mm.h 49.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12
#ifndef _LINUX_MM_H
#define _LINUX_MM_H

#include <linux/errno.h>

#ifdef __KERNEL__

#include <linux/gfp.h>
#include <linux/list.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/prio_tree.h>
13
#include <linux/debug_locks.h>
14
#include <linux/mm_types.h>
15
#include <linux/range.h>
16
#include <linux/pfn.h>
L
Linus Torvalds 已提交
17 18 19

struct mempolicy;
struct anon_vma;
A
Alexey Dobriyan 已提交
20
struct file_ra_state;
A
Alexey Dobriyan 已提交
21
struct user_struct;
A
Alexey Dobriyan 已提交
22
struct writeback_control;
L
Linus Torvalds 已提交
23 24 25 26 27 28

#ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
extern unsigned long max_mapnr;
#endif

extern unsigned long num_physpages;
29
extern unsigned long totalram_pages;
L
Linus Torvalds 已提交
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44
extern void * high_memory;
extern int page_cluster;

#ifdef CONFIG_SYSCTL
extern int sysctl_legacy_va_layout;
#else
#define sysctl_legacy_va_layout 0
#endif

#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/processor.h>

#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))

45 46 47
/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)

L
Linus Torvalds 已提交
48 49 50 51 52 53 54 55 56
/*
 * Linux kernel virtual memory manager primitives.
 * The idea being to have a "virtual" mm in the same way
 * we have a virtual fs - giving a cleaner interface to the
 * mm details, and allowing different kinds of memory mappings
 * (from shared memory to executable loading to arbitrary
 * mmap() functions).
 */

57 58
extern struct kmem_cache *vm_area_cachep;

L
Linus Torvalds 已提交
59
#ifndef CONFIG_MMU
60 61
extern struct rb_root nommu_region_tree;
extern struct rw_semaphore nommu_region_sem;
L
Linus Torvalds 已提交
62 63 64 65 66

extern unsigned int kobjsize(const void *objp);
#endif

/*
H
Hugh Dickins 已提交
67
 * vm_flags in vm_area_struct, see mm_types.h.
L
Linus Torvalds 已提交
68 69 70 71 72 73
 */
#define VM_READ		0x00000001	/* currently active flags */
#define VM_WRITE	0x00000002
#define VM_EXEC		0x00000004
#define VM_SHARED	0x00000008

74
/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
L
Linus Torvalds 已提交
75 76 77 78 79 80 81
#define VM_MAYREAD	0x00000010	/* limits for mprotect() etc */
#define VM_MAYWRITE	0x00000020
#define VM_MAYEXEC	0x00000040
#define VM_MAYSHARE	0x00000080

#define VM_GROWSDOWN	0x00000100	/* general info on the segment */
#define VM_GROWSUP	0x00000200
82
#define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
L
Linus Torvalds 已提交
83 84 85 86 87 88 89 90 91 92 93 94
#define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */

#define VM_EXECUTABLE	0x00001000
#define VM_LOCKED	0x00002000
#define VM_IO           0x00004000	/* Memory mapped I/O or similar */

					/* Used by sys_madvise() */
#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */

#define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
#define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
H
Hugh Dickins 已提交
95
#define VM_RESERVED	0x00080000	/* Count as reserved_vm like IO */
L
Linus Torvalds 已提交
96
#define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
97
#define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
L
Linus Torvalds 已提交
98 99 100
#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) */
101
#define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */
R
Roland McGrath 已提交
102
#define VM_ALWAYSDUMP	0x04000000	/* Always include in core dumps */
103

N
Nick Piggin 已提交
104
#define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */
J
Jared Hulbert 已提交
105
#define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
106
#define VM_SAO		0x20000000	/* Strong Access Ordering (powerpc) */
107
#define VM_PFN_AT_MMAP	0x40000000	/* PFNMAP vma that is fully mapped at mmap time */
H
Hugh Dickins 已提交
108
#define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */
L
Linus Torvalds 已提交
109

110 111 112
/* Bits set in the VMA until the stack is in its final location */
#define VM_STACK_INCOMPLETE_SETUP	(VM_RAND_READ | VM_SEQ_READ)

L
Linus Torvalds 已提交
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
#ifndef VM_STACK_DEFAULT_FLAGS		/* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
#endif

#ifdef CONFIG_STACK_GROWSUP
#define VM_STACK_FLAGS	(VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#else
#define VM_STACK_FLAGS	(VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
#endif

#define VM_READHINTMASK			(VM_SEQ_READ | VM_RAND_READ)
#define VM_ClearReadHint(v)		(v)->vm_flags &= ~VM_READHINTMASK
#define VM_NormalReadHint(v)		(!((v)->vm_flags & VM_READHINTMASK))
#define VM_SequentialReadHint(v)	((v)->vm_flags & VM_SEQ_READ)
#define VM_RandomReadHint(v)		((v)->vm_flags & VM_RAND_READ)

N
Nick Piggin 已提交
129 130 131 132 133
/*
 * special vmas that are non-mergable, non-mlock()able
 */
#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)

L
Linus Torvalds 已提交
134 135 136 137 138 139
/*
 * mapping from the currently active vm_flags protection bits (the
 * low four bits) to a page protection mask..
 */
extern pgprot_t protection_map[16];

N
Nick Piggin 已提交
140 141
#define FAULT_FLAG_WRITE	0x01	/* Fault was a write access */
#define FAULT_FLAG_NONLINEAR	0x02	/* Fault was via a nonlinear mapping */
142
#define FAULT_FLAG_MKWRITE	0x04	/* Fault was mkwrite of existing pte */
N
Nick Piggin 已提交
143

144 145 146 147 148 149 150 151
/*
 * 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.
 */
152 153
static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
{
154
	return (vma->vm_flags & VM_PFN_AT_MMAP);
155 156 157 158 159 160
}

static inline int is_pfn_mapping(struct vm_area_struct *vma)
{
	return (vma->vm_flags & VM_PFNMAP);
}
N
Nick Piggin 已提交
161

162
/*
N
Nick Piggin 已提交
163
 * vm_fault is filled by the the pagefault handler and passed to the vma's
N
Nick Piggin 已提交
164 165
 * ->fault function. The vma's ->fault is responsible for returning a bitmask
 * of VM_FAULT_xxx flags that give details about how the fault was handled.
166
 *
N
Nick Piggin 已提交
167 168 169
 * pgoff should be used in favour of virtual_address, if possible. If pgoff
 * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear
 * mapping support.
170
 */
N
Nick Piggin 已提交
171 172 173 174 175 176
struct vm_fault {
	unsigned int flags;		/* FAULT_FLAG_xxx flags */
	pgoff_t pgoff;			/* Logical page offset based on vma */
	void __user *virtual_address;	/* Faulting virtual address */

	struct page *page;		/* ->fault handlers should return a
N
Nick Piggin 已提交
177
					 * page here, unless VM_FAULT_NOPAGE
N
Nick Piggin 已提交
178
					 * is set (which is also implied by
N
Nick Piggin 已提交
179
					 * VM_FAULT_ERROR).
N
Nick Piggin 已提交
180
					 */
181
};
L
Linus Torvalds 已提交
182 183 184 185 186 187 188 189 190

/*
 * These are the virtual MM functions - opening of an area, closing and
 * unmapping it (needed to keep files on disk up-to-date etc), pointer
 * to the functions called when a no-page or a wp-page exception occurs. 
 */
struct vm_operations_struct {
	void (*open)(struct vm_area_struct * area);
	void (*close)(struct vm_area_struct * area);
N
Nick Piggin 已提交
191
	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
192 193 194

	/* notification that a previously read-only page is about to become
	 * writable, if an error is returned it will cause a SIGBUS */
195
	int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf);
196 197 198 199 200 201

	/* 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);
L
Linus Torvalds 已提交
202
#ifdef CONFIG_NUMA
203 204 205 206 207 208 209
	/*
	 * 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.
	 */
L
Linus Torvalds 已提交
210
	int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
211 212 213 214 215 216 217 218 219 220 221

	/*
	 * 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.
	 */
L
Linus Torvalds 已提交
222 223
	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
					unsigned long addr);
224 225
	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
		const nodemask_t *to, unsigned long flags);
L
Linus Torvalds 已提交
226 227 228 229 230 231
#endif
};

struct mmu_gather;
struct inode;

A
Andrew Morton 已提交
232 233
#define page_private(page)		((page)->private)
#define set_page_private(page, v)	((page)->private = (v))
H
Hugh Dickins 已提交
234

L
Linus Torvalds 已提交
235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254
/*
 * FIXME: take this include out, include page-flags.h in
 * files which need it (119 of them)
 */
#include <linux/page-flags.h>

/*
 * Methods to modify the page usage count.
 *
 * What counts for a page usage:
 * - cache mapping   (page->mapping)
 * - private data    (page->private)
 * - page mapped in a task's page tables, each mapping
 *   is counted separately
 *
 * Also, many kernel routines increase the page count before a critical
 * routine so they can be sure the page doesn't go away from under them.
 */

/*
N
Nick Piggin 已提交
255
 * Drop a ref, return true if the refcount fell to zero (the page has no users)
L
Linus Torvalds 已提交
256
 */
257 258
static inline int put_page_testzero(struct page *page)
{
N
Nick Piggin 已提交
259
	VM_BUG_ON(atomic_read(&page->_count) == 0);
260
	return atomic_dec_and_test(&page->_count);
261
}
L
Linus Torvalds 已提交
262 263

/*
264 265
 * Try to grab a ref unless the page has a refcount of zero, return false if
 * that is the case.
L
Linus Torvalds 已提交
266
 */
267 268
static inline int get_page_unless_zero(struct page *page)
{
269
	return atomic_inc_not_zero(&page->_count);
270
}
L
Linus Torvalds 已提交
271

272 273
extern int page_is_ram(unsigned long pfn);

274
/* Support for virtually mapped pages */
275 276
struct page *vmalloc_to_page(const void *addr);
unsigned long vmalloc_to_pfn(const void *addr);
277

278 279 280 281 282 283
/*
 * Determine if an address is within the vmalloc range
 *
 * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
 * is no special casing required.
 */
284 285
static inline int is_vmalloc_addr(const void *x)
{
286
#ifdef CONFIG_MMU
287 288 289
	unsigned long addr = (unsigned long)x;

	return addr >= VMALLOC_START && addr < VMALLOC_END;
290 291
#else
	return 0;
292
#endif
293
}
294 295 296
#ifdef CONFIG_MMU
extern int is_vmalloc_or_module_addr(const void *x);
#else
297
static inline int is_vmalloc_or_module_addr(const void *x)
298 299 300 301
{
	return 0;
}
#endif
302

303 304
static inline struct page *compound_head(struct page *page)
{
305
	if (unlikely(PageTail(page)))
306 307 308 309
		return page->first_page;
	return page;
}

H
Hugh Dickins 已提交
310
static inline int page_count(struct page *page)
L
Linus Torvalds 已提交
311
{
312
	return atomic_read(&compound_head(page)->_count);
L
Linus Torvalds 已提交
313 314 315 316
}

static inline void get_page(struct page *page)
{
317
	page = compound_head(page);
N
Nick Piggin 已提交
318
	VM_BUG_ON(atomic_read(&page->_count) == 0);
L
Linus Torvalds 已提交
319 320 321
	atomic_inc(&page->_count);
}

322 323 324 325 326 327
static inline struct page *virt_to_head_page(const void *x)
{
	struct page *page = virt_to_page(x);
	return compound_head(page);
}

328 329 330 331 332 333 334 335 336
/*
 * Setup the page count before being freed into the page allocator for
 * the first time (boot or memory hotplug)
 */
static inline void init_page_count(struct page *page)
{
	atomic_set(&page->_count, 1);
}

L
Linus Torvalds 已提交
337
void put_page(struct page *page);
338
void put_pages_list(struct list_head *pages);
L
Linus Torvalds 已提交
339

N
Nick Piggin 已提交
340
void split_page(struct page *page, unsigned int order);
341
int split_free_page(struct page *page);
N
Nick Piggin 已提交
342

343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360
/*
 * Compound pages have a destructor function.  Provide a
 * prototype for that function and accessor functions.
 * These are _only_ valid on the head of a PG_compound page.
 */
typedef void compound_page_dtor(struct page *);

static inline void set_compound_page_dtor(struct page *page,
						compound_page_dtor *dtor)
{
	page[1].lru.next = (void *)dtor;
}

static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
{
	return (compound_page_dtor *)page[1].lru.next;
}

361 362
static inline int compound_order(struct page *page)
{
363
	if (!PageHead(page))
364 365 366 367 368 369 370 371 372
		return 0;
	return (unsigned long)page[1].lru.prev;
}

static inline void set_compound_order(struct page *page, unsigned long order)
{
	page[1].lru.prev = (void *)order;
}

L
Linus Torvalds 已提交
373 374 375 376 377 378 379
/*
 * Multiple processes may "see" the same page. E.g. for untouched
 * mappings of /dev/null, all processes see the same page full of
 * zeroes, and text pages of executables and shared libraries have
 * only one copy in memory, at most, normally.
 *
 * For the non-reserved pages, page_count(page) denotes a reference count.
380 381
 *   page_count() == 0 means the page is free. page->lru is then used for
 *   freelist management in the buddy allocator.
N
Nick Piggin 已提交
382
 *   page_count() > 0  means the page has been allocated.
L
Linus Torvalds 已提交
383
 *
N
Nick Piggin 已提交
384 385 386 387 388
 * Pages are allocated by the slab allocator in order to provide memory
 * to kmalloc and kmem_cache_alloc. In this case, the management of the
 * page, and the fields in 'struct page' are the responsibility of mm/slab.c
 * unless a particular usage is carefully commented. (the responsibility of
 * freeing the kmalloc memory is the caller's, of course).
L
Linus Torvalds 已提交
389
 *
N
Nick Piggin 已提交
390 391 392 393 394 395 396 397 398
 * A page may be used by anyone else who does a __get_free_page().
 * In this case, page_count still tracks the references, and should only
 * be used through the normal accessor functions. The top bits of page->flags
 * and page->virtual store page management information, but all other fields
 * are unused and could be used privately, carefully. The management of this
 * page is the responsibility of the one who allocated it, and those who have
 * subsequently been given references to it.
 *
 * The other pages (we may call them "pagecache pages") are completely
L
Linus Torvalds 已提交
399 400 401
 * managed by the Linux memory manager: I/O, buffers, swapping etc.
 * The following discussion applies only to them.
 *
N
Nick Piggin 已提交
402 403 404 405
 * A pagecache page contains an opaque `private' member, which belongs to the
 * page's address_space. Usually, this is the address of a circular list of
 * the page's disk buffers. PG_private must be set to tell the VM to call
 * into the filesystem to release these pages.
L
Linus Torvalds 已提交
406
 *
N
Nick Piggin 已提交
407 408 409
 * A page may belong to an inode's memory mapping. In this case, page->mapping
 * is the pointer to the inode, and page->index is the file offset of the page,
 * in units of PAGE_CACHE_SIZE.
L
Linus Torvalds 已提交
410
 *
N
Nick Piggin 已提交
411 412 413
 * If pagecache pages are not associated with an inode, they are said to be
 * anonymous pages. These may become associated with the swapcache, and in that
 * case PG_swapcache is set, and page->private is an offset into the swapcache.
L
Linus Torvalds 已提交
414
 *
N
Nick Piggin 已提交
415 416 417
 * In either case (swapcache or inode backed), the pagecache itself holds one
 * reference to the page. Setting PG_private should also increment the
 * refcount. The each user mapping also has a reference to the page.
L
Linus Torvalds 已提交
418
 *
N
Nick Piggin 已提交
419 420 421 422
 * The pagecache pages are stored in a per-mapping radix tree, which is
 * rooted at mapping->page_tree, and indexed by offset.
 * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space
 * lists, we instead now tag pages as dirty/writeback in the radix tree.
L
Linus Torvalds 已提交
423
 *
N
Nick Piggin 已提交
424
 * All pagecache pages may be subject to I/O:
L
Linus Torvalds 已提交
425 426
 * - inode pages may need to be read from disk,
 * - inode pages which have been modified and are MAP_SHARED may need
N
Nick Piggin 已提交
427 428 429 430
 *   to be written back to the inode on disk,
 * - anonymous pages (including MAP_PRIVATE file mappings) which have been
 *   modified may need to be swapped out to swap space and (later) to be read
 *   back into memory.
L
Linus Torvalds 已提交
431 432 433 434 435 436
 */

/*
 * The zone field is never updated after free_area_init_core()
 * sets it, so none of the operations on it need to be atomic.
 */
437

A
Andy Whitcroft 已提交
438 439 440 441 442 443 444 445 446 447 448

/*
 * page->flags layout:
 *
 * There are three possibilities for how page->flags get
 * laid out.  The first is for the normal case, without
 * sparsemem.  The second is for sparsemem when there is
 * plenty of space for node and section.  The last is when
 * we have run out of space and have to fall back to an
 * alternate (slower) way of determining the node.
 *
449 450 451
 * 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 |
A
Andy Whitcroft 已提交
452
 */
453
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
A
Andy Whitcroft 已提交
454 455 456 457 458 459 460
#define SECTIONS_WIDTH		SECTIONS_SHIFT
#else
#define SECTIONS_WIDTH		0
#endif

#define ZONES_WIDTH		ZONES_SHIFT

461
#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
A
Andy Whitcroft 已提交
462 463
#define NODES_WIDTH		NODES_SHIFT
#else
464 465 466
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#error "Vmemmap: No space for nodes field in page flags"
#endif
A
Andy Whitcroft 已提交
467 468 469 470
#define NODES_WIDTH		0
#endif

/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
471
#define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
A
Andy Whitcroft 已提交
472 473 474 475 476 477 478
#define NODES_PGOFF		(SECTIONS_PGOFF - NODES_WIDTH)
#define ZONES_PGOFF		(NODES_PGOFF - ZONES_WIDTH)

/*
 * We are going to use the flags for the page to node mapping if its in
 * there.  This includes the case where there is no node, so it is implicit.
 */
479 480 481
#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
#define NODE_NOT_IN_PAGE_FLAGS
#endif
A
Andy Whitcroft 已提交
482 483 484 485

#ifndef PFN_SECTION_SHIFT
#define PFN_SECTION_SHIFT 0
#endif
486 487 488 489 490 491

/*
 * Define the bit shifts to access each section.  For non-existant
 * sections we define the shift as 0; that plus a 0 mask ensures
 * the compiler will optimise away reference to them.
 */
A
Andy Whitcroft 已提交
492 493 494
#define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
#define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
#define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
495

496 497 498
/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allcator */
#ifdef NODE_NOT_IN_PAGEFLAGS
#define ZONEID_SHIFT		(SECTIONS_SHIFT + ZONES_SHIFT)
499 500
#define ZONEID_PGOFF		((SECTIONS_PGOFF < ZONES_PGOFF)? \
						SECTIONS_PGOFF : ZONES_PGOFF)
A
Andy Whitcroft 已提交
501
#else
502
#define ZONEID_SHIFT		(NODES_SHIFT + ZONES_SHIFT)
503 504
#define ZONEID_PGOFF		((NODES_PGOFF < ZONES_PGOFF)? \
						NODES_PGOFF : ZONES_PGOFF)
505 506
#endif

507
#define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0))
508

509 510
#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
511 512
#endif

A
Andy Whitcroft 已提交
513 514 515
#define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK		((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
516
#define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
517

518
static inline enum zone_type page_zonenum(struct page *page)
L
Linus Torvalds 已提交
519
{
520
	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
L
Linus Torvalds 已提交
521 522
}

523 524 525 526 527 528 529 530
/*
 * The identification function is only used by the buddy allocator for
 * determining if two pages could be buddies. We are not really
 * identifying a zone since we could be using a the section number
 * id if we have not node id available in page flags.
 * We guarantee only that it will return the same value for two
 * combinable pages in a zone.
 */
531 532
static inline int page_zone_id(struct page *page)
{
533
	return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK;
534 535
}

536
static inline int zone_to_nid(struct zone *zone)
537
{
538 539 540 541 542
#ifdef CONFIG_NUMA
	return zone->node;
#else
	return 0;
#endif
543 544
}

545
#ifdef NODE_NOT_IN_PAGE_FLAGS
546
extern int page_to_nid(struct page *page);
547
#else
548
static inline int page_to_nid(struct page *page)
A
Andy Whitcroft 已提交
549
{
550
	return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
A
Andy Whitcroft 已提交
551
}
552 553 554 555 556 557 558
#endif

static inline struct zone *page_zone(struct page *page)
{
	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
}

559
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
A
Andy Whitcroft 已提交
560 561 562 563
static inline unsigned long page_to_section(struct page *page)
{
	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
564
#endif
A
Andy Whitcroft 已提交
565

566
static inline void set_page_zone(struct page *page, enum zone_type zone)
567 568 569 570
{
	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
	page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
}
571

572 573 574 575
static inline void set_page_node(struct page *page, unsigned long node)
{
	page->flags &= ~(NODES_MASK << NODES_PGSHIFT);
	page->flags |= (node & NODES_MASK) << NODES_PGSHIFT;
L
Linus Torvalds 已提交
576
}
577

A
Andy Whitcroft 已提交
578 579 580 581 582
static inline void set_page_section(struct page *page, unsigned long section)
{
	page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
	page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
}
L
Linus Torvalds 已提交
583

584
static inline void set_page_links(struct page *page, enum zone_type zone,
A
Andy Whitcroft 已提交
585
	unsigned long node, unsigned long pfn)
L
Linus Torvalds 已提交
586
{
587 588
	set_page_zone(page, zone);
	set_page_node(page, node);
A
Andy Whitcroft 已提交
589
	set_page_section(page, pfn_to_section_nr(pfn));
L
Linus Torvalds 已提交
590 591
}

592 593 594 595 596
/*
 * Some inline functions in vmstat.h depend on page_zone()
 */
#include <linux/vmstat.h>

597
static __always_inline void *lowmem_page_address(struct page *page)
L
Linus Torvalds 已提交
598
{
599
	return __va(PFN_PHYS(page_to_pfn(page)));
L
Linus Torvalds 已提交
600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
}

#if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
#define HASHED_PAGE_VIRTUAL
#endif

#if defined(WANT_PAGE_VIRTUAL)
#define page_address(page) ((page)->virtual)
#define set_page_address(page, address)			\
	do {						\
		(page)->virtual = (address);		\
	} while(0)
#define page_address_init()  do { } while(0)
#endif

#if defined(HASHED_PAGE_VIRTUAL)
void *page_address(struct page *page);
void set_page_address(struct page *page, void *virtual);
void page_address_init(void);
#endif

#if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL)
#define page_address(page) lowmem_page_address(page)
#define set_page_address(page, address)  do { } while(0)
#define page_address_init()  do { } while(0)
#endif

/*
 * On an anonymous page mapped into a user virtual memory area,
 * page->mapping points to its anon_vma, not to a struct address_space;
H
Hugh Dickins 已提交
630 631 632 633 634 635 636 637
 * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
 *
 * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
 * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit;
 * and then page->mapping points, not to an anon_vma, but to a private
 * structure which KSM associates with that merged page.  See ksm.h.
 *
 * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used.
L
Linus Torvalds 已提交
638 639 640 641 642 643
 *
 * Please note that, confusingly, "page_mapping" refers to the inode
 * address_space which maps the page from disk; whereas "page_mapped"
 * refers to user virtual address space into which the page is mapped.
 */
#define PAGE_MAPPING_ANON	1
H
Hugh Dickins 已提交
644 645
#define PAGE_MAPPING_KSM	2
#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
L
Linus Torvalds 已提交
646 647 648 649 650 651

extern struct address_space swapper_space;
static inline struct address_space *page_mapping(struct page *page)
{
	struct address_space *mapping = page->mapping;

652
	VM_BUG_ON(PageSlab(page));
L
Linus Torvalds 已提交
653 654
	if (unlikely(PageSwapCache(page)))
		mapping = &swapper_space;
655
	else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
L
Linus Torvalds 已提交
656 657 658 659
		mapping = NULL;
	return mapping;
}

H
Hugh Dickins 已提交
660 661 662 663 664 665
/* Neutral page->mapping pointer to address_space or anon_vma or other */
static inline void *page_rmapping(struct page *page)
{
	return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS);
}

L
Linus Torvalds 已提交
666 667 668 669 670 671 672 673 674 675 676 677
static inline int PageAnon(struct page *page)
{
	return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0;
}

/*
 * Return the pagecache index of the passed page.  Regular pagecache pages
 * use ->index whereas swapcache pages use ->private
 */
static inline pgoff_t page_index(struct page *page)
{
	if (unlikely(PageSwapCache(page)))
H
Hugh Dickins 已提交
678
		return page_private(page);
L
Linus Torvalds 已提交
679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709
	return page->index;
}

/*
 * The atomic page->_mapcount, like _count, starts from -1:
 * so that transitions both from it and to it can be tracked,
 * using atomic_inc_and_test and atomic_add_negative(-1).
 */
static inline void reset_page_mapcount(struct page *page)
{
	atomic_set(&(page)->_mapcount, -1);
}

static inline int page_mapcount(struct page *page)
{
	return atomic_read(&(page)->_mapcount) + 1;
}

/*
 * Return true if this page is mapped into pagetables.
 */
static inline int page_mapped(struct page *page)
{
	return atomic_read(&(page)->_mapcount) >= 0;
}

/*
 * 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.
 */
N
Nick Piggin 已提交
710

N
Nick Piggin 已提交
711
#define VM_FAULT_MINOR	0 /* For backwards compat. Remove me quickly. */
N
Nick Piggin 已提交
712

N
Nick Piggin 已提交
713 714 715 716
#define VM_FAULT_OOM	0x0001
#define VM_FAULT_SIGBUS	0x0002
#define VM_FAULT_MAJOR	0x0004
#define VM_FAULT_WRITE	0x0008	/* Special case for get_user_pages */
717
#define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned page */
N
Nick Piggin 已提交
718

N
Nick Piggin 已提交
719 720
#define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
L
Linus Torvalds 已提交
721

722
#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)
N
Nick Piggin 已提交
723

724 725 726 727 728
/*
 * Can be called by the pagefault handler when it gets a VM_FAULT_OOM.
 */
extern void pagefault_out_of_memory(void);

L
Linus Torvalds 已提交
729 730 731 732
#define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)

extern void show_free_areas(void);

H
Hugh Dickins 已提交
733
int shmem_lock(struct file *file, int lock, struct user_struct *user);
734
struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
L
Linus Torvalds 已提交
735 736
int shmem_zero_setup(struct vm_area_struct *);

737 738 739 740 741 742 743 744
#ifndef CONFIG_MMU
extern unsigned long shmem_get_unmapped_area(struct file *file,
					     unsigned long addr,
					     unsigned long len,
					     unsigned long pgoff,
					     unsigned long flags);
#endif

A
Alexey Dobriyan 已提交
745
extern int can_do_mlock(void);
L
Linus Torvalds 已提交
746 747 748 749 750 751 752 753 754 755 756 757 758 759 760
extern int user_shm_lock(size_t, struct user_struct *);
extern void user_shm_unlock(size_t, struct user_struct *);

/*
 * Parameter block passed down to zap_pte_range in exceptional cases.
 */
struct zap_details {
	struct vm_area_struct *nonlinear_vma;	/* Check page->index if set */
	struct address_space *check_mapping;	/* Check page->mapping if set */
	pgoff_t	first_index;			/* Lowest page->index to unmap */
	pgoff_t last_index;			/* Highest page->index to unmap */
	spinlock_t *i_mmap_lock;		/* For unmap_mapping_range: */
	unsigned long truncate_count;		/* Compare vm_truncate_count */
};

N
Nick Piggin 已提交
761 762 763
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
		pte_t pte);

764 765
int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
		unsigned long size);
766
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
L
Linus Torvalds 已提交
767
		unsigned long size, struct zap_details *);
768
unsigned long unmap_vmas(struct mmu_gather **tlb,
L
Linus Torvalds 已提交
769 770 771
		struct vm_area_struct *start_vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *);
772 773 774 775 776 777 778 779

/**
 * mm_walk - callbacks for walk_page_range
 * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
 * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
 * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
 * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
 * @pte_hole: if set, called for each hole at all levels
780
 * @hugetlb_entry: if set, called for each hugetlb entry
781 782 783 784
 *
 * (see walk_page_range for more details)
 */
struct mm_walk {
D
Dave Hansen 已提交
785 786 787 788 789
	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 *);
790 791
	int (*hugetlb_entry)(pte_t *, unsigned long,
			     unsigned long, unsigned long, struct mm_walk *);
D
Dave Hansen 已提交
792 793
	struct mm_struct *mm;
	void *private;
794 795
};

D
Dave Hansen 已提交
796 797
int walk_page_range(unsigned long addr, unsigned long end,
		struct mm_walk *walk);
798
void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
799
		unsigned long end, unsigned long floor, unsigned long ceiling);
L
Linus Torvalds 已提交
800 801 802 803
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);
J
Johannes Weiner 已提交
804 805
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
	unsigned long *pfn);
806 807
int follow_phys(struct vm_area_struct *vma, unsigned long address,
		unsigned int flags, unsigned long *prot, resource_size_t *phys);
808 809
int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
			void *buf, int len, int write);
L
Linus Torvalds 已提交
810 811 812 813 814 815 816

static inline void unmap_shared_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen)
{
	unmap_mapping_range(mapping, holebegin, holelen, 0);
}

N
npiggin@suse.de 已提交
817 818 819
extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
extern int vmtruncate(struct inode *inode, loff_t offset);
extern int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end);
N
Nick Piggin 已提交
820

821
int truncate_inode_page(struct address_space *mapping, struct page *page);
822
int generic_error_remove_page(struct address_space *mapping, struct page *page);
823

824 825
int invalidate_inode_page(struct page *page);

826
#ifdef CONFIG_MMU
N
Nick Piggin 已提交
827
extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
828
			unsigned long address, unsigned int flags);
829 830 831
#else
static inline int handle_mm_fault(struct mm_struct *mm,
			struct vm_area_struct *vma, unsigned long address,
832
			unsigned int flags)
833 834 835 836 837 838
{
	/* should never happen if there's no MMU */
	BUG();
	return VM_FAULT_SIGBUS;
}
#endif
N
Nick Piggin 已提交
839

L
Linus Torvalds 已提交
840 841 842
extern int make_pages_present(unsigned long addr, unsigned long end);
extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);

843
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
844
			unsigned long start, int nr_pages, int write, int force,
845 846 847
			struct page **pages, struct vm_area_struct **vmas);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
			struct page **pages);
H
Hugh Dickins 已提交
848
struct page *get_dump_page(unsigned long addr);
L
Linus Torvalds 已提交
849

850 851 852
extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern void do_invalidatepage(struct page *page, unsigned long offset);

L
Linus Torvalds 已提交
853
int __set_page_dirty_nobuffers(struct page *page);
854
int __set_page_dirty_no_writeback(struct page *page);
L
Linus Torvalds 已提交
855 856
int redirty_page_for_writepage(struct writeback_control *wbc,
				struct page *page);
857
void account_page_dirtied(struct page *page, struct address_space *mapping);
858
int set_page_dirty(struct page *page);
L
Linus Torvalds 已提交
859 860 861
int set_page_dirty_lock(struct page *page);
int clear_page_dirty_for_io(struct page *page);

862 863 864
extern unsigned long move_page_tables(struct vm_area_struct *vma,
		unsigned long old_addr, struct vm_area_struct *new_vma,
		unsigned long new_addr, unsigned long len);
L
Linus Torvalds 已提交
865 866 867
extern unsigned long do_mremap(unsigned long addr,
			       unsigned long old_len, unsigned long new_len,
			       unsigned long flags, unsigned long new_addr);
868 869 870
extern int mprotect_fixup(struct vm_area_struct *vma,
			  struct vm_area_struct **pprev, unsigned long start,
			  unsigned long end, unsigned long newflags);
L
Linus Torvalds 已提交
871

872 873 874 875 876
/*
 * doesn't attempt to fault and will return short.
 */
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
			  struct page **pages);
K
KAMEZAWA Hiroyuki 已提交
877 878 879
/*
 * per-process(per-mm_struct) statistics.
 */
880
#if defined(SPLIT_RSS_COUNTING)
K
KAMEZAWA Hiroyuki 已提交
881 882 883 884 885 886 887 888 889
/*
 * The mm counters are not protected by its page_table_lock,
 * so must be incremented atomically.
 */
static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
{
	atomic_long_set(&mm->rss_stat.count[member], value);
}

890
unsigned long get_mm_counter(struct mm_struct *mm, int member);
K
KAMEZAWA Hiroyuki 已提交
891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977

static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
{
	atomic_long_add(value, &mm->rss_stat.count[member]);
}

static inline void inc_mm_counter(struct mm_struct *mm, int member)
{
	atomic_long_inc(&mm->rss_stat.count[member]);
}

static inline void dec_mm_counter(struct mm_struct *mm, int member)
{
	atomic_long_dec(&mm->rss_stat.count[member]);
}

#else  /* !USE_SPLIT_PTLOCKS */
/*
 * The mm counters are protected by its page_table_lock,
 * so can be incremented directly.
 */
static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
{
	mm->rss_stat.count[member] = value;
}

static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
{
	return mm->rss_stat.count[member];
}

static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
{
	mm->rss_stat.count[member] += value;
}

static inline void inc_mm_counter(struct mm_struct *mm, int member)
{
	mm->rss_stat.count[member]++;
}

static inline void dec_mm_counter(struct mm_struct *mm, int member)
{
	mm->rss_stat.count[member]--;
}

#endif /* !USE_SPLIT_PTLOCKS */

static inline unsigned long get_mm_rss(struct mm_struct *mm)
{
	return get_mm_counter(mm, MM_FILEPAGES) +
		get_mm_counter(mm, MM_ANONPAGES);
}

static inline unsigned long get_mm_hiwater_rss(struct mm_struct *mm)
{
	return max(mm->hiwater_rss, get_mm_rss(mm));
}

static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
{
	return max(mm->hiwater_vm, mm->total_vm);
}

static inline void update_hiwater_rss(struct mm_struct *mm)
{
	unsigned long _rss = get_mm_rss(mm);

	if ((mm)->hiwater_rss < _rss)
		(mm)->hiwater_rss = _rss;
}

static inline void update_hiwater_vm(struct mm_struct *mm)
{
	if (mm->hiwater_vm < mm->total_vm)
		mm->hiwater_vm = mm->total_vm;
}

static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
					 struct mm_struct *mm)
{
	unsigned long hiwater_rss = get_mm_hiwater_rss(mm);

	if (*maxrss < hiwater_rss)
		*maxrss = hiwater_rss;
}

K
KAMEZAWA Hiroyuki 已提交
978
#if defined(SPLIT_RSS_COUNTING)
979
void sync_mm_rss(struct task_struct *task, struct mm_struct *mm);
K
KAMEZAWA Hiroyuki 已提交
980 981 982 983 984
#else
static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
{
}
#endif
985

L
Linus Torvalds 已提交
986
/*
987
 * A callback you can register to apply pressure to ageable caches.
L
Linus Torvalds 已提交
988
 *
989 990 991 992 993
 * 'shrink' is passed a count 'nr_to_scan' and a 'gfpmask'.  It should
 * look through the least-recently-used 'nr_to_scan' entries and
 * attempt to free them up.  It should return the number of objects
 * which remain in the cache.  If it returns -1, it means it cannot do
 * any scanning at this time (eg. there is a risk of deadlock).
L
Linus Torvalds 已提交
994
 *
995 996 997 998 999
 * The 'gfpmask' refers to the allocation we are currently trying to
 * fulfil.
 *
 * Note that 'shrink' will be passed nr_to_scan == 0 when the VM is
 * querying the cache size, so a fastpath for that case is appropriate.
L
Linus Torvalds 已提交
1000
 */
1001
struct shrinker {
1002
	int (*shrink)(struct shrinker *, int nr_to_scan, gfp_t gfp_mask);
1003
	int seeks;	/* seeks to recreate an obj */
L
Linus Torvalds 已提交
1004

1005 1006 1007 1008 1009 1010 1011
	/* These are for internal use */
	struct list_head list;
	long nr;	/* objs pending delete */
};
#define DEFAULT_SEEKS 2 /* A good number if you don't know better. */
extern void register_shrinker(struct shrinker *);
extern void unregister_shrinker(struct shrinker *);
L
Linus Torvalds 已提交
1012

A
Alexey Dobriyan 已提交
1013
int vma_wants_writenotify(struct vm_area_struct *vma);
1014

1015
extern pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, spinlock_t **ptl);
1016

N
Nick Piggin 已提交
1017 1018 1019 1020 1021 1022 1023
#ifdef __PAGETABLE_PUD_FOLDED
static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
						unsigned long address)
{
	return 0;
}
#else
1024
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
N
Nick Piggin 已提交
1025 1026 1027 1028 1029 1030 1031 1032 1033
#endif

#ifdef __PAGETABLE_PMD_FOLDED
static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
						unsigned long address)
{
	return 0;
}
#else
1034
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
N
Nick Piggin 已提交
1035 1036
#endif

1037 1038 1039
int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);

L
Linus Torvalds 已提交
1040 1041 1042 1043
/*
 * The following ifdef needed to get the 4level-fixup.h header to work.
 * Remove it when 4level-fixup.h has been removed.
 */
1044
#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
L
Linus Torvalds 已提交
1045 1046
static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
1047 1048
	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
		NULL: pud_offset(pgd, address);
L
Linus Torvalds 已提交
1049 1050 1051 1052
}

static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
1053 1054
	return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
		NULL: pmd_offset(pud, address);
L
Linus Torvalds 已提交
1055
}
1056 1057
#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */

1058
#if USE_SPLIT_PTLOCKS
H
Hugh Dickins 已提交
1059 1060 1061 1062 1063 1064
/*
 * 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
 * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
 * When freeing, reset page->mapping so free_pages_check won't complain.
 */
A
Andrew Morton 已提交
1065
#define __pte_lockptr(page)	&((page)->ptl)
H
Hugh Dickins 已提交
1066 1067 1068 1069 1070
#define pte_lock_init(_page)	do {					\
	spin_lock_init(__pte_lockptr(_page));				\
} while (0)
#define pte_lock_deinit(page)	((page)->mapping = NULL)
#define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
1071
#else	/* !USE_SPLIT_PTLOCKS */
H
Hugh Dickins 已提交
1072 1073 1074 1075 1076 1077
/*
 * 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;})
1078
#endif /* USE_SPLIT_PTLOCKS */
H
Hugh Dickins 已提交
1079

1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091
static inline void pgtable_page_ctor(struct page *page)
{
	pte_lock_init(page);
	inc_zone_page_state(page, NR_PAGETABLE);
}

static inline void pgtable_page_dtor(struct page *page)
{
	pte_lock_deinit(page);
	dec_zone_page_state(page, NR_PAGETABLE);
}

H
Hugh Dickins 已提交
1092 1093
#define pte_offset_map_lock(mm, pmd, address, ptlp)	\
({							\
H
Hugh Dickins 已提交
1094
	spinlock_t *__ptl = pte_lockptr(mm, pmd);	\
H
Hugh Dickins 已提交
1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
	pte_t *__pte = pte_offset_map(pmd, address);	\
	*(ptlp) = __ptl;				\
	spin_lock(__ptl);				\
	__pte;						\
})

#define pte_unmap_unlock(pte, ptl)	do {		\
	spin_unlock(ptl);				\
	pte_unmap(pte);					\
} while (0)

1106 1107 1108 1109
#define pte_alloc_map(mm, pmd, address)			\
	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
		NULL: pte_offset_map(pmd, address))

H
Hugh Dickins 已提交
1110 1111 1112 1113
#define pte_alloc_map_lock(mm, pmd, address, ptlp)	\
	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
		NULL: pte_offset_map_lock(mm, pmd, address, ptlp))

1114 1115 1116
#define pte_alloc_kernel(pmd, address)			\
	((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
		NULL: pte_offset_kernel(pmd, address))
L
Linus Torvalds 已提交
1117 1118

extern void free_area_init(unsigned long * zones_size);
1119 1120
extern void free_area_init_node(int nid, unsigned long * zones_size,
		unsigned long zone_start_pfn, unsigned long *zholes_size);
1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
 * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its
 * zones, allocate the backing mem_map and account for memory holes in a more
 * architecture independent manner. This is a substitute for creating the
 * zone_sizes[] and zholes_size[] arrays and passing them to
 * free_area_init_node()
 *
 * An architecture is expected to register range of page frames backed by
 * physical memory with add_active_range() before calling
 * free_area_init_nodes() passing in the PFN each zone ends at. At a basic
 * usage, an architecture is expected to do something like
 *
 * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn,
 * 							 max_highmem_pfn};
 * for_each_valid_physical_page_range()
 * 	add_active_range(node_id, start_pfn, end_pfn)
 * free_area_init_nodes(max_zone_pfns);
 *
 * If the architecture guarantees that there are no holes in the ranges
 * registered with add_active_range(), free_bootmem_active_regions()
 * will call free_bootmem_node() for each registered physical page range.
 * Similarly sparse_memory_present_with_active_regions() calls
 * memory_present() for each range when SPARSEMEM is enabled.
 *
 * See mm/page_alloc.c for more information on each function exposed by
 * CONFIG_ARCH_POPULATES_NODE_MAP
 */
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);
1152 1153
extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
					unsigned long end_pfn);
1154
extern void remove_all_active_ranges(void);
1155 1156 1157
void sort_node_map(void);
unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
						unsigned long end_pfn);
1158 1159 1160 1161 1162 1163 1164
extern unsigned long absent_pages_in_range(unsigned long start_pfn,
						unsigned long end_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 void free_bootmem_with_active_regions(int nid,
						unsigned long max_low_pfn);
1165 1166 1167 1168
int add_from_early_node_map(struct range *range, int az,
				   int nr_range, int nid);
void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
				 u64 goal, u64 limit);
1169
typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
1170
extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
1171 1172
extern void sparse_memory_present_with_active_regions(int nid);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188

#if !defined(CONFIG_ARCH_POPULATES_NODE_MAP) && \
    !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID)
static inline int __early_pfn_to_nid(unsigned long pfn)
{
	return 0;
}
#else
/* please see mm/page_alloc.c */
extern int __meminit early_pfn_to_nid(unsigned long pfn);
#ifdef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
/* there is a per-arch backend function. */
extern int __meminit __early_pfn_to_nid(unsigned long pfn);
#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
#endif

1189
extern void set_dma_reserve(unsigned long new_dma_reserve);
D
Dave Hansen 已提交
1190 1191
extern void memmap_init_zone(unsigned long, int, unsigned long,
				unsigned long, enum memmap_context);
1192
extern void setup_per_zone_wmarks(void);
1193
extern void calculate_zone_inactive_ratio(struct zone *zone);
L
Linus Torvalds 已提交
1194
extern void mem_init(void);
1195
extern void __init mmap_init(void);
L
Linus Torvalds 已提交
1196 1197 1198
extern void show_mem(void);
extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid);
1199
extern int after_bootmem;
L
Linus Torvalds 已提交
1200

1201 1202
extern void setup_per_cpu_pageset(void);

1203 1204
extern void zone_pcp_update(struct zone *zone);

1205
/* nommu.c */
1206
extern atomic_long_t mmap_pages_allocated;
1207
extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
1208

L
Linus Torvalds 已提交
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227
/* 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 *);
void vma_prio_tree_remove(struct vm_area_struct *, struct prio_tree_root *);
struct vm_area_struct *vma_prio_tree_next(struct vm_area_struct *vma,
	struct prio_tree_iter *iter);

#define vma_prio_tree_foreach(vma, iter, root, begin, end)	\
	for (prio_tree_iter_init(iter, root, begin, end), vma = NULL;	\
		(vma = vma_prio_tree_next(vma, iter)); )

static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
					struct list_head *list)
{
	vma->shared.vm_set.parent = NULL;
	list_add_tail(&vma->shared.vm_set.list, list);
}

/* mmap.c */
1228
extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
1229
extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
L
Linus Torvalds 已提交
1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240
	unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert);
extern struct vm_area_struct *vma_merge(struct mm_struct *,
	struct vm_area_struct *prev, unsigned long addr, unsigned long end,
	unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
	struct mempolicy *);
extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
extern int split_vma(struct mm_struct *,
	struct vm_area_struct *, unsigned long addr, int new_below);
extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *,
	struct rb_node **, struct rb_node *);
1241
extern void unlink_file_vma(struct vm_area_struct *);
L
Linus Torvalds 已提交
1242 1243 1244
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 *);
M
Matt Helsley 已提交
1245

1246 1247 1248
extern int mm_take_all_locks(struct mm_struct *mm);
extern void mm_drop_all_locks(struct mm_struct *mm);

M
Matt Helsley 已提交
1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260
#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 */

A
akpm@osdl.org 已提交
1261
extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
1262 1263 1264
extern int install_special_mapping(struct mm_struct *mm,
				   unsigned long addr, unsigned long len,
				   unsigned long flags, struct page **pages);
L
Linus Torvalds 已提交
1265 1266 1267 1268 1269 1270

extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);

extern unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long pgoff);
M
Miklos Szeredi 已提交
1271 1272
extern unsigned long mmap_region(struct file *file, unsigned long addr,
	unsigned long len, unsigned long flags,
1273
	unsigned int vm_flags, unsigned long pgoff);
L
Linus Torvalds 已提交
1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294

static inline unsigned long do_mmap(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long offset)
{
	unsigned long ret = -EINVAL;
	if ((offset + PAGE_ALIGN(len)) < offset)
		goto out;
	if (!(offset & ~PAGE_MASK))
		ret = do_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
out:
	return ret;
}

extern int do_munmap(struct mm_struct *, unsigned long, size_t);

extern unsigned long do_brk(unsigned long, unsigned long);

/* filemap.c */
extern unsigned long page_unuse(struct page *);
extern void truncate_inode_pages(struct address_space *, loff_t);
1295 1296
extern void truncate_inode_pages_range(struct address_space *,
				       loff_t lstart, loff_t lend);
L
Linus Torvalds 已提交
1297 1298

/* generic vm_area_ops exported for stackable file systems */
N
Nick Piggin 已提交
1299
extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
L
Linus Torvalds 已提交
1300 1301 1302

/* mm/page-writeback.c */
int write_one_page(struct page *page, int wait);
N
Nick Piggin 已提交
1303
void task_dirty_inc(struct task_struct *tsk);
L
Linus Torvalds 已提交
1304 1305 1306 1307 1308 1309

/* readahead.c */
#define VM_MAX_READAHEAD	128	/* kbytes */
#define VM_MIN_READAHEAD	16	/* kbytes (includes current page) */

int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
A
Andrew Morton 已提交
1310
			pgoff_t offset, unsigned long nr_to_read);
1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324

void page_cache_sync_readahead(struct address_space *mapping,
			       struct file_ra_state *ra,
			       struct file *filp,
			       pgoff_t offset,
			       unsigned long size);

void page_cache_async_readahead(struct address_space *mapping,
				struct file_ra_state *ra,
				struct file *filp,
				struct page *pg,
				pgoff_t offset,
				unsigned long size);

L
Linus Torvalds 已提交
1325
unsigned long max_sane_readahead(unsigned long nr);
1326 1327 1328
unsigned long ra_submit(struct file_ra_state *ra,
			struct address_space *mapping,
			struct file *filp);
L
Linus Torvalds 已提交
1329 1330

/* Do stack extension */
H
Hugh Dickins 已提交
1331
extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
1332
#ifdef CONFIG_IA64
H
Hugh Dickins 已提交
1333
extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
1334
#endif
1335 1336
extern int expand_stack_downwards(struct vm_area_struct *vma,
				  unsigned long address);
L
Linus Torvalds 已提交
1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358

/* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
					     struct vm_area_struct **pprev);

/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
   NULL if none.  Assume start_addr < end_addr. */
static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr)
{
	struct vm_area_struct * vma = find_vma(mm,start_addr);

	if (vma && end_addr <= vma->vm_start)
		vma = NULL;
	return vma;
}

static inline unsigned long vma_pages(struct vm_area_struct *vma)
{
	return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
}

1359
pgprot_t vm_get_page_prot(unsigned long vm_flags);
1360 1361 1362
struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
			unsigned long pfn, unsigned long size, pgprot_t);
1363
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
N
Nick Piggin 已提交
1364 1365
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn);
N
Nick Piggin 已提交
1366 1367
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn);
1368

1369
struct page *follow_page(struct vm_area_struct *, unsigned long address,
1370 1371 1372 1373
			unsigned int foll_flags);
#define FOLL_WRITE	0x01	/* check pte is writable */
#define FOLL_TOUCH	0x02	/* mark page accessed */
#define FOLL_GET	0x04	/* do get_page on page */
H
Hugh Dickins 已提交
1374
#define FOLL_DUMP	0x08	/* give error on hole if it would be zero */
H
Hugh Dickins 已提交
1375
#define FOLL_FORCE	0x10	/* get_user_pages read/write w/o permission */
L
Linus Torvalds 已提交
1376

1377
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
1378 1379 1380 1381
			void *data);
extern int apply_to_page_range(struct mm_struct *mm, unsigned long address,
			       unsigned long size, pte_fn_t fn, void *data);

L
Linus Torvalds 已提交
1382
#ifdef CONFIG_PROC_FS
1383
void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
L
Linus Torvalds 已提交
1384
#else
1385
static inline void vm_stat_account(struct mm_struct *mm,
L
Linus Torvalds 已提交
1386 1387 1388 1389 1390
			unsigned long flags, struct file *file, long pages)
{
}
#endif /* CONFIG_PROC_FS */

1391 1392 1393 1394 1395 1396 1397 1398 1399
#ifdef CONFIG_DEBUG_PAGEALLOC
extern int debug_pagealloc_enabled;

extern void kernel_map_pages(struct page *page, int numpages, int enable);

static inline void enable_debug_pagealloc(void)
{
	debug_pagealloc_enabled = 1;
}
1400 1401 1402
#ifdef CONFIG_HIBERNATION
extern bool kernel_page_present(struct page *page);
#endif /* CONFIG_HIBERNATION */
1403
#else
L
Linus Torvalds 已提交
1404
static inline void
N
Nick Piggin 已提交
1405
kernel_map_pages(struct page *page, int numpages, int enable) {}
1406 1407 1408
static inline void enable_debug_pagealloc(void)
{
}
1409 1410 1411
#ifdef CONFIG_HIBERNATION
static inline bool kernel_page_present(struct page *page) { return true; }
#endif /* CONFIG_HIBERNATION */
L
Linus Torvalds 已提交
1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422
#endif

extern struct vm_area_struct *get_gate_vma(struct task_struct *tsk);
#ifdef	__HAVE_ARCH_GATE_AREA
int in_gate_area_no_task(unsigned long addr);
int in_gate_area(struct task_struct *task, unsigned long addr);
#else
int in_gate_area_no_task(unsigned long addr);
#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);})
#endif	/* __HAVE_ARCH_GATE_AREA */

1423
int drop_caches_sysctl_handler(struct ctl_table *, int,
A
Andrew Morton 已提交
1424
					void __user *, size_t *, loff_t *);
1425
unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
A
Andrew Morton 已提交
1426 1427
			unsigned long lru_pages);

1428 1429 1430
#ifndef CONFIG_MMU
#define randomize_va_space 0
#else
1431
extern int randomize_va_space;
1432
#endif
1433

1434
const char * arch_vma_name(struct vm_area_struct *vma);
1435
void print_vma_addr(char *prefix, unsigned long rip);
1436

1437 1438 1439 1440 1441 1442
void sparse_mem_maps_populate_node(struct page **map_map,
				   unsigned long pnum_begin,
				   unsigned long pnum_end,
				   unsigned long map_count,
				   int nodeid);

1443
struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
1444 1445 1446 1447
pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
1448
void *vmemmap_alloc_block(unsigned long size, int node);
1449
void *vmemmap_alloc_block_buf(unsigned long size, int node);
1450
void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
1451 1452 1453
int vmemmap_populate_basepages(struct page *start_page,
						unsigned long pages, int node);
int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
1454
void vmemmap_populate_print_last(void);
1455

1456

1457 1458 1459
enum mf_flags {
	MF_COUNT_INCREASED = 1 << 0,
};
1460
extern void memory_failure(unsigned long pfn, int trapno);
1461
extern int __memory_failure(unsigned long pfn, int trapno, int flags);
W
Wu Fengguang 已提交
1462
extern int unpoison_memory(unsigned long pfn);
1463 1464
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
1465
extern void shake_page(struct page *p, int access);
1466
extern atomic_long_t mce_bad_pages;
1467
extern int soft_offline_page(struct page *page, int flags);
1468

1469 1470
extern void dump_page(struct page *page);

L
Linus Torvalds 已提交
1471 1472
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */