfn, unsigned long nr_pages, int nid, struct vmem_altmap *altmap, struct dev_pagemap *pgmap); +void pmd_init(void *addr); +void pud_init(void *addr); pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node); pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node); @@ -3266,8 +3397,14 @@ struct vmem_altmap; void *vmemmap_alloc_block_buf(unsigned long size, int node, struct vmem_altmap *altmap); void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); +void vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next); +int vmemmap_check_pmd(pmd_t *pmd, int node, + unsigned long addr, unsigned long next); int vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); +int vmemmap_populate_hugepages(unsigned long start, unsigned long end, + int node, struct vmem_altmap *altmap); int vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap); void vmemmap_populate_print_last(void); @@ -3290,7 +3427,6 @@ enum mf_flags { int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags); extern int memory_failure(unsigned long pfn, int flags); -extern void memory_failure_queue(unsigned long pfn, int flags); extern void memory_failure_queue_kick(int cpu); extern int unpoison_memory(unsigned long pfn); extern int sysctl_memory_failure_early_kill; @@ -3299,12 +3435,42 @@ extern void shake_page(struct page *p); extern atomic_long_t num_poisoned_pages __read_mostly; extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE -extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags); +extern void memory_failure_queue(unsigned long pfn, int flags); +extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared); +void num_poisoned_pages_inc(unsigned long pfn); +void num_poisoned_pages_sub(unsigned long pfn, long i); #else -static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags) +static inline void memory_failure_queue(unsigned long pfn, int flags) +{ +} + +static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, + bool *migratable_cleared) { return 0; } + +static inline void num_poisoned_pages_inc(unsigned long pfn) +{ +} + +static inline void num_poisoned_pages_sub(unsigned long pfn, long i) +{ +} +#endif + +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) +extern void memblk_nr_poison_inc(unsigned long pfn); +extern void memblk_nr_poison_sub(unsigned long pfn, long i); +#else +static inline void memblk_nr_poison_inc(unsigned long pfn) +{ +} + +static inline void memblk_nr_poison_sub(unsigned long pfn, long i) +{ +} #endif #ifndef arch_memory_failure |