summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/mm/book3s64/radix_pgtable.c
blob: 26245aaf12b8bddb8f6082ce5b2b3c093f2e00cc (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
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Page table handling routines for radix page table.
 *
 * Copyright 2015-2016, Aneesh Kumar K.V, IBM Corporation.
 */

#define pr_fmt(fmt) "radix-mmu: " fmt

#include <linux/io.h>
#include <linux/kernel.h>
#include <linux/sched/mm.h>
#include <linux/memblock.h>
#include <linux/of.h>
#include <linux/of_fdt.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/string_helpers.h>
#include <linux/memory.h>

#include <asm/pgalloc.h>
#include <asm/mmu_context.h>
#include <asm/dma.h>
#include <asm/machdep.h>
#include <asm/mmu.h>
#include <asm/firmware.h>
#include <asm/powernv.h>
#include <asm/sections.h>
#include <asm/smp.h>
#include <asm/trace.h>
#include <asm/uaccess.h>
#include <asm/ultravisor.h>
#include <asm/set_memory.h>

#include <trace/events/thp.h>

#include <mm/mmu_decl.h>

unsigned int mmu_base_pid;
unsigned long radix_mem_block_size __ro_after_init;

static __ref void *early_alloc_pgtable(unsigned long size, int nid,
			unsigned long region_start, unsigned long region_end)
{
	phys_addr_t min_addr = MEMBLOCK_LOW_LIMIT;
	phys_addr_t max_addr = MEMBLOCK_ALLOC_ANYWHERE;
	void *ptr;

	if (region_start)
		min_addr = region_start;
	if (region_end)
		max_addr = region_end;

	ptr = memblock_alloc_try_nid(size, size, min_addr, max_addr, nid);

	if (!ptr)
		panic("%s: Failed to allocate %lu bytes align=0x%lx nid=%d from=%pa max_addr=%pa\n",
		      __func__, size, size, nid, &min_addr, &max_addr);

	return ptr;
}

/*
 * When allocating pud or pmd pointers, we allocate a complete page
 * of PAGE_SIZE rather than PUD_TABLE_SIZE or PMD_TABLE_SIZE. This
 * is to ensure that the page obtained from the memblock allocator
 * can be completely used as page table page and can be freed
 * correctly when the page table entries are removed.
 */
static int early_map_kernel_page(unsigned long ea, unsigned long pa,
			  pgprot_t flags,
			  unsigned int map_page_size,
			  int nid,
			  unsigned long region_start, unsigned long region_end)
{
	unsigned long pfn = pa >> PAGE_SHIFT;
	pgd_t *pgdp;
	p4d_t *p4dp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	pgdp = pgd_offset_k(ea);
	p4dp = p4d_offset(pgdp, ea);
	if (p4d_none(*p4dp)) {
		pudp = early_alloc_pgtable(PAGE_SIZE, nid,
					   region_start, region_end);
		p4d_populate(&init_mm, p4dp, pudp);
	}
	pudp = pud_offset(p4dp, ea);
	if (map_page_size == PUD_SIZE) {
		ptep = (pte_t *)pudp;
		goto set_the_pte;
	}
	if (pud_none(*pudp)) {
		pmdp = early_alloc_pgtable(PAGE_SIZE, nid, region_start,
					   region_end);
		pud_populate(&init_mm, pudp, pmdp);
	}
	pmdp = pmd_offset(pudp, ea);
	if (map_page_size == PMD_SIZE) {
		ptep = pmdp_ptep(pmdp);
		goto set_the_pte;
	}
	if (!pmd_present(*pmdp)) {
		ptep = early_alloc_pgtable(PAGE_SIZE, nid,
						region_start, region_end);
		pmd_populate_kernel(&init_mm, pmdp, ptep);
	}
	ptep = pte_offset_kernel(pmdp, ea);

set_the_pte:
	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
	asm volatile("ptesync": : :"memory");
	return 0;
}

/*
 * nid, region_start, and region_end are hints to try to place the page
 * table memory in the same node or region.
 */
static int __map_kernel_page(unsigned long ea, unsigned long pa,
			  pgprot_t flags,
			  unsigned int map_page_size,
			  int nid,
			  unsigned long region_start, unsigned long region_end)
{
	unsigned long pfn = pa >> PAGE_SHIFT;
	pgd_t *pgdp;
	p4d_t *p4dp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;
	/*
	 * Make sure task size is correct as per the max adddr
	 */
	BUILD_BUG_ON(TASK_SIZE_USER64 > RADIX_PGTABLE_RANGE);

#ifdef CONFIG_PPC_64K_PAGES
	BUILD_BUG_ON(RADIX_KERN_MAP_SIZE != (1UL << MAX_EA_BITS_PER_CONTEXT));
#endif

	if (unlikely(!slab_is_available()))
		return early_map_kernel_page(ea, pa, flags, map_page_size,
						nid, region_start, region_end);

	/*
	 * Should make page table allocation functions be able to take a
	 * node, so we can place kernel page tables on the right nodes after
	 * boot.
	 */
	pgdp = pgd_offset_k(ea);
	p4dp = p4d_offset(pgdp, ea);
	pudp = pud_alloc(&init_mm, p4dp, ea);
	if (!pudp)
		return -ENOMEM;
	if (map_page_size == PUD_SIZE) {
		ptep = (pte_t *)pudp;
		goto set_the_pte;
	}
	pmdp = pmd_alloc(&init_mm, pudp, ea);
	if (!pmdp)
		return -ENOMEM;
	if (map_page_size == PMD_SIZE) {
		ptep = pmdp_ptep(pmdp);
		goto set_the_pte;
	}
	ptep = pte_alloc_kernel(pmdp, ea);
	if (!ptep)
		return -ENOMEM;

set_the_pte:
	set_pte_at(&init_mm, ea, ptep, pfn_pte(pfn, flags));
	asm volatile("ptesync": : :"memory");
	return 0;
}

int radix__map_kernel_page(unsigned long ea, unsigned long pa,
			  pgprot_t flags,
			  unsigned int map_page_size)
{
	return __map_kernel_page(ea, pa, flags, map_page_size, -1, 0, 0);
}

#ifdef CONFIG_STRICT_KERNEL_RWX
static void radix__change_memory_range(unsigned long start, unsigned long end,
				       unsigned long clear)
{
	unsigned long idx;
	pgd_t *pgdp;
	p4d_t *p4dp;
	pud_t *pudp;
	pmd_t *pmdp;
	pte_t *ptep;

	start = ALIGN_DOWN(start, PAGE_SIZE);
	end = PAGE_ALIGN(end); // aligns up

	pr_debug("Changing flags on range %lx-%lx removing 0x%lx\n",
		 start, end, clear);

	for (idx = start; idx < end; idx += PAGE_SIZE) {
		pgdp = pgd_offset_k(idx);
		p4dp = p4d_offset(pgdp, idx);
		pudp = pud_alloc(&init_mm, p4dp, idx);
		if (!pudp)
			continue;
		if (pud_is_leaf(*pudp)) {
			ptep = (pte_t *)pudp;
			goto update_the_pte;
		}
		pmdp = pmd_alloc(&init_mm, pudp, idx);
		if (!pmdp)
			continue;
		if (pmd_is_leaf(*pmdp)) {
			ptep = pmdp_ptep(pmdp);
			goto update_the_pte;
		}
		ptep = pte_alloc_kernel(pmdp, idx);
		if (!ptep)
			continue;
update_the_pte:
		radix__pte_update(&init_mm, idx, ptep, clear, 0, 0);
	}

	radix__flush_tlb_kernel_range(start, end);
}

void radix__mark_rodata_ro(void)
{
	unsigned long start, end;

	start = (unsigned long)_stext;
	end = (unsigned long)__end_rodata;

	radix__change_memory_range(start, end, _PAGE_WRITE);

	for (start = PAGE_OFFSET; start < (unsigned long)_stext; start += PAGE_SIZE) {
		end = start + PAGE_SIZE;
		if (overlaps_interrupt_vector_text(start, end))
			radix__change_memory_range(start, end, _PAGE_WRITE);
		else
			break;
	}
}

void radix__mark_initmem_nx(void)
{
	unsigned long start = (unsigned long)__init_begin;
	unsigned long end = (unsigned long)__init_end;

	radix__change_memory_range(start, end, _PAGE_EXEC);
}
#endif /* CONFIG_STRICT_KERNEL_RWX */

static inline void __meminit
print_mapping(unsigned long start, unsigned long end, unsigned long size, bool exec)
{
	char buf[10];

	if (end <= start)
		return;

	string_get_size(size, 1, STRING_UNITS_2, buf, sizeof(buf));

	pr_info("Mapped 0x%016lx-0x%016lx with %s pages%s\n", start, end, buf,
		exec ? " (exec)" : "");
}

static unsigned long next_boundary(unsigned long addr, unsigned long end)
{
#ifdef CONFIG_STRICT_KERNEL_RWX
	unsigned long stext_phys;

	stext_phys = __pa_symbol(_stext);

	// Relocatable kernel running at non-zero real address
	if (stext_phys != 0) {
		// The end of interrupts code at zero is a rodata boundary
		unsigned long end_intr = __pa_symbol(__end_interrupts) - stext_phys;
		if (addr < end_intr)
			return end_intr;

		// Start of relocated kernel text is a rodata boundary
		if (addr < stext_phys)
			return stext_phys;
	}

	if (addr < __pa_symbol(__srwx_boundary))
		return __pa_symbol(__srwx_boundary);
#endif
	return end;
}

static int __meminit create_physical_mapping(unsigned long start,
					     unsigned long end,
					     int nid, pgprot_t _prot)
{
	unsigned long vaddr, addr, mapping_size = 0;
	bool prev_exec, exec = false;
	pgprot_t prot;
	int psize;
	unsigned long max_mapping_size = radix_mem_block_size;

	if (debug_pagealloc_enabled_or_kfence())
		max_mapping_size = PAGE_SIZE;

	start = ALIGN(start, PAGE_SIZE);
	end   = ALIGN_DOWN(end, PAGE_SIZE);
	for (addr = start; addr < end; addr += mapping_size) {
		unsigned long gap, previous_size;
		int rc;

		gap = next_boundary(addr, end) - addr;
		if (gap > max_mapping_size)
			gap = max_mapping_size;
		previous_size = mapping_size;
		prev_exec = exec;

		if (IS_ALIGNED(addr, PUD_SIZE) && gap >= PUD_SIZE &&
		    mmu_psize_defs[MMU_PAGE_1G].shift) {
			mapping_size = PUD_SIZE;
			psize = MMU_PAGE_1G;
		} else if (IS_ALIGNED(addr, PMD_SIZE) && gap >= PMD_SIZE &&
			   mmu_psize_defs[MMU_PAGE_2M].shift) {
			mapping_size = PMD_SIZE;
			psize = MMU_PAGE_2M;
		} else {
			mapping_size = PAGE_SIZE;
			psize = mmu_virtual_psize;
		}

		vaddr = (unsigned long)__va(addr);

		if (overlaps_kernel_text(vaddr, vaddr + mapping_size) ||
		    overlaps_interrupt_vector_text(vaddr, vaddr + mapping_size)) {
			prot = PAGE_KERNEL_X;
			exec = true;
		} else {
			prot = _prot;
			exec = false;
		}

		if (mapping_size != previous_size || exec != prev_exec) {
			print_mapping(start, addr, previous_size, prev_exec);
			start = addr;
		}

		rc = __map_kernel_page(vaddr, addr, prot, mapping_size, nid, start, end);
		if (rc)
			return rc;

		update_page_count(psize, 1);
	}

	print_mapping(start, addr, mapping_size, exec);
	return 0;
}

static void __init radix_init_pgtable(void)
{
	unsigned long rts_field;
	phys_addr_t start, end;
	u64 i;

	/* We don't support slb for radix */
	slb_set_size(0);

	/*
	 * Create the linear mapping
	 */
	for_each_mem_range(i, &start, &end) {
		/*
		 * The memblock allocator  is up at this point, so the
		 * page tables will be allocated within the range. No
		 * need or a node (which we don't have yet).
		 */

		if (end >= RADIX_VMALLOC_START) {
			pr_warn("Outside the supported range\n");
			continue;
		}

		WARN_ON(create_physical_mapping(start, end,
						-1, PAGE_KERNEL));
	}

	if (!cpu_has_feature(CPU_FTR_HVMODE) &&
			cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
		/*
		 * Older versions of KVM on these machines prefer if the
		 * guest only uses the low 19 PID bits.
		 */
		mmu_pid_bits = 19;
	}
	mmu_base_pid = 1;

