summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/init_64.c
blob: 1ff7906a9a4dbc7afa6dfdd24f274e077cd26773 (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
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
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
/*
 *  linux/arch/x86_64/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *  Copyright (C) 2000  Pavel Machek <pavel@suse.cz>
 *  Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
 */

#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/proc_fs.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/dma-mapping.h>
#include <linux/module.h>
#include <linux/memory_hotplug.h>
#include <linux/nmi.h>

#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/tlb.h>
#include <asm/mmu_context.h>
#include <asm/proto.h>
#include <asm/smp.h>
#include <asm/sections.h>
#include <asm/kdebug.h>
#include <asm/numa.h>
#include <asm/cacheflush.h>

static unsigned long dma_reserve __initdata;

DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);

int direct_gbpages __meminitdata
#ifdef CONFIG_DIRECT_GBPAGES
				= 1
#endif
;

static int __init parse_direct_gbpages_off(char *arg)
{
	direct_gbpages = 0;
	return 0;
}
early_param("nogbpages", parse_direct_gbpages_off);

static int __init parse_direct_gbpages_on(char *arg)
{
	direct_gbpages = 1;
	return 0;
}
early_param("gbpages", parse_direct_gbpages_on);

/*
 * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
 * physical space so we can cache the place of the first one and move
 * around without checking the pgd every time.
 */

void show_mem(void)
{
	long i, total = 0, reserved = 0;
	long shared = 0, cached = 0;
	struct page *page;
	pg_data_t *pgdat;

	printk(KERN_INFO "Mem-info:\n");
	show_free_areas();
	for_each_online_pgdat(pgdat) {
		for (i = 0; i < pgdat->node_spanned_pages; ++i) {
			/*
			 * This loop can take a while with 256 GB and
			 * 4k pages so defer the NMI watchdog:
			 */
			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
				touch_nmi_watchdog();

			if (!pfn_valid(pgdat->node_start_pfn + i))
				continue;

			page = pfn_to_page(pgdat->node_start_pfn + i);
			total++;
			if (PageReserved(page))
				reserved++;
			else if (PageSwapCache(page))
				cached++;
			else if (page_count(page))
				shared += page_count(page) - 1;
		}
	}
	printk(KERN_INFO "%lu pages of RAM\n",		total);
	printk(KERN_INFO "%lu reserved pages\n",	reserved);
	printk(KERN_INFO "%lu pages shared\n",		shared);
	printk(KERN_INFO "%lu pages swap cached\n",	cached);
}

int after_bootmem;

static __init void *spp_getpage(void)
{
	void *ptr;

	if (after_bootmem)
		ptr = (void *) get_zeroed_page(GFP_ATOMIC);
	else
		ptr = alloc_bootmem_pages(PAGE_SIZE);

	if (!ptr || ((unsigned long)ptr & ~PAGE_MASK)) {
		panic("set_pte_phys: cannot allocate page data %s\n",
			after_bootmem ? "after bootmem" : "");
	}

	pr_debug("spp_getpage %p\n", ptr);

	return ptr;
}

static __init void
set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte, new_pte;

	pr_debug("set_pte_phys %lx to %lx\n", vaddr, phys);

	pgd = pgd_offset_k(vaddr);
	if (pgd_none(*pgd)) {
		printk(KERN_ERR
			"PGD FIXMAP MISSING, it should be setup in head.S!\n");
		return;
	}
	pud = pud_offset(pgd, vaddr);
	if (pud_none(*pud)) {
		pmd = (pmd_t *) spp_getpage();
		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER));
		if (pmd != pmd_offset(pud, 0)) {
			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
				pmd, pmd_offset(pud, 0));
			return;
		}
	}
	pmd = pmd_offset(pud, vaddr);
	if (pmd_none(*pmd)) {
		pte = (pte_t *) spp_getpage();
		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER));
		if (pte != pte_offset_kernel(pmd, 0)) {
			printk(KERN_ERR "PAGETABLE BUG #02!\n");
			return;
		}
	}
	new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);

	pte = pte_offset_kernel(pmd, vaddr);
	if (!pte_none(*pte) &&
	    pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask))
		pte_ERROR(*pte);
	set_pte(pte, new_pte);

	/*
	 * It's enough to flush this one mapping.
	 * (PGE mappings get flushed as well)
	 */
	__flush_tlb_one(vaddr);
}

/*
 * The head.S code sets up the kernel high mapping:
 *
 *   from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text)
 *
 * phys_addr holds the negative offset to the kernel, which is added
 * to the compile time generated pmds. This results in invalid pmds up
 * to the point where we hit the physaddr 0 mapping.
 *
 * We limit the mappings to the region from _text to _end.  _end is
 * rounded up to the 2MB boundary. This catches the invalid pmds as
 * well, as they are located before _text:
 */
void __init cleanup_highmap(void)
{
	unsigned long vaddr = __START_KERNEL_map;
	unsigned long end = round_up((unsigned long)_end, PMD_SIZE) - 1;
	pmd_t *pmd = level2_kernel_pgt;
	pmd_t *last_pmd = pmd + PTRS_PER_PMD;

	for (; pmd < last_pmd; pmd++, vaddr += PMD_SIZE) {
		if (!pmd_present(*pmd))
			continue;
		if (vaddr < (unsigned long) _text || vaddr > end)
			set_pmd(pmd, __pmd(0));
	}
}

/* NOTE: this is meant to be run only at boot */
void __init
__set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
{
	unsigned long address = __fix_to_virt(idx);

	if (idx >= __end_of_fixed_addresses) {
		printk(KERN_ERR "Invalid __set_fixmap\n");
		return;
	}
	set_pte_phys(address, phys, prot);
}

static unsigned long __initdata table_start;
static unsigned long __meminitdata table_end;

static __meminit void *alloc_low_page(unsigned long *phys)
{
	unsigned long pfn = table_end++;
	void *adr;

	if (after_bootmem) {
		adr = (void *)get_zeroed_page(GFP_ATOMIC);
		*phys = __pa(adr);

		return adr;
	}

	if (pfn >= end_pfn)
		panic("alloc_low_page: ran out of memory");

	adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
	memset(adr, 0, PAGE_SIZE);
	*phys  = pfn * PAGE_SIZE;
	return adr;
}

static __meminit void unmap_low_page(void *adr)
{
	if (after_bootmem)
		return;

	early_iounmap(adr, PAGE_SIZE);
}

/* Must run before zap_low_mappings */
__meminit void *early_ioremap(unsigned long addr, unsigned long size)
{
	pmd_t *pmd, *last_pmd;
	unsigned long vaddr;
	int i, pmds;

	pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
	vaddr = __START_KERNEL_map;
	pmd = level2_kernel_pgt;
	last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1;

	for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) {
		for (i = 0; i < pmds; i++) {
			if (pmd_present(pmd[i]))
				goto continue_outer_loop;
		}
		vaddr += addr & ~PMD_MASK;
		addr &= PMD_MASK;

		for (i = 0; i < pmds; i++, addr += PMD_SIZE)
			set_pmd(pmd+i, __pmd(addr | __PAGE_KERNEL_LARGE_EXEC));
		__flush_tlb_all();

		return (void *)vaddr;
continue_outer_loop:
		;
	}
	printk(KERN_ERR "early_ioremap(0x%lx, %lu) failed\n", addr, size);

	return NULL;
}

/*
 * To avoid virtual aliases later:
 */
__meminit void early_iounmap(void *addr, unsigned long size)
{
	unsigned long vaddr;
	pmd_t *pmd;
	int i, pmds;

	vaddr = (unsigned long)addr;
	pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
	pmd = level2_kernel_pgt + pmd_index(vaddr);

	for (i = 0; i < pmds; i++)
		pmd_clear(pmd + i);

	__flush_tlb_all();
}

static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
{
	int i = pmd_index(address);

	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
		pmd_t *pmd = pmd_page + pmd_index(address);

		if (address >= end) {
			if (!after_bootmem) {
				for (; i < PTRS_PER_PMD; i++, pmd++)
					set_pmd(pmd, __pmd(0));
			}
			break;
		}

		if (pmd_val(*pmd))
			continue;

		set_pte((pte_t *)pmd,
			pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
	}
	return address;
}

static unsigned long __meminit
phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
{
	pmd_t *pmd = pmd_offset(pud, 0);
	unsigned long last_map_addr;

	spin_lock(&init_mm.page_table_lock);
	last_map_addr = phys_pmd_init(pmd, address, end);
	spin_unlock(&init_mm.page_table_lock);
	__flush_tlb_all();
	return last_map_addr;
}

static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
{
	unsigned long last_map_addr = end;
	int i = pud_index(addr);

	for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE) {
		unsigned long pmd_phys;
		pud_t *pud = pud_page + pud_index(addr);
		pmd_t *pmd;

		if (addr >= end)
			break;

		if (!after_bootmem &&
				!e820_any_mapped(addr, addr+PUD_SIZE, 0)) {
			set_pud(pud, __pud(0));
			continue;
		}

		if (pud_val(*pud)) {
			if (!pud_large(*pud))
				last_map_addr = phys_pmd_update(pud, addr, end);
			continue;
		}

		if (direct_gbpages) {
			set_pte((pte_t *)pud,
				pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
			last_map_addr = (addr & PUD_MASK) + PUD_SIZE;
			continue;
		}

		pmd = alloc_low_page(&pmd_phys);

		spin_lock(&init_mm.page_table_lock);
		set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
		last_map_addr = phys_pmd_init(pmd, addr, end);
		spin_unlock(&init_mm.page_table_lock);

		unmap_low_page(pmd);
	}
	__flush_tlb_all();

	return last_map_addr >> PAGE_SHIFT;
}

static void __init find_early_table_space(unsigned long end)
{
	unsigned long puds, pmds, tables, start;

	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE);
	if (!direct_gbpages) {
		pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
		tables += round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
	}

	/*
	 * RED-PEN putting page tables only on node 0 could
	 * cause a hotspot and fill up ZONE_DMA. The page tables
	 * need roughly 0.5KB per GB.
	 */
	start = 0x8000;
	table_start = find_e820_area(start, end, tables, PAGE_SIZE);
	if (table_start == -1UL)
		panic("Cannot find space for the kernel page tables");

	table_start >>= PAGE_SHIFT;
	table_end = table_start;

	early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
		end, table_start << PAGE_SHIFT,
		(table_start << PAGE_SHIFT) + tables);
}

static void __init init_gbpages(void)
{
	if (direct_gbpages && cpu_has_gbpages)
		printk(KERN_INFO "Using GB pages for direct mapping\n");
	else
		direct_gbpages = 0;
}

#ifdef CONFIG_MEMTEST_BOOTPARAM

static void __init memtest(unsigned long start_phys, unsigned long size,
				 unsigned pattern)
{
	unsigned long i;
	unsigned long *start;
	unsigned long start_bad;
	unsigned long last_bad;
	unsigned long val;
	unsigned long start_phys_aligned;
	unsigned long count;
	unsigned long incr;

	switch (pattern) {
	case 0:
		val = 0UL;
		break;
	case 1:
		val = -1UL;
		break;
	case 2:
		val = 0x5555555555555555UL;
		break;
	case 3:
		val = 0xaaaaaaaaaaaaaaaaUL;
		break;
	default:
		return;
	}

	incr = sizeof(unsigned long);
	start_phys_aligned = ALIGN(start_phys, incr);
	count = (size - (start_phys_aligned - start_phys))/incr;
	start = __va(start_phys_aligned);
	start_bad = 0;
	last_bad = 0;

	for (i = 0; i < count; i++)
		start[i] = val;
	for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
		if (*start != val) {
			if (start_phys_aligned == last_bad + incr) {
				last_bad += incr;
			} else {
				if (start_bad) {
					printk(KERN_CONT "\n  %016lx bad mem addr %016lx - %016lx reserved",
						val, start_bad, last_bad + incr);
					reserve_early(start_bad, last_bad - start_bad, "BAD RAM");
				}
				start_bad = last_bad = start_phys_aligned;
			}
		}
	}
	if (start_bad) {
		printk(KERN_CONT "\n  %016lx bad mem addr %016lx - %016lx reserved",
			val, start_bad, last_bad + incr);
		reserve_early(start_bad, last_bad - start_bad, "BAD RAM");
	}

}

static int memtest_pattern __initdata = CONFIG_MEMTEST_BOOTPARAM_VALUE;

static int __init parse_memtest(char *arg)
{
	if (arg)
		memtest_pattern = simple_strtoul(arg, NULL, 0);
	return 0;
}

early_param("memtest", parse_memtest);

static void __init early_memtest(unsigned long start, unsigned long end)
{
	unsigned long t_start, t_size;
	unsigned pattern;

	if (!memtest_pattern)
		return;

	printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern);
	for (pattern = 0; pattern < memtest_pattern; pattern++) {
		t_start = start;
		t_size = 0;
		while (t_start < end) {
			t_start = find_e820_area_size(t_start, &t_size, 1);

			/* done ? */
			if (t_start >= end)
				break;
			if (t_start + t_size > end)
				t_size = end - t_start;

			printk(KERN_CONT "\n  %016lx - %016lx pattern %d",
				t_start, t_start + t_size, pattern);

			memtest(t_start, t_size, pattern);

			t_start += t_size;
		}
	}
	printk(KERN_CONT "\n");
}
#else
static void __init early_memtest(unsigned long start, unsigned long end)
{
}
#endif

/*
 * Setup the direct mapping of the physical memory at PAGE_OFFSET.
 * This runs before bootmem is initialized and gets pages directly from
 * the physical memory. To access them they are temporarily mapped.
 */
unsigned long __init_refok init_memory_mapping(unsigned long start, unsigned long end)
{
	unsigned long next, last_map_addr = end;
	unsigned long start_phys = start, end_phys = end;

	printk(KERN_INFO "init_memory_mapping\n");

	/*
	 * Find space for the kernel direct mapping tables.
	 *
	 * Later we should allocate these tables in the local node of the
	 * memory mapped. Unfortunately this is done currently before the
	 * nodes are discovered.
	 */
	if (!after_bootmem) {
		init_gbpages();
		find_early_table_space(end);
	}

	start = (unsigned long)__va(start);
	end = (unsigned long)__va(end);

	for (; start < end; start = next) {
		pgd_t *pgd = pgd_offset_k(start);
		unsigned long pud_phys;
		pud_t *pud;

		if (after_bootmem)
			pud = pud_offset(pgd, start & PGDIR_MASK);
		else
			pud = alloc_low_page(&pud_phys);

		next = start + PGDIR_SIZE;
		if (next > end)
			next = end;
		last_map_addr = phys_pud_init(pud, __pa(start), __pa(next));
		if (!after_bootmem)
			set_pgd(pgd_offset_k(start), mk_kernel_pgd(pud_phys));
		unmap_low_page(pud);
	}

	if (!after_bootmem)
		mmu_cr4_features = read_cr4();
	__flush_tlb_all();

	if (!after_bootmem)
		reserve_early(table_start << PAGE_SHIFT,
				 table_end << PAGE_SHIFT, "PGTABLE");

	if (!after_bootmem)
		early_memtest(start_phys, end_phys);

	return last_map_addr;
}

#ifndef CONFIG_NUMA
void __init paging_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES];

	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
	max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
	max_zone_pfns[ZONE_NORMAL] = end_pfn;

	memory_present(0, 0, end_pfn);
	sparse_init();
	free_area_init_nodes(max_zone_pfns);
}
#endif

/*
 * Memory hotplug specific functions
 */
void online_page(struct page *page)
{
	ClearPageReserved(page);
	init_page_count(page);
	__free_page(page);
	totalram_pages++;
	num_physpages++;
}

#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * Memory is added always to NORMAL zone. This means you will never get
 * additional DMA/DMA32 memory.
 */
int arch_add_memory(int nid, u64 start, u64 size)
{
	struct pglist_data *pgdat = NODE_DATA(nid);
	struct zone *zone = pgdat->node_zones + ZONE_NORMAL;
	unsigned long last_mapped_pfn, start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;
	int ret;

	last_mapped_pfn = init_memory_mapping(start, start + size-1);
	if (last_mapped_pfn > max_pfn_mapped)
		max_pfn_mapped = last_mapped_pfn;

	ret = __add_pages(zone, start_pfn, nr_pages);
	WARN_ON(1);

	return ret;
}
EXPORT_SYMBOL_GPL(arch_add_memory);

#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA)
int memory_add_physaddr_to_nid(u64 start)
{
	return 0;
}
EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
#endif

#endif /* CONFIG_MEMORY_HOTPLUG */

static struct kcore_list kcore_mem, kcore_vmalloc, kcore_kernel,
			 kcore_modules, kcore_vsyscall;

void __init mem_init(void)
{
	long codesize, reservedpages, datasize, initsize;

	pci_iommu_alloc();

	/* clear_bss() already clear the empty_zero_page */

	reservedpages = 0;

	/* this will put all low memory onto the freelists */
#ifdef CONFIG_NUMA
	totalram_pages = numa_free_all_bootmem();
#else
	totalram_pages = free_all_bootmem();
#endif
	reservedpages = end_pfn - totalram_pages -
					absent_pages_in_range(0, end_pfn);
	after_bootmem = 1;

	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;

	/* Register memory areas for /proc/kcore */
	kclist_add(&kcore_mem, __va(0), max_low_pfn << PAGE_SHIFT);
	kclist_add(&kcore_vmalloc, (void *)VMALLOC_START,
		   VMALLOC_END-VMALLOC_START);
	kclist_add(&kcore_kernel, &_stext, _end - _stext);
	kclist_add(&kcore_modules, (void *)MODULES_VADDR, MODULES_LEN);
	kclist_add(&kcore_vsyscall, (void *)VSYSCALL_START,
				 VSYSCALL_END - VSYSCALL_START);

	printk(KERN_INFO "Memory: %luk/%luk available (%ldk kernel code, "
				"%ldk reserved, %ldk data, %ldk init)\n",
		(unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
		end_pfn << (PAGE_SHIFT-10),
		codesize >> 10,
		reservedpages << (PAGE_SHIFT-10),
		datasize >> 10,
		initsize >> 10);

	cpa_init();
}

void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
	unsigned long addr = begin;

	if (addr >= end)
		return;

	/*
	 * If debugging page accesses then do not free this memory but
	 * mark them not present - any buggy init-section access will
	 * create a kernel page fault:
	 */
#ifdef CONFIG_DEBUG_PAGEALLOC
	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
		begin, PAGE_ALIGN(end));
	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
#else
	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);

	for (; addr < end; addr += PAGE_SIZE) {
		ClearPageReserved(virt_to_page(addr));
		init_page_count(virt_to_page(addr));
		memset((void *)(addr & ~(PAGE_SIZE-1)),
			POISON_FREE_INITMEM, PAGE_SIZE);
		free_page(addr);
		totalram_pages++;
	}
#endif
}

void free_initmem(void)
{
	free_init_pages("unused kernel memory",
			(unsigned long)(&__init_begin),
			(unsigned long)(&__init_end));
}

#ifdef CONFIG_DEBUG_RODATA
const int rodata_test_data = 0xC3;
EXPORT_SYMBOL_GPL(rodata_test_data);

void mark_rodata_ro(void)
{
	unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);

	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
	       (end - start) >> 10);
	set_memory_ro(start, (end - start) >> PAGE_SHIFT);

	/*
	 * The rodata section (but not the kernel text!) should also be
	 * not-executable.
	 */
	start = ((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
	set_memory_nx(start, (end - start) >> PAGE_SHIFT);

	rodata_test();

#ifdef CONFIG_CPA_DEBUG
	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, end);
	set_memory_rw(start, (end-start) >> PAGE_SHIFT);

	printk(KERN_INFO "Testing CPA: again\n");
	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
#endif
}

#endif

#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
	free_init_pages("initrd memory", start, end);
}
#endif

void __init reserve_bootmem_generic(unsigned long phys, unsigned len)
{
#ifdef CONFIG_NUMA
	int nid = phys_to_nid(phys);
#endif
	unsigned long pfn = phys >> PAGE_SHIFT;

	if (pfn >= end_pfn) {
		/*
		 * This can happen with kdump kernels when accessing
		 * firmware tables:
		 */
		if (pfn < max_pfn_mapped)
			return;

		printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n",
				phys, len);
		return;
	}

	/* Should check here against the e820 map to avoid double free */
#ifdef CONFIG_NUMA
	reserve_bootmem_node(NODE_DATA(nid), phys, len, BOOTMEM_DEFAULT);
#else
	reserve_bootmem(phys, len, BOOTMEM_DEFAULT);
#endif
	if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) {
		dma_reserve += len / PAGE_SIZE;
		set_dma_reserve(dma_reserve);
	}
}

int kern_addr_valid(unsigned long addr)
{
	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	if (above != 0 && above != -1UL)
		return 0;

	pgd = pgd_offset_k(addr);
	if (pgd_none(*pgd))
		return 0;

	pud = pud_offset(pgd, addr);
	if (pud_none(*pud))
		return 0;

	pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd))
		return 0;

	if (pmd_large(*pmd))
		return pfn_valid(pmd_pfn(*pmd));

	pte = pte_offset_kernel(pmd, addr);
	if (pte_none(*pte))
		return 0;

	return pfn_valid(pte_pfn(*pte));
}

/*
 * A pseudo VMA to allow ptrace access for the vsyscall page.  This only
 * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
 * not need special handling anymore:
 */
static struct vm_area_struct gate_vma = {
	.vm_start	= VSYSCALL_START,
	.vm_end		= VSYSCALL_START + (VSYSCALL_MAPPED_PAGES * PAGE_SIZE),
	.vm_page_prot	= PAGE_READONLY_EXEC,
	.vm_flags	= VM_READ | VM_EXEC
};

struct vm_area_struct *get_gate_vma(struct task_struct *tsk)
{
#ifdef CONFIG_IA32_EMULATION
	if (test_tsk_thread_flag(tsk, TIF_IA32))
		return NULL;
#endif
	return &gate_vma;
}

int in_gate_area(struct task_struct *task, unsigned long addr)
{
	struct vm_area_struct *vma = get_gate_vma(task);

	if (!vma)
		return 0;

	return (addr >= vma->vm_start) && (addr < vma->vm_end);
}

/*
 * Use this when you have no reliable task/vma, typically from interrupt
 * context. It is less reliable than using the task's vma and may give
 * false positives:
 */
int in_gate_area_no_task(unsigned long addr)
{
	return (addr >= VSYSCALL_START) && (addr < VSYSCALL_END);
}

const char *arch_vma_name(struct vm_area_struct *vma)
{
	if (vma->vm_mm && vma->vm_start == (long)vma->vm_mm->context.vdso)
		return "[vdso]";
	if (vma == &gate_vma)
		return "[vsyscall]";
	return NULL;
}

#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
 * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
 */
int __meminit
vmemmap_populate(struct page *start_page, unsigned long size, int node)
{
	unsigned long addr = (unsigned long)start_page;
	unsigned long end = (unsigned long)(start_page + size);
	unsigned long next;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	for (; addr < end; addr = next) {
		next = pmd_addr_end(addr, end);

		pgd = vmemmap_pgd_populate(addr, node);
		if (!pgd)
			return -ENOMEM;

		pud = vmemmap_pud_populate(pgd, addr, node);
		if (!pud)
			return -ENOMEM;

		pmd = pmd_offset(pud, addr);
		if (pmd_none(*pmd)) {
			pte_t entry;
			void *p;

			p = vmemmap_alloc_block(PMD_SIZE, node);
			if (!p)
				return -ENOMEM;

			entry = pfn_pte(__pa(p) >> PAGE_SHIFT,
							PAGE_KERNEL_LARGE);
			set_pmd(pmd, __pmd(pte_val(entry)));

			printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
				addr, addr + PMD_SIZE - 1, p, node);
		} else {
			vmemmap_verify((pte_t *)pmd, node, addr, next);
		}
	}
	return 0;
}
#endif
OpenPOWER on IntegriCloud