mmzone.h 26.8 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
10
11
12
13
#ifndef _LINUX_MMZONE_H
#define _LINUX_MMZONE_H

#ifdef __KERNEL__
#ifndef __ASSEMBLY__

#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/cache.h>
#include <linux/threads.h>
#include <linux/numa.h>
#include <linux/init.h>
14
#include <linux/seqlock.h>
15
#include <linux/nodemask.h>
16
#include <linux/pageblock-flags.h>
Linus Torvalds's avatar
Linus Torvalds committed
17
#include <asm/atomic.h>
Ralf Baechle's avatar
Ralf Baechle committed
18
#include <asm/page.h>
Linus Torvalds's avatar
Linus Torvalds committed
19
20
21
22
23
24
25

/* Free memory management - zoned buddy allocator.  */
#ifndef CONFIG_FORCE_MAX_ZONEORDER
#define MAX_ORDER 11
#else
#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER
#endif
26
#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))
Linus Torvalds's avatar
Linus Torvalds committed
27

Andy Whitcroft's avatar
Andy Whitcroft committed
28
29
30
31
32
33
34
35
/*
 * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
 * costly to service.  That is between allocation orders which should
 * coelesce naturally under reasonable reclaim pressure and those which
 * will not.
 */
#define PAGE_ALLOC_COSTLY_ORDER 3

36
37
38
39
40
41
42
43
#define MIGRATE_UNMOVABLE     0
#define MIGRATE_MOVABLE       1
#define MIGRATE_TYPES         2

#define for_each_migratetype_order(order, type) \
	for (order = 0; order < MAX_ORDER; order++) \
		for (type = 0; type < MIGRATE_TYPES; type++)

Linus Torvalds's avatar
Linus Torvalds committed
44
struct free_area {
45
	struct list_head	free_list[MIGRATE_TYPES];
Linus Torvalds's avatar
Linus Torvalds committed
46
47
48
49
50
51
52
53
54
55
56
57
58
59
	unsigned long		nr_free;
};

struct pglist_data;

/*
 * zone->lock and zone->lru_lock are two of the hottest locks in the kernel.
 * So add a wild amount of padding here to ensure that they fall into separate
 * cachelines.  There are very few zone structures in the machine, so space
 * consumption is not a concern here.
 */
#if defined(CONFIG_SMP)
struct zone_padding {
	char x[0];
60
} ____cacheline_internodealigned_in_smp;
Linus Torvalds's avatar
Linus Torvalds committed
61
62
63
64
65
#define ZONE_PADDING(name)	struct zone_padding name;
#else
#define ZONE_PADDING(name)
#endif

66
enum zone_stat_item {
67
	/* First 128 byte cacheline (assuming 64 bit words) */
68
	NR_FREE_PAGES,
69
70
	NR_INACTIVE,
	NR_ACTIVE,
71
72
	NR_ANON_PAGES,	/* Mapped anonymous pages */
	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
73
			   only modified from process context */
74
	NR_FILE_PAGES,
75
	NR_FILE_DIRTY,
76
	NR_WRITEBACK,
77
78
79
80
	/* Second 128 byte cacheline */
	NR_SLAB_RECLAIMABLE,
	NR_SLAB_UNRECLAIMABLE,
	NR_PAGETABLE,		/* used for pagetables */
81
	NR_UNSTABLE_NFS,	/* NFS unstable pages */
82
	NR_BOUNCE,
83
	NR_VMSCAN_WRITE,
84
85
86
87
88
89
90
91
#ifdef CONFIG_NUMA
	NUMA_HIT,		/* allocated in intended node */
	NUMA_MISS,		/* allocated in non intended node */
	NUMA_FOREIGN,		/* was intended here, hit elsewhere */
	NUMA_INTERLEAVE_HIT,	/* interleaver preferred this zone */
	NUMA_LOCAL,		/* allocation from local node */
	NUMA_OTHER,		/* allocation from other node */
#endif
92
93
	NR_VM_ZONE_STAT_ITEMS };

Linus Torvalds's avatar
Linus Torvalds committed
94
95
96
97
98
99
100
101
102
struct per_cpu_pages {
	int count;		/* number of pages in the list */
	int high;		/* high watermark, emptying needed */
	int batch;		/* chunk size for buddy add/remove */
	struct list_head list;	/* the list of pages */
};

struct per_cpu_pageset {
	struct per_cpu_pages pcp[2];	/* 0: hot.  1: cold */
103
104
105
#ifdef CONFIG_NUMA
	s8 expire;
#endif
106
#ifdef CONFIG_SMP
107
	s8 stat_threshold;
108
109
	s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
Linus Torvalds's avatar
Linus Torvalds committed
110
111
} ____cacheline_aligned_in_smp;

