| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1 | #ifndef _LINUX_MM_H | 
|  | 2 | #define _LINUX_MM_H | 
|  | 3 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 4 | #include <linux/errno.h> | 
|  | 5 |  | 
|  | 6 | #ifdef __KERNEL__ | 
|  | 7 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 8 | #include <linux/gfp.h> | 
|  | 9 | #include <linux/list.h> | 
| Jiri Slaby | 59ea746 | 2008-06-12 13:56:40 +0200 | [diff] [blame] | 10 | #include <linux/mmdebug.h> | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 11 | #include <linux/mmzone.h> | 
|  | 12 | #include <linux/rbtree.h> | 
|  | 13 | #include <linux/prio_tree.h> | 
| Ingo Molnar | 9a11b49a | 2006-07-03 00:24:33 -0700 | [diff] [blame] | 14 | #include <linux/debug_locks.h> | 
| Heiko Carstens | 5b99cd0 | 2006-09-27 01:50:01 -0700 | [diff] [blame] | 15 | #include <linux/mm_types.h> | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 16 |  | 
|  | 17 | struct mempolicy; | 
|  | 18 | struct anon_vma; | 
| Alexey Dobriyan | 4e950f6 | 2007-07-30 02:36:13 +0400 | [diff] [blame] | 19 | struct file_ra_state; | 
| Alexey Dobriyan | e8edc6e | 2007-05-21 01:22:52 +0400 | [diff] [blame] | 20 | struct user_struct; | 
| Alexey Dobriyan | 4e950f6 | 2007-07-30 02:36:13 +0400 | [diff] [blame] | 21 | struct writeback_control; | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 22 |  | 
|  | 23 | #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */ | 
|  | 24 | extern unsigned long max_mapnr; | 
|  | 25 | #endif | 
|  | 26 |  | 
|  | 27 | extern unsigned long num_physpages; | 
|  | 28 | extern void * high_memory; | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 29 | extern int page_cluster; | 
|  | 30 |  | 
|  | 31 | #ifdef CONFIG_SYSCTL | 
|  | 32 | extern int sysctl_legacy_va_layout; | 
|  | 33 | #else | 
|  | 34 | #define sysctl_legacy_va_layout 0 | 
|  | 35 | #endif | 
|  | 36 |  | 
| James Morris | 42d7896 | 2007-12-26 15:12:37 +1100 | [diff] [blame] | 37 | extern unsigned long mmap_min_addr; | 
|  | 38 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 39 | #include <asm/page.h> | 
|  | 40 | #include <asm/pgtable.h> | 
|  | 41 | #include <asm/processor.h> | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 42 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 43 | #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) | 
|  | 44 |  | 
| Andrea Righi | 27ac792 | 2008-07-23 21:28:13 -0700 | [diff] [blame] | 45 | /* to align the pointer to the (next) page boundary */ | 
|  | 46 | #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) | 
|  | 47 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 48 | /* | 
|  | 49 | * Linux kernel virtual memory manager primitives. | 
|  | 50 | * The idea being to have a "virtual" mm in the same way | 
|  | 51 | * we have a virtual fs - giving a cleaner interface to the | 
|  | 52 | * mm details, and allowing different kinds of memory mappings | 
|  | 53 | * (from shared memory to executable loading to arbitrary | 
|  | 54 | * mmap() functions). | 
|  | 55 | */ | 
|  | 56 |  | 
| Christoph Lameter | c43692e | 2006-12-06 20:32:48 -0800 | [diff] [blame] | 57 | extern struct kmem_cache *vm_area_cachep; | 
|  | 58 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 59 | /* | 
|  | 60 | * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is | 
|  | 61 | * disabled, then there's a single shared list of VMAs maintained by the | 
|  | 62 | * system, and mm's subscribe to these individually | 
|  | 63 | */ | 
|  | 64 | struct vm_list_struct { | 
|  | 65 | struct vm_list_struct	*next; | 
|  | 66 | struct vm_area_struct	*vma; | 
|  | 67 | }; | 
|  | 68 |  | 
|  | 69 | #ifndef CONFIG_MMU | 
|  | 70 | extern struct rb_root nommu_vma_tree; | 
|  | 71 | extern struct rw_semaphore nommu_vma_sem; | 
|  | 72 |  | 
|  | 73 | extern unsigned int kobjsize(const void *objp); | 
|  | 74 | #endif | 
|  | 75 |  | 
|  | 76 | /* | 
| Hugh Dickins | 605d928 | 2008-08-16 11:07:21 +0100 | [diff] [blame] | 77 | * vm_flags in vm_area_struct, see mm_types.h. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 78 | */ | 
|  | 79 | #define VM_READ		0x00000001	/* currently active flags */ | 
|  | 80 | #define VM_WRITE	0x00000002 | 
|  | 81 | #define VM_EXEC		0x00000004 | 
|  | 82 | #define VM_SHARED	0x00000008 | 
|  | 83 |  | 
| Paolo 'Blaisorblade' Giarrusso | 7e2cff4 | 2005-09-21 09:55:39 -0700 | [diff] [blame] | 84 | /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 85 | #define VM_MAYREAD	0x00000010	/* limits for mprotect() etc */ | 
|  | 86 | #define VM_MAYWRITE	0x00000020 | 
|  | 87 | #define VM_MAYEXEC	0x00000040 | 
|  | 88 | #define VM_MAYSHARE	0x00000080 | 
|  | 89 |  | 
|  | 90 | #define VM_GROWSDOWN	0x00000100	/* general info on the segment */ | 
|  | 91 | #define VM_GROWSUP	0x00000200 | 
| Linus Torvalds | 6aab341 | 2005-11-28 14:34:23 -0800 | [diff] [blame] | 92 | #define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 93 | #define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */ | 
|  | 94 |  | 
|  | 95 | #define VM_EXECUTABLE	0x00001000 | 
|  | 96 | #define VM_LOCKED	0x00002000 | 
|  | 97 | #define VM_IO           0x00004000	/* Memory mapped I/O or similar */ | 
|  | 98 |  | 
|  | 99 | /* Used by sys_madvise() */ | 
|  | 100 | #define VM_SEQ_READ	0x00008000	/* App will access data sequentially */ | 
|  | 101 | #define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */ | 
|  | 102 |  | 
|  | 103 | #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */ | 
|  | 104 | #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */ | 
| Hugh Dickins | 0b14c17 | 2005-11-21 21:32:15 -0800 | [diff] [blame] | 105 | #define VM_RESERVED	0x00080000	/* Count as reserved_vm like IO */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 106 | #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */ | 
| Andy Whitcroft | cdfd432 | 2008-07-23 21:27:28 -0700 | [diff] [blame] | 107 | #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 108 | #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */ | 
|  | 109 | #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */ | 
|  | 110 | #define VM_MAPPED_COPY	0x01000000	/* T if mapped copy of data (nommu mmap) */ | 
| Linus Torvalds | 4d7672b | 2005-12-16 10:21:23 -0800 | [diff] [blame] | 111 | #define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */ | 
| Roland McGrath | e5b97dd | 2007-01-26 00:56:48 -0800 | [diff] [blame] | 112 | #define VM_ALWAYSDUMP	0x04000000	/* Always include in core dumps */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 113 |  | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 114 | #define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */ | 
| Jared Hulbert | b379d79 | 2008-04-28 02:12:58 -0700 | [diff] [blame] | 115 | #define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */ | 
| Dave Kleikamp | aba46c5 | 2008-07-08 00:28:52 +1000 | [diff] [blame] | 116 | #define VM_SAO		0x20000000	/* Strong Access Ordering (powerpc) */ | 
| Nick Piggin | d00806b | 2007-07-19 01:46:57 -0700 | [diff] [blame] | 117 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 118 | #ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */ | 
|  | 119 | #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS | 
|  | 120 | #endif | 
|  | 121 |  | 
|  | 122 | #ifdef CONFIG_STACK_GROWSUP | 
|  | 123 | #define VM_STACK_FLAGS	(VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) | 
|  | 124 | #else | 
|  | 125 | #define VM_STACK_FLAGS	(VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) | 
|  | 126 | #endif | 
|  | 127 |  | 
|  | 128 | #define VM_READHINTMASK			(VM_SEQ_READ | VM_RAND_READ) | 
|  | 129 | #define VM_ClearReadHint(v)		(v)->vm_flags &= ~VM_READHINTMASK | 
|  | 130 | #define VM_NormalReadHint(v)		(!((v)->vm_flags & VM_READHINTMASK)) | 
|  | 131 | #define VM_SequentialReadHint(v)	((v)->vm_flags & VM_SEQ_READ) | 
|  | 132 | #define VM_RandomReadHint(v)		((v)->vm_flags & VM_RAND_READ) | 
|  | 133 |  | 
|  | 134 | /* | 
| Nick Piggin | b291f00 | 2008-10-18 20:26:44 -0700 | [diff] [blame] | 135 | * special vmas that are non-mergable, non-mlock()able | 
|  | 136 | */ | 
|  | 137 | #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) | 
|  | 138 |  | 
|  | 139 | /* | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 140 | * mapping from the currently active vm_flags protection bits (the | 
|  | 141 | * low four bits) to a page protection mask.. | 
|  | 142 | */ | 
|  | 143 | extern pgprot_t protection_map[16]; | 
|  | 144 |  | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 145 | #define FAULT_FLAG_WRITE	0x01	/* Fault was a write access */ | 
|  | 146 | #define FAULT_FLAG_NONLINEAR	0x02	/* Fault was via a nonlinear mapping */ | 
|  | 147 |  | 
|  | 148 |  | 
| Nick Piggin | 54cb882 | 2007-07-19 01:46:59 -0700 | [diff] [blame] | 149 | /* | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 150 | * vm_fault is filled by the the pagefault handler and passed to the vma's | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 151 | * ->fault function. The vma's ->fault is responsible for returning a bitmask | 
|  | 152 | * of VM_FAULT_xxx flags that give details about how the fault was handled. | 
| Nick Piggin | 54cb882 | 2007-07-19 01:46:59 -0700 | [diff] [blame] | 153 | * | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 154 | * pgoff should be used in favour of virtual_address, if possible. If pgoff | 
|  | 155 | * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear | 
|  | 156 | * mapping support. | 
| Nick Piggin | 54cb882 | 2007-07-19 01:46:59 -0700 | [diff] [blame] | 157 | */ | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 158 | struct vm_fault { | 
|  | 159 | unsigned int flags;		/* FAULT_FLAG_xxx flags */ | 
|  | 160 | pgoff_t pgoff;			/* Logical page offset based on vma */ | 
|  | 161 | void __user *virtual_address;	/* Faulting virtual address */ | 
|  | 162 |  | 
|  | 163 | struct page *page;		/* ->fault handlers should return a | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 164 | * page here, unless VM_FAULT_NOPAGE | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 165 | * is set (which is also implied by | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 166 | * VM_FAULT_ERROR). | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 167 | */ | 
| Nick Piggin | 54cb882 | 2007-07-19 01:46:59 -0700 | [diff] [blame] | 168 | }; | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 169 |  | 
|  | 170 | /* | 
|  | 171 | * These are the virtual MM functions - opening of an area, closing and | 
|  | 172 | * unmapping it (needed to keep files on disk up-to-date etc), pointer | 
|  | 173 | * to the functions called when a no-page or a wp-page exception occurs. | 
|  | 174 | */ | 
|  | 175 | struct vm_operations_struct { | 
|  | 176 | void (*open)(struct vm_area_struct * area); | 
|  | 177 | void (*close)(struct vm_area_struct * area); | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 178 | int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); | 
| David Howells | 9637a5e | 2006-06-23 02:03:43 -0700 | [diff] [blame] | 179 |  | 
|  | 180 | /* notification that a previously read-only page is about to become | 
|  | 181 | * writable, if an error is returned it will cause a SIGBUS */ | 
|  | 182 | int (*page_mkwrite)(struct vm_area_struct *vma, struct page *page); | 
| Rik van Riel | 28b2ee2 | 2008-07-23 21:27:05 -0700 | [diff] [blame] | 183 |  | 
|  | 184 | /* called by access_process_vm when get_user_pages() fails, typically | 
|  | 185 | * for use by special VMAs that can switch between memory and hardware | 
|  | 186 | */ | 
|  | 187 | int (*access)(struct vm_area_struct *vma, unsigned long addr, | 
|  | 188 | void *buf, int len, int write); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 189 | #ifdef CONFIG_NUMA | 
| Lee Schermerhorn | a6020ed | 2008-04-28 02:13:14 -0700 | [diff] [blame] | 190 | /* | 
|  | 191 | * set_policy() op must add a reference to any non-NULL @new mempolicy | 
|  | 192 | * to hold the policy upon return.  Caller should pass NULL @new to | 
|  | 193 | * remove a policy and fall back to surrounding context--i.e. do not | 
|  | 194 | * install a MPOL_DEFAULT policy, nor the task or system default | 
|  | 195 | * mempolicy. | 
|  | 196 | */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 197 | int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); | 
| Lee Schermerhorn | a6020ed | 2008-04-28 02:13:14 -0700 | [diff] [blame] | 198 |  | 
|  | 199 | /* | 
|  | 200 | * get_policy() op must add reference [mpol_get()] to any policy at | 
|  | 201 | * (vma,addr) marked as MPOL_SHARED.  The shared policy infrastructure | 
|  | 202 | * in mm/mempolicy.c will do this automatically. | 
|  | 203 | * get_policy() must NOT add a ref if the policy at (vma,addr) is not | 
|  | 204 | * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. | 
|  | 205 | * If no [shared/vma] mempolicy exists at the addr, get_policy() op | 
|  | 206 | * must return NULL--i.e., do not "fallback" to task or system default | 
|  | 207 | * policy. | 
|  | 208 | */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 209 | struct mempolicy *(*get_policy)(struct vm_area_struct *vma, | 
|  | 210 | unsigned long addr); | 
| Christoph Lameter | 7b2259b | 2006-06-25 05:46:48 -0700 | [diff] [blame] | 211 | int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from, | 
|  | 212 | const nodemask_t *to, unsigned long flags); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 213 | #endif | 
|  | 214 | }; | 
|  | 215 |  | 
|  | 216 | struct mmu_gather; | 
|  | 217 | struct inode; | 
|  | 218 |  | 
| Andrew Morton | 349aef0 | 2006-01-08 01:04:36 -0800 | [diff] [blame] | 219 | #define page_private(page)		((page)->private) | 
|  | 220 | #define set_page_private(page, v)	((page)->private = (v)) | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 221 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 222 | /* | 
|  | 223 | * FIXME: take this include out, include page-flags.h in | 
|  | 224 | * files which need it (119 of them) | 
|  | 225 | */ | 
|  | 226 | #include <linux/page-flags.h> | 
|  | 227 |  | 
|  | 228 | /* | 
|  | 229 | * Methods to modify the page usage count. | 
|  | 230 | * | 
|  | 231 | * What counts for a page usage: | 
|  | 232 | * - cache mapping   (page->mapping) | 
|  | 233 | * - private data    (page->private) | 
|  | 234 | * - page mapped in a task's page tables, each mapping | 
|  | 235 | *   is counted separately | 
|  | 236 | * | 
|  | 237 | * Also, many kernel routines increase the page count before a critical | 
|  | 238 | * routine so they can be sure the page doesn't go away from under them. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 239 | */ | 
|  | 240 |  | 
|  | 241 | /* | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 242 | * Drop a ref, return true if the refcount fell to zero (the page has no users) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 243 | */ | 
| Nick Piggin | 7c8ee9a | 2006-03-22 00:08:03 -0800 | [diff] [blame] | 244 | static inline int put_page_testzero(struct page *page) | 
|  | 245 | { | 
| Nick Piggin | 725d704 | 2006-09-25 23:30:55 -0700 | [diff] [blame] | 246 | VM_BUG_ON(atomic_read(&page->_count) == 0); | 
| Nick Piggin | 8dc04ef | 2006-03-22 00:08:03 -0800 | [diff] [blame] | 247 | return atomic_dec_and_test(&page->_count); | 
| Nick Piggin | 7c8ee9a | 2006-03-22 00:08:03 -0800 | [diff] [blame] | 248 | } | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 249 |  | 
|  | 250 | /* | 
| Nick Piggin | 7c8ee9a | 2006-03-22 00:08:03 -0800 | [diff] [blame] | 251 | * Try to grab a ref unless the page has a refcount of zero, return false if | 
|  | 252 | * that is the case. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 253 | */ | 
| Nick Piggin | 7c8ee9a | 2006-03-22 00:08:03 -0800 | [diff] [blame] | 254 | static inline int get_page_unless_zero(struct page *page) | 
|  | 255 | { | 
| Christoph Lameter | aec2c3e | 2008-02-04 22:28:35 -0800 | [diff] [blame] | 256 | VM_BUG_ON(PageTail(page)); | 
| Nick Piggin | 8dc04ef | 2006-03-22 00:08:03 -0800 | [diff] [blame] | 257 | return atomic_inc_not_zero(&page->_count); | 
| Nick Piggin | 7c8ee9a | 2006-03-22 00:08:03 -0800 | [diff] [blame] | 258 | } | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 259 |  | 
| Christoph Lameter | 48667e7 | 2008-02-04 22:28:31 -0800 | [diff] [blame] | 260 | /* Support for virtually mapped pages */ | 
| Christoph Lameter | b3bdda0 | 2008-02-04 22:28:32 -0800 | [diff] [blame] | 261 | struct page *vmalloc_to_page(const void *addr); | 
|  | 262 | unsigned long vmalloc_to_pfn(const void *addr); | 
| Christoph Lameter | 48667e7 | 2008-02-04 22:28:31 -0800 | [diff] [blame] | 263 |  | 
| Paul Mundt | 0738c4b | 2008-03-12 16:51:31 +0900 | [diff] [blame] | 264 | /* | 
|  | 265 | * Determine if an address is within the vmalloc range | 
|  | 266 | * | 
|  | 267 | * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there | 
|  | 268 | * is no special casing required. | 
|  | 269 | */ | 
| Christoph Lameter | 9e2779f | 2008-02-04 22:28:34 -0800 | [diff] [blame] | 270 | static inline int is_vmalloc_addr(const void *x) | 
|  | 271 | { | 
| Paul Mundt | 0738c4b | 2008-03-12 16:51:31 +0900 | [diff] [blame] | 272 | #ifdef CONFIG_MMU | 
| Christoph Lameter | 9e2779f | 2008-02-04 22:28:34 -0800 | [diff] [blame] | 273 | unsigned long addr = (unsigned long)x; | 
|  | 274 |  | 
|  | 275 | return addr >= VMALLOC_START && addr < VMALLOC_END; | 
| Paul Mundt | 0738c4b | 2008-03-12 16:51:31 +0900 | [diff] [blame] | 276 | #else | 
|  | 277 | return 0; | 
| David Howells | 8ca3ed8 | 2008-02-23 15:23:37 -0800 | [diff] [blame] | 278 | #endif | 
| Paul Mundt | 0738c4b | 2008-03-12 16:51:31 +0900 | [diff] [blame] | 279 | } | 
| Christoph Lameter | 9e2779f | 2008-02-04 22:28:34 -0800 | [diff] [blame] | 280 |  | 
| Christoph Lameter | d85f338 | 2007-05-06 14:49:39 -0700 | [diff] [blame] | 281 | static inline struct page *compound_head(struct page *page) | 
|  | 282 | { | 
| Christoph Lameter | 6d77795 | 2007-05-06 14:49:40 -0700 | [diff] [blame] | 283 | if (unlikely(PageTail(page))) | 
| Christoph Lameter | d85f338 | 2007-05-06 14:49:39 -0700 | [diff] [blame] | 284 | return page->first_page; | 
|  | 285 | return page; | 
|  | 286 | } | 
|  | 287 |  | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 288 | static inline int page_count(struct page *page) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 289 | { | 
| Christoph Lameter | d85f338 | 2007-05-06 14:49:39 -0700 | [diff] [blame] | 290 | return atomic_read(&compound_head(page)->_count); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 291 | } | 
|  | 292 |  | 
|  | 293 | static inline void get_page(struct page *page) | 
|  | 294 | { | 
| Christoph Lameter | d85f338 | 2007-05-06 14:49:39 -0700 | [diff] [blame] | 295 | page = compound_head(page); | 
| Nick Piggin | 725d704 | 2006-09-25 23:30:55 -0700 | [diff] [blame] | 296 | VM_BUG_ON(atomic_read(&page->_count) == 0); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 297 | atomic_inc(&page->_count); | 
|  | 298 | } | 
|  | 299 |  | 
| Christoph Lameter | b49af68 | 2007-05-06 14:49:41 -0700 | [diff] [blame] | 300 | static inline struct page *virt_to_head_page(const void *x) | 
|  | 301 | { | 
|  | 302 | struct page *page = virt_to_page(x); | 
|  | 303 | return compound_head(page); | 
|  | 304 | } | 
|  | 305 |  | 
| Nick Piggin | 7835e98 | 2006-03-22 00:08:40 -0800 | [diff] [blame] | 306 | /* | 
|  | 307 | * Setup the page count before being freed into the page allocator for | 
|  | 308 | * the first time (boot or memory hotplug) | 
|  | 309 | */ | 
|  | 310 | static inline void init_page_count(struct page *page) | 
|  | 311 | { | 
|  | 312 | atomic_set(&page->_count, 1); | 
|  | 313 | } | 
|  | 314 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 315 | void put_page(struct page *page); | 
| Alexander Zarochentsev | 1d7ea73 | 2006-08-13 23:24:27 -0700 | [diff] [blame] | 316 | void put_pages_list(struct list_head *pages); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 317 |  | 
| Nick Piggin | 8dfcc9b | 2006-03-22 00:08:05 -0800 | [diff] [blame] | 318 | void split_page(struct page *page, unsigned int order); | 
| Nick Piggin | 8dfcc9b | 2006-03-22 00:08:05 -0800 | [diff] [blame] | 319 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 320 | /* | 
| Andy Whitcroft | 33f2ef8 | 2006-12-06 20:33:32 -0800 | [diff] [blame] | 321 | * Compound pages have a destructor function.  Provide a | 
|  | 322 | * prototype for that function and accessor functions. | 
|  | 323 | * These are _only_ valid on the head of a PG_compound page. | 
|  | 324 | */ | 
|  | 325 | typedef void compound_page_dtor(struct page *); | 
|  | 326 |  | 
|  | 327 | static inline void set_compound_page_dtor(struct page *page, | 
|  | 328 | compound_page_dtor *dtor) | 
|  | 329 | { | 
|  | 330 | page[1].lru.next = (void *)dtor; | 
|  | 331 | } | 
|  | 332 |  | 
|  | 333 | static inline compound_page_dtor *get_compound_page_dtor(struct page *page) | 
|  | 334 | { | 
|  | 335 | return (compound_page_dtor *)page[1].lru.next; | 
|  | 336 | } | 
|  | 337 |  | 
| Christoph Lameter | d85f338 | 2007-05-06 14:49:39 -0700 | [diff] [blame] | 338 | static inline int compound_order(struct page *page) | 
|  | 339 | { | 
| Christoph Lameter | 6d77795 | 2007-05-06 14:49:40 -0700 | [diff] [blame] | 340 | if (!PageHead(page)) | 
| Christoph Lameter | d85f338 | 2007-05-06 14:49:39 -0700 | [diff] [blame] | 341 | return 0; | 
|  | 342 | return (unsigned long)page[1].lru.prev; | 
|  | 343 | } | 
|  | 344 |  | 
|  | 345 | static inline void set_compound_order(struct page *page, unsigned long order) | 
|  | 346 | { | 
|  | 347 | page[1].lru.prev = (void *)order; | 
|  | 348 | } | 
|  | 349 |  | 
| Andy Whitcroft | 33f2ef8 | 2006-12-06 20:33:32 -0800 | [diff] [blame] | 350 | /* | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 351 | * Multiple processes may "see" the same page. E.g. for untouched | 
|  | 352 | * mappings of /dev/null, all processes see the same page full of | 
|  | 353 | * zeroes, and text pages of executables and shared libraries have | 
|  | 354 | * only one copy in memory, at most, normally. | 
|  | 355 | * | 
|  | 356 | * For the non-reserved pages, page_count(page) denotes a reference count. | 
| Paolo 'Blaisorblade' Giarrusso | 7e871b6 | 2005-09-21 09:55:38 -0700 | [diff] [blame] | 357 | *   page_count() == 0 means the page is free. page->lru is then used for | 
|  | 358 | *   freelist management in the buddy allocator. | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 359 | *   page_count() > 0  means the page has been allocated. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 360 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 361 | * Pages are allocated by the slab allocator in order to provide memory | 
|  | 362 | * to kmalloc and kmem_cache_alloc. In this case, the management of the | 
|  | 363 | * page, and the fields in 'struct page' are the responsibility of mm/slab.c | 
|  | 364 | * unless a particular usage is carefully commented. (the responsibility of | 
|  | 365 | * freeing the kmalloc memory is the caller's, of course). | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 366 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 367 | * A page may be used by anyone else who does a __get_free_page(). | 
|  | 368 | * In this case, page_count still tracks the references, and should only | 
|  | 369 | * be used through the normal accessor functions. The top bits of page->flags | 
|  | 370 | * and page->virtual store page management information, but all other fields | 
|  | 371 | * are unused and could be used privately, carefully. The management of this | 
|  | 372 | * page is the responsibility of the one who allocated it, and those who have | 
|  | 373 | * subsequently been given references to it. | 
|  | 374 | * | 
|  | 375 | * The other pages (we may call them "pagecache pages") are completely | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 376 | * managed by the Linux memory manager: I/O, buffers, swapping etc. | 
|  | 377 | * The following discussion applies only to them. | 
|  | 378 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 379 | * A pagecache page contains an opaque `private' member, which belongs to the | 
|  | 380 | * page's address_space. Usually, this is the address of a circular list of | 
|  | 381 | * the page's disk buffers. PG_private must be set to tell the VM to call | 
|  | 382 | * into the filesystem to release these pages. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 383 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 384 | * A page may belong to an inode's memory mapping. In this case, page->mapping | 
|  | 385 | * is the pointer to the inode, and page->index is the file offset of the page, | 
|  | 386 | * in units of PAGE_CACHE_SIZE. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 387 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 388 | * If pagecache pages are not associated with an inode, they are said to be | 
|  | 389 | * anonymous pages. These may become associated with the swapcache, and in that | 
|  | 390 | * case PG_swapcache is set, and page->private is an offset into the swapcache. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 391 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 392 | * In either case (swapcache or inode backed), the pagecache itself holds one | 
|  | 393 | * reference to the page. Setting PG_private should also increment the | 
|  | 394 | * refcount. The each user mapping also has a reference to the page. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 395 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 396 | * The pagecache pages are stored in a per-mapping radix tree, which is | 
|  | 397 | * rooted at mapping->page_tree, and indexed by offset. | 
|  | 398 | * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space | 
|  | 399 | * lists, we instead now tag pages as dirty/writeback in the radix tree. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 400 | * | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 401 | * All pagecache pages may be subject to I/O: | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 402 | * - inode pages may need to be read from disk, | 
|  | 403 | * - inode pages which have been modified and are MAP_SHARED may need | 
| Nick Piggin | da6052f | 2006-09-25 23:31:35 -0700 | [diff] [blame] | 404 | *   to be written back to the inode on disk, | 
|  | 405 | * - anonymous pages (including MAP_PRIVATE file mappings) which have been | 
|  | 406 | *   modified may need to be swapped out to swap space and (later) to be read | 
|  | 407 | *   back into memory. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 408 | */ | 
|  | 409 |  | 
|  | 410 | /* | 
|  | 411 | * The zone field is never updated after free_area_init_core() | 
|  | 412 | * sets it, so none of the operations on it need to be atomic. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 413 | */ | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 414 |  | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 415 |  | 
|  | 416 | /* | 
|  | 417 | * page->flags layout: | 
|  | 418 | * | 
|  | 419 | * There are three possibilities for how page->flags get | 
|  | 420 | * laid out.  The first is for the normal case, without | 
|  | 421 | * sparsemem.  The second is for sparsemem when there is | 
|  | 422 | * plenty of space for node and section.  The last is when | 
|  | 423 | * we have run out of space and have to fall back to an | 
|  | 424 | * alternate (slower) way of determining the node. | 
|  | 425 | * | 
| Christoph Lameter | 308c05e | 2008-04-28 02:12:43 -0700 | [diff] [blame] | 426 | * No sparsemem or sparsemem vmemmap: |       NODE     | ZONE | ... | FLAGS | | 
|  | 427 | * classic sparse with space for node:| SECTION | NODE | ZONE | ... | FLAGS | | 
|  | 428 | * classic sparse no space for node:  | SECTION |     ZONE    | ... | FLAGS | | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 429 | */ | 
| Christoph Lameter | 308c05e | 2008-04-28 02:12:43 -0700 | [diff] [blame] | 430 | #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 431 | #define SECTIONS_WIDTH		SECTIONS_SHIFT | 
|  | 432 | #else | 
|  | 433 | #define SECTIONS_WIDTH		0 | 
|  | 434 | #endif | 
|  | 435 |  | 
|  | 436 | #define ZONES_WIDTH		ZONES_SHIFT | 
|  | 437 |  | 
| Christoph Lameter | 9223b41 | 2008-04-28 02:12:48 -0700 | [diff] [blame] | 438 | #if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 439 | #define NODES_WIDTH		NODES_SHIFT | 
|  | 440 | #else | 
| Christoph Lameter | 308c05e | 2008-04-28 02:12:43 -0700 | [diff] [blame] | 441 | #ifdef CONFIG_SPARSEMEM_VMEMMAP | 
|  | 442 | #error "Vmemmap: No space for nodes field in page flags" | 
|  | 443 | #endif | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 444 | #define NODES_WIDTH		0 | 
|  | 445 | #endif | 
|  | 446 |  | 
|  | 447 | /* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */ | 
| Andi Kleen | 07808b7 | 2005-11-05 17:25:53 +0100 | [diff] [blame] | 448 | #define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH) | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 449 | #define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH) | 
|  | 450 | #define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH) | 
|  | 451 |  | 
|  | 452 | /* | 
|  | 453 | * We are going to use the flags for the page to node mapping if its in | 
|  | 454 | * there.  This includes the case where there is no node, so it is implicit. | 
|  | 455 | */ | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 456 | #if !(NODES_WIDTH > 0 || NODES_SHIFT == 0) | 
|  | 457 | #define NODE_NOT_IN_PAGE_FLAGS | 
|  | 458 | #endif | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 459 |  | 
|  | 460 | #ifndef PFN_SECTION_SHIFT | 
|  | 461 | #define PFN_SECTION_SHIFT 0 | 
|  | 462 | #endif | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 463 |  | 
|  | 464 | /* | 
|  | 465 | * Define the bit shifts to access each section.  For non-existant | 
|  | 466 | * sections we define the shift as 0; that plus a 0 mask ensures | 
|  | 467 | * the compiler will optimise away reference to them. | 
|  | 468 | */ | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 469 | #define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) | 
|  | 470 | #define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0)) | 
|  | 471 | #define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0)) | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 472 |  | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 473 | /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allcator */ | 
|  | 474 | #ifdef NODE_NOT_IN_PAGEFLAGS | 
|  | 475 | #define ZONEID_SHIFT		(SECTIONS_SHIFT + ZONES_SHIFT) | 
| Andy Whitcroft | bd8029b | 2007-02-10 01:43:14 -0800 | [diff] [blame] | 476 | #define ZONEID_PGOFF		((SECTIONS_PGOFF < ZONES_PGOFF)? \ | 
|  | 477 | SECTIONS_PGOFF : ZONES_PGOFF) | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 478 | #else | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 479 | #define ZONEID_SHIFT		(NODES_SHIFT + ZONES_SHIFT) | 
| Andy Whitcroft | bd8029b | 2007-02-10 01:43:14 -0800 | [diff] [blame] | 480 | #define ZONEID_PGOFF		((NODES_PGOFF < ZONES_PGOFF)? \ | 
|  | 481 | NODES_PGOFF : ZONES_PGOFF) | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 482 | #endif | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 483 |  | 
| Andy Whitcroft | bd8029b | 2007-02-10 01:43:14 -0800 | [diff] [blame] | 484 | #define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0)) | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 485 |  | 
| Christoph Lameter | 9223b41 | 2008-04-28 02:12:48 -0700 | [diff] [blame] | 486 | #if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS | 
|  | 487 | #error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 488 | #endif | 
|  | 489 |  | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 490 | #define ZONES_MASK		((1UL << ZONES_WIDTH) - 1) | 
|  | 491 | #define NODES_MASK		((1UL << NODES_WIDTH) - 1) | 
|  | 492 | #define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1) | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 493 | #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1) | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 494 |  | 
| Christoph Lameter | 2f1b624 | 2006-09-25 23:31:13 -0700 | [diff] [blame] | 495 | static inline enum zone_type page_zonenum(struct page *page) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 496 | { | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 497 | return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 498 | } | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 499 |  | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 500 | /* | 
|  | 501 | * The identification function is only used by the buddy allocator for | 
|  | 502 | * determining if two pages could be buddies. We are not really | 
|  | 503 | * identifying a zone since we could be using a the section number | 
|  | 504 | * id if we have not node id available in page flags. | 
|  | 505 | * We guarantee only that it will return the same value for two | 
|  | 506 | * combinable pages in a zone. | 
|  | 507 | */ | 
| Andy Whitcroft | cb2b95e | 2006-06-23 02:03:01 -0700 | [diff] [blame] | 508 | static inline int page_zone_id(struct page *page) | 
|  | 509 | { | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 510 | return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 511 | } | 
|  | 512 |  | 
| Andy Whitcroft | 25ba77c | 2006-12-06 20:33:03 -0800 | [diff] [blame] | 513 | static inline int zone_to_nid(struct zone *zone) | 
| Christoph Lameter | 89fa302 | 2006-09-25 23:31:55 -0700 | [diff] [blame] | 514 | { | 
| Christoph Lameter | d5f541e | 2006-09-27 01:50:08 -0700 | [diff] [blame] | 515 | #ifdef CONFIG_NUMA | 
|  | 516 | return zone->node; | 
|  | 517 | #else | 
|  | 518 | return 0; | 
|  | 519 | #endif | 
| Christoph Lameter | 89fa302 | 2006-09-25 23:31:55 -0700 | [diff] [blame] | 520 | } | 
|  | 521 |  | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 522 | #ifdef NODE_NOT_IN_PAGE_FLAGS | 
| Andy Whitcroft | 25ba77c | 2006-12-06 20:33:03 -0800 | [diff] [blame] | 523 | extern int page_to_nid(struct page *page); | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 524 | #else | 
| Andy Whitcroft | 25ba77c | 2006-12-06 20:33:03 -0800 | [diff] [blame] | 525 | static inline int page_to_nid(struct page *page) | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 526 | { | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 527 | return (page->flags >> NODES_PGSHIFT) & NODES_MASK; | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 528 | } | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 529 | #endif | 
|  | 530 |  | 
|  | 531 | static inline struct zone *page_zone(struct page *page) | 
|  | 532 | { | 
|  | 533 | return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; | 
|  | 534 | } | 
|  | 535 |  | 
| Christoph Lameter | 308c05e | 2008-04-28 02:12:43 -0700 | [diff] [blame] | 536 | #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 537 | static inline unsigned long page_to_section(struct page *page) | 
|  | 538 | { | 
|  | 539 | return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; | 
|  | 540 | } | 
| Christoph Lameter | 308c05e | 2008-04-28 02:12:43 -0700 | [diff] [blame] | 541 | #endif | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 542 |  | 
| Christoph Lameter | 2f1b624 | 2006-09-25 23:31:13 -0700 | [diff] [blame] | 543 | static inline void set_page_zone(struct page *page, enum zone_type zone) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 544 | { | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 545 | page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); | 
|  | 546 | page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; | 
|  | 547 | } | 
| Christoph Lameter | 2f1b624 | 2006-09-25 23:31:13 -0700 | [diff] [blame] | 548 |  | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 549 | static inline void set_page_node(struct page *page, unsigned long node) | 
|  | 550 | { | 
|  | 551 | page->flags &= ~(NODES_MASK << NODES_PGSHIFT); | 
|  | 552 | page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; | 
|  | 553 | } | 
| Christoph Lameter | 89689ae | 2006-12-06 20:31:45 -0800 | [diff] [blame] | 554 |  | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 555 | static inline void set_page_section(struct page *page, unsigned long section) | 
|  | 556 | { | 
|  | 557 | page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); | 
|  | 558 | page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; | 
|  | 559 | } | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 560 |  | 
| Christoph Lameter | 2f1b624 | 2006-09-25 23:31:13 -0700 | [diff] [blame] | 561 | static inline void set_page_links(struct page *page, enum zone_type zone, | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 562 | unsigned long node, unsigned long pfn) | 
| Dave Hansen | 348f8b6 | 2005-06-23 00:07:40 -0700 | [diff] [blame] | 563 | { | 
|  | 564 | set_page_zone(page, zone); | 
|  | 565 | set_page_node(page, node); | 
| Andy Whitcroft | d41dee3 | 2005-06-23 00:07:54 -0700 | [diff] [blame] | 566 | set_page_section(page, pfn_to_section_nr(pfn)); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 567 | } | 
|  | 568 |  | 
| Christoph Lameter | f6ac235 | 2006-06-30 01:55:32 -0700 | [diff] [blame] | 569 | /* | 
| Eric Paris | 7cd9414 | 2007-11-26 18:47:40 -0500 | [diff] [blame] | 570 | * If a hint addr is less than mmap_min_addr change hint to be as | 
|  | 571 | * low as possible but still greater than mmap_min_addr | 
|  | 572 | */ | 
|  | 573 | static inline unsigned long round_hint_to_min(unsigned long hint) | 
|  | 574 | { | 
|  | 575 | #ifdef CONFIG_SECURITY | 
|  | 576 | hint &= PAGE_MASK; | 
|  | 577 | if (((void *)hint != NULL) && | 
|  | 578 | (hint < mmap_min_addr)) | 
|  | 579 | return PAGE_ALIGN(mmap_min_addr); | 
|  | 580 | #endif | 
|  | 581 | return hint; | 
|  | 582 | } | 
|  | 583 |  | 
|  | 584 | /* | 
| Christoph Lameter | f6ac235 | 2006-06-30 01:55:32 -0700 | [diff] [blame] | 585 | * Some inline functions in vmstat.h depend on page_zone() | 
|  | 586 | */ | 
|  | 587 | #include <linux/vmstat.h> | 
|  | 588 |  | 
| Ingo Molnar | 652050a | 2006-01-14 13:21:30 -0800 | [diff] [blame] | 589 | static __always_inline void *lowmem_page_address(struct page *page) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 590 | { | 
|  | 591 | return __va(page_to_pfn(page) << PAGE_SHIFT); | 
|  | 592 | } | 
|  | 593 |  | 
|  | 594 | #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) | 
|  | 595 | #define HASHED_PAGE_VIRTUAL | 
|  | 596 | #endif | 
|  | 597 |  | 
|  | 598 | #if defined(WANT_PAGE_VIRTUAL) | 
|  | 599 | #define page_address(page) ((page)->virtual) | 
|  | 600 | #define set_page_address(page, address)			\ | 
|  | 601 | do {						\ | 
|  | 602 | (page)->virtual = (address);		\ | 
|  | 603 | } while(0) | 
|  | 604 | #define page_address_init()  do { } while(0) | 
|  | 605 | #endif | 
|  | 606 |  | 
|  | 607 | #if defined(HASHED_PAGE_VIRTUAL) | 
|  | 608 | void *page_address(struct page *page); | 
|  | 609 | void set_page_address(struct page *page, void *virtual); | 
|  | 610 | void page_address_init(void); | 
|  | 611 | #endif | 
|  | 612 |  | 
|  | 613 | #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) | 
|  | 614 | #define page_address(page) lowmem_page_address(page) | 
|  | 615 | #define set_page_address(page, address)  do { } while(0) | 
|  | 616 | #define page_address_init()  do { } while(0) | 
|  | 617 | #endif | 
|  | 618 |  | 
|  | 619 | /* | 
|  | 620 | * On an anonymous page mapped into a user virtual memory area, | 
|  | 621 | * page->mapping points to its anon_vma, not to a struct address_space; | 
|  | 622 | * with the PAGE_MAPPING_ANON bit set to distinguish it. | 
|  | 623 | * | 
|  | 624 | * Please note that, confusingly, "page_mapping" refers to the inode | 
|  | 625 | * address_space which maps the page from disk; whereas "page_mapped" | 
|  | 626 | * refers to user virtual address space into which the page is mapped. | 
|  | 627 | */ | 
|  | 628 | #define PAGE_MAPPING_ANON	1 | 
|  | 629 |  | 
|  | 630 | extern struct address_space swapper_space; | 
|  | 631 | static inline struct address_space *page_mapping(struct page *page) | 
|  | 632 | { | 
|  | 633 | struct address_space *mapping = page->mapping; | 
|  | 634 |  | 
| Christoph Lameter | b5fab14 | 2007-07-17 04:03:33 -0700 | [diff] [blame] | 635 | VM_BUG_ON(PageSlab(page)); | 
| Andrew Morton | 726b801 | 2008-04-28 02:12:44 -0700 | [diff] [blame] | 636 | #ifdef CONFIG_SWAP | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 637 | if (unlikely(PageSwapCache(page))) | 
|  | 638 | mapping = &swapper_space; | 
| Andrew Morton | 726b801 | 2008-04-28 02:12:44 -0700 | [diff] [blame] | 639 | else | 
|  | 640 | #endif | 
|  | 641 | if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON)) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 642 | mapping = NULL; | 
|  | 643 | return mapping; | 
|  | 644 | } | 
|  | 645 |  | 
|  | 646 | static inline int PageAnon(struct page *page) | 
|  | 647 | { | 
|  | 648 | return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; | 
|  | 649 | } | 
|  | 650 |  | 
|  | 651 | /* | 
|  | 652 | * Return the pagecache index of the passed page.  Regular pagecache pages | 
|  | 653 | * use ->index whereas swapcache pages use ->private | 
|  | 654 | */ | 
|  | 655 | static inline pgoff_t page_index(struct page *page) | 
|  | 656 | { | 
|  | 657 | if (unlikely(PageSwapCache(page))) | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 658 | return page_private(page); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 659 | return page->index; | 
|  | 660 | } | 
|  | 661 |  | 
|  | 662 | /* | 
|  | 663 | * The atomic page->_mapcount, like _count, starts from -1: | 
|  | 664 | * so that transitions both from it and to it can be tracked, | 
|  | 665 | * using atomic_inc_and_test and atomic_add_negative(-1). | 
|  | 666 | */ | 
|  | 667 | static inline void reset_page_mapcount(struct page *page) | 
|  | 668 | { | 
|  | 669 | atomic_set(&(page)->_mapcount, -1); | 
|  | 670 | } | 
|  | 671 |  | 
|  | 672 | static inline int page_mapcount(struct page *page) | 
|  | 673 | { | 
|  | 674 | return atomic_read(&(page)->_mapcount) + 1; | 
|  | 675 | } | 
|  | 676 |  | 
|  | 677 | /* | 
|  | 678 | * Return true if this page is mapped into pagetables. | 
|  | 679 | */ | 
|  | 680 | static inline int page_mapped(struct page *page) | 
|  | 681 | { | 
|  | 682 | return atomic_read(&(page)->_mapcount) >= 0; | 
|  | 683 | } | 
|  | 684 |  | 
|  | 685 | /* | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 686 | * Different kinds of faults, as returned by handle_mm_fault(). | 
|  | 687 | * Used to decide whether a process gets delivered SIGBUS or | 
|  | 688 | * just gets major/minor fault counters bumped up. | 
|  | 689 | */ | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 690 |  | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 691 | #define VM_FAULT_MINOR	0 /* For backwards compat. Remove me quickly. */ | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 692 |  | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 693 | #define VM_FAULT_OOM	0x0001 | 
|  | 694 | #define VM_FAULT_SIGBUS	0x0002 | 
|  | 695 | #define VM_FAULT_MAJOR	0x0004 | 
|  | 696 | #define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */ | 
| Nick Piggin | f33ea7f | 2005-08-03 20:24:01 +1000 | [diff] [blame] | 697 |  | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 698 | #define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */ | 
|  | 699 | #define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 700 |  | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 701 | #define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS) | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 702 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 703 | #define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK) | 
|  | 704 |  | 
|  | 705 | extern void show_free_areas(void); | 
|  | 706 |  | 
|  | 707 | #ifdef CONFIG_SHMEM | 
| Lee Schermerhorn | 89e004ea | 2008-10-18 20:26:43 -0700 | [diff] [blame] | 708 | extern int shmem_lock(struct file *file, int lock, struct user_struct *user); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 709 | #else | 
| Russell King | 03b00eb | 2006-01-06 00:10:52 -0800 | [diff] [blame] | 710 | static inline int shmem_lock(struct file *file, int lock, | 
| Lee Schermerhorn | 89e004ea | 2008-10-18 20:26:43 -0700 | [diff] [blame] | 711 | struct user_struct *user) | 
| Russell King | 03b00eb | 2006-01-06 00:10:52 -0800 | [diff] [blame] | 712 | { | 
|  | 713 | return 0; | 
|  | 714 | } | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 715 | #endif | 
|  | 716 | struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags); | 
|  | 717 |  | 
|  | 718 | int shmem_zero_setup(struct vm_area_struct *); | 
|  | 719 |  | 
| David Howells | b0e1519 | 2006-01-06 00:11:42 -0800 | [diff] [blame] | 720 | #ifndef CONFIG_MMU | 
|  | 721 | extern unsigned long shmem_get_unmapped_area(struct file *file, | 
|  | 722 | unsigned long addr, | 
|  | 723 | unsigned long len, | 
|  | 724 | unsigned long pgoff, | 
|  | 725 | unsigned long flags); | 
|  | 726 | #endif | 
|  | 727 |  | 
| Alexey Dobriyan | e8edc6e | 2007-05-21 01:22:52 +0400 | [diff] [blame] | 728 | extern int can_do_mlock(void); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 729 | extern int user_shm_lock(size_t, struct user_struct *); | 
|  | 730 | extern void user_shm_unlock(size_t, struct user_struct *); | 
|  | 731 |  | 
|  | 732 | /* | 
|  | 733 | * Parameter block passed down to zap_pte_range in exceptional cases. | 
|  | 734 | */ | 
|  | 735 | struct zap_details { | 
|  | 736 | struct vm_area_struct *nonlinear_vma;	/* Check page->index if set */ | 
|  | 737 | struct address_space *check_mapping;	/* Check page->mapping if set */ | 
|  | 738 | pgoff_t	first_index;			/* Lowest page->index to unmap */ | 
|  | 739 | pgoff_t last_index;			/* Highest page->index to unmap */ | 
|  | 740 | spinlock_t *i_mmap_lock;		/* For unmap_mapping_range: */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 741 | unsigned long truncate_count;		/* Compare vm_truncate_count */ | 
|  | 742 | }; | 
|  | 743 |  | 
| Nick Piggin | 7e67513 | 2008-04-28 02:13:00 -0700 | [diff] [blame] | 744 | struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, | 
|  | 745 | pte_t pte); | 
|  | 746 |  | 
| Jack Steiner | c627f9c | 2008-07-29 22:33:53 -0700 | [diff] [blame] | 747 | int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, | 
|  | 748 | unsigned long size); | 
| Hugh Dickins | ee39b37 | 2005-04-19 13:29:15 -0700 | [diff] [blame] | 749 | unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 750 | unsigned long size, struct zap_details *); | 
| Hugh Dickins | 508034a | 2005-10-29 18:16:30 -0700 | [diff] [blame] | 751 | unsigned long unmap_vmas(struct mmu_gather **tlb, | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 752 | struct vm_area_struct *start_vma, unsigned long start_addr, | 
|  | 753 | unsigned long end_addr, unsigned long *nr_accounted, | 
|  | 754 | struct zap_details *); | 
| Matt Mackall | e647309 | 2008-02-04 22:29:01 -0800 | [diff] [blame] | 755 |  | 
|  | 756 | /** | 
|  | 757 | * mm_walk - callbacks for walk_page_range | 
|  | 758 | * @pgd_entry: if set, called for each non-empty PGD (top-level) entry | 
|  | 759 | * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry | 
|  | 760 | * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry | 
|  | 761 | * @pte_entry: if set, called for each non-empty PTE (4th-level) entry | 
|  | 762 | * @pte_hole: if set, called for each hole at all levels | 
|  | 763 | * | 
|  | 764 | * (see walk_page_range for more details) | 
|  | 765 | */ | 
|  | 766 | struct mm_walk { | 
| Dave Hansen | 2165009 | 2008-06-12 15:21:47 -0700 | [diff] [blame] | 767 | int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, struct mm_walk *); | 
|  | 768 | int (*pud_entry)(pud_t *, unsigned long, unsigned long, struct mm_walk *); | 
|  | 769 | int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, struct mm_walk *); | 
|  | 770 | int (*pte_entry)(pte_t *, unsigned long, unsigned long, struct mm_walk *); | 
|  | 771 | int (*pte_hole)(unsigned long, unsigned long, struct mm_walk *); | 
|  | 772 | struct mm_struct *mm; | 
|  | 773 | void *private; | 
| Matt Mackall | e647309 | 2008-02-04 22:29:01 -0800 | [diff] [blame] | 774 | }; | 
|  | 775 |  | 
| Dave Hansen | 2165009 | 2008-06-12 15:21:47 -0700 | [diff] [blame] | 776 | int walk_page_range(unsigned long addr, unsigned long end, | 
|  | 777 | struct mm_walk *walk); | 
| Jan Beulich | 42b7772 | 2008-07-23 21:27:10 -0700 | [diff] [blame] | 778 | void free_pgd_range(struct mmu_gather *tlb, unsigned long addr, | 
| Hugh Dickins | 3bf5ee9 | 2005-04-19 13:29:16 -0700 | [diff] [blame] | 779 | unsigned long end, unsigned long floor, unsigned long ceiling); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 780 | int copy_page_range(struct mm_struct *dst, struct mm_struct *src, | 
|  | 781 | struct vm_area_struct *vma); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 782 | void unmap_mapping_range(struct address_space *mapping, | 
|  | 783 | loff_t const holebegin, loff_t const holelen, int even_cows); | 
| Rik van Riel | 28b2ee2 | 2008-07-23 21:27:05 -0700 | [diff] [blame] | 784 | int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, | 
|  | 785 | void *buf, int len, int write); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 786 |  | 
|  | 787 | static inline void unmap_shared_mapping_range(struct address_space *mapping, | 
|  | 788 | loff_t const holebegin, loff_t const holelen) | 
|  | 789 | { | 
|  | 790 | unmap_mapping_range(mapping, holebegin, holelen, 0); | 
|  | 791 | } | 
|  | 792 |  | 
|  | 793 | extern int vmtruncate(struct inode * inode, loff_t offset); | 
| Badari Pulavarty | f6b3ec2 | 2006-01-06 00:10:38 -0800 | [diff] [blame] | 794 | extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end); | 
| Nick Piggin | f33ea7f | 2005-08-03 20:24:01 +1000 | [diff] [blame] | 795 |  | 
| David Howells | 7ee1dd3 | 2006-01-06 00:11:44 -0800 | [diff] [blame] | 796 | #ifdef CONFIG_MMU | 
| Nick Piggin | 83c5407 | 2007-07-19 01:47:05 -0700 | [diff] [blame] | 797 | extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, | 
| David Howells | 7ee1dd3 | 2006-01-06 00:11:44 -0800 | [diff] [blame] | 798 | unsigned long address, int write_access); | 
| David Howells | 7ee1dd3 | 2006-01-06 00:11:44 -0800 | [diff] [blame] | 799 | #else | 
|  | 800 | static inline int handle_mm_fault(struct mm_struct *mm, | 
|  | 801 | struct vm_area_struct *vma, unsigned long address, | 
|  | 802 | int write_access) | 
|  | 803 | { | 
|  | 804 | /* should never happen if there's no MMU */ | 
|  | 805 | BUG(); | 
|  | 806 | return VM_FAULT_SIGBUS; | 
|  | 807 | } | 
|  | 808 | #endif | 
| Nick Piggin | f33ea7f | 2005-08-03 20:24:01 +1000 | [diff] [blame] | 809 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 810 | extern int make_pages_present(unsigned long addr, unsigned long end); | 
|  | 811 | extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 812 |  | 
|  | 813 | int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, | 
|  | 814 | int len, int write, int force, struct page **pages, struct vm_area_struct **vmas); | 
|  | 815 |  | 
| David Howells | cf9a2ae | 2006-08-29 19:05:54 +0100 | [diff] [blame] | 816 | extern int try_to_release_page(struct page * page, gfp_t gfp_mask); | 
|  | 817 | extern void do_invalidatepage(struct page *page, unsigned long offset); | 
|  | 818 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 819 | int __set_page_dirty_nobuffers(struct page *page); | 
| Ken Chen | 7671932 | 2007-02-10 01:43:15 -0800 | [diff] [blame] | 820 | int __set_page_dirty_no_writeback(struct page *page); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 821 | int redirty_page_for_writepage(struct writeback_control *wbc, | 
|  | 822 | struct page *page); | 
| Harvey Harrison | b3c9752 | 2008-02-13 15:03:15 -0800 | [diff] [blame] | 823 | int set_page_dirty(struct page *page); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 824 | int set_page_dirty_lock(struct page *page); | 
|  | 825 | int clear_page_dirty_for_io(struct page *page); | 
|  | 826 |  | 
| Ollie Wild | b6a2fea | 2007-07-19 01:48:16 -0700 | [diff] [blame] | 827 | extern unsigned long move_page_tables(struct vm_area_struct *vma, | 
