diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 220 |
1 files changed, 192 insertions, 28 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 721f451c302..6507dde38b1 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -14,6 +14,7 @@ #include <linux/mm_types.h> #include <linux/range.h> #include <linux/pfn.h> +#include <linux/bit_spinlock.h> struct mempolicy; struct anon_vma; @@ -82,6 +83,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_GROWSUP 0x00000200 #else #define VM_GROWSUP 0x00000000 +#define VM_NOHUGEPAGE 0x00000200 /* MADV_NOHUGEPAGE marked this vma */ #endif #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ @@ -101,7 +103,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ +#ifndef CONFIG_TRANSPARENT_HUGEPAGE #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ +#else +#define VM_HUGEPAGE 0x01000000 /* MADV_HUGEPAGE marked this vma */ +#endif #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ @@ -131,7 +137,8 @@ extern unsigned int kobjsize(const void *objp); #define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ) /* - * special vmas that are non-mergable, non-mlock()able + * Special vmas that are non-mergable, non-mlock()able. + * Note: mm/huge_memory.c VM_NO_THP depends on this definition. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) @@ -145,6 +152,7 @@ extern pgprot_t protection_map[16]; #define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ #define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ +#define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ /* * This interface is used by x86 PAT code to identify a pfn mapping that is @@ -242,6 +250,7 @@ struct inode; * files which need it (119 of them) */ #include <linux/page-flags.h> +#include <linux/huge_mm.h> /* * Methods to modify the page usage count. @@ -305,6 +314,39 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif +static inline void compound_lock(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bit_spin_lock(PG_compound_lock, &page->flags); +#endif +} + +static inline void compound_unlock(struct page *page) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + bit_spin_unlock(PG_compound_lock, &page->flags); +#endif +} + +static inline unsigned long compound_lock_irqsave(struct page *page) +{ + unsigned long uninitialized_var(flags); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + local_irq_save(flags); + compound_lock(page); +#endif + return flags; +} + +static inline void compound_unlock_irqrestore(struct page *page, + unsigned long flags) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + compound_unlock(page); + local_irq_restore(flags); +#endif +} + static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) @@ -319,9 +361,29 @@ static inline int page_count(struct page *page) static inline void get_page(struct page *page) { - page = compound_head(page); - VM_BUG_ON(atomic_read(&page->_count) == 0); + /* + * Getting a normal page or the head of a compound page + * requires to already have an elevated page->_count. Only if + * we're getting a tail page, the elevated page->_count is + * required only in the head page, so for tail pages the + * bugcheck only verifies that the page->_count isn't + * negative. + */ + VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page)); atomic_inc(&page->_count); + /* + * Getting a tail page will elevate both the head and tail + * page->_count(s). + */ + if (unlikely(PageTail(page))) { + /* + * This is safe only because + * __split_huge_page_refcount can't run under + * get_page(). + */ + VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0); + atomic_inc(&page->first_page->_count); + } } static inline struct page *virt_to_head_page(const void *x) @@ -339,6 +401,34 @@ static inline void init_page_count(struct page *page) atomic_set(&page->_count, 1); } +/* + * PageBuddy() indicate that the page is free and in the buddy system + * (see mm/page_alloc.c). + * + * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to + * -2 so that an underflow of the page_mapcount() won't be mistaken + * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very + * efficiently by most CPU architectures. + */ +#define PAGE_BUDDY_MAPCOUNT_VALUE (-128) + +static inline int PageBuddy(struct page *page) +{ + return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE; +} + +static inline void __SetPageBuddy(struct page *page) +{ + VM_BUG_ON(atomic_read(&page->_mapcount) != -1); + atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE); +} + +static inline void __ClearPageBuddy(struct page *page) +{ + VM_BUG_ON(!PageBuddy(page)); + atomic_set(&page->_mapcount, -1); +} + void put_page(struct page *page); void put_pages_list(struct list_head *pages); @@ -370,11 +460,40 @@ static inline int compound_order(struct page *page) return (unsigned long)page[1].lru.prev; } +static inline int compound_trans_order(struct page *page) +{ + int order; + unsigned long flags; + + if (!PageHead(page)) + return 0; + + flags = compound_lock_irqsave(page); + order = compound_order(page); + compound_unlock_irqrestore(page, flags); + return order; +} + static inline void set_compound_order(struct page *page, unsigned long order) { page[1].lru.prev = (void *)order; } +#ifdef CONFIG_MMU +/* + * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when + * servicing faults for write access. In the normal case, do always want + * pte_mkwrite. But get_user_pages can cause write faults for mappings + * that do not have writing enabled, when used by access_process_vm. + */ +static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pte = pte_mkwrite(pte); + return pte; +} +#endif + /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of @@ -490,7 +609,7 @@ static inline void set_compound_order(struct page *page, unsigned long order) #endif /* - * Define the bit shifts to access each section. For non-existant + * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ @@ -657,7 +776,7 @@ static inline struct address_space *page_mapping(struct page *page) VM_BUG_ON(PageSlab(page)); if (unlikely(PageSwapCache(page))) mapping = &swapper_space; - else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) + else if ((unsigned long)mapping & PAGE_MAPPING_ANON) mapping = NULL; return mapping; } @@ -742,7 +861,14 @@ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) +/* + * Flags passed to show_mem() and __show_free_areas() to suppress output in + * various contexts. + */ +#define SHOW_MEM_FILTER_NODES (0x0001u) /* filter disallowed nodes */ + extern void show_free_areas(void); +extern void __show_free_areas(unsigned int flags); int shmem_lock(struct file *file, int lock, struct user_struct *user); struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); @@ -789,6 +915,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlb, * @pgd_entry: if set, called for each non-empty PGD (top-level) entry * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry * @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 @@ -854,7 +983,13 @@ static inline int handle_mm_fault(struct mm_struct *mm, extern int make_pages_present(unsigned long addr, unsigned long end); extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); +extern int access_remote_vm(struct mm_struct *mm, unsigned long addr, + void *buf, int len, int write); +int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int len, unsigned int foll_flags, + struct page **pages, struct vm_area_struct **vmas, + int *nonblocking); int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas); @@ -876,11 +1011,33 @@ int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); /* Is the vma a continuation of the stack vma above it? */ -static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr) +static inline int vma_growsdown(struct vm_area_struct *vma, unsigned long addr) { return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN); } +static inline int stack_guard_page_start(struct vm_area_struct *vma, + unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSDOWN) && + (vma->vm_start == addr) && + !vma_growsdown(vma->vm_prev, addr); +} + +/* Is the vma a continuation of the stack vma below it? */ +static inline int vma_growsup(struct vm_area_struct *vma, unsigned long addr) +{ + return vma && (vma->vm_start == addr) && (vma->vm_flags & VM_GROWSUP); +} + +static inline int stack_guard_page_end(struct vm_area_struct *vma, + unsigned long addr) +{ + return (vma->vm_flags & VM_GROWSUP) && + (vma->vm_end == addr) && + !vma_growsup(vma->vm_next, addr); +} + extern unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long old_addr, struct vm_area_struct *new_vma, unsigned long new_addr, unsigned long len); @@ -1064,7 +1221,8 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); #endif -int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address); +int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, + pmd_t *pmd, unsigned long address); int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); /* @@ -1133,16 +1291,18 @@ static inline void pgtable_page_dtor(struct page *page) pte_unmap(pte); \ } while (0) -#define pte_alloc_map(mm, pmd, address) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ - NULL: pte_offset_map(pmd, address)) +#define pte_alloc_map(mm, vma, pmd, address) \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma, \ + pmd, address))? \ + NULL: pte_offset_map(pmd, address)) #define pte_alloc_map_lock(mm, pmd, address, ptlp) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL, \ + pmd, address))? \ NULL: pte_offset_map_lock(mm, pmd, address, ptlp)) #define pte_alloc_kernel(pmd, address) \ - ((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ + ((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); @@ -1196,8 +1356,6 @@ int add_from_early_node_map(struct range *range, int az, int nr_range, int nid); u64 __init find_memory_core_early(int nid, u64 size, u64 align, u64 goal, u64 limit); -void *__alloc_memory_core_early(int nodeid, u64 size, u64 align, - u64 goal, u64 limit); typedef int (*work_fn_t)(unsigned long, unsigned long, void *); extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data); extern void sparse_memory_present_with_active_regions(int nid); @@ -1225,7 +1383,7 @@ extern void setup_per_zone_wmarks(void); extern void calculate_zone_inactive_ratio(struct zone *zone); extern void mem_init(void); extern void __init mmap_init(void); -extern void show_mem(void); +extern void show_mem(unsigned int flags); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); extern int after_bootmem; @@ -1415,6 +1573,11 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address, #define FOLL_GET 0x04 /* do get_page on page */ #define FOLL_DUMP 0x08 /* give error on hole if it would be zero */ #define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */ +#define FOLL_NOWAIT 0x20 /* if a disk transfer is needed, start the IO + * and return without waiting upon it */ +#define FOLL_MLOCK 0x40 /* mark page as mlocked */ +#define FOLL_SPLIT 0x80 /* don't return transhuge pages, split them */ +#define FOLL_HWPOISON 0x100 /* check page is hwpoisoned */ typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, void *data); @@ -1453,13 +1616,13 @@ static inline bool kernel_page_present(struct page *page) { return true; } #endif /* CONFIG_HIBERNATION */ #endif -extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk); +extern struct vm_area_struct *get_gate_vma(struct mm_struct *mm); #ifdef __HAVE_ARCH_GATE_AREA -int in_gate_area_no_task(unsigned long addr); -int in_gate_area(struct task_struct *task, unsigned long addr); +int in_gate_area_no_mm(unsigned long addr); +int in_gate_area(struct mm_struct *mm, unsigned long addr); #else -int in_gate_area_no_task(unsigned long addr); -#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);}) +int in_gate_area_no_mm(unsigned long addr); +#define in_gate_area(mm, addr) ({(void)mm; in_gate_area_no_mm(addr);}) #endif /* __HAVE_ARCH_GATE_AREA */ int drop_caches_sysctl_handler(struct ctl_table *, int, @@ -1507,16 +1670,17 @@ extern int sysctl_memory_failure_recovery; extern void shake_page(struct page *p, int access); extern atomic_long_t mce_bad_pages; extern int soft_offline_page(struct page *page, int flags); -#ifdef CONFIG_MEMORY_FAILURE -int is_hwpoison_address(unsigned long addr); -#else -static inline int is_hwpoison_address(unsigned long addr) -{ - return 0; -} -#endif extern void dump_page(struct page *page); +#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS) +extern void clear_huge_page(struct page *page, + unsigned long addr, + unsigned int pages_per_huge_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); +#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */ + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ |