aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/mm/init.c
blob: 8dacdb96899ec5a76749751d2675b5b827855141 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
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
#include <linux/gfp.h>
#include <linux/initrd.h>
#include <linux/ioport.h>
#include <linux/swap.h>
#include <linux/memblock.h>
#include <linux/swapfile.h>
#include <linux/swapops.h>
#include <linux/kmemleak.h>

#include <asm/set_memory.h>
#include <asm/e820/api.h>
#include <asm/init.h>
#include <asm/page.h>
#include <asm/page_types.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <asm/proto.h>
#include <asm/dma.h>		/* for MAX_DMA_PFN */
#include <asm/microcode.h>
#include <asm/kaslr.h>
#include <asm/hypervisor.h>
#include <asm/cpufeature.h>
#include <asm/pti.h>

/*
 * We need to define the tracepoints somewhere, and tlb.c
 * is only compied when SMP=y.
 */
#define CREATE_TRACE_POINTS
#include <trace/events/tlb.h>

#include "mm_internal.h"

/*
 * Tables translating between page_cache_type_t and pte encoding.
 *
 * The default values are defined statically as minimal supported mode;
 * WC and WT fall back to UC-.  pat_init() updates these values to support
 * more cache modes, WC and WT, when it is safe to do so.  See pat_init()
 * for the details.  Note, __early_ioremap() used during early boot-time
 * takes pgprot_t (pte encoding) and does not use these tables.
 *
 *   Index into __cachemode2pte_tbl[] is the cachemode.
 *
 *   Index into __pte2cachemode_tbl[] are the caching attribute bits of the pte
 *   (_PAGE_PWT, _PAGE_PCD, _PAGE_PAT) at index bit positions 0, 1, 2.
 */
uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM] = {
	[_PAGE_CACHE_MODE_WB      ]	= 0         | 0        ,
	[_PAGE_CACHE_MODE_WC      ]	= 0         | _PAGE_PCD,
	[_PAGE_CACHE_MODE_UC_MINUS]	= 0         | _PAGE_PCD,
	[_PAGE_CACHE_MODE_UC      ]	= _PAGE_PWT | _PAGE_PCD,
	[_PAGE_CACHE_MODE_WT      ]	= 0         | _PAGE_PCD,
	[_PAGE_CACHE_MODE_WP      ]	= 0         | _PAGE_PCD,
};
EXPORT_SYMBOL(__cachemode2pte_tbl);

uint8_t __pte2cachemode_tbl[8] = {
	[__pte2cm_idx( 0        | 0         | 0        )] = _PAGE_CACHE_MODE_WB,
	[__pte2cm_idx(_PAGE_PWT | 0         | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
	[__pte2cm_idx( 0        | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC_MINUS,
	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | 0        )] = _PAGE_CACHE_MODE_UC,
	[__pte2cm_idx( 0        | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_WB,
	[__pte2cm_idx(_PAGE_PWT | 0         | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
	[__pte2cm_idx(0         | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC_MINUS,
	[__pte2cm_idx(_PAGE_PWT | _PAGE_PCD | _PAGE_PAT)] = _PAGE_CACHE_MODE_UC,
};
EXPORT_SYMBOL(__pte2cachemode_tbl);

static unsigned long __initdata pgt_buf_start;
static unsigned long __initdata pgt_buf_end;
static unsigned long __initdata pgt_buf_top;

static unsigned long min_pfn_mapped;

static bool __initdata can_use_brk_pgt = true;

/*
 * Pages returned are already directly mapped.
 *
 * Changing that is likely to break Xen, see commit:
 *
 *    279b706 x86,xen: introduce x86_init.mapping.pagetable_reserve
 *
 * for detailed information.
 */
__ref void *alloc_low_pages(unsigned int num)
{
	unsigned long pfn;
	int i;

	if (after_bootmem) {
		unsigned int order;

		order = get_order((unsigned long)num << PAGE_SHIFT);
		return (void *)__get_free_pages(GFP_ATOMIC | __GFP_ZERO, order);
	}

	if ((pgt_buf_end + num) > pgt_buf_top || !can_use_brk_pgt) {
		unsigned long ret = 0;

		if (min_pfn_mapped < max_pfn_mapped) {
			ret = memblock_find_in_range(
					min_pfn_mapped << PAGE_SHIFT,
					max_pfn_mapped << PAGE_SHIFT,
					PAGE_SIZE * num , PAGE_SIZE);
		}
		if (ret)
			memblock_reserve(ret, PAGE_SIZE * num);
		else if (can_use_brk_pgt)
			ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE));

		if (!ret)
			panic("alloc_low_pages: can not alloc memory");

		pfn = ret >> PAGE_SHIFT;
	} else {
		pfn = pgt_buf_end;
		pgt_buf_end += num;
		printk(KERN_DEBUG "BRK [%#010lx, %#010lx] PGTABLE\n",
			pfn << PAGE_SHIFT, (pgt_buf_end << PAGE_SHIFT) - 1);
	}

	for (i = 0; i < num; i++) {
		void *adr;

		adr = __va((pfn + i) << PAGE_SHIFT);
		clear_page(adr);
	}

	return __va(pfn << PAGE_SHIFT);
}

/*
 * By default need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS.
 * With KASLR memory randomization, depending on the machine e820 memory
 * and the PUD alignment. We may need twice more pages when KASLR memory
 * randomization is enabled.
 */
#ifndef CONFIG_RANDOMIZE_MEMORY
#define INIT_PGD_PAGE_COUNT      6
#else
#define INIT_PGD_PAGE_COUNT      12
#endif
#define INIT_PGT_BUF_SIZE	(INIT_PGD_PAGE_COUNT * PAGE_SIZE)
RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
void  __init early_alloc_pgt_buf(void)
{
	unsigned long tables = INIT_PGT_BUF_SIZE;
	phys_addr_t base;

	base = __pa(extend_brk(tables, PAGE_SIZE));

	pgt_buf_start = base >> PAGE_SHIFT;
	pgt_buf_end = pgt_buf_start;
	pgt_buf_top = pgt_buf_start + (tables >> PAGE_SHIFT);
}

int after_bootmem;

early_param_on_off("gbpages", "nogbpages", direct_gbpages, CONFIG_X86_DIRECT_GBPAGES);

struct map_range {
	unsigned long start;
	unsigned long end;
	unsigned page_size_mask;
};

static int page_size_mask;

static void __init probe_page_size_mask(void)
{
	/*
	 * For pagealloc debugging, identity mapping will use small pages.
	 * This will simplify cpa(), which otherwise needs to support splitting
	 * large pages into small in interrupt context, etc.
	 */
	if (boot_cpu_has(X86_FEATURE_PSE) && !debug_pagealloc_enabled())
		page_size_mask |= 1 << PG_LEVEL_2M;
	else
		direct_gbpages = 0;

	/* Enable PSE if available */
	if (boot_cpu_has(X86_FEATURE_PSE))
		cr4_set_bits_and_update_boot(X86_CR4_PSE);

	/* Enable PGE if available */
	__supported_pte_mask &= ~_PAGE_GLOBAL;
	if (boot_cpu_has(X86_FEATURE_PGE)) {
		cr4_set_bits_and_update_boot(X86_CR4_PGE);
		__supported_pte_mask |= _PAGE_GLOBAL;
	}

	/* By the default is everything supported: */
	__default_kernel_pte_mask = __supported_pte_mask;
	/* Except when with PTI where the kernel is mostly non-Global: */
	if (cpu_feature_enabled(X86_FEATURE_PTI))
		__default_kernel_pte_mask &= ~_PAGE_GLOBAL;

	/* Enable 1 GB linear kernel mappings if available: */
	if (direct_gbpages && boot_cpu_has(X86_FEATURE_GBPAGES)) {
		printk(KERN_INFO "Using GB pages for direct mapping\n");
		page_size_mask |= 1 << PG_LEVEL_1G;
	} else {
		direct_gbpages = 0;
	}
}

static void setup_pcid(void)
{
	if (!IS_ENABLED(CONFIG_X86_64))
		return;

	if (!boot_cpu_has(X86_FEATURE_PCID))
		return;

	if (boot_cpu_has(X86_FEATURE_PGE)) {
		/*
		 * This can't be cr4_set_bits_and_update_boot() -- the
		 * trampoline code can't handle CR4.PCIDE and it wouldn't
		 * do any good anyway.  Despite the name,
		 * cr4_set_bits_and_update_boot() doesn't actually cause
		 * the bits in question to remain set all the way through
		 * the secondary boot asm.
		 *
		 * Instead, we brute-force it and set CR4.PCIDE manually in
		 * start_secondary().
		 */
		cr4_set_bits(X86_CR4_PCIDE);

		/*
		 * INVPCID's single-context modes (2/3) only work if we set
		 * X86_CR4_PCIDE, *and* we INVPCID support.  It's unusable
		 * on systems that have X86_CR4_PCIDE clear, or that have
		 * no INVPCID support at all.
		 */
		if (boot_cpu_has(X86_FEATURE_INVPCID))
			setup_force_cpu_cap(X86_FEATURE_INVPCID_SINGLE);
	} else {
		/*
		 * flush_tlb_all(), as currently implemented, won't work if
		 * PCID is on but PGE is not.  Since that combination
		 * doesn't exist on real hardware, there's no reason to try
		 * to fully support it, but it's polite to avoid corrupting
		 * data if we're on an improperly configured VM.
		 */
		setup_clear_cpu_cap(X86_FEATURE_PCID);
	}
}

#ifdef CONFIG_X86_32
#define NR_RANGE_MR 3
#else /* CONFIG_X86_64 */
#define NR_RANGE_MR 5
#endif

static int __meminit save_mr(struct map_range *mr, int nr_range,
			     unsigned long start_pfn, unsigned long end_pfn,
			     unsigned long page_size_mask)
{
	if (start_pfn < end_pfn) {
		if (nr_range >= NR_RANGE_MR)
			panic("run out of range for init_memory_mapping\n");
		mr[nr_range].start = start_pfn<<PAGE_SHIFT;
		mr[nr_range].end   = end_pfn<<PAGE_SHIFT;
		mr[nr_range].page_size_mask = page_size_mask;
		nr_range++;
	}

	return nr_range;
}

/*
 * adjust the page_size_mask for small range to go with
 *	big page size instead small one if nearby are ram too.
 */
static void __ref adjust_range_page_size_mask(struct map_range *mr,
							 int nr_range)
{
	int i;

	for (i = 0; i < nr_range; i++) {
		if ((page_size_mask & (1<<PG_LEVEL_2M)) &&
		    !(mr[i].page_size_mask & (1<<PG_LEVEL_2M))) {
			unsigned long start = round_down(mr[i].start, PMD_SIZE);
			unsigned long end = round_up(mr[i].end, PMD_SIZE);

#ifdef CONFIG_X86_32
			if ((end >> PAGE_SHIFT) > max_low_pfn)
				continue;
#endif

			if (memblock_is_region_memory(start, end - start))
				mr[i].page_size_mask |= 1<<PG_LEVEL_2M;
		}
		if ((page_size_mask & (1<<PG_LEVEL_1G)) &&
		    !(mr[i].page_size_mask & (1<<PG_LEVEL_1G))) {
			unsigned long start = round_down(mr[i].start, PUD_SIZE);
			unsigned long end = round_up(mr[i].end, PUD_SIZE);

			if (memblock_is_region_memory(start, end - start))
				mr[i].page_size_mask |= 1<<PG_LEVEL_1G;
		}
	}
}

static const char *page_size_string(struct map_range *mr)
{
	static const char str_1g[] = "1G";
	static const char str_2m[] = "2M";
	static const char str_4m[] = "4M";
	static const char str_4k[] = "4k";

	if (mr->page_size_mask & (1<<PG_LEVEL_1G))
		return str_1g;
	/*
	 * 32-bit without PAE has a 4M large page size.
	 * PG_LEVEL_2M is misnamed, but we can at least
	 * print out the right size in the string.
	 */
	if (IS_ENABLED(CONFIG_X86_32) &&
	    !IS_ENABLED(CONFIG_X86_PAE) &&
	    mr->page_size_mask & (1<<PG_LEVEL_2M))
		return str_4m;

	if (mr->page_size_mask & (1<<PG_LEVEL_2M))
		return str_2m;

	return str_4k;
}

static int __meminit split_mem_range(struct map_range *mr, int nr_range,
				     unsigned long start,
				     unsigned long end)
{
	unsigned long start_pfn, end_pfn, limit_pfn;
	unsigned long pfn;
	int i;

	limit_pfn = PFN_DOWN(end);

	/* head if not big page alignment ? */
	pfn = start_pfn = PFN_DOWN(start);
#ifdef CONFIG_X86_32
	/*
	 * Don't use a large page for the first 2/4MB of memory
	 * because there are often fixed size MTRRs in there
	 * and overlapping MTRRs into large pages can cause
	 * slowdowns.
	 */
	if (pfn == 0)
		end_pfn = PFN_DOWN(PMD_SIZE);
	else
		end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
#else /* CONFIG_X86_64 */
	end_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
#endif
	if (end_pfn > limit_pfn)
		end_pfn = limit_pfn;
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
		pfn = end_pfn;
	}

	/* big page (2M) range */
	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
#ifdef CONFIG_X86_32
	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
#else /* CONFIG_X86_64 */
	end_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
	if (end_pfn > round_down(limit_pfn, PFN_DOWN(PMD_SIZE)))
		end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
#endif

	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask & (1<<PG_LEVEL_2M));
		pfn = end_pfn;
	}

#ifdef CONFIG_X86_64
	/* big page (1G) range */
	start_pfn = round_up(pfn, PFN_DOWN(PUD_SIZE));
	end_pfn = round_down(limit_pfn, PFN_DOWN(PUD_SIZE));
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask &
				 ((1<<PG_LEVEL_2M)|(1<<PG_LEVEL_1G)));
		pfn = end_pfn;
	}

	/* tail is not big page (1G) alignment */
	start_pfn = round_up(pfn, PFN_DOWN(PMD_SIZE));
	end_pfn = round_down(limit_pfn, PFN_DOWN(PMD_SIZE));
	if (start_pfn < end_pfn) {
		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn,
				page_size_mask & (1<<PG_LEVEL_2M));
		pfn = end_pfn;
	}
#endif

	/* tail is not big page (2M) alignment */
	start_pfn = pfn;
	end_pfn = limit_pfn;
	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);

	if (!after_bootmem)
		adjust_range_page_size_mask(mr, nr_range);

	/* try to merge same page size and continuous */
	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
		unsigned long old_start;
		if (mr[i].end != mr[i+1].start ||
		    mr[i].page_size_mask != mr[i+1].page_size_mask)
			continue;
		/* move it */
		old_start = mr[i].start;
		memmove(&mr[i], &mr[i+1],
			(nr_range - 1 - i) * sizeof(struct map_range));
		mr[i--].start = old_start;
		nr_range--;
	}

	for (i = 0; i < nr_range; i++)
		pr_debug(" [mem %#010lx-%#010lx] page %s\n",
				mr[i].start, mr[i].end - 1,
				page_size_string(&mr[i]));

	return nr_range;
}

struct range pfn_mapped[E820_MAX_ENTRIES];
int nr_pfn_mapped;

static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
{
	nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES,
					     nr_pfn_mapped, start_pfn, end_pfn);
	nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES);

	max_pfn_mapped = max(max_pfn_mapped, end_pfn);

	if (start_pfn < (1UL<<(32-PAGE_SHIFT)))
		max_low_pfn_mapped = max(max_low_pfn_mapped,
					 min(end_pfn, 1UL<<(32-PAGE_SHIFT)));
}

bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
{
	int i;

	for (i = 0; i < nr_pfn_mapped; i++)
		if ((start_pfn >= pfn_mapped[i].start) &&
		    (end_pfn <= pfn_mapped[i].end))
			return true;

	return false;
}

/*
 * 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 __ref init_memory_mapping(unsigned long start,
					       unsigned long end)
{
	struct map_range mr[NR_RANGE_MR];
	unsigned long ret = 0;
	int nr_range, i;

	pr_debug("init_memory_mapping: [mem %#010lx-%#010lx]\n",
	       start, end - 1);

	memset(mr, 0, sizeof(mr));
	nr_range = split_mem_range(mr, 0, start, end);

	for (i = 0; i < nr_range; i++)
		ret = kernel_physical_mapping_init(mr[i].start, mr[i].end,
						   mr[i].page_size_mask);

	add_pfn_range_mapped(start >> PAGE_SHIFT, ret >> PAGE_SHIFT);

	return ret >> PAGE_SHIFT;
}

/*
 * We need to iterate through the E820 memory map and create direct mappings
 * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply
 * create direct mappings for all pfns from [0 to max_low_pfn) and
 * [4GB to max_pfn) because of possible memory holes in high addresses
 * that cannot be marked as UC by fixed/variable range MTRRs.
 * Depending on the alignment of E820 ranges, this may possibly result
 * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
 *
 * init_mem_mapping() calls init_range_memory_mapping() with big range.
 * That range would have hole in the middle or ends, and only ram parts
 * will be mapped in init_range_memory_mapping().
 */
static unsigned long __init init_range_memory_mapping(
					   unsigned long r_start,
					   unsigned long r_end)
{
	unsigned long start_pfn, end_pfn;
	unsigned long mapped_ram_size = 0;
	int i;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
		u64 start = clamp_val(PFN_PHYS(start_pfn), r_start, r_end);
		u64 end = clamp_val(PFN_PHYS(end_pfn), r_start, r_end);
		if (start >= end)
			continue;

		/*
		 * if it is overlapping with brk pgt, we need to
		 * alloc pgt buf from memblock instead.
		 */
		can_use_brk_pgt = max(start, (u64)pgt_buf_end<<PAGE_SHIFT) >=
				    min(end, (u64)pgt_buf_top<<PAGE_SHIFT);
		init_memory_mapping(start, end);
		mapped_ram_size += end - start;
		can_use_brk_pgt = true;
	}

	return mapped_ram_size;
}

static unsigned long __init get_new_step_size(unsigned long step_size)
{
	/*
	 * Initial mapped size is PMD_SIZE (2M).
	 * We can not set step_size to be PUD_SIZE (1G) yet.
	 * In worse case, when we cross the 1G boundary, and
	 * PG_LEVEL_2M is not set, we will need 1+1+512 pages (2M + 8k)
	 * to map 1G range with PTE. Hence we use one less than the
	 * difference of page table level shifts.
	 *
	 * Don't need to worry about overflow in the top-down case, on 32bit,
	 * when step_size is 0, round_down() returns 0 for start, and that
	 * turns it into 0x100000000ULL.
	 * In the bottom-up case, round_up(x, 0) returns 0 though too, which
	 * needs to be taken into consideration by the code below.
	 */
	return step_size << (PMD_SHIFT - PAGE_SHIFT - 1);
}

/**
 * memory_map_top_down - Map [map_start, map_end) top down
 * @map_start: start address of the target memory range
 * @map_end: end address of the target memory range
 *
 * This function will setup direct mapping for memory range
 * [map_start, map_end) in top-down. That said, the page tables
 * will be allocated at the end of the memory, and we map the
 * memory in top-down.
 */
static void __init memory_map_top_down(unsigned long map_start,
				       unsigned long map_end)
{
	unsigned long real_end, start, last_start;
	unsigned long step_size;
	unsigned long addr;
	unsigned long mapped_ram_size = 0;

	/* xen has big range in reserved near end of ram, skip it at first.*/
	addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
	real_end = addr + PMD_SIZE;

	/* step_size need to be small so pgt_buf from BRK could cover it */
	step_size = PMD_SIZE;
	max_pfn_mapped = 0; /* will get exact value next */
	min_pfn_mapped = real_end >> PAGE_SHIFT;
	last_start = start = real_end;

	/*
	 * We start from the top (end of memory) and go to the bottom.
	 * The memblock_find_in_range() gets us a block of RAM from the
	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
	 * for page table.
	 */
	while (last_start > map_start) {
		if (last_start > step_size) {
			start = round_down(last_start - 1, step_size);
			if (start < map_start)
				start = map_start;
		} else
			start = map_start;
		mapped_ram_size += init_range_memory_mapping(start,
							last_start);
		last_start = start;
		min_pfn_mapped = last_start >> PAGE_SHIFT;
		if (mapped_ram_size >= step_size)
			step_size = get_new_step_size(step_size);
	}

	if (real_end < map_end)
		init_range_memory_mapping(real_end, map_end);
}

/**
 * memory_map_bottom_up - Map [map_start, map_end) bottom up
 * @map_start: start address of the target memory range
 * @map_end: end address of the target memory range
 *
 * This function will setup direct mapping for memory range
 * [map_start, map_end) in bottom-up. Since we have limited the
 * bottom-up allocation above the kernel, the page tables will
 * be allocated just above the kernel and we map the memory
 * in [map_start, map_end) in bottom-up.
 */
static void __init memory_map_bottom_up(unsigned long map_start,
					unsigned long map_end)
{
	unsigned long next, start;
	unsigned long mapped_ram_size = 0;
	/* step_size need to be small so pgt_buf from BRK could cover it */
	unsigned long step_size = PMD_SIZE;

	start = map_start;
	min_pfn_mapped = start >> PAGE_SHIFT;

	/*
	 * We start from the bottom (@map_start) and go to the top (@map_end).
	 * The memblock_find_in_range() gets us a block of RAM from the
	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
	 * for page table.
	 */
	while (start < map_end) {
		if (step_size && map_end - start > step_size) {
			next = round_up(start + 1, step_size);
			if (next > map_end)
				next = map_end;
		} else {
			next = map_end;
		}

		mapped_ram_size += init_range_memory_mapping(start, next);
		start = next;

		if (mapped_ram_size >= step_size)
			step_size = get_new_step_size(step_size);
	}
}

void __init init_mem_mapping(void)
{
	unsigned long end;

	pti_check_boottime_disable();
	probe_page_size_mask();
	setup_pcid();

#ifdef CONFIG_X86_64
	end = max_pfn << PAGE_SHIFT;
#else
	end = max_low_pfn << PAGE_SHIFT;
#endif

	/* the ISA range is always mapped regardless of memory holes */
	init_memory_mapping(0, ISA_END_ADDRESS);

	/* Init the trampoline, possibly with KASLR memory offset */
	init_trampoline();

	/*
	 * If the allocation is in bottom-up direction, we setup direct mapping
	 * in bottom-up, otherwise we setup direct mapping in top-down.
	 */
	if (memblock_bottom_up()) {
		unsigned long kernel_end = __pa_symbol(_end);

		/*
		 * we need two separate calls here. This is because we want to
		 * allocate page tables above the kernel. So we first map
		 * [kernel_end, end) to make memory above the kernel be mapped
		 * as soon as possible. And then use page tables allocated above
		 * the kernel to map [ISA_END_ADDRESS, kernel_end).
		 */
		memory_map_bottom_up(kernel_end, end);
		memory_map_bottom_up(ISA_END_ADDRESS, kernel_end);
	} else {
		memory_map_top_down(ISA_END_ADDRESS, end);
	}

#ifdef CONFIG_X86_64
	if (max_pfn > max_low_pfn) {
		/* can we preseve max_low_pfn ?*/
		max_low_pfn = max_pfn;
	}
#else
	early_ioremap_page_table_range_init();
#endif

	load_cr3(swapper_pg_dir);
	__flush_tlb_all();

	x86_init.hyper.init_mem_mapping();

	early_memtest(0, max_pfn_mapped << PAGE_SHIFT);
}

/*
 * devmem_is_allowed() checks to see if /dev/mem access to a certain address
 * is valid. The argument is a physical page number.
 *
 * On x86, access has to be given to the first megabyte of RAM because that
 * area traditionally contains BIOS code and data regions used by X, dosemu,
 * and similar apps. Since they map the entire memory range, the whole range
 * must be allowed (for mapping), but any areas that would otherwise be
 * disallowed are flagged as being "zero filled" instead of rejected.
 * Access has to be given to non-kernel-ram areas as well, these contain the
 * PCI mmio resources as well as potential bios/acpi data regions.
 */
int devmem_is_allowed(unsigned long pagenr)
{
	if (region_intersects(PFN_PHYS(pagenr), PAGE_SIZE,
				IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE)
			!= REGION_DISJOINT) {
		/*
		 * For disallowed memory regions in the low 1MB range,
		 * request that the page be shown as all zeros.
		 */
		if (pagenr < 256)
			return 2;

		return 0;
	}

	/*
	 * This must follow RAM test, since System RAM is considered a
	 * restricted resource under CONFIG_STRICT_IOMEM.
	 */
	if (iomem_is_exclusive(pagenr << PAGE_SHIFT)) {
		/* Low 1MB bypasses iomem restrictions. */
		if (pagenr < 256)
			return 1;

		return 0;
	}

	return 1;
}

void free_init_pages(const char *what, unsigned long begin, unsigned long end)
{
	unsigned long begin_aligned, end_aligned;

	/* Make sure boundaries are page aligned */
	begin_aligned = PAGE_ALIGN(begin);
	end_aligned   = end & PAGE_MASK;

	if (WARN_ON(begin_aligned != begin || end_aligned != end)) {
		begin = begin_aligned;
		end   = end_aligned;
	}

	if (begin >= 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:
	 */
	if (debug_pagealloc_enabled()) {
		pr_info("debug: unmapping init [mem %#010lx-%#010lx]\n",
			begin, end - 1);
		/*
		 * Inform kmemleak about the hole in the memory since the
		 * corresponding pages will be unmapped.
		 */
		kmemleak_free_part((void *)begin, end - begin);
		set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
	} else {
		/*
		 * We just marked the kernel text read only above, now that
		 * we are going to free part of that, we need to make that
		 * writeable and non-executable first.
		 */
		set_memory_nx(begin, (end - begin) >> PAGE_SHIFT);
		set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);

		free_reserved_area((void *)begin, (void *)end,
				   POISON_FREE_INITMEM, what);
	}
}

/*
 * begin/end can be in the direct map or the "high kernel mapping"
 * used for the kernel image only.  free_init_pages() will do the
 * right thing for either kind of address.
 */
void free_kernel_image_pages(void *begin, void *end)
{
	unsigned long begin_ul = (unsigned long)begin;
	unsigned long end_ul = (unsigned long)end;
	unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;


	free_init_pages("unused kernel image", begin_ul, end_ul);

	/*
	 * PTI maps some of the kernel into userspace.  For performance,
	 * this includes some kernel areas that do not contain secrets.
	 * Those areas might be adjacent to the parts of the kernel image
	 * being freed, which may contain secrets.  Remove the "high kernel
	 * image mapping" for these freed areas, ensuring they are not even
	 * potentially vulnerable to Meltdown regardless of the specific
	 * optimizations PTI is currently using.
	 *
	 * The "noalias" prevents unmapping the direct map alias which is
	 * needed to access the freed pages.
	 *
	 * This is only valid for 64bit kernels. 32bit has only one mapping
	 * which can't be treated in this way for obvious reasons.
	 */
	if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI))
		set_memory_np_noalias(begin_ul, len_pages);
}

void __weak mem_encrypt_free_decrypted_mem(void) { }

void __ref free_initmem(void)
{
	e820__reallocate_tables();

	mem_encrypt_free_decrypted_mem();

	free_kernel_image_pages(&__init_begin, &__init_end);
}

#ifdef CONFIG_BLK_DEV_INITRD
void __init free_initrd_mem(unsigned long start, unsigned long end)
{
	/*
	 * end could be not aligned, and We can not align that,
	 * decompresser could be confused by aligned initrd_end
	 * We already reserve the end partial page before in
	 *   - i386_start_kernel()
	 *   - x86_64_start_kernel()
	 *   - relocate_initrd()
	 * So here We can do PAGE_ALIGN() safely to get partial page to be freed
	 */
	free_init_pages("initrd", start, PAGE_ALIGN(end));
}
#endif

/*
 * Calculate the precise size of the DMA zone (first 16 MB of RAM),
 * and pass it to the MM layer - to help it set zone watermarks more
 * accurately.
 *
 * Done on 64-bit systems only for the time being, although 32-bit systems
 * might benefit from this as well.
 */
void __init memblock_find_dma_reserve(void)
{
#ifdef CONFIG_X86_64
	u64 nr_pages = 0, nr_free_pages = 0;
	unsigned long start_pfn, end_pfn;
	phys_addr_t start_addr, end_addr;
	int i;
	u64 u;

	/*
	 * Iterate over all memory ranges (free and reserved ones alike),
	 * to calculate the total number of pages in the first 16 MB of RAM:
	 */
	nr_pages = 0;
	for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) {
		start_pfn = min(start_pfn, MAX_DMA_PFN);
		end_pfn   = min(end_pfn,   MAX_DMA_PFN);

		nr_pages += end_pfn - start_pfn;
	}

	/*
	 * Iterate over free memory ranges to calculate the number of free
	 * pages in the DMA zone, while not counting potential partial
	 * pages at the beginning or the end of the range:
	 */
	nr_free_pages = 0;
	for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) {
		start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN);
		end_pfn   = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN);

		if (start_pfn < end_pfn)
			nr_free_pages += end_pfn - start_pfn;
	}

	set_dma_reserve(nr_pages - nr_free_pages);
#endif
}

void __init zone_sizes_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES];

	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));

#ifdef CONFIG_ZONE_DMA
	max_zone_pfns[ZONE_DMA]		= min(MAX_DMA_PFN, max_low_pfn);
#endif
#ifdef CONFIG_ZONE_DMA32
	max_zone_pfns[ZONE_DMA32]	= min(MAX_DMA32_PFN, max_low_pfn);
#endif
	max_zone_pfns[ZONE_NORMAL]	= max_low_pfn;
#ifdef CONFIG_HIGHMEM
	max_zone_pfns[ZONE_HIGHMEM]	= max_pfn;
#endif

	free_area_init_nodes(max_zone_pfns);
}

__visible DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate) = {
	.loaded_mm = &init_mm,
	.next_asid = 1,
	.cr4 = ~0UL,	/* fail hard if we screw up cr4 shadow initialization */
};
EXPORT_PER_CPU_SYMBOL(cpu_tlbstate);

void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
{
	/* entry 0 MUST be WB (hardwired to speed up translations) */
	BUG_ON(!entry && cache != _PAGE_CACHE_MODE_WB);

	__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
	__pte2cachemode_tbl[entry] = cache;
}

#ifdef CONFIG_SWAP
unsigned long max_swapfile_size(void)
{
	unsigned long pages;

	pages = generic_max_swapfile_size();

	if (boot_cpu_has_bug(X86_BUG_L1TF) && l1tf_mitigation != L1TF_MITIGATION_OFF) {
		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
		unsigned long long l1tf_limit = l1tf_pfn_limit();
		/*
		 * We encode swap offsets also with 3 bits below those for pfn
		 * which makes the usable limit higher.
		 */
#if CONFIG_PGTABLE_LEVELS > 2
		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
#endif
		pages = min_t(unsigned long long, l1tf_limit, pages);
	}
	return pages;
}
#endif