page_alloc.c 64.2 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
/*
 *  linux/mm/page_alloc.c
 *
 *  Manages the free list, the system allocates free pages here.
 *  Note that kmalloc() lives in slab.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *  Swap reorganised 29.12.95, Stephen Tweedie
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 *  Reshaped it to be a zoned allocator, Ingo Molnar, Red Hat, 1999
 *  Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
 *  Zone balancing, Kanoj Sarcar, SGI, Jan 2000
 *  Per cpu hot/cold page lists, bulk allocation, Martin J. Bligh, Sept 2002
 *          (lots of bits borrowed from Ingo Molnar & Andrew Morton)
 */

#include <linux/config.h>
#include <linux/stddef.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/compiler.h>
25
#include <linux/kernel.h>
Linus Torvalds's avatar
Linus Torvalds committed
26
27
28
29
30
31
32
33
34
35
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/pagevec.h>
#include <linux/blkdev.h>
#include <linux/slab.h>
#include <linux/notifier.h>
#include <linux/topology.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
36
#include <linux/memory_hotplug.h>
Linus Torvalds's avatar
Linus Torvalds committed
37
38
39
40
41
42
43
44
45
46
#include <linux/nodemask.h>
#include <linux/vmalloc.h>

#include <asm/tlbflush.h>
#include "internal.h"

/*
 * MCD - HACK: Find somewhere to initialize this EARLY, or make this
 * initializer cleaner
 */
47
nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
48
EXPORT_SYMBOL(node_online_map);
49
nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
50
EXPORT_SYMBOL(node_possible_map);
51
struct pglist_data *pgdat_list __read_mostly;
52
53
unsigned long totalram_pages __read_mostly;
unsigned long totalhigh_pages __read_mostly;
Linus Torvalds's avatar
Linus Torvalds committed
54
55
56
57
58
59
60
61
62
long nr_swap_pages;

/*
 * results with 256, 32 in the lowmem_reserve sysctl:
 *	1G machine -> (16M dma, 800M-16M normal, 1G-800M high)
 *	1G machine -> (16M dma, 784M normal, 224M high)
 *	NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA
 *	HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL
 *	HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA
63
64
65
 *
 * TBD: should special case ZONE_DMA32 machines here - in those we normally
 * don't need any ZONE_NORMAL reservation
Linus Torvalds's avatar
Linus Torvalds committed
66
 */
67
int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { 256, 256, 32 };
Linus Torvalds's avatar
Linus Torvalds committed
68
69
70
71
72
73
74

EXPORT_SYMBOL(totalram_pages);

/*
 * Used by page_zone() to look up the address of the struct zone whose
 * id is encoded in the upper bits of page->flags
 */
75
struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly;
Linus Torvalds's avatar
Linus Torvalds committed
76
77
EXPORT_SYMBOL(zone_table);

78
static char *zone_names[MAX_NR_ZONES] = { "DMA", "DMA32", "Normal", "HighMem" };
Linus Torvalds's avatar
Linus Torvalds committed
79
80
81
82
83
int min_free_kbytes = 1024;

unsigned long __initdata nr_kernel_pages;
unsigned long __initdata nr_all_pages;

Nick Piggin's avatar
Nick Piggin committed
84
#ifdef CONFIG_DEBUG_VM
85
static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
Linus Torvalds's avatar
Linus Torvalds committed
86
{
87
88
89
	int ret = 0;
	unsigned seq;
	unsigned long pfn = page_to_pfn(page);
90

91
92
93
94
95
96
97
98
99
	do {
		seq = zone_span_seqbegin(zone);
		if (pfn >= zone->zone_start_pfn + zone->spanned_pages)
			ret = 1;
		else if (pfn < zone->zone_start_pfn)
			ret = 1;
	} while (zone_span_seqretry(zone, seq));

	return ret;
100
101
102
103
}

static int page_is_consistent(struct zone *zone, struct page *page)
{
Linus Torvalds's avatar
Linus Torvalds committed
104
105
#ifdef CONFIG_HOLES_IN_ZONE
	if (!pfn_valid(page_to_pfn(page)))
106
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed
107
108
#endif
	if (zone != page_zone(page))
109
110
111
112
113
114
115
116
117
118
		return 0;

	return 1;
}
/*
 * Temporary debugging check for pages not lying within a given zone.
 */
static int bad_range(struct zone *zone, struct page *page)
{
	if (page_outside_zone_boundaries(zone, page))
Linus Torvalds's avatar
Linus Torvalds committed
119
		return 1;
120
121
122
	if (!page_is_consistent(zone, page))
		return 1;

Linus Torvalds's avatar
Linus Torvalds committed
123
124
125
	return 0;
}

Nick Piggin's avatar
Nick Piggin committed
126
127
128
129
130
131
132
#else
static inline int bad_range(struct zone *zone, struct page *page)
{
	return 0;
}
#endif

Linus Torvalds's avatar
Linus Torvalds committed
133
134
135
136
137
static void bad_page(const char *function, struct page *page)
{
	printk(KERN_EMERG "Bad page state at %s (in process '%s', page %p)\n",
		function, current->comm, page);
	printk(KERN_EMERG "flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
138
		(int)(2*sizeof(unsigned long)), (unsigned long)page->flags,
Linus Torvalds's avatar
Linus Torvalds committed
139
140
141
142
		page->mapping, page_mapcount(page), page_count(page));
	printk(KERN_EMERG "Backtrace:\n");
	dump_stack();
	printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n");
143
144
	page->flags &= ~(1 << PG_lru	|
			1 << PG_private |
Linus Torvalds's avatar
Linus Torvalds committed
145
146
147
			1 << PG_locked	|
			1 << PG_active	|
			1 << PG_dirty	|
148
149
			1 << PG_reclaim |
			1 << PG_slab    |
Linus Torvalds's avatar
Linus Torvalds committed
150
			1 << PG_swapcache |
151
			1 << PG_writeback );
Linus Torvalds's avatar
Linus Torvalds committed
152
153
154
	set_page_count(page, 0);
	reset_page_mapcount(page);
	page->mapping = NULL;
155
	add_taint(TAINT_BAD_PAGE);
Linus Torvalds's avatar
Linus Torvalds committed
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
}

/*
 * Higher-order pages are called "compound pages".  They are structured thusly:
 *
 * The first PAGE_SIZE page is called the "head page".
 *
 * The remaining PAGE_SIZE pages are called "tail pages".
 *
 * All pages have PG_compound set.  All pages have their ->private pointing at
 * the head page (even the head page has this).
 *
 * The first tail page's ->mapping, if non-zero, holds the address of the
 * compound page's put_page() function.
 *
 * The order of the allocation is stored in the first tail page's ->index
 * This is only for debug at present.  This usage means that zero-order pages
 * may not be compound.
 */
static void prep_compound_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;

	page[1].mapping = NULL;
	page[1].index = order;
	for (i = 0; i < nr_pages; i++) {
		struct page *p = page + i;

		SetPageCompound(p);
186
		set_page_private(p, (unsigned long)page);
Linus Torvalds's avatar
Linus Torvalds committed
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
	}
}

static void destroy_compound_page(struct page *page, unsigned long order)
{
	int i;
	int nr_pages = 1 << order;

	if (!PageCompound(page))
		return;

	if (page[1].index != order)
		bad_page(__FUNCTION__, page);

	for (i = 0; i < nr_pages; i++) {
		struct page *p = page + i;

		if (!PageCompound(p))
			bad_page(__FUNCTION__, page);
206
		if (page_private(p) != (unsigned long)page)
Linus Torvalds's avatar
Linus Torvalds committed
207
208
209
210
211
212
213
214
215
216
217
			bad_page(__FUNCTION__, page);
		ClearPageCompound(p);
	}
}

/*
 * function for dealing with page's order in buddy system.
 * zone->lock is already acquired when we use these.
 * So, we don't need atomic page->flags operations here.
 */
static inline unsigned long page_order(struct page *page) {
218
	return page_private(page);
Linus Torvalds's avatar
Linus Torvalds committed
219
220
221
}

static inline void set_page_order(struct page *page, int order) {
222
	set_page_private(page, order);
Linus Torvalds's avatar
Linus Torvalds committed
223
224
225
226
227
228
	__SetPagePrivate(page);
}

static inline void rmv_page_order(struct page *page)
{
	__ClearPagePrivate(page);
229
	set_page_private(page, 0);
Linus Torvalds's avatar
Linus Torvalds committed
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
}

/*
 * 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 contigious at least up to MAX_ORDER
 */
static inline struct page *
__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
{
	unsigned long buddy_idx = page_idx ^ (1 << order);

	return page + (buddy_idx - page_idx);
}

static inline unsigned long
__find_combined_index(unsigned long page_idx, unsigned int order)
{
	return (page_idx & ~(1 << order));
}

/*
 * This function checks whether a page is free && is the buddy
 * we can do coalesce a page and its buddy if
Nick Piggin's avatar
Nick Piggin committed
266
267
268
269
 * (a) the buddy is not in a hole &&
 * (b) the buddy is free &&
 * (c) the buddy is on the buddy system &&
 * (d) a page and its buddy have the same order.
270
 * for recording page's order, we use page_private(page) and PG_private.
Linus Torvalds's avatar
Linus Torvalds committed
271
272
273
274
 *
 */
static inline int page_is_buddy(struct page *page, int order)
{
Nick Piggin's avatar
Nick Piggin committed
275
276
277
278
279
#ifdef CONFIG_HOLES_IN_ZONE
	if (!pfn_valid(page_to_pfn(page)))
		return 0;
#endif

Linus Torvalds's avatar
Linus Torvalds committed
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
       if (PagePrivate(page)           &&
           (page_order(page) == order) &&
            page_count(page) == 0)
               return 1;
       return 0;
}

/*
 * Freeing function for a buddy system allocator.
 *
 * The concept of a buddy system is to maintain direct-mapped table
 * (containing bit values) for memory blocks of various "orders".
 * The bottom level table contains the map for the smallest allocatable
 * units of memory (here, pages), and each level above it describes
 * pairs of units from the levels below, hence, "buddies".
 * At a high level, all that happens here is marking the table entry
 * at the bottom level available, and propagating the changes upward
 * as necessary, plus some accounting needed to play nicely with other
 * parts of the VM system.
 * At each level, we keep a list of pages, which are heads of continuous
 * free pages of length of (1 << order) and marked with PG_Private.Page's
301
 * order is recorded in page_private(page) field.
Linus Torvalds's avatar
Linus Torvalds committed
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
 * So when we are allocating or freeing one, we can derive the state of the
 * other.  That is, if we allocate a small block, and both were   
 * free, the remainder of the region must be split into blocks.   
 * If a block is freed, and its buddy is also free, then this
 * triggers coalescing into a block of larger size.            
 *
 * -- wli
 */

static inline void __free_pages_bulk (struct page *page,
		struct zone *zone, unsigned int order)
{
	unsigned long page_idx;
	int order_size = 1 << order;

	if (unlikely(order))
		destroy_compound_page(page, order);

	page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);

	BUG_ON(page_idx & (order_size - 1));
	BUG_ON(bad_range(zone, page));

	zone->free_pages += order_size;
	while (order < MAX_ORDER-1) {
		unsigned long combined_idx;
		struct free_area *area;
		struct page *buddy;

		buddy = __page_find_buddy(page, page_idx, order);
		if (!page_is_buddy(buddy, order))
			break;		/* Move the buddy up one level. */
Nick Piggin's avatar
Nick Piggin committed
334

Linus Torvalds's avatar
Linus Torvalds committed
335
336
337
338
		list_del(&buddy->lru);
		area = zone->free_area + order;
		area->nr_free--;
		rmv_page_order(buddy);
Nick Piggin's avatar
Nick Piggin committed
339
		combined_idx = __find_combined_index(page_idx, order);
Linus Torvalds's avatar
Linus Torvalds committed
340
341
342
343
344
345
346
347
348
		page = page + (combined_idx - page_idx);
		page_idx = combined_idx;
		order++;
	}
	set_page_order(page, order);
	list_add(&page->lru, &zone->free_area[order].free_list);
	zone->free_area[order].nr_free++;
}

349
static inline int free_pages_check(const char *function, struct page *page)
Linus Torvalds's avatar
Linus Torvalds committed
350
{
Nick Piggin's avatar
Nick Piggin committed
351
352
353
	if (unlikely(page_mapcount(page) |
		(page->mapping != NULL)  |
		(page_count(page) != 0)  |
Linus Torvalds's avatar
Linus Torvalds committed
354
355
356
357
358
359
360
361
		(page->flags & (
			1 << PG_lru	|
			1 << PG_private |
			1 << PG_locked	|
			1 << PG_active	|
			1 << PG_reclaim	|
			1 << PG_slab	|
			1 << PG_swapcache |
Nick Piggin's avatar
Nick Piggin committed
362
			1 << PG_writeback |
Nick Piggin's avatar
Nick Piggin committed
363
			1 << PG_reserved ))))
Linus Torvalds's avatar
Linus Torvalds committed
364
365
		bad_page(function, page);
	if (PageDirty(page))
Nick Piggin's avatar
Nick Piggin committed
366
		__ClearPageDirty(page);
367
368
369
370
371
372
	/*
	 * For now, we report if PG_reserved was found set, but do not
	 * clear it, and do not free the page.  But we shall soon need
	 * to do more, for when the ZERO_PAGE count wraps negative.
	 */
	return PageReserved(page);
Linus Torvalds's avatar
Linus Torvalds committed
373
374
375
376
377
}

/*
 * Frees a list of pages. 
 * Assumes all pages on list are in same zone, and of same order.
378
 * count is the number of pages to free.
Linus Torvalds's avatar
Linus Torvalds committed
379
380
381
382
383
384
385
386
387
388
389
390
391
392
 *
 * If the zone was previously in an "all pages pinned" state then look to
 * see if this freeing clears that state.
 *
 * And clear the zone's pages_scanned counter, to hold off the "all pages are
 * pinned" detection logic.
 */
static int
free_pages_bulk(struct zone *zone, int count,
		struct list_head *list, unsigned int order)
{
	struct page *page = NULL;
	int ret = 0;

Nick Piggin's avatar
Nick Piggin committed
393
	spin_lock(&zone->lock);
Linus Torvalds's avatar
Linus Torvalds committed
394
395
396
397
398
399
400
401
402
	zone->all_unreclaimable = 0;
	zone->pages_scanned = 0;
	while (!list_empty(list) && count--) {
		page = list_entry(list->prev, struct page, lru);
		/* have to delete it as __free_pages_bulk list manipulates */
		list_del(&page->lru);
		__free_pages_bulk(page, zone, order);
		ret++;
	}
Nick Piggin's avatar
Nick Piggin committed
403
	spin_unlock(&zone->lock);
Linus Torvalds's avatar
Linus Torvalds committed
404
405
406
407
408
	return ret;
}

void __free_pages_ok(struct page *page, unsigned int order)
{
Nick Piggin's avatar
Nick Piggin committed
409
	unsigned long flags;
Linus Torvalds's avatar
Linus Torvalds committed
410
411
	LIST_HEAD(list);
	int i;
412
	int reserved = 0;
Linus Torvalds's avatar
Linus Torvalds committed
413
414
415
416
417
418
419
420
421
422

	arch_free_page(page, order);

#ifndef CONFIG_MMU
	if (order > 0)
		for (i = 1 ; i < (1 << order) ; ++i)
			__put_page(page + i);
#endif

	for (i = 0 ; i < (1 << order) ; ++i)
423
424
425
426
		reserved += free_pages_check(__FUNCTION__, page + i);
	if (reserved)
		return;

Linus Torvalds's avatar
Linus Torvalds committed
427
	list_add(&page->lru, &list);
428
	mod_page_state(pgfree, 1 << order);
Linus Torvalds's avatar
Linus Torvalds committed
429
	kernel_map_pages(page, 1<<order, 0);
Nick Piggin's avatar
Nick Piggin committed
430
	local_irq_save(flags);
Linus Torvalds's avatar
Linus Torvalds committed
431
	free_pages_bulk(page_zone(page), 1, &list, order);
Nick Piggin's avatar
Nick Piggin committed
432
	local_irq_restore(flags);
Linus Torvalds's avatar
Linus Torvalds committed
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
}


/*
 * The order of subdivision here is critical for the IO subsystem.
 * Please do not alter this order without good reasons and regression
 * testing. Specifically, as large blocks of memory are subdivided,
 * the order in which smaller blocks are delivered depends on the order
 * they're subdivided in this function. This is the primary factor
 * influencing the order in which pages are delivered to the IO
 * subsystem according to empirical testing, and this is also justified
 * by considering the behavior of a buddy system containing a single
 * large block of memory acted on by a series of small allocations.
 * This behavior is a critical factor in sglist merging's success.
 *
 * -- wli
 */
static inline struct page *
expand(struct zone *zone, struct page *page,
 	int low, int high, struct free_area *area)
{
	unsigned long size = 1 << high;

	while (high > low) {
		area--;
		high--;
		size >>= 1;
		BUG_ON(bad_range(zone, &page[size]));
		list_add(&page[size].lru, &area->free_list);
		area->nr_free++;
		set_page_order(&page[size], high);
	}
	return page;
}

/*
 * This page is about to be returned from the page allocator
 */
471
static int prep_new_page(struct page *page, int order)
Linus Torvalds's avatar
Linus Torvalds committed
472
{
Nick Piggin's avatar
Nick Piggin committed
473
474
475
	if (unlikely(page_mapcount(page) |
		(page->mapping != NULL)  |
		(page_count(page) != 0)  |
476
477
		(page->flags & (
			1 << PG_lru	|
Linus Torvalds's avatar
Linus Torvalds committed
478
479
480
481
482
			1 << PG_private	|
			1 << PG_locked	|
			1 << PG_active	|
			1 << PG_dirty	|
			1 << PG_reclaim	|
483
			1 << PG_slab    |
Linus Torvalds's avatar
Linus Torvalds committed
484
			1 << PG_swapcache |
Nick Piggin's avatar
Nick Piggin committed
485
			1 << PG_writeback |
Nick Piggin's avatar
Nick Piggin committed
486
			1 << PG_reserved ))))
Linus Torvalds's avatar
Linus Torvalds committed
487
488
		bad_page(__FUNCTION__, page);

489
490
491
492
493
494
495
	/*
	 * For now, we report if PG_reserved was found set, but do not
	 * clear it, and do not allocate the page: as a safety net.
	 */
	if (PageReserved(page))
		return 1;

Linus Torvalds's avatar
Linus Torvalds committed
496
497
498
	page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
			1 << PG_referenced | 1 << PG_arch_1 |
			1 << PG_checked | 1 << PG_mappedtodisk);
499
	set_page_private(page, 0);
Linus Torvalds's avatar
Linus Torvalds committed
500
501
	set_page_refs(page, order);
	kernel_map_pages(page, 1 << order, 1);
502
	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
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
}

/* 
 * Do the hard work of removing an element from the buddy allocator.
 * Call me with the zone->lock already held.
 */
static struct page *__rmqueue(struct zone *zone, unsigned int order)
{
	struct free_area * area;
	unsigned int current_order;
	struct page *page;

	for (current_order = order; current_order < MAX_ORDER; ++current_order) {
		area = zone->free_area + current_order;
		if (list_empty(&area->free_list))
			continue;

		page = list_entry(area->free_list.next, struct page, lru);
		list_del(&page->lru);
		rmv_page_order(page);
		area->nr_free--;
		zone->free_pages -= 1UL << order;
		return expand(zone, page, order, current_order, area);
	}

	return NULL;
}

/* 
 * Obtain a specified number of elements from the buddy allocator, all under
 * a single hold of the lock, for efficiency.  Add them to the supplied list.
 * Returns the number of new pages which were placed at *list.
 */
static int rmqueue_bulk(struct zone *zone, unsigned int order, 
			unsigned long count, struct list_head *list)
{
	int i;
	int allocated = 0;
	struct page *page;
	
Nick Piggin's avatar
Nick Piggin committed
543
	spin_lock(&zone->lock);
Linus Torvalds's avatar
Linus Torvalds committed
544
545
546
547
548
549
550
	for (i = 0; i < count; ++i) {
		page = __rmqueue(zone, order);
		if (page == NULL)
			break;
		allocated++;
		list_add_tail(&page->lru, list);
	}
Nick Piggin's avatar
Nick Piggin committed
551
	spin_unlock(&zone->lock);
Linus Torvalds's avatar
Linus Torvalds committed
552
553
554
	return allocated;
}

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
#ifdef CONFIG_NUMA
/* Called from the slab reaper to drain remote pagesets */
void drain_remote_pages(void)
{
	struct zone *zone;
	int i;
	unsigned long flags;

	local_irq_save(flags);
	for_each_zone(zone) {
		struct per_cpu_pageset *pset;

		/* Do not drain local pagesets */
		if (zone->zone_pgdat->node_id == numa_node_id())
			continue;

		pset = zone->pageset[smp_processor_id()];
		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
			struct per_cpu_pages *pcp;

			pcp = &pset->pcp[i];
			if (pcp->count)
				pcp->count -= free_pages_bulk(zone, pcp->count,
						&pcp->list, 0);
		}
	}
	local_irq_restore(flags);
}
#endif

Linus Torvalds's avatar
Linus Torvalds committed
585
586
587
#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
static void __drain_pages(unsigned int cpu)
{
Nick Piggin's avatar
Nick Piggin committed
588
	unsigned long flags;
Linus Torvalds's avatar
Linus Torvalds committed
589
590
591
592
593
594
	struct zone *zone;
	int i;

	for_each_zone(zone) {
		struct per_cpu_pageset *pset;

595
		pset = zone_pcp(zone, cpu);
Linus Torvalds's avatar
Linus Torvalds committed
596
597
598
599
		for (i = 0; i < ARRAY_SIZE(pset->pcp); i++) {
			struct per_cpu_pages *pcp;

			pcp = &pset->pcp[i];
Nick Piggin's avatar
Nick Piggin committed
600
			local_irq_save(flags);
Linus Torvalds's avatar
Linus Torvalds committed
601
602
			pcp->count -= free_pages_bulk(zone, pcp->count,
						&pcp->list, 0);
Nick Piggin's avatar
Nick Piggin committed
603
			local_irq_restore(flags);
Linus Torvalds's avatar
Linus Torvalds committed
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
		}
	}
}
#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */

#ifdef CONFIG_PM

void mark_free_pages(struct zone *zone)
{
	unsigned long zone_pfn, flags;
	int order;
	struct list_head *curr;

	if (!zone->spanned_pages)
		return;

	spin_lock_irqsave(&zone->lock, flags);
	for (zone_pfn = 0; zone_pfn < zone->spanned_pages; ++zone_pfn)
		ClearPageNosaveFree(pfn_to_page(zone_pfn + zone->zone_start_pfn));

	for (order = MAX_ORDER - 1; order >= 0; --order)
		list_for_each(curr, &zone->free_area[order].free_list) {
			unsigned long start_pfn, i;

			start_pfn = page_to_pfn(list_entry(curr, struct page, lru));

			for (i=0; i < (1<<order); i++)
				SetPageNosaveFree(pfn_to_page(start_pfn+i));
	}
	spin_unlock_irqrestore(&zone->lock, flags);
}

/*
 * Spill all of this CPU's per-cpu pages back into the buddy allocator.
 */
void drain_local_pages(void)
{
	unsigned long flags;

	local_irq_save(flags);	
	__drain_pages(smp_processor_id());
	local_irq_restore(flags);	
}
#endif /* CONFIG_PM */

static void zone_statistics(struct zonelist *zonelist, struct zone *z)
{
#ifdef CONFIG_NUMA
	unsigned long flags;
	int cpu;
	pg_data_t *pg = z->zone_pgdat;
	pg_data_t *orig = zonelist->zones[0]->zone_pgdat;
	struct per_cpu_pageset *p;

	local_irq_save(flags);
	cpu = smp_processor_id();
660
	p = zone_pcp(z,cpu);
Linus Torvalds's avatar
Linus Torvalds committed
661
	if (pg == orig) {
662
		p->numa_hit++;
Linus Torvalds's avatar
Linus Torvalds committed
663
664
	} else {
		p->numa_miss++;
665
		zone_pcp(zonelist->zones[0], cpu)->numa_foreign++;
Linus Torvalds's avatar
Linus Torvalds committed
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
	}
	if (pg == NODE_DATA(numa_node_id()))
		p->local_node++;
	else
		p->other_node++;
	local_irq_restore(flags);
#endif
}

/*
 * Free a 0-order page
 */
static void FASTCALL(free_hot_cold_page(struct page *page, int cold));
static void fastcall free_hot_cold_page(struct page *page, int cold)
{
	struct zone *zone = page_zone(page);
	struct per_cpu_pages *pcp;
	unsigned long flags;

	arch_free_page(page, 0);

	if (PageAnon(page))
		page->mapping = NULL;
689
690
691
692
693
694
	if (free_pages_check(__FUNCTION__, page))
		return;

	inc_page_state(pgfree);
	kernel_map_pages(page, 1, 0);

695
	pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
Linus Torvalds's avatar
Linus Torvalds committed
696
697
698
	local_irq_save(flags);
	list_add(&page->lru, &pcp->list);
	pcp->count++;
699
700
	if (pcp->count >= pcp->high)
		pcp->count -= free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
Linus Torvalds's avatar
Linus Torvalds committed
701
702
703
704
705
706
707
708
709
710
711
712
713
714
	local_irq_restore(flags);
	put_cpu();
}

void fastcall free_hot_page(struct page *page)
{
	free_hot_cold_page(page, 0);
}
	
void fastcall free_cold_page(struct page *page)
{
	free_hot_cold_page(page, 1);
}

715
static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
Linus Torvalds's avatar
Linus Torvalds committed
716
717
718
719
720
721
722
723
724
725
726
727
728
729
{
	int i;

	BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
	for(i = 0; i < (1 << order); i++)
		clear_highpage(page + i);
}

/*
 * Really, prep_compound_page() should be called from __rmqueue_bulk().  But
 * we cheat by calling it from here, in the order > 0 path.  Saves a branch
 * or two.
 */
static struct page *
730
buffered_rmqueue(struct zone *zone, int order, gfp_t gfp_flags)
Linus Torvalds's avatar
Linus Torvalds committed
731
732
{
	unsigned long flags;
733
	struct page *page;
Linus Torvalds's avatar
Linus Torvalds committed
734
735
	int cold = !!(gfp_flags & __GFP_COLD);

736
again:
Linus Torvalds's avatar
Linus Torvalds committed
737
738
739
	if (order == 0) {
		struct per_cpu_pages *pcp;

740
		page = NULL;
741
		pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
Linus Torvalds's avatar
Linus Torvalds committed
742
		local_irq_save(flags);
Nick Piggin's avatar
Nick Piggin committed
743
		if (!pcp->count)
Linus Torvalds's avatar
Linus Torvalds committed
744
745
			pcp->count += rmqueue_bulk(zone, 0,
						pcp->batch, &pcp->list);
Nick Piggin's avatar
Nick Piggin committed
746
		if (likely(pcp->count)) {
Linus Torvalds's avatar
Linus Torvalds committed
747
748
749
750
751
752
			page = list_entry(pcp->list.next, struct page, lru);
			list_del(&page->lru);
			pcp->count--;
		}
		local_irq_restore(flags);
		put_cpu();
Rohit Seth's avatar
Rohit Seth committed
753
	} else {
Linus Torvalds's avatar
Linus Torvalds committed
754
755
756
757
758
759
760
761
		spin_lock_irqsave(&zone->lock, flags);
		page = __rmqueue(zone, order);
		spin_unlock_irqrestore(&zone->lock, flags);
	}

	if (page != NULL) {
		BUG_ON(bad_range(zone, page));
		mod_page_state_zone(zone, pgalloc, 1 << order);
762
763
		if (prep_new_page(page, order))
			goto again;
Linus Torvalds's avatar
Linus Torvalds committed
764
765
766
767
768
769
770
771
772
773

		if (gfp_flags & __GFP_ZERO)
			prep_zero_page(page, order, gfp_flags);

		if (order && (gfp_flags & __GFP_COMP))
			prep_compound_page(page, order);
	}
	return page;
}

Rohit Seth's avatar
Rohit Seth committed
774
#define ALLOC_NO_WATERMARKS	0x01 /* don't check watermarks at all */
775
776
777
778
779
780
#define ALLOC_WMARK_MIN		0x02 /* use pages_min watermark */
#define ALLOC_WMARK_LOW		0x04 /* use pages_low watermark */
#define ALLOC_WMARK_HIGH	0x08 /* use pages_high watermark */
#define ALLOC_HARDER		0x10 /* try to alloc harder */
#define ALLOC_HIGH		0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET		0x40 /* check for correct cpuset */
Rohit Seth's avatar
Rohit Seth committed
781

Linus Torvalds's avatar
Linus Torvalds committed
782
783
784
785
786
/*
 * Return 1 if free pages are above 'mark'. This takes into account the order
 * of the allocation.
 */
int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
Rohit Seth's avatar
Rohit Seth committed
787
		      int classzone_idx, int alloc_flags)
Linus Torvalds's avatar
Linus Torvalds committed
788
789
790
791
792
{
	/* free_pages my go negative - that's OK */
	long min = mark, free_pages = z->free_pages - (1 << order) + 1;
	int o;

Rohit Seth's avatar
Rohit Seth committed
793
	if (alloc_flags & ALLOC_HIGH)
Linus Torvalds's avatar
Linus Torvalds committed
794
		min -= min / 2;
Rohit Seth's avatar
Rohit Seth committed
795
	if (alloc_flags & ALLOC_HARDER)
Linus Torvalds's avatar
Linus Torvalds committed
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
		min -= min / 4;

	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
		return 0;
	for (o = 0; o < order; o++) {
		/* At the next order, this order's pages become unavailable */
		free_pages -= z->free_area[o].nr_free << o;

		/* Require fewer higher order pages to be free */
		min >>= 1;

		if (free_pages <= min)
			return 0;
	}
	return 1;
}

Rohit Seth's avatar
Rohit Seth committed
813
814
815
816
817
818
819
/*
 * get_page_from_freeliest goes through the zonelist trying to allocate
 * a page.
 */
static struct page *
get_page_from_freelist(gfp_t gfp_mask, unsigned int order,
		struct zonelist *zonelist, int alloc_flags)
Martin Hicks's avatar
Martin Hicks committed
820
{
Rohit Seth's avatar
Rohit Seth committed
821
822
823
824
825
826
827
828
829
830
831
832
833
834
	struct zone **z = zonelist->zones;
	struct page *page = NULL;
	int classzone_idx = zone_idx(*z);

	/*
	 * Go through the zonelist once, looking for a zone with enough free.
	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
	 */
	do {
		if ((alloc_flags & ALLOC_CPUSET) &&
				!cpuset_zone_allowed(*z, gfp_mask))
			continue;

		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
835
836
837
838
839
840
841
842
			unsigned long mark;
			if (alloc_flags & ALLOC_WMARK_MIN)
				mark = (*z)->pages_min;
			else if (alloc_flags & ALLOC_WMARK_LOW)
				mark = (*z)->pages_low;
			else
				mark = (*z)->pages_high;
			if (!zone_watermark_ok(*z, order, mark,
Rohit Seth's avatar
Rohit Seth committed
843
844
845
846
847
848
849
850
851
852
853
				    classzone_idx, alloc_flags))
				continue;
		}

		page = buffered_rmqueue(*z, order, gfp_mask);
		if (page) {
			zone_statistics(zonelist, *z);
			break;
		}
	} while (*(++z) != NULL);
	return page;
Martin Hicks's avatar
Martin Hicks committed
854
855
}

Linus Torvalds's avatar
Linus Torvalds committed
856
857
858
859
/*
 * This is the 'heart' of the zoned buddy allocator.
 */
struct page * fastcall
860
__alloc_pages(gfp_t gfp_mask, unsigned int order,
Linus Torvalds's avatar
Linus Torvalds committed
861
862
		struct zonelist *zonelist)
{
Al Viro's avatar
Al Viro committed
863
	const gfp_t wait = gfp_mask & __GFP_WAIT;
Rohit Seth's avatar
Rohit Seth committed
864
	struct zone **z;
Linus Torvalds's avatar
Linus Torvalds committed
865
866
867
868
	struct page *page;
	struct reclaim_state reclaim_state;
	struct task_struct *p = current;
	int do_retry;
Rohit Seth's avatar
Rohit Seth committed
869
	int alloc_flags;
Linus Torvalds's avatar
Linus Torvalds committed
870
871
872
873
	int did_some_progress;

	might_sleep_if(wait);

874
restart:
Rohit Seth's avatar
Rohit Seth committed
875
	z = zonelist->zones;  /* the list of zones suitable for gfp_mask */
Linus Torvalds's avatar
Linus Torvalds committed
876

Rohit Seth's avatar
Rohit Seth committed
877
	if (unlikely(*z == NULL)) {
Linus Torvalds's avatar
Linus Torvalds committed
878
879
880
		/* Should this ever happen?? */
		return NULL;
	}
881

Rohit Seth's avatar
Rohit Seth committed
882
	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
883
				zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
Rohit Seth's avatar
Rohit Seth committed
884
885
	if (page)
		goto got_pg;
Linus Torvalds's avatar
Linus Torvalds committed
886

887
	do {
Rohit Seth's avatar
Rohit Seth committed
888
		wakeup_kswapd(*z, order);
889
	} while (*(++z));
Linus Torvalds's avatar
Linus Torvalds committed
890

891
	/*
Rohit Seth's avatar
Rohit Seth committed
892
893
894
895
896
897
898
	 * OK, we're below the kswapd watermark and have kicked background
	 * reclaim. Now things get more complex, so set up alloc_flags according
	 * to how we want to proceed.
	 *
	 * The caller may dip into page reserves a bit more if the caller
	 * cannot run direct reclaim, or if the caller has realtime scheduling
	 * policy.
899
	 */
900
	alloc_flags = ALLOC_WMARK_MIN;
Rohit Seth's avatar
Rohit Seth committed
901
902
903
904
	if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
		alloc_flags |= ALLOC_HARDER;
	if (gfp_mask & __GFP_HIGH)
		alloc_flags |= ALLOC_HIGH;
905
	alloc_flags |= ALLOC_CPUSET;
Linus Torvalds's avatar
Linus Torvalds committed
906
907
908

	/*
	 * Go through the zonelist again. Let __GFP_HIGH and allocations
Rohit Seth's avatar
Rohit Seth committed
909
	 * coming from realtime tasks go deeper into reserves.
Linus Torvalds's avatar
Linus Torvalds committed
910
911
912
	 *
	 * This is the last chance, in general, before the goto nopage.
	 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
913
	 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
Linus Torvalds's avatar
Linus Torvalds committed
914
	 */
Rohit Seth's avatar
Rohit Seth committed
915
916
917
	page = get_page_from_freelist(gfp_mask, order, zonelist, alloc_flags);
	if (page)
		goto got_pg;
Linus Torvalds's avatar
Linus Torvalds committed
918
919

	/* This allocation should allow future memory freeing. */
920
921
922
923

	if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE)))
			&& !in_interrupt()) {
		if (!(gfp_mask & __GFP_NOMEMALLOC)) {
Kirill Korotaev's avatar
Kirill Korotaev committed
924
nofail_alloc:
925
			/* go through the zonelist yet again, ignoring mins */
Rohit Seth's avatar
Rohit Seth committed
926
			page = get_page_from_freelist(gfp_mask, order,
927
				zonelist, ALLOC_NO_WATERMARKS);
Rohit Seth's avatar
Rohit Seth committed
928
929
			if (page)
				goto got_pg;
Kirill Korotaev's avatar
Kirill Korotaev committed
930
931
932
933
			if (gfp_mask & __GFP_NOFAIL) {
				blk_congestion_wait(WRITE, HZ/50);
				goto nofail_alloc;
			}
Linus Torvalds's avatar
Linus Torvalds committed
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
		}
		goto nopage;
	}

	/* Atomic allocations - we can't balance anything */
	if (!wait)
		goto nopage;

rebalance:
	cond_resched();

	/* We now go into synchronous reclaim */
	p->flags |= PF_MEMALLOC;
	reclaim_state.reclaimed_slab = 0;
	p->reclaim_state = &reclaim_state;

Rohit Seth's avatar
Rohit Seth committed
950
	did_some_progress = try_to_free_pages(zonelist->zones, gfp_mask);
Linus Torvalds's avatar
Linus Torvalds committed
951
952
953
954
955
956
957

	p->reclaim_state = NULL;
	p->flags &= ~PF_MEMALLOC;

	cond_resched();

	if (likely(did_some_progress)) {
Rohit Seth's avatar
Rohit Seth committed
958
959
960
961
		page = get_page_from_freelist(gfp_mask, order,
						zonelist, alloc_flags);
		if (page)
			goto got_pg;
Linus Torvalds's avatar
Linus Torvalds committed
962
963
964
965
966
967
968
	} else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) {
		/*
		 * Go through the zonelist yet one more time, keep
		 * very high watermark here, this is only to catch
		 * a parallel oom killing, we must fail if we're still
		 * under heavy pressure.
		 */
Rohit Seth's avatar
Rohit Seth committed
969
		page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
970
				zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
Rohit Seth's avatar
Rohit Seth committed
971
972
		if (page)
			goto got_pg;
Linus Torvalds's avatar
Linus Torvalds committed
973

974
		out_of_memory(gfp_mask, order);
Linus Torvalds's avatar
Linus Torvalds committed
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
		goto restart;
	}

	/*
	 * Don't let big-order allocations loop unless the caller explicitly
	 * requests that.  Wait for some write requests to complete then retry.
	 *
	 * In this implementation, __GFP_REPEAT means __GFP_NOFAIL for order
	 * <= 3, but that may not be true in other implementations.
	 */
	do_retry = 0;
	if (!(gfp_mask & __GFP_NORETRY)) {
		if ((order <= 3) || (gfp_mask & __GFP_REPEAT))
			do_retry = 1;
		if (gfp_mask & __GFP_NOFAIL)
			do_retry = 1;
	}
	if (do_retry) {
		blk_congestion_wait(WRITE, HZ/50);
		goto rebalance;
	}

nopage:
	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
		printk(KERN_WARNING "%s: page allocation failure."
			" order:%d, mode:0x%x\n",
			p->comm, order, gfp_mask);
		dump_stack();
Janet Morgan's avatar
Janet Morgan committed
1003
		show_mem();
Linus Torvalds's avatar
Linus Torvalds committed
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
	}
got_pg:
	return page;
}

EXPORT_SYMBOL(__alloc_pages);

/*
 * Common helper functions.
 */
1014
fastcall unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
Linus Torvalds's avatar
Linus Torvalds committed
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
{
	struct page * page;
	page = alloc_pages(gfp_mask, order);
	if (!page)
		return 0;
	return (unsigned long) page_address(page);
}

EXPORT_SYMBOL(__get_free_pages);

1025
fastcall unsigned long get_zeroed_page(gfp_t gfp_mask)
Linus Torvalds's avatar
Linus Torvalds committed
1026
1027
1028
1029
1030
1031
1032
{
	struct page * page;

	/*
	 * get_zeroed_page() returns a 32-bit address, which cannot represent
	 * a highmem page
	 */
Al Viro's avatar
Al Viro committed
1033
	BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
Linus Torvalds's avatar
Linus Torvalds committed
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052

	page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
	if (page)
		return (unsigned long) page_address(page);
	return 0;
}

EXPORT_SYMBOL(get_zeroed_page);

void __pagevec_free(struct pagevec *pvec)
{
	int i = pagevec_count(pvec);

	while (--i >= 0)
		free_hot_cold_page(pvec->pages[i], pvec->cold);
}

fastcall void __free_pages(struct page *page, unsigned int order)
{
Nick Piggin's avatar
Nick Piggin committed
1053
	if (put_page_testzero(page)) {
Linus Torvalds's avatar
Linus Torvalds committed
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
		if (order == 0)
			free_hot_page(page);
		else
			__free_pages_ok(page, order);
	}
}

EXPORT_SYMBOL(__free_pages);

fastcall void free_pages(unsigned long addr, unsigned int order)
{
	if (addr != 0) {
		BUG_ON(!virt_addr_valid((void *)addr));
		__free_pages(virt_to_page((void *)addr), order);
	}
}

EXPORT_SYMBOL(free_pages);

/*
 * Total amount of free (allocatable) RAM:
 */
unsigned int nr_free_pages(void)
{
	unsigned int sum = 0;
	struct zone *zone;

	for_each_zone(zone)
		sum += zone->free_pages;

	return sum;
}

EXPORT_SYMBOL(nr_free_pages);

#ifdef CONFIG_NUMA
unsigned int nr_free_pages_pgdat(pg_data_t *pgdat)
{
	unsigned int i, sum = 0;

	for (i = 0; i < MAX_NR_ZONES; i++)
		sum += pgdat->node_zones[i].free_pages;

	return sum;
}
#endif

static unsigned int nr_free_zone_pages(int offset)
{
1103
1104
	/* Just pick one node, since fallback list is circular */
	pg_data_t *pgdat = NODE_DATA(numa_node_id());
Linus Torvalds's avatar
Linus Torvalds committed
1105
1106
	unsigned int sum = 0;

1107
1108
1109
	struct zonelist *zonelist = pgdat->node_zonelists + offset;
	struct zone **zonep = zonelist->zones;
	struct zone *zone;
Linus Torvalds's avatar
Linus Torvalds committed
1110

1111
1112
1113
1114
1115
	for (zone = *zonep++; zone; zone = *zonep++) {
		unsigned long size = zone->present_pages;
		unsigned long high = zone->pages_high;
		if (size > high)
			sum += size - high;
Linus Torvalds's avatar
Linus Torvalds committed
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
	}

	return sum;
}

/*
 * Amount of free RAM allocatable within ZONE_DMA and ZONE_NORMAL
 */
unsigned int nr_free_buffer_pages(void)
{
Al Viro's avatar
Al Viro committed
1126
	return nr_free_zone_pages(gfp_zone(GFP_USER));
Linus Torvalds's avatar
Linus Torvalds committed
1127
1128
1129
1130
1131
1132
1133
}

/*
 * Amount of free RAM allocatable within all zones
 */
unsigned int nr_free_pagecache_pages(void)
{
Al Viro's avatar
Al Viro committed
1134
	return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER));
Linus Torvalds's avatar
Linus Torvalds committed
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
}

#ifdef CONFIG_HIGHMEM
unsigned int nr_free_highpages (void)
{
	pg_data_t *pgdat;
	unsigned int pages = 0;

	for_each_pgdat(pgdat)
		pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;

	return pages;
}
#endif

#ifdef CONFIG_NUMA
static void show_node(struct zone *zone)
{
	printk("Node %d ", zone->zone_pgdat->node_id);
}
#else
#define show_node(zone)	do { } while (0)
#endif

/*
 * Accumulate the page_state information across all CPUs.
 * The result is unavoidably approximate - it can change
 * during and after execution of this function.
 */
static DEFINE_PER_CPU(struct page_state, page_states) = {0};

atomic_t nr_pagecache = ATOMIC_INIT(0);
EXPORT_SYMBOL(nr_pagecache);
#ifdef CONFIG_SMP
DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
#endif

Nick Piggin's avatar
Nick Piggin committed
1172
static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
Linus Torvalds's avatar
Linus Torvalds committed
1173
1174
1175
1176
1177
{
	int cpu = 0;

	memset(ret, 0, sizeof(*ret));

1178
	cpu = first_cpu(*cpumask);
Linus Torvalds's avatar
Linus Torvalds committed
1179
1180
1181
1182
1183
	while (cpu < NR_CPUS) {
		unsigned long *in, *out, off;

		in = (unsigned long *)&per_cpu(page_states, cpu);

1184
		cpu = next_cpu(cpu, *cpumask);
Linus Torvalds's avatar
Linus Torvalds committed
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194

		if (cpu < NR_CPUS)
			prefetch(&per_cpu(page_states, cpu));

		out = (unsigned long *)ret;
		for (off = 0; off < nr; off++)
			*out++ += *in++;
	}
}

1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
void get_page_state_node(struct page_state *ret, int node)
{
	int nr;
	cpumask_t mask = node_to_cpumask(node);

	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
	nr /= sizeof(unsigned long);

	__get_page_state(ret, nr+1, &mask);
}

Linus Torvalds's avatar
Linus Torvalds committed
1206
1207
1208
void get_page_state(struct page_state *ret)
{
	int nr;
1209
	cpumask_t mask = CPU_MASK_ALL;
Linus Torvalds's avatar
Linus Torvalds committed
1210
1211
1212
1213

	nr = offsetof(struct page_state, GET_PAGE_STATE_LAST);
	nr /= sizeof(unsigned long);

1214
	__get_page_state(ret, nr + 1, &mask);
Linus Torvalds's avatar
Linus Torvalds committed
1215
1216
1217
1218
}

void get_full_page_state(struct page_state *ret)
{
1219
1220
1221
	cpumask_t mask = CPU_MASK_ALL;

	__get_page_state(ret, sizeof(*ret) / sizeof(unsigned long), &mask);
Linus Torvalds's avatar
Linus Torvalds committed
1222
1223
}

1224
unsigned long __read_page_state(unsigned long offset)
Linus Torvalds's avatar
Linus Torvalds committed
1225
1226
1227
1228
{
	unsigned long ret = 0;
	int cpu;

Nick Piggin's avatar
Nick Piggin committed
1229
	for_each_cpu(cpu) {
Linus Torvalds's avatar
Linus Torvalds committed
1230
1231
1232
1233
1234
1235
1236
1237
		unsigned long in;

		in = (unsigned long)&per_cpu(page_states, cpu) + offset;
		ret += *((unsigned long *)in);
	}
	return ret;
}

1238
void __mod_page_state(unsigned long offset, unsigned long delta)
Linus Torvalds's avatar
Linus Torvalds committed
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
{
	unsigned long flags;
	void* ptr;

	local_irq_save(flags);
	ptr = &__get_cpu_var(page_states);
	*(unsigned long*)(ptr + offset) += delta;
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__mod_page_state);

void __get_zone_counts(unsigned long *active, unsigned long *inactive,
			unsigned long *free, struct pglist_data *pgdat)
{
	struct zone *zones = pgdat->node_zones;
	int i;

	*active = 0;
	*inactive = 0;
	*free = 0;
	for (i = 0; i < MAX_NR_ZONES; i++) {
		*active += zones[i].nr_active;
		*inactive += zones[i].nr_inactive;
		*free += zones[i].free_pages;
	}
}

void get_zone_counts(unsigned long *active,
		unsigned long *inactive, unsigned long *free)
{
	struct pglist_data *pgdat;

	*active = 0;
	*inactive = 0;
	*free = 0;
	for_each_pgdat(pgdat) {
		unsigned long l, m, n;
		__get_zone_counts(&l, &m, &n, pgdat);
		*active += l;
		*inactive += m;
		*free += n;
	}
}

void si_meminfo(struct sysinfo *val)
{
	val->totalram = totalram_pages;
	val->sharedram = 0;
	val->freeram = nr_free_pages();
	val->bufferram = nr_blockdev_pages();
#ifdef CONFIG_HIGHMEM
	val->totalhigh = totalhigh_pages;
	val->freehigh = nr_free_highpages();
#else
	val->totalhigh = 0;
	val->freehigh = 0;
#endif
	val->mem_unit = PAGE_SIZE;
}

EXPORT_SYMBOL(si_meminfo);

#ifdef CONFIG_NUMA
void si_meminfo_node(struct sysinfo *val, int nid)
{
	pg_data_t *pgdat = NODE_DATA(nid);

	val->totalram = pgdat->node_present_pages;
	val->freeram = nr_free_pages_pgdat(pgdat);
	val->totalhigh = pgdat->node_zones[ZONE_HIGHMEM].present_pages;
	val->freehigh = pgdat->node_zones[ZONE_HIGHMEM].free_pages;
	val->mem_unit = PAGE_SIZE;
}
#endif

#define K(x) ((x) << (PAGE_SHIFT-10))

/*
 * Show free area list (used inside shift_scroll-lock stuff)
 * We also calculate the percentage fragmentation. We do this by counting the
 * memory on each free list with the exception of the first item on the list.
 */
void show_free_areas(void)
{
	struct page_state ps;
	int cpu, temperature;
	unsigned long active;
	unsigned long inactive;
	unsigned long free;
	struct zone *zone;

	for_each_zone(zone) {
		show_node(zone);
		printk("%s per-cpu:", zone->name);

		if (!zone->present_pages) {
			printk(" empty\n");
			continue;
		} else
			printk("\n");

1341
		for_each_online_cpu(cpu) {
Linus Torvalds's avatar
Linus Torvalds committed
1342
1343
			struct per_cpu_pageset *pageset;

1344
			pageset = zone_pcp(zone, cpu);
Linus Torvalds's avatar
Linus Torvalds committed
1345
1346

			for (temperature = 0; temperature < 2; temperature++)
Nick Piggin's avatar
Nick Piggin committed
1347
				printk("cpu %d %s: high %d, batch %d used:%d\n",
Linus Torvalds's avatar
Linus Torvalds committed
1348
1349
1350
					cpu,
					temperature ? "cold" : "hot",
					pageset->pcp[temperature].high,
1351
1352
					pageset->pcp[temperature].batch,
					pageset->pcp[temperature].count);
Linus Torvalds's avatar
Linus Torvalds committed
1353
1354
1355
1356
1357
1358
		}
	}

	get_page_state(&ps);
	get_zone_counts(&active, &inactive, &free);

Denis Vlasenko's avatar
Denis Vlasenko committed
1359
	printk("Free pages: %11ukB (%ukB HighMem)\n",
Linus Torvalds's avatar
Linus Torvalds committed
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
		K(nr_free_pages()),
		K(nr_free_highpages()));

	printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu "
		"unstable:%lu free:%u slab:%lu mapped:%lu pagetables:%lu\n",
		active,
		inactive,
		ps.nr_dirty,
		ps.nr_writeback,
		ps.nr_unstable,
		nr_free_pages(),
		ps.nr_slab,
		ps.nr_mapped,
		ps.nr_page_table_pages);

	for_each_zone(zone) {
		int i;

		show_node(zone);
		printk("%s"
			" free:%lukB"
			" min:%lukB"
			" low:%lukB"
			" high:%lukB"
			" active:%lukB"
			" inactive:%lukB"
			" present:%lukB"
			" pages_scanned:%lu"
			" all_unreclaimable? %s"
			"\n",
			zone->name,
			K(zone->free_pages),
			K(zone->pages_min),
			K(zone->pages_low),
			K(zone->pages_high),
			K(zone->nr_active),
			K(zone->nr_inactive),
			K(zone->present_pages),
			zone->pages_scanned,
			(zone->all_unreclaimable ? "yes" : "no")
			);
		printk("lowmem_reserve[]:");
		for (i = 0; i < MAX_NR_ZONES; i++)
			printk(" %lu", zone->lowmem_reserve[i]);
		printk("\n");
	}

	for_each_zone(zone) {
 		unsigned long nr, flags, order, total = 0;

		show_node(zone);
		printk("%s: ", zone->name);
		if (!zone->present_pages) {
			printk("empty\n");
			continue;
		}

		spin_lock_irqsave(&zone->lock, flags);
		for (order = 0; order < MAX_ORDER; order++) {
			nr = zone->free_area[order].nr_free;
			total += nr << order;
			printk("%lu*%lukB ", nr, K(1UL) << order);
		}
		spin_unlock_irqrestore(&zone->lock, flags);
		printk("= %lukB\n", K(total));
	}

	show_swap_cache_info();
}

/*
 * Builds allocation fallback zone lists.
 */
static int __init build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, int j, int k)
{
	switch (k) {
		struct zone *zone;
	default:
		BUG();
	case ZONE_HIGHMEM:
		zone = pgdat->node_zones + ZONE_HIGHMEM;
		if (zone->present_pages) {
#ifndef CONFIG_HIGHMEM
			BUG();
#endif
			zonelist->zones[j++] = zone;
		}
	case ZONE_NORMAL:
		zone = pgdat->node_zones + ZONE_NORMAL;
		if (zone->present_pages)
			zonelist->zones[j++] = zone;
1451
1452
1453
1454
	case ZONE_DMA32:
		zone = pgdat->node_zones + ZONE_DMA32;
		if (zone->present_pages)
			zonelist->zones[j++] = zone;
Linus Torvalds's avatar
Linus Torvalds committed
1455
1456
1457
1458
1459
1460
1461
1462
1463
	case ZONE_DMA:
		zone = pgdat->node_zones + ZONE_DMA;
		if (zone->present_pages)
			zonelist->zones[j++] = zone;
	}

	return j;
}

Al Viro's avatar
Al Viro committed
1464
1465
1466
1467
1468
static inline int highest_zone(int zone_bits)
{
	int res = ZONE_NORMAL;
	if (zone_bits & (__force int)__GFP_HIGHMEM)
		res = ZONE_HIGHMEM;
1469
1470
	if (zone_bits & (__force int)__GFP_DMA32)
		res = ZONE_DMA32;
Al Viro's avatar
Al Viro committed
1471
1472
1473
1474
1475
	if (zone_bits & (__force int)__GFP_DMA)
		res = ZONE_DMA;
	return res;
}

Linus Torvalds's avatar
Linus Torvalds committed
1476
1477
1478
1479
#ifdef CONFIG_NUMA
#define MAX_NODE_LOAD (num_online_nodes())
static int __initdata node_load[MAX_NUMNODES];
/**
1480
 * find_next_best_node - find the next node that should appear in a given node's fallback list
Linus Torvalds's avatar
Linus Torvalds committed
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
 * @node: node whose fallback list we're appending
 * @used_node_mask: nodemask_t of already used nodes
 *
 * We use a number of factors to determine which is the next node that should
 * appear on a given node's fallback list.  The node should not have appeared
 * already in @node's fallback list, and it should be the next closest node
 * according to the distance array (which contains arbitrary distance values
 * from each node to each node in the system), and should also prefer nodes
 * with no CPUs, since presumably they'll have very little allocation pressure
 * on them otherwise.
 * It returns -1 if no node is found.
 */
static int __init find_next_best_node(int node, nodemask_t *used_node_mask)
{
	int i, n, val;
	int min_val = INT_MAX;
	int best_node = -1;

	for_each_online_node(i) {
		cpumask_t tmp;

		/* Start from local node */
		n = (node+i) % num_online_nodes();

		/* Don't want a node to appear more than once */
		if (node_isset(n, *used_node_mask))
			continue;

		/* Use the local node if we haven't already */
		if (!node_isset(node, *used_node_mask)) {
			best_node = node;
			break;
		}

		/* Use the distance array to find the distance */
		val = node_distance(node, n);

		/* Give preference to headless and unused nodes */
		tmp = node_to_cpumask(n);
		if (!cpus_empty(tmp))
			val += PENALTY_FOR_NODE_WITH_CPUS;

		/* Slight preference for less loaded node */
		val *= (MAX_NODE_LOAD*MAX_NUMNODES);
		val += node_load[n];

		if (val < min_val) {
			min_val = val;
			best_node = n;
		}
	}

	if (best_node >= 0)
		node_set(best_node, *used_node_mask);

	return best_node;
}

static void __init build_zonelists(pg_data_t *pgdat)
{
	int i, j, k, node, local_node;
	int prev_node, load;
	struct zonelist *zonelist;
	nodemask_t used_mask;

	/* initialize zonelists */
	for (i = 0; i < GFP_ZONETYPES; i++) {
		zonelist = pgdat->node_zonelists + i;
		zonelist->zones[0] = NULL;
	}

	/* NUMA-aware ordering of nodes */
	local_node = pgdat->node_id;
	load = num_online_nodes();
	prev_node = local_node;
	nodes_clear(used_mask);
	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
		/*
		 * We don't want to pressure a particular node.
		 * So adding penalty to the first node in same
		 * distance group to make it round-robin.
		 */
		if (node_distance(local_node, node) !=
				node_distance(local_node, prev_node))
			node_load[node] += load;
		prev_node = node;
		load--;
		for (i = 0; i < GFP_ZONETYPES; i++) {
			zonelist = pgdat->node_zonelists + i;
			for (j = 0; zonelist->zones[j] != NULL; j++);

Al Viro's avatar
Al Viro committed
1572
			k = highest_zone(i);
Linus Torvalds's avatar
Linus Torvalds committed
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592

	 		j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
			zonelist->zones[j] = NULL;
		}
	}
}

#else	/* CONFIG_NUMA */

static void __init build_zonelists(pg_data_t *pgdat)
{
	int i, j, k, node, local_node;

	local_node = pgdat->node_id;
	for (i = 0; i < GFP_ZONETYPES; i++) {
		struct zonelist *zonelist;

		zonelist = pgdat->node_zonelists + i;

		j = 0;
Al Viro's avatar
Al Viro committed
1593
		k = highest_zone(i);
Linus Torvalds's avatar
Linus Torvalds committed
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
 		j = build_zonelists_node(pgdat, zonelist, j, k);
 		/*
 		 * Now we build the zonelist so that it contains the zones
 		 * of all the other nodes.
 		 * We don't want to pressure a particular node, so when
 		 * building the zones for node N, we make sure that the
 		 * zones coming right after the local ones are those from
 		 * node N+1 (modulo N)
 		 */
		for (node = local_node + 1; node < MAX_NUMNODES; node++) {
			if (!node_online(node))
				continue;
			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
		}
		for (node = 0; node < local_node; node++) {
			if (!node_online(node))
				continue;
			j = build_zonelists_node(NODE_DATA(node), zonelist, j, k);
		}

		zonelist->zones[j] = NULL;
	}
}

#endif	/* CONFIG_NUMA */

void __init build_all_zonelists(void)
{
	int i;

	for_each_online_node(i)
		build_zonelists(NODE_DATA(i));
	printk("Built %i zonelists\n", num_online_nodes());
	cpuset_init_current_mems_allowed();
}

/*
 * Helper functions to size the waitqueue hash table.
 * Essentially these want to choose hash table sizes sufficiently
 * large so that collisions trying to wait on pages are rare.
 * But in fact, the number of active page waitqueues on typical
 * systems is ridiculously low, less than 200. So this is even
 * conservative, even though it seems large.
 *
 * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
 * waitqueues, i.e. the size of the waitq table given the number of pages.
 */
#define PAGES_PER_WAITQUEUE	256

static inline unsigned long wait_table_size(unsigned long pages)
{
	unsigned long size = 1;

	pages /= PAGES_PER_WAITQUEUE;

	while (size < pages)
		size <<= 1;

	/*
	 * Once we have dozens or even hundreds of threads sleeping
	 * on IO we've got bigger problems than wait queue collision.
	 * Limit the size of the wait table to a reasonable size.
	 */
	size = min(size, 4096UL);

	return max(size, 4UL);
}

/*
 * This is an integer logarithm so that shifts can be used later
 * to extract the more random high bits from the multiplicative
 * hash function before the remainder is taken.
 */
static inline unsigned long wait_table_bits(unsigned long size)
{
	return ffz(~size);
}

#define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1))

static void __init calculate_zone_totalpages(struct pglist_data *pgdat,
		unsigned long *zones_size, unsigned long *zholes_size)
{
	unsigned long realtotalpages, totalpages = 0;
	int i;

	for (i = 0; i < MAX_NR_ZONES; i++)
		totalpages += zones_size[i];
	pgdat->node_spanned_pages = totalpages;

	realtotalpages = totalpages;
	if (zholes_size)
		for (i = 0; i < MAX_NR_ZONES; i++)
			realtotalpages -= zholes_size[i];
	pgdat->node_present_pages = realtotalpages;
	printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages);
}


/*
 * Initially all pages are reserved - free ones are freed
 * up by free_all_bootmem() once the early boot process is
 * done. Non-atomic initialization, single-pass.
 */
1698
void __devinit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
Linus Torvalds's avatar
Linus Torvalds committed
1699
1700
1701
		unsigned long start_pfn)
{
	struct page *page;
1702
1703
	unsigned long end_pfn = start_pfn + size;
	unsigned long pfn;
Linus Torvalds's avatar
Linus Torvalds committed
1704

1705
1706
1707
1708
1709
	for (pfn = start_pfn; pfn < end_pfn; pfn++, page++) {
		if (!early_pfn_valid(pfn))
			continue;
		page = pfn_to_page(pfn);
		set_page_links(page, zone, nid, pfn);
Nick Piggin's avatar
Nick Piggin committed
1710
		set_page_count(page, 1);
Linus Torvalds's avatar
Linus Torvalds committed
1711
1712
1713
1714
1715
1716
		reset_page_mapcount(page);
		SetPageReserved(page);
		INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
		/* The shift won't overflow because ZONE_NORMAL is below 4G. */
		if (!is_highmem_idx(zone))
1717
			set_page_address(page, __va(pfn << PAGE_SHIFT));
Linus Torvalds's avatar
Linus Torvalds committed
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
#endif
	}
}

void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone,
				unsigned long size)
{
	int order;
	for (order = 0; order < MAX_ORDER ; order++) {
		INIT_LIST_HEAD(&zone->free_area[order].free_list);
		zone->free_area[order].nr_free = 0;
	}
}

1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
#define ZONETABLE_INDEX(x, zone_nr)	((x << ZONES_SHIFT) | zone_nr)
void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn,
		unsigned long size)
{
	unsigned long snum = pfn_to_section_nr(pfn);
	unsigned long end = pfn_to_section_nr(pfn + size);

	if (FLAGS_HAS_NODE)
		zone_table[ZONETABLE_INDEX(nid, zid)] = zone;
	else
		for (; snum <= end; snum++)
			zone_table[ZONETABLE_INDEX(snum, zid)] = zone;
}

Linus Torvalds's avatar
Linus Torvalds committed
1746
1747
1748
1749
1750
#ifndef __HAVE_ARCH_MEMMAP_INIT
#define memmap_init(size, nid, zone, start_pfn) \
	memmap_init_zone((size), (nid), (zone), (start_pfn))
#endif