Blame view
mm/internal.h
15.4 KB
1da177e4c
|
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. */ |
0f8053a50
|
11 12 |
#ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H |
29f175d12
|
13 |
#include <linux/fs.h> |
0f8053a50
|
14 |
#include <linux/mm.h> |
e9b61f198
|
15 |
#include <linux/pagemap.h> |
edf14cdbf
|
16 |
#include <linux/tracepoint-defs.h> |
1da177e4c
|
17 |
|
dd56b0464
|
18 19 20 21 22 23 24 25 |
/* * 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_REPEAT|__GFP_NOFAIL|\ |
e838a45f9
|
26 27 |
__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_ATOMIC) |
dd56b0464
|
28 29 30 31 32 33 34 35 36 |
/* 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) |
bae473a42
|
37 |
int do_swap_page(struct fault_env *fe, pte_t orig_pte); |
8a966ed74
|
38 |
|
42b777281
|
39 40 |
void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); |
aac453635
|
41 42 43 44 |
void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); |
29f175d12
|
45 46 47 48 49 50 51 52 53 54 55 56 57 |
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); } |
7835e98b2
|
58 |
/* |
0139aa7b7
|
59 |
* Turn a non-refcounted page (->_refcount == 0) into refcounted with |
7835e98b2
|
60 61 62 63 |
* a count of one. */ static inline void set_page_refcounted(struct page *page) { |
309381fea
|
64 |
VM_BUG_ON_PAGE(PageTail(page), page); |
fe896d187
|
65 |
VM_BUG_ON_PAGE(page_ref_count(page), page); |
77a8a7883
|
66 |
set_page_count(page, 1); |
77a8a7883
|
67 |
} |
03f6462a3
|
68 |
extern unsigned long highest_memmap_pfn; |
894bc3104
|
69 70 71 |
/* * in mm/vmscan.c: */ |
62695a84e
|
72 |
extern int isolate_lru_page(struct page *page); |
894bc3104
|
73 |
extern void putback_lru_page(struct page *page); |
599d0c954
|
74 |
extern bool pgdat_reclaimable(struct pglist_data *pgdat); |
62695a84e
|
75 |
|
894bc3104
|
76 |
/* |
6219049ae
|
77 78 79 80 81 |
* in mm/rmap.c: */ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* |
894bc3104
|
82 83 |
* in mm/page_alloc.c */ |
3c605096d
|
84 85 |
/* |
1a6d53a10
|
86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
* 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; |
c33d6c06f
|
101 |
struct zoneref *preferred_zoneref; |
1a6d53a10
|
102 103 |
int migratetype; enum zone_type high_zoneidx; |
c9ab0c4fb
|
104 |
bool spread_dirty_pages; |
1a6d53a10
|
105 |
}; |
93ea9964d
|
106 |
#define ac_classzone_idx(ac) zonelist_zone_idx(ac->preferred_zoneref) |
1a6d53a10
|
107 |
/* |
3c605096d
|
108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 |
* 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); } |
7cf91a98e
|
129 130 131 132 133 134 135 136 137 138 139 |
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); } |
3c605096d
|
140 |
extern int __isolate_free_page(struct page *page, unsigned int order); |
d70ddd7a5
|
141 142 |
extern void __free_pages_bootmem(struct page *page, unsigned long pfn, unsigned int order); |
d00181b96
|
143 |
extern void prep_compound_page(struct page *page, unsigned int order); |
46f24fd85
|
144 145 |
extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); |
42aa83cb6
|
146 |
extern int user_min_free_kbytes; |
20a0307c0
|
147 |
|
ff9543fd3
|
148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 |
#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 */ |
1a16718cf
|
167 |
unsigned long last_migrated_pfn;/* Not yet flushed page being freed */ |
e0b9daeb4
|
168 |
enum migrate_mode mode; /* Async or sync migration mode */ |
bb13ffeb9
|
169 |
bool ignore_skip_hint; /* Scan blocks even if marked skip */ |
9f7e33879
|
170 |
bool ignore_block_suitable; /* Scan blocks considered unsuitable */ |
accf62422
|
171 |
bool direct_compaction; /* False from kcompactd or /proc/... */ |
06ed29989
|
172 |
bool whole_zone; /* Whole zone should/has been scanned */ |
ff9543fd3
|
173 |
int order; /* order a direct compactor needs */ |
6d7ce5594
|
174 |
const gfp_t gfp_mask; /* gfp mask of a direct compactor */ |
c603844bd
|
175 |
const unsigned int alloc_flags; /* alloc flags of a direct compactor */ |
ebff39801
|
176 |
const int classzone_idx; /* zone index of a direct compactor */ |
ff9543fd3
|
177 |
struct zone *zone; |
c3486f537
|
178 |
bool contended; /* Signal lock or sched contention */ |
ff9543fd3
|
179 180 181 |
}; unsigned long |
bb13ffeb9
|
182 183 |
isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); |
ff9543fd3
|
184 |
unsigned long |
edc2ca612
|
185 186 |
isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); |
2149cdaef
|
187 188 |
int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); |
ff9543fd3
|
189 190 |
#endif |
0f8053a50
|
191 |
|
48f13bf3e
|
192 |
/* |
6c14466cc
|
193 194 195 196 |
* 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 |
99c0fd5e5
|
197 198 |
* page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use page_order_unsafe() below. |
48f13bf3e
|
199 |
*/ |
d00181b96
|
200 |
static inline unsigned int page_order(struct page *page) |
48f13bf3e
|
201 |
{ |
572438f9b
|
202 |
/* PageBuddy() must be checked by the caller */ |
48f13bf3e
|
203 204 |
return page_private(page); } |
b5a0e0113
|
205 |
|
99c0fd5e5
|
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. * |
4db0c3c29
|
211 |
* READ_ONCE is used so that if the caller assigns the result into a local |
99c0fd5e5
|
212 213 214 215 216 |
* 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. */ |
4db0c3c29
|
217 |
#define page_order_unsafe(page) READ_ONCE(page_private(page)) |
99c0fd5e5
|
218 |
|
4bbd4c776
|
219 220 221 222 |
static inline bool is_cow_mapping(vm_flags_t flags) { return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } |
30bdbb780
|
223 224 225 226 227 228 229 |
/* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ |
d977d56ce
|
230 231 |
static inline bool is_exec_mapping(vm_flags_t flags) { |
30bdbb780
|
232 |
return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; |
d977d56ce
|
233 |
} |
30bdbb780
|
234 235 236 237 238 239 |
/* * Stack area - atomatically grows in one direction * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ |
d977d56ce
|
240 241 |
static inline bool is_stack_mapping(vm_flags_t flags) { |
30bdbb780
|
242 |
return (flags & VM_STACK) == VM_STACK; |
d977d56ce
|
243 |
} |
30bdbb780
|
244 245 246 |
/* * Data area - private, writable, not stack */ |
d977d56ce
|
247 248 |
static inline bool is_data_mapping(vm_flags_t flags) { |
30bdbb780
|
249 |
return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; |
d977d56ce
|
250 |
} |
6038def0d
|
251 252 253 |
/* 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); |
af8e3354b
|
254 |
#ifdef CONFIG_MMU |
fc05f5662
|
255 |
extern long populate_vma_page_range(struct vm_area_struct *vma, |
cea10a19b
|
256 |
unsigned long start, unsigned long end, int *nonblocking); |
af8e3354b
|
257 258 259 260 261 262 |
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); } |
b291f0003
|
263 |
/* |
73848b468
|
264 |
* must be called with vma's mmap_sem held for read or write, and page locked. |
b291f0003
|
265 266 |
*/ extern void mlock_vma_page(struct page *page); |
ff6a6da60
|
267 |
extern unsigned int munlock_vma_page(struct page *page); |
b291f0003
|
268 269 270 271 272 273 274 275 276 277 |
/* * 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. */ |
e6c509f85
|
278 |
extern void clear_page_mlock(struct page *page); |
b291f0003
|
279 280 |
/* |
51afb12ba
|
281 282 283 |
* 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. |
b291f0003
|
284 285 286 |
*/ static inline void mlock_migrate_page(struct page *newpage, struct page *page) { |
5344b7e64
|
287 |
if (TestClearPageMlocked(page)) { |
b32967ff1
|
288 |
int nr_pages = hpage_nr_pages(page); |
5344b7e64
|
289 |
|
51afb12ba
|
290 |
/* Holding pmd lock, no change in irq context: __mod is safe */ |
b32967ff1
|
291 |
__mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages); |
b291f0003
|
292 |
SetPageMlocked(newpage); |
b32967ff1
|
293 |
__mod_zone_page_state(page_zone(newpage), NR_MLOCK, nr_pages); |
5344b7e64
|
294 |
} |
b291f0003
|
295 |
} |
b32967ff1
|
296 |
extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); |
e9b61f198
|
297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 |
/* * 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 address = __vma_address(page, vma); /* page should be within @vma mapping range */ VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma); return address; } |
af8e3354b
|
317 |
#else /* !CONFIG_MMU */ |
b291f0003
|
318 319 320 |
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) { } |
af8e3354b
|
321 |
#endif /* !CONFIG_MMU */ |
894bc3104
|
322 |
|
b5a0e0113
|
323 |
/* |
69d177c2f
|
324 325 326 327 328 329 330 |
* 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)) |
bc7f84c0e
|
331 |
return nth_page(base, offset); |
69d177c2f
|
332 333 334 335 |
return base + offset; } /* |
25985edce
|
336 |
* Iterator over all subpages within the maximally aligned gigantic |
69d177c2f
|
337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 |
* 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; } /* |
b5a0e0113
|
352 353 354 355 356 357 358 359 360 361 |
* 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 |
6b74ab97b
|
362 363 364 365 366 367 368 369 370 371 372 373 374 375 |
/* 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) { \ |
fc5199d1a
|
376 |
if (level <= MMINIT_WARNING) \ |
1170532bb
|
377 |
pr_warn("mminit::" prefix " " fmt, ##arg); \ |
fc5199d1a
|
378 379 |
else \ printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ |
6b74ab97b
|
380 381 |
} \ } while (0) |
708614e61
|
382 |
extern void mminit_verify_pageflags_layout(void); |
68ad8df42
|
383 |
extern void mminit_verify_zonelist(void); |
6b74ab97b
|
384 385 386 387 388 389 |
#else static inline void mminit_dprintk(enum mminit_level level, const char *prefix, const char *fmt, ...) { } |
708614e61
|
390 391 392 |
static inline void mminit_verify_pageflags_layout(void) { } |
68ad8df42
|
393 394 395 |
static inline void mminit_verify_zonelist(void) { } |
6b74ab97b
|
396 |
#endif /* CONFIG_DEBUG_MEMORY_INIT */ |
2dbb51c49
|
397 398 399 400 401 402 403 404 405 406 407 |
/* 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 */ |
a5f5f91da
|
408 409 410 411 |
#define NODE_RECLAIM_NOSCAN -2 #define NODE_RECLAIM_FULL -1 #define NODE_RECLAIM_SOME 0 #define NODE_RECLAIM_SUCCESS 1 |
7c116f2b0
|
412 |
|
31d3d3484
|
413 |
extern int hwpoison_filter(struct page *p); |
7c116f2b0
|
414 415 |
extern u32 hwpoison_filter_dev_major; extern u32 hwpoison_filter_dev_minor; |
478c5ffc0
|
416 417 |
extern u64 hwpoison_filter_flags_mask; extern u64 hwpoison_filter_flags_value; |
4fd466eb4
|
418 |
extern u64 hwpoison_filter_memcg; |
1bfe5febe
|
419 |
extern u32 hwpoison_filter_enable; |
eb36c5873
|
420 |
|
dc0ef0df7
|
421 |
extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, |
eb36c5873
|
422 |
unsigned long, unsigned long, |
9fbeb5ab5
|
423 |
unsigned long, unsigned long); |
ca57df79d
|
424 425 |
extern void set_pageblock_order(void); |
02c6de8d7
|
426 427 |
unsigned long reclaim_clean_pages_from_list(struct zone *zone, struct list_head *page_list); |
d95ea5d18
|
428 429 430 431 432 433 434 435 436 437 438 439 440 |
/* 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 */ |
72b252aed
|
441 442 443 444 445 |
enum ttu_flags; struct tlbflush_unmap_batch; #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH void try_to_unmap_flush(void); |
d950c9477
|
446 |
void try_to_unmap_flush_dirty(void); |
5a1eef71a
|
447 |
void flush_tlb_batched_pending(struct mm_struct *mm); |
72b252aed
|
448 449 450 451 |
#else static inline void try_to_unmap_flush(void) { } |
d950c9477
|
452 453 454 |
static inline void try_to_unmap_flush_dirty(void) { } |
5a1eef71a
|
455 456 457 |
static inline void flush_tlb_batched_pending(struct mm_struct *mm) { } |
72b252aed
|
458 |
#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ |
edf14cdbf
|
459 460 461 462 |
extern const struct trace_print_flags pageflag_names[]; extern const struct trace_print_flags vmaflag_names[]; extern const struct trace_print_flags gfpflag_names[]; |
db9714188
|
463 |
#endif /* __MM_INTERNAL_H */ |