aboutsummaryrefslogtreecommitdiffstats
path: root/mm/bootmem.c
blob: e5415a5414a54c387dcd2a5550235a0ee02debab (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
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
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
/*
 *  bootmem - A boot-time physical memory allocator and configurator
 *
 *  Copyright (C) 1999 Ingo Molnar
 *                1999 Kanoj Sarcar, SGI
 *                2008 Johannes Weiner
 *
 * Access to this subsystem has to be serialized externally (which is true
 * for the boot process anyway).
 */
#include <linux/init.h>
#include <linux/pfn.h>
#include <linux/bootmem.h>
#include <linux/module.h>

#include <asm/bug.h>
#include <asm/io.h>
#include <asm/processor.h>

#include "internal.h"

unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;

#ifdef CONFIG_CRASH_DUMP
/*
 * If we have booted due to a crash, max_pfn will be a very low value. We need
 * to know the amount of memory that the previous kernel used.
 */
unsigned long saved_max_pfn;
#endif

bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;

static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);

static int bootmem_debug;

static int __init bootmem_debug_setup(char *buf)
{
	bootmem_debug = 1;
	return 0;
}
early_param("bootmem_debug", bootmem_debug_setup);

#define bdebug(fmt, args...) ({				\
	if (unlikely(bootmem_debug))			\
		printk(KERN_INFO			\
			"bootmem::%s " fmt,		\
			__FUNCTION__, ## args);		\
})

static unsigned long __init bootmap_bytes(unsigned long pages)
{
	unsigned long bytes = (pages + 7) / 8;

	return ALIGN(bytes, sizeof(long));
}

/**
 * bootmem_bootmap_pages - calculate bitmap size in pages
 * @pages: number of pages the bitmap has to represent
 */
unsigned long __init bootmem_bootmap_pages(unsigned long pages)
{
	unsigned long bytes = bootmap_bytes(pages);

	return PAGE_ALIGN(bytes) >> PAGE_SHIFT;
}

/*
 * link bdata in order
 */
static void __init link_bootmem(bootmem_data_t *bdata)
{
	struct list_head *iter;

	list_for_each(iter, &bdata_list) {
		bootmem_data_t *ent;

		ent = list_entry(iter, bootmem_data_t, list);
		if (bdata->node_boot_start < ent->node_boot_start)
			break;
	}
	list_add_tail(&bdata->list, iter);
}

/*
 * Called once to set up the allocator itself.
 */
static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
	unsigned long mapstart, unsigned long start, unsigned long end)
{
	unsigned long mapsize;

	mminit_validate_memmodel_limits(&start, &end);
	bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
	bdata->node_boot_start = PFN_PHYS(start);
	bdata->node_low_pfn = end;
	link_bootmem(bdata);

	/*
	 * Initially all pages are reserved - setup_arch() has to
	 * register free RAM areas explicitly.
	 */
	mapsize = bootmap_bytes(end - start);
	memset(bdata->node_bootmem_map, 0xff, mapsize);

	bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n",
		bdata - bootmem_node_data, start, mapstart, end, mapsize);

	return mapsize;
}

/**
 * init_bootmem_node - register a node as boot memory
 * @pgdat: node to register
 * @freepfn: pfn where the bitmap for this node is to be placed
 * @startpfn: first pfn on the node
 * @endpfn: first pfn after the node
 *
 * Returns the number of bytes needed to hold the bitmap for this node.
 */
unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
				unsigned long startpfn, unsigned long endpfn)
{
	return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn);
}

/**
 * init_bootmem - register boot memory
 * @start: pfn where the bitmap is to be placed
 * @pages: number of available physical pages
 *
 * Returns the number of bytes needed to hold the bitmap.
 */
unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
{
	max_low_pfn = pages;
	min_low_pfn = start;
	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
}

static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
{
	int aligned;
	struct page *page;
	unsigned long start, end, pages, count = 0;

	if (!bdata->node_bootmem_map)
		return 0;

	start = PFN_DOWN(bdata->node_boot_start);
	end = bdata->node_low_pfn;

	/*
	 * If the start is aligned to the machines wordsize, we might
	 * be able to free pages in bulks of that order.
	 */
	aligned = !(start & (BITS_PER_LONG - 1));

	bdebug("nid=%td start=%lx end=%lx aligned=%d\n",
		bdata - bootmem_node_data, start, end, aligned);

	while (start < end) {
		unsigned long *map, idx, vec;

		map = bdata->node_bootmem_map;
		idx = start - PFN_DOWN(bdata->node_boot_start);
		vec = ~map[idx / BITS_PER_LONG];

		if (aligned && vec == ~0UL && start + BITS_PER_LONG < end) {
			int order = ilog2(BITS_PER_LONG);

			__free_pages_bootmem(pfn_to_page(start), order);
			count += BITS_PER_LONG;
		} else {
			unsigned long off = 0;

			while (vec && off < BITS_PER_LONG) {
				if (vec & 1) {
					page = pfn_to_page(start + off);
					__free_pages_bootmem(page, 0);
					count++;
				}
				vec >>= 1;
				off++;
			}
		}
		start += BITS_PER_LONG;
	}

	page = virt_to_page(bdata->node_bootmem_map);
	pages = bdata->node_low_pfn - PFN_DOWN(bdata->node_boot_start);
	pages = bootmem_bootmap_pages(pages);
	count += pages;
	while (pages--)
		__free_pages_bootmem(page++, 0);

	bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);

	return count;
}

/**
 * free_all_bootmem_node - release a node's free pages to the buddy allocator
 * @pgdat: node to be released
 *
 * Returns the number of pages actually released.
 */
unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
{
	register_page_bootmem_info_node(pgdat);
	return free_all_bootmem_core(pgdat->bdata);
}

/**
 * free_all_bootmem - release free pages to the buddy allocator
 *
 * Returns the number of pages actually released.
 */
unsigned long __init free_all_bootmem(void)
{
	return free_all_bootmem_core(NODE_DATA(0)->bdata);
}

static void __init __free(bootmem_data_t *bdata,
			unsigned long sidx, unsigned long eidx)
{
	unsigned long idx;

	bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data,
		sidx + PFN_DOWN(bdata->node_boot_start),
		eidx + PFN_DOWN(bdata->node_boot_start));

	if (bdata->hint_idx > sidx)
		bdata->hint_idx = sidx;

	for (idx = sidx; idx < eidx; idx++)
		if (!test_and_clear_bit(idx, bdata->node_bootmem_map))
			BUG();
}

static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
			unsigned long eidx, int flags)
{
	unsigned long idx;
	int exclusive = flags & BOOTMEM_EXCLUSIVE;

	bdebug("nid=%td start=%lx end=%lx flags=%x\n",
		bdata - bootmem_node_data,
		sidx + PFN_DOWN(bdata->node_boot_start),
		eidx + PFN_DOWN(bdata->node_boot_start),
		flags);

	for (idx = sidx; idx < eidx; idx++)
		if (test_and_set_bit(idx, bdata->node_bootmem_map)) {
			if (exclusive) {
				__free(bdata, sidx, idx);
				return -EBUSY;
			}
			bdebug("silent double reserve of PFN %lx\n",
				idx + PFN_DOWN(bdata->node_boot_start));
		}
	return 0;
}

static int __init mark_bootmem_node(bootmem_data_t *bdata,
				unsigned long start, unsigned long end,
				int reserve, int flags)
{
	unsigned long sidx, eidx;

	bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n",
		bdata - bootmem_node_data, start, end, reserve, flags);

	BUG_ON(start < PFN_DOWN(bdata->node_boot_start));
	BUG_ON(end > bdata->node_low_pfn);

	sidx = start - PFN_DOWN(bdata->node_boot_start);
	eidx = end - PFN_DOWN(bdata->node_boot_start);

	if (reserve)
		return __reserve(bdata, sidx, eidx, flags);
	else
		__free(bdata, sidx, eidx);
	return 0;
}

static int __init mark_bootmem(unsigned long start, unsigned long end,
				int reserve, int flags)
{
	unsigned long pos;
	bootmem_data_t *bdata;

	pos = start;
	list_for_each_entry(bdata, &bdata_list, list) {
		int err;
		unsigned long max;

		if (pos < PFN_DOWN(bdata->node_boot_start)) {
			BUG_ON(pos != start);
			continue;
		}

		max = min(bdata->node_low_pfn, end);

		err = mark_bootmem_node(bdata, pos, max, reserve, flags);
		if (reserve && err) {
			mark_bootmem(start, pos, 0, 0);
			return err;
		}

		if (max == end)
			return 0;
		pos = bdata->node_low_pfn;
	}
	BUG();
}

/**
 * free_bootmem_node - mark a page range as usable
 * @pgdat: node the range resides on
 * @physaddr: starting address of the range
 * @size: size of the range in bytes
 *
 * Partial pages will be considered reserved and left as they are.
 *
 * The range must reside completely on the specified node.
 */
void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
			      unsigned long size)
{
	unsigned long start, end;

	start = PFN_UP(physaddr);
	end = PFN_DOWN(physaddr + size);

	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
}

/**
 * free_bootmem - mark a page range as usable
 * @addr: starting address of the range
 * @size: size of the range in bytes
 *
 * Partial pages will be considered reserved and left as they are.
 *
 * The range must be contiguous but may span node boundaries.
 */
void __init free_bootmem(unsigned long addr, unsigned long size)
{
	unsigned long start, end;

	start = PFN_UP(addr);
	end = PFN_DOWN(addr + size);

	mark_bootmem(start, end, 0, 0);
}

/**
 * reserve_bootmem_node - mark a page range as reserved
 * @pgdat: node the range resides on
 * @physaddr: starting address of the range
 * @size: size of the range in bytes
 * @flags: reservation flags (see linux/bootmem.h)
 *
 * Partial pages will be reserved.
 *
 * The range must reside completely on the specified node.
 */
int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
				 unsigned long size, int flags)
{
	unsigned long start, end;

	start = PFN_DOWN(physaddr);
	end = PFN_UP(physaddr + size);

	return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
}

#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
/**
 * reserve_bootmem - mark a page range as usable
 * @addr: starting address of the range
 * @size: size of the range in bytes
 * @flags: reservation flags (see linux/bootmem.h)
 *
 * Partial pages will be reserved.
 *
 * The range must be contiguous but may span node boundaries.
 */
int __init reserve_bootmem(unsigned long addr, unsigned long size,
			    int flags)
{
	unsigned long start, end;

	start = PFN_DOWN(addr);
	end = PFN_UP(addr + size);

	return mark_bootmem(start, end, 1, flags);
}
#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */

static void * __init alloc_bootmem_core(struct bootmem_data *bdata,
				unsigned long size, unsigned long align,
				unsigned long goal, unsigned long limit)
{
	unsigned long min, max, start, sidx, midx, step;

	BUG_ON(!size);
	BUG_ON(align & (align - 1));
	BUG_ON(limit && goal + size > limit);

	if (!bdata->node_bootmem_map)
		return NULL;

	bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n",
		bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT,
		align, goal, limit);

	min = PFN_DOWN(bdata->node_boot_start);
	max = bdata->node_low_pfn;

	goal >>= PAGE_SHIFT;
	limit >>= PAGE_SHIFT;

	if (limit && max > limit)
		max = limit;
	if (max <= min)
		return NULL;

	step = max(align >> PAGE_SHIFT, 1UL);

	if (goal && min < goal && goal < max)
		start = ALIGN(goal, step);
	else
		start = ALIGN(min, step);

	sidx = start - PFN_DOWN(bdata->node_boot_start);
	midx = max - PFN_DOWN(bdata->node_boot_start);

	if (bdata->hint_idx > sidx) {
		/* Make sure we retry on failure */
		goal = 1;
		sidx = ALIGN(bdata->hint_idx, step);
	}

	while (1) {
		int merge;
		void *region;
		unsigned long eidx, i, start_off, end_off;
find_block:
		sidx = find_next_zero_bit(bdata->node_bootmem_map, midx, sidx);
		sidx = ALIGN(sidx, step);
		eidx = sidx + PFN_UP(size);

		if (sidx >= midx || eidx > midx)
			break;

		for (i = sidx; i < eidx; i++)
			if (test_bit(i, bdata->node_bootmem_map)) {
				sidx = ALIGN(i, step);
				if (sidx == i)
					sidx += step;
				goto find_block;
			}

		if (bdata->last_end_off &&
				PFN_DOWN(bdata->last_end_off) + 1 == sidx)
			start_off = ALIGN(bdata->last_end_off, align);
		else
			start_off = PFN_PHYS(sidx);

		merge = PFN_DOWN(start_off) < sidx;
		end_off = start_off + size;

		bdata->last_end_off = end_off;
		bdata->hint_idx = PFN_UP(end_off);

		/*
		 * Reserve the area now:
		 */
		if (__reserve(bdata, PFN_DOWN(start_off) + merge,
				PFN_UP(end_off), BOOTMEM_EXCLUSIVE))
			BUG();

		region = phys_to_virt(bdata->node_boot_start + start_off);
		memset(region, 0, size);
		return region;
	}

	if (goal) {
		goal = 0;
		sidx = 0;
		goto find_block;
	}

	return NULL;
}

/**
 * __alloc_bootmem_nopanic - allocate boot memory without panicking
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may happen on any node in the system.
 *
 * Returns NULL on failure.
 */
void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
				      unsigned long goal)
{
	bootmem_data_t *bdata;
	void *ptr;

	list_for_each_entry(bdata, &bdata_list, list) {
		ptr = alloc_bootmem_core(bdata, size, align, goal, 0);
		if (ptr)
			return ptr;
	}
	return NULL;
}

/**
 * __alloc_bootmem - allocate boot memory
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may happen on any node in the system.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem(unsigned long size, unsigned long align,
			      unsigned long goal)
{
	void *mem = __alloc_bootmem_nopanic(size,align,goal);

	if (mem)
		return mem;
	/*
	 * Whoops, we cannot satisfy the allocation request.
	 */
	printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
	panic("Out of memory");
	return NULL;
}

/**
 * __alloc_bootmem_node - allocate boot memory from a specific node
 * @pgdat: node to allocate from
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may fall back to any node in the system if the specified node
 * can not hold the requested memory.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
				   unsigned long align, unsigned long goal)
{
	void *ptr;

	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
	if (ptr)
		return ptr;

	return __alloc_bootmem(size, align, goal);
}

#ifdef CONFIG_SPARSEMEM
/**
 * alloc_bootmem_section - allocate boot memory from a specific section
 * @size: size of the request in bytes
 * @section_nr: sparse map section to allocate from
 *
 * Return NULL on failure.
 */
void * __init alloc_bootmem_section(unsigned long size,
				    unsigned long section_nr)
{
	void *ptr;
	unsigned long limit, goal, start_nr, end_nr, pfn;
	struct pglist_data *pgdat;

	pfn = section_nr_to_pfn(section_nr);
	goal = PFN_PHYS(pfn);
	limit = PFN_PHYS(section_nr_to_pfn(section_nr + 1)) - 1;
	pgdat = NODE_DATA(early_pfn_to_nid(pfn));
	ptr = alloc_bootmem_core(pgdat->bdata, size, SMP_CACHE_BYTES, goal,
				limit);

	if (!ptr)
		return NULL;

	start_nr = pfn_to_section_nr(PFN_DOWN(__pa(ptr)));
	end_nr = pfn_to_section_nr(PFN_DOWN(__pa(ptr) + size));
	if (start_nr != section_nr || end_nr != section_nr) {
		printk(KERN_WARNING "alloc_bootmem failed on section %ld.\n",
		       section_nr);
		free_bootmem_node(pgdat, __pa(ptr), size);
		ptr = NULL;
	}

	return ptr;
}
#endif

void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
				   unsigned long align, unsigned long goal)
{
	void *ptr;

	ptr = alloc_bootmem_core(pgdat->bdata, size, align, goal, 0);
	if (ptr)
		return ptr;

	return __alloc_bootmem_nopanic(size, align, goal);
}

#ifndef ARCH_LOW_ADDRESS_LIMIT
#define ARCH_LOW_ADDRESS_LIMIT	0xffffffffUL
#endif

/**
 * __alloc_bootmem_low - allocate low boot memory
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may happen on any node in the system.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
				  unsigned long goal)
{
	bootmem_data_t *bdata;
	void *ptr;

	list_for_each_entry(bdata, &bdata_list, list) {
		ptr = alloc_bootmem_core(bdata, size, align, goal,
					ARCH_LOW_ADDRESS_LIMIT);
		if (ptr)
			return ptr;
	}

	/*
	 * Whoops, we cannot satisfy the allocation request.
	 */
	printk(KERN_ALERT "low bootmem alloc of %lu bytes failed!\n", size);
	panic("Out of low memory");
	return NULL;
}

/**
 * __alloc_bootmem_low_node - allocate low boot memory from a specific node
 * @pgdat: node to allocate from
 * @size: size of the request in bytes
 * @align: alignment of the region
 * @goal: preferred starting address of the region
 *
 * The goal is dropped if it can not be satisfied and the allocation will
 * fall back to memory below @goal.
 *
 * Allocation may fall back to any node in the system if the specified node
 * can not hold the requested memory.
 *
 * The function panics if the request can not be satisfied.
 */
void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
				       unsigned long align, unsigned long goal)
{
	return alloc_bootmem_core(pgdat->bdata, size, align, goal,
				ARCH_LOW_ADDRESS_LIMIT);
}