diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 119 |
1 files changed, 53 insertions, 66 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index ef815b9cd426..b84615b0f64c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -126,7 +126,7 @@ extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *, #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */ -#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)addr, PAGE_SIZE) +#define PAGE_ALIGNED(addr) IS_ALIGNED((unsigned long)(addr), PAGE_SIZE) /* * Linux kernel virtual memory manager primitives. @@ -292,36 +292,23 @@ extern pgprot_t protection_map[16]; * pgoff should be used in favour of virtual_address, if possible. */ struct vm_fault { + struct vm_area_struct *vma; /* Target VMA */ unsigned int flags; /* FAULT_FLAG_xxx flags */ gfp_t gfp_mask; /* gfp mask to be used for allocations */ pgoff_t pgoff; /* Logical page offset based on vma */ - void __user *virtual_address; /* Faulting virtual address */ + unsigned long address; /* Faulting virtual address */ + pmd_t *pmd; /* Pointer to pmd entry matching + * the 'address' */ + pte_t orig_pte; /* Value of PTE at the time of fault */ - struct page *cow_page; /* Handler may choose to COW */ + struct page *cow_page; /* Page handler may use for COW fault */ + struct mem_cgroup *memcg; /* Cgroup cow_page belongs to */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ - void *entry; /* ->fault handler can alternatively - * return locked DAX entry. In that - * case handler should return - * VM_FAULT_DAX_LOCKED and fill in - * entry here. - */ -}; - -/* - * Page fault context: passes though page fault handler instead of endless list - * of function arguments. - */ -struct fault_env { - struct vm_area_struct *vma; /* Target VMA */ - unsigned long address; /* Faulting virtual address */ - unsigned int flags; /* FAULT_FLAG_xxx flags */ - pmd_t *pmd; /* Pointer to pmd entry matching - * the 'address' - */ + /* These three entries are valid only while holding ptl lock */ pte_t *pte; /* Pointer to pte entry matching * the 'address'. NULL if the page * table hasn't been allocated. @@ -351,7 +338,7 @@ struct vm_operations_struct { int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); int (*pmd_fault)(struct vm_area_struct *, unsigned long address, pmd_t *, unsigned int flags); - void (*map_pages)(struct fault_env *fe, + void (*map_pages)(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); /* notification that a previously read-only page is about to become @@ -625,8 +612,10 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) return pte; } -int alloc_set_pte(struct fault_env *fe, struct mem_cgroup *memcg, +int alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg, struct page *page); +int finish_fault(struct vm_fault *vmf); +int finish_mkwrite_fault(struct vm_fault *vmf); #endif /* @@ -1048,28 +1037,16 @@ struct address_space *page_file_mapping(struct page *page) return page->mapping; } -/* - * Return the pagecache index of the passed page. Regular pagecache pages - * use ->index whereas swapcache pages use ->private - */ -static inline pgoff_t page_index(struct page *page) -{ - if (unlikely(PageSwapCache(page))) - return page_private(page); - return page->index; -} - extern pgoff_t __page_file_index(struct page *page); /* - * Return the file index of the page. Regular pagecache pages use ->index - * whereas swapcache pages use swp_offset(->private) + * Return the pagecache index of the passed page. Regular pagecache pages + * use ->index whereas swapcache pages use swp_offset(->private) */ -static inline pgoff_t page_file_index(struct page *page) +static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); - return page->index; } @@ -1122,7 +1099,7 @@ static inline void clear_page_pfmemalloc(struct page *page) #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ #define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ #define VM_FAULT_FALLBACK 0x0800 /* huge page fault failed, fall back to small */ -#define VM_FAULT_DAX_LOCKED 0x1000 /* ->fault has locked DAX entry */ +#define VM_FAULT_DONE_COW 0x1000 /* ->fault has fully handled COW */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ @@ -1197,10 +1174,10 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * @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. A positive returned + * 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." 0 means "skip the current vma." + * 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 @@ -1233,6 +1210,8 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma); void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows); +int follow_pte_pmd(struct mm_struct *mm, unsigned long address, + pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp); int follow_pfn(struct vm_area_struct *vma, unsigned long address, unsigned long *pfn); int follow_phys(struct vm_area_struct *vma, unsigned long address, @@ -1278,29 +1257,24 @@ static inline int fixup_user_fault(struct task_struct *tsk, } #endif -extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); +extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, + unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, - void *buf, int len, int write); + void *buf, int len, unsigned int gup_flags); +extern int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, + unsigned long addr, void *buf, int len, unsigned int gup_flags); -long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - unsigned int foll_flags, struct page **pages, - struct vm_area_struct **vmas, int *nonblocking); long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, - struct vm_area_struct **vmas); + 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, - int write, int force, struct page **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, - int write, int force, struct page **pages, int *locked); -long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages, - unsigned int gup_flags); + unsigned int gup_flags, struct page **pages, int *locked); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, - int write, int force, struct page **pages); + struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); @@ -1318,7 +1292,7 @@ struct frame_vector { struct frame_vector *frame_vector_create(unsigned int nr_frames); void frame_vector_destroy(struct frame_vector *vec); int get_vaddr_frames(unsigned long start, unsigned int nr_pfns, - bool write, bool force, struct frame_vector *vec); + unsigned int gup_flags, struct frame_vector *vec); void put_vaddr_frames(struct frame_vector *vec); int frame_vector_to_pages(struct frame_vector *vec); void frame_vector_to_pfns(struct frame_vector *vec); @@ -1403,7 +1377,7 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma, !vma_growsup(vma->vm_next, addr); } -int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t); +int vma_is_stack_for_current(struct vm_area_struct *vma); extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, @@ -1529,7 +1503,7 @@ static inline int pte_devmap(pte_t pte) } #endif -int vma_wants_writenotify(struct vm_area_struct *vma); +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); @@ -1784,6 +1758,8 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } +extern void __init pagecache_init(void); + extern void free_area_init(unsigned long * zones_size); extern void free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); @@ -1924,10 +1900,12 @@ extern void show_mem(unsigned int flags); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); +#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES +extern unsigned long arch_reserved_kernel_pages(void); +#endif -extern __printf(3, 4) -void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, - const char *fmt, ...); +extern __printf(2, 3) +void warn_alloc(gfp_t gfp_mask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); @@ -1977,8 +1955,14 @@ 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); +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, @@ -2019,6 +2003,8 @@ extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); +extern bool vma_is_special_mapping(const struct vm_area_struct *vma, + const struct vm_special_mapping *sm); extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, unsigned long flags, @@ -2103,7 +2089,7 @@ extern void truncate_inode_pages_final(struct address_space *); /* generic vm_area_ops exported for stackable file systems */ extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); -extern void filemap_map_pages(struct fault_env *fe, +extern void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff); extern int filemap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf); @@ -2234,6 +2220,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_TRIED 0x800 /* a retry, previous pass started an IO */ #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ +#define FOLL_COW 0x4000 /* internal GUP flag */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); |