X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fmm.h;h=e8ddc98b8405fdf7c9d32680731e0d5738bb97e1;hb=b08ead0527bcfdcab39a347b531701289485b484;hp=ca973359fe5f7f8d1c38b4cd8d467112e66bf5f3;hpb=3c18ddd160d1fcd46d1131d9ad6c594dd8e9af99;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/linux/mm.h b/include/linux/mm.h index ca97335..e8ddc98 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -7,6 +7,7 @@ #include #include +#include #include #include #include @@ -41,6 +42,9 @@ extern unsigned long mmap_min_addr; #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) +/* to align the pointer to the (next) page boundary */ +#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) + /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way @@ -52,25 +56,15 @@ extern unsigned long mmap_min_addr; extern struct kmem_cache *vm_area_cachep; -/* - * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is - * disabled, then there's a single shared list of VMAs maintained by the - * system, and mm's subscribe to these individually - */ -struct vm_list_struct { - struct vm_list_struct *next; - struct vm_area_struct *vma; -}; - #ifndef CONFIG_MMU -extern struct rb_root nommu_vma_tree; -extern struct rw_semaphore nommu_vma_sem; +extern struct rb_root nommu_region_tree; +extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* - * vm_flags.. + * vm_flags in vm_area_struct, see mm_types.h. */ #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 @@ -100,6 +94,7 @@ 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_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) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ @@ -107,6 +102,8 @@ extern unsigned int kobjsize(const void *objp); #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ #define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ +#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ +#define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */ #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS @@ -125,6 +122,11 @@ 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 + */ +#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) + +/* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ @@ -133,6 +135,23 @@ 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 */ +/* + * This interface is used by x86 PAT code to identify a pfn mapping that is + * linear over entire vma. This is to optimize PAT code that deals with + * marking the physical region with a particular prot. This is not for generic + * mm use. Note also that this check will not work if the pfn mapping is + * linear for a vma starting at physical address 0. In which case PAT code + * falls back to slow path of reserving physical range page by page. + */ +static inline int is_linear_pfn_mapping(struct vm_area_struct *vma) +{ + return ((vma->vm_flags & VM_PFNMAP) && vma->vm_pgoff); +} + +static inline int is_pfn_mapping(struct vm_area_struct *vma) +{ + return (vma->vm_flags & VM_PFNMAP); +} /* * vm_fault is filled by the the pagefault handler and passed to the vma's @@ -164,14 +183,36 @@ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); - 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 */ int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); + + /* called by access_process_vm when get_user_pages() fails, typically + * for use by special VMAs that can switch between memory and hardware + */ + int (*access)(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); #ifdef CONFIG_NUMA + /* + * set_policy() op must add a reference to any non-NULL @new mempolicy + * to hold the policy upon return. Caller should pass NULL @new to + * remove a policy and fall back to surrounding context--i.e. do not + * install a MPOL_DEFAULT policy, nor the task or system default + * mempolicy. + */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); + + /* + * get_policy() op must add reference [mpol_get()] to any policy at + * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure + * in mm/mempolicy.c will do this automatically. + * get_policy() must NOT add a ref if the policy at (vma,addr) is not + * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. + * If no [shared/vma] mempolicy exists at the addr, get_policy() op + * must return NULL--i.e., do not "fallback" to task or system default + * policy. + */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from, @@ -191,12 +232,6 @@ struct inode; */ #include -#ifdef CONFIG_DEBUG_VM -#define VM_BUG_ON(cond) BUG_ON(cond) -#else -#define VM_BUG_ON(condition) do { } while(0) -#endif - /* * Methods to modify the page usage count. * @@ -225,7 +260,6 @@ static inline int put_page_testzero(struct page *page) */ static inline int get_page_unless_zero(struct page *page) { - VM_BUG_ON(PageTail(page)); return atomic_inc_not_zero(&page->_count); } @@ -395,11 +429,11 @@ static inline void set_compound_order(struct page *page, unsigned long order) * we have run out of space and have to fall back to an * alternate (slower) way of determining the node. * - * No sparsemem: | NODE | ZONE | ... | FLAGS | - * with space for node: | SECTION | NODE | ZONE | ... | FLAGS | - * no space for node: | SECTION | ZONE | ... | FLAGS | + * No sparsemem or sparsemem vmemmap: | NODE | ZONE | ... | FLAGS | + * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | + * classic sparse no space for node: | SECTION | ZONE | ... | FLAGS | */ -#ifdef CONFIG_SPARSEMEM +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTIONS_WIDTH SECTIONS_SHIFT #else #define SECTIONS_WIDTH 0 @@ -407,9 +441,12 @@ static inline void set_compound_order(struct page *page, unsigned long order) #define ZONES_WIDTH ZONES_SHIFT -#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= FLAGS_RESERVED +#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS #define NODES_WIDTH NODES_SHIFT #else +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#error "Vmemmap: No space for nodes field in page flags" +#endif #define NODES_WIDTH 0 #endif @@ -452,8 +489,8 @@ static inline void set_compound_order(struct page *page, unsigned long order) #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) -#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED -#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED +#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS +#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #endif #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) @@ -502,10 +539,12 @@ static inline struct zone *page_zone(struct page *page) return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } +#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) static inline unsigned long page_to_section(struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } +#endif static inline void set_page_zone(struct page *page, enum zone_type zone) { @@ -600,9 +639,12 @@ static inline struct address_space *page_mapping(struct page *page) struct address_space *mapping = page->mapping; VM_BUG_ON(PageSlab(page)); +#ifdef CONFIG_SWAP if (unlikely(PageSwapCache(page))) mapping = &swapper_space; - else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) + else +#endif + if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) mapping = NULL; return mapping; } @@ -647,13 +689,6 @@ static inline int page_mapped(struct page *page) } /* - * Error return values for the *_nopfn functions - */ -#define NOPFN_SIGBUS ((unsigned long) -1) -#define NOPFN_OOM ((unsigned long) -2) -#define NOPFN_REFAULT ((unsigned long) -3) - -/* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. @@ -671,15 +706,20 @@ static inline int page_mapped(struct page *page) #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS) +/* + * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. + */ +extern void pagefault_out_of_memory(void); + #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) extern void show_free_areas(void); #ifdef CONFIG_SHMEM -int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern int shmem_lock(struct file *file, int lock, struct user_struct *user); #else static inline int shmem_lock(struct file *file, int lock, - struct user_struct *user) + struct user_struct *user) { return 0; } @@ -712,7 +752,11 @@ struct zap_details { unsigned long truncate_count; /* Compare vm_truncate_count */ }; -struct page *vm_normal_page(struct vm_area_struct *, unsigned long, pte_t); +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte); + +int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size); unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); unsigned long unmap_vmas(struct mmu_gather **tlb, @@ -731,24 +775,27 @@ unsigned long unmap_vmas(struct mmu_gather **tlb, * (see walk_page_range for more details) */ struct mm_walk { - int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, void *); - int (*pud_entry)(pud_t *, unsigned long, unsigned long, void *); - int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, void *); - int (*pte_entry)(pte_t *, unsigned long, unsigned long, void *); - int (*pte_hole)(unsigned long, unsigned long, void *); + int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); + int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); + struct mm_struct *mm; + void *private; }; -int walk_page_range(const struct mm_struct *, unsigned long addr, - unsigned long end, const struct mm_walk *walk, - void *private); -void free_pgd_range(struct mmu_gather **tlb, unsigned long addr, +int walk_page_range(unsigned long addr, unsigned long end, + struct mm_walk *walk); +void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling); -void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma, - unsigned long floor, unsigned long ceiling); 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_phys(struct vm_area_struct *vma, unsigned long address, + unsigned int flags, unsigned long *prot, resource_size_t *phys); +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write); static inline void unmap_shared_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen) @@ -778,7 +825,6 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void * 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); -void print_bad_pte(struct vm_area_struct *, pte_t, unsigned long); extern int try_to_release_page(struct page * page, gfp_t gfp_mask); extern void do_invalidatepage(struct page *page, unsigned long offset); @@ -802,6 +848,19 @@ extern int mprotect_fixup(struct vm_area_struct *vma, unsigned long end, unsigned long newflags); /* + * get_user_pages_fast provides equivalent functionality to get_user_pages, + * operating on current and current->mm (force=0 and doesn't return any vmas). + * + * get_user_pages_fast may take mmap_sem and page tables, so no assumptions + * can be made about locking. get_user_pages_fast is to be implemented in a + * way that is advantageous (vs get_user_pages()) when the user memory area is + * already faulted in and present in ptes. However if the pages have to be + * faulted in, it may turn out to be slightly slower). + */ +int get_user_pages_fast(unsigned long start, int nr_pages, int write, + struct page **pages); + +/* * A callback you can register to apply pressure to ageable caches. * * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'. It should @@ -873,7 +932,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a } #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ -#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS +#if USE_SPLIT_PTLOCKS /* * We tuck a spinlock to guard each pagetable page into its struct page, * at page->private, with BUILD_BUG_ON to make sure that this will not @@ -886,14 +945,14 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a } while (0) #define pte_lock_deinit(page) ((page)->mapping = NULL) #define pte_lockptr(mm, pmd) ({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));}) -#else +#else /* !USE_SPLIT_PTLOCKS */ /* * We use mm->page_table_lock to guard all pagetable pages of the mm. */ #define pte_lock_init(page) do {} while (0) #define pte_lock_deinit(page) do {} while (0) #define pte_lockptr(mm, pmd) ({(void)(pmd); &(mm)->page_table_lock;}) -#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */ +#endif /* USE_SPLIT_PTLOCKS */ static inline void pgtable_page_ctor(struct page *page) { @@ -934,9 +993,8 @@ static inline void pgtable_page_dtor(struct page *page) NULL: pte_offset_kernel(pmd, address)) extern void free_area_init(unsigned long * zones_size); -extern void free_area_init_node(int nid, pg_data_t *pgdat, - unsigned long * zones_size, unsigned long zone_start_pfn, - unsigned long *zholes_size); +extern void free_area_init_node(int nid, unsigned long * zones_size, + unsigned long zone_start_pfn, unsigned long *zholes_size); #ifdef CONFIG_ARCH_POPULATES_NODE_MAP /* * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its @@ -968,8 +1026,8 @@ extern void free_area_init_node(int nid, pg_data_t *pgdat, extern void free_area_init_nodes(unsigned long *max_zone_pfn); extern void add_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); -extern void shrink_active_range(unsigned int nid, unsigned long old_end_pfn, - unsigned long new_end_pfn); +extern void remove_active_range(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn); extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void remove_all_active_ranges(void); @@ -978,9 +1036,10 @@ extern unsigned long absent_pages_in_range(unsigned long start_pfn, extern void get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn); extern unsigned long find_min_pfn_with_active_regions(void); -extern unsigned long find_max_pfn_with_active_regions(void); extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); +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); #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID extern int early_pfn_to_nid(unsigned long pfn); @@ -991,9 +1050,11 @@ extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long, enum memmap_context); extern void setup_per_zone_pages_min(void); extern void mem_init(void); +extern void __init mmap_init(void); extern void show_mem(void); extern void si_meminfo(struct sysinfo * val); extern void si_meminfo_node(struct sysinfo *val, int nid); +extern int after_bootmem; #ifdef CONFIG_NUMA extern void setup_per_cpu_pageset(void); @@ -1001,6 +1062,9 @@ extern void setup_per_cpu_pageset(void); static inline void setup_per_cpu_pageset(void) {} #endif +/* nommu.c */ +extern atomic_t mmap_pages_allocated; + /* prio_tree.c */ void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *); @@ -1037,6 +1101,22 @@ extern void unlink_file_vma(struct vm_area_struct *); extern struct vm_area_struct *copy_vma(struct vm_area_struct **, unsigned long addr, unsigned long len, pgoff_t pgoff); extern void exit_mmap(struct mm_struct *); + +extern int mm_take_all_locks(struct mm_struct *mm); +extern void mm_drop_all_locks(struct mm_struct *mm); + +#ifdef CONFIG_PROC_FS +/* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ +extern void added_exe_file_vma(struct mm_struct *mm); +extern void removed_exe_file_vma(struct mm_struct *mm); +#else +static inline void added_exe_file_vma(struct mm_struct *mm) +{} + +static inline void removed_exe_file_vma(struct mm_struct *mm) +{} +#endif /* CONFIG_PROC_FS */ + extern int may_expand_vm(struct mm_struct *mm, unsigned long npages); extern int install_special_mapping(struct mm_struct *mm, unsigned long addr, unsigned long len, @@ -1141,6 +1221,8 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); +int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn); struct page *follow_page(struct vm_area_struct *, unsigned long address, unsigned int foll_flags); @@ -1199,8 +1281,6 @@ int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages); -void drop_pagecache(void); -void drop_slab(void); #ifndef CONFIG_MMU #define randomize_va_space 0 @@ -1223,5 +1303,7 @@ int vmemmap_populate_basepages(struct page *start_page, int vmemmap_populate(struct page *start_page, unsigned long pages, int node); void vmemmap_populate_print_last(void); +extern void *alloc_locked_buffer(size_t size); +extern void free_locked_buffer(void *buffer, size_t size); #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */