diff options
Diffstat (limited to 'include/linux/mm.h')
| -rw-r--r-- | include/linux/mm.h | 189 |
1 files changed, 98 insertions, 91 deletions
diff --git a/include/linux/mm.h b/include/linux/mm.h index 4f2b42c92664..1692dd6cb915 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2,7 +2,6 @@ #define _LINUX_MM_H #include <linux/errno.h> -#include <linux/capability.h> #ifdef __KERNEL__ @@ -11,7 +10,6 @@ #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/prio_tree.h> -#include <linux/fs.h> #include <linux/mutex.h> #include <linux/debug_locks.h> #include <linux/backing-dev.h> @@ -19,7 +17,9 @@ struct mempolicy; struct anon_vma; +struct file_ra_state; struct user_struct; +struct writeback_control; #ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; @@ -27,7 +27,6 @@ extern unsigned long max_mapnr; extern unsigned long num_physpages; extern void * high_memory; -extern unsigned long vmalloc_earlyreserve; extern int page_cluster; #ifdef CONFIG_SYSCTL @@ -164,13 +163,14 @@ extern unsigned int kobjsize(const void *objp); #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_RESERVED 0x00080000 /* Count as reserved_vm like IO */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ -#define VM_XIP 0x00200000 /* Execute In Place from ROM/flash */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ #define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ +#define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ + #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif @@ -193,6 +193,30 @@ extern unsigned int kobjsize(const void *objp); */ extern pgprot_t protection_map[16]; +#define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ +#define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ + + +/* + * 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 + * of VM_FAULT_xxx flags that give details about how the fault was handled. + * + * pgoff should be used in favour of virtual_address, if possible. If pgoff + * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear + * mapping support. + */ +struct vm_fault { + unsigned int flags; /* FAULT_FLAG_xxx flags */ + pgoff_t pgoff; /* Logical page offset based on vma */ + void __user *virtual_address; /* Faulting virtual address */ + + struct page *page; /* ->fault handlers should return a + * page here, unless VM_FAULT_NOPAGE + * is set (which is also implied by + * VM_FAULT_ERROR). + */ +}; /* * These are the virtual MM functions - opening of an area, closing and @@ -202,9 +226,11 @@ extern pgprot_t protection_map[16]; struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); - struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type); - unsigned long (*nopfn)(struct vm_area_struct * area, unsigned long address); - int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock); + int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); + struct page *(*nopage)(struct vm_area_struct *area, + unsigned long address, int *type); + unsigned long (*nopfn)(struct vm_area_struct *area, + unsigned long address); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ @@ -602,6 +628,7 @@ static inline struct address_space *page_mapping(struct page *page) { struct address_space *mapping = page->mapping; + VM_BUG_ON(PageSlab(page)); if (unlikely(PageSwapCache(page))) mapping = &swapper_space; #ifdef CONFIG_SLUB @@ -657,7 +684,6 @@ static inline int page_mapped(struct page *page) */ #define NOPAGE_SIGBUS (NULL) #define NOPAGE_OOM ((struct page *) (-1)) -#define NOPAGE_REFAULT ((struct page *) (-2)) /* Return to userspace, rerun */ /* * Error return values for the *_nopfn functions @@ -671,16 +697,18 @@ static inline int page_mapped(struct page *page) * Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. */ -#define VM_FAULT_OOM 0x00 -#define VM_FAULT_SIGBUS 0x01 -#define VM_FAULT_MINOR 0x02 -#define VM_FAULT_MAJOR 0x03 - -/* - * Special case for get_user_pages. - * Must be in a distinct bit from the above VM_FAULT_ flags. - */ -#define VM_FAULT_WRITE 0x10 + +#define VM_FAULT_MINOR 0 /* For backwards compat. Remove me quickly. */ + +#define VM_FAULT_OOM 0x0001 +#define VM_FAULT_SIGBUS 0x0002 +#define VM_FAULT_MAJOR 0x0004 +#define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ + +#define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ +#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ + +#define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS) #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) @@ -764,20 +792,10 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping, extern int vmtruncate(struct inode * inode, loff_t offset); extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); -extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot); -extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot); #ifdef CONFIG_MMU -extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, +extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access); - -static inline int handle_mm_fault(struct mm_struct *mm, - struct vm_area_struct *vma, unsigned long address, - int write_access) -{ - return __handle_mm_fault(mm, vma, address, write_access) & - (~VM_FAULT_WRITE); -} #else static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, @@ -791,7 +809,6 @@ 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); -void install_arg_page(struct vm_area_struct *, struct page *, unsigned long); int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); @@ -808,65 +825,44 @@ int FASTCALL(set_page_dirty(struct page *page)); int set_page_dirty_lock(struct page *page); int clear_page_dirty_for_io(struct page *page); +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); extern unsigned long do_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr); +extern int mprotect_fixup(struct vm_area_struct *vma, + struct vm_area_struct **pprev, unsigned long start, + unsigned long end, unsigned long newflags); /* - * Prototype to add a shrinker callback for ageable caches. - * - * These functions are passed a count `nr_to_scan' and a gfpmask. They should - * scan `nr_to_scan' objects, attempting to free them. + * A callback you can register to apply pressure to ageable caches. * - * The callback must return the number of objects which remain in the cache. + * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should + * look through the least-recently-used 'nr_to_scan' entries and + * attempt to free them up. It should return the number of objects + * which remain in the cache. If it returns -1, it means it cannot do + * any scanning at this time (eg. there is a risk of deadlock). * - * The callback will be passed nr_to_scan == 0 when the VM is querying the - * cache size, so a fastpath for that case is appropriate. - */ -typedef int (*shrinker_t)(int nr_to_scan, gfp_t gfp_mask); - -/* - * Add an aging callback. The int is the number of 'seeks' it takes - * to recreate one of the objects that these functions age. - */ - -#define DEFAULT_SEEKS 2 -struct shrinker; -extern struct shrinker *set_shrinker(int, shrinker_t); -extern void remove_shrinker(struct shrinker *shrinker); - -/* - * Some shared mappigns will want the pages marked read-only - * to track write events. If so, we'll downgrade vm_page_prot - * to the private version (using protection_map[] without the - * VM_SHARED bit). + * The 'gfpmask' refers to the allocation we are currently trying to + * fulfil. + * + * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is + * querying the cache size, so a fastpath for that case is appropriate. */ -static inline int vma_wants_writenotify(struct vm_area_struct *vma) -{ - unsigned int vm_flags = vma->vm_flags; - - /* If it was private or non-writable, the write bit is already clear */ - if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED))) - return 0; +struct shrinker { + int (*shrink)(int nr_to_scan, gfp_t gfp_mask); + int seeks; /* seeks to recreate an obj */ - /* The backer wishes to know when pages are first written to? */ - if (vma->vm_ops && vma->vm_ops->page_mkwrite) - return 1; + /* These are for internal use */ + struct list_head list; + long nr; /* objs pending delete */ +}; +#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ +extern void register_shrinker(struct shrinker *); +extern void unregister_shrinker(struct shrinker *); - /* The open routine did something to the protections already? */ - if (pgprot_val(vma->vm_page_prot) != - pgprot_val(protection_map[vm_flags & - (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)])) - return 0; - - /* Specialty mapping? */ - if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE)) - return 0; - - /* Can the mapping track the dirty pages? */ - return vma->vm_file && vma->vm_file->f_mapping && - mapping_cap_account_dirty(vma->vm_file->f_mapping); -} +int vma_wants_writenotify(struct vm_area_struct *vma); extern pte_t *FASTCALL(get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl)); @@ -1046,7 +1042,7 @@ static inline void vma_nonlinear_insert(struct vm_area_struct *vma, } /* mmap.c */ -extern int __vm_enough_memory(long pages, int cap_sys_admin); +extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern void vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert); extern struct vm_area_struct *vma_merge(struct mm_struct *, @@ -1073,6 +1069,10 @@ extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned lo extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff); +extern unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, unsigned long flags, + unsigned int vm_flags, unsigned long pgoff, + int accountable); static inline unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, @@ -1098,9 +1098,7 @@ extern void truncate_inode_pages_range(struct address_space *, loff_t lstart, loff_t lend); /* generic vm_area_ops exported for stackable file systems */ -extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *); -extern int filemap_populate(struct vm_area_struct *, unsigned long, - unsigned long, pgprot_t, unsigned long, int); +extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); /* mm/page-writeback.c */ int write_one_page(struct page *page, int wait); @@ -1115,13 +1113,20 @@ int do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read); int force_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read); -unsigned long page_cache_readahead(struct address_space *mapping, - struct file_ra_state *ra, - struct file *filp, - pgoff_t offset, - unsigned long size); -void handle_ra_miss(struct address_space *mapping, - struct file_ra_state *ra, pgoff_t offset); + +void page_cache_sync_readahead(struct address_space *mapping, + struct file_ra_state *ra, + struct file *filp, + pgoff_t offset, + unsigned long size); + +void page_cache_async_readahead(struct address_space *mapping, + struct file_ra_state *ra, + struct file *filp, + struct page *pg, + pgoff_t offset, + unsigned long size); + unsigned long max_sane_readahead(unsigned long nr); /* Do stack extension */ @@ -1129,6 +1134,8 @@ extern int expand_stack(struct vm_area_struct *vma, unsigned long address); #ifdef CONFIG_IA64 extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); #endif +extern int expand_stack_downwards(struct vm_area_struct *vma, + unsigned long address); /* Look up the first VMA which satisfies addr < vm_end, NULL if none. */ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); @@ -1209,7 +1216,7 @@ void drop_slab(void); extern int randomize_va_space; #endif -__attribute__((weak)) const char *arch_vma_name(struct vm_area_struct *vma); +const char * arch_vma_name(struct vm_area_struct *vma); #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ |