aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/mm/init_64.c
blob: 75c9a6a5969723e63c2cc575df54aac99353672c (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
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
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
/*
 *  linux/arch/x86_64/mm/init.c
 *
 *  Copyright (C) 1995  Linus Torvalds
 *  Copyright (C) 2000  Pavel Machek <pavel@ucw.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/initrd.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/memblock.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.h>
#include <linux/memory_hotplug.h>
#include <linux/nmi.h>
#include <linux/gfp.h>

#include <asm/processor.h>
#include <asm/bios_ebda.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>
#include <asm/init.h>
#include <asm/uv/uv.h>
#include <asm/setup.h>

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.
 */

pteval_t __supported_pte_mask __read_mostly = ~_PAGE_IOMAP;
EXPORT_SYMBOL_GPL(__supported_pte_mask);

int force_personality32;

/*
 * noexec32=on|off
 * Control non executable heap for 32bit processes.
 * To control the stack too use noexec=off
 *
 * on	PROT_READ does not imply PROT_EXEC for 32-bit processes (default)
 * off	PROT_READ implies PROT_EXEC
 */
static int __init nonx32_setup(char *str)
{
	if (!strcmp(str, "on"))
		force_personality32 &= ~READ_IMPLIES_EXEC;
	else if (!strcmp(str, "off"))
		force_personality32 |= READ_IMPLIES_EXEC;
	return 1;
}
__setup("noexec32=", nonx32_setup);

/*
 * When memory was added/removed make sure all the processes MM have
 * suitable PGD entries in the local PGD level page.
 */
void sync_global_pgds(unsigned long start, unsigned long end)
{
	unsigned long address;

	for (address = start; address <= end; address += PGDIR_SIZE) {
		const pgd_t *pgd_ref = pgd_offset_k(address);
		struct page *page;

		if (pgd_none(*pgd_ref))
			continue;

		spin_lock(&pgd_lock);
		list_for_each_entry(page, &pgd_list, lru) {
			pgd_t *pgd;
			spinlock_t *pgt_lock;

			pgd = (pgd_t *)page_address(page) + pgd_index(address);
			/* the pgt_lock only for Xen */
			pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
			spin_lock(pgt_lock);

			if (pgd_none(*pgd))
				set_pgd(pgd, *pgd_ref);
			else
				BUG_ON(pgd_page_vaddr(*pgd)
				       != pgd_page_vaddr(*pgd_ref));

			spin_unlock(pgt_lock);
		}
		spin_unlock(&pgd_lock);
	}
}

/*
 * NOTE: This function is marked __ref because it calls __init function
 * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
 */
static __ref void *spp_getpage(void)
{
	void *ptr;

	if (after_bootmem)
		ptr = (void *) get_zeroed_page(GFP_ATOMIC | __GFP_NOTRACK);
	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 pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr)
{
	if (pgd_none(*pgd)) {
		pud_t *pud = (pud_t *)spp_getpage();
		pgd_populate(&init_mm, pgd, pud);
		if (pud != pud_offset(pgd, 0))
			printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
			       pud, pud_offset(pgd, 0));
	}
	return pud_offset(pgd, vaddr);
}

static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
{
	if (pud_none(*pud)) {
		pmd_t *pmd = (pmd_t *) spp_getpage();
		pud_populate(&init_mm, pud, pmd);
		if (pmd != pmd_offset(pud, 0))
			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
			       pmd, pmd_offset(pud, 0));
	}
	return pmd_offset(pud, vaddr);
}

static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr)
{
	if (pmd_none(*pmd)) {
		pte_t *pte = (pte_t *) spp_getpage();
		pmd_populate_kernel(&init_mm, pmd, pte);
		if (pte != pte_offset_kernel(pmd, 0))
			printk(KERN_ERR "PAGETABLE BUG #02!\n");
	}
	return pte_offset_kernel(pmd, vaddr);
}

void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
{
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	pud = pud_page + pud_index(vaddr);
	pmd = fill_pmd(pud, vaddr);
	pte = fill_pte(pmd, vaddr);

	set_pte(pte, new_pte);

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

void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
{
	pgd_t *pgd;
	pud_t *pud_page;

	pr_debug("set_pte_vaddr %lx to %lx\n", vaddr, native_pte_val(pteval));

	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_page = (pud_t*)pgd_page_vaddr(*pgd);
	set_pte_vaddr_pud(pud_page, vaddr, pteval);
}

pmd_t * __init populate_extra_pmd(unsigned long vaddr)
{
	pgd_t *pgd;
	pud_t *pud;

	pgd = pgd_offset_k(vaddr);
	pud = fill_pud(pgd, vaddr);
	return fill_pmd(pud, vaddr);
}

pte_t * __init populate_extra_pte(unsigned long vaddr)
{
	pmd_t *pmd;

	pmd = populate_extra_pmd(vaddr);
	return fill_pte(pmd, vaddr);
}

/*
 * Create large page table mappings for a range of physical addresses.
 */
static void __init __init_extra_mapping(unsigned long phys, unsigned long size,
						pgprot_t prot)
{
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;

	BUG_ON((phys & ~PMD_MASK) || (size & ~PMD_MASK));
	for (; size; phys += PMD_SIZE, size -= PMD_SIZE) {
		pgd = pgd_offset_k((unsigned long)__va(phys));
		if (pgd_none(*pgd)) {
			pud = (pud_t *) spp_getpage();
			set_pgd(pgd, __pgd(__pa(pud) | _KERNPG_TABLE |
						_PAGE_USER));
		}
		pud = pud_offset(pgd, (unsigned long)__va(phys));
		if (pud_none(*pud)) {
			pmd = (pmd_t *) spp_getpage();
			set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE |
						_PAGE_USER));
		}
		pmd = pmd_offset(pud, phys);
		BUG_ON(!pmd_none(*pmd));
		set_pmd(pmd, __pmd(phys | pgprot_val(prot)));
	}
}

void __init init_extra_mapping_wb(unsigned long phys, unsigned long size)
{
	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE);
}

void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
{
	__init_extra_mapping(phys, size, PAGE_KERNEL_LARGE_NOCACHE);
}

/*
 * 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 _brk_end.  _brk_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 vaddr_end = __START_KERNEL_map + (max_pfn_mapped << PAGE_SHIFT);
	unsigned long end = roundup((unsigned long)_brk_end, PMD_SIZE) - 1;
	pmd_t *pmd = level2_kernel_pgt;

	for (; vaddr + PMD_SIZE - 1 < vaddr_end; pmd++, vaddr += PMD_SIZE) {
		if (pmd_none(*pmd))
			continue;
		if (vaddr < (unsigned long) _text || vaddr > end)
			set_pmd(pmd, __pmd(0));
	}
}

static __ref void *alloc_low_page(unsigned long *phys)
{
	unsigned long pfn = pgt_buf_end++;
	void *adr;

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

		return adr;
	}

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

	adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
	clear_page(adr);
	*phys  = pfn * PAGE_SIZE;
	return adr;
}

static __ref void *map_low_page(void *virt)
{
	void *adr;
	unsigned long phys, left;

	if (after_bootmem)
		return virt;

	phys = __pa(virt);
	left = phys & (PAGE_SIZE - 1);
	adr = early_memremap(phys & PAGE_MASK, PAGE_SIZE);
	adr = (void *)(((unsigned long)adr) | left);

	return adr;
}

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

	early_iounmap((void *)((unsigned long)adr & PAGE_MASK), PAGE_SIZE);
}

static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
	      pgprot_t prot)
{
	unsigned pages = 0;
	unsigned long last_map_addr = end;
	int i;

	pte_t *pte = pte_page + pte_index(addr);

	for(i = pte_index(addr); i < PTRS_PER_PTE; i++, addr += PAGE_SIZE, pte++) {

		if (addr >= end) {
			if (!after_bootmem) {
				for(; i < PTRS_PER_PTE; i++, pte++)
					set_pte(pte, __pte(0));
			}
			break;
		}

		/*
		 * We will re-use the existing mapping.
		 * Xen for example has some special requirements, like mapping
		 * pagetable pages as RO. So assume someone who pre-setup
		 * these mappings are more intelligent.
		 */
		if (pte_val(*pte)) {
			if (!after_bootmem)
				pages++;
			continue;
		}

		if (0)
			printk("   pte=%p addr=%lx pte=%016lx\n",
			       pte, addr, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL).pte);
		pages++;
		set_pte(pte, pfn_pte(addr >> PAGE_SHIFT, prot));
		last_map_addr = (addr & PAGE_MASK) + PAGE_SIZE;
	}

	update_page_count(PG_LEVEL_4K, pages);

	return last_map_addr;
}

static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
	      unsigned long page_size_mask, pgprot_t prot)
{
	unsigned long pages = 0, next;
	unsigned long last_map_addr = end;

	int i = pmd_index(address);

	for (; i < PTRS_PER_PMD; i++, address = next) {
		unsigned long pte_phys;
		pmd_t *pmd = pmd_page + pmd_index(address);
		pte_t *pte;
		pgprot_t new_prot = prot;

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

		next = (address & PMD_MASK) + PMD_SIZE;

		if (pmd_val(*pmd)) {
			if (!pmd_large(*pmd)) {
				spin_lock(&init_mm.page_table_lock);
				pte = map_low_page((pte_t *)pmd_page_vaddr(*pmd));
				last_map_addr = phys_pte_init(pte, address,
								end, prot);
				unmap_low_page(pte);
				spin_unlock(&init_mm.page_table_lock);
				continue;
			}
			/*
			 * If we are ok with PG_LEVEL_2M mapping, then we will
			 * use the existing mapping,
			 *
			 * Otherwise, we will split the large page mapping but
			 * use the same existing protection bits except for
			 * large page, so that we don't violate Intel's TLB
			 * Application note (317080) which says, while changing
			 * the page sizes, new and old translations should
			 * not differ with respect to page frame and
			 * attributes.
			 */
			if (page_size_mask & (1 << PG_LEVEL_2M)) {
				if (!after_bootmem)
					pages++;
				last_map_addr = next;
				continue;
			}
			new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
		}

		if (page_size_mask & (1<<PG_LEVEL_2M)) {
			pages++;
			spin_lock(&init_mm.page_table_lock);
			set_pte((pte_t *)pmd,
				pfn_pte(address >> PAGE_SHIFT,
					__pgprot(pgprot_val(prot) | _PAGE_PSE)));
			spin_unlock(&init_mm.page_table_lock);
			last_map_addr = next;
			continue;
		}

		pte = alloc_low_page(&pte_phys);
		last_map_addr = phys_pte_init(pte, address, end, new_prot);
		unmap_low_page(pte);

		spin_lock(&init_mm.page_table_lock);
		pmd_populate_kernel(&init_mm, pmd, __va(pte_phys));
		spin_unlock(&init_mm.page_table_lock);
	}
	update_page_count(PG_LEVEL_2M, pages);
	return last_map_addr;
}

static unsigned long __meminit
phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
			 unsigned long page_size_mask)
{
	unsigned long pages = 0, next;
	unsigned long last_map_addr = end;
	int i = pud_index(addr);

	for (; i < PTRS_PER_PUD; i++, addr = next) {
		unsigned long pmd_phys;
		pud_t *pud = pud_page + pud_index(addr);
		pmd_t *pmd;
		pgprot_t prot = PAGE_KERNEL;

		if (addr >= end)
			break;

		next = (addr & PUD_MASK) + PUD_SIZE;

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

		if (pud_val(*pud)) {
			if (!pud_large(*pud)) {
				pmd = map_low_page(pmd_offset(pud, 0));
				last_map_addr = phys_pmd_init(pmd, addr, end,
							 page_size_mask, prot);
				unmap_low_page(pmd);
				__flush_tlb_all();
				continue;
			}
			/*
			 * If we are ok with PG_LEVEL_1G mapping, then we will
			 * use the existing mapping.
			 *
			 * Otherwise, we will split the gbpage mapping but use
			 * the same existing protection  bits except for large
			 * page, so that we don't violate Intel's TLB
			 * Application note (317080) which says, while changing
			 * the page sizes, new and old translations should
			 * not differ with respect to page frame and
			 * attributes.
			 */
			if (page_size_mask & (1 << PG_LEVEL_1G)) {
				if (!after_bootmem)
					pages++;
				last_map_addr = next;
				continue;
			}
			prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
		}

		if (page_size_mask & (1<<PG_LEVEL_1G)) {
			pages++;
			spin_lock(&init_mm.page_table_lock);
			set_pte((pte_t *)pud,
				pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE));
			spin_unlock(&init_mm.page_table_lock);
			last_map_addr = next;
			continue;
		}

		pmd = alloc_low_page(&pmd_phys);
		last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
					      prot);
		unmap_low_page(pmd);

		spin_lock(&init_mm.page_table_lock);
		pud_populate(&init_mm, pud, __va(pmd_phys));
		spin_unlock(&init_mm.page_table_lock);
	}
	__flush_tlb_all();

	update_page_count(PG_LEVEL_1G, pages);

	return last_map_addr;
}

unsigned long __meminit
kernel_physical_mapping_init(unsigned long start,
			     unsigned long end,
			     unsigned long page_size_mask)
{
	bool pgd_changed = false;
	unsigned long next, last_map_addr = end;
	unsigned long addr;

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

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

		next = (start + PGDIR_SIZE) & PGDIR_MASK;
		if (next > end)
			next = end;

		if (pgd_val(*pgd)) {
			pud = map_low_page((pud_t *)pgd_page_vaddr(*pgd));
			last_map_addr = phys_pud_init(pud, __pa(start),
						 __pa(end), page_size_mask);
			unmap_low_page(pud);
			continue;
		}

		pud = alloc_low_page(&pud_phys);
		last_map_addr = phys_pud_init(pud, __pa(start), __pa(next),
						 page_size_mask);
		unmap_low_page(pud);

		spin_lock(&init_mm.page_table_lock);
		pgd_populate(&init_mm, pgd, __va(pud_phys));
		spin_unlock(&init_mm.page_table_lock);
		pgd_changed = true;
	}

	if (pgd_changed)
		sync_global_pgds(addr, end);

	__flush_tlb_all();

	return last_map_addr;
}

#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
	memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0);
}
#endif

void __init paging_init(void)
{
	sparse_memory_present_with_active_regions(MAX_NUMNODES);
	sparse_init();

	/*
	 * clear the default setting with node 0
	 * note: don't use nodes_clear here, that is really clearing when
	 *	 numa support is not compiled in, and later node_set_state
	 *	 will not set it back.
	 */
	node_clear_state(0, N_MEMORY);
	if (N_MEMORY != N_NORMAL_MEMORY)
		node_clear_state(0, N_NORMAL_MEMORY);

	zone_sizes_init();
}

/*
 * Memory hotplug specific functions
 */
#ifdef CONFIG_MEMORY_HOTPLUG
/*
 * After memory hotplug the variables max_pfn, max_low_pfn and high_memory need
 * updating.
 */
static void  update_end_of_memory_vars(u64 start, u64 size)
{
	unsigned long end_pfn = PFN_UP(start + size);

	if (end_pfn > max_pfn) {
		max_pfn = end_pfn;
		max_low_pfn = end_pfn;
		high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1;
	}
}

/*
 * 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);
	if (last_mapped_pfn > max_pfn_mapped)
		max_pfn_mapped = last_mapped_pfn;

	ret = __add_pages(nid, zone, start_pfn, nr_pages);
	WARN_ON_ONCE(ret);

	/* update max_pfn, max_low_pfn and high_memory */
	update_end_of_memory_vars(start, size);

	return ret;
}
EXPORT_SYMBOL_GPL(arch_add_memory);

#endif /* CONFIG_MEMORY_HOTPLUG */

static struct kcore_list kcore_vsyscall;

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

	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

	absent_pages = absent_pages_in_range(0, max_pfn);
	reservedpages = max_pfn - totalram_pages - absent_pages;
	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_vsyscall, (void *)VSYSCALL_START,
			 VSYSCALL_END - VSYSCALL_START, KCORE_OTHER);

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

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

int kernel_set_to_readonly;

void set_kernel_text_rw(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long end = PFN_ALIGN(__stop___ex_table);

	if (!kernel_set_to_readonly)
		return;

	pr_debug("Set kernel text: %lx - %lx for read write\n",
		 start, end);

	/*
	 * Make the kernel identity mapping for text RW. Kernel text
	 * mapping will always be RO. Refer to the comment in
	 * static_protections() in pageattr.c
	 */
	set_memory_rw(start, (end - start) >> PAGE_SHIFT);
}

void set_kernel_text_ro(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long end = PFN_ALIGN(__stop___ex_table);

	if (!kernel_set_to_readonly)
		return;

	pr_debug("Set kernel text: %lx - %lx for read only\n",
		 start, end);

	/*
	 * Set the kernel identity mapping for text RO.
	 */
	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
}

void mark_rodata_ro(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long rodata_start =
		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
	unsigned long end = (unsigned long) &__end_rodata_hpage_align;
	unsigned long text_end = PAGE_ALIGN((unsigned long) &__stop___ex_table);
	unsigned long rodata_end = PAGE_ALIGN((unsigned long) &__end_rodata);
	unsigned long data_start = (unsigned long) &_sdata;

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

	kernel_set_to_readonly = 1;

	/*
	 * The rodata section (but not the kernel text!) should also be
	 * not-executable.
	 */
	set_memory_nx(rodata_start, (end - rodata_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

	free_init_pages("unused kernel memory",
			(unsigned long) page_address(virt_to_page(text_end)),
			(unsigned long)
				 page_address(virt_to_page(rodata_start)));
	free_init_pages("unused kernel memory",
			(unsigned long) page_address(virt_to_page(rodata_end)),
			(unsigned long) page_address(virt_to_page(data_start)));
}

#endif

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;

	if (pud_large(*pud))
		return pfn_valid(pud_pfn(*pud));

	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 mm_struct *mm)
{
#ifdef CONFIG_IA32_EMULATION
	if (!mm || mm->context.ia32_compat)
		return NULL;
#endif
	return &gate_vma;
}

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

	if (!vma)
		return 0;

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

/*
 * Use this when you have no reliable mm, typically from interrupt
 * context. It is less reliable than using a task's mm and may give
 * false positives.
 */
int in_gate_area_no_mm(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_X86_UV
unsigned long memory_block_size_bytes(void)
{
	if (is_uv_system()) {
		printk(KERN_INFO "UV: memory block size 2GB\n");
		return 2UL * 1024 * 1024 * 1024;
	}
	return MIN_MEMORY_BLOCK_SIZE;
}
#endif

#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
 * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
 */
static long __meminitdata addr_start, addr_end;
static void __meminitdata *p_start, *p_end;
static int __meminitdata node_start;

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) {
		void *p = NULL;

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

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

		if (!cpu_has_pse) {
			next = (addr + PAGE_SIZE) & PAGE_MASK;
			pmd = vmemmap_pmd_populate(pud, addr, node);

			if (!pmd)
				return -ENOMEM;

			p = vmemmap_pte_populate(pmd, addr, node);

			if (!p)
				return -ENOMEM;

			addr_end = addr + PAGE_SIZE;
			p_end = p + PAGE_SIZE;
		} else {
			next = pmd_addr_end(addr, end);

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

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

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

				/* check to see if we have contiguous blocks */
				if (p_end != p || node_start != node) {
					if (p_start)
						printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
						       addr_start, addr_end-1, p_start, p_end-1, node_start);
					addr_start = addr;
					node_start = node;
					p_start = p;
				}

				addr_end = addr + PMD_SIZE;
				p_end = p + PMD_SIZE;
			} else
				vmemmap_verify((pte_t *)pmd, node, addr, next);
		}

	}
	sync_global_pgds((unsigned long)start_page, end);
	return 0;
}

void __meminit vmemmap_populate_print_last(void)
{
	if (p_start) {
		printk(KERN_DEBUG " [%lx-%lx] PMD -> [%p-%p] on node %d\n",
			addr_start, addr_end-1, p_start, p_end-1, node_start);
		p_start = NULL;
		p_end = NULL;
		node_start = 0;
	}
}
#endif