|  | 828 | unsigned long old_addr, struct vm_area_struct *new_vma, | 
|  | 829 | unsigned long new_addr, unsigned long len); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 830 | extern unsigned long do_mremap(unsigned long addr, | 
|  | 831 | unsigned long old_len, unsigned long new_len, | 
|  | 832 | unsigned long flags, unsigned long new_addr); | 
| Ollie Wild | b6a2fea | 2007-07-19 01:48:16 -0700 | [diff] [blame] | 833 | extern int mprotect_fixup(struct vm_area_struct *vma, | 
|  | 834 | struct vm_area_struct **pprev, unsigned long start, | 
|  | 835 | unsigned long end, unsigned long newflags); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 836 |  | 
| Nick Piggin | 21cc199 | 2008-07-25 19:45:22 -0700 | [diff] [blame] | 837 | /* | 
|  | 838 | * get_user_pages_fast provides equivalent functionality to get_user_pages, | 
|  | 839 | * operating on current and current->mm (force=0 and doesn't return any vmas). | 
|  | 840 | * | 
|  | 841 | * get_user_pages_fast may take mmap_sem and page tables, so no assumptions | 
|  | 842 | * can be made about locking. get_user_pages_fast is to be implemented in a | 
|  | 843 | * way that is advantageous (vs get_user_pages()) when the user memory area is | 
|  | 844 | * already faulted in and present in ptes. However if the pages have to be | 
|  | 845 | * faulted in, it may turn out to be slightly slower). | 
|  | 846 | */ | 
|  | 847 | int get_user_pages_fast(unsigned long start, int nr_pages, int write, | 
|  | 848 | struct page **pages); | 
|  | 849 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 850 | /* | 
| Rusty Russell | 8e1f936 | 2007-07-17 04:03:17 -0700 | [diff] [blame] | 851 | * A callback you can register to apply pressure to ageable caches. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 852 | * | 
| Rusty Russell | 8e1f936 | 2007-07-17 04:03:17 -0700 | [diff] [blame] | 853 | * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'.  It should | 
|  | 854 | * look through the least-recently-used 'nr_to_scan' entries and | 
|  | 855 | * attempt to free them up.  It should return the number of objects | 
|  | 856 | * which remain in the cache.  If it returns -1, it means it cannot do | 
|  | 857 | * any scanning at this time (eg. there is a risk of deadlock). | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 858 | * | 
| Rusty Russell | 8e1f936 | 2007-07-17 04:03:17 -0700 | [diff] [blame] | 859 | * The 'gfpmask' refers to the allocation we are currently trying to | 
|  | 860 | * fulfil. | 
|  | 861 | * | 
|  | 862 | * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is | 
|  | 863 | * querying the cache size, so a fastpath for that case is appropriate. | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 864 | */ | 
| Rusty Russell | 8e1f936 | 2007-07-17 04:03:17 -0700 | [diff] [blame] | 865 | struct shrinker { | 
|  | 866 | int (*shrink)(int nr_to_scan, gfp_t gfp_mask); | 
|  | 867 | int seeks;	/* seeks to recreate an obj */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 868 |  | 
| Rusty Russell | 8e1f936 | 2007-07-17 04:03:17 -0700 | [diff] [blame] | 869 | /* These are for internal use */ | 
|  | 870 | struct list_head list; | 
|  | 871 | long nr;	/* objs pending delete */ | 
|  | 872 | }; | 
|  | 873 | #define DEFAULT_SEEKS 2 /* A good number if you don't know better. */ | 
|  | 874 | extern void register_shrinker(struct shrinker *); | 
|  | 875 | extern void unregister_shrinker(struct shrinker *); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 876 |  | 
| Alexey Dobriyan | 4e950f6 | 2007-07-30 02:36:13 +0400 | [diff] [blame] | 877 | int vma_wants_writenotify(struct vm_area_struct *vma); | 
| Peter Zijlstra | d08b385 | 2006-09-25 23:30:57 -0700 | [diff] [blame] | 878 |  | 
| Harvey Harrison | b3c9752 | 2008-02-13 15:03:15 -0800 | [diff] [blame] | 879 | extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl); | 
| Linus Torvalds | c9cfcdd | 2005-11-29 14:03:14 -0800 | [diff] [blame] | 880 |  | 
| Nick Piggin | 5f22df0 | 2007-05-06 14:49:02 -0700 | [diff] [blame] | 881 | #ifdef __PAGETABLE_PUD_FOLDED | 
|  | 882 | static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, | 
|  | 883 | unsigned long address) | 
|  | 884 | { | 
|  | 885 | return 0; | 
|  | 886 | } | 
|  | 887 | #else | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 888 | int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address); | 
| Nick Piggin | 5f22df0 | 2007-05-06 14:49:02 -0700 | [diff] [blame] | 889 | #endif | 
|  | 890 |  | 
|  | 891 | #ifdef __PAGETABLE_PMD_FOLDED | 
|  | 892 | static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud, | 
|  | 893 | unsigned long address) | 
|  | 894 | { | 
|  | 895 | return 0; | 
|  | 896 | } | 
|  | 897 | #else | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 898 | int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address); | 
| Nick Piggin | 5f22df0 | 2007-05-06 14:49:02 -0700 | [diff] [blame] | 899 | #endif | 
|  | 900 |  | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 901 | int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address); | 
|  | 902 | int __pte_alloc_kernel(pmd_t *pmd, unsigned long address); | 
|  | 903 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 904 | /* | 
|  | 905 | * The following ifdef needed to get the 4level-fixup.h header to work. | 
|  | 906 | * Remove it when 4level-fixup.h has been removed. | 
|  | 907 | */ | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 908 | #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 909 | static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) | 
|  | 910 | { | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 911 | return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))? | 
|  | 912 | NULL: pud_offset(pgd, address); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 913 | } | 
|  | 914 |  | 
|  | 915 | static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) | 
|  | 916 | { | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 917 | return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))? | 
|  | 918 | NULL: pmd_offset(pud, address); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 919 | } | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 920 | #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ | 
|  | 921 |  | 
| Jeremy Fitzhardinge | f7d0b92 | 2008-09-09 15:43:22 -0700 | [diff] [blame] | 922 | #if USE_SPLIT_PTLOCKS | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 923 | /* | 
|  | 924 | * We tuck a spinlock to guard each pagetable page into its struct page, | 
|  | 925 | * at page->private, with BUILD_BUG_ON to make sure that this will not | 
|  | 926 | * overflow into the next struct page (as it might with DEBUG_SPINLOCK). | 
|  | 927 | * When freeing, reset page->mapping so free_pages_check won't complain. | 
|  | 928 | */ | 
| Andrew Morton | 349aef0 | 2006-01-08 01:04:36 -0800 | [diff] [blame] | 929 | #define __pte_lockptr(page)	&((page)->ptl) | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 930 | #define pte_lock_init(_page)	do {					\ | 
|  | 931 | spin_lock_init(__pte_lockptr(_page));				\ | 
|  | 932 | } while (0) | 
|  | 933 | #define pte_lock_deinit(page)	((page)->mapping = NULL) | 
|  | 934 | #define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));}) | 
| Jeremy Fitzhardinge | f7d0b92 | 2008-09-09 15:43:22 -0700 | [diff] [blame] | 935 | #else	/* !USE_SPLIT_PTLOCKS */ | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 936 | /* | 
|  | 937 | * We use mm->page_table_lock to guard all pagetable pages of the mm. | 
|  | 938 | */ | 
|  | 939 | #define pte_lock_init(page)	do {} while (0) | 
|  | 940 | #define pte_lock_deinit(page)	do {} while (0) | 
|  | 941 | #define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;}) | 
| Jeremy Fitzhardinge | f7d0b92 | 2008-09-09 15:43:22 -0700 | [diff] [blame] | 942 | #endif /* USE_SPLIT_PTLOCKS */ | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 943 |  | 
| Martin Schwidefsky | 2f569af | 2008-02-08 04:22:04 -0800 | [diff] [blame] | 944 | static inline void pgtable_page_ctor(struct page *page) | 
|  | 945 | { | 
|  | 946 | pte_lock_init(page); | 
|  | 947 | inc_zone_page_state(page, NR_PAGETABLE); | 
|  | 948 | } | 
|  | 949 |  | 
|  | 950 | static inline void pgtable_page_dtor(struct page *page) | 
|  | 951 | { | 
|  | 952 | pte_lock_deinit(page); | 
|  | 953 | dec_zone_page_state(page, NR_PAGETABLE); | 
|  | 954 | } | 
|  | 955 |  | 
| Hugh Dickins | c74df32 | 2005-10-29 18:16:23 -0700 | [diff] [blame] | 956 | #define pte_offset_map_lock(mm, pmd, address, ptlp)	\ | 
|  | 957 | ({							\ | 
| Hugh Dickins | 4c21e2f | 2005-10-29 18:16:40 -0700 | [diff] [blame] | 958 | spinlock_t *__ptl = pte_lockptr(mm, pmd);	\ | 
| Hugh Dickins | c74df32 | 2005-10-29 18:16:23 -0700 | [diff] [blame] | 959 | pte_t *__pte = pte_offset_map(pmd, address);	\ | 
|  | 960 | *(ptlp) = __ptl;				\ | 
|  | 961 | spin_lock(__ptl);				\ | 
|  | 962 | __pte;						\ | 
|  | 963 | }) | 
|  | 964 |  | 
|  | 965 | #define pte_unmap_unlock(pte, ptl)	do {		\ | 
|  | 966 | spin_unlock(ptl);				\ | 
|  | 967 | pte_unmap(pte);					\ | 
|  | 968 | } while (0) | 
|  | 969 |  | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 970 | #define pte_alloc_map(mm, pmd, address)			\ | 
|  | 971 | ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ | 
|  | 972 | NULL: pte_offset_map(pmd, address)) | 
|  | 973 |  | 
| Hugh Dickins | c74df32 | 2005-10-29 18:16:23 -0700 | [diff] [blame] | 974 | #define pte_alloc_map_lock(mm, pmd, address, ptlp)	\ | 
|  | 975 | ((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \ | 
|  | 976 | NULL: pte_offset_map_lock(mm, pmd, address, ptlp)) | 
|  | 977 |  | 
| Hugh Dickins | 1bb3630 | 2005-10-29 18:16:22 -0700 | [diff] [blame] | 978 | #define pte_alloc_kernel(pmd, address)			\ | 
|  | 979 | ((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \ | 
|  | 980 | NULL: pte_offset_kernel(pmd, address)) | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 981 |  | 
|  | 982 | extern void free_area_init(unsigned long * zones_size); | 
| Johannes Weiner | 9109fb7 | 2008-07-23 21:27:20 -0700 | [diff] [blame] | 983 | extern void free_area_init_node(int nid, unsigned long * zones_size, | 
|  | 984 | unsigned long zone_start_pfn, unsigned long *zholes_size); | 
| Mel Gorman | c713216 | 2006-09-27 01:49:43 -0700 | [diff] [blame] | 985 | #ifdef CONFIG_ARCH_POPULATES_NODE_MAP | 
|  | 986 | /* | 
|  | 987 | * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its | 
|  | 988 | * zones, allocate the backing mem_map and account for memory holes in a more | 
|  | 989 | * architecture independent manner. This is a substitute for creating the | 
|  | 990 | * zone_sizes[] and zholes_size[] arrays and passing them to | 
|  | 991 | * free_area_init_node() | 
|  | 992 | * | 
|  | 993 | * An architecture is expected to register range of page frames backed by | 
|  | 994 | * physical memory with add_active_range() before calling | 
|  | 995 | * free_area_init_nodes() passing in the PFN each zone ends at. At a basic | 
|  | 996 | * usage, an architecture is expected to do something like | 
|  | 997 | * | 
|  | 998 | * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, | 
|  | 999 | * 							 max_highmem_pfn}; | 
|  | 1000 | * for_each_valid_physical_page_range() | 
|  | 1001 | * 	add_active_range(node_id, start_pfn, end_pfn) | 
|  | 1002 | * free_area_init_nodes(max_zone_pfns); | 
|  | 1003 | * | 
|  | 1004 | * If the architecture guarantees that there are no holes in the ranges | 
|  | 1005 | * registered with add_active_range(), free_bootmem_active_regions() | 
|  | 1006 | * will call free_bootmem_node() for each registered physical page range. | 
|  | 1007 | * Similarly sparse_memory_present_with_active_regions() calls | 
|  | 1008 | * memory_present() for each range when SPARSEMEM is enabled. | 
|  | 1009 | * | 
|  | 1010 | * See mm/page_alloc.c for more information on each function exposed by | 
|  | 1011 | * CONFIG_ARCH_POPULATES_NODE_MAP | 
|  | 1012 | */ | 
|  | 1013 | extern void free_area_init_nodes(unsigned long *max_zone_pfn); | 
|  | 1014 | extern void add_active_range(unsigned int nid, unsigned long start_pfn, | 
|  | 1015 | unsigned long end_pfn); | 
| Yinghai Lu | cc1050b | 2008-06-13 19:08:52 -0700 | [diff] [blame] | 1016 | extern void remove_active_range(unsigned int nid, unsigned long start_pfn, | 
|  | 1017 | unsigned long end_pfn); | 
| Mel Gorman | fb01439 | 2006-09-27 01:49:59 -0700 | [diff] [blame] | 1018 | extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn, | 
|  | 1019 | unsigned long end_pfn); | 
| Mel Gorman | c713216 | 2006-09-27 01:49:43 -0700 | [diff] [blame] | 1020 | extern void remove_all_active_ranges(void); | 
|  | 1021 | extern unsigned long absent_pages_in_range(unsigned long start_pfn, | 
|  | 1022 | unsigned long end_pfn); | 
|  | 1023 | extern void get_pfn_range_for_nid(unsigned int nid, | 
|  | 1024 | unsigned long *start_pfn, unsigned long *end_pfn); | 
|  | 1025 | extern unsigned long find_min_pfn_with_active_regions(void); | 
| Mel Gorman | c713216 | 2006-09-27 01:49:43 -0700 | [diff] [blame] | 1026 | extern void free_bootmem_with_active_regions(int nid, | 
|  | 1027 | unsigned long max_low_pfn); | 
| Yinghai Lu | d52d53b | 2008-06-16 20:10:55 -0700 | [diff] [blame] | 1028 | typedef int (*work_fn_t)(unsigned long, unsigned long, void *); | 
| Yinghai Lu | b5bc6c0 | 2008-06-14 18:32:52 -0700 | [diff] [blame] | 1029 | extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data); | 
| Mel Gorman | c713216 | 2006-09-27 01:49:43 -0700 | [diff] [blame] | 1030 | extern void sparse_memory_present_with_active_regions(int nid); | 
|  | 1031 | #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID | 
|  | 1032 | extern int early_pfn_to_nid(unsigned long pfn); | 
|  | 1033 | #endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ | 
|  | 1034 | #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ | 
| Mel Gorman | 0e0b864 | 2006-09-27 01:49:56 -0700 | [diff] [blame] | 1035 | extern void set_dma_reserve(unsigned long new_dma_reserve); | 
| Dave Hansen | a2f3aa0 | 2007-01-10 23:15:30 -0800 | [diff] [blame] | 1036 | extern void memmap_init_zone(unsigned long, int, unsigned long, | 
|  | 1037 | unsigned long, enum memmap_context); | 
| Dave Hansen | 3947be1 | 2005-10-29 18:16:54 -0700 | [diff] [blame] | 1038 | extern void setup_per_zone_pages_min(void); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1039 | extern void mem_init(void); | 
|  | 1040 | extern void show_mem(void); | 
|  | 1041 | extern void si_meminfo(struct sysinfo * val); | 
|  | 1042 | extern void si_meminfo_node(struct sysinfo *val, int nid); | 
| Mike Travis | 3461b0a | 2008-05-12 21:21:13 +0200 | [diff] [blame] | 1043 | extern int after_bootmem; | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1044 |  | 
| Christoph Lameter | e7c8d5c | 2005-06-21 17:14:47 -0700 | [diff] [blame] | 1045 | #ifdef CONFIG_NUMA | 
|  | 1046 | extern void setup_per_cpu_pageset(void); | 
|  | 1047 | #else | 
|  | 1048 | static inline void setup_per_cpu_pageset(void) {} | 
|  | 1049 | #endif | 
|  | 1050 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1051 | /* prio_tree.c */ | 
|  | 1052 | void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old); | 
|  | 1053 | void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *); | 
|  | 1054 | void vma_prio_tree_remove(struct vm_area_struct *, struct prio_tree_root *); | 
|  | 1055 | struct vm_area_struct *vma_prio_tree_next(struct vm_area_struct *vma, | 
|  | 1056 | struct prio_tree_iter *iter); | 
|  | 1057 |  | 
|  | 1058 | #define vma_prio_tree_foreach(vma, iter, root, begin, end)	\ | 
|  | 1059 | for (prio_tree_iter_init(iter, root, begin, end), vma = NULL;	\ | 
|  | 1060 | (vma = vma_prio_tree_next(vma, iter)); ) | 
|  | 1061 |  | 
|  | 1062 | static inline void vma_nonlinear_insert(struct vm_area_struct *vma, | 
|  | 1063 | struct list_head *list) | 
|  | 1064 | { | 
|  | 1065 | vma->shared.vm_set.parent = NULL; | 
|  | 1066 | list_add_tail(&vma->shared.vm_set.list, list); | 
|  | 1067 | } | 
|  | 1068 |  | 
|  | 1069 | /* mmap.c */ | 
| Alan Cox | 34b4e4a | 2007-08-22 14:01:28 -0700 | [diff] [blame] | 1070 | extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1071 | extern void vma_adjust(struct vm_area_struct *vma, unsigned long start, | 
|  | 1072 | unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert); | 
|  | 1073 | extern struct vm_area_struct *vma_merge(struct mm_struct *, | 
|  | 1074 | struct vm_area_struct *prev, unsigned long addr, unsigned long end, | 
|  | 1075 | unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, | 
|  | 1076 | struct mempolicy *); | 
|  | 1077 | extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); | 
|  | 1078 | extern int split_vma(struct mm_struct *, | 
|  | 1079 | struct vm_area_struct *, unsigned long addr, int new_below); | 
|  | 1080 | extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *); | 
|  | 1081 | extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *, | 
|  | 1082 | struct rb_node **, struct rb_node *); | 
| Hugh Dickins | a8fb561 | 2005-10-29 18:15:57 -0700 | [diff] [blame] | 1083 | extern void unlink_file_vma(struct vm_area_struct *); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1084 | extern struct vm_area_struct *copy_vma(struct vm_area_struct **, | 
|  | 1085 | unsigned long addr, unsigned long len, pgoff_t pgoff); | 
|  | 1086 | extern void exit_mmap(struct mm_struct *); | 
| Matt Helsley | 925d1c4 | 2008-04-29 01:01:36 -0700 | [diff] [blame] | 1087 |  | 
| Andrea Arcangeli | 7906d00 | 2008-07-28 15:46:26 -0700 | [diff] [blame] | 1088 | extern int mm_take_all_locks(struct mm_struct *mm); | 
|  | 1089 | extern void mm_drop_all_locks(struct mm_struct *mm); | 
|  | 1090 |  | 
| Matt Helsley | 925d1c4 | 2008-04-29 01:01:36 -0700 | [diff] [blame] | 1091 | #ifdef CONFIG_PROC_FS | 
|  | 1092 | /* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */ | 
|  | 1093 | extern void added_exe_file_vma(struct mm_struct *mm); | 
|  | 1094 | extern void removed_exe_file_vma(struct mm_struct *mm); | 
|  | 1095 | #else | 
|  | 1096 | static inline void added_exe_file_vma(struct mm_struct *mm) | 
|  | 1097 | {} | 
|  | 1098 |  | 
|  | 1099 | static inline void removed_exe_file_vma(struct mm_struct *mm) | 
|  | 1100 | {} | 
|  | 1101 | #endif /* CONFIG_PROC_FS */ | 
|  | 1102 |  | 
| akpm@osdl.org | 119f657 | 2005-05-01 08:58:35 -0700 | [diff] [blame] | 1103 | extern int may_expand_vm(struct mm_struct *mm, unsigned long npages); | 
| Roland McGrath | fa5dc22 | 2007-02-08 14:20:41 -0800 | [diff] [blame] | 1104 | extern int install_special_mapping(struct mm_struct *mm, | 
|  | 1105 | unsigned long addr, unsigned long len, | 
|  | 1106 | unsigned long flags, struct page **pages); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1107 |  | 
|  | 1108 | extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); | 
|  | 1109 |  | 
|  | 1110 | extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr, | 
|  | 1111 | unsigned long len, unsigned long prot, | 
|  | 1112 | unsigned long flag, unsigned long pgoff); | 
| Miklos Szeredi | 0165ab4 | 2007-07-15 23:38:26 -0700 | [diff] [blame] | 1113 | extern unsigned long mmap_region(struct file *file, unsigned long addr, | 
|  | 1114 | unsigned long len, unsigned long flags, | 
|  | 1115 | unsigned int vm_flags, unsigned long pgoff, | 
|  | 1116 | int accountable); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1117 |  | 
|  | 1118 | static inline unsigned long do_mmap(struct file *file, unsigned long addr, | 
|  | 1119 | unsigned long len, unsigned long prot, | 
|  | 1120 | unsigned long flag, unsigned long offset) | 
|  | 1121 | { | 
|  | 1122 | unsigned long ret = -EINVAL; | 
|  | 1123 | if ((offset + PAGE_ALIGN(len)) < offset) | 
|  | 1124 | goto out; | 
|  | 1125 | if (!(offset & ~PAGE_MASK)) | 
|  | 1126 | ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); | 
|  | 1127 | out: | 
|  | 1128 | return ret; | 
|  | 1129 | } | 
|  | 1130 |  | 
|  | 1131 | extern int do_munmap(struct mm_struct *, unsigned long, size_t); | 
|  | 1132 |  | 
|  | 1133 | extern unsigned long do_brk(unsigned long, unsigned long); | 
|  | 1134 |  | 
|  | 1135 | /* filemap.c */ | 
|  | 1136 | extern unsigned long page_unuse(struct page *); | 
|  | 1137 | extern void truncate_inode_pages(struct address_space *, loff_t); | 
| Hans Reiser | d733907 | 2006-01-06 00:10:36 -0800 | [diff] [blame] | 1138 | extern void truncate_inode_pages_range(struct address_space *, | 
|  | 1139 | loff_t lstart, loff_t lend); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1140 |  | 
|  | 1141 | /* generic vm_area_ops exported for stackable file systems */ | 
| Nick Piggin | d0217ac | 2007-07-19 01:47:03 -0700 | [diff] [blame] | 1142 | extern int filemap_fault(struct vm_area_struct *, struct vm_fault *); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1143 |  | 
|  | 1144 | /* mm/page-writeback.c */ | 
|  | 1145 | int write_one_page(struct page *page, int wait); | 
|  | 1146 |  | 
|  | 1147 | /* readahead.c */ | 
|  | 1148 | #define VM_MAX_READAHEAD	128	/* kbytes */ | 
|  | 1149 | #define VM_MIN_READAHEAD	16	/* kbytes (includes current page) */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1150 |  | 
|  | 1151 | int do_page_cache_readahead(struct address_space *mapping, struct file *filp, | 
| Andrew Morton | 7361f4d | 2005-11-07 00:59:28 -0800 | [diff] [blame] | 1152 | pgoff_t offset, unsigned long nr_to_read); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1153 | int force_page_cache_readahead(struct address_space *mapping, struct file *filp, | 
| Andrew Morton | 7361f4d | 2005-11-07 00:59:28 -0800 | [diff] [blame] | 1154 | pgoff_t offset, unsigned long nr_to_read); | 
| Rusty Russell | cf914a7 | 2007-07-19 01:48:08 -0700 | [diff] [blame] | 1155 |  | 
|  | 1156 | void page_cache_sync_readahead(struct address_space *mapping, | 
|  | 1157 | struct file_ra_state *ra, | 
|  | 1158 | struct file *filp, | 
|  | 1159 | pgoff_t offset, | 
|  | 1160 | unsigned long size); | 
|  | 1161 |  | 
|  | 1162 | void page_cache_async_readahead(struct address_space *mapping, | 
|  | 1163 | struct file_ra_state *ra, | 
|  | 1164 | struct file *filp, | 
|  | 1165 | struct page *pg, | 
|  | 1166 | pgoff_t offset, | 
|  | 1167 | unsigned long size); | 
|  | 1168 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1169 | unsigned long max_sane_readahead(unsigned long nr); | 
|  | 1170 |  | 
|  | 1171 | /* Do stack extension */ | 
| Hugh Dickins | 46dea3d | 2005-10-29 18:16:20 -0700 | [diff] [blame] | 1172 | extern int expand_stack(struct vm_area_struct *vma, unsigned long address); | 
| Matthew Wilcox | 9ab8851 | 2005-11-18 16:16:42 -0500 | [diff] [blame] | 1173 | #ifdef CONFIG_IA64 | 
| Hugh Dickins | 46dea3d | 2005-10-29 18:16:20 -0700 | [diff] [blame] | 1174 | extern int expand_upwards(struct vm_area_struct *vma, unsigned long address); | 
| Matthew Wilcox | 9ab8851 | 2005-11-18 16:16:42 -0500 | [diff] [blame] | 1175 | #endif | 
| Ollie Wild | b6a2fea | 2007-07-19 01:48:16 -0700 | [diff] [blame] | 1176 | extern int expand_stack_downwards(struct vm_area_struct *vma, | 
|  | 1177 | unsigned long address); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1178 |  | 
|  | 1179 | /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */ | 
|  | 1180 | extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr); | 
|  | 1181 | extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr, | 
|  | 1182 | struct vm_area_struct **pprev); | 
|  | 1183 |  | 
|  | 1184 | /* Look up the first VMA which intersects the interval start_addr..end_addr-1, | 
|  | 1185 | NULL if none.  Assume start_addr < end_addr. */ | 
|  | 1186 | static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr) | 
|  | 1187 | { | 
|  | 1188 | struct vm_area_struct * vma = find_vma(mm,start_addr); | 
|  | 1189 |  | 
|  | 1190 | if (vma && end_addr <= vma->vm_start) | 
|  | 1191 | vma = NULL; | 
|  | 1192 | return vma; | 
|  | 1193 | } | 
|  | 1194 |  | 
|  | 1195 | static inline unsigned long vma_pages(struct vm_area_struct *vma) | 
|  | 1196 | { | 
|  | 1197 | return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; | 
|  | 1198 | } | 
|  | 1199 |  | 
| Hugh Dickins | 804af2c | 2006-07-26 21:39:49 +0100 | [diff] [blame] | 1200 | pgprot_t vm_get_page_prot(unsigned long vm_flags); | 
| Hugh Dickins | deceb6c | 2005-10-29 18:16:33 -0700 | [diff] [blame] | 1201 | struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); | 
| Hugh Dickins | deceb6c | 2005-10-29 18:16:33 -0700 | [diff] [blame] | 1202 | int remap_pfn_range(struct vm_area_struct *, unsigned long addr, | 
|  | 1203 | unsigned long pfn, unsigned long size, pgprot_t); | 
| Linus Torvalds | a145dd4 | 2005-11-30 09:35:19 -0800 | [diff] [blame] | 1204 | int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); | 
| Nick Piggin | e0dc0d8 | 2007-02-12 00:51:36 -0800 | [diff] [blame] | 1205 | int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, | 
|  | 1206 | unsigned long pfn); | 
| Nick Piggin | 423bad6 | 2008-04-28 02:13:01 -0700 | [diff] [blame] | 1207 | int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, | 
|  | 1208 | unsigned long pfn); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1209 |  | 
| Linus Torvalds | 6aab341 | 2005-11-28 14:34:23 -0800 | [diff] [blame] | 1210 | struct page *follow_page(struct vm_area_struct *, unsigned long address, | 
| Hugh Dickins | deceb6c | 2005-10-29 18:16:33 -0700 | [diff] [blame] | 1211 | unsigned int foll_flags); | 
|  | 1212 | #define FOLL_WRITE	0x01	/* check pte is writable */ | 
|  | 1213 | #define FOLL_TOUCH	0x02	/* mark page accessed */ | 
|  | 1214 | #define FOLL_GET	0x04	/* do get_page on page */ | 
|  | 1215 | #define FOLL_ANON	0x08	/* give ZERO_PAGE if no pgtable */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1216 |  | 
| Martin Schwidefsky | 2f569af | 2008-02-08 04:22:04 -0800 | [diff] [blame] | 1217 | typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr, | 
| Jeremy Fitzhardinge | aee16b3 | 2007-05-06 14:48:54 -0700 | [diff] [blame] | 1218 | void *data); | 
|  | 1219 | extern int apply_to_page_range(struct mm_struct *mm, unsigned long address, | 
|  | 1220 | unsigned long size, pte_fn_t fn, void *data); | 
|  | 1221 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1222 | #ifdef CONFIG_PROC_FS | 
| Hugh Dickins | ab50b8e | 2005-10-29 18:15:56 -0700 | [diff] [blame] | 1223 | void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long); | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1224 | #else | 
| Hugh Dickins | ab50b8e | 2005-10-29 18:15:56 -0700 | [diff] [blame] | 1225 | static inline void vm_stat_account(struct mm_struct *mm, | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1226 | unsigned long flags, struct file *file, long pages) | 
|  | 1227 | { | 
|  | 1228 | } | 
|  | 1229 | #endif /* CONFIG_PROC_FS */ | 
|  | 1230 |  | 
| Ingo Molnar | 12d6f21 | 2008-01-30 13:33:58 +0100 | [diff] [blame] | 1231 | #ifdef CONFIG_DEBUG_PAGEALLOC | 
|  | 1232 | extern int debug_pagealloc_enabled; | 
|  | 1233 |  | 
|  | 1234 | extern void kernel_map_pages(struct page *page, int numpages, int enable); | 
|  | 1235 |  | 
|  | 1236 | static inline void enable_debug_pagealloc(void) | 
|  | 1237 | { | 
|  | 1238 | debug_pagealloc_enabled = 1; | 
|  | 1239 | } | 
| Rafael J. Wysocki | 8a235ef | 2008-02-20 01:47:44 +0100 | [diff] [blame] | 1240 | #ifdef CONFIG_HIBERNATION | 
|  | 1241 | extern bool kernel_page_present(struct page *page); | 
|  | 1242 | #endif /* CONFIG_HIBERNATION */ | 
| Ingo Molnar | 12d6f21 | 2008-01-30 13:33:58 +0100 | [diff] [blame] | 1243 | #else | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1244 | static inline void | 
| Nick Piggin | 9858db5 | 2006-10-11 01:21:30 -0700 | [diff] [blame] | 1245 | kernel_map_pages(struct page *page, int numpages, int enable) {} | 
| Ingo Molnar | 12d6f21 | 2008-01-30 13:33:58 +0100 | [diff] [blame] | 1246 | static inline void enable_debug_pagealloc(void) | 
|  | 1247 | { | 
|  | 1248 | } | 
| Rafael J. Wysocki | 8a235ef | 2008-02-20 01:47:44 +0100 | [diff] [blame] | 1249 | #ifdef CONFIG_HIBERNATION | 
|  | 1250 | static inline bool kernel_page_present(struct page *page) { return true; } | 
|  | 1251 | #endif /* CONFIG_HIBERNATION */ | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1252 | #endif | 
|  | 1253 |  | 
|  | 1254 | extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk); | 
|  | 1255 | #ifdef	__HAVE_ARCH_GATE_AREA | 
|  | 1256 | int in_gate_area_no_task(unsigned long addr); | 
|  | 1257 | int in_gate_area(struct task_struct *task, unsigned long addr); | 
|  | 1258 | #else | 
|  | 1259 | int in_gate_area_no_task(unsigned long addr); | 
|  | 1260 | #define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);}) | 
|  | 1261 | #endif	/* __HAVE_ARCH_GATE_AREA */ | 
|  | 1262 |  | 
| Andrew Morton | 9d0243b | 2006-01-08 01:00:39 -0800 | [diff] [blame] | 1263 | int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, | 
|  | 1264 | void __user *, size_t *, loff_t *); | 
| Andrew Morton | 69e0594 | 2006-03-22 00:08:19 -0800 | [diff] [blame] | 1265 | unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, | 
| Andrew Morton | 9d0243b | 2006-01-08 01:00:39 -0800 | [diff] [blame] | 1266 | unsigned long lru_pages); | 
| Andrew Morton | 9d0243b | 2006-01-08 01:00:39 -0800 | [diff] [blame] | 1267 |  | 
| Luke Yang | 7a9166e | 2006-02-20 18:28:07 -0800 | [diff] [blame] | 1268 | #ifndef CONFIG_MMU | 
|  | 1269 | #define randomize_va_space 0 | 
|  | 1270 | #else | 
| Andi Kleen | a62eaf1 | 2006-02-16 23:41:58 +0100 | [diff] [blame] | 1271 | extern int randomize_va_space; | 
| Luke Yang | 7a9166e | 2006-02-20 18:28:07 -0800 | [diff] [blame] | 1272 | #endif | 
| Andi Kleen | a62eaf1 | 2006-02-16 23:41:58 +0100 | [diff] [blame] | 1273 |  | 
| Sam Ravnborg | 045e72a | 2007-07-26 10:41:13 -0700 | [diff] [blame] | 1274 | const char * arch_vma_name(struct vm_area_struct *vma); | 
| Andi Kleen | 0325291 | 2008-01-30 13:33:18 +0100 | [diff] [blame] | 1275 | void print_vma_addr(char *prefix, unsigned long rip); | 
| Ingo Molnar | e6e5494 | 2006-06-27 02:53:50 -0700 | [diff] [blame] | 1276 |  | 
| Yasunori Goto | 98f3cfc | 2007-10-16 01:26:14 -0700 | [diff] [blame] | 1277 | struct page *sparse_mem_map_populate(unsigned long pnum, int nid); | 
| Andy Whitcroft | 29c7111 | 2007-10-16 01:24:14 -0700 | [diff] [blame] | 1278 | pgd_t *vmemmap_pgd_populate(unsigned long addr, int node); | 
|  | 1279 | pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node); | 
|  | 1280 | pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node); | 
|  | 1281 | pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node); | 
| Christoph Lameter | 8f6aac4 | 2007-10-16 01:24:13 -0700 | [diff] [blame] | 1282 | void *vmemmap_alloc_block(unsigned long size, int node); | 
|  | 1283 | void vmemmap_verify(pte_t *, int, unsigned long, unsigned long); | 
| Andy Whitcroft | 29c7111 | 2007-10-16 01:24:14 -0700 | [diff] [blame] | 1284 | int vmemmap_populate_basepages(struct page *start_page, | 
|  | 1285 | unsigned long pages, int node); | 
|  | 1286 | int vmemmap_populate(struct page *start_page, unsigned long pages, int node); | 
| Yinghai Lu | c2b91e2 | 2008-04-12 01:19:24 -0700 | [diff] [blame] | 1287 | void vmemmap_populate_print_last(void); | 
| Christoph Lameter | 8f6aac4 | 2007-10-16 01:24:13 -0700 | [diff] [blame] | 1288 |  | 
| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1289 | #endif /* __KERNEL__ */ | 
|  | 1290 | #endif /* _LINUX_MM_H */ |