diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 141 |
1 files changed, 94 insertions, 47 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index c97ea3b694e6..73a044ed6981 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; @@ -625,24 +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; @@ -921,10 +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) @@ -952,9 +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; @@ -963,7 +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; @@ -971,11 +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) @@ -1028,37 +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_lock(struct page **pages, unsigned long npages, - bool make_dirty); +void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, + bool make_dirty); -void put_user_pages(struct page **pages, unsigned long npages); +void unpin_user_pages(struct page **pages, unsigned long npages); #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS @@ -1506,9 +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, @@ -1516,6 +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, @@ -2328,6 +2329,7 @@ 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, @@ -2579,13 +2581,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #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 @@ -2600,11 +2604,39 @@ 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) @@ -2621,6 +2653,9 @@ 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); @@ -2655,14 +2690,26 @@ 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; |