112
113
114
115
116
117
#ifdef CONFIG_NUMA
#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)])
#else
#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
#endif

118
enum zone_type {
119
#ifdef CONFIG_ZONE_DMA
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
	/*
	 * ZONE_DMA is used when there are devices that are not able
	 * to do DMA to all of addressable memory (ZONE_NORMAL). Then we
	 * carve out the portion of memory that is needed for these devices.
	 * The range is arch specific.
	 *
	 * Some examples
	 *
	 * Architecture		Limit
	 * ---------------------------
	 * parisc, ia64, sparc	<4G
	 * s390			<2G
	 * arm			Various
	 * alpha		Unlimited or 0-16MB.
	 *
	 * i386, x86_64 and multiple other arches
	 * 			<16M.
	 */
	ZONE_DMA,
139
#endif
140
#ifdef CONFIG_ZONE_DMA32
141
142
143
144
145
146
	/*
	 * x86_64 needs two ZONE_DMAs because it supports devices that are
	 * only able to do DMA to the lower 16M but also 32 bit devices that
	 * can only do DMA areas below 4G.
	 */
	ZONE_DMA32,
147
#endif
148
149
150
151
152
153
	/*
	 * Normal addressable memory is in ZONE_NORMAL. DMA operations can be
	 * performed on pages in ZONE_NORMAL if the DMA devices support
	 * transfers to all addressable memory.
	 */
	ZONE_NORMAL,
154
#ifdef CONFIG_HIGHMEM
155
156
157
158
159
160
161
162
163
	/*
	 * A memory area that is only addressable by the kernel through
	 * mapping portions into its own address space. This is for example
	 * used by i386 to allow the kernel to address the memory beyond
	 * 900MB. The kernel will set up special mappings (page
	 * table entries on i386) for each page that the kernel needs to
	 * access.
	 */
	ZONE_HIGHMEM,
164
#endif
Mel Gorman's avatar
Mel Gorman committed
165
	ZONE_MOVABLE,
166
167
	MAX_NR_ZONES
};
Linus Torvalds's avatar
Linus Torvalds committed
168
169
170
171
172
173

/*
 * When a memory allocation must conform to specific limitations (such
 * as being suitable for DMA) the caller will pass in hints to the
 * allocator in the gfp_mask, in the zone modifier bits.  These bits
 * are used to select a priority ordered list of memory zones which
174
 * match the requested limits. See gfp_zone() in include/linux/gfp.h
Linus Torvalds's avatar
Linus Torvalds committed
175
 */
176

177
178
179
180
181
182
183
184
185
186
/*
 * Count the active zones.  Note that the use of defined(X) outside
 * #if and family is not necessarily defined so ensure we cannot use
 * it later.  Use __ZONE_COUNT to work out how many shift bits we need.
 */
#define __ZONE_COUNT (			\
	  defined(CONFIG_ZONE_DMA)	\
	+ defined(CONFIG_ZONE_DMA32)	\
	+ 1				\
	+ defined(CONFIG_HIGHMEM)	\
Mel Gorman's avatar
Mel Gorman committed
187
	+ 1				\
188
189
190
191
)
#if __ZONE_COUNT < 2
#define ZONES_SHIFT 0
#elif __ZONE_COUNT <= 2
192
#define ZONES_SHIFT 1
193
#elif __ZONE_COUNT <= 4
194
#define ZONES_SHIFT 2
195
196
#else
#error ZONES_SHIFT -- too many zones configured adjust calculation
197
#endif
198
#undef __ZONE_COUNT
Linus Torvalds's avatar
Linus Torvalds committed
199
200
201
202
203
204
205
206
207
208
209
210
211
212

struct zone {
	/* Fields commonly accessed by the page allocator */
	unsigned long		pages_min, pages_low, pages_high;
	/*
	 * We don't know if the memory that we're going to allocate will be freeable
	 * or/and it will be released eventually, so to avoid totally wasting several
	 * GB of ram we must reserve some of the lower zone memory (otherwise we risk
	 * to run OOM on the lower zones despite there's tons of freeable ram
	 * on the higher zones). This array is recalculated at runtime if the
	 * sysctl_lowmem_reserve_ratio sysctl changes.
	 */
	unsigned long		lowmem_reserve[MAX_NR_ZONES];

213
#ifdef CONFIG_NUMA
214
	int node;
215
216
217
	/*
	 * zone reclaim becomes active if more unmapped pages exist.
	 */
218
	unsigned long		min_unmapped_pages;
219
	unsigned long		min_slab_pages;
220
221
	struct per_cpu_pageset	*pageset[NR_CPUS];
#else
Linus Torvalds's avatar
Linus Torvalds committed
222
	struct per_cpu_pageset	pageset[NR_CPUS];
223
#endif
Linus Torvalds's avatar
Linus Torvalds committed
224
225
226
227
	/*
	 * free areas of different sizes
	 */
	spinlock_t		lock;
228
229
230
231
#ifdef CONFIG_MEMORY_HOTPLUG
	/* see spanned/present_pages for more description */
	seqlock_t		span_seqlock;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
232
233
	struct free_area	free_area[MAX_ORDER];

234
235
236
237
238
239
240
241
#ifndef CONFIG_SPARSEMEM
	/*
	 * Flags for a MAX_ORDER_NR_PAGES block. See pageblock-flags.h.
	 * In SPARSEMEM, this map is stored in struct mem_section
	 */
	unsigned long		*pageblock_flags;
#endif /* CONFIG_SPARSEMEM */

Linus Torvalds's avatar
Linus Torvalds committed
242
243
244
245
246
247
248
249
250
251
252
253

	ZONE_PADDING(_pad1_)

	/* Fields commonly accessed by the page reclaim scanner */
	spinlock_t		lru_lock;	
	struct list_head	active_list;
	struct list_head	inactive_list;
	unsigned long		nr_scan_active;
	unsigned long		nr_scan_inactive;
	unsigned long		pages_scanned;	   /* since last reclaim */
	int			all_unreclaimable; /* All pages pinned */

254
255
	/* A count of how many reclaimers are scanning this zone */
	atomic_t		reclaim_in_progress;
Martin Hicks's avatar
Martin Hicks committed
256

257
258
	/* Zone statistics */
	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
259

Linus Torvalds's avatar
Linus Torvalds committed
260
261
262
263
264
265
266
267
268
269
	/*
	 * prev_priority holds the scanning priority for this zone.  It is
	 * defined as the scanning priority at which we achieved our reclaim
	 * target at the previous try_to_free_pages() or balance_pgdat()
	 * invokation.
	 *
	 * We use prev_priority as a measure of how much stress page reclaim is
	 * under - it drives the swappiness decision: whether to unmap mapped
	 * pages.
	 *
270
	 * Access to both this field is quite racy even on uniprocessor.  But
Linus Torvalds's avatar
Linus Torvalds committed
271
272
273
274
275
276
277
278
279
280
	 * it is expected to average out OK.
	 */
	int prev_priority;


	ZONE_PADDING(_pad2_)
	/* Rarely used or read-mostly fields */

	/*
	 * wait_table		-- the array holding the hash table
281
	 * wait_table_hash_nr_entries	-- the size of the hash table array
Linus Torvalds's avatar
Linus Torvalds committed
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
	 * wait_table_bits	-- wait_table_size == (1 << wait_table_bits)
	 *
	 * The purpose of all these is to keep track of the people
	 * waiting for a page to become available and make them
	 * runnable again when possible. The trouble is that this
	 * consumes a lot of space, especially when so few things
	 * wait on pages at a given time. So instead of using
	 * per-page waitqueues, we use a waitqueue hash table.
	 *
	 * The bucket discipline is to sleep on the same queue when
	 * colliding and wake all in that wait queue when removing.
	 * When something wakes, it must check to be sure its page is
	 * truly available, a la thundering herd. The cost of a
	 * collision is great, but given the expected load of the
	 * table, they should be so rare as to be outweighed by the
	 * benefits from the saved space.
	 *
	 * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
	 * primary users of these fields, and in mm/page_alloc.c
	 * free_area_init_core() performs the initialization of them.
	 */
	wait_queue_head_t	* wait_table;
304
	unsigned long		wait_table_hash_nr_entries;
Linus Torvalds's avatar
Linus Torvalds committed
305
306
307
308
309
310
311
312
313
	unsigned long		wait_table_bits;

	/*
	 * Discontig memory support fields.
	 */
	struct pglist_data	*zone_pgdat;
	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
	unsigned long		zone_start_pfn;

314
315
316
317
318
319
320
321
322
323
	/*
	 * zone_start_pfn, spanned_pages and present_pages are all
	 * protected by span_seqlock.  It is a seqlock because it has
	 * to be read outside of zone->lock, and it is done in the main
	 * allocator path.  But, it is written quite infrequently.
	 *
	 * The lock is declared along with zone->lock because it is
	 * frequently read in proximity to zone->lock.  It's good to
	 * give them a chance of being in the same cacheline.
	 */
Linus Torvalds's avatar
Linus Torvalds committed
324
325
326
327
328
329
	unsigned long		spanned_pages;	/* total size, including holes */
	unsigned long		present_pages;	/* amount of memory (excluding holes) */

