mm.h 32.3 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
#ifndef _LINUX_MM_H
#define _LINUX_MM_H

#include <linux/sched.h>
#include <linux/errno.h>

#ifdef __KERNEL__

#include <linux/config.h>
#include <linux/gfp.h>
#include <linux/list.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/prio_tree.h>
#include <linux/fs.h>

struct mempolicy;
struct anon_vma;

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

extern unsigned long num_physpages;
extern void * high_memory;
extern unsigned long vmalloc_earlyreserve;
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>
#include <asm/atomic.h>

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

/*
 * 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).
 */

/*
 * This struct defines a memory VMM memory area. There is one of these
 * per VM-area/task.  A VM area is any part of the process virtual memory
 * space that has a special rule for the page-fault handlers (ie a shared
 * library, the executable area etc).
 */
struct vm_area_struct {
	struct mm_struct * vm_mm;	/* The address space we belong to. */
	unsigned long vm_start;		/* Our start address within vm_mm. */
	unsigned long vm_end;		/* The first byte after our end address
					   within vm_mm. */

	/* linked list of VM areas per task, sorted by address */
	struct vm_area_struct *vm_next;

	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
	unsigned long vm_flags;		/* Flags, listed below. */

	struct rb_node vm_rb;

	/*
	 * For areas with an address space and backing store,
	 * linkage into the address_space->i_mmap prio tree, or
	 * linkage to the list of like vmas hanging off its node, or
	 * linkage of vma in the address_space->i_mmap_nonlinear list.
	 */
	union {
		struct {
			struct list_head list;
			void *parent;	/* aligns with prio_tree_node parent */
			struct vm_area_struct *head;
		} vm_set;

		struct raw_prio_tree_node prio_tree_node;
	} shared;

	/*
	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
	 * list, after a COW of one of the file pages.  A MAP_SHARED vma
	 * can only be in the i_mmap tree.  An anonymous MAP_PRIVATE, stack
	 * or brk vma (with NULL file) can only be in an anon_vma list.
	 */
	struct list_head anon_vma_node;	/* Serialized by anon_vma->lock */
	struct anon_vma *anon_vma;	/* Serialized by page_table_lock */

	/* Function pointers to deal with this struct. */
	struct vm_operations_struct * vm_ops;

	/* Information about our backing store: */
	unsigned long vm_pgoff;		/* Offset (within vm_file) in PAGE_SIZE
					   units, *not* PAGE_CACHE_SIZE */
	struct file * vm_file;		/* File we map to (can be NULL). */
	void * vm_private_data;		/* was vm_pte (shared mem) */
	unsigned long vm_truncate_count;/* truncate_count or restart_addr */

#ifndef CONFIG_MMU
	atomic_t vm_usage;		/* refcount (VMAs shared if !MMU) */
#endif
#ifdef CONFIG_NUMA
	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
#endif
};

/*
 * This struct defines the per-mm list of VMAs for uClinux. If CONFIG_MMU is
 * disabled, then there's a single shared list of VMAs maintained by the
 * system, and mm's subscribe to these individually
 */
struct vm_list_struct {
	struct vm_list_struct	*next;
	struct vm_area_struct	*vma;
};

#ifndef CONFIG_MMU
extern struct rb_root nommu_vma_tree;
extern struct rw_semaphore nommu_vma_sem;

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

/*
 * vm_flags..
 */
#define VM_READ		0x00000001	/* currently active flags */
#define VM_WRITE	0x00000002
#define VM_EXEC		0x00000004
#define VM_SHARED	0x00000008

139
/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
L
Linus Torvalds 已提交
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353
#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
#define VM_SHM		0x00000400	/* shared memory area, don't swap out */
#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() */
#define VM_RESERVED	0x00080000	/* Don't unmap it from swap_out */
#define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
#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) */

#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)

/*
 * mapping from the currently active vm_flags protection bits (the
 * low four bits) to a page protection mask..
 */
extern pgprot_t protection_map[16];


/*
 * 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);
	struct page * (*nopage)(struct vm_area_struct * area, unsigned long address, int *type);
	int (*populate)(struct vm_area_struct * area, unsigned long address, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock);
#ifdef CONFIG_NUMA
	int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
					unsigned long addr);
#endif
};

struct mmu_gather;
struct inode;

#ifdef ARCH_HAS_ATOMIC_UNSIGNED
typedef unsigned page_flags_t;
#else
typedef unsigned long page_flags_t;
#endif

/*
 * Each physical page in the system has a struct page associated with
 * it to keep track of whatever it is we are using the page for at the
 * moment. Note that we have no way to track which tasks are using
 * a page.
 */
struct page {
	page_flags_t flags;		/* Atomic flags, some possibly
					 * updated asynchronously */
	atomic_t _count;		/* Usage count, see below. */
	atomic_t _mapcount;		/* Count of ptes mapped in mms,
					 * to show when page is mapped
					 * & limit reverse map searches.
					 */
	unsigned long private;		/* Mapping-private opaque data:
					 * usually used for buffer_heads
					 * if PagePrivate set; used for
					 * swp_entry_t if PageSwapCache
					 * When page is free, this indicates
					 * order in the buddy system.
					 */
	struct address_space *mapping;	/* If low bit clear, points to
					 * inode address_space, or NULL.
					 * If page mapped as anonymous
					 * memory, low bit is set, and
					 * it points to anon_vma object:
					 * see PAGE_MAPPING_ANON below.
					 */
	pgoff_t index;			/* Our offset within mapping. */
	struct list_head lru;		/* Pageout list, eg. active_list
					 * protected by zone->lru_lock !
					 */
	/*
	 * On machines where all RAM is mapped into kernel address space,
	 * we can simply calculate the virtual address. On machines with
	 * highmem some memory is mapped into kernel virtual memory
	 * dynamically, so we need a place to store that address.
	 * Note that this field could be 16 bits on x86 ... ;)
	 *
	 * Architectures with slow multiplication can define
	 * WANT_PAGE_VIRTUAL in asm/page.h
	 */
#if defined(WANT_PAGE_VIRTUAL)
	void *virtual;			/* Kernel virtual address (NULL if
					   not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */
};

/*
 * 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.
 *
 * Since 2.6.6 (approx), a free page has ->_count = -1.  This is so that we
 * can use atomic_add_negative(-1, page->_count) to detect when the page
 * becomes free and so that we can also use atomic_inc_and_test to atomically
 * detect when we just tried to grab a ref on a page which some other CPU has
 * already deemed to be freeable.
 *
 * NO code should make assumptions about this internal detail!  Use the provided
 * macros which retain the old rules: page_count(page) == 0 is a free page.
 */

/*
 * Drop a ref, return true if the logical refcount fell to zero (the page has
 * no users)
 */
#define put_page_testzero(p)				\
	({						\
		BUG_ON(page_count(p) == 0);		\
		atomic_add_negative(-1, &(p)->_count);	\
	})

/*
 * Grab a ref, return true if the page previously had a logical refcount of
 * zero.  ie: returns true if we just grabbed an already-deemed-to-be-free page
 */
#define get_page_testone(p)	atomic_inc_and_test(&(p)->_count)

#define set_page_count(p,v) 	atomic_set(&(p)->_count, v - 1)
#define __put_page(p)		atomic_dec(&(p)->_count)

extern void FASTCALL(__page_cache_release(struct page *));

#ifdef CONFIG_HUGETLB_PAGE

static inline int page_count(struct page *p)
{
	if (PageCompound(p))
		p = (struct page *)p->private;
	return atomic_read(&(p)->_count) + 1;
}

static inline void get_page(struct page *page)
{
	if (unlikely(PageCompound(page)))
		page = (struct page *)page->private;
	atomic_inc(&page->_count);
}

void put_page(struct page *page);

#else		/* CONFIG_HUGETLB_PAGE */

#define page_count(p)		(atomic_read(&(p)->_count) + 1)

static inline void get_page(struct page *page)
{
	atomic_inc(&page->_count);
}

static inline void put_page(struct page *page)
{
	if (!PageReserved(page) && put_page_testzero(page))
		__page_cache_release(page);
}

#endif		/* CONFIG_HUGETLB_PAGE */

/*
 * 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.
354 355
 *   page_count() == 0 means the page is free. page->lru is then used for
 *   freelist management in the buddy allocator.
L
Linus Torvalds 已提交
356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
 *   page_count() == 1 means the page is used for exactly one purpose
 *   (e.g. a private data page of one process).
 *
 * A page may be used for kmalloc() or anyone else who does a
 * __get_free_page(). In this case the page_count() is at least 1, and
 * all other fields are unused but should be 0 or NULL. The
 * management of this page is the responsibility of the one who uses
 * it.
 *
 * The other pages (we may call them "process pages") are completely
 * managed by the Linux memory manager: I/O, buffers, swapping etc.
 * The following discussion applies only to them.
 *
 * 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.
 *
 * A 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.
 *
 * For pages belonging to inodes, the page_count() is the number of
 * attaches, plus 1 if `private' contains something, plus one for
 * the page cache itself.
 *
381 382
 * Instead of keeping dirty/clean pages in per address-space lists, we instead
 * now tag pages as dirty/under writeback in the radix tree.
L
Linus Torvalds 已提交
383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
 *
 * There is also a per-mapping radix tree mapping index to the page
 * in memory if present. The tree is rooted at mapping->root.  
 *
 * All process pages can do I/O:
 * - inode pages may need to be read from disk,
 * - inode pages which have been modified and are MAP_SHARED may need
 *   to be written to disk,
 * - private pages which have been modified may need to be swapped out
 *   to swap space and (later) to be read back into memory.
 */

/*
 * The zone field is never updated after free_area_init_core()
 * sets it, so none of the operations on it need to be atomic.
 */
399

A
Andy Whitcroft 已提交
400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442

/*
 * 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.
 *
 *        No sparsemem: |       NODE     | ZONE | ... | FLAGS |
 * with space for node: | SECTION | NODE | ZONE | ... | FLAGS |
 *   no space for node: | SECTION |     ZONE    | ... | FLAGS |
 */
#ifdef CONFIG_SPARSEMEM
#define SECTIONS_WIDTH		SECTIONS_SHIFT
#else
#define SECTIONS_WIDTH		0
#endif

#define ZONES_WIDTH		ZONES_SHIFT

#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= FLAGS_RESERVED
#define NODES_WIDTH		NODES_SHIFT
#else
#define NODES_WIDTH		0
#endif

/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
#define SECTIONS_PGOFF		((sizeof(page_flags_t)*8) - SECTIONS_WIDTH)
#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.
 */
#define FLAGS_HAS_NODE		(NODES_WIDTH > 0 || NODES_SHIFT == 0)

#ifndef PFN_SECTION_SHIFT
#define PFN_SECTION_SHIFT 0
#endif
443 444 445 446 447 448

/*
 * 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
449 450 451
#define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
#define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
#define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
452

A
Andy Whitcroft 已提交
453 454
/* NODE:ZONE or SECTION:ZONE is used to lookup the zone from a page. */
#if FLAGS_HAS_NODE
455
#define ZONETABLE_SHIFT		(NODES_SHIFT + ZONES_SHIFT)
A
Andy Whitcroft 已提交
456 457 458
#else
#define ZONETABLE_SHIFT		(SECTIONS_SHIFT + ZONES_SHIFT)
#endif
459 460
#define ZONETABLE_PGSHIFT	ZONES_PGSHIFT

A
Andy Whitcroft 已提交
461 462
#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > FLAGS_RESERVED
463 464
#endif

A
Andy Whitcroft 已提交
465 466 467
#define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK		((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
468 469
#define ZONETABLE_MASK		((1UL << ZONETABLE_SHIFT) - 1)

L
Linus Torvalds 已提交
470 471
static inline unsigned long page_zonenum(struct page *page)
{
472
	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
L
Linus Torvalds 已提交
473 474 475 476 477 478 479
}

struct zone;
extern struct zone *zone_table[];

static inline struct zone *page_zone(struct page *page)
{
480 481 482 483
	return zone_table[(page->flags >> ZONETABLE_PGSHIFT) &
			ZONETABLE_MASK];
}

A
Andy Whitcroft 已提交
484 485 486 487 488 489 490 491 492 493 494 495
static inline unsigned long page_to_nid(struct page *page)
{
	if (FLAGS_HAS_NODE)
		return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
	else
		return page_zone(page)->zone_pgdat->node_id;
}
static inline unsigned long page_to_section(struct page *page)
{
	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}

496 497 498 499 500 501 502 503 504
static inline void set_page_zone(struct page *page, unsigned long zone)
{
	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
	page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
}
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
505
}
A
Andy Whitcroft 已提交
506 507 508 509 510
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
511

512
static inline void set_page_links(struct page *page, unsigned long zone,
A
Andy Whitcroft 已提交
513
	unsigned long node, unsigned long pfn)
L
Linus Torvalds 已提交
514
{
515 516
	set_page_zone(page, zone);
	set_page_node(page, node);
A
Andy Whitcroft 已提交
517
	set_page_section(page, pfn_to_section_nr(pfn));
L
Linus Torvalds 已提交
518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627
}

#ifndef CONFIG_DISCONTIGMEM
/* The array of struct pages - for discontigmem use pgdat->lmem_map */
extern struct page *mem_map;
#endif

static inline void *lowmem_page_address(struct page *page)
{
	return __va(page_to_pfn(page) << PAGE_SHIFT);
}

#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;
 * with the PAGE_MAPPING_ANON bit set to distinguish it.
 *
 * 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

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

	if (unlikely(PageSwapCache(page)))
		mapping = &swapper_space;
	else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
		mapping = NULL;
	return mapping;
}

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)))
		return page->private;
	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;
}

/*
 * Error return values for the *_nopage functions
 */
#define NOPAGE_SIGBUS	(NULL)
#define NOPAGE_OOM	((struct page *) (-1))

/*
 * 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
628 629 630 631 632 633 634 635 636 637
#define VM_FAULT_OOM	0x00
#define VM_FAULT_SIGBUS	0x01
#define VM_FAULT_MINOR	0x02
#define VM_FAULT_MAJOR	0x03

/* 
 * Special case for get_user_pages.
 * Must be in a distinct bit from the above VM_FAULT_ flags.
 */
#define VM_FAULT_WRITE	0x10
L
Linus Torvalds 已提交
638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682

#define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)

extern void show_free_areas(void);

#ifdef CONFIG_SHMEM
struct page *shmem_nopage(struct vm_area_struct *vma,
			unsigned long address, int *type);
int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new);
struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
					unsigned long addr);
int shmem_lock(struct file *file, int lock, struct user_struct *user);
#else
#define shmem_nopage filemap_nopage
#define shmem_lock(a, b, c) 	({0;})	/* always in memory, no need to lock */
#define shmem_set_policy(a, b)	(0)
#define shmem_get_policy(a, b)	(NULL)
#endif
struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags);

int shmem_zero_setup(struct vm_area_struct *);

static inline int can_do_mlock(void)
{
	if (capable(CAP_IPC_LOCK))
		return 1;
	if (current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur != 0)
		return 1;
	return 0;
}
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 */
};

683
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
L
Linus Torvalds 已提交
684
		unsigned long size, struct zap_details *);
685
unsigned long unmap_vmas(struct mmu_gather **tlb, struct mm_struct *mm,
L
Linus Torvalds 已提交
686 687 688
		struct vm_area_struct *start_vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *);
689 690 691
void free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
		unsigned long end, unsigned long floor, unsigned long ceiling);
void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,
692
		unsigned long floor, unsigned long ceiling);
L
Linus Torvalds 已提交
693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712
int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
			struct vm_area_struct *vma);
int zeromap_page_range(struct vm_area_struct *vma, unsigned long from,
			unsigned long size, pgprot_t prot);
void unmap_mapping_range(struct address_space *mapping,
		loff_t const holebegin, loff_t const holelen, int even_cows);

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);
}

extern int vmtruncate(struct inode * inode, loff_t offset);
extern pud_t *FASTCALL(__pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address));
extern pmd_t *FASTCALL(__pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address));
extern pte_t *FASTCALL(pte_alloc_kernel(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
extern pte_t *FASTCALL(pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address));
extern int install_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, struct page *page, pgprot_t prot);
extern int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long pgoff, pgprot_t prot);
N
Nick Piggin 已提交
713 714 715 716 717 718 719
extern int __handle_mm_fault(struct mm_struct *mm,struct vm_area_struct *vma, unsigned long address, int write_access);

static inline int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, int write_access)
{
	return __handle_mm_fault(mm, vma, address, write_access) & (~VM_FAULT_WRITE);
}

L
Linus Torvalds 已提交
720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744
extern int make_pages_present(unsigned long addr, unsigned long end);
extern int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write);
void install_arg_page(struct vm_area_struct *, struct page *, unsigned long);

int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start,
		int len, int write, int force, struct page **pages, struct vm_area_struct **vmas);

int __set_page_dirty_buffers(struct page *page);
int __set_page_dirty_nobuffers(struct page *page);
int redirty_page_for_writepage(struct writeback_control *wbc,
				struct page *page);
int FASTCALL(set_page_dirty(struct page *page));
int set_page_dirty_lock(struct page *page);
int clear_page_dirty_for_io(struct page *page);

extern unsigned long do_mremap(unsigned long addr,
			       unsigned long old_len, unsigned long new_len,
			       unsigned long flags, unsigned long new_addr);

/*
 * Prototype to add a shrinker callback for ageable caches.
 * 
 * These functions are passed a count `nr_to_scan' and a gfpmask.  They should
 * scan `nr_to_scan' objects, attempting to free them.
 *
745
 * The callback must return the number of objects which remain in the cache.
L
Linus Torvalds 已提交
746
 *
747
 * The callback will be passed nr_to_scan == 0 when the VM is querying the
L
Linus Torvalds 已提交
748 749
 * cache size, so a fastpath for that case is appropriate.
 */
A
Al Viro 已提交
750
typedef int (*shrinker_t)(int nr_to_scan, gfp_t gfp_mask);
L
Linus Torvalds 已提交
751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798

/*
 * Add an aging callback.  The int is the number of 'seeks' it takes
 * to recreate one of the objects that these functions age.
 */

#define DEFAULT_SEEKS 2
struct shrinker;
extern struct shrinker *set_shrinker(int, shrinker_t);
extern void remove_shrinker(struct shrinker *shrinker);

/*
 * On a two-level or three-level page table, this ends up being trivial. Thus
 * the inlining and the symmetry break with pte_alloc_map() that does all
 * of this out-of-line.
 */
/*
 * The following ifdef needed to get the 4level-fixup.h header to work.
 * Remove it when 4level-fixup.h has been removed.
 */
#ifdef CONFIG_MMU
#ifndef __ARCH_HAS_4LEVEL_HACK 
static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
	if (pgd_none(*pgd))
		return __pud_alloc(mm, pgd, address);
	return pud_offset(pgd, address);
}

static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
	if (pud_none(*pud))
		return __pmd_alloc(mm, pud, address);
	return pmd_offset(pud, address);
}
#endif
#endif /* CONFIG_MMU */

extern void free_area_init(unsigned long * zones_size);
extern void free_area_init_node(int nid, pg_data_t *pgdat,
	unsigned long * zones_size, unsigned long zone_start_pfn, 
	unsigned long *zholes_size);
extern void memmap_init_zone(unsigned long, int, unsigned long, unsigned long);
extern void mem_init(void);
extern void show_mem(void);
extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid);

799 800 801 802 803 804
#ifdef CONFIG_NUMA
extern void setup_per_cpu_pageset(void);
#else
static inline void setup_per_cpu_pageset(void) {}
#endif

L
Linus Torvalds 已提交
805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839
/* 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 */
extern int __vm_enough_memory(long pages, int cap_sys_admin);
extern void vma_adjust(struct vm_area_struct *vma, unsigned long start,
	unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert);
extern struct vm_area_struct *vma_merge(struct mm_struct *,
	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 *);
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 *);
A
akpm@osdl.org 已提交
840
extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
L
Linus Torvalds 已提交
841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930

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);

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);

/* generic vm_area_ops exported for stackable file systems */
extern struct page *filemap_nopage(struct vm_area_struct *, unsigned long, int *);
extern int filemap_populate(struct vm_area_struct *, unsigned long,
		unsigned long, pgprot_t, unsigned long, int);

/* mm/page-writeback.c */
int write_one_page(struct page *page, int wait);

/* readahead.c */
#define VM_MAX_READAHEAD	128	/* kbytes */
#define VM_MIN_READAHEAD	16	/* kbytes (includes current page) */
#define VM_MAX_CACHE_HIT    	256	/* max pages in a row in cache before
					 * turning readahead off */

int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
			unsigned long offset, unsigned long nr_to_read);
int force_page_cache_readahead(struct address_space *mapping, struct file *filp,
			unsigned long offset, unsigned long nr_to_read);
unsigned long  page_cache_readahead(struct address_space *mapping,
			  struct file_ra_state *ra,
			  struct file *filp,
			  unsigned long offset,
			  unsigned long size);
void handle_ra_miss(struct address_space *mapping, 
		    struct file_ra_state *ra, pgoff_t offset);
unsigned long max_sane_readahead(unsigned long nr);

/* Do stack extension */
extern int expand_stack(struct vm_area_struct * vma, unsigned long address);

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

extern struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr);

extern struct page * vmalloc_to_page(void *addr);
extern unsigned long vmalloc_to_pfn(void *addr);
extern struct page * follow_page(struct mm_struct *mm, unsigned long address,
		int write);
extern int check_user_page_readable(struct mm_struct *mm, unsigned long address);
int remap_pfn_range(struct vm_area_struct *, unsigned long,
		unsigned long, unsigned long, pgprot_t);

#ifdef CONFIG_PROC_FS
931
void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
L
Linus Torvalds 已提交
932
#else
933
static inline void vm_stat_account(struct mm_struct *mm,
L
Linus Torvalds 已提交
934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957
			unsigned long flags, struct file *file, long pages)
{
}
#endif /* CONFIG_PROC_FS */

/* update per process rss and vm hiwater data */
extern void update_mem_hiwater(struct task_struct *tsk);

#ifndef CONFIG_DEBUG_PAGEALLOC
static inline void
kernel_map_pages(struct page *page, int numpages, int enable)
{
}
#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 */

958 959 960
/* /proc/<pid>/oom_adj set to -17 protects from the oom-killer */
#define OOM_DISABLE -17

L
Linus Torvalds 已提交
961 962
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */