aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/mm/init.c
blob: 72a2b8cee319c9c2c09e71d76fc397165d6f7cec (plain)
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
/*
 *  linux/arch/arm/mm/init.c
 *
 *  Copyright (C) 1995-2002 Russell King
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/swap.h>
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/initrd.h>

#include <asm/mach-types.h>
#include <asm/hardware.h>
#include <asm/setup.h>
#include <asm/tlb.h>

#include <asm/mach/arch.h>
#include <asm/mach/map.h>

#define TABLE_SIZE	(2 * PTRS_PER_PTE * sizeof(pte_t))

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);

extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
extern void _stext, _text, _etext, __data_start, _end, __init_begin, __init_end;
extern unsigned long phys_initrd_start;
extern unsigned long phys_initrd_size;

/*
 * The sole use of this is to pass memory configuration
 * data from paging_init to mem_init.
 */
static struct meminfo meminfo __initdata = { 0, };

/*
 * empty_zero_page is a special page that is used for
 * zero-initialized data and COW.
 */
struct page *empty_zero_page;

void show_mem(void)
{
	int free = 0, total = 0, reserved = 0;
	int shared = 0, cached = 0, slab = 0, node;

	printk("Mem-info:\n");
	show_free_areas();
	printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));

	for_each_online_node(node) {
		struct page *page, *end;

		page = NODE_MEM_MAP(node);
		end  = page + NODE_DATA(node)->node_spanned_pages;

		do {
			total++;
			if (PageReserved(page))
				reserved++;
			else if (PageSwapCache(page))
				cached++;
			else if (PageSlab(page))
				slab++;
			else if (!page_count(page))
				free++;
			else
				shared += page_count(page) - 1;
			page++;
		} while (page < end);
	}

	printk("%d pages of RAM\n", total);
	printk("%d free pages\n", free);
	printk("%d reserved pages\n", reserved);
	printk("%d slab pages\n", slab);
	printk("%d pages shared\n", shared);
	printk("%d pages swap cached\n", cached);
}

struct node_info {
	unsigned int start;
	unsigned int end;
	int bootmap_pages;
};

#define O_PFN_DOWN(x)	((x) >> PAGE_SHIFT)
#define V_PFN_DOWN(x)	O_PFN_DOWN(__pa(x))

#define O_PFN_UP(x)	(PAGE_ALIGN(x) >> PAGE_SHIFT)
#define V_PFN_UP(x)	O_PFN_UP(__pa(x))

#define PFN_SIZE(x)	((x) >> PAGE_SHIFT)
#define PFN_RANGE(s,e)	PFN_SIZE(PAGE_ALIGN((unsigned long)(e)) - \
				(((unsigned long)(s)) & PAGE_MASK))

/*
 * FIXME: We really want to avoid allocating the bootmap bitmap
 * over the top of the initrd.  Hopefully, this is located towards
 * the start of a bank, so if we allocate the bootmap bitmap at
 * the end, we won't clash.
 */
static unsigned int __init
find_bootmap_pfn(int node, struct meminfo *mi, unsigned int bootmap_pages)
{
	unsigned int start_pfn, bank, bootmap_pfn;

	start_pfn   = V_PFN_UP(&_end);
	bootmap_pfn = 0;

	for (bank = 0; bank < mi->nr_banks; bank ++) {
		unsigned int start, end;

		if (mi->bank[bank].node != node)
			continue;

		start = O_PFN_UP(mi->bank[bank].start);
		end   = O_PFN_DOWN(mi->bank[bank].size +
				   mi->bank[bank].start);

		if (end < start_pfn)
			continue;

		if (start < start_pfn)
			start = start_pfn;

		if (end <= start)
			continue;

		if (end - start >= bootmap_pages) {
			bootmap_pfn = start;
			break;
		}
	}

	if (bootmap_pfn == 0)
		BUG();

	return bootmap_pfn;
}

/*
 * Scan the memory info structure and pull out:
 *  - the end of memory
 *  - the number of nodes
 *  - the pfn range of each node
 *  - the number of bootmem bitmap pages
 */
static unsigned int __init
find_memend_and_nodes(struct meminfo *mi, struct node_info *np)
{
	unsigned int i, bootmem_pages = 0, memend_pfn = 0;

	for (i = 0; i < MAX_NUMNODES; i++) {
		np[i].start = -1U;
		np[i].end = 0;
		np[i].bootmap_pages = 0;
	}

	for (i = 0; i < mi->nr_banks; i++) {
		unsigned long start, end;
		int node;

		if (mi->bank[i].size == 0) {
			/*
			 * Mark this bank with an invalid node number
			 */
			mi->bank[i].node = -1;
			continue;
		}

		node = mi->bank[i].node;

		/*
		 * Make sure we haven't exceeded the maximum number of nodes
		 * that we have in this configuration.  If we have, we're in
		 * trouble.  (maybe we ought to limit, instead of bugging?)
		 */
		if (node >= MAX_NUMNODES)
			BUG();
		node_set_online(node);

		/*
		 * Get the start and end pfns for this bank
		 */
		start = O_PFN_UP(mi->bank[i].start);
		end   = O_PFN_DOWN(mi->bank[i].start + mi->bank[i].size);

		if (np[node].start > start)
			np[node].start = start;

		if (np[node].end < end)
			np[node].end = end;

		if (memend_pfn < end)
			memend_pfn = end;
	}

	/*
	 * Calculate the number of pages we require to
	 * store the bootmem bitmaps.
	 */
	for_each_online_node(i) {
		if (np[i].end == 0)
			continue;

		np[i].bootmap_pages = bootmem_bootmap_pages(np[i].end -
							    np[i].start);
		bootmem_pages += np[i].bootmap_pages;
	}

	high_memory = __va(memend_pfn << PAGE_SHIFT);

	/*
	 * This doesn't seem to be used by the Linux memory
	 * manager any more.  If we can get rid of it, we
	 * also get rid of some of the stuff above as well.
	 *
	 * Note: max_low_pfn and max_pfn reflect the number
	 * of _pages_ in the system, not the maximum PFN.
	 */
	max_low_pfn = memend_pfn - O_PFN_DOWN(PHYS_OFFSET);
	max_pfn = memend_pfn - O_PFN_DOWN(PHYS_OFFSET);

	return bootmem_pages;
}

static int __init check_initrd(struct meminfo *mi)
{
	int initrd_node = -2;
#ifdef CONFIG_BLK_DEV_INITRD
	unsigned long end = phys_initrd_start + phys_initrd_size;

	/*
	 * Make sure that the initrd is within a valid area of
	 * memory.
	 */
	if (phys_initrd_size) {
		unsigned int i;

		initrd_node = -1;

		for (i = 0; i < mi->nr_banks; i++) {
			unsigned long bank_end;

			bank_end = mi->bank[i].start + mi->bank[i].size;

			if (mi->bank[i].start <= phys_initrd_start &&
			    end <= bank_end)
				initrd_node = mi->bank[i].node;
		}
	}

	if (initrd_node == -1) {
		printk(KERN_ERR "initrd (0x%08lx - 0x%08lx) extends beyond "
		       "physical memory - disabling initrd\n",
		       phys_initrd_start, end);
		phys_initrd_start = phys_initrd_size = 0;
	}
#endif

	return initrd_node;
}

/*
 * Reserve the various regions of node 0
 */
static __init void reserve_node_zero(unsigned int bootmap_pfn, unsigned int bootmap_pages)
{
	pg_data_t *pgdat = NODE_DATA(0);
	unsigned long res_size = 0;

	/*
	 * Register the kernel text and data with bootmem.
	 * Note that this can only be in node 0.
	 */
#ifdef CONFIG_XIP_KERNEL
	reserve_bootmem_node(pgdat, __pa(&__data_start), &_end - &__data_start);
#else
	reserve_bootmem_node(pgdat, __pa(&_stext), &_end - &_stext);
#endif

	/*
	 * Reserve the page tables.  These are already in use,
	 * and can only be in node 0.
	 */
	reserve_bootmem_node(pgdat, __pa(swapper_pg_dir),
			     PTRS_PER_PGD * sizeof(pgd_t));

	/*
	 * And don't forget to reserve the allocator bitmap,
	 * which will be freed later.
	 */
	reserve_bootmem_node(pgdat, bootmap_pfn << PAGE_SHIFT,
			     bootmap_pages << PAGE_SHIFT);

	/*
	 * Hmm... This should go elsewhere, but we really really need to
	 * stop things allocating the low memory; ideally we need a better
	 * implementation of GFP_DMA which does not assume that DMA-able
	 * memory starts at zero.
	 */
	if (machine_is_integrator() || machine_is_cintegrator())
		res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;

	/*
	 * These should likewise go elsewhere.  They pre-reserve the
	 * screen memory region at the start of main system memory.
	 */
	if (machine_is_edb7211())
		res_size = 0x00020000;
	if (machine_is_p720t())
		res_size = 0x00014000;

#ifdef CONFIG_SA1111
	/*
	 * Because of the SA1111 DMA bug, we want to preserve our
	 * precious DMA-able memory...
	 */
	res_size = __pa(swapper_pg_dir) - PHYS_OFFSET;
#endif
	if (res_size)
		reserve_bootmem_node(pgdat, PHYS_OFFSET, res_size);
}

/*
 * Register all available RAM in this node with the bootmem allocator.
 */
static inline void free_bootmem_node_bank(int node, struct meminfo *mi)
{
	pg_data_t *pgdat = NODE_DATA(node);
	int bank;

	for (bank = 0; bank < mi->nr_banks; bank++)
		if (mi->bank[bank].node == node)
			free_bootmem_node(pgdat, mi->bank[bank].start,
					  mi->bank[bank].size);
}

/*
 * Initialise the bootmem allocator for all nodes.  This is called
 * early during the architecture specific initialisation.
 */
static void __init bootmem_init(struct meminfo *mi)
{
	struct node_info node_info[MAX_NUMNODES], *np = node_info;
	unsigned int bootmap_pages, bootmap_pfn, map_pg;
	int node, initrd_node;

	bootmap_pages = find_memend_and_nodes(mi, np);
	bootmap_pfn   = find_bootmap_pfn(0, mi, bootmap_pages);
	initrd_node   = check_initrd(mi);

	map_pg = bootmap_pfn;

	/*
	 * Initialise the bootmem nodes.
	 *
	 * What we really want to do is:
	 *
	 *   unmap_all_regions_except_kernel();
	 *   for_each_node_in_reverse_order(node) {
	 *     map_node(node);
	 *     allocate_bootmem_map(node);
	 *     init_bootmem_node(node);
	 *     free_bootmem_node(node);
	 *   }
	 *
	 * but this is a 2.5-type change.  For now, we just set
	 * the nodes up in reverse order.
	 *
	 * (we could also do with rolling bootmem_init and paging_init
	 * into one generic "memory_init" type function).
	 */
	np += num_online_nodes() - 1;
	for (node = num_online_nodes() - 1; node >= 0; node--, np--) {
		/*
		 * If there are no pages in this node, ignore it.
		 * Note that node 0 must always have some pages.
		 */
		if (np->end == 0 || !node_online(node)) {
			if (node == 0)
				BUG();
			continue;
		}

		/*
		 * Initialise the bootmem allocator.
		 */
		init_bootmem_node(NODE_DATA(node), map_pg, np->start, np->end);
		free_bootmem_node_bank(node, mi);
		map_pg += np->bootmap_pages;

		/*
		 * If this is node 0, we need to reserve some areas ASAP -
		 * we may use bootmem on node 0 to setup the other nodes.
		 */
		if (node == 0)
			reserve_node_zero(bootmap_pfn, bootmap_pages);
	}


#ifdef CONFIG_BLK_DEV_INITRD
	if (phys_initrd_size && initrd_node >= 0) {
		reserve_bootmem_node(NODE_DATA(initrd_node), phys_initrd_start,
				     phys_initrd_size);
		initrd_start = __phys_to_virt(phys_initrd_start);
		initrd_end = initrd_start + phys_initrd_size;
	}
#endif

	BUG_ON(map_pg != bootmap_pfn + bootmap_pages);
}

/*
 * paging_init() sets up the page tables, initialises the zone memory
 * maps, and sets up the zero page, bad page and bad page tables.
 */
void __init paging_init(struct meminfo *mi, struct machine_desc *mdesc)
{
	void *zero_page;
	int node;

	bootmem_init(mi);

	memcpy(&meminfo, mi, sizeof(meminfo));

	/*
	 * allocate the zero page.  Note that we count on this going ok.
	 */
	zero_page = alloc_bootmem_low_pages(PAGE_SIZE);

	/*
	 * initialise the page tables.
	 */
	memtable_init(mi);
	if (mdesc->map_io)
		mdesc->map_io();
	flush_tlb_all();

	/*
	 * initialise the zones within each node
	 */
	for_each_online_node(node) {
		unsigned long zone_size[MAX_NR_ZONES];
		unsigned long zhole_size[MAX_NR_ZONES];
		struct bootmem_data *bdata;
		pg_data_t *pgdat;
		int i;

		/*
		 * Initialise the zone size information.
		 */
		for (i = 0; i < MAX_NR_ZONES; i++) {
			zone_size[i]  = 0;
			zhole_size[i] = 0;
		}

		pgdat = NODE_DATA(node);
		bdata = pgdat->bdata;

		/*
		 * The size of this node has already been determined.
		 * If we need to do anything fancy with the allocation
		 * of this memory to the zones, now is the time to do
		 * it.
		 */
		zone_size[0] = bdata->node_low_pfn -
				(bdata->node_boot_start >> PAGE_SHIFT);

		/*
		 * If this zone has zero size, skip it.
		 */
		if (!zone_size[0])
			continue;

		/*
		 * For each bank in this node, calculate the size of the
		 * holes.  holes = node_size - sum(bank_sizes_in_node)
		 */
		zhole_size[0] = zone_size[0];
		for (i = 0; i < mi->nr_banks; i++) {
			if (mi->bank[i].node != node)
				continue;

			zhole_size[0] -= mi->bank[i].size >> PAGE_SHIFT;
		}

		/*
		 * Adjust the sizes according to any special
		 * requirements for this machine type.
		 */
		arch_adjust_zones(node, zone_size, zhole_size);

		free_area_init_node(node, pgdat, zone_size,
				bdata->node_boot_start >> PAGE_SHIFT, zhole_size);
	}

	/*
	 * finish off the bad pages once
	 * the mem_map is initialised
	 */
	memzero(zero_page, PAGE_SIZE);
	empty_zero_page = virt_to_page(zero_page);
	flush_dcache_page(empty_zero_page);
}

static inline void free_area(unsigned long addr, unsigned long end, char *s)
{
	unsigned int size = (end - addr) >> 10;

	for (; addr < end; addr += PAGE_SIZE) {
		struct page *page = virt_to_page(addr);
		ClearPageReserved(page);
		set_page_count(page, 1);
		free_page(addr);
		totalram_pages++;
	}

	if (size && s)
		printk(KERN_INFO "Freeing %s memory: %dK\n", s, size);
}

/*
 * mem_init() marks the free areas in the mem_map and tells us how much
 * memory is free.  This is done after various parts of the system have
 * claimed their memory after the kernel image.
 */
void __init mem_init(void)
{
	unsigned int codepages, datapages, initpages;
	int i, node;

	codepages = &_etext - &_text;
	datapages = &_end - &__data_start;
	initpages = &__init_end - &__init_begin;

#ifndef CONFIG_DISCONTIGMEM
	max_mapnr   = virt_to_page(high_memory) - mem_map;
#endif

	/*
	 * We may have non-contiguous memory.
	 */
	if (meminfo.nr_banks != 1)
		create_memmap_holes(&meminfo);

	/* this will put all unused low memory onto the freelists */
	for_each_online_node(node) {
		pg_data_t *pgdat = NODE_DATA(node);

		if (pgdat->node_spanned_pages != 0)
			totalram_pages += free_all_bootmem_node(pgdat);
	}

#ifdef CONFIG_SA1111
	/* now that our DMA memory is actually so designated, we can free it */
	free_area(PAGE_OFFSET, (unsigned long)swapper_pg_dir, NULL);
#endif

	/*
	 * Since our memory may not be contiguous, calculate the
	 * real number of pages we have in this system
	 */
	printk(KERN_INFO "Memory:");

	num_physpages = 0;
	for (i = 0; i < meminfo.nr_banks; i++) {
		num_physpages += meminfo.bank[i].size >> PAGE_SHIFT;
		printk(" %ldMB", meminfo.bank[i].size >> 20);
	}

	printk(" = %luMB total\n", num_physpages >> (20 - PAGE_SHIFT));
	printk(KERN_NOTICE "Memory: %luKB available (%dK code, "
		"%dK data, %dK init)\n",
		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
		codepages >> 10, datapages >> 10, initpages >> 10);

	if (PAGE_SIZE >= 16384 && num_physpages <= 128) {
		extern int sysctl_overcommit_memory;
		/*
		 * On a machine this small we won't get
		 * anywhere without overcommit, so turn
		 * it on by default.
		 */
		sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;
	}
}

void free_initmem(void)
{
	if (!machine_is_integrator() && !machine_is_cintegrator()) {
		free_area((unsigned long)(&__init_begin),
			  (unsigned long)(&__init_end),
			  "init");
	}
}

#ifdef CONFIG_BLK_DEV_INITRD

static int keep_initrd;

void free_initrd_mem(unsigned long start, unsigned long end)
{
	if (!keep_initrd)
		free_area(start, end, "initrd");
}

static int __init keepinitrd_setup(char *__unused)
{
	keep_initrd = 1;
	return 1;
}

__setup("keepinitrd", keepinitrd_setup);
#endif