	/*
	 * rarely used fields:
	 */
330
	const char		*name;
331
} ____cacheline_internodealigned_in_smp;
Linus Torvalds's avatar
Linus Torvalds committed
332
333
334
335
336
337
338
339

/*
 * The "priority" of VM scanning is how much of the queues we will scan in one
 * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
 * queues ("queue_length >> 12") during an aging round.
 */
#define DEF_PRIORITY 12

340
341
342
343
/* Maximum number of zones on a zonelist */
#define MAX_ZONES_PER_ZONELIST (MAX_NUMNODES * MAX_NR_ZONES)

#ifdef CONFIG_NUMA
344
345
346
347
348
349
350
351
352
353
354

/*
 * The NUMA zonelists are doubled becausse we need zonelists that restrict the
 * allocations to a single node for GFP_THISNODE.
 *
 * [0 .. MAX_NR_ZONES -1] 		: Zonelists with fallback
 * [MAZ_NR_ZONES ... MAZ_ZONELISTS -1]  : No fallback (GFP_THISNODE)
 */
#define MAX_ZONELISTS (2 * MAX_NR_ZONES)


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
/*
 * We cache key information from each zonelist for smaller cache
 * footprint when scanning for free pages in get_page_from_freelist().
 *
 * 1) The BITMAP fullzones tracks which zones in a zonelist have come
 *    up short of free memory since the last time (last_fullzone_zap)
 *    we zero'd fullzones.
 * 2) The array z_to_n[] maps each zone in the zonelist to its node
 *    id, so that we can efficiently evaluate whether that node is
 *    set in the current tasks mems_allowed.
 *
 * Both fullzones and z_to_n[] are one-to-one with the zonelist,
 * indexed by a zones offset in the zonelist zones[] array.
 *
 * The get_page_from_freelist() routine does two scans.  During the
 * first scan, we skip zones whose corresponding bit in 'fullzones'
 * is set or whose corresponding node in current->mems_allowed (which
 * comes from cpusets) is not set.  During the second scan, we bypass
 * this zonelist_cache, to ensure we look methodically at each zone.
 *
 * Once per second, we zero out (zap) fullzones, forcing us to
 * reconsider nodes that might have regained more free memory.
 * The field last_full_zap is the time we last zapped fullzones.
 *
 * This mechanism reduces the amount of time we waste repeatedly
 * reexaming zones for free memory when they just came up low on
 * memory momentarilly ago.
 *
 * The zonelist_cache struct members logically belong in struct
 * zonelist.  However, the mempolicy zonelists constructed for
 * MPOL_BIND are intentionally variable length (and usually much
 * shorter).  A general purpose mechanism for handling structs with
 * multiple variable length members is more mechanism than we want
 * here.  We resort to some special case hackery instead.
 *
 * The MPOL_BIND zonelists don't need this zonelist_cache (in good
 * part because they are shorter), so we put the fixed length stuff
 * at the front of the zonelist struct, ending in a variable length
 * zones[], as is needed by MPOL_BIND.
 *
 * Then we put the optional zonelist cache on the end of the zonelist
 * struct.  This optional stuff is found by a 'zlcache_ptr' pointer in
 * the fixed length portion at the front of the struct.  This pointer
 * both enables us to find the zonelist cache, and in the case of
 * MPOL_BIND zonelists, (which will just set the zlcache_ptr to NULL)
 * to know that the zonelist cache is not there.
 *
 * The end result is that struct zonelists come in two flavors:
 *  1) The full, fixed length version, shown below, and
 *  2) The custom zonelists for MPOL_BIND.
 * The custom MPOL_BIND zonelists have a NULL zlcache_ptr and no zlcache.
 *
 * Even though there may be multiple CPU cores on a node modifying
 * fullzones or last_full_zap in the same zonelist_cache at the same
 * time, we don't lock it.  This is just hint data - if it is wrong now
 * and then, the allocator will still function, perhaps a bit slower.
 */


struct zonelist_cache {
	unsigned short z_to_n[MAX_ZONES_PER_ZONELIST];		/* zone->nid */
416
	DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST);	/* zone full? */
417
418
419
	unsigned long last_full_zap;		/* when last zap'd (jiffies) */
};
#else
420
#define MAX_ZONELISTS MAX_NR_ZONES
421
422
423
struct zonelist_cache;
#endif

Linus Torvalds's avatar
Linus Torvalds committed
424
425
426
427
428
429
/*
 * One allocation request operates on a zonelist. A zonelist
 * is a list of zones, the first one is the 'goal' of the
 * allocation, the other zones are fallback zones, in decreasing
 * priority.
 *
430
431
 * If zlcache_ptr is not NULL, then it is just the address of zlcache,
 * as explained above.  If zlcache_ptr is NULL, there is no zlcache.
Linus Torvalds's avatar
Linus Torvalds committed
432
 */
433

Linus Torvalds's avatar
Linus Torvalds committed
434
struct zonelist {
435
436
437
438
439
	struct zonelist_cache *zlcache_ptr;		     // NULL or &zlcache
	struct zone *zones[MAX_ZONES_PER_ZONELIST + 1];      // NULL delimited
#ifdef CONFIG_NUMA
	struct zonelist_cache zlcache;			     // optional ...
#endif
Linus Torvalds's avatar
Linus Torvalds committed
440
441
};

442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
#ifdef CONFIG_NUMA
/*
 * Only custom zonelists like MPOL_BIND need to be filtered as part of
 * policies. As described in the comment for struct zonelist_cache, these
 * zonelists will not have a zlcache so zlcache_ptr will not be set. Use
 * that to determine if the zonelists needs to be filtered or not.
 */
static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
{
	return !zonelist->zlcache_ptr;
}
#else
static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
{
	return 0;
}
#endif /* CONFIG_NUMA */

460
461
462
463
464
465
466
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
struct node_active_region {
	unsigned long start_pfn;
	unsigned long end_pfn;
	int nid;
};
#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */
Linus Torvalds's avatar
Linus Torvalds committed
467

468
469
470
471
472
#ifndef CONFIG_DISCONTIGMEM
/* The array of struct pages - for discontigmem use pgdat->lmem_map */
extern struct page *mem_map;
#endif

Linus Torvalds's avatar
Linus Torvalds committed
473
474
475
476
477
478
479
480
481
482
483
484
485
486
/*
 * The pg_data_t structure is used in machines with CONFIG_DISCONTIGMEM
 * (mostly NUMA machines?) to denote a higher-level memory zone than the
 * zone denotes.
 *
 * On NUMA machines, each NUMA node would have a pg_data_t to describe
 * it's memory layout.
 *
 * Memory statistics and page replacement data structures are maintained on a
 * per-zone basis.
 */
struct bootmem_data;
typedef struct pglist_data {
	struct zone node_zones[MAX_NR_ZONES];
487
	struct zonelist node_zonelists[MAX_ZONELISTS];
Linus Torvalds's avatar
Linus Torvalds committed
488
	int nr_zones;
489
#ifdef CONFIG_FLAT_NODE_MEM_MAP
Linus Torvalds's avatar
Linus Torvalds committed
490
	struct page *node_mem_map;
491
#endif
Linus Torvalds's avatar
Linus Torvalds committed
492
	struct bootmem_data *bdata;
493
494
495
496
497
498
499
500
501
502
#ifdef CONFIG_MEMORY_HOTPLUG
	/*
	 * Must be held any time you expect node_start_pfn, node_present_pages
	 * or node_spanned_pages stay constant.  Holding this will also
	 * guarantee that any pfn_valid() stays that way.
	 *
	 * Nests above zone->lock and zone->size_seqlock.
	 */
	spinlock_t node_size_lock;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
503
504
505
506
507
508
509
510
511
512
513
514
	unsigned long node_start_pfn;
	unsigned long node_present_pages; /* total number of physical pages */
	unsigned long node_spanned_pages; /* total size of physical page
					     range, including holes */
	int node_id;
	wait_queue_head_t kswapd_wait;
	struct task_struct *kswapd;
	int kswapd_max_order;
} pg_data_t;

#define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
#define node_spanned_pages(nid)	(NODE_DATA(nid)->node_spanned_pages)
515
#ifdef CONFIG_FLAT_NODE_MEM_MAP
516
#define pgdat_page_nr(pgdat, pagenr)	((pgdat)->node_mem_map + (pagenr))
517
518
519
#else
#define pgdat_page_nr(pgdat, pagenr)	pfn_to_page((pgdat)->node_start_pfn + (pagenr))
#endif
520
#define nid_page_nr(nid, pagenr) 	pgdat_page_nr(NODE_DATA(nid),(pagenr))
Linus Torvalds's avatar
Linus Torvalds committed
521

522
523
#include <linux/memory_hotplug.h>

Linus Torvalds's avatar
Linus Torvalds committed
524
525
526
527
528
void get_zone_counts(unsigned long *active, unsigned long *inactive,
			unsigned long *free);
void build_all_zonelists(void);
void wakeup_kswapd(struct zone *zone, int order);
int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
Rohit Seth's avatar
Rohit Seth committed
529
		int classzone_idx, int alloc_flags);
Dave Hansen's avatar
Dave Hansen committed
530
531
532
533
enum memmap_context {
	MEMMAP_EARLY,
	MEMMAP_HOTPLUG,
};
534
extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
Dave Hansen's avatar
Dave Hansen committed
535
536
				     unsigned long size,
				     enum memmap_context context);
537

Linus Torvalds's avatar
Linus Torvalds committed
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
#ifdef CONFIG_HAVE_MEMORY_PRESENT
void memory_present(int nid, unsigned long start, unsigned long end);
#else
static inline void memory_present(int nid, unsigned long start, unsigned long end) {}
#endif

#ifdef CONFIG_NEED_NODE_MEMMAP_SIZE
unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
#endif

/*
 * zone_idx() returns 0 for the ZONE_DMA zone, 1 for the ZONE_NORMAL zone, etc.
 */
#define zone_idx(zone)		((zone) - (zone)->zone_pgdat->node_zones)

553
554
555
556
557
static inline int populated_zone(struct zone *zone)
{
	return (!!zone->present_pages);
}

Mel Gorman's avatar
Mel Gorman committed
558
559
560
561
562
563
564
565
566
567
568
extern int movable_zone;

static inline int zone_movable_is_highmem(void)
{
#if defined(CONFIG_HIGHMEM) && defined(CONFIG_ARCH_POPULATES_NODE_MAP)
	return movable_zone == ZONE_HIGHMEM;
#else
	return 0;
#endif
}

569
static inline int is_highmem_idx(enum zone_type idx)
Linus Torvalds's avatar
Linus Torvalds committed
570
{
571
#ifdef CONFIG_HIGHMEM
Mel Gorman's avatar
Mel Gorman committed
572
573
	return (idx == ZONE_HIGHMEM ||
		(idx == ZONE_MOVABLE && zone_movable_is_highmem()));
574
575
576
#else
	return 0;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
577
578
}

579
static inline int is_normal_idx(enum zone_type idx)
Linus Torvalds's avatar
Linus Torvalds committed
580
581
582
{
	return (idx == ZONE_NORMAL);
}
583

Linus Torvalds's avatar
Linus Torvalds committed
584
585
586
587
588
589
590
591
/**
 * is_highmem - helper function to quickly check if a struct zone is a 
 *              highmem zone or not.  This is an attempt to keep references
 *              to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum.
 * @zone - pointer to struct zone variable
 */
static inline int is_highmem(struct zone *zone)
{
592
#ifdef CONFIG_HIGHMEM
Mel Gorman's avatar
Mel Gorman committed
593
594
595
	int zone_idx = zone - zone->zone_pgdat->node_zones;
	return zone_idx == ZONE_HIGHMEM ||
		(zone_idx == ZONE_MOVABLE && zone_movable_is_highmem());
596
597
598
#else
	return 0;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
599
600
601
602
603
604
605
}

static inline int is_normal(struct zone *zone)
{
	return zone == zone->zone_pgdat->node_zones + ZONE_NORMAL;
}

606
607
static inline int is_dma32(struct zone *zone)
{
608
#ifdef CONFIG_ZONE_DMA32
609
	return zone == zone->zone_pgdat->node_zones + ZONE_DMA32;
610
611
612
#else
	return 0;
#endif
613
614
615
616
}

static inline int is_dma(struct zone *zone)
{
617
#ifdef CONFIG_ZONE_DMA
618
	return zone == zone->zone_pgdat->node_zones + ZONE_DMA;
619
620
621
#else
	return 0;
#endif
622
623
}

Linus Torvalds's avatar
Linus Torvalds committed
624
625
626
627
628
629
630
631
/* These two functions are used to setup the per zone pages min values */
struct ctl_table;
struct file;
int min_free_kbytes_sysctl_handler(struct ctl_table *, int, struct file *, 
					void __user *, size_t *, loff_t *);
extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1];
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, struct file *,
					void __user *, size_t *, loff_t *);
632
633
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
					void __user *, size_t *, loff_t *);
634
635
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
			struct file *, void __user *, size_t *, loff_t *);
636
637
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
			struct file *, void __user *, size_t *, loff_t *);
Linus Torvalds's avatar
Linus Torvalds committed
638

639
640
641
642
643
extern int numa_zonelist_order_handler(struct ctl_table *, int,
			struct file *, void __user *, size_t *, loff_t *);
extern char numa_zonelist_order[];
#define NUMA_ZONELIST_ORDER_LEN 16	/* string buffer size */

Linus Torvalds's avatar
Linus Torvalds committed
644
645
#include <linux/topology.h>
/* Returns the number of the current Node. */
646
#ifndef numa_node_id
647
#define numa_node_id()		(cpu_to_node(raw_smp_processor_id()))
648
#endif
Linus Torvalds's avatar
Linus Torvalds committed
649

650
#ifndef CONFIG_NEED_MULTIPLE_NODES
Linus Torvalds's avatar
Linus Torvalds committed
651
652
653
654
655
656

extern struct pglist_data contig_page_data;
#define NODE_DATA(nid)		(&contig_page_data)
#define NODE_MEM_MAP(nid)	mem_map
#define MAX_NODES_SHIFT		1

657
#else /* CONFIG_NEED_MULTIPLE_NODES */
Linus Torvalds's avatar
Linus Torvalds committed
658
659
660

#include <asm/mmzone.h>

661
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
662

663
664
665
extern struct pglist_data *first_online_pgdat(void);
extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat);
extern struct zone *next_zone(struct zone *zone);
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686

/**
 * for_each_pgdat - helper macro to iterate over all nodes
 * @pgdat - pointer to a pg_data_t variable
 */
#define for_each_online_pgdat(pgdat)			\
	for (pgdat = first_online_pgdat();		\
	     pgdat;					\
	     pgdat = next_online_pgdat(pgdat))
/**
 * for_each_zone - helper macro to iterate over all memory zones
 * @zone - pointer to struct zone variable
 *
 * The user only needs to declare the zone variable, for_each_zone
 * fills it in.
 */
#define for_each_zone(zone)			        \
	for (zone = (first_online_pgdat())->node_zones; \
	     zone;					\
	     zone = next_zone(zone))

687
688
689
690
#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif

691
#if BITS_PER_LONG == 32
Linus Torvalds's avatar
Linus Torvalds committed
692
/*
693
694
 * with 32 bit page->flags field, we reserve 9 bits for node/zone info.
 * there are 4 zones (3 bits) and this leaves 9-3=6 bits for nodes.
Linus Torvalds's avatar
Linus Torvalds committed
695
 */
696
#define FLAGS_RESERVED		9
697

Linus Torvalds's avatar
Linus Torvalds committed
698
699
700
701
#elif BITS_PER_LONG == 64
/*
 * with 64 bit flags field, there's plenty of room.
 */
702
#define FLAGS_RESERVED		32
Linus Torvalds's avatar
Linus Torvalds committed
703

704
#else
Linus Torvalds's avatar
Linus Torvalds committed
705

706
#error BITS_PER_LONG not defined
Linus Torvalds's avatar
Linus Torvalds committed
707
708
709

#endif

710
711
#if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \
	!defined(CONFIG_ARCH_POPULATES_NODE_MAP)
712
713
714
#define early_pfn_to_nid(nid)  (0UL)
#endif

715
716
717
718
#ifdef CONFIG_FLATMEM
#define pfn_to_nid(pfn)		(0)
#endif

719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
#define pfn_to_section_nr(pfn) ((pfn) >> PFN_SECTION_SHIFT)
#define section_nr_to_pfn(sec) ((sec) << PFN_SECTION_SHIFT)

#ifdef CONFIG_SPARSEMEM

/*
 * SECTION_SHIFT    		#bits space required to store a section #
 *
 * PA_SECTION_SHIFT		physical address to/from section number
 * PFN_SECTION_SHIFT		pfn to/from section number
 */
#define SECTIONS_SHIFT		(MAX_PHYSMEM_BITS - SECTION_SIZE_BITS)

#define PA_SECTION_SHIFT	(SECTION_SIZE_BITS)
#define PFN_SECTION_SHIFT	(SECTION_SIZE_BITS - PAGE_SHIFT)

#define NR_MEM_SECTIONS		(1UL << SECTIONS_SHIFT)

#define PAGES_PER_SECTION       (1UL << PFN_SECTION_SHIFT)
#define PAGE_SECTION_MASK	(~(PAGES_PER_SECTION-1))

740
741
742
#define SECTION_BLOCKFLAGS_BITS \
		((SECTION_SIZE_BITS - (MAX_ORDER-1)) * NR_PAGEBLOCK_BITS)

743
744
745
746
747
748
#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS
#error Allocator MAX_ORDER exceeds SECTION_SIZE
#endif

struct page;
struct mem_section {
749
750
751
752
753
	/*
	 * This is, logically, a pointer to an array of struct
	 * pages.  However, it is stored with some other magic.
	 * (see sparse.c::sparse_init_one_section())
	 *
754
755
756
757
	 * Additionally during early boot we encode node id of
	 * the location of the section here to guide allocation.
	 * (see sparse.c::memory_present())
	 *
758
759
760
761
	 * Making it a UL at least makes someone do a cast
	 * before using it wrong.
	 */
	unsigned long section_mem_map;
762
	DECLARE_BITMAP(pageblock_flags, SECTION_BLOCKFLAGS_BITS);
763
764
};

765
766
767
768
769
#ifdef CONFIG_SPARSEMEM_EXTREME
#define SECTIONS_PER_ROOT       (PAGE_SIZE / sizeof (struct mem_section))
#else
#define SECTIONS_PER_ROOT	1
#endif
Bob Picco's avatar
Bob Picco committed
770

771
772
773
#define SECTION_NR_TO_ROOT(sec)	((sec) / SECTIONS_PER_ROOT)
#define NR_SECTION_ROOTS	(NR_MEM_SECTIONS / SECTIONS_PER_ROOT)
#define SECTION_ROOT_MASK	(SECTIONS_PER_ROOT - 1)
Bob Picco's avatar
Bob Picco committed
774

775
776
#ifdef CONFIG_SPARSEMEM_EXTREME
extern struct mem_section *mem_section[NR_SECTION_ROOTS];
Bob Picco's avatar
Bob Picco committed
777
#else
778
779
extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
#endif
780

781
782
static inline struct mem_section *__nr_to_section(unsigned long nr)
{
783
784
785
	if (!mem_section[SECTION_NR_TO_ROOT(nr)])
		return NULL;
	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
786
}
787
extern int __section_nr(struct mem_section* ms);
788
789
790
791
792
793
794
795
796
797

/*
 * We use the lower bits of the mem_map pointer to store
 * a little bit of information.  There should be at least
 * 3 bits here due to 32-bit alignment.
 */
#define	SECTION_MARKED_PRESENT	(1UL<<0)
#define SECTION_HAS_MEM_MAP	(1UL<<1)
#define SECTION_MAP_LAST_BIT	(1UL<<2)
#define SECTION_MAP_MASK	(~(SECTION_MAP_LAST_BIT-1))
798
#define SECTION_NID_SHIFT	2
799
800
801
802
803
804
805
806

static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
	unsigned long map = section->section_mem_map;
	map &= SECTION_MAP_MASK;
	return (struct page *)map;
}

807
static inline int present_section(struct mem_section *section)
808
{
Bob Picco's avatar
Bob Picco committed
809
	return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
810
811
}

812
813
814
815
816
817
static inline int present_section_nr(unsigned long nr)
{
	return present_section(__nr_to_section(nr));
}

static inline int valid_section(struct mem_section *section)
818
{
Bob Picco's avatar
Bob Picco committed
819
	return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
820
821
822
823
824
825
826
}

static inline int valid_section_nr(unsigned long nr)
{
	return valid_section(__nr_to_section(nr));
}

827
828
static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
829
	return __nr_to_section(pfn_to_section_nr(pfn));
830
831
832
833
834
835
}

static inline int pfn_valid(unsigned long pfn)
{
	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
		return 0;
836
	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
837
838
}

839
840
841
842
843
844
845
static inline int pfn_present(unsigned long pfn)
{
	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
		return 0;
	return present_section(__nr_to_section(pfn_to_section_nr(pfn)));
}

846
847
848
849
850
851
/*
 * These are _only_ used during initialisation, therefore they
 * can use __initdata ...  They could have names to indicate
 * this restriction.
 */
#ifdef CONFIG_NUMA
852
853
854
855
856
#define pfn_to_nid(pfn)							\
({									\
	unsigned long __pfn_to_nid_pfn = (pfn);				\
	page_to_nid(pfn_to_page(__pfn_to_nid_pfn));			\
})
857
858
#else
#define pfn_to_nid(pfn)		(0)
859
860
861
862
863
864
#endif

#define early_pfn_valid(pfn)	pfn_valid(pfn)
void sparse_init(void);
#else
#define sparse_init()	do {} while (0)
865
#define sparse_index_init(_sec, _nid)  do {} while (0)
866
867
#endif /* CONFIG_SPARSEMEM */

868
869
870
871
872
873
#ifdef CONFIG_NODES_SPAN_OTHER_NODES
#define early_pfn_in_nid(pfn, nid)	(early_pfn_to_nid(pfn) == (nid))
#else
#define early_pfn_in_nid(pfn, nid)	(1)
#endif

874
875
876
877
878
879
880
#ifndef early_pfn_valid
#define early_pfn_valid(pfn)	(1)
#endif

void memory_present(int nid, unsigned long start, unsigned long end);
unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);

881
882
883
884
885
886
887
888
889
890
891
892
/*
 * If it is possible to have holes within a MAX_ORDER_NR_PAGES, then we
 * need to check pfn validility within that MAX_ORDER_NR_PAGES block.
 * pfn_valid_within() should be used in this case; we optimise this away
 * when we have no holes within a MAX_ORDER_NR_PAGES block.
 */
#ifdef CONFIG_HOLES_IN_ZONE
#define pfn_valid_within(pfn) pfn_valid(pfn)
#else
#define pfn_valid_within(pfn) (1)
#endif

Linus Torvalds's avatar
Linus Torvalds committed
893
894
895
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _LINUX_MMZONE_H */