diff options
Diffstat (limited to 'include/linux/mm.h')
-rw-r--r-- | include/linux/mm.h | 135 |
1 files changed, 102 insertions, 33 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 6b10c21630f5..0e8834ac32b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -124,10 +124,45 @@ extern int mmap_rnd_compat_bits __read_mostly; /* * On some architectures it is expensive to call memset() for small sizes. - * Those architectures should provide their own implementation of "struct page" - * zeroing by defining this macro in <asm/pgtable.h>. + * If an architecture decides to implement their own version of + * mm_zero_struct_page they should wrap the defines below in a #ifndef and + * define their own version of this macro in <asm/pgtable.h> */ -#ifndef mm_zero_struct_page +#if BITS_PER_LONG == 64 +/* This function must be updated when the size of struct page grows above 80 + * or reduces below 56. The idea that compiler optimizes out switch() + * statement, and only leaves move/store instructions. Also the compiler can + * combine write statments if they are both assignments and can be reordered, + * this can result in several of the writes here being dropped. + */ +#define mm_zero_struct_page(pp) __mm_zero_struct_page(pp) +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 */ + BUILD_BUG_ON(sizeof(struct page) & 7); + BUILD_BUG_ON(sizeof(struct page) < 56); + BUILD_BUG_ON(sizeof(struct page) > 80); + + switch (sizeof(struct page)) { + case 80: + _pp[9] = 0; /* fallthrough */ + case 72: + _pp[8] = 0; /* fallthrough */ + case 64: + _pp[7] = 0; /* fallthrough */ + case 56: + _pp[6] = 0; + _pp[5] = 0; + _pp[4] = 0; + _pp[3] = 0; + _pp[2] = 0; + _pp[1] = 0; + _pp[0] = 0; + } +} +#else #define mm_zero_struct_page(pp) ((void)memset((pp), 0, sizeof(struct page))) #endif @@ -501,9 +536,6 @@ static inline void vma_set_anonymous(struct vm_area_struct *vma) struct mmu_gather; struct inode; -#define page_private(page) ((page)->private) -#define set_page_private(page, v) ((page)->private = (v)) - #if !defined(__HAVE_ARCH_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE) static inline int pmd_devmap(pmd_t pmd) { @@ -1007,6 +1039,30 @@ static inline void put_page(struct page *page) __put_page(page); } +/** + * put_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. + * + * 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. + */ +static inline void put_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); + #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif @@ -1505,21 +1561,8 @@ long get_user_pages_locked(unsigned long start, unsigned long nr_pages, long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); -#if defined(CONFIG_FS_DAX) || defined(CONFIG_CMA) -long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, - unsigned int gup_flags, struct page **pages, - struct vm_area_struct **vmas); -#else -static inline long get_user_pages_longterm(unsigned long start, - unsigned long nr_pages, unsigned int gup_flags, - struct page **pages, struct vm_area_struct **vmas) -{ - return get_user_pages(start, nr_pages, gup_flags, pages, vmas); -} -#endif /* CONFIG_FS_DAX */ - -int get_user_pages_fast(unsigned long start, int nr_pages, int write, - struct page **pages); +int get_user_pages_fast(unsigned long start, int nr_pages, + unsigned int gup_flags, struct page **pages); /* Container for pinned pfns / pages */ struct frame_vector { @@ -2533,6 +2576,10 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); +int vm_map_pages(struct vm_area_struct *vma, struct page **pages, + unsigned long num); +int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages, + unsigned long num); vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, @@ -2583,6 +2630,34 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address, #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #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 */ + +/* + * NOTE on FOLL_LONGTERM: + * + * 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. + * + * 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: longterm 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. + */ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags) { @@ -2610,37 +2685,31 @@ static inline void kernel_poison_pages(struct page *page, int numpages, int enable) { } #endif -#ifdef CONFIG_DEBUG_PAGEALLOC extern bool _debug_pagealloc_enabled; -extern void __kernel_map_pages(struct page *page, int numpages, int enable); static inline bool debug_pagealloc_enabled(void) { - return _debug_pagealloc_enabled; + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && _debug_pagealloc_enabled; } +#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_ARCH_HAS_SET_DIRECT_MAP) +extern void __kernel_map_pages(struct page *page, int numpages, int enable); + static inline void kernel_map_pages(struct page *page, int numpages, int enable) { - if (!debug_pagealloc_enabled()) - return; - __kernel_map_pages(page, numpages, enable); } #ifdef CONFIG_HIBERNATION extern bool kernel_page_present(struct page *page); #endif /* CONFIG_HIBERNATION */ -#else /* CONFIG_DEBUG_PAGEALLOC */ +#else /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ static inline void kernel_map_pages(struct page *page, int numpages, int enable) {} #ifdef CONFIG_HIBERNATION static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ -static inline bool debug_pagealloc_enabled(void) -{ - return false; -} -#endif /* CONFIG_DEBUG_PAGEALLOC */ +#endif /* CONFIG_DEBUG_PAGEALLOC || CONFIG_ARCH_HAS_SET_DIRECT_MAP */ #ifdef __HAVE_ARCH_GATE_AREA extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); |