summaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/init_32.c
blob: 63b09bae250940349d492693a5fee704577a6ab1 (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
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
/*
 *
 *  Copyright (C) 1995  Linus Torvalds
 *
 *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
 */

#include <linux/module.h>
#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/hugetlb.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/pci.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/bootmem.h>
#include <linux/memblock.h>
#include <linux/proc_fs.h>
#include <linux/memory_hotplug.h>
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <linux/gfp.h>

#include <asm/asm.h>
#include <asm/bios_ebda.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/dma.h>
#include <asm/fixmap.h>
#include <asm/e820.h>
#include <asm/apic.h>
#include <asm/bugs.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/pgalloc.h>
#include <asm/sections.h>
#include <asm/paravirt.h>
#include <asm/setup.h>
#include <asm/cacheflush.h>
#include <asm/page_types.h>
#include <asm/init.h>

unsigned long highstart_pfn, highend_pfn;

static noinline int do_test_wp_bit(void);

bool __read_mostly __vmalloc_start_set = false;

static __init void *alloc_low_page(void)
{
	unsigned long pfn = e820_table_end++;
	void *adr;

	if (pfn >= e820_table_top)
		panic("alloc_low_page: ran out of memory");

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

/*
 * Creates a middle page table and puts a pointer to it in the
 * given global directory entry. This only returns the gd entry
 * in non-PAE compilation mode, since the middle layer is folded.
 */
static pmd_t * __init one_md_table_init(pgd_t *pgd)
{
	pud_t *pud;
	pmd_t *pmd_table;

#ifdef CONFIG_X86_PAE
	if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
		if (after_bootmem)
			pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE);
		else
			pmd_table = (pmd_t *)alloc_low_page();
		paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
		set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
		pud = pud_offset(pgd, 0);
		BUG_ON(pmd_table != pmd_offset(pud, 0));

		return pmd_table;
	}
#endif
	pud = pud_offset(pgd, 0);
	pmd_table = pmd_offset(pud, 0);

	return pmd_table;
}

/*
 * Create a page table and place a pointer to it in a middle page
 * directory entry:
 */
static pte_t * __init one_page_table_init(pmd_t *pmd)
{
	if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
		pte_t *page_table = NULL;

		if (after_bootmem) {
#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
			page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
#endif
			if (!page_table)
				page_table =
				(pte_t *)alloc_bootmem_pages(PAGE_SIZE);
		} else
			page_table = (pte_t *)alloc_low_page();

		paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
		BUG_ON(page_table != pte_offset_kernel(pmd, 0));
	}

	return pte_offset_kernel(pmd, 0);
}

pmd_t * __init populate_extra_pmd(unsigned long vaddr)
{
	int pgd_idx = pgd_index(vaddr);
	int pmd_idx = pmd_index(vaddr);

	return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx;
}

pte_t * __init populate_extra_pte(unsigned long vaddr)
{
	int pte_idx = pte_index(vaddr);
	pmd_t *pmd;

	pmd = populate_extra_pmd(vaddr);
	return one_page_table_init(pmd) + pte_idx;
}

static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
					   unsigned long vaddr, pte_t *lastpte)
{
#ifdef CONFIG_HIGHMEM
	/*
	 * Something (early fixmap) may already have put a pte
	 * page here, which causes the page table allocation
	 * to become nonlinear. Attempt to fix it, and if it
	 * is still nonlinear then we have to bug.
	 */
	int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
	int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;

	if (pmd_idx_kmap_begin != pmd_idx_kmap_end
	    && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
	    && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
	    && ((__pa(pte) >> PAGE_SHIFT) < e820_table_start
		|| (__pa(pte) >> PAGE_SHIFT) >= e820_table_end)) {
		pte_t *newpte;
		int i;

		BUG_ON(after_bootmem);
		newpte = alloc_low_page();
		for (i = 0; i < PTRS_PER_PTE; i++)
			set_pte(newpte + i, pte[i]);

		paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
		set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
		BUG_ON(newpte != pte_offset_kernel(pmd, 0));
		__flush_tlb_all();

		paravirt_release_pte(__pa(pte) >> PAGE_SHIFT);
		pte = newpte;
	}
	BUG_ON(vaddr < fix_to_virt(FIX_KMAP_BEGIN - 1)
	       && vaddr > fix_to_virt(FIX_KMAP_END)
	       && lastpte && lastpte + PTRS_PER_PTE != pte);
#endif
	return pte;
}

/*
 * This function initializes a certain range of kernel virtual memory
 * with new bootmem page tables, everywhere page tables are missing in
 * the given range.
 *
 * NOTE: The pagetables are allocated contiguous on the physical space
 * so we can cache the place of the first one and move around without
 * checking the pgd every time.
 */
static void __init
page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
{
	int pgd_idx, pmd_idx;
	unsigned long vaddr;
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte = NULL;

	vaddr = start;
	pgd_idx = pgd_index(vaddr);
	pmd_idx = pmd_index(vaddr);
	pgd = pgd_base + pgd_idx;

	for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd++, pgd_idx++) {
		pmd = one_md_table_init(pgd);
		pmd = pmd + pmd_index(vaddr);
		for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
							pmd++, pmd_idx++) {
			pte = page_table_kmap_check(one_page_table_init(pmd),
			                            pmd, vaddr, pte);

			vaddr += PMD_SIZE;
		}
		pmd_idx = 0;
	}
}

static inline int is_kernel_text(unsigned long addr)
{
	if (addr >= PAGE_OFFSET && addr <= (unsigned long)__init_end)
		return 1;
	return 0;
}

/*
 * This maps the physical memory to kernel virtual address space, a total
 * of max_low_pfn pages, by creating page tables starting from address
 * PAGE_OFFSET:
 */
unsigned long __init
kernel_physical_mapping_init(unsigned long start,
			     unsigned long end,
			     unsigned long page_size_mask)
{
	int use_pse = page_size_mask == (1<<PG_LEVEL_2M);
	unsigned long last_map_addr = end;
	unsigned long start_pfn, end_pfn;
	pgd_t *pgd_base = swapper_pg_dir;
	int pgd_idx, pmd_idx, pte_ofs;
	unsigned long pfn;
	pgd_t *pgd;
	pmd_t *pmd;
	pte_t *pte;
	unsigned pages_2m, pages_4k;
	int mapping_iter;

	start_pfn = start >> PAGE_SHIFT;
	end_pfn = end >> PAGE_SHIFT;

	/*
	 * First iteration will setup identity mapping using large/small pages
	 * based on use_pse, with other attributes same as set by
	 * the early code in head_32.S
	 *
	 * Second iteration will setup the appropriate attributes (NX, GLOBAL..)
	 * as desired for the kernel identity mapping.
	 *
	 * This two pass mechanism conforms to the TLB app note which says:
	 *
	 *     "Software should not write to a paging-structure entry in a way
	 *      that would change, for any linear address, both the page size
	 *      and either the page frame or attributes."
	 */
	mapping_iter = 1;

	if (!cpu_has_pse)
		use_pse = 0;

repeat:
	pages_2m = pages_4k = 0;
	pfn = start_pfn;
	pgd_idx = pgd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
	pgd = pgd_base + pgd_idx;
	for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
		pmd = one_md_table_init(pgd);

		if (pfn >= end_pfn)
			continue;
#ifdef CONFIG_X86_PAE
		pmd_idx = pmd_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
		pmd += pmd_idx;
#else
		pmd_idx = 0;
#endif
		for (; pmd_idx < PTRS_PER_PMD && pfn < end_pfn;
		     pmd++, pmd_idx++) {
			unsigned int addr = pfn * PAGE_SIZE + PAGE_OFFSET;

			/*
			 * Map with big pages if possible, otherwise
			 * create normal page tables:
			 */
			if (use_pse) {
				unsigned int addr2;
				pgprot_t prot = PAGE_KERNEL_LARGE;
				/*
				 * first pass will use the same initial
				 * identity mapping attribute + _PAGE_PSE.
				 */
				pgprot_t init_prot =
					__pgprot(PTE_IDENT_ATTR |
						 _PAGE_PSE);

				addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
					PAGE_OFFSET + PAGE_SIZE-1;

				if (is_kernel_text(addr) ||
				    is_kernel_text(addr2))
					prot = PAGE_KERNEL_LARGE_EXEC;

				pages_2m++;
				if (mapping_iter == 1)
					set_pmd(pmd, pfn_pmd(pfn, init_prot));
				else
					set_pmd(pmd, pfn_pmd(pfn, prot));

				pfn += PTRS_PER_PTE;
				continue;
			}
			pte = one_page_table_init(pmd);

			pte_ofs = pte_index((pfn<<PAGE_SHIFT) + PAGE_OFFSET);
			pte += pte_ofs;
			for (; pte_ofs < PTRS_PER_PTE && pfn < end_pfn;
			     pte++, pfn++, pte_ofs++, addr += PAGE_SIZE) {
				pgprot_t prot = PAGE_KERNEL;
				/*
				 * first pass will use the same initial
				 * identity mapping attribute.
				 */
				pgprot_t init_prot = __pgprot(PTE_IDENT_ATTR);

				if (is_kernel_text(addr))
					prot = PAGE_KERNEL_EXEC;

				pages_4k++;
				if (mapping_iter == 1) {
					set_pte(pte, pfn_pte(pfn, init_prot));
					last_map_addr = (pfn << PAGE_SHIFT) + PAGE_SIZE;
				} else
					set_pte(pte, pfn_pte(pfn, prot));
			}
		}
	}
	if (mapping_iter == 1) {
		/*
		 * update direct mapping page count only in the first
		 * iteration.
		 */
		update_page_count(PG_LEVEL_2M, pages_2m);
		update_page_count(PG_LEVEL_4K, pages_4k);

		/*
		 * local global flush tlb, which will flush the previous
		 * mappings present in both small and large page TLB's.
		 */
		__flush_tlb_all();

		/*
		 * Second iteration will set the actual desired PTE attributes.
		 */
		mapping_iter = 2;
		goto repeat;
	}
	return last_map_addr;
}

pte_t *kmap_pte;
pgprot_t kmap_prot;

static inline pte_t *kmap_get_fixmap_pte(unsigned long vaddr)
{
	return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
			vaddr), vaddr), vaddr);
}

static void __init kmap_init(void)
{
	unsigned long kmap_vstart;

	/*
	 * Cache the first kmap pte:
	 */
	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
	kmap_pte = kmap_get_fixmap_pte(kmap_vstart);

	kmap_prot = PAGE_KERNEL;
}

#ifdef CONFIG_HIGHMEM
static void __init permanent_kmaps_init(pgd_t *pgd_base)
{
	unsigned long vaddr;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	vaddr = PKMAP_BASE;
	page_table_range_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, pgd_base);

	pgd = swapper_pg_dir + pgd_index(vaddr);
	pud = pud_offset(pgd, vaddr);
	pmd = pmd_offset(pud, vaddr);
	pte = pte_offset_kernel(pmd, vaddr);
	pkmap_page_table = pte;
}

static void __init add_one_highpage_init(struct page *page)
{
	ClearPageReserved(page);
	init_page_count(page);
	__free_page(page);
	totalhigh_pages++;
}

struct add_highpages_data {
	unsigned long start_pfn;
	unsigned long end_pfn;
};

static int __init add_highpages_work_fn(unsigned long start_pfn,
					 unsigned long end_pfn, void *datax)
{
	int node_pfn;
	struct page *page;
	unsigned long final_start_pfn, final_end_pfn;
	struct add_highpages_data *data;

	data = (struct add_highpages_data *)datax;

	final_start_pfn = max(start_pfn, data->start_pfn);
	final_end_pfn = min(end_pfn, data->end_pfn);
	if (final_start_pfn >= final_end_pfn)
		return 0;

	for (node_pfn = final_start_pfn; node_pfn < final_end_pfn;
	     node_pfn++) {
		if (!pfn_valid(node_pfn))
			continue;
		page = pfn_to_page(node_pfn);
		add_one_highpage_init(page);
	}

	return 0;

}

void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
					      unsigned long end_pfn)
{
	struct add_highpages_data data;

	data.start_pfn = start_pfn;
	data.end_pfn = end_pfn;

	work_with_active_regions(nid, add_highpages_work_fn, &data);
}

#else
static inline void permanent_kmaps_init(pgd_t *pgd_base)
{
}
#endif /* CONFIG_HIGHMEM */

void __init native_pagetable_setup_start(pgd_t *base)
{
	unsigned long pfn, va;
	pgd_t *pgd;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	/*
	 * Remove any mappings which extend past the end of physical
	 * memory from the boot time page table:
	 */
	for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
		va = PAGE_OFFSET + (pfn<<PAGE_SHIFT);
		pgd = base + pgd_index(va);
		if (!pgd_present(*pgd))
			break;

		pud = pud_offset(pgd, va);
		pmd = pmd_offset(pud, va);
		if (!pmd_present(*pmd))
			break;

		pte = pte_offset_kernel(pmd, va);
		if (!pte_present(*pte))
			break;

		pte_clear(NULL, va, pte);
	}
	paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
}

void __init native_pagetable_setup_done(pgd_t *base)
{
}

/*
 * Build a proper pagetable for the kernel mappings.  Up until this
 * point, we've been running on some set of pagetables constructed by
 * the boot process.
 *
 * If we're booting on native hardware, this will be a pagetable
 * constructed in arch/x86/kernel/head_32.S.  The root of the
 * pagetable will be swapper_pg_dir.
 *
 * If we're booting paravirtualized under a hypervisor, then there are
 * more options: we may already be running PAE, and the pagetable may
 * or may not be based in swapper_pg_dir.  In any case,
 * paravirt_pagetable_setup_start() will set up swapper_pg_dir
 * appropriately for the rest of the initialization to work.
 *
 * In general, pagetable_init() assumes that the pagetable may already
 * be partially populated, and so it avoids stomping on any existing
 * mappings.
 */
void __init early_ioremap_page_table_range_init(void)
{
	pgd_t *pgd_base = swapper_pg_dir;
	unsigned long vaddr, end;

	/*
	 * Fixed mappings, only the page table structure has to be
	 * created - mappings will be set by set_fixmap():
	 */
	vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
	end = (FIXADDR_TOP + PMD_SIZE - 1) & PMD_MASK;
	page_table_range_init(vaddr, end, pgd_base);
	early_ioremap_reset();
}

static void __init pagetable_init(void)
{
	pgd_t *pgd_base = swapper_pg_dir;

	permanent_kmaps_init(pgd_base);
}

#ifdef CONFIG_ACPI_SLEEP
/*
 * ACPI suspend needs this for resume, because things like the intel-agp
 * driver might have split up a kernel 4MB mapping.
 */
char swsusp_pg_dir[PAGE_SIZE]
	__attribute__ ((aligned(PAGE_SIZE)));

static inline void save_pg_dir(void)
{
	memcpy(swsusp_pg_dir, swapper_pg_dir, PAGE_SIZE);
}
#else /* !CONFIG_ACPI_SLEEP */
static inline void save_pg_dir(void)
{
}
#endif /* !CONFIG_ACPI_SLEEP */

void zap_low_mappings(bool early)
{
	int i;

	/*
	 * Zap initial low-memory mappings.
	 *
	 * Note that "pgd_clear()" doesn't do it for
	 * us, because pgd_clear() is a no-op on i386.
	 */
	for (i = 0; i < KERNEL_PGD_BOUNDARY; i++) {
#ifdef CONFIG_X86_PAE
		set_pgd(swapper_pg_dir+i, __pgd(1 + __pa(empty_zero_page)));
#else
		set_pgd(swapper_pg_dir+i, __pgd(0));
#endif
	}

	if (early)
		__flush_tlb();
	else
		flush_tlb_all();
}

pteval_t __supported_pte_mask __read_mostly = ~(_PAGE_NX | _PAGE_GLOBAL | _PAGE_IOMAP);
EXPORT_SYMBOL_GPL(__supported_pte_mask);

/* user-defined highmem size */
static unsigned int highmem_pages = -1;

/*
 * highmem=size forces highmem to be exactly 'size' bytes.
 * This works even on boxes that have no highmem otherwise.
 * This also works to reduce highmem size on bigger boxes.
 */
static int __init parse_highmem(char *arg)
{
	if (!arg)
		return -EINVAL;

	highmem_pages = memparse(arg, &arg) >> PAGE_SHIFT;
	return 0;
}
early_param("highmem", parse_highmem);

#define MSG_HIGHMEM_TOO_BIG \
	"highmem size (%luMB) is bigger than pages available (%luMB)!\n"

#define MSG_LOWMEM_TOO_SMALL \
	"highmem size (%luMB) results in <64MB lowmem, ignoring it!\n"
/*
 * All of RAM fits into lowmem - but if user wants highmem
 * artificially via the highmem=x boot parameter then create
 * it:
 */
void __init lowmem_pfn_init(void)
{
	/* max_low_pfn is 0, we already have early_res support */
	max_low_pfn = max_pfn;

	if (highmem_pages == -1)
		highmem_pages = 0;
#ifdef CONFIG_HIGHMEM
	if (highmem_pages >= max_pfn) {
		printk(KERN_ERR MSG_HIGHMEM_TOO_BIG,
			pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
		highmem_pages = 0;
	}
	if (highmem_pages) {
		if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) {
			printk(KERN_ERR MSG_LOWMEM_TOO_SMALL,
				pages_to_mb(highmem_pages));
			highmem_pages = 0;
		}
		max_low_pfn -= highmem_pages;
	}
#else
	if (highmem_pages)
		printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
#endif
}

#define MSG_HIGHMEM_TOO_SMALL \
	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"

#define MSG_HIGHMEM_TRIMMED \
	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
/*
 * We have more RAM than fits into lowmem - we try to put it into
 * highmem, also taking the highmem=x boot parameter into account:
 */
void __init highmem_pfn_init(void)
{
	max_low_pfn = MAXMEM_PFN;

	if (highmem_pages == -1)
		highmem_pages = max_pfn - MAXMEM_PFN;

	if (highmem_pages + MAXMEM_PFN < max_pfn)
		max_pfn = MAXMEM_PFN + highmem_pages;

	if (highmem_pages + MAXMEM_PFN > max_pfn) {
		printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL,
			pages_to_mb(max_pfn - MAXMEM_PFN),
			pages_to_mb(highmem_pages));
		highmem_pages = 0;
	}
#ifndef CONFIG_HIGHMEM
	/* Maximum memory usable is what is directly addressable */
	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
	if (max_pfn > MAX_NONPAE_PFN)
		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
	else
		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
	max_pfn = MAXMEM_PFN;
#else /* !CONFIG_HIGHMEM */
#ifndef CONFIG_HIGHMEM64G
	if (max_pfn > MAX_NONPAE_PFN) {
		max_pfn = MAX_NONPAE_PFN;
		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
	}
#endif /* !CONFIG_HIGHMEM64G */
#endif /* !CONFIG_HIGHMEM */
}

/*
 * Determine low and high memory ranges:
 */
void __init find_low_pfn_range(void)
{
	/* it could update max_pfn */

	if (max_pfn <= MAXMEM_PFN)
		lowmem_pfn_init();
	else
		highmem_pfn_init();
}

#ifndef CONFIG_NEED_MULTIPLE_NODES
void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn,
				int acpi, int k8)
{
#ifdef CONFIG_HIGHMEM
	highstart_pfn = highend_pfn = max_pfn;
	if (max_pfn > max_low_pfn)
		highstart_pfn = max_low_pfn;
	memblock_x86_register_active_regions(0, 0, highend_pfn);
	sparse_memory_present_with_active_regions(0);
	printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
		pages_to_mb(highend_pfn - highstart_pfn));
	num_physpages = highend_pfn;
	high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
#else
	memblock_x86_register_active_regions(0, 0, max_low_pfn);
	sparse_memory_present_with_active_regions(0);
	num_physpages = max_low_pfn;
	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
#endif
#ifdef CONFIG_FLATMEM
	max_mapnr = num_physpages;
#endif
	__vmalloc_start_set = true;

	printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
			pages_to_mb(max_low_pfn));

	setup_bootmem_allocator();
}
#endif /* !CONFIG_NEED_MULTIPLE_NODES */

static void __init zone_sizes_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES];
	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
	max_zone_pfns[ZONE_DMA] =
		virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
#ifdef CONFIG_HIGHMEM
	max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
#endif

	free_area_init_nodes(max_zone_pfns);
}

#ifndef CONFIG_NO_BOOTMEM
static unsigned long __init setup_node_bootmem(int nodeid,
				 unsigned long start_pfn,
				 unsigned long end_pfn,
				 unsigned long bootmap)
{
	unsigned long bootmap_size;

	/* don't touch min_low_pfn */
	bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
					 bootmap >> PAGE_SHIFT,
					 start_pfn, end_pfn);
	printk(KERN_INFO "  node %d low ram: %08lx - %08lx\n",
		nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT);
	printk(KERN_INFO "  node %d bootmap %08lx - %08lx\n",
		 nodeid, bootmap, bootmap + bootmap_size);
	free_bootmem_with_active_regions(nodeid, end_pfn);

	return bootmap + bootmap_size;
}
#endif

void __init setup_bootmem_allocator(void)
{
#ifndef CONFIG_NO_BOOTMEM
	int nodeid;
	phys_addr_t bootmap_size, bootmap;
	/*
	 * Initialize the boot-time allocator (with low memory only):
	 */
	bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT;
	bootmap = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size,
				 PAGE_SIZE);
	if (bootmap == MEMBLOCK_ERROR)
		panic("Cannot find bootmem map of size %ld\n", bootmap_size);
	memblock_x86_reserve_range(bootmap, bootmap + bootmap_size, "BOOTMAP");
#endif

	printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
		 max_pfn_mapped<<PAGE_SHIFT);
	printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);

#ifndef CONFIG_NO_BOOTMEM
	for_each_online_node(nodeid) {
		 unsigned long start_pfn, end_pfn;

#ifdef CONFIG_NEED_MULTIPLE_NODES
		start_pfn = node_start_pfn[nodeid];
		end_pfn = node_end_pfn[nodeid];
		if (start_pfn > max_low_pfn)
			continue;
		if (end_pfn > max_low_pfn)
			end_pfn = max_low_pfn;
#else
		start_pfn = 0;
		end_pfn = max_low_pfn;
#endif
		bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn,
						 bootmap);
	}
#endif

	after_bootmem = 1;
}

/*
 * paging_init() sets up the page tables - note that the first 8MB are
 * already mapped by head.S.
 *
 * This routines also unmaps the page at virtual kernel address 0, so
 * that we can trap those pesky NULL-reference errors in the kernel.
 */
void __init paging_init(void)
{
	pagetable_init();

	__flush_tlb_all();

	kmap_init();

	/*
	 * NOTE: at this point the bootmem allocator is fully available.
	 */
	sparse_init();
	zone_sizes_init();
}

/*
 * Test if the WP bit works in supervisor mode. It isn't supported on 386's
 * and also on some strange 486's. All 586+'s are OK. This used to involve
 * black magic jumps to work around some nasty CPU bugs, but fortunately the
 * switch to using exceptions got rid of all that.
 */
static void __init test_wp_bit(void)
{
	printk(KERN_INFO
  "Checking if this processor honours the WP bit even in supervisor mode...");

	/* Any page-aligned address will do, the test is non-destructive */
	__set_fixmap(FIX_WP_TEST, __pa(&swapper_pg_dir), PAGE_READONLY);
	boot_cpu_data.wp_works_ok = do_test_wp_bit();
	clear_fixmap(FIX_WP_TEST);

	if (!boot_cpu_data.wp_works_ok) {
		printk(KERN_CONT "No.\n");
#ifdef CONFIG_X86_WP_WORKS_OK
		panic(
  "This kernel doesn't support CPU's with broken WP. Recompile it for a 386!");
#endif
	} else {
		printk(KERN_CONT "Ok.\n");
	}
}

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

	pci_iommu_alloc();

#ifdef CONFIG_FLATMEM
	BUG_ON(!mem_map);
#endif
	/* this will put all low memory onto the freelists */
	totalram_pages += free_all_bootmem();

	reservedpages = 0;
	for (tmp = 0; tmp < max_low_pfn; tmp++)
		/*
		 * Only count reserved RAM pages:
		 */
		if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
			reservedpages++;

	set_highmem_pages_init();

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

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

	printk(KERN_INFO "virtual kernel memory layout:\n"
		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
#ifdef CONFIG_HIGHMEM
		"    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\n"
#endif
		"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
		"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
		"      .init : 0x%08lx - 0x%08lx   (%4ld kB)\n"
		"      .data : 0x%08lx - 0x%08lx   (%4ld kB)\n"
		"      .text : 0x%08lx - 0x%08lx   (%4ld kB)\n",
		FIXADDR_START, FIXADDR_TOP,
		(FIXADDR_TOP - FIXADDR_START) >> 10,

#ifdef CONFIG_HIGHMEM
		PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
		(LAST_PKMAP*PAGE_SIZE) >> 10,
#endif

		VMALLOC_START, VMALLOC_END,
		(VMALLOC_END - VMALLOC_START) >> 20,

		(unsigned long)__va(0), (unsigned long)high_memory,
		((unsigned long)high_memory - (unsigned long)__va(0)) >> 20,

		(unsigned long)&__init_begin, (unsigned long)&__init_end,
		((unsigned long)&__init_end -
		 (unsigned long)&__init_begin) >> 10,

		(unsigned long)&_etext, (unsigned long)&_edata,
		((unsigned long)&_edata - (unsigned long)&_etext) >> 10,

		(unsigned long)&_text, (unsigned long)&_etext,
		((unsigned long)&_etext - (unsigned long)&_text) >> 10);

	/*
	 * Check boundaries twice: Some fundamental inconsistencies can
	 * be detected at build time already.
	 */
#define __FIXADDR_TOP (-PAGE_SIZE)
#ifdef CONFIG_HIGHMEM
	BUILD_BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
	BUILD_BUG_ON(VMALLOC_END			> PKMAP_BASE);
#endif
#define high_memory (-128UL << 20)
	BUILD_BUG_ON(VMALLOC_START			>= VMALLOC_END);
#undef high_memory
#undef __FIXADDR_TOP

#ifdef CONFIG_HIGHMEM
	BUG_ON(PKMAP_BASE + LAST_PKMAP*PAGE_SIZE	> FIXADDR_START);
	BUG_ON(VMALLOC_END				> PKMAP_BASE);
#endif
	BUG_ON(VMALLOC_START				>= VMALLOC_END);
	BUG_ON((unsigned long)high_memory		> VMALLOC_START);

	if (boot_cpu_data.wp_works_ok < 0)
		test_wp_bit();

	save_pg_dir();
	zap_low_mappings(true);
}

#ifdef CONFIG_MEMORY_HOTPLUG
int arch_add_memory(int nid, u64 start, u64 size)
{
	struct pglist_data *pgdata = NODE_DATA(nid);
	struct zone *zone = pgdata->node_zones + ZONE_HIGHMEM;
	unsigned long start_pfn = start >> PAGE_SHIFT;
	unsigned long nr_pages = size >> PAGE_SHIFT;

	return __add_pages(nid, zone, start_pfn, nr_pages);
}
#endif

/*
 * This function cannot be __init, since exceptions don't work in that
 * section.  Put this after the callers, so that it cannot be inlined.
 */
static noinline int do_test_wp_bit(void)
{
	char tmp_reg;
	int flag;

	__asm__ __volatile__(
		"	movb %0, %1	\n"
		"1:	movb %1, %0	\n"
		"	xorl %2, %2	\n"
		"2:			\n"
		_ASM_EXTABLE(1b,2b)
		:"=m" (*(char *)fix_to_virt(FIX_WP_TEST)),
		 "=q" (tmp_reg),
		 "=r" (flag)
		:"2" (1)
		:"memory");

	return flag;
}

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

int kernel_set_to_readonly __read_mostly;

void set_kernel_text_rw(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long size = PFN_ALIGN(_etext) - start;

	if (!kernel_set_to_readonly)
		return;

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

	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
}

void set_kernel_text_ro(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long size = PFN_ALIGN(_etext) - start;

	if (!kernel_set_to_readonly)
		return;

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

	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
}

void mark_rodata_ro(void)
{
	unsigned long start = PFN_ALIGN(_text);
	unsigned long size = PFN_ALIGN(_etext) - start;

	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
	printk(KERN_INFO "Write protecting the kernel text: %luk\n",
		size >> 10);

	kernel_set_to_readonly = 1;

#ifdef CONFIG_CPA_DEBUG
	printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
		start, start+size);
	set_pages_rw(virt_to_page(start), size>>PAGE_SHIFT);

	printk(KERN_INFO "Testing CPA: write protecting again\n");
	set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
#endif

	start += size;
	size = (unsigned long)__end_rodata - start;
	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
		size >> 10);
	rodata_test();

#ifdef CONFIG_CPA_DEBUG
	printk(KERN_INFO "Testing CPA: undo %lx-%lx\n", start, start + size);
	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);

	printk(KERN_INFO "Testing CPA: write protecting again\n");
	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
#endif
}
#endif