mm.h 54.5 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>
A
Andrea Arcangeli 已提交
17
#include <linux/bit_spinlock.h>
L
Linus Torvalds 已提交
18 19 20

struct mempolicy;
struct anon_vma;
A
Alexey Dobriyan 已提交
21
struct file_ra_state;
A
Alexey Dobriyan 已提交
22
struct user_struct;
A
Alexey Dobriyan 已提交
23
struct writeback_control;
L
Linus Torvalds 已提交
24 25 26 27 28 29

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

extern unsigned long num_physpages;
30
extern unsigned long totalram_pages;
L
Linus Torvalds 已提交
31 32 33 34 35 36 37 38 39 40 41 42 43 44 45
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))

46 47 48
/* to align the pointer to the (next) page boundary */
#define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)

L
Linus Torvalds 已提交
49 50 51 52 53 54 55 56 57
/*
 * 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).
 */

58 59
extern struct kmem_cache *vm_area_cachep;

L
Linus Torvalds 已提交
60
#ifndef CONFIG_MMU
61 62
extern struct rb_root nommu_region_tree;
extern struct rw_semaphore nommu_region_sem;
L
Linus Torvalds 已提交
63 64 65 66 67

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

/*
H
Hugh Dickins 已提交
68
 * vm_flags in vm_area_struct, see mm_types.h.
L
Linus Torvalds 已提交
69 70 71 72 73 74
 */
#define VM_READ		0x00000001	/* currently active flags */
#define VM_WRITE	0x00000002
#define VM_EXEC		0x00000004
#define VM_SHARED	0x00000008

75
/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
L
Linus Torvalds 已提交
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 */
82
#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64)
L
Linus Torvalds 已提交
83
#define VM_GROWSUP	0x00000200
84 85
#else
#define VM_GROWSUP	0x00000000
A
Andrea Arcangeli 已提交
86
#define VM_NOHUGEPAGE	0x00000200	/* MADV_NOHUGEPAGE marked this vma */
87
#endif
88
#define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
L
Linus Torvalds 已提交
89 90 91 92 93 94 95 96 97 98 99 100
#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
101
#define VM_RESERVED	0x00080000	/* Count as reserved_vm like IO */
L
Linus Torvalds 已提交
102
#define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
103
#define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
L
Linus Torvalds 已提交
104 105
#define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
#define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
J
Johannes Weiner 已提交
106
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
L
Linus Torvalds 已提交
107
#define VM_MAPPED_COPY	0x01000000	/* T if mapped copy of data (nommu mmap) */
J
Johannes Weiner 已提交
108 109 110
#else
#define VM_HUGEPAGE	0x01000000	/* MADV_HUGEPAGE marked this vma */
#endif
111
#define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */
R
Roland McGrath 已提交
112
#define VM_ALWAYSDUMP	0x04000000	/* Always include in core dumps */
113

N
Nick Piggin 已提交
114
#define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */
J
Jared Hulbert 已提交
115
#define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
116
#define VM_SAO		0x20000000	/* Strong Access Ordering (powerpc) */
117
#define VM_PFN_AT_MMAP	0x40000000	/* PFNMAP vma that is fully mapped at mmap time */
H
Hugh Dickins 已提交
118
#define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */
L
Linus Torvalds 已提交
119

120 121 122
/* 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
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138
#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
139 140 141 142 143
/*
 * 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
144 145 146 147 148 149
/*
 * 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
150 151
#define FAULT_FLAG_WRITE	0x01	/* Fault was a write access */
#define FAULT_FLAG_NONLINEAR	0x02	/* Fault was via a nonlinear mapping */
152
#define FAULT_FLAG_MKWRITE	0x04	/* Fault was mkwrite of existing pte */
153
#define FAULT_FLAG_ALLOW_RETRY	0x08	/* Retry fault if blocking */
N
Nick Piggin 已提交
154

155 156 157 158 159 160 161 162
/*
 * 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.
 */
163 164
static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
{
165
	return (vma->vm_flags & VM_PFN_AT_MMAP);
166 167 168 169 170 171
}

static inline int is_pfn_mapping(struct vm_area_struct *vma)
{
	return (vma->vm_flags & VM_PFNMAP);
}
N
Nick Piggin 已提交
172

173
/*
N
Nick Piggin 已提交
174
 * vm_fault is filled by the the pagefault handler and passed to the vma's
N
Nick Piggin 已提交
175 176
 * ->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.
177
 *
N
Nick Piggin 已提交
178 179 180
 * 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.
181
 */
N
Nick Piggin 已提交
182 183 184 185 186 187
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
188
					 * page here, unless VM_FAULT_NOPAGE
N
Nick Piggin 已提交
189
					 * is set (which is also implied by
N
Nick Piggin 已提交
190
					 * VM_FAULT_ERROR).
N
Nick Piggin 已提交
191
					 */
192
};
L
Linus Torvalds 已提交
193 194 195 196 197 198 199 200 201

/*
 * 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
202
	int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf);
203 204 205

	/* notification that a previously read-only page is about to become
	 * writable, if an error is returned it will cause a SIGBUS */
206
	int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf);
207 208 209 210 211 212

	/* 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
213
#ifdef CONFIG_NUMA
214 215 216 217 218 219 220
	/*
	 * 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
221
	int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new);
222 223 224 225 226 227 228 229 230 231 232

	/*
	 * 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
233 234
	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
					unsigned long addr);
235 236
	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
		const nodemask_t *to, unsigned long flags);
L
Linus Torvalds 已提交
237 238 239 240 241 242
#endif
};

struct mmu_gather;
struct inode;

A
Andrew Morton 已提交
243 244
#define page_private(page)		((page)->private)
#define set_page_private(page, v)	((page)->private = (v))
H
Hugh Dickins 已提交
245

L
Linus Torvalds 已提交
246 247 248 249 250
/*
 * FIXME: take this include out, include page-flags.h in
 * files which need it (119 of them)
 */
#include <linux/page-flags.h>
251
#include <linux/huge_mm.h>
L
Linus Torvalds 已提交
252 253 254 255 256 257 258 259 260 261 262 263 264 265 266

/*
 * 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
267
 * Drop a ref, return true if the refcount fell to zero (the page has no users)
L
Linus Torvalds 已提交
268
 */
269 270
static inline int put_page_testzero(struct page *page)
{
N
Nick Piggin 已提交
271
	VM_BUG_ON(atomic_read(&page->_count) == 0);
272
	return atomic_dec_and_test(&page->_count);
273
}
L
Linus Torvalds 已提交
274 275

/*
276 277
 * 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
278
 */
279 280
static inline int get_page_unless_zero(struct page *page)
{
281
	return atomic_inc_not_zero(&page->_count);
282
}
L
Linus Torvalds 已提交
283

284 285
extern int page_is_ram(unsigned long pfn);

286
/* Support for virtually mapped pages */
287 288
struct page *vmalloc_to_page(const void *addr);
unsigned long vmalloc_to_pfn(const void *addr);
289

290 291 292 293 294 295
/*
 * 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.
 */
296 297
static inline int is_vmalloc_addr(const void *x)
{
298
#ifdef CONFIG_MMU
299 300 301
	unsigned long addr = (unsigned long)x;

	return addr >= VMALLOC_START && addr < VMALLOC_END;
302 303
#else
	return 0;
304
#endif
305
}
306 307 308
#ifdef CONFIG_MMU
extern int is_vmalloc_or_module_addr(const void *x);
#else
309
static inline int is_vmalloc_or_module_addr(const void *x)
310 311 312 313
{
	return 0;
}
#endif
314

A
Andrea Arcangeli 已提交
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
static inline void compound_lock(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	bit_spin_lock(PG_compound_lock, &page->flags);
#endif
}

static inline void compound_unlock(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	bit_spin_unlock(PG_compound_lock, &page->flags);
#endif
}

static inline unsigned long compound_lock_irqsave(struct page *page)
{
	unsigned long uninitialized_var(flags);
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	local_irq_save(flags);
	compound_lock(page);
#endif
	return flags;
}

static inline void compound_unlock_irqrestore(struct page *page,
					      unsigned long flags)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
	compound_unlock(page);
	local_irq_restore(flags);
#endif
}

348 349
static inline struct page *compound_head(struct page *page)
{
350
	if (unlikely(PageTail(page)))
351 352 353 354
		return page->first_page;
	return page;
}

H
Hugh Dickins 已提交
355
static inline int page_count(struct page *page)
L
Linus Torvalds 已提交
356
{
357
	return atomic_read(&compound_head(page)->_count);
L
Linus Torvalds 已提交
358 359 360 361
}

static inline void get_page(struct page *page)
{
362 363 364 365 366 367 368 369 370
	/*
	 * Getting a normal page or the head of a compound page
	 * requires to already have an elevated page->_count. Only if
	 * we're getting a tail page, the elevated page->_count is
	 * required only in the head page, so for tail pages the
	 * bugcheck only verifies that the page->_count isn't
	 * negative.
	 */
	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
L
Linus Torvalds 已提交
371
	atomic_inc(&page->_count);
372 373 374 375 376 377 378 379 380 381 382 383 384
	/*
	 * Getting a tail page will elevate both the head and tail
	 * page->_count(s).
	 */
	if (unlikely(PageTail(page))) {
		/*
		 * This is safe only because
		 * __split_huge_page_refcount can't run under
		 * get_page().
		 */
		VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
		atomic_inc(&page->first_page->_count);
	}
L
Linus Torvalds 已提交
385 386
}

387 388 389 390 391 392
static inline struct page *virt_to_head_page(const void *x)
{
	struct page *page = virt_to_page(x);
	return compound_head(page);
}

393 394 395 396 397 398 399 400 401
/*
 * 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);
}

A
Andrea Arcangeli 已提交
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422
/*
 * PageBuddy() indicate that the page is free and in the buddy system
 * (see mm/page_alloc.c).
 */
static inline int PageBuddy(struct page *page)
{
	return atomic_read(&page->_mapcount) == -2;
}

static inline void __SetPageBuddy(struct page *page)
{
	VM_BUG_ON(atomic_read(&page->_mapcount) != -1);
	atomic_set(&page->_mapcount, -2);
}

static inline void __ClearPageBuddy(struct page *page)
{
	VM_BUG_ON(!PageBuddy(page));
	atomic_set(&page->_mapcount, -1);
}

L
Linus Torvalds 已提交
423
void put_page(struct page *page);
424
void put_pages_list(struct list_head *pages);
L
Linus Torvalds 已提交
425

N
Nick Piggin 已提交
426
void split_page(struct page *page, unsigned int order);
427
int split_free_page(struct page *page);
N
Nick Piggin 已提交
428

429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446
/*
 * 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;
}

447 448
static inline int compound_order(struct page *page)
{
449
	if (!PageHead(page))
450 451 452 453
		return 0;
	return (unsigned long)page[1].lru.prev;
}

A
Andrea Arcangeli 已提交
454 455 456 457 458 459 460 461 462 463 464 465 466 467
static inline int compound_trans_order(struct page *page)
{
	int order;
	unsigned long flags;

	if (!PageHead(page))
		return 0;

	flags = compound_lock_irqsave(page);
	order = compound_order(page);
	compound_unlock_irqrestore(page, flags);
	return order;
}

468 469 470 471 472
static inline void set_compound_order(struct page *page, unsigned long order)
{
	page[1].lru.prev = (void *)order;
}

A
Andrea Arcangeli 已提交
473 474 475 476 477 478 479 480 481 482 483 484 485
/*
 * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
 * servicing faults for write access.  In the normal case, do always want
 * pte_mkwrite.  But get_user_pages can cause write faults for mappings
 * that do not have writing enabled, when used by access_process_vm.
 */
static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
{
	if (likely(vma->vm_flags & VM_WRITE))
		pte = pte_mkwrite(pte);
	return pte;
}

L
Linus Torvalds 已提交
486 487 488 489 490 491 492
/*
 * 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.
493 494
 *   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
495
 *   page_count() > 0  means the page has been allocated.
L
Linus Torvalds 已提交
496
 *
N
Nick Piggin 已提交
497 498 499 500 501
 * 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
502
 *
N
Nick Piggin 已提交
503 504 505 506 507 508 509 510 511
 * 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
512 513 514
 * managed by the Linux memory manager: I/O, buffers, swapping etc.
 * The following discussion applies only to them.
 *
N
Nick Piggin 已提交
515 516 517 518
 * 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
519
 *
N
Nick Piggin 已提交
520 521 522
 * 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
523
 *
N
Nick Piggin 已提交
524 525 526
 * 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
527
 *
N
Nick Piggin 已提交
528 529 530
 * 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
531
 *
N
Nick Piggin 已提交
532 533 534 535
 * 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
536
 *
N
Nick Piggin 已提交
537
 * All pagecache pages may be subject to I/O:
L
Linus Torvalds 已提交
538 539
 * - 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
540 541 542 543
 *   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
544 545 546 547 548 549
 */

/*
 * The zone field is never updated after free_area_init_core()
 * sets it, so none of the operations on it need to be atomic.
 */
550

A
Andy Whitcroft 已提交
551 552 553 554 555 556 557 558 559 560 561

/*
 * 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.
 *
562 563 564
 * 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
565
 */
566
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
A
Andy Whitcroft 已提交
567 568 569 570 571 572 573
#define SECTIONS_WIDTH		SECTIONS_SHIFT
#else
#define SECTIONS_WIDTH		0
#endif

#define ZONES_WIDTH		ZONES_SHIFT

574
#if SECTIONS_WIDTH+ZONES_WIDTH+NODES_SHIFT <= BITS_PER_LONG - NR_PAGEFLAGS
A
Andy Whitcroft 已提交
575 576
#define NODES_WIDTH		NODES_SHIFT
#else
577 578 579
#ifdef CONFIG_SPARSEMEM_VMEMMAP
#error "Vmemmap: No space for nodes field in page flags"
#endif
A
Andy Whitcroft 已提交
580 581 582 583
#define NODES_WIDTH		0
#endif

/* Page flags: | [SECTION] | [NODE] | ZONE | ... | FLAGS | */
584
#define SECTIONS_PGOFF		((sizeof(unsigned long)*8) - SECTIONS_WIDTH)
A
Andy Whitcroft 已提交
585 586 587 588 589 590 591
#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.
 */
592 593 594
#if !(NODES_WIDTH > 0 || NODES_SHIFT == 0)
#define NODE_NOT_IN_PAGE_FLAGS
#endif
A
Andy Whitcroft 已提交
595 596 597 598

#ifndef PFN_SECTION_SHIFT
#define PFN_SECTION_SHIFT 0
#endif
599 600 601 602 603 604

/*
 * 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
605 606 607
#define SECTIONS_PGSHIFT	(SECTIONS_PGOFF * (SECTIONS_WIDTH != 0))
#define NODES_PGSHIFT		(NODES_PGOFF * (NODES_WIDTH != 0))
#define ZONES_PGSHIFT		(ZONES_PGOFF * (ZONES_WIDTH != 0))
608

609 610
/* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */
#ifdef NODE_NOT_IN_PAGE_FLAGS
611
#define ZONEID_SHIFT		(SECTIONS_SHIFT + ZONES_SHIFT)
612 613
#define ZONEID_PGOFF		((SECTIONS_PGOFF < ZONES_PGOFF)? \
						SECTIONS_PGOFF : ZONES_PGOFF)
A
Andy Whitcroft 已提交
614
#else
615
#define ZONEID_SHIFT		(NODES_SHIFT + ZONES_SHIFT)
616 617
#define ZONEID_PGOFF		((NODES_PGOFF < ZONES_PGOFF)? \
						NODES_PGOFF : ZONES_PGOFF)
618 619
#endif

620
#define ZONEID_PGSHIFT		(ZONEID_PGOFF * (ZONEID_SHIFT != 0))
621

622 623
#if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
#error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS
624 625
#endif

A
Andy Whitcroft 已提交
626 627 628
#define ZONES_MASK		((1UL << ZONES_WIDTH) - 1)
#define NODES_MASK		((1UL << NODES_WIDTH) - 1)
#define SECTIONS_MASK		((1UL << SECTIONS_WIDTH) - 1)
629
#define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
630

631
static inline enum zone_type page_zonenum(struct page *page)
L
Linus Torvalds 已提交
632
{
633
	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
L
Linus Torvalds 已提交
634 635
}

636 637 638 639 640 641 642 643
/*
 * 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.
 */
644 645
static inline int page_zone_id(struct page *page)
{
646
	return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK;
647 648
}

649
static inline int zone_to_nid(struct zone *zone)
650
{
651 652 653 654 655
#ifdef CONFIG_NUMA
	return zone->node;
#else
	return 0;
#endif
656 657
}

658
#ifdef NODE_NOT_IN_PAGE_FLAGS
659
extern int page_to_nid(struct page *page);
660
#else
661
static inline int page_to_nid(struct page *page)
A
Andy Whitcroft 已提交
662
{
663
	return (page->flags >> NODES_PGSHIFT) & NODES_MASK;
A
Andy Whitcroft 已提交
664
}
665 666 667 668 669 670 671
#endif

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

672
#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
A
Andy Whitcroft 已提交
673 674 675 676
static inline unsigned long page_to_section(struct page *page)
{
	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
}
677
#endif
A
Andy Whitcroft 已提交
678

679
static inline void set_page_zone(struct page *page, enum zone_type zone)
680 681 682 683
{
	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
	page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
}
684

685 686 687 688
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
689
}
690

A
Andy Whitcroft 已提交
691 692 693 694 695
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
696

697
static inline void set_page_links(struct page *page, enum zone_type zone,
A
Andy Whitcroft 已提交
698
	unsigned long node, unsigned long pfn)
L
Linus Torvalds 已提交
699
{
700 701
	set_page_zone(page, zone);
	set_page_node(page, node);
A
Andy Whitcroft 已提交
702
	set_page_section(page, pfn_to_section_nr(pfn));
L
Linus Torvalds 已提交
703 704
}

705 706 707 708 709
/*
 * Some inline functions in vmstat.h depend on page_zone()
 */
#include <linux/vmstat.h>

710
static __always_inline void *lowmem_page_address(struct page *page)
L
Linus Torvalds 已提交
711
{
712
	return __va(PFN_PHYS(page_to_pfn(page)));
L
Linus Torvalds 已提交
713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
}

#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
743 744 745 746 747 748 749 750
 * 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
751 752 753 754 755 756
 *
 * 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
757 758
#define PAGE_MAPPING_KSM	2
#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_KSM)
L
Linus Torvalds 已提交
759 760 761 762 763 764

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

765
	VM_BUG_ON(PageSlab(page));
L
Linus Torvalds 已提交
766 767
	if (unlikely(PageSwapCache(page)))
		mapping = &swapper_space;
768
	else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
L
Linus Torvalds 已提交
769 770 771 772
		mapping = NULL;
	return mapping;
}

H
Hugh Dickins 已提交
773 774 775 776 777 778
/* 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
779 780 781 782 783 784 785 786 787 788 789 790
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
791
		return page_private(page);
L
Linus Torvalds 已提交
792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822
	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
823

N
Nick Piggin 已提交
824
#define VM_FAULT_MINOR	0 /* For backwards compat. Remove me quickly. */
N
Nick Piggin 已提交
825

N
Nick Piggin 已提交
826 827 828 829
#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 */
830 831
#define VM_FAULT_HWPOISON 0x0010	/* Hit poisoned small page */
#define VM_FAULT_HWPOISON_LARGE 0x0020  /* Hit poisoned large page. Index encoded in upper bits */
N
Nick Piggin 已提交
832

N
Nick Piggin 已提交
833 834
#define VM_FAULT_NOPAGE	0x0100	/* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED	0x0200	/* ->fault locked the returned page */
835
#define VM_FAULT_RETRY	0x0400	/* ->fault blocked, must retry */
L
Linus Torvalds 已提交
836

837 838 839 840 841 842 843 844
#define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */

#define VM_FAULT_ERROR	(VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \
			 VM_FAULT_HWPOISON_LARGE)

/* Encode hstate index for a hwpoisoned large page */
#define VM_FAULT_SET_HINDEX(x) ((x) << 12)
#define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf)
N
Nick Piggin 已提交
845

846 847 848 849 850
/*
 * 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
851 852 853 854
#define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)

extern void show_free_areas(void);

H
Hugh Dickins 已提交
855
int shmem_lock(struct file *file, int lock, struct user_struct *user);
856
struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
L
Linus Torvalds 已提交
857 858
int shmem_zero_setup(struct vm_area_struct *);

859 860 861 862 863 864 865 866
#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
867
extern int can_do_mlock(void);
L
Linus Torvalds 已提交
868 869 870 871 872 873 874 875 876 877 878 879 880 881 882
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
883 884 885
struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
		pte_t pte);

886 887
int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
		unsigned long size);
888
unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address,
L
Linus Torvalds 已提交
889
		unsigned long size, struct zap_details *);
890
unsigned long unmap_vmas(struct mmu_gather **tlb,
L
Linus Torvalds 已提交
891 892 893
		struct vm_area_struct *start_vma, unsigned long start_addr,
		unsigned long end_addr, unsigned long *nr_accounted,
		struct zap_details *);
894 895 896 897 898 899 900 901

/**
 * 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
902
 * @hugetlb_entry: if set, called for each hugetlb entry
903 904 905 906
 *
 * (see walk_page_range for more details)
 */
struct mm_walk {
D
Dave Hansen 已提交
907 908 909 910 911
	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 *);
912 913
	int (*hugetlb_entry)(pte_t *, unsigned long,
			     unsigned long, unsigned long, struct mm_walk *);
D
Dave Hansen 已提交
914 915
	struct mm_struct *mm;
	void *private;
916 917
};

D
Dave Hansen 已提交
918 919
int walk_page_range(unsigned long addr, unsigned long end,
		struct mm_walk *walk);
920
void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
921
		unsigned long end, unsigned long floor, unsigned long ceiling);
L
Linus Torvalds 已提交
922 923 924 925
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
926 927
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
	unsigned long *pfn);
928 929
int follow_phys(struct vm_area_struct *vma, unsigned long address,
		unsigned int flags, unsigned long *prot, resource_size_t *phys);
930 931
int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
			void *buf, int len, int write);
L
Linus Torvalds 已提交
932 933 934 935 936 937 938

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
939
extern void truncate_pagecache(struct inode *inode, loff_t old, loff_t new);
940
extern void truncate_setsize(struct inode *inode, loff_t newsize);
N
npiggin@suse.de 已提交
941 942
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
943

944
int truncate_inode_page(struct address_space *mapping, struct page *page);
945
int generic_error_remove_page(struct address_space *mapping, struct page *page);
946

947 948
int invalidate_inode_page(struct page *page);

949
#ifdef CONFIG_MMU
N
Nick Piggin 已提交
950
extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
951
			unsigned long address, unsigned int flags);
952 953 954
#else
static inline int handle_mm_fault(struct mm_struct *mm,
			struct vm_area_struct *vma, unsigned long address,
955
			unsigned int flags)
956 957 958 959 960 961
{
	/* should never happen if there's no MMU */
	BUG();
	return VM_FAULT_SIGBUS;
}
#endif
N
Nick Piggin 已提交
962

L
Linus Torvalds 已提交
963 964 965
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);

966
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
967
			unsigned long start, int nr_pages, int write, int force,
968 969 970
			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
971
struct page *get_dump_page(unsigned long addr);
L
Linus Torvalds 已提交
972

973 974 975
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
976
int __set_page_dirty_nobuffers(struct page *page);
977
int __set_page_dirty_no_writeback(struct page *page);
L
Linus Torvalds 已提交
978 979
int redirty_page_for_writepage(struct writeback_control *wbc,
				struct page *page);
980
void account_page_dirtied(struct page *page, struct address_space *mapping);
M
Michael Rubin 已提交
981
void account_page_writeback(struct page *page);
982
int set_page_dirty(struct page *page);
L
Linus Torvalds 已提交
983 984 985
int set_page_dirty_lock(struct page *page);
int clear_page_dirty_for_io(struct page *page);

986 987 988 989 990 991
/* Is the vma a continuation of the stack vma above it? */
static inline int vma_stack_continue(struct vm_area_struct *vma, unsigned long addr)
{
	return vma && (vma->vm_end == addr) && (vma->vm_flags & VM_GROWSDOWN);
}

992 993 994
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
995 996 997
extern unsigned long do_mremap(unsigned long addr,
			       unsigned long old_len, unsigned long new_len,
			       unsigned long flags, unsigned long new_addr);
998 999 1000
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
1001

1002 1003 1004 1005 1006
/*
 * 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
1007 1008 1009
/*
 * per-process(per-mm_struct) statistics.
 */
1010
#if defined(SPLIT_RSS_COUNTING)
K
KAMEZAWA Hiroyuki 已提交
1011 1012 1013 1014 1015 1016 1017 1018 1019
/*
 * 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);
}

1020
unsigned long get_mm_counter(struct mm_struct *mm, int member);
K
KAMEZAWA Hiroyuki 已提交
1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107

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
1108
#if defined(SPLIT_RSS_COUNTING)
1109
void sync_mm_rss(struct task_struct *task, struct mm_struct *mm);
K
KAMEZAWA Hiroyuki 已提交
1110 1111 1112 1113 1114
#else
static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
{
}
#endif
1115

L
Linus Torvalds 已提交
1116
/*
1117
 * A callback you can register to apply pressure to ageable caches.
L
Linus Torvalds 已提交
1118
 *
1119 1120 1121 1122 1123
 * '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
1124
 *
1125 1126 1127 1128 1129
 * 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
1130
 */
1131
struct shrinker {
1132
	int (*shrink)(struct shrinker *, int nr_to_scan, gfp_t gfp_mask);
1133
	int seeks;	/* seeks to recreate an obj */
L
Linus Torvalds 已提交
1134

1135 1136 1137 1138 1139 1140 1141
	/* 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
1142

A
Alexey Dobriyan 已提交
1143
int vma_wants_writenotify(struct vm_area_struct *vma);
1144

1145 1146 1147 1148 1149 1150 1151 1152 1153
extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
			       spinlock_t **ptl);
static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
				    spinlock_t **ptl)
{
	pte_t *ptep;
	__cond_lock(*ptl, ptep = __get_locked_pte(mm, addr, ptl));
	return ptep;
}
1154

N
Nick Piggin 已提交
1155 1156 1157 1158 1159 1160 1161
#ifdef __PAGETABLE_PUD_FOLDED
static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
						unsigned long address)
{
	return 0;
}
#else
1162
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
N
Nick Piggin 已提交
1163 1164 1165 1166 1167 1168 1169 1170 1171
#endif

#ifdef __PAGETABLE_PMD_FOLDED
static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
						unsigned long address)
{
	return 0;
}
#else
1172
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
N
Nick Piggin 已提交
1173 1174
#endif

1175 1176
int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
		pmd_t *pmd, unsigned long address);
1177 1178
int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);

L
Linus Torvalds 已提交
1179 1180 1181 1182
/*
 * The following ifdef needed to get the 4level-fixup.h header to work.
 * Remove it when 4level-fixup.h has been removed.
 */
1183
#if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
L
Linus Torvalds 已提交
1184 1185
static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
{
1186 1187
	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
		NULL: pud_offset(pgd, address);
L
Linus Torvalds 已提交
1188 1189 1190 1191
}

static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
1192 1193
	return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
		NULL: pmd_offset(pud, address);
L
Linus Torvalds 已提交
1194
}
1195 1196
#endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */

1197
#if USE_SPLIT_PTLOCKS
H
Hugh Dickins 已提交
1198 1199 1200 1201 1202 1203
/*
 * 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
1204
#define __pte_lockptr(page)	&((page)->ptl)
H
Hugh Dickins 已提交
1205 1206 1207 1208 1209
#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)));})
1210
#else	/* !USE_SPLIT_PTLOCKS */
H
Hugh Dickins 已提交
1211 1212 1213 1214 1215 1216
/*
 * 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;})
1217
#endif /* USE_SPLIT_PTLOCKS */
H
Hugh Dickins 已提交
1218

1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
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
1231 1232
#define pte_offset_map_lock(mm, pmd, address, ptlp)	\
({							\
H
Hugh Dickins 已提交
1233
	spinlock_t *__ptl = pte_lockptr(mm, pmd);	\
H
Hugh Dickins 已提交
1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244
	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)

1245 1246 1247 1248
#define pte_alloc_map(mm, vma, pmd, address)				\
	((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma,	\
							pmd, address))?	\
	 NULL: pte_offset_map(pmd, address))
1249

H
Hugh Dickins 已提交
1250
#define pte_alloc_map_lock(mm, pmd, address, ptlp)	\
1251 1252
	((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL,	\
							pmd, address))?	\
H
Hugh Dickins 已提交
1253 1254
		NULL: pte_offset_map_lock(mm, pmd, address, ptlp))

1255
#define pte_alloc_kernel(pmd, address)			\
1256
	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
1257
		NULL: pte_offset_kernel(pmd, address))
L
Linus Torvalds 已提交
1258 1259

extern void free_area_init(unsigned long * zones_size);
1260 1261
extern void free_area_init_node(int nid, unsigned long * zones_size,
		unsigned long zone_start_pfn, unsigned long *zholes_size);
1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292
#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);
1293 1294
extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
					unsigned long end_pfn);
1295
extern void remove_all_active_ranges(void);
1296 1297 1298
void sort_node_map(void);
unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
						unsigned long end_pfn);
1299 1300 1301 1302 1303 1304 1305
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);
1306 1307
int add_from_early_node_map(struct range *range, int az,
				   int nr_range, int nid);
1308 1309
u64 __init find_memory_core_early(int nid, u64 size, u64 align,
					u64 goal, u64 limit);
1310 1311
void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
				 u64 goal, u64 limit);
1312
typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
1313
extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data);
1314 1315
extern void sparse_memory_present_with_active_regions(int nid);
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331

#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

1332
extern void set_dma_reserve(unsigned long new_dma_reserve);
D
Dave Hansen 已提交
1333 1334
extern void memmap_init_zone(unsigned long, int, unsigned long,
				unsigned long, enum memmap_context);
1335
extern void setup_per_zone_wmarks(void);
1336
extern void calculate_zone_inactive_ratio(struct zone *zone);
L
Linus Torvalds 已提交
1337
extern void mem_init(void);
1338
extern void __init mmap_init(void);
L
Linus Torvalds 已提交
1339 1340 1341
extern void show_mem(void);
extern void si_meminfo(struct sysinfo * val);
extern void si_meminfo_node(struct sysinfo *val, int nid);
1342
extern int after_bootmem;
L
Linus Torvalds 已提交
1343

1344 1345
extern void setup_per_cpu_pageset(void);

1346 1347
extern void zone_pcp_update(struct zone *zone);

1348
/* nommu.c */
1349
extern atomic_long_t mmap_pages_allocated;
1350
extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
1351

L
Linus Torvalds 已提交
1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370
/* 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 */
1371
extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
1372
extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
L
Linus Torvalds 已提交
1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383
	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 *);
1384
extern void unlink_file_vma(struct vm_area_struct *);
L
Linus Torvalds 已提交
1385 1386 1387
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
1388

1389 1390 1391
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
1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403
#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
1404
extern int may_expand_vm(struct mm_struct *mm, unsigned long npages);
1405 1406 1407
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
1408 1409 1410 1411 1412 1413

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
1414 1415
extern unsigned long mmap_region(struct file *file, unsigned long addr,
	unsigned long len, unsigned long flags,
1416
	unsigned int vm_flags, unsigned long pgoff);
L
Linus Torvalds 已提交
1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437

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);
1438 1439
extern void truncate_inode_pages_range(struct address_space *,
				       loff_t lstart, loff_t lend);
L
Linus Torvalds 已提交
1440 1441

/* generic vm_area_ops exported for stackable file systems */
N
Nick Piggin 已提交
1442
extern int filemap_fault(struct vm_area_struct *, struct vm_fault *);
L
Linus Torvalds 已提交
1443 1444 1445

/* mm/page-writeback.c */
int write_one_page(struct page *page, int wait);
N
Nick Piggin 已提交
1446
void task_dirty_inc(struct task_struct *tsk);
L
Linus Torvalds 已提交
1447 1448 1449 1450 1451 1452

/* 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
1453
			pgoff_t offset, unsigned long nr_to_read);
1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467

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
1468
unsigned long max_sane_readahead(unsigned long nr);
1469 1470 1471
unsigned long ra_submit(struct file_ra_state *ra,
			struct address_space *mapping,
			struct file *filp);
L
Linus Torvalds 已提交
1472 1473

/* Do stack extension */
H
Hugh Dickins 已提交
1474
extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
1475
#if VM_GROWSUP
H
Hugh Dickins 已提交
1476
extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
1477 1478
#else
  #define expand_upwards(vma, address) do { } while (0)
1479
#endif
1480 1481
extern int expand_stack_downwards(struct vm_area_struct *vma,
				  unsigned long address);
L
Linus Torvalds 已提交
1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503

/* 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;
}

1504
#ifdef CONFIG_MMU
1505
pgprot_t vm_get_page_prot(unsigned long vm_flags);
1506 1507 1508 1509 1510 1511 1512
#else
static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
	return __pgprot(0);
}
#endif

1513 1514 1515
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);
1516
int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
N
Nick Piggin 已提交
1517 1518
int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn);
N
Nick Piggin 已提交
1519 1520
int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
			unsigned long pfn);
1521

1522
struct page *follow_page(struct vm_area_struct *, unsigned long address,
1523 1524 1525 1526
			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
1527
#define FOLL_DUMP	0x08	/* give error on hole if it would be zero */
H
Hugh Dickins 已提交
1528
#define FOLL_FORCE	0x10	/* get_user_pages read/write w/o permission */
1529
#define FOLL_MLOCK	0x40	/* mark page as mlocked */
1530
#define FOLL_SPLIT	0x80	/* don't return transhuge pages, split them */
L
Linus Torvalds 已提交
1531

1532
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
1533 1534 1535 1536
			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
1537
#ifdef CONFIG_PROC_FS
1538
void vm_stat_account(struct mm_struct *, unsigned long, struct file *, long);
L
Linus Torvalds 已提交
1539
#else
1540
static inline void vm_stat_account(struct mm_struct *mm,
L
Linus Torvalds 已提交
1541 1542 1543 1544 1545
			unsigned long flags, struct file *file, long pages)
{
}
#endif /* CONFIG_PROC_FS */

1546 1547 1548 1549 1550 1551 1552 1553 1554
#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;
}
1555 1556 1557
#ifdef CONFIG_HIBERNATION
extern bool kernel_page_present(struct page *page);
#endif /* CONFIG_HIBERNATION */
1558
#else
L
Linus Torvalds 已提交
1559
static inline void
N
Nick Piggin 已提交
1560
kernel_map_pages(struct page *page, int numpages, int enable) {}
1561 1562 1563
static inline void enable_debug_pagealloc(void)
{
}
1564 1565 1566
#ifdef CONFIG_HIBERNATION
static inline bool kernel_page_present(struct page *page) { return true; }
#endif /* CONFIG_HIBERNATION */
L
Linus Torvalds 已提交
1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577
#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 */

1578
int drop_caches_sysctl_handler(struct ctl_table *, int,
A
Andrew Morton 已提交
1579
					void __user *, size_t *, loff_t *);
1580
unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
A
Andrew Morton 已提交
1581 1582
			unsigned long lru_pages);

1583 1584 1585
#ifndef CONFIG_MMU
#define randomize_va_space 0
#else
1586
extern int randomize_va_space;
1587
#endif
1588

1589
const char * arch_vma_name(struct vm_area_struct *vma);
1590
void print_vma_addr(char *prefix, unsigned long rip);
1591

1592 1593 1594 1595 1596 1597
void sparse_mem_maps_populate_node(struct page **map_map,
				   unsigned long pnum_begin,
				   unsigned long pnum_end,
				   unsigned long map_count,
				   int nodeid);

1598
struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
1599 1600 1601 1602
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);
1603
void *vmemmap_alloc_block(unsigned long size, int node);
1604
void *vmemmap_alloc_block_buf(unsigned long size, int node);
1605
void vmemmap_verify(pte_t *, int, unsigned long, unsigned long);
1606 1607 1608
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);
1609
void vmemmap_populate_print_last(void);
1610

1611

1612 1613 1614
enum mf_flags {
	MF_COUNT_INCREASED = 1 << 0,
};
1615
extern void memory_failure(unsigned long pfn, int trapno);
1616
extern int __memory_failure(unsigned long pfn, int trapno, int flags);
W
Wu Fengguang 已提交
1617
extern int unpoison_memory(unsigned long pfn);
1618 1619
extern int sysctl_memory_failure_early_kill;
extern int sysctl_memory_failure_recovery;
1620
extern void shake_page(struct page *p, int access);
1621
extern atomic_long_t mce_bad_pages;
1622
extern int soft_offline_page(struct page *page, int flags);
1623 1624 1625 1626 1627 1628 1629 1630
#ifdef CONFIG_MEMORY_FAILURE
int is_hwpoison_address(unsigned long addr);
#else
static inline int is_hwpoison_address(unsigned long addr)
{
	return 0;
}
#endif
1631

1632 1633
extern void dump_page(struct page *page);

A
Andrea Arcangeli 已提交
1634 1635 1636 1637 1638 1639 1640 1641 1642
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
extern void clear_huge_page(struct page *page,
			    unsigned long addr,
			    unsigned int pages_per_huge_page);
extern void copy_user_huge_page(struct page *dst, struct page *src,
				unsigned long addr, struct vm_area_struct *vma,
				unsigned int pages_per_huge_page);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */

L
Linus Torvalds 已提交
1643 1644
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */