internal.h 12.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10
/* internal.h: mm/ internal definitions
 *
 * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License
 * as published by the Free Software Foundation; either version
 * 2 of the License, or (at your option) any later version.
 */
11 12 13
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H

14
#include <linux/fs.h>
15
#include <linux/mm.h>
L
Linus Torvalds 已提交
16

17 18 19
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma,
		unsigned long floor, unsigned long ceiling);

20
static inline void set_page_count(struct page *page, int v)
N
Nick Piggin 已提交
21
{
22 23 24
	atomic_set(&page->_count, v);
}

25 26 27 28 29 30 31 32 33 34 35 36 37 38
extern int __do_page_cache_readahead(struct address_space *mapping,
		struct file *filp, pgoff_t offset, unsigned long nr_to_read,
		unsigned long lookahead_size);

/*
 * Submit IO for the read-ahead request in file_ra_state.
 */
static inline unsigned long ra_submit(struct file_ra_state *ra,
		struct address_space *mapping, struct file *filp)
{
	return __do_page_cache_readahead(mapping, filp,
					ra->start, ra->size, ra->async_size);
}

39 40 41 42 43 44
/*
 * Turn a non-refcounted page (->_count == 0) into refcounted with
 * a count of one.
 */
static inline void set_page_refcounted(struct page *page)
{
45 46
	VM_BUG_ON_PAGE(PageTail(page), page);
	VM_BUG_ON_PAGE(atomic_read(&page->_count), page);
N
Nick Piggin 已提交
47 48 49
	set_page_count(page, 1);
}

50 51 52 53 54 55 56 57 58 59 60 61 62 63
static inline void __get_page_tail_foll(struct page *page,
					bool get_page_head)
{
	/*
	 * If we're getting a tail page, the elevated page->_count is
	 * required only in the head page and we will elevate the head
	 * page->_count and tail page->_mapcount.
	 *
	 * We elevate page_tail->_mapcount for tail pages to force
	 * page_tail->_count to be zero at all times to avoid getting
	 * false positives from get_page_unless_zero() with
	 * speculative page access (like in
	 * page_cache_get_speculative()) on tail pages.
	 */
64
	VM_BUG_ON_PAGE(atomic_read(&page->first_page->_count) <= 0, page);
65 66
	if (get_page_head)
		atomic_inc(&page->first_page->_count);
67
	get_huge_page_tail(page);
68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88
}

/*
 * This is meant to be called as the FOLL_GET operation of
 * follow_page() and it must be called while holding the proper PT
 * lock while the pte (or pmd_trans_huge) is still mapping the page.
 */
static inline void get_page_foll(struct page *page)
{
	if (unlikely(PageTail(page)))
		/*
		 * This is safe only because
		 * __split_huge_page_refcount() can't run under
		 * get_page_foll() because we hold the proper PT lock.
		 */
		__get_page_tail_foll(page, true);
	else {
		/*
		 * Getting a normal page or the head of a compound page
		 * requires to already have an elevated page->_count.
		 */
89
		VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
90 91 92 93
		atomic_inc(&page->_count);
	}
}

H
Hugh Dickins 已提交
94 95
extern unsigned long highest_memmap_pfn;

L
Lee Schermerhorn 已提交
96 97 98
/*
 * in mm/vmscan.c:
 */
99
extern int isolate_lru_page(struct page *page);
L
Lee Schermerhorn 已提交
100
extern void putback_lru_page(struct page *page);
101
extern bool zone_reclaimable(struct zone *zone);
102

B
Bob Liu 已提交
103 104 105 106 107
/*
 * in mm/rmap.c:
 */
extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);

L
Lee Schermerhorn 已提交
108 109 110
/*
 * in mm/page_alloc.c
 */
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

/*
 * Locate the struct page for both the matching buddy in our
 * pair (buddy1) and the combined O(n+1) page they form (page).
 *
 * 1) Any buddy B1 will have an order O twin B2 which satisfies
 * the following equation:
 *     B2 = B1 ^ (1 << O)
 * For example, if the starting buddy (buddy2) is #8 its order
 * 1 buddy is #10:
 *     B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10
 *
 * 2) Any buddy B will have an order O+1 parent P which
 * satisfies the following equation:
 *     P = B & ~(1 << O)
 *
 * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
 */
static inline unsigned long
__find_buddy_index(unsigned long page_idx, unsigned int order)
{
	return page_idx ^ (1 << order);
}

extern int __isolate_free_page(struct page *page, unsigned int order);
136
extern void __free_pages_bootmem(struct page *page, unsigned int order);
137
extern void prep_compound_page(struct page *page, unsigned long order);
138 139 140
#ifdef CONFIG_MEMORY_FAILURE
extern bool is_free_buddy_page(struct page *page);
#endif
141
extern int user_min_free_kbytes;
142

143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
#if defined CONFIG_COMPACTION || defined CONFIG_CMA

/*
 * in mm/compaction.c
 */
/*
 * compact_control is used to track pages being migrated and the free pages
 * they are being migrated to during memory compaction. The free_pfn starts
 * at the end of a zone and migrate_pfn begins at the start. Movable pages
 * are moved to the end of a zone during a compaction run and the run
 * completes when free_pfn <= migrate_pfn
 */
struct compact_control {
	struct list_head freepages;	/* List of free pages to migrate to */
	struct list_head migratepages;	/* List of pages being migrated */
	unsigned long nr_freepages;	/* Number of isolated free pages */
	unsigned long nr_migratepages;	/* Number of pages to migrate */
	unsigned long free_pfn;		/* isolate_freepages search base */
	unsigned long migrate_pfn;	/* isolate_migratepages search base */
162
	enum migrate_mode mode;		/* Async or sync migration mode */
163
	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
164
	int order;			/* order a direct compactor needs */
165
	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
166 167
	const int alloc_flags;		/* alloc flags of a direct compactor */
	const int classzone_idx;	/* zone index of a direct compactor */
168
	struct zone *zone;
169 170
	int contended;			/* Signal need_sched() or lock
					 * contention detected during
171 172
					 * compaction
					 */
173 174 175
};

unsigned long
176 177
isolate_freepages_range(struct compact_control *cc,
			unsigned long start_pfn, unsigned long end_pfn);
178
unsigned long
179 180
isolate_migratepages_range(struct compact_control *cc,
			   unsigned long low_pfn, unsigned long end_pfn);
181 182

#endif
183

184
/*
185 186 187 188
 * This function returns the order of a free page in the buddy system. In
 * general, page_zone(page)->lock must be held by the caller to prevent the
 * page from being allocated in parallel and returning garbage as the order.
 * If a caller does not hold page_zone(page)->lock, it must guarantee that the
189 190
 * page cannot be allocated or merged in parallel. Alternatively, it must
 * handle invalid values gracefully, and use page_order_unsafe() below.
191 192 193
 */
static inline unsigned long page_order(struct page *page)
{
194
	/* PageBuddy() must be checked by the caller */
195 196
	return page_private(page);
}
197

198 199 200 201 202 203 204 205 206 207 208 209 210
/*
 * Like page_order(), but for callers who cannot afford to hold the zone lock.
 * PageBuddy() should be checked first by the caller to minimize race window,
 * and invalid values must be handled gracefully.
 *
 * ACCESS_ONCE is used so that if the caller assigns the result into a local
 * variable and e.g. tests it for valid range before using, the compiler cannot
 * decide to remove the variable and inline the page_private(page) multiple
 * times, potentially observing different values in the tests and the actual
 * use of the result.
 */
#define page_order_unsafe(page)		ACCESS_ONCE(page_private(page))

211 212 213 214 215
static inline bool is_cow_mapping(vm_flags_t flags)
{
	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}

216 217 218 219
/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
		struct vm_area_struct *prev, struct rb_node *rb_parent);

H
Hugh Dickins 已提交
220
#ifdef CONFIG_MMU
221 222
extern long __mlock_vma_pages_range(struct vm_area_struct *vma,
		unsigned long start, unsigned long end, int *nonblocking);
H
Hugh Dickins 已提交
223 224 225 226 227 228 229
extern void munlock_vma_pages_range(struct vm_area_struct *vma,
			unsigned long start, unsigned long end);
static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
{
	munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
}

N
Nick Piggin 已提交
230
/*
H
Hugh Dickins 已提交
231
 * must be called with vma's mmap_sem held for read or write, and page locked.
N
Nick Piggin 已提交
232 233
 */
extern void mlock_vma_page(struct page *page);
234
extern unsigned int munlock_vma_page(struct page *page);
N
Nick Piggin 已提交
235 236 237 238 239 240 241 242 243 244

/*
 * Clear the page's PageMlocked().  This can be useful in a situation where
 * we want to unconditionally remove a page from the pagecache -- e.g.,
 * on truncation or freeing.
 *
 * It is legal to call this function for any page, mlocked or not.
 * If called for a page that is still mapped by mlocked vmas, all we do
 * is revert to lazy LRU behaviour -- semantics are not broken.
 */
245
extern void clear_page_mlock(struct page *page);
N
Nick Piggin 已提交
246 247 248

/*
 * mlock_migrate_page - called only from migrate_page_copy() to
N
Nick Piggin 已提交
249
 * migrate the Mlocked page flag; update statistics.
N
Nick Piggin 已提交
250 251 252
 */
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
{
N
Nick Piggin 已提交
253 254
	if (TestClearPageMlocked(page)) {
		unsigned long flags;
255
		int nr_pages = hpage_nr_pages(page);
N
Nick Piggin 已提交
256 257

		local_irq_save(flags);
258
		__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
N
Nick Piggin 已提交
259
		SetPageMlocked(newpage);
260
		__mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages);
N
Nick Piggin 已提交
261 262
		local_irq_restore(flags);
	}
N
Nick Piggin 已提交
263 264
}

265 266
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);

267 268 269 270
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
extern unsigned long vma_address(struct page *page,
				 struct vm_area_struct *vma);
#endif
H
Hugh Dickins 已提交
271
#else /* !CONFIG_MMU */
N
Nick Piggin 已提交
272 273 274 275
static inline void clear_page_mlock(struct page *page) { }
static inline void mlock_vma_page(struct page *page) { }
static inline void mlock_migrate_page(struct page *new, struct page *old) { }

H
Hugh Dickins 已提交
276
#endif /* !CONFIG_MMU */
L
Lee Schermerhorn 已提交
277

278 279 280 281 282 283 284 285
/*
 * Return the mem_map entry representing the 'offset' subpage within
 * the maximally aligned gigantic page 'base'.  Handle any discontiguity
 * in the mem_map at MAX_ORDER_NR_PAGES boundaries.
 */
static inline struct page *mem_map_offset(struct page *base, int offset)
{
	if (unlikely(offset >= MAX_ORDER_NR_PAGES))
F
Fabian Frederick 已提交
286
		return nth_page(base, offset);
287 288 289 290
	return base + offset;
}

/*
L
Lucas De Marchi 已提交
291
 * Iterator over all subpages within the maximally aligned gigantic
292 293 294 295 296 297 298 299 300 301 302 303 304 305
 * page 'base'.  Handle any discontiguity in the mem_map.
 */
static inline struct page *mem_map_next(struct page *iter,
						struct page *base, int offset)
{
	if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) {
		unsigned long pfn = page_to_pfn(base) + offset;
		if (!pfn_valid(pfn))
			return NULL;
		return pfn_to_page(pfn);
	}
	return iter + 1;
}

306 307 308 309 310 311 312 313 314 315 316 317
/*
 * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
 * so all functions starting at paging_init should be marked __init
 * in those cases. SPARSEMEM, however, allows for memory hotplug,
 * and alloc_bootmem_node is not used.
 */
#ifdef CONFIG_SPARSEMEM
#define __paginginit __meminit
#else
#define __paginginit __init
#endif

318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336
/* Memory initialisation debug and verification */
enum mminit_level {
	MMINIT_WARNING,
	MMINIT_VERIFY,
	MMINIT_TRACE
};

#ifdef CONFIG_DEBUG_MEMORY_INIT

extern int mminit_loglevel;

#define mminit_dprintk(level, prefix, fmt, arg...) \
do { \
	if (level < mminit_loglevel) { \
		printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \
		printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \
	} \
} while (0)

337 338 339
extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_page_links(struct page *page,
		enum zone_type zone, unsigned long nid, unsigned long pfn);
340
extern void mminit_verify_zonelist(void);
341

342 343 344 345 346 347 348
#else

static inline void mminit_dprintk(enum mminit_level level,
				const char *prefix, const char *fmt, ...)
{
}

349 350 351 352 353 354 355 356
static inline void mminit_verify_pageflags_layout(void)
{
}

static inline void mminit_verify_page_links(struct page *page,
		enum zone_type zone, unsigned long nid, unsigned long pfn)
{
}
357 358 359 360

static inline void mminit_verify_zonelist(void)
{
}
361
#endif /* CONFIG_DEBUG_MEMORY_INIT */
362 363 364 365 366 367 368 369 370 371 372 373

/* mminit_validate_memmodel_limits is independent of CONFIG_DEBUG_MEMORY_INIT */
#if defined(CONFIG_SPARSEMEM)
extern void mminit_validate_memmodel_limits(unsigned long *start_pfn,
				unsigned long *end_pfn);
#else
static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
				unsigned long *end_pfn)
{
}
#endif /* CONFIG_SPARSEMEM */

374 375 376 377
#define ZONE_RECLAIM_NOSCAN	-2
#define ZONE_RECLAIM_FULL	-1
#define ZONE_RECLAIM_SOME	0
#define ZONE_RECLAIM_SUCCESS	1
W
Wu Fengguang 已提交
378

379 380
extern int hwpoison_filter(struct page *p);

W
Wu Fengguang 已提交
381 382
extern u32 hwpoison_filter_dev_major;
extern u32 hwpoison_filter_dev_minor;
W
Wu Fengguang 已提交
383 384
extern u64 hwpoison_filter_flags_mask;
extern u64 hwpoison_filter_flags_value;
A
Andi Kleen 已提交
385
extern u64 hwpoison_filter_memcg;
386
extern u32 hwpoison_filter_enable;
A
Al Viro 已提交
387 388 389 390

extern unsigned long vm_mmap_pgoff(struct file *, unsigned long,
        unsigned long, unsigned long,
        unsigned long, unsigned long);
391 392

extern void set_pageblock_order(void);
393 394
unsigned long reclaim_clean_pages_from_list(struct zone *zone,
					    struct list_head *page_list);
395 396 397 398 399 400 401 402 403 404 405 406 407
/* The ALLOC_WMARK bits are used as an index to zone->watermark */
#define ALLOC_WMARK_MIN		WMARK_MIN
#define ALLOC_WMARK_LOW		WMARK_LOW
#define ALLOC_WMARK_HIGH	WMARK_HIGH
#define ALLOC_NO_WATERMARKS	0x04 /* don't check watermarks at all */

/* Mask to get the watermark bits */
#define ALLOC_WMARK_MASK	(ALLOC_NO_WATERMARKS-1)

#define ALLOC_HARDER		0x10 /* try to alloc harder */
#define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET		0x40 /* check for correct cpuset */
#define ALLOC_CMA		0x80 /* allow allocations from CMA areas */
408
#define ALLOC_FAIR		0x100 /* fair zone allocation */
409

410
#endif	/* __MM_INTERNAL_H */