diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 294 |
1 files changed, 160 insertions, 134 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 0334ca97c584..52269e56c514 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -70,11 +70,6 @@ static inline void totalram_pages_add(long count) atomic_long_add(count, &_totalram_pages); } -static inline void totalram_pages_set(long val) -{ - atomic_long_set(&_totalram_pages, val); -} - extern void * high_memory; extern int page_cluster; @@ -564,21 +559,6 @@ int vma_is_stack_for_current(struct vm_area_struct *vma); struct mmu_gather; struct inode; -#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) -static inline int pmd_devmap(pmd_t pmd) -{ - return 0; -} -static inline int pud_devmap(pud_t pud) -{ - return 0; -} -static inline int pgd_devmap(pgd_t pgd) -{ - return 0; -} -#endif - /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) @@ -640,24 +620,19 @@ unsigned long vmalloc_to_pfn(const void *addr); * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ -static inline bool is_vmalloc_addr(const void *x) -{ -#ifdef CONFIG_MMU - unsigned long addr = (unsigned long)x; - - return addr >= VMALLOC_START && addr < VMALLOC_END; -#else - return false; -#endif -} #ifndef is_ioremap_addr #define is_ioremap_addr(x) is_vmalloc_addr(x) #endif #ifdef CONFIG_MMU +extern bool is_vmalloc_addr(const void *x); extern int is_vmalloc_or_module_addr(const void *x); #else +static inline bool is_vmalloc_addr(const void *x) +{ + return false; +} static inline int is_vmalloc_or_module_addr(const void *x) { return 0; @@ -695,11 +670,6 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags) extern void kvfree(const void *addr); -static inline atomic_t *compound_mapcount_ptr(struct page *page) -{ - return &page[1].compound_mapcount; -} - static inline int compound_mapcount(struct page *page) { VM_BUG_ON_PAGE(!PageCompound(page), page); @@ -805,6 +775,24 @@ static inline void set_compound_order(struct page *page, unsigned int order) page[1].compound_order = order; } +/* Returns the number of pages in this potentially compound page. */ +static inline unsigned long compound_nr(struct page *page) +{ + return 1UL << compound_order(page); +} + +/* Returns the number of bytes in this potentially compound page. */ +static inline unsigned long page_size(struct page *page) +{ + return PAGE_SIZE << compound_order(page); +} + +/* Returns the number of bits needed for the number of bytes in a page */ +static inline unsigned int page_shift(struct page *page) +{ + return PAGE_SHIFT + compound_order(page); +} + void free_compound_page(struct page *page); #ifdef CONFIG_MMU @@ -923,10 +911,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf); #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) -#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS -#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS -#endif - #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) @@ -954,9 +938,10 @@ static inline bool is_zone_device_page(const struct page *page) #endif #ifdef CONFIG_DEV_PAGEMAP_OPS -void __put_devmap_managed_page(struct page *page); +void free_devmap_managed_page(struct page *page); DECLARE_STATIC_KEY_FALSE(devmap_managed_key); -static inline bool put_devmap_managed_page(struct page *page) + +static inline bool page_is_devmap_managed(struct page *page) { if (!static_branch_unlikely(&devmap_managed_key)) return false; @@ -965,7 +950,6 @@ static inline bool put_devmap_managed_page(struct page *page) switch (page->pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_FS_DAX: - __put_devmap_managed_page(page); return true; default: break; @@ -973,11 +957,17 @@ static inline bool put_devmap_managed_page(struct page *page) return false; } +void put_devmap_managed_page(struct page *page); + #else /* CONFIG_DEV_PAGEMAP_OPS */ -static inline bool put_devmap_managed_page(struct page *page) +static inline bool page_is_devmap_managed(struct page *page) { return false; } + +static inline void put_devmap_managed_page(struct page *page) +{ +} #endif /* CONFIG_DEV_PAGEMAP_OPS */ static inline bool is_device_private_page(const struct page *page) @@ -1030,36 +1020,37 @@ static inline void put_page(struct page *page) * need to inform the device driver through callback. See * include/linux/memremap.h and HMM for details. */ - if (put_devmap_managed_page(page)) + if (page_is_devmap_managed(page)) { + put_devmap_managed_page(page); return; + } if (put_page_testzero(page)) __put_page(page); } /** - * put_user_page() - release a gup-pinned page + * unpin_user_page() - release a gup-pinned page * @page: pointer to page to be released * - * Pages that were pinned via get_user_pages*() must be released via - * either put_user_page(), or one of the put_user_pages*() routines - * below. This is so that eventually, pages that are pinned via - * get_user_pages*() can be separately tracked and uniquely handled. In - * particular, interactions with RDMA and filesystems need special - * handling. + * Pages that were pinned via pin_user_pages*() must be released via either + * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so + * that eventually such pages can be separately tracked and uniquely handled. In + * particular, interactions with RDMA and filesystems need special handling. * - * put_user_page() and put_page() are not interchangeable, despite this early - * implementation that makes them look the same. put_user_page() calls must - * be perfectly matched up with get_user_page() calls. + * unpin_user_page() and put_page() are not interchangeable, despite this early + * implementation that makes them look the same. unpin_user_page() calls must + * be perfectly matched up with pin*() calls. */ -static inline void put_user_page(struct page *page) +static inline void unpin_user_page(struct page *page) { put_page(page); } -void put_user_pages_dirty(struct page **pages, unsigned long npages); -void put_user_pages_dirty_lock(struct page **pages, unsigned long npages); -void put_user_pages(struct page **pages, unsigned long npages); +void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty); + +void unpin_user_pages(struct page **pages, unsigned long npages); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS @@ -1405,7 +1396,11 @@ extern void pagefault_out_of_memory(void); extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); +#ifdef CONFIG_MMU extern bool can_do_mlock(void); +#else +static inline bool can_do_mlock(void) { return false; } +#endif extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); @@ -1430,54 +1425,8 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long address, void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); -/** - * mm_walk - callbacks for walk_page_range - * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry - * this handler should only handle pud_trans_huge() puds. - * the pmd_entry or pte_entry callbacks will be used for - * regular PUDs. - * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry - * this handler is required to be able to handle - * pmd_trans_huge() pmds. They may simply choose to - * split_huge_page() instead of handling it explicitly. - * @pte_entry: if set, called for each non-empty PTE (4th-level) entry - * @pte_hole: if set, called for each hole at all levels - * @hugetlb_entry: if set, called for each hugetlb entry - * @test_walk: caller specific callback function to determine whether - * we walk over the current vma or not. Returning 0 - * value means "do page table walk over the current vma," - * and a negative one means "abort current page table walk - * right now." 1 means "skip the current vma." - * @mm: mm_struct representing the target process of page table walk - * @vma: vma currently walked (NULL if walking outside vmas) - * @private: private data for callbacks' usage - * - * (see the comment on walk_page_range() for more details) - */ -struct mm_walk { - int (*pud_entry)(pud_t *pud, unsigned long addr, - unsigned long next, struct mm_walk *walk); - int (*pmd_entry)(pmd_t *pmd, unsigned long addr, - unsigned long next, struct mm_walk *walk); - int (*pte_entry)(pte_t *pte, unsigned long addr, - unsigned long next, struct mm_walk *walk); - int (*pte_hole)(unsigned long addr, unsigned long next, - struct mm_walk *walk); - int (*hugetlb_entry)(pte_t *pte, unsigned long hmask, - unsigned long addr, unsigned long next, - struct mm_walk *walk); - int (*test_walk)(unsigned long addr, unsigned long next, - struct mm_walk *walk); - struct mm_struct *mm; - struct vm_area_struct *vma; - void *private; -}; - struct mmu_notifier_range; -int walk_page_range(unsigned long addr, unsigned long end, - struct mm_walk *walk); -int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk); void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); int copy_page_range(struct mm_struct *dst, struct mm_struct *src, @@ -1549,9 +1498,16 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *locked); +long pin_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas, int *locked); long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas); +long pin_user_pages(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); long get_user_pages_locked(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, @@ -1559,6 +1515,8 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); +int pin_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc); int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, @@ -1671,19 +1629,27 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member) return (unsigned long)val; } +void mm_trace_rss_stat(struct mm_struct *mm, int member, long count); + static inline void add_mm_counter(struct mm_struct *mm, int member, long value) { - atomic_long_add(value, &mm->rss_stat.count[member]); + long count = atomic_long_add_return(value, &mm->rss_stat.count[member]); + + mm_trace_rss_stat(mm, member, count); } static inline void inc_mm_counter(struct mm_struct *mm, int member) { - atomic_long_inc(&mm->rss_stat.count[member]); + long count = atomic_long_inc_return(&mm->rss_stat.count[member]); + + mm_trace_rss_stat(mm, member, count); } static inline void dec_mm_counter(struct mm_struct *mm, int member) { - atomic_long_dec(&mm->rss_stat.count[member]); + long count = atomic_long_dec_return(&mm->rss_stat.count[member]); + + mm_trace_rss_stat(mm, member, count); } /* Optimized variant when page is already known not to be PageAnon */ @@ -1873,12 +1839,12 @@ static inline void mm_dec_nr_ptes(struct mm_struct *mm) {} int __pte_alloc(struct mm_struct *mm, pmd_t *pmd); int __pte_alloc_kernel(pmd_t *pmd); +#if defined(CONFIG_MMU) + /* - * The following ifdef needed to get the 4level-fixup.h header to work. - * Remove it when 4level-fixup.h has been removed. + * The following ifdef needed to get the 5level-fixup.h header to work. + * Remove it when 5level-fixup.h has been removed. */ -#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) - #ifndef __ARCH_HAS_5LEVEL_HACK static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) @@ -1900,7 +1866,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? NULL: pmd_offset(pud, address); } -#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ +#endif /* CONFIG_MMU */ #if USE_SPLIT_PTE_PTLOCKS #if ALLOC_SPLIT_PTLOCKS @@ -1972,7 +1938,7 @@ static inline void pgtable_init(void) pgtable_cache_init(); } -static inline bool pgtable_page_ctor(struct page *page) +static inline bool pgtable_pte_page_ctor(struct page *page) { if (!ptlock_init(page)) return false; @@ -1981,7 +1947,7 @@ static inline bool pgtable_page_ctor(struct page *page) return true; } -static inline void pgtable_page_dtor(struct page *page) +static inline void pgtable_pte_page_dtor(struct page *page) { ptlock_free(page); __ClearPageTable(page); @@ -2216,12 +2182,6 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if !defined(CONFIG_FLAT_NODE_MEM_MAP) -void zero_resv_unavail(void); -#else -static inline void zero_resv_unavail(void) {} -#endif - extern void set_dma_reserve(unsigned long new_dma_reserve); extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context, struct vmem_altmap *); @@ -2242,9 +2202,6 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); -extern void zone_pcp_update(struct zone *zone); -extern void zone_pcp_reset(struct zone *zone); - /* page_alloc.c */ extern int min_free_kbytes; extern int watermark_boost_factor; @@ -2351,6 +2308,8 @@ extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, struct page **pages); +unsigned long randomize_stack_top(unsigned long stack_top); + extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long mmap_region(struct file *file, unsigned long addr, @@ -2364,6 +2323,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); +extern int do_madvise(unsigned long start, size_t len_in, int behavior); static inline unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, @@ -2569,6 +2529,8 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); +vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len); @@ -2614,13 +2576,16 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_COW 0x4000 /* internal GUP flag */ #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 */ /* - * NOTE on FOLL_LONGTERM: + * 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 contrasted with - * iov_iter_get_pages() where usages which are transient. + * 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 @@ -2635,11 +2600,39 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, * 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 + * FAULT_FLAG_ALLOW_RETRY. * - * In the CMA case: longterm pins in a CMA region would unnecessarily fragment - * that region. And so CMA attempts to migrate the page before pinning when + * 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/vm/pin_user_pages.rst for more information. */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) @@ -2656,7 +2649,9 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data); extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, unsigned long size, pte_fn_t fn, void *data); - +extern int apply_to_existing_page_range(struct mm_struct *mm, + unsigned long address, unsigned long size, + pte_fn_t fn, void *data); #ifdef CONFIG_PAGE_POISONING extern bool page_poisoning_enabled(void); @@ -2691,14 +2686,26 @@ static inline bool want_init_on_free(void) !page_poisoning_enabled(); } -#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT -DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); +#ifdef CONFIG_DEBUG_PAGEALLOC +extern void init_debug_pagealloc(void); #else -DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +static inline void init_debug_pagealloc(void) {} #endif +extern bool _debug_pagealloc_enabled_early; +DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) { + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && + _debug_pagealloc_enabled_early; +} + +/* + * For use in fast paths after init_debug_pagealloc() has run, or when a + * false negative result is not harmful when called too early. + */ +static inline bool debug_pagealloc_enabled_static(void) +{ if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; @@ -2806,7 +2813,7 @@ extern int sysctl_memory_failure_early_kill; extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t num_poisoned_pages __read_mostly; -extern int soft_offline_page(struct page *page, int flags); +extern int soft_offline_page(unsigned long pfn, int flags); /* @@ -2891,5 +2898,24 @@ void __init setup_nr_node_ids(void); static inline void setup_nr_node_ids(void) {} #endif +extern int memcmp_pages(struct page *page1, struct page *page2); + +static inline int pages_identical(struct page *page1, struct page *page2) +{ + return !memcmp_pages(page1, page2); +} + +#ifdef CONFIG_MAPPING_DIRTY_HELPERS +unsigned long clean_record_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr, + pgoff_t bitmap_pgoff, + unsigned long *bitmap, + pgoff_t *start, + pgoff_t *end); + +unsigned long wp_shared_mapping_range(struct address_space *mapping, + pgoff_t first_index, pgoff_t nr); +#endif + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ |
