summaryrefslogtreecommitdiffstats
path: root/mm/internal.h
blob: f762a34b0c570ff0db963ef6b077223e83c55f6a (plain)
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
139
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
354
355
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
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
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
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/* internal.h: mm/ internal definitions
 *
 * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */
#ifndef __MM_INTERNAL_H
#define __MM_INTERNAL_H

#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/tracepoint-defs.h>

/*
 * The set of flags that only affect watermark checking and reclaim
 * behaviour. This is used by the MM to obey the caller constraints
 * about IO, FS and watermark checking while ignoring placement
 * hints such as HIGHMEM usage.
 */
#define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\
			__GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\
			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\
			__GFP_ATOMIC)

/* The GFP flags allowed during early boot */
#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS))

/* Control allocation cpuset and node placement constraints */
#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)

/* Do not use these with a slab allocator */
#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)

void page_writeback_init(void);

vm_fault_t do_swap_page(struct vm_fault *vmf);

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

static inline bool can_madv_lru_vma(struct vm_area_struct *vma)
{
	return !(vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP));
}

void unmap_page_range(struct mmu_gather *tlb,
			     struct vm_area_struct *vma,
			     unsigned long addr, unsigned long end,
			     struct zap_details *details);

void force_page_cache_readahead(struct address_space *, struct file *,
		pgoff_t index, unsigned long nr_to_read);
void __do_page_cache_readahead(struct address_space *, struct file *,
		pgoff_t index, unsigned long nr_to_read,
		unsigned long lookahead_size);

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

/**
 * page_evictable - test whether a page is evictable
 * @page: the page to test
 *
 * Test whether page is evictable--i.e., should be placed on active/inactive
 * lists vs unevictable list.
 *
 * Reasons page might not be evictable:
 * (1) page's mapping marked unevictable
 * (2) page is part of an mlocked VMA
 *
 */
static inline bool page_evictable(struct page *page)
{
	bool ret;

	/* Prevent address_space of inode and swap cache from being freed */
	rcu_read_lock();
	ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
	rcu_read_unlock();
	return ret;
}

/*
 * Turn a non-refcounted page (->_refcount == 0) into refcounted with
 * a count of one.
 */
static inline void set_page_refcounted(struct page *page)
{
	VM_BUG_ON_PAGE(PageTail(page), page);
	VM_BUG_ON_PAGE(page_ref_count(page), page);
	set_page_count(page, 1);
}

extern unsigned long highest_memmap_pfn;

/*
 * Maximum number of reclaim retries without progress before the OOM
 * killer is consider the only way forward.
 */
#define MAX_RECLAIM_RETRIES 16

/*
 * in mm/vmscan.c:
 */
extern int isolate_lru_page(struct page *page);
extern void putback_lru_page(struct page *page);

/*
 * in mm/rmap.c:
 */
extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);

/*
 * in mm/page_alloc.c
 */

/*
 * Structure for holding the mostly immutable allocation parameters passed
 * between functions involved in allocations, including the alloc_pages*
 * family of functions.
 *
 * nodemask, migratetype and high_zoneidx are initialized only once in
 * __alloc_pages_nodemask() and then never change.
 *
 * zonelist, preferred_zone and classzone_idx are set first in
 * __alloc_pages_nodemask() for the fast path, and might be later changed
 * in __alloc_pages_slowpath(). All other functions pass the whole strucure
 * by a const pointer.
 */
struct alloc_context {
	struct zonelist *zonelist;
	nodemask_t *nodemask;
	struct zoneref *preferred_zoneref;
	int migratetype;
	enum zone_type high_zoneidx;
	bool spread_dirty_pages;
};

#define ac_classzone_idx(ac) zonelist_zone_idx(ac->preferred_zoneref)

/*
 * 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_pfn(unsigned long page_pfn, unsigned int order)
{
	return page_pfn ^ (1 << order);
}

extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
				unsigned long end_pfn, struct zone *zone);

static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn,
				unsigned long end_pfn, struct zone *zone)
{
	if (zone->contiguous)
		return pfn_to_page(start_pfn);

	return __pageblock_pfn_to_page(start_pfn, end_pfn, zone);
}

extern int __isolate_free_page(struct page *page, unsigned int order);
extern void __putback_isolated_page(struct page *page, unsigned int order,
				    int mt);
extern void memblock_free_pages(struct page *page, unsigned long pfn,
					unsigned int order);
extern void __free_pages_core(struct page *page, unsigned int order);
extern void prep_compound_page(struct page *page, unsigned int order);
extern void post_alloc_hook(struct page *page, unsigned int order,
					gfp_t gfp_flags);
extern int user_min_free_kbytes;

extern void zone_pcp_update(struct zone *zone);
extern void zone_pcp_reset(struct zone *zone);

#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 int nr_freepages;	/* Number of isolated free pages */
	unsigned int nr_migratepages;	/* Number of pages to migrate */
	unsigned long free_pfn;		/* isolate_freepages search base */
	unsigned long migrate_pfn;	/* isolate_migratepages search base */
	unsigned long fast_start_pfn;	/* a pfn to start linear scan from */
	struct zone *zone;
	unsigned long total_migrate_scanned;
	unsigned long total_free_scanned;
	unsigned short fast_search_fail;/* failures to use free list searches */
	short search_order;		/* order to start a fast search at */
	const gfp_t gfp_mask;		/* gfp mask of a direct compactor */
	int order;			/* order a direct compactor needs */
	int migratetype;		/* migratetype of direct compactor */
	const unsigned int alloc_flags;	/* alloc flags of a direct compactor */
	const int classzone_idx;	/* zone index of a direct compactor */
	enum migrate_mode mode;		/* Async or sync migration mode */
	bool ignore_skip_hint;		/* Scan blocks even if marked skip */
	bool no_set_skip_hint;		/* Don't mark blocks for skipping */
	bool ignore_block_suitable;	/* Scan blocks considered unsuitable */
	bool direct_compaction;		/* False from kcompactd or /proc/... */
	bool whole_zone;		/* Whole zone should/has been scanned */
	bool contended;			/* Signal lock or sched contention */
	bool rescan;			/* Rescanning the same pageblock */
	bool alloc_contig;		/* alloc_contig_range allocation */
};

/*
 * Used in direct compaction when a page should be taken from the freelists
 * immediately when one is created during the free path.
 */
struct capture_control {
	struct compact_control *cc;
	struct page *page;
};

unsigned long
isolate_freepages_range(struct compact_control *cc,
			unsigned long start_pfn, unsigned long end_pfn);
unsigned long
isolate_migratepages_range(struct compact_control *cc,
			   unsigned long low_pfn, unsigned long end_pfn);
int find_suitable_fallback(struct free_area *area, unsigned int order,
			int migratetype, bool only_stealable, bool *can_steal);

#endif

/*
 * 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
 * page cannot be allocated or merged in parallel. Alternatively, it must
 * handle invalid values gracefully, and use page_order_unsafe() below.
 */
static inline unsigned int page_order(struct page *page)
{
	/* PageBuddy() must be checked by the caller */
	return page_private(page);
}

/*
 * 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.
 *
 * READ_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)		READ_ONCE(page_private(page))

static inline bool is_cow_mapping(vm_flags_t flags)
{
	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}

/*
 * These three helpers classifies VMAs for virtual memory accounting.
 */

/*
 * Executable code area - executable, not writable, not stack
 */
static inline bool is_exec_mapping(vm_flags_t flags)
{
	return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
}

/*
 * Stack area - atomatically grows in one direction
 *
 * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
 * do_mmap() forbids all other combinations.
 */
static inline bool is_stack_mapping(vm_flags_t flags)
{
	return (flags & VM_STACK) == VM_STACK;
}

/*
 * Data area - private, writable, not stack
 */
static inline bool is_data_mapping(vm_flags_t flags)
{
	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
}

/* mm/util.c */
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
		struct vm_area_struct *prev);
void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma);

#ifdef CONFIG_MMU
extern long populate_vma_page_range(struct vm_area_struct *vma,
		unsigned long start, unsigned long end, int *nonblocking);
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);
}

/*
 * must be called with vma's mmap_sem held for read or write, and page locked.
 */
extern void mlock_vma_page(struct page *page);
extern unsigned int munlock_vma_page(struct page *page);

/*
 * 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.
 */
extern void clear_page_mlock(struct page *page);

/*
 * mlock_migrate_page - called only from migrate_misplaced_transhuge_page()
 * (because that does not go through the full procedure of migration ptes):
 * to migrate the Mlocked page flag; update statistics.
 */
static inline void mlock_migrate_page(struct page *newpage, struct page *page)
{
	if (TestClearPageMlocked(page)) {
		int nr_pages = hpage_nr_pages(page);

		/* Holding pmd lock, no change in irq context: __mod is safe */
		__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
		SetPageMlocked(newpage);
		__mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages);
	}
}

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

/*
 * At what user virtual address is page expected in @vma?
 */
static inline unsigned long
__vma_address(struct page *page, struct vm_area_struct *vma)
{
	pgoff_t pgoff = page_to_pgoff(page);
	return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
}

static inline unsigned long
vma_address(struct page *page, struct vm_area_struct *vma)
{
	unsigned long start, end;

	start = __vma_address(page, vma);
	end = start + PAGE_SIZE * (hpage_nr_pages(page) - 1);

	/* page should be within @vma mapping range */
	VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);

	return max(start, vma->vm_start);
}

static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
						    struct file *fpin)
{
	int flags = vmf->flags;

	if (fpin)
		return fpin;

	/*
	 * FAULT_FLAG_RETRY_NOWAIT means we don't want to wait on page locks or
	 * anything, so we only pin the file and drop the mmap_sem if only
	 * FAULT_FLAG_ALLOW_RETRY is set, while this is the first attempt.
	 */
	if (fault_flag_allow_retry_first(flags) &&
	    !(flags & FAULT_FLAG_RETRY_NOWAIT)) {
		fpin = get_file(vmf->vma->vm_file);
		up_read(&vmf->vma->vm_mm->mmap_sem);
	}
	return fpin;
}

#else /* !CONFIG_MMU */
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) { }

#endif /* !CONFIG_MMU */

/*
 * 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))
		return nth_page(base, offset);
	return base + offset;
}

/*
 * Iterator over all subpages within the maximally aligned gigantic
 * 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;
}

/* 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) { \
		if (level <= MMINIT_WARNING) \
			pr_warn("mminit::" prefix " " fmt, ##arg);	\
		else \
			printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \
	} \
} while (0)

extern void mminit_verify_pageflags_layout(void);
extern void mminit_verify_zonelist(void);
#else

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

static inline void mminit_verify_pageflags_layout(void)
{
}

static inline void mminit_verify_zonelist(void)
{
}
#endif /* CONFIG_DEBUG_MEMORY_INIT */

/* 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 */

#define NODE_RECLAIM_NOSCAN	-2
#define NODE_RECLAIM_FULL	-1
#define NODE_RECLAIM_SOME	0
#define NODE_RECLAIM_SUCCESS	1

#ifdef CONFIG_NUMA
extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
#else
static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
				unsigned int order)
{
	return NODE_RECLAIM_NOSCAN;
}
#endif

extern int hwpoison_filter(struct page *p);

extern u32 hwpoison_filter_dev_major;
extern u32 hwpoison_filter_dev_minor;
extern u64 hwpoison_filter_flags_mask;
extern u64 hwpoison_filter_flags_value;
extern u64 hwpoison_filter_memcg;
extern u32 hwpoison_filter_enable;

extern unsigned long  __must_check vm_mmap_pgoff(struct file *, unsigned long,
        unsigned long, unsigned long,
        unsigned long, unsigned long);

extern void set_pageblock_order(void);
unsigned long reclaim_clean_pages_from_list(struct zone *zone,
					    struct list_head *page_list);
/* 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)

/*
 * Only MMU archs have async oom victim reclaim - aka oom_reaper so we
 * cannot assume a reduced access to memory reserves is sufficient for
 * !MMU
 */
#ifdef CONFIG_MMU
#define ALLOC_OOM		0x08
#else
#define ALLOC_OOM		ALLOC_NO_WATERMARKS
#endif

#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 */
#ifdef CONFIG_ZONE_DMA32
#define ALLOC_NOFRAGMENT	0x100 /* avoid mixing pageblock types */
#else
#define ALLOC_NOFRAGMENT	  0x0
#endif
#define ALLOC_KSWAPD		0x800 /* allow waking of kswapd, __GFP_KSWAPD_RECLAIM set */

enum ttu_flags;
struct tlbflush_unmap_batch;


/*
 * only for MM internal work items which do not depend on
 * any allocations or locks which might depend on allocations
 */
extern struct workqueue_struct *mm_percpu_wq;

#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
void try_to_unmap_flush(void);
void try_to_unmap_flush_dirty(void);
void flush_tlb_batched_pending(struct mm_struct *mm);
#else
static inline void try_to_unmap_flush(void)
{
}
static inline void try_to_unmap_flush_dirty(void)
{
}
static inline void flush_tlb_batched_pending(struct mm_struct *mm)
{
}
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */

extern const struct trace_print_flags pageflag_names[];
extern const struct trace_print_flags vmaflag_names[];
extern const struct trace_print_flags gfpflag_names[];

static inline bool is_migrate_highatomic(enum migratetype migratetype)
{
	return migratetype == MIGRATE_HIGHATOMIC;
}

static inline bool is_migrate_highatomic_page(struct page *page)
{
	return get_pageblock_migratetype(page) == MIGRATE_HIGHATOMIC;
}

void setup_zone_pageset(struct zone *zone);
extern struct page *alloc_new_node_page(struct page *page, unsigned long node);
#endif	/* __MM_INTERNAL_H */