summaryrefslogtreecommitdiffstats
path: root/arch/riscv/mm/init.c
blob: c27294128e182d77d8f0b7e29ac35b4549069943 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2012 Regents of the University of California
 * Copyright (C) 2019 Western Digital Corporation or its affiliates.
 * Copyright (C) 2020 FORTH-ICS/CARV
 *  Nick Kossifidis <mick@ics.forth.gr>
 */

#include <linux/init.h>
#include <linux/mm.h>
#include <linux/memblock.h>
#include <linux/initrd.h>
#include <linux/swap.h>
#include <linux/swiotlb.h>
#include <linux/sizes.h>
#include <linux/of_fdt.h>
#include <linux/of_reserved_mem.h>
#include <linux/libfdt.h>
#include <linux/set_memory.h>
#include <linux/dma-map-ops.h>
#include <linux/crash_dump.h>
#include <linux/hugetlb.h>

#include <asm/fixmap.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
#include <asm/soc.h>
#include <asm/io.h>
#include <asm/ptdump.h>
#include <asm/numa.h>

#include "../kernel/head.h"

struct kernel_mapping kernel_map __ro_after_init;
EXPORT_SYMBOL(kernel_map);
#ifdef CONFIG_XIP_KERNEL
#define kernel_map	(*(struct kernel_mapping *)XIP_FIXUP(&kernel_map))
#endif

#ifdef CONFIG_64BIT
u64 satp_mode = !IS_ENABLED(CONFIG_XIP_KERNEL) ? SATP_MODE_48 : SATP_MODE_39;
#else
u64 satp_mode = SATP_MODE_32;
#endif
EXPORT_SYMBOL(satp_mode);

bool pgtable_l4_enabled = IS_ENABLED(CONFIG_64BIT) && !IS_ENABLED(CONFIG_XIP_KERNEL);
EXPORT_SYMBOL(pgtable_l4_enabled);

phys_addr_t phys_ram_base __ro_after_init;
EXPORT_SYMBOL(phys_ram_base);

unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]
							__page_aligned_bss;
EXPORT_SYMBOL(empty_zero_page);

extern char _start[];
#define DTB_EARLY_BASE_VA      PGDIR_SIZE
void *_dtb_early_va __initdata;
uintptr_t _dtb_early_pa __initdata;

static phys_addr_t dma32_phys_limit __initdata;

static void __init zone_sizes_init(void)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };

#ifdef CONFIG_ZONE_DMA32
	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
#endif
	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;

	free_area_init(max_zone_pfns);
}

#if defined(CONFIG_MMU) && defined(CONFIG_DEBUG_VM)
static inline void print_mlk(char *name, unsigned long b, unsigned long t)
{
	pr_notice("%12s : 0x%08lx - 0x%08lx   (%4ld kB)\n", name, b, t,
		  (((t) - (b)) >> 10));
}

static inline void print_mlm(char *name, unsigned long b, unsigned long t)
{
	pr_notice("%12s : 0x%08lx - 0x%08lx   (%4ld MB)\n", name, b, t,
		  (((t) - (b)) >> 20));
}

static void __init print_vm_layout(void)
{
	pr_notice("Virtual kernel memory layout:\n");
	print_mlk("fixmap", (unsigned long)FIXADDR_START,
		  (unsigned long)FIXADDR_TOP);
	print_mlm("pci io", (unsigned long)PCI_IO_START,
		  (unsigned long)PCI_IO_END);
	print_mlm("vmemmap", (unsigned long)VMEMMAP_START,
		  (unsigned long)VMEMMAP_END);
	print_mlm("vmalloc", (unsigned long)VMALLOC_START,
		  (unsigned long)VMALLOC_END);
	print_mlm("lowmem", (unsigned long)PAGE_OFFSET,
		  (unsigned long)high_memory);
	if (IS_ENABLED(CONFIG_64BIT)) {
#ifdef CONFIG_KASAN
		print_mlm("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END);
#endif

		print_mlm("kernel", (unsigned long)KERNEL_LINK_ADDR,
			  (unsigned long)ADDRESS_SPACE_END);
	}
}
#else
static void print_vm_layout(void) { }
#endif /* CONFIG_DEBUG_VM */

void __init mem_init(void)
{
#ifdef CONFIG_FLATMEM
	BUG_ON(!mem_map);
#endif /* CONFIG_FLATMEM */

#ifdef CONFIG_SWIOTLB
	if (swiotlb_force == SWIOTLB_FORCE ||
	    max_pfn > PFN_DOWN(dma32_phys_limit))
		swiotlb_init(1);
	else
		swiotlb_force = SWIOTLB_NO_FORCE;
#endif
	high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
	memblock_free_all();

	print_vm_layout();
}

/* Limit the memory size via mem. */
static phys_addr_t memory_limit;

static int __init early_mem(char *p)
{
	u64 size;

	if (!p)
		return 1;

	size = memparse(p, &p) & PAGE_MASK;
	memory_limit = min_t(u64, size, memory_limit);

	pr_notice("Memory limited to %lldMB\n", (u64)memory_limit >> 20);

	return 0;
}
early_param("mem", early_mem);

static void __init setup_bootmem(void)
{
	phys_addr_t vmlinux_end = __pa_symbol(&_end);
	phys_addr_t max_mapped_addr;
	phys_addr_t phys_ram_end, vmlinux_start;

	if (IS_ENABLED(CONFIG_XIP_KERNEL))
		vmlinux_start = __pa_symbol(&_sdata);
	else
		vmlinux_start = __pa_symbol(&_start);

	memblock_enforce_memory_limit(memory_limit);

	/*
	 * Make sure we align the reservation on PMD_SIZE since we will
	 * map the kernel in the linear mapping as read-only: we do not want
	 * any allocation to happen between _end and the next pmd aligned page.
	 */
	if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
		vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK;
	/*
	 * Reserve from the start of the kernel to the end of the kernel
	 */
	memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);

	phys_ram_end = memblock_end_of_DRAM();
	if (!IS_ENABLED(CONFIG_XIP_KERNEL))
		phys_ram_base = memblock_start_of_DRAM();
	/*
	 * memblock allocator is not aware of the fact that last 4K bytes of
	 * the addressable memory can not be mapped because of IS_ERR_VALUE
	 * macro. Make sure that last 4k bytes are not usable by memblock
	 * if end of dram is equal to maximum addressable memory.  For 64-bit
	 * kernel, this problem can't happen here as the end of the virtual
	 * address space is occupied by the kernel mapping then this check must
	 * be done as soon as the kernel mapping base address is determined.
	 */
	if (!IS_ENABLED(CONFIG_64BIT)) {
		max_mapped_addr = __pa(~(ulong)0);
		if (max_mapped_addr == (phys_ram_end - 1))
			memblock_set_current_limit(max_mapped_addr - 4096);
	}

	min_low_pfn = PFN_UP(phys_ram_base);
	max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);

	dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn));
	set_max_mapnr(max_low_pfn - ARCH_PFN_OFFSET);

	reserve_initrd_mem();
	/*
	 * If DTB is built in, no need to reserve its memblock.
	 * Otherwise, do reserve it but avoid using
	 * early_init_fdt_reserve_self() since __pa() does
	 * not work for DTB pointers that are fixmap addresses
	 */
	if (!IS_ENABLED(CONFIG_BUILTIN_DTB))
		memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));

	early_init_fdt_scan_reserved_mem();
	dma_contiguous_reserve(dma32_phys_limit);
	if (IS_ENABLED(CONFIG_64BIT))
		hugetlb_cma_reserve(PUD_SHIFT - PAGE_SHIFT);
	memblock_allow_resize();
}

#ifdef CONFIG_MMU
struct pt_alloc_ops pt_ops __initdata;

unsigned long riscv_pfn_base __ro_after_init;
EXPORT_SYMBOL(riscv_pfn_base);

pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss;
static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss;

pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE);
static pud_t __maybe_unused early_dtb_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);
static pmd_t __maybe_unused early_dtb_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);

#ifdef CONFIG_XIP_KERNEL
#define pt_ops			(*(struct pt_alloc_ops *)XIP_FIXUP(&pt_ops))
#define riscv_pfn_base         (*(unsigned long  *)XIP_FIXUP(&riscv_pfn_base))
#define trampoline_pg_dir      ((pgd_t *)XIP_FIXUP(trampoline_pg_dir))
#define fixmap_pte             ((pte_t *)XIP_FIXUP(fixmap_pte))
#define early_pg_dir           ((pgd_t *)XIP_FIXUP(early_pg_dir))
#endif /* CONFIG_XIP_KERNEL */

void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot)
{
	unsigned long addr = __fix_to_virt(idx);
	pte_t *ptep;

	BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);

	ptep = &fixmap_pte[pte_index(addr)];

	if (pgprot_val(prot))
		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot));
	else
		pte_clear(&init_mm, addr, ptep);
	local_flush_tlb_page(addr);
}

static inline pte_t *__init get_pte_virt_early(phys_addr_t pa)
{
	return (pte_t *)((uintptr_t)pa);
}

static inline pte_t *__init get_pte_virt_fixmap(phys_addr_t pa)
{
	clear_fixmap(FIX_PTE);
	return (pte_t *)set_fixmap_offset(FIX_PTE, pa);
}

static inline pte_t *__init get_pte_virt_late(phys_addr_t pa)
{
	return (pte_t *) __va(pa);
}

static inline phys_addr_t __init alloc_pte_early(uintptr_t va)
{
	/*
	 * We only create PMD or PGD early mappings so we
	 * should never reach here with MMU disabled.
	 */
	BUG();
}

static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va)
{
	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
}

static phys_addr_t __init alloc_pte_late(uintptr_t va)
{
	unsigned long vaddr;

	vaddr = __get_free_page(GFP_KERNEL);
	BUG_ON(!vaddr || !pgtable_pte_page_ctor(virt_to_page(vaddr)));

	return __pa(vaddr);
}

static void __init create_pte_mapping(pte_t *ptep,
				      uintptr_t va, phys_addr_t pa,
				      phys_addr_t sz, pgprot_t prot)
{
	uintptr_t pte_idx = pte_index(va);

	BUG_ON(sz != PAGE_SIZE);

	if (pte_none(ptep[pte_idx]))
		ptep[pte_idx] = pfn_pte(PFN_DOWN(pa), prot);
}

#ifndef __PAGETABLE_PMD_FOLDED

static pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss;
static pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss;
static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE);

#ifdef CONFIG_XIP_KERNEL
#define trampoline_pmd ((pmd_t *)XIP_FIXUP(trampoline_pmd))
#define fixmap_pmd     ((pmd_t *)XIP_FIXUP(fixmap_pmd))
#define early_pmd      ((pmd_t *)XIP_FIXUP(early_pmd))
#endif /* CONFIG_XIP_KERNEL */

static pud_t trampoline_pud[PTRS_PER_PUD] __page_aligned_bss;
static pud_t fixmap_pud[PTRS_PER_PUD] __page_aligned_bss;
static pud_t early_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE);

#ifdef CONFIG_XIP_KERNEL
#define trampoline_pud ((pud_t *)XIP_FIXUP(trampoline_pud))
#define fixmap_pud     ((pud_t *)XIP_FIXUP(fixmap_pud))
#define early_pud      ((pud_t *)XIP_FIXUP(early_pud))
#endif /* CONFIG_XIP_KERNEL */

static pmd_t *__init get_pmd_virt_early(phys_addr_t pa)
{
	/* Before MMU is enabled */
	return (pmd_t *)((uintptr_t)pa);
}

static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa)
{
	clear_fixmap(FIX_PMD);
	return (pmd_t *)set_fixmap_offset(FIX_PMD, pa);
}

static pmd_t *__init get_pmd_virt_late(phys_addr_t pa)
{
	return (pmd_t *) __va(pa);
}

static phys_addr_t __init alloc_pmd_early(uintptr_t va)
{
	BUG_ON((va - kernel_map.virt_addr) >> PUD_SHIFT);

	return (uintptr_t)early_pmd;
}

static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va)
{
	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
}

static phys_addr_t __init alloc_pmd_late(uintptr_t va)
{
	unsigned long vaddr;

	vaddr = __get_free_page(GFP_KERNEL);
	BUG_ON(!vaddr || !pgtable_pmd_page_ctor(virt_to_page(vaddr)));

	return __pa(vaddr);
}

static void __init create_pmd_mapping(pmd_t *pmdp,
				      uintptr_t va, phys_addr_t pa,
				      phys_addr_t sz, pgprot_t prot)
{
	pte_t *ptep;
	phys_addr_t pte_phys;
	uintptr_t pmd_idx = pmd_index(va);

	if (sz == PMD_SIZE) {
		if (pmd_none(pmdp[pmd_idx]))
			pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pa), prot);
		return;
	}

	if (pmd_none(pmdp[pmd_idx])) {
		pte_phys = pt_ops.alloc_pte(va);
		pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pte_phys), PAGE_TABLE);
		ptep = pt_ops.get_pte_virt(pte_phys);
		memset(ptep, 0, PAGE_SIZE);
	} else {
		pte_phys = PFN_PHYS(_pmd_pfn(pmdp[pmd_idx]));
		ptep = pt_ops.get_pte_virt(pte_phys);
	}

	create_pte_mapping(ptep, va, pa, sz, prot);
}

static pud_t *__init get_pud_virt_early(phys_addr_t pa)
{
	return (pud_t *)((uintptr_t)pa);
}

static pud_t *__init get_pud_virt_fixmap(phys_addr_t pa)
{
	clear_fixmap(FIX_PUD);
	return (pud_t *)set_fixmap_offset(FIX_PUD, pa);
}

static pud_t *__init get_pud_virt_late(phys_addr_t pa)
{
	return (pud_t *)__va(pa);
}

static phys_addr_t __init alloc_pud_early(uintptr_t va)
{
	/* Only one PUD is available for early mapping */
	BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT);

	return (uintptr_t)early_pud;
}

static phys_addr_t __init alloc_pud_fixmap(uintptr_t va)
{
	return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE);
}

static phys_addr_t alloc_pud_late(uintptr_t va)
{
	unsigned long vaddr;

	vaddr = __get_free_page(GFP_KERNEL);
	BUG_ON(!vaddr);
	return __pa(vaddr);
}

static void __init create_pud_mapping(pud_t *pudp,
				      uintptr_t va, phys_addr_t pa,
				      phys_addr_t sz, pgprot_t prot)
{
	pmd_t *nextp;
	phys_addr_t next_phys;
	uintptr_t pud_index = pud_index(va);

	if (sz == PUD_SIZE) {
		if (pud_val(pudp[pud_index]) == 0)
			pudp[pud_index] = pfn_pud(PFN_DOWN(pa), prot);
		return;
	}

	if (pud_val(pudp[pud_index]) == 0) {
		next_phys = pt_ops.alloc_pmd(va);
		pudp[pud_index] = pfn_pud(PFN_DOWN(next_phys), PAGE_TABLE);
		nextp = pt_ops.get_pmd_virt(next_phys);
		memset(nextp, 0, PAGE_SIZE);
	} else {
		next_phys = PFN_PHYS(_pud_pfn(pudp[pud_index]));
		nextp = pt_ops.get_pmd_virt(next_phys);
	}

	create_pmd_mapping(nextp, va, pa, sz, prot);
}

#define pgd_next_t		pud_t
#define alloc_pgd_next(__va)	(pgtable_l4_enabled ?			\
		pt_ops.alloc_pud(__va) : pt_ops.alloc_pmd(__va))
#define get_pgd_next_virt(__pa)	(pgtable_l4_enabled ?			\
		pt_ops.get_pud_virt(__pa) : (pgd_next_t *)pt_ops.get_pmd_virt(__pa))
#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
				(pgtable_l4_enabled ?			\
		create_pud_mapping(__nextp, __va, __pa, __sz, __prot) :	\
		create_pmd_mapping((pmd_t *)__nextp, __va, __pa, __sz, __prot))
#define fixmap_pgd_next		(pgtable_l4_enabled ?			\
		(uintptr_t)fixmap_pud : (uintptr_t)fixmap_pmd)
#define trampoline_pgd_next	(pgtable_l4_enabled ?			\
		(uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd)
#define early_dtb_pgd_next	(pgtable_l4_enabled ?			\
		(uintptr_t)early_dtb_pud : (uintptr_t)early_dtb_pmd)
#else
#define pgd_next_t		pte_t
#define alloc_pgd_next(__va)	pt_ops.alloc_pte(__va)
#define get_pgd_next_virt(__pa)	pt_ops.get_pte_virt(__pa)
#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot)	\
	create_pte_mapping(__nextp, __va, __pa, __sz, __prot)
#define fixmap_pgd_next		((uintptr_t)fixmap_pte)
#define early_dtb_pgd_next	((uintptr_t)early_dtb_pmd)
#define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot)
#define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot)
#endif /* __PAGETABLE_PMD_FOLDED */

void __init create_pgd_mapping(pgd_t *pgdp,
				      uintptr_t va, phys_addr_t pa,
				      phys_addr_t sz, pgprot_t prot)
{
	pgd_next_t *nextp;
	phys_addr_t next_phys;
	uintptr_t pgd_idx = pgd_index(va);

	if (sz == PGDIR_SIZE) {
		if (pgd_val(pgdp[pgd_idx]) == 0)
			pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(pa), prot);
		return;
	}

	if (pgd_val(pgdp[pgd_idx]) == 0) {
		next_phys = alloc_pgd_next(va);
		pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(next_phys), PAGE_TABLE);
		nextp = get_pgd_next_virt(next_phys);
		memset(nextp, 0, PAGE_SIZE);
	} else {
		next_phys = PFN_PHYS(_pgd_pfn(pgdp[pgd_idx]));
		nextp = get_pgd_next_virt(next_phys);
	}

	create_pgd_next_mapping(nextp, va, pa, sz, prot);
}

static uintptr_t __init best_map_size(phys_addr_t base, phys_addr_t size)
{
	/* Upgrade to PMD_SIZE mappings whenever possible */
	if ((base & (PMD_SIZE - 1)) || (size & (PMD_SIZE - 1)))
		return PAGE_SIZE;

	return PMD_SIZE;
}

#ifdef CONFIG_XIP_KERNEL
#define phys_ram_base  (*(phys_addr_t *)XIP_FIXUP(&phys_ram_base))
extern char _xiprom[], _exiprom[], __data_loc;

/* called from head.S with MMU off */
asmlinkage void __init __copy_data(void)
{
	void *from = (void *)(&__data_loc);
	void *to = (void *)CONFIG_PHYS_RAM_BASE;
	size_t sz = (size_t)((uintptr_t)(&_end) - (uintptr_t)(&_sdata));

	memcpy(to, from, sz);
}
#endif

#ifdef CONFIG_STRICT_KERNEL_RWX
static __init pgprot_t pgprot_from_va(uintptr_t va)
{
	if (is_va_kernel_text(va))
		return PAGE_KERNEL_READ_EXEC;

	/*
	 * In 64-bit kernel, the kernel mapping is outside the linear mapping so
	 * we must protect its linear mapping alias from being executed and
	 * written.
	 * And rodata section is marked readonly in mark_rodata_ro.
	 */
	if (IS_ENABLED(CONFIG_64BIT) && is_va_kernel_lm_alias_text(va))
		return PAGE_KERNEL_READ;

	return PAGE_KERNEL;
}

void mark_rodata_ro(void)
{
	set_kernel_memory(__start_rodata, _data, set_memory_ro);
	if (IS_ENABLED(CONFIG_64BIT))
		set_kernel_memory(lm_alias(__start_rodata), lm_alias(_data),
				  set_memory_ro);

	debug_checkwx();
}
#else
static __init pgprot_t pgprot_from_va(uintptr_t va)
{
	if (IS_ENABLED(CONFIG_64BIT) && !is_kernel_mapping(va))
		return PAGE_KERNEL;

	return PAGE_KERNEL_EXEC;
}
#endif /* CONFIG_STRICT_KERNEL_RWX */

#ifdef CONFIG_64BIT
static void __init disable_pgtable_l4(void)
{
	pgtable_l4_enabled = false;
	kernel_map.page_offset = PAGE_OFFSET_L3;
	satp_mode = SATP_MODE_39;
}

/*
 * There is a simple way to determine if 4-level is supported by the
 * underlying hardware: establish 1:1 mapping in 4-level page table mode
 * then read SATP to see if the configuration was taken into account
 * meaning sv48 is supported.
 */
static __init void set_satp_mode(void)
{
	u64 identity_satp, hw_satp;
	uintptr_t set_satp_mode_pmd;

	set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK;
	create_pgd_mapping(early_pg_dir,
			   set_satp_mode_pmd, (uintptr_t)early_pud,
			   PGDIR_SIZE, PAGE_TABLE);
	create_pud_mapping(early_pud,
			   set_satp_mode_pmd, (uintptr_t)early_pmd,
			   PUD_SIZE, PAGE_TABLE);
	/* Handle the case where set_satp_mode straddles 2 PMDs */
	create_pmd_mapping(early_pmd,
			   set_satp_mode_pmd, set_satp_mode_pmd,
			   PMD_SIZE, PAGE_KERNEL_EXEC);
	create_pmd_mapping(early_pmd,
			   set_satp_mode_pmd + PMD_SIZE,
			   set_satp_mode_pmd + PMD_SIZE,
			   PMD_SIZE, PAGE_KERNEL_EXEC);

	identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode;

	local_flush_tlb_all();
	csr_write(CSR_SATP, identity_satp);
	hw_satp = csr_swap(CSR_SATP, 0ULL);
	local_flush_tlb_all();

	if (hw_satp != identity_satp)
		disable_pgtable_l4();

	memset(early_pg_dir, 0, PAGE_SIZE);
	memset(early_pud, 0, PAGE_SIZE);
	memset(early_pmd, 0, PAGE_SIZE);
}
#endif

/*
 * setup_vm() is called from head.S with MMU-off.
 *
 * Following requirements should be honoured for setup_vm() to work
 * correctly:
 * 1) It should use PC-relative addressing for accessing kernel symbols.
 *    To achieve this we always use GCC cmodel=medany.
 * 2) The compiler instrumentation for FTRACE will not work for setup_vm()
 *    so disable compiler instrumentation when FTRACE is enabled.
 *
 * Currently, the above requirements are honoured by using custom CFLAGS
 * for init.o in mm/Makefile.
 */

#ifndef __riscv_cmodel_medany
#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing."
#endif

#ifdef CONFIG_XIP_KERNEL
static void __init create_kernel_page_table(pgd_t *pgdir,
					    __always_unused bool early)
{
	uintptr_t va, end_va;

	/* Map the flash resident part */
	end_va = kernel_map.virt_addr + kernel_map.xiprom_sz;
	for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE)
		create_pgd_mapping(pgdir, va,
				   kernel_map.xiprom + (va - kernel_map.virt_addr),
				   PMD_SIZE, PAGE_KERNEL_EXEC);

	/* Map the data in RAM */
	end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size;
	for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE)
		create_pgd_mapping(pgdir, va,
				   kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
				   PMD_SIZE, PAGE_KERNEL);
}
#else
static void __init create_kernel_page_table(pgd_t *pgdir, bool early)
{
	uintptr_t va, end_va;

	end_va = kernel_map.virt_addr + kernel_map.size;
	for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE)
		create_pgd_mapping(pgdir, va,
				   kernel_map.phys_addr + (va - kernel_map.virt_addr),
				   PMD_SIZE,
				   early ?
					PAGE_KERNEL_EXEC : pgprot_from_va(va));
}
#endif

/*
 * Setup a 4MB mapping that encompasses the device tree: for 64-bit kernel,
 * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR
 * entry.
 */
static void __init create_fdt_early_page_table(pgd_t *pgdir, uintptr_t dtb_pa)
{
#ifndef CONFIG_BUILTIN_DTB
	uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1);

	create_pgd_mapping(early_pg_dir, DTB_EARLY_BASE_VA,
			   IS_ENABLED(CONFIG_64BIT) ? early_dtb_pgd_next : pa,
			   PGDIR_SIZE,
			   IS_ENABLED(CONFIG_64BIT) ? PAGE_TABLE : PAGE_KERNEL);

	if (pgtable_l4_enabled) {
		create_pud_mapping(early_dtb_pud, DTB_EARLY_BASE_VA,
				   (uintptr_t)early_dtb_pmd, PUD_SIZE, PAGE_TABLE);
	}

	if (IS_ENABLED(CONFIG_64BIT)) {
		create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA,
				   pa, PMD_SIZE, PAGE_KERNEL);
		create_pmd_mapping(early_dtb_pmd, DTB_EARLY_BASE_VA + PMD_SIZE,
				   pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL);
	}

	dtb_early_va = (void *)DTB_EARLY_BASE_VA + (dtb_pa & (PMD_SIZE - 1));
#else
	/*
	 * For 64-bit kernel, __va can't be used since it would return a linear
	 * mapping address whereas dtb_early_va will be used before
	 * setup_vm_final installs the linear mapping. For 32-bit kernel, as the
	 * kernel is mapped in the linear mapping, that makes no difference.
	 */
	dtb_early_va = kernel_mapping_pa_to_va(XIP_FIXUP(dtb_pa));
#endif

	dtb_early_pa = dtb_pa;
}

/*
 * MMU is not enabled, the page tables are allocated directly using
 * early_pmd/pud/p4d and the address returned is the physical one.
 */
void __init pt_ops_set_early(void)
{
	pt_ops.alloc_pte = alloc_pte_early;
	pt_ops.get_pte_virt = get_pte_virt_early;
#ifndef __PAGETABLE_PMD_FOLDED
	pt_ops.alloc_pmd = alloc_pmd_early;
	pt_ops.get_pmd_virt = get_pmd_virt_early;
	pt_ops.alloc_pud = alloc_pud_early;
	pt_ops.get_pud_virt = get_pud_virt_early;
#endif
}

/*
 * MMU is enabled but page table setup is not complete yet.
 * fixmap page table alloc functions must be used as a means to temporarily
 * map the allocated physical pages since the linear mapping does not exist yet.
 *
 * Note that this is called with MMU disabled, hence kernel_mapping_pa_to_va,
 * but it will be used as described above.
 */
void __init pt_ops_set_fixmap(void)
{
	pt_ops.alloc_pte = kernel_mapping_pa_to_va((uintptr_t)alloc_pte_fixmap);
	pt_ops.get_pte_virt = kernel_mapping_pa_to_va((uintptr_t)get_pte_virt_fixmap);
#ifndef __PAGETABLE_PMD_FOLDED
	pt_ops.alloc_pmd = kernel_mapping_pa_to_va((uintptr_t)alloc_pmd_fixmap);
	pt_ops.get_pmd_virt = kernel_mapping_pa_to_va((uintptr_t)get_pmd_virt_fixmap);
	pt_ops.alloc_pud = kernel_mapping_pa_to_va((uintptr_t)alloc_pud_fixmap);
	pt_ops.get_pud_virt = kernel_mapping_pa_to_va((uintptr_t)get_pud_virt_fixmap);
#endif
}

/*
 * MMU is enabled and page table setup is complete, so from now, we can use
 * generic page allocation functions to setup page table.
 */
void __init pt_ops_set_late(void)
{
	pt_ops.alloc_pte = alloc_pte_late;
	pt_ops.get_pte_virt = get_pte_virt_late;
#ifndef __PAGETABLE_PMD_FOLDED
	pt_ops.alloc_pmd = alloc_pmd_late;
	pt_ops.get_pmd_virt = get_pmd_virt_late;
	pt_ops.alloc_pud = alloc_pud_late;
	pt_ops.get_pud_virt = get_pud_virt_late;
#endif
}

asmlinkage void __init setup_vm(uintptr_t dtb_pa)
{
	pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd;

	kernel_map.virt_addr = KERNEL_LINK_ADDR;
	kernel_map.page_offset = _AC(CONFIG_PAGE_OFFSET, UL);

#ifdef CONFIG_XIP_KERNEL
	kernel_map.xiprom = (uintptr_t)CONFIG_XIP_PHYS_ADDR;
	kernel_map.xiprom_sz = (uintptr_t)(&_exiprom) - (uintptr_t)(&_xiprom);

	phys_ram_base = CONFIG_PHYS_RAM_BASE;
	kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
	kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);

	kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
#else
	kernel_map.phys_addr = (uintptr_t)(&_start);
	kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr;
#endif

#if defined(CONFIG_64BIT) && !defined(CONFIG_XIP_KERNEL)
	set_satp_mode();
#endif

	kernel_map.va_pa_offset = PAGE_OFFSET - kernel_map.phys_addr;
	kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr;

	riscv_pfn_base = PFN_DOWN(kernel_map.phys_addr);

	/*
	 * The default maximal physical memory size is KERN_VIRT_SIZE for 32-bit
	 * kernel, whereas for 64-bit kernel, the end of the virtual address
	 * space is occupied by the modules/BPF/kernel mappings which reduces
	 * the available size of the linear mapping.
	 */
	memory_limit = KERN_VIRT_SIZE - (IS_ENABLED(CONFIG_64BIT) ? SZ_4G : 0);

	/* Sanity check alignment and size */
	BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0);
	BUG_ON((kernel_map.phys_addr % PMD_SIZE) != 0);

#ifdef CONFIG_64BIT
	/*
	 * The last 4K bytes of the addressable memory can not be mapped because
	 * of IS_ERR_VALUE macro.
	 */
	BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K);
#endif

	pt_ops_set_early();

	/* Setup early PGD for fixmap */
	create_pgd_mapping(early_pg_dir, FIXADDR_START,
			   fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE);

#ifndef __PAGETABLE_PMD_FOLDED
	/* Setup fixmap PUD and PMD */
	if (pgtable_l4_enabled)
		create_pud_mapping(fixmap_pud, FIXADDR_START,
				   (uintptr_t)fixmap_pmd, PUD_SIZE, PAGE_TABLE);
	create_pmd_mapping(fixmap_pmd, FIXADDR_START,
			   (uintptr_t)fixmap_pte, PMD_SIZE, PAGE_TABLE);
	/* Setup trampoline PGD and PMD */
	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
			   trampoline_pgd_next, PGDIR_SIZE, PAGE_TABLE);
	if (pgtable_l4_enabled)
		create_pud_mapping(trampoline_pud, kernel_map.virt_addr,
				   (uintptr_t)trampoline_pmd, PUD_SIZE, PAGE_TABLE);
#ifdef CONFIG_XIP_KERNEL
	create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
			   kernel_map.xiprom, PMD_SIZE, PAGE_KERNEL_EXEC);
#else
	create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr,
			   kernel_map.phys_addr, PMD_SIZE, PAGE_KERNEL_EXEC);
#endif
#else
	/* Setup trampoline PGD */
	create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr,
			   kernel_map.phys_addr, PGDIR_SIZE, PAGE_KERNEL_EXEC);
#endif

	/*
	 * Setup early PGD covering entire kernel which will allow
	 * us to reach paging_init(). We map all memory banks later
	 * in setup_vm_final() below.
	 */
	create_kernel_page_table(early_pg_dir, true);

	/* Setup early mapping for FDT early scan */
	create_fdt_early_page_table(early_pg_dir, dtb_pa);

	/*
	 * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap
	 * range can not span multiple pmds.
	 */
	BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT)
		     != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT));

#ifndef __PAGETABLE_PMD_FOLDED
	/*
	 * Early ioremap fixmap is already created as it lies within first 2MB
	 * of fixmap region. We always map PMD_SIZE. Thus, both FIX_BTMAP_END
	 * FIX_BTMAP_BEGIN should lie in the same pmd. Verify that and warn
	 * the user if not.
	 */
	fix_bmap_spmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_BEGIN))];
	fix_bmap_epmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_END))];
	if (pmd_val(fix_bmap_spmd) != pmd_val(fix_bmap_epmd)) {
		WARN_ON(1);
		pr_warn("fixmap btmap start [%08lx] != end [%08lx]\n",
			pmd_val(fix_bmap_spmd), pmd_val(fix_bmap_epmd));
		pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n",
			fix_to_virt(FIX_BTMAP_BEGIN));
		pr_warn("fix_to_virt(FIX_BTMAP_END):   %08lx\n",
			fix_to_virt(FIX_BTMAP_END));

		pr_warn("FIX_BTMAP_END:       %d\n", FIX_BTMAP_END);
		pr_warn("FIX_BTMAP_BEGIN:     %d\n", FIX_BTMAP_BEGIN);
	}
#endif

	pt_ops_set_fixmap();
}

static void __init setup_vm_final(void)
{
	uintptr_t va, map_size;
	phys_addr_t pa, start, end;
	u64 i;

	/* Setup swapper PGD for fixmap */
	create_pgd_mapping(swapper_pg_dir, FIXADDR_START,
			   __pa_symbol(fixmap_pgd_next),
			   PGDIR_SIZE, PAGE_TABLE);

	/* Map all memory banks in the linear mapping */
	for_each_mem_range(i, &start, &end) {
		if (start >= end)
			break;
		if (start <= __pa(PAGE_OFFSET) &&
		    __pa(PAGE_OFFSET) < end)
			start = __pa(PAGE_OFFSET);
		if (end >= __pa(PAGE_OFFSET) + memory_limit)
			end = __pa(PAGE_OFFSET) + memory_limit;

		map_size = best_map_size(start, end - start);
		for (pa = start; pa < end; pa += map_size) {
			va = (uintptr_t)__va(pa);

			create_pgd_mapping(swapper_pg_dir, va, pa, map_size,
					   pgprot_from_va(va));
		}
	}

	/* Map the kernel */
	if (IS_ENABLED(CONFIG_64BIT))
		create_kernel_page_table(swapper_pg_dir, false);

#ifdef CONFIG_KASAN
	kasan_swapper_init();
#endif

	/* Clear fixmap PTE and PMD mappings */
	clear_fixmap(FIX_PTE);
	clear_fixmap(FIX_PMD);
	clear_fixmap(FIX_PUD);

	/* Move to swapper page table */
	csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | satp_mode);
	local_flush_tlb_all();

	pt_ops_set_late();
}
#else
asmlinkage void __init setup_vm(uintptr_t dtb_pa)
{
	dtb_early_va = (void *)dtb_pa;
	dtb_early_pa = dtb_pa;
}

static inline void setup_vm_final(void)
{
}
#endif /* CONFIG_MMU */

#ifdef CONFIG_KEXEC_CORE
/*
 * reserve_crashkernel() - reserves memory for crash kernel
 *
 * This function reserves memory area given in "crashkernel=" kernel command
 * line parameter. The memory reserved is used by dump capture kernel when
 * primary kernel is crashing.
 */
static void __init reserve_crashkernel(void)
{
	unsigned long long crash_base = 0;
	unsigned long long crash_size = 0;
	unsigned long search_start = memblock_start_of_DRAM();
	unsigned long search_end = memblock_end_of_DRAM();

	int ret = 0;

	/*
	 * Don't reserve a region for a crash kernel on a crash kernel
	 * since it doesn't make much sense and we have limited memory
	 * resources.
	 */
	if (is_kdump_kernel()) {
		pr_info("crashkernel: ignoring reservation request\n");
		return;
	}

	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
				&crash_size, &crash_base);
	if (ret || !crash_size)
		return;

	crash_size = PAGE_ALIGN(crash_size);

	if (crash_base) {
		search_start = crash_base;
		search_end = crash_base + crash_size;
	}

	/*
	 * Current riscv boot protocol requires 2MB alignment for
	 * RV64 and 4MB alignment for RV32 (hugepage size)
	 *
	 * Try to alloc from 32bit addressible physical memory so that
	 * swiotlb can work on the crash kernel.
	 */
	crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
					       search_start,
					       min(search_end, (unsigned long) SZ_4G));
	if (crash_base == 0) {
		/* Try again without restricting region to 32bit addressible memory */
		crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
						search_start, search_end);
		if (crash_base == 0) {
			pr_warn("crashkernel: couldn't allocate %lldKB\n",
				crash_size >> 10);
			return;
		}
	}

	pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
		crash_base, crash_base + crash_size, crash_size >> 20);

	crashk_res.start = crash_base;
	crashk_res.end = crash_base + crash_size - 1;
}
#endif /* CONFIG_KEXEC_CORE */

void __init paging_init(void)
{
	setup_bootmem();
	setup_vm_final();
}

void __init misc_mem_init(void)
{
	early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT);
	arch_numa_init();
	sparse_init();
	zone_sizes_init();
#ifdef CONFIG_KEXEC_CORE
	reserve_crashkernel();
#endif
	memblock_dump_all();
}

#ifdef CONFIG_SPARSEMEM_VMEMMAP
int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
			       struct vmem_altmap *altmap)
{
	return vmemmap_populate_basepages(start, end, node, NULL);
}
#endif