diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 188 |
1 files changed, 127 insertions, 61 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index a92c8d73aeaf..0d65dd72c0f4 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -76,6 +76,10 @@ extern int mmap_rnd_compat_bits __read_mostly; #define page_to_virt(x) __va(PFN_PHYS(page_to_pfn(x))) #endif +#ifndef lm_alias +#define lm_alias(x) __va(__pa_symbol(x)) +#endif + /* * To prevent common memory management code establishing * a zero page mapping on a read fault. @@ -281,6 +285,17 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_REMOTE 0x80 /* faulting for non current tsk/mm */ #define FAULT_FLAG_INSTRUCTION 0x100 /* The fault was during an instruction fetch */ +#define FAULT_FLAG_TRACE \ + { FAULT_FLAG_WRITE, "WRITE" }, \ + { FAULT_FLAG_MKWRITE, "MKWRITE" }, \ + { FAULT_FLAG_ALLOW_RETRY, "ALLOW_RETRY" }, \ + { FAULT_FLAG_RETRY_NOWAIT, "RETRY_NOWAIT" }, \ + { FAULT_FLAG_KILLABLE, "KILLABLE" }, \ + { FAULT_FLAG_TRIED, "TRIED" }, \ + { FAULT_FLAG_USER, "USER" }, \ + { FAULT_FLAG_REMOTE, "REMOTE" }, \ + { FAULT_FLAG_INSTRUCTION, "INSTRUCTION" } + /* * vm_fault is filled by the the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask @@ -292,36 +307,26 @@ 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' */ + pud_t *pud; /* Pointer to pud 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. @@ -339,6 +344,13 @@ struct fault_env { */ }; +/* page entry size for vm->huge_fault() */ +enum page_entry_size { + PE_SIZE_PTE = 0, + PE_SIZE_PMD, + PE_SIZE_PUD, +}; + /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer @@ -348,18 +360,17 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*mremap)(struct vm_area_struct * area); - 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, + int (*fault)(struct vm_fault *vmf); + int (*huge_fault)(struct vm_fault *vmf, enum page_entry_size pe_size); + 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 * writable, if an error is returned it will cause a SIGBUS */ - int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf); + int (*page_mkwrite)(struct vm_fault *vmf); /* same as page_mkwrite when using VM_PFNMAP|VM_MIXEDMAP */ - int (*pfn_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf); + int (*pfn_mkwrite)(struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs that can switch between memory and hardware @@ -415,6 +426,10 @@ static inline int pmd_devmap(pmd_t pmd) { return 0; } +static inline int pud_devmap(pud_t pud) +{ + return 0; +} #endif /* @@ -625,8 +640,10 @@ 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 /* @@ -1110,7 +1127,7 @@ 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 */ @@ -1118,6 +1135,20 @@ static inline void clear_page_pfmemalloc(struct page *page) VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE | \ VM_FAULT_FALLBACK) +#define VM_FAULT_RESULT_TRACE \ + { VM_FAULT_OOM, "OOM" }, \ + { VM_FAULT_SIGBUS, "SIGBUS" }, \ + { VM_FAULT_MAJOR, "MAJOR" }, \ + { VM_FAULT_WRITE, "WRITE" }, \ + { VM_FAULT_HWPOISON, "HWPOISON" }, \ + { VM_FAULT_HWPOISON_LARGE, "HWPOISON_LARGE" }, \ + { VM_FAULT_SIGSEGV, "SIGSEGV" }, \ + { VM_FAULT_NOPAGE, "NOPAGE" }, \ + { VM_FAULT_LOCKED, "LOCKED" }, \ + { VM_FAULT_RETRY, "RETRY" }, \ + { VM_FAULT_FALLBACK, "FALLBACK" }, \ + { VM_FAULT_DONE_COW, "DONE_COW" } + /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) #define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf) @@ -1135,18 +1166,7 @@ extern void pagefault_out_of_memory(void); */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ -extern void show_free_areas(unsigned int flags); -extern bool skip_free_areas_node(unsigned int flags, int nid); - -int shmem_zero_setup(struct vm_area_struct *); -#ifdef CONFIG_SHMEM -bool shmem_mapping(struct address_space *mapping); -#else -static inline bool shmem_mapping(struct address_space *mapping) -{ - return false; -} -#endif +extern void show_free_areas(unsigned int flags, nodemask_t *nodemask); extern bool can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); @@ -1159,8 +1179,6 @@ struct zap_details { struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ - bool ignore_dirty; /* Ignore dirty pages */ - bool check_swap_entries; /* Check also swap entries */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, @@ -1171,12 +1189,16 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, - unsigned long size, struct zap_details *); + unsigned long size); 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 @@ -1196,6 +1218,8 @@ void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, * (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, @@ -1221,6 +1245,8 @@ 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, @@ -1270,19 +1296,18 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * unsigned int gup_flags); extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, 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_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); + 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 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(struct task_struct *tsk, struct mm_struct *mm, - unsigned long start, unsigned long nr_pages, - struct page **pages, unsigned int gup_flags); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); int get_user_pages_fast(unsigned long start, int nr_pages, int write, @@ -1365,6 +1390,16 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma) return !vma->vm_ops; } +#ifdef CONFIG_SHMEM +/* + * The vma_is_shmem is not inline because it is used only by slow + * paths in userfault. + */ +bool vma_is_shmem(struct vm_area_struct *vma); +#else +static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; } +#endif + static inline int stack_guard_page_start(struct vm_area_struct *vma, unsigned long addr) { @@ -1768,6 +1803,26 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd) return ptl; } +/* + * No scalability reason to split PUD locks yet, but follow the same pattern + * as the PMD locks to make it easier if we decide to. The VM should not be + * considered ready to switch to split PUD locks yet; there may be places + * which need to be converted from page_table_lock. + */ +static inline spinlock_t *pud_lockptr(struct mm_struct *mm, pud_t *pud) +{ + return &mm->page_table_lock; +} + +static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud) +{ + spinlock_t *ptl = pud_lockptr(mm, pud); + + spin_lock(ptl); + 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); @@ -1904,7 +1959,7 @@ extern void setup_per_zone_wmarks(void); extern int __meminit init_per_zone_wmark_min(void); extern void mem_init(void); extern void __init mmap_init(void); -extern void show_mem(unsigned int flags); +extern void show_mem(unsigned int flags, nodemask_t *nodemask); extern long si_mem_available(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); @@ -1912,8 +1967,8 @@ extern void si_meminfo_node(struct sysinfo *val, int nid); extern unsigned long arch_reserved_kernel_pages(void); #endif -extern __printf(2, 3) -void warn_alloc(gfp_t gfp_mask, const char *fmt, ...); +extern __printf(3, 4) +void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...); extern void setup_per_cpu_pageset(void); @@ -1976,8 +2031,10 @@ extern struct vm_area_struct *vma_merge(struct mm_struct *, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); -extern int split_vma(struct mm_struct *, - struct vm_area_struct *, unsigned long addr, int new_below); +extern int __split_vma(struct mm_struct *, struct vm_area_struct *, + unsigned long addr, int new_below); +extern int split_vma(struct mm_struct *, struct vm_area_struct *, + unsigned long addr, int new_below); extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, struct rb_node **, struct rb_node *); @@ -2025,18 +2082,22 @@ extern int install_special_mapping(struct mm_struct *mm, 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, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff); + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf); extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate); -extern int do_munmap(struct mm_struct *, unsigned long, size_t); + vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, + struct list_head *uf); +extern int do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf); static inline unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, - unsigned long pgoff, unsigned long *populate) + unsigned long pgoff, unsigned long *populate, + struct list_head *uf) { - return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate); + return do_mmap(file, addr, len, prot, flags, 0, pgoff, populate, uf); } #ifdef CONFIG_MMU @@ -2053,6 +2114,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len) {} /* These take the mm semaphore themselves */ extern int __must_check vm_brk(unsigned long, unsigned long); +extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long); extern int vm_munmap(unsigned long, size_t); extern unsigned long __must_check vm_mmap(struct file *, unsigned long, unsigned long, unsigned long, @@ -2096,10 +2158,10 @@ extern void truncate_inode_pages_range(struct address_space *, 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 int filemap_fault(struct vm_fault *vmf); +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); +extern int filemap_page_mkwrite(struct vm_fault *vmf); /* mm/page-writeback.c */ int write_one_page(struct page *page, int wait); @@ -2404,6 +2466,10 @@ extern void clear_huge_page(struct page *page, extern void copy_user_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma, unsigned int pages_per_huge_page); +extern long copy_huge_page_from_user(struct page *dst_page, + const void __user *usr_src, + unsigned int pages_per_huge_page, + bool allow_pagefault); #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ extern struct page_ext_operations debug_guardpage_ops; |