mmzone.h 20.9 KB
Newer Older
L
Linus Torvalds 已提交
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>
L
Linus Torvalds 已提交
16
#include <asm/atomic.h>
R
Ralf Baechle 已提交
17
#include <asm/page.h>
L
Linus Torvalds 已提交
18 19 20 21 22 23 24

/* Free memory management - zoned buddy allocator.  */
#ifndef CONFIG_FORCE_MAX_ZONEORDER
#define MAX_ORDER 11
#else
#define MAX_ORDER CONFIG_FORCE_MAX_ZONEORDER
#endif
25
#define MAX_ORDER_NR_PAGES (1 << (MAX_ORDER - 1))
L
Linus Torvalds 已提交
26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42

struct free_area {
	struct list_head	free_list;
	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];
43
} ____cacheline_internodealigned_in_smp;
L
Linus Torvalds 已提交
44 45 46 47 48
#define ZONE_PADDING(name)	struct zone_padding name;
#else
#define ZONE_PADDING(name)
#endif

49
enum zone_stat_item {
50 51
	NR_ANON_PAGES,	/* Mapped anonymous pages */
	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
52
			   only modified from process context */
53
	NR_FILE_PAGES,
54
	NR_SLAB,	/* Pages used by slab allocator */
55
	NR_PAGETABLE,	/* used for pagetables */
56
	NR_FILE_DIRTY,
57
	NR_WRITEBACK,
58
	NR_UNSTABLE_NFS,	/* NFS unstable pages */
59
	NR_BOUNCE,
60 61 62 63 64 65 66 67
#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
68 69
	NR_VM_ZONE_STAT_ITEMS };

L
Linus Torvalds 已提交
70 71 72 73 74 75 76 77 78
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 */
79
#ifdef CONFIG_SMP
80
	s8 stat_threshold;
81 82
	s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
#endif
L
Linus Torvalds 已提交
83 84
} ____cacheline_aligned_in_smp;

85 86 87 88 89 90
#ifdef CONFIG_NUMA
#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)])
#else
#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
#endif

91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
enum zone_type {
	/*
	 * 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
	 * arm26		<48M
	 * arm			Various
	 * alpha		Unlimited or 0-16MB.
	 *
	 * i386, x86_64 and multiple other arches
	 * 			<16M.
	 */
	ZONE_DMA,
112
#ifdef CONFIG_ZONE_DMA32
113 114 115 116 117 118
	/*
	 * 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,
119
#endif
120 121 122 123 124 125
	/*
	 * 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,
126
#ifdef CONFIG_HIGHMEM
127 128 129 130 131 132 133 134 135
	/*
	 * 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,
136
#endif
137 138
	MAX_NR_ZONES
};
L
Linus Torvalds 已提交
139 140 141 142 143 144 145 146 147 148 149 150 151 152


/*
 * 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
 * match the requested limits.  GFP_ZONEMASK defines which bits within
 * the gfp_mask should be considered as zone modifiers.  Each valid
 * combination of the zone modifier bits has a corresponding list
 * of zones (in node_zonelists).  Thus for two zone modifiers there
 * will be a maximum of 4 (2 ** 2) zonelists, for 3 modifiers there will
 * be 8 (2 ** 3) zonelists.  GFP_ZONETYPES defines the number of possible
 * combinations of zone modifiers in "zone modifier space".
153
 *
154 155 156 157 158 159 160
 * As an optimisation any zone modifier bits which are only valid when
 * no other zone modifier bits are set (loners) should be placed in
 * the highest order bits of this field.  This allows us to reduce the
 * extent of the zonelists thus saving space.  For example in the case
 * of three zone modifier bits, we could require up to eight zonelists.
 * If the left most zone modifier is a "loner" then the highest valid
 * zonelist would be four allowing us to allocate only five zonelists.
161 162
 * Use the first form for GFP_ZONETYPES when the left most bit is not
 * a "loner", otherwise use the second.
163
 *
164
 * NOTE! Make sure this matches the zones in <linux/gfp.h>
L
Linus Torvalds 已提交
165
 */
166 167

#ifdef CONFIG_ZONE_DMA32
168 169 170

#ifdef CONFIG_HIGHMEM
#define GFP_ZONETYPES		((GFP_ZONEMASK + 1) / 2 + 1)    /* Loner */
171
#define GFP_ZONEMASK		0x07
172
#define ZONES_SHIFT		2	/* ceil(log2(MAX_NR_ZONES)) */
173
#else
174 175 176 177 178 179 180 181 182
#define GFP_ZONETYPES		((0x07 + 1) / 2 + 1)    /* Loner */
/* Mask __GFP_HIGHMEM */
#define GFP_ZONEMASK		0x05
#define ZONES_SHIFT		2
#endif

#else
#ifdef CONFIG_HIGHMEM

183
#define GFP_ZONEMASK		0x03
184 185 186 187 188 189 190 191 192 193
#define ZONES_SHIFT		2
#define GFP_ZONETYPES		3

#else

#define GFP_ZONEMASK		0x01
#define ZONES_SHIFT		1
#define GFP_ZONETYPES		2

#endif
194
#endif
L
Linus Torvalds 已提交
195 196 197 198 199 200 201 202 203 204 205 206 207 208 209

struct zone {
	/* Fields commonly accessed by the page allocator */
	unsigned long		free_pages;
	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];

210
#ifdef CONFIG_NUMA
211 212 213 214
	/*
	 * zone reclaim becomes active if more unmapped pages exist.
	 */
	unsigned long		min_unmapped_ratio;
215 216
	struct per_cpu_pageset	*pageset[NR_CPUS];
#else
L
Linus Torvalds 已提交
217
	struct per_cpu_pageset	pageset[NR_CPUS];
218
#endif
L
Linus Torvalds 已提交
219 220 221 222
	/*
	 * free areas of different sizes
	 */
	spinlock_t		lock;
223 224 225 226
#ifdef CONFIG_MEMORY_HOTPLUG
	/* see spanned/present_pages for more description */
	seqlock_t		span_seqlock;
#endif
L
Linus Torvalds 已提交
227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242
	struct free_area	free_area[MAX_ORDER];


	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		nr_active;
	unsigned long		nr_inactive;
	unsigned long		pages_scanned;	   /* since last reclaim */
	int			all_unreclaimable; /* All pages pinned */

243 244
	/* A count of how many reclaimers are scanning this zone */
	atomic_t		reclaim_in_progress;
M
Martin Hicks 已提交
245

246 247
	/* Zone statistics */
	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
248

L
Linus Torvalds 已提交
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
	/*
	 * 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.
	 *
	 * temp_priority is used to remember the scanning priority at which
	 * this zone was successfully refilled to free_pages == pages_high.
	 *
	 * Access to both these fields is quite racy even on uniprocessor.  But
	 * it is expected to average out OK.
	 */
	int temp_priority;
	int prev_priority;


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

	/*
	 * wait_table		-- the array holding the hash table
274
	 * wait_table_hash_nr_entries	-- the size of the hash table array
L
Linus Torvalds 已提交
275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296
	 * 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;
297
	unsigned long		wait_table_hash_nr_entries;
L
Linus Torvalds 已提交
298 299 300 301 302 303 304 305 306
	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;

307 308 309 310 311 312 313 314 315 316
	/*
	 * 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.
	 */
L
Linus Torvalds 已提交
317 318 319 320 321 322 323
	unsigned long		spanned_pages;	/* total size, including holes */
	unsigned long		present_pages;	/* amount of memory (excluding holes) */

	/*
	 * rarely used fields:
	 */
	char			*name;
324
} ____cacheline_internodealigned_in_smp;
L
Linus Torvalds 已提交
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

/*
 * 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

/*
 * 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.
 *
 * Right now a zonelist takes up less than a cacheline. We never
 * modify it apart from boot-up, and only a few indices are used,
 * so despite the zonelist table being relatively big, the cache
 * footprint of this construct is very small.
 */
struct zonelist {
	struct zone *zones[MAX_NUMNODES * MAX_NR_ZONES + 1]; // NULL delimited
};


/*
 * 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];
	struct zonelist node_zonelists[GFP_ZONETYPES];
	int nr_zones;
A
Andy Whitcroft 已提交
365
#ifdef CONFIG_FLAT_NODE_MEM_MAP
L
Linus Torvalds 已提交
366
	struct page *node_mem_map;
A
Andy Whitcroft 已提交
367
#endif
L
Linus Torvalds 已提交
368
	struct bootmem_data *bdata;
369 370 371 372 373 374 375 376 377 378
#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
L
Linus Torvalds 已提交
379 380 381 382 383 384 385 386 387 388 389 390
	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)
A
Andy Whitcroft 已提交
391
#ifdef CONFIG_FLAT_NODE_MEM_MAP
392
#define pgdat_page_nr(pgdat, pagenr)	((pgdat)->node_mem_map + (pagenr))
A
Andy Whitcroft 已提交
393 394 395
#else
#define pgdat_page_nr(pgdat, pagenr)	pfn_to_page((pgdat)->node_start_pfn + (pagenr))
#endif
396
#define nid_page_nr(nid, pagenr) 	pgdat_page_nr(NODE_DATA(nid),(pagenr))
L
Linus Torvalds 已提交
397

398 399
#include <linux/memory_hotplug.h>

L
Linus Torvalds 已提交
400 401 402 403 404 405 406
void __get_zone_counts(unsigned long *active, unsigned long *inactive,
			unsigned long *free, struct pglist_data *pgdat);
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,
R
Rohit Seth 已提交
407
		int classzone_idx, int alloc_flags);
L
Linus Torvalds 已提交
408

409 410 411
extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
				     unsigned long size);

L
Linus Torvalds 已提交
412 413 414 415 416 417 418 419 420 421 422 423 424 425 426
#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)

427 428 429 430 431
static inline int populated_zone(struct zone *zone)
{
	return (!!zone->present_pages);
}

432
static inline int is_highmem_idx(enum zone_type idx)
L
Linus Torvalds 已提交
433
{
434
#ifdef CONFIG_HIGHMEM
L
Linus Torvalds 已提交
435
	return (idx == ZONE_HIGHMEM);
436 437 438
#else
	return 0;
#endif
L
Linus Torvalds 已提交
439 440
}

441
static inline int is_normal_idx(enum zone_type idx)
L
Linus Torvalds 已提交
442 443 444
{
	return (idx == ZONE_NORMAL);
}
N
Nick Piggin 已提交
445

L
Linus Torvalds 已提交
446 447 448 449 450 451 452 453
/**
 * 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)
{
454
#ifdef CONFIG_HIGHMEM
L
Linus Torvalds 已提交
455
	return zone == zone->zone_pgdat->node_zones + ZONE_HIGHMEM;
456 457 458
#else
	return 0;
#endif
L
Linus Torvalds 已提交
459 460 461 462 463 464 465
}

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

N
Nick Piggin 已提交
466 467
static inline int is_dma32(struct zone *zone)
{
468
#ifdef CONFIG_ZONE_DMA32
N
Nick Piggin 已提交
469
	return zone == zone->zone_pgdat->node_zones + ZONE_DMA32;
470 471 472
#else
	return 0;
#endif
N
Nick Piggin 已提交
473 474 475 476 477 478 479
}

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

L
Linus Torvalds 已提交
480 481 482 483 484 485 486 487
/* 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 *);
488 489
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
					void __user *, size_t *, loff_t *);
490 491
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
			struct file *, void __user *, size_t *, loff_t *);
L
Linus Torvalds 已提交
492 493 494

#include <linux/topology.h>
/* Returns the number of the current Node. */
495
#ifndef numa_node_id
I
Ingo Molnar 已提交
496
#define numa_node_id()		(cpu_to_node(raw_smp_processor_id()))
497
#endif
L
Linus Torvalds 已提交
498

499
#ifndef CONFIG_NEED_MULTIPLE_NODES
L
Linus Torvalds 已提交
500 501 502 503 504 505

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

506
#else /* CONFIG_NEED_MULTIPLE_NODES */
L
Linus Torvalds 已提交
507 508 509

#include <asm/mmzone.h>

510
#endif /* !CONFIG_NEED_MULTIPLE_NODES */
511

512 513 514
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);
515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535

/**
 * 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))

A
Andy Whitcroft 已提交
536 537 538 539
#ifdef CONFIG_SPARSEMEM
#include <asm/sparsemem.h>
#endif

540
#if BITS_PER_LONG == 32
L
Linus Torvalds 已提交
541
/*
A
Andi Kleen 已提交
542 543
 * 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.
L
Linus Torvalds 已提交
544
 */
A
Andi Kleen 已提交
545
#define FLAGS_RESERVED		9
546

L
Linus Torvalds 已提交
547 548 549 550
#elif BITS_PER_LONG == 64
/*
 * with 64 bit flags field, there's plenty of room.
 */
551
#define FLAGS_RESERVED		32
L
Linus Torvalds 已提交
552

553
#else
L
Linus Torvalds 已提交
554

555
#error BITS_PER_LONG not defined
L
Linus Torvalds 已提交
556 557 558

#endif

559 560 561 562
#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
#define early_pfn_to_nid(nid)  (0UL)
#endif

563 564 565 566
#ifdef CONFIG_FLATMEM
#define pfn_to_nid(pfn)		(0)
#endif

A
Andy Whitcroft 已提交
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
#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))

#if (MAX_ORDER - 1 + PAGE_SHIFT) > SECTION_SIZE_BITS
#error Allocator MAX_ORDER exceeds SECTION_SIZE
#endif

struct page;
struct mem_section {
A
Andy Whitcroft 已提交
594 595 596 597 598
	/*
	 * 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())
	 *
599 600 601 602
	 * Additionally during early boot we encode node id of
	 * the location of the section here to guide allocation.
	 * (see sparse.c::memory_present())
	 *
A
Andy Whitcroft 已提交
603 604 605 606
	 * Making it a UL at least makes someone do a cast
	 * before using it wrong.
	 */
	unsigned long section_mem_map;
A
Andy Whitcroft 已提交
607 608
};

609 610 611 612 613
#ifdef CONFIG_SPARSEMEM_EXTREME
#define SECTIONS_PER_ROOT       (PAGE_SIZE / sizeof (struct mem_section))
#else
#define SECTIONS_PER_ROOT	1
#endif
B
Bob Picco 已提交
614

615 616 617
#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)
B
Bob Picco 已提交
618

619 620
#ifdef CONFIG_SPARSEMEM_EXTREME
extern struct mem_section *mem_section[NR_SECTION_ROOTS];
B
Bob Picco 已提交
621
#else
622 623
extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT];
#endif
A
Andy Whitcroft 已提交
624

A
Andy Whitcroft 已提交
625 626
static inline struct mem_section *__nr_to_section(unsigned long nr)
{
627 628 629
	if (!mem_section[SECTION_NR_TO_ROOT(nr)])
		return NULL;
	return &mem_section[SECTION_NR_TO_ROOT(nr)][nr & SECTION_ROOT_MASK];
A
Andy Whitcroft 已提交
630
}
631
extern int __section_nr(struct mem_section* ms);
A
Andy Whitcroft 已提交
632 633 634 635 636 637 638 639 640 641

/*
 * 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))
642
#define SECTION_NID_SHIFT	2
A
Andy Whitcroft 已提交
643 644 645 646 647 648 649 650 651 652

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;
}

static inline int valid_section(struct mem_section *section)
{
B
Bob Picco 已提交
653
	return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
A
Andy Whitcroft 已提交
654 655 656 657
}

static inline int section_has_mem_map(struct mem_section *section)
{
B
Bob Picco 已提交
658
	return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
A
Andy Whitcroft 已提交
659 660 661 662 663 664 665
}

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

A
Andy Whitcroft 已提交
666 667
static inline struct mem_section *__pfn_to_section(unsigned long pfn)
{
A
Andy Whitcroft 已提交
668
	return __nr_to_section(pfn_to_section_nr(pfn));
A
Andy Whitcroft 已提交
669 670 671 672 673 674
}

static inline int pfn_valid(unsigned long pfn)
{
	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
		return 0;
A
Andy Whitcroft 已提交
675
	return valid_section(__nr_to_section(pfn_to_section_nr(pfn)));
A
Andy Whitcroft 已提交
676 677 678 679 680 681 682 683
}

/*
 * These are _only_ used during initialisation, therefore they
 * can use __initdata ...  They could have names to indicate
 * this restriction.
 */
#ifdef CONFIG_NUMA
684 685 686 687 688
#define pfn_to_nid(pfn)							\
({									\
	unsigned long __pfn_to_nid_pfn = (pfn);				\
	page_to_nid(pfn_to_page(__pfn_to_nid_pfn));			\
})
689 690
#else
#define pfn_to_nid(pfn)		(0)
A
Andy Whitcroft 已提交
691 692 693 694 695 696
#endif

#define early_pfn_valid(pfn)	pfn_valid(pfn)
void sparse_init(void);
#else
#define sparse_init()	do {} while (0)
697
#define sparse_index_init(_sec, _nid)  do {} while (0)
A
Andy Whitcroft 已提交
698 699 700 701 702 703 704 705 706
#endif /* CONFIG_SPARSEMEM */

#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);

L
Linus Torvalds 已提交
707 708 709
#endif /* !__ASSEMBLY__ */
#endif /* __KERNEL__ */
#endif /* _LINUX_MMZONE_H */