	/*
	 * Allocate Partition table and process table for the
	 * host.
	 */
	BUG_ON(PRTB_SIZE_SHIFT > 36);
	process_tb = early_alloc_pgtable(1UL << PRTB_SIZE_SHIFT, -1, 0, 0);
	/*
	 * Fill in the process table.
	 */
	rts_field = radix__get_tree_size();
	process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE);

	/*
	 * The init_mm context is given the first available (non-zero) PID,
	 * which is the "guard PID" and contains no page table. PIDR should
	 * never be set to zero because that duplicates the kernel address
	 * space at the 0x0... offset (quadrant 0)!
	 *
	 * An arbitrary PID that may later be allocated by the PID allocator
	 * for userspace processes must not be used either, because that
	 * would cause stale user mappings for that PID on CPUs outside of
	 * the TLB invalidation scheme (because it won't be in mm_cpumask).
	 *
	 * So permanently carve out one PID for the purpose of a guard PID.
	 */
	init_mm.context.id = mmu_base_pid;
	mmu_base_pid++;
}

static void __init radix_init_partition_table(void)
{
	unsigned long rts_field, dw0, dw1;

	mmu_partition_table_init();
	rts_field = radix__get_tree_size();
	dw0 = rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE | PATB_HR;
	dw1 = __pa(process_tb) | (PRTB_SIZE_SHIFT - 12) | PATB_GR;
	mmu_partition_table_set_entry(0, dw0, dw1, false);

	pr_info("Initializing Radix MMU\n");
}

static int __init get_idx_from_shift(unsigned int shift)
{
	int idx = -1;

	switch (shift) {
	case 0xc:
		idx = MMU_PAGE_4K;
		break;
	case 0x10:
		idx = MMU_PAGE_64K;
		break;
	case 0x15:
		idx = MMU_PAGE_2M;
		break;
	case 0x1e:
		idx = MMU_PAGE_1G;
		break;
	}
	return idx;
}

static int __init radix_dt_scan_page_sizes(unsigned long node,
					   const char *uname, int depth,
					   void *data)
{
	int size = 0;
	int shift, idx;
	unsigned int ap;
	const __be32 *prop;
	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);

	/* We are scanning "cpu" nodes only */
	if (type == NULL || strcmp(type, "cpu") != 0)
		return 0;

	/* Grab page size encodings */
	prop = of_get_flat_dt_prop(node, "ibm,processor-radix-AP-encodings", &size);
	if (!prop)
		return 0;

	pr_info("Page sizes from device-tree:\n");
	for (; size >= 4; size -= 4, ++prop) {

		struct mmu_psize_def *def;

		/* top 3 bit is AP encoding */
		shift = be32_to_cpu(prop[0]) & ~(0xe << 28);
		ap = be32_to_cpu(prop[0]) >> 29;
		pr_info("Page size shift = %d AP=0x%x\n", shift, ap);

		idx = get_idx_from_shift(shift);
		if (idx < 0)
			continue;

		def = &mmu_psize_defs[idx];
		def->shift = shift;
		def->ap  = ap;
		def->h_rpt_pgsize = psize_to_rpti_pgsize(idx);
	}

	/* needed ? */
	cur_cpu_spec->mmu_features &= ~MMU_FTR_NO_SLBIE_B;
	return 1;
}

#ifdef CONFIG_MEMORY_HOTPLUG
static int __init probe_memory_block_size(unsigned long node, const char *uname, int
					  depth, void *data)
{
	unsigned long *mem_block_size = (unsigned long *)data;
	const __be32 *prop;
	int len;

	if (depth != 1)
		return 0;

	if (strcmp(uname, "ibm,dynamic-reconfiguration-memory"))
		return 0;

	prop = of_get_flat_dt_prop(node, "ibm,lmb-size", &len);

	if (!prop || len < dt_root_size_cells * sizeof(__be32))
		/*
		 * Nothing in the device tree
		 */
		*mem_block_size = MIN_MEMORY_BLOCK_SIZE;
	else
		*mem_block_size = of_read_number(prop, dt_root_size_cells);
	return 1;
}

static unsigned long __init radix_memory_block_size(void)
{
	unsigned long mem_block_size = MIN_MEMORY_BLOCK_SIZE;

	/*
	 * OPAL firmware feature is set by now. Hence we are ok
	 * to test OPAL feature.
	 */
	if (firmware_has_feature(FW_FEATURE_OPAL))
		mem_block_size = 1UL * 1024 * 1024 * 1024;
	else
		of_scan_flat_dt(probe_memory_block_size, &mem_block_size);

	return mem_block_size;
}

#else   /* CONFIG_MEMORY_HOTPLUG */

static unsigned long __init radix_memory_block_size(void)
{
	return 1UL * 1024 * 1024 * 1024;
}

#endif /* CONFIG_MEMORY_HOTPLUG */


void __init radix__early_init_devtree(void)
{
	int rc;

	/*
	 * Try to find the available page sizes in the device-tree
	 */
	rc = of_scan_flat_dt(radix_dt_scan_page_sizes, NULL);
	if (!rc) {
		/*
		 * No page size details found in device tree.
		 * Let's assume we have page 4k and 64k support
		 */
		mmu_psize_defs[MMU_PAGE_4K].shift = 12;
		mmu_psize_defs[MMU_PAGE_4K].ap = 0x0;
		mmu_psize_defs[MMU_PAGE_4K].h_rpt_pgsize =
			psize_to_rpti_pgsize(MMU_PAGE_4K);

		mmu_psize_defs[MMU_PAGE_64K].shift = 16;
		mmu_psize_defs[MMU_PAGE_64K].ap = 0x5;
		mmu_psize_defs[MMU_PAGE_64K].h_rpt_pgsize =
			psize_to_rpti_pgsize(MMU_PAGE_64K);
	}

	/*
	 * Max mapping size used when mapping pages. We don't use
	 * ppc_md.memory_block_size() here because this get called
	 * early and we don't have machine probe called yet. Also
	 * the pseries implementation only check for ibm,lmb-size.
	 * All hypervisor supporting radix do expose that device
	 * tree node.
	 */
	radix_mem_block_size = radix_memory_block_size();
	return;
}

void __init radix__early_init_mmu(void)
{
	unsigned long lpcr;

#ifdef CONFIG_PPC_64S_HASH_MMU
#ifdef CONFIG_PPC_64K_PAGES
	/* PAGE_SIZE mappings */
	mmu_virtual_psize = MMU_PAGE_64K;
#else
	mmu_virtual_psize = MMU_PAGE_4K;
#endif

#ifdef CONFIG_SPARSEMEM_VMEMMAP
	/* vmemmap mapping */
	if (mmu_psize_defs[MMU_PAGE_2M].shift) {
		/*
		 * map vmemmap using 2M if available
		 */
		mmu_vmemmap_psize = MMU_PAGE_2M;
	} else
		mmu_vmemmap_psize = mmu_virtual_psize;
#endif
#endif
	/*
	 * initialize page table size
	 */
	__pte_index_size = RADIX_PTE_INDEX_SIZE;
	__pmd_index_size = RADIX_PMD_INDEX_SIZE;
	__pud_index_size = RADIX_PUD_INDEX_SIZE;
	__pgd_index_size = RADIX_PGD_INDEX_SIZE;
	__pud_cache_index = RADIX_PUD_INDEX_SIZE;
	__pte_table_size = RADIX_PTE_TABLE_SIZE;
	__pmd_table_size = RADIX_PMD_TABLE_SIZE;
	__pud_table_size = RADIX_PUD_TABLE_SIZE;
	__pgd_table_size = RADIX_PGD_TABLE_SIZE;

	__pmd_val_bits = RADIX_PMD_VAL_BITS;
	__pud_val_bits = RADIX_PUD_VAL_BITS;
	__pgd_val_bits = RADIX_PGD_VAL_BITS;

	__kernel_virt_start = RADIX_KERN_VIRT_START;
	__vmalloc_start = RADIX_VMALLOC_START;
	__vmalloc_end = RADIX_VMALLOC_END;
	__kernel_io_start = RADIX_KERN_IO_START;
	__kernel_io_end = RADIX_KERN_IO_END;
	vmemmap = (struct page *)RADIX_VMEMMAP_START;
	ioremap_bot = IOREMAP_BASE;

#ifdef CONFIG_PCI
	pci_io_base = ISA_IO_BASE;
#endif
	__pte_frag_nr = RADIX_PTE_FRAG_NR;
	__pte_frag_size_shift = RADIX_PTE_FRAG_SIZE_SHIFT;
	__pmd_frag_nr = RADIX_PMD_FRAG_NR;
	__pmd_frag_size_shift = RADIX_PMD_FRAG_SIZE_SHIFT;

	radix_init_pgtable();

	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
		lpcr = mfspr(SPRN_LPCR);
		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
		radix_init_partition_table();
	} else {
		radix_init_pseries();
	}

	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);

	/* Switch to the guard PID before turning on MMU */
	radix__switch_mmu_context(NULL, &init_mm);
	tlbiel_all();
}

void radix__early_init_mmu_secondary(void)
{
	unsigned long lpcr;
	/*
	 * update partition table control register and UPRT
	 */
	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
		lpcr = mfspr(SPRN_LPCR);
		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);

		set_ptcr_when_no_uv(__pa(partition_tb) |
				    (PATB_SIZE_SHIFT - 12));
	}

	radix__switch_mmu_context(NULL, &init_mm);
	tlbiel_all();

	/* Make sure userspace can't change the AMR */
	mtspr(SPRN_UAMOR, 0);
}

/* Called during kexec sequence with MMU off */
notrace void radix__mmu_cleanup_all(void)
{
	unsigned long lpcr;

	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
		lpcr = mfspr(SPRN_LPCR);
		mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT);
		set_ptcr_when_no_uv(0);
		powernv_set_nmmu_ptcr(0);
		radix__flush_tlb_all();
	}
}

#ifdef CONFIG_MEMORY_HOTPLUG
static void free_pte_table(pte_t *pte_start, pmd_t *pmd)
{
	pte_t *pte;
	int i;

	for (i = 0; i < PTRS_PER_PTE; i++) {
		pte = pte_start + i;
		if (!pte_none(*pte))
			return;
	}

	pte_free_kernel(&init_mm, pte_start);
	pmd_clear(pmd);
}

static void free_pmd_table(pmd_t *pmd_start, pud_t *pud)
{
	pmd_t *pmd;
	int i;

	for (i = 0; i < PTRS_PER_PMD; i++) {
		pmd = pmd_start + i;
		if (!pmd_none(*pmd))
			return;
	}

	pmd_free(&init_mm, pmd_start);
	pud_clear(pud);
}

static void free_pud_table(pud_t *pud_start, p4d_t *p4d)
{
	pud_t *pud;
	int i;

	for (i = 0; i < PTRS_PER_PUD; i++) {
		pud = pud_start + i;
		if (!pud_none(*pud))
			return;
	}

	pud_free(&init_mm, pud_start);
	p4d_clear(p4d);
}

static void remove_pte_table(pte_t *pte_start, unsigned long addr,
			     unsigned long end)
{
	unsigned long next;
	pte_t *pte;

	pte = pte_start + pte_index(addr);
	for (; addr < end; addr = next, pte++) {
		next = (addr + PAGE_SIZE) & PAGE_MASK;
		if (next > end)
			next = end;

		if (!pte_present(*pte))
			continue;

		if (!PAGE_ALIGNED(addr) || !PAGE_ALIGNED(next)) {
			/*
			 * The vmemmap_free() and remove_section_mapping()
			 * codepaths call us with aligned addresses.
			 */
			WARN_ONCE(1, "%s: unaligned range\n", __func__);
			continue;
		}

		pte_clear(&init_mm, addr, pte);
	}
}

static void __meminit remove_pmd_table(pmd_t *pmd_start, unsigned long addr,
			     unsigned long end)
{
	unsigned long next;
	pte_t *pte_base;
	pmd_t *pmd;

	pmd = pmd_start + pmd_index(addr);
	for (; addr < end; addr = next, pmd++) {
		next = pmd_addr_end(addr, end);

		if (!pmd_present(*pmd))
			continue;

		if (pmd_is_leaf(*pmd)) {
			if (!IS_ALIGNED(addr, PMD_SIZE) ||
			    !IS_ALIGNED(next, PMD_SIZE)) {
				WARN_ONCE(1, "%s: unaligned range\n", __func__);
				continue;
			}
			pte_clear(&init_mm, addr, (pte_t *)pmd);
			continue;
		}

		pte_base = (pte_t *)pmd_page_vaddr(*pmd);
		remove_pte_table(pte_base, addr, next);
		free_pte_table(pte_base, pmd);
	}
}

static void __meminit remove_pud_table(pud_t *pud_start, unsigned long addr,
			     unsigned long end)
{
	unsigned long next;
	pmd_t *pmd_base;
	pud_t *pud;

	pud = pud_start + pud_index(addr);
	for (; addr < end; addr = next, pud++) {
		next = pud_addr_end(addr, end);

		if (!pud_present(*pud))
			continue;

		if (pud_is_leaf(*pud)) {
			if (!IS_ALIGNED(addr, PUD_SIZE) ||
			    !IS_ALIGNED(next, PUD_SIZE)) {
				WARN_ONCE(1, "%s: unaligned range\n", __func__);
				continue;
			}
			pte_clear(&init_mm, addr, (pte_t *)pud);
			continue;
		}

		pmd_base = pud_pgtable(*pud);
		remove_pmd_table(pmd_base, addr, next);
		free_pmd_table(pmd_base, pud);
	}
}

static void __meminit remove_pagetable(unsigned long start, unsigned long end)
{
	unsigned long addr, next;
	pud_t *pud_base;
	pgd_t *pgd;
	p4d_t *p4d;

	spin_lock(&init_mm.page_table_lock);

	for (addr = start; addr < end; addr = next) {
		next = pgd_addr_end(addr, end);

		pgd = pgd_offset_k(addr);
		p4d = p4d_offset(pgd, addr);
		if (!p4d_present(*p4d))
			continue;

		if (p4d_is_leaf(*p4d)) {
			if (!IS_ALIGNED(addr, P4D_SIZE) ||
			    !IS_ALIGNED(next, P4D_SIZE)) {
				WARN_ONCE(1, "%s: unaligned range\n", __func__);
				continue;
			}

			pte_clear(&init_mm, addr, (pte_t *)pgd);
			continue;
		}

		pud_base = p4d_pgtable(*p4d);
		remove_pud_table(pud_base, addr, next);
		free_pud_table(pud_base, p4d);
	}

	spin_unlock(&init_mm.page_table_lock);
	radix__flush_tlb_kernel_range(start, end);
}

int __meminit radix__create_section_mapping(unsigned long start,
					    unsigned long end, int nid,
					    pgprot_t prot)
{
	if (end >= RADIX_VMALLOC_START) {
		pr_warn("Outside the supported range\n");
		return -1;
	}

	return create_physical_mapping(__pa(start), __pa(end),
				       nid, prot);
}

int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
{
	remove_pagetable(start, end);
	return 0;
}
#endif /* CONFIG_MEMORY_HOTPLUG */

#ifdef CONFIG_SPARSEMEM_VMEMMAP
static int __map_kernel_page_nid(unsigned long ea, unsigned long pa,
				 pgprot_t flags, unsigned int map_page_size,
				 int nid)
{
	return __map_kernel_page(ea, pa, flags, map_page_size, nid, 0, 0);
}

int __meminit radix__vmemmap_create_mapping(unsigned long start,
				      unsigned long page_size,
				      unsigned long phys)
{
	/* Create a PTE encoding */
	unsigned long flags = _PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_KERNEL_RW;
	int nid = early_pfn_to_nid(phys >> PAGE_SHIFT);
	int ret;

	if ((start + page_size) >= RADIX_VMEMMAP_END) {
		pr_warn("Outside the supported range\n");
		return -1;
	}

	ret = __map_kernel_page_nid(start, phys, __pgprot(flags), page_size, nid);
	BUG_ON(ret);

	return 0;
}

#ifdef CONFIG_MEMORY_HOTPLUG
void __meminit radix__vmemmap_remove_mapping(unsigned long start, unsigned long page_size)
{
	remove_pagetable(start, start + page_size);
}
#endif
#endif

#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KFENCE)
void radix__kernel_map_pages(struct page *page, int numpages, int enable)
{
	unsigned long addr;

	addr = (unsigned long)page_address(page);

	if (enable)
		set_memory_p(addr, numpages);
	else
		set_memory_np(addr, numpages);
}
#endif

#ifdef CONFIG_TRANSPARENT_HUGEPAGE

unsigned long radix__pmd_hugepage_update(struct mm_struct *mm, unsigned long addr,
				  pmd_t *pmdp, unsigned long clr,
				  unsigned long set)
{
	unsigned long old;

#ifdef CONFIG_DEBUG_VM
	WARN_ON(!radix__pmd_trans_huge(*pmdp) && !pmd_devmap(*pmdp));
	assert_spin_locked(pmd_lockptr(mm, pmdp));
#endif

	old = radix__pte_update(mm, addr, (pte_t *)pmdp, clr, set, 1);
	trace_hugepage_update(addr, old, clr, set);

	return old;
}

pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
			pmd_t *pmdp)

{
	pmd_t pmd;

	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
	VM_BUG_ON(radix__pmd_trans_huge(*pmdp));
	VM_BUG_ON(pmd_devmap(*pmdp));
	/*
	 * khugepaged calls this for normal pmd
	 */
	pmd = *pmdp;
	pmd_clear(pmdp);

	radix__flush_tlb_collapsed_pmd(vma->vm_mm, address);

	return pmd;
}

/*
 * For us pgtable_t is pte_t *. Inorder to save the deposisted
 * page table, we consider the allocated page table as a list
 * head. On withdraw we need to make sure we zero out the used
 * list_head memory area.
 */
void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
				 pgtable_t pgtable)
{
	struct list_head *lh = (struct list_head *) pgtable;

	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	if (!pmd_huge_pte(mm, pmdp))
		INIT_LIST_HEAD(lh);
	else
		list_add(lh, (struct list_head *) pmd_huge_pte(mm, pmdp));
	pmd_huge_pte(mm, pmdp) = pgtable;
}

pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
{
	pte_t *ptep;
	pgtable_t pgtable;
	struct list_head *lh;

	assert_spin_locked(pmd_lockptr(mm, pmdp));

	/* FIFO */
	pgtable = pmd_huge_pte(mm, pmdp);
	lh = (struct list_head *) pgtable;
	if (list_empty(lh))
		pmd_huge_pte(mm, pmdp) = NULL;
	else {
		pmd_huge_pte(mm, pmdp) = (pgtable_t) lh->next;
		list_del(lh);
	}
	ptep = (pte_t *) pgtable;
	*ptep = __pte(0);
	ptep++;
	*ptep = __pte(0);
	return pgtable;
}

pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
				     unsigned long addr, pmd_t *pmdp)
{
	pmd_t old_pmd;
	unsigned long old;

	old = radix__pmd_hugepage_update(mm, addr, pmdp, ~0UL, 0);
	old_pmd = __pmd(old);
	return old_pmd;
}

#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
				  pte_t entry, unsigned long address, int psize)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long set = pte_val(entry) & (_PAGE_DIRTY | _PAGE_ACCESSED |
					      _PAGE_RW | _PAGE_EXEC);

	unsigned long change = pte_val(entry) ^ pte_val(*ptep);
	/*
	 * On POWER9, the NMMU is not able to relax PTE access permissions
	 * for a translation with a TLB. The PTE must be invalidated, TLB
	 * flushed before the new PTE is installed.
	 *
	 * This only needs to be done for radix, because hash translation does
	 * flush when updating the linux pte (and we don't support NMMU
	 * accelerators on HPT on POWER9 anyway XXX: do we?).
	 *
	 * POWER10 (and P9P) NMMU does behave as per ISA.
	 */
	if (!cpu_has_feature(CPU_FTR_ARCH_31) && (change & _PAGE_RW) &&
	    atomic_read(&mm->context.copros) > 0) {
		unsigned long old_pte, new_pte;

		old_pte = __radix_pte_update(ptep, _PAGE_PRESENT, _PAGE_INVALID);
		new_pte = old_pte | set;
		radix__flush_tlb_page_psize(mm, address, psize);
		__radix_pte_update(ptep, _PAGE_INVALID, new_pte);
	} else {
		__radix_pte_update(ptep, 0, set);
		/*
		 * Book3S does not require a TLB flush when relaxing access
		 * restrictions when the address space (modulo the POWER9 nest
		 * MMU issue above) because the MMU will reload the PTE after
		 * taking an access fault, as defined by the architecture. See
		 * "Setting a Reference or Change Bit or Upgrading Access
		 *  Authority (PTE Subject to Atomic Hardware Updates)" in
		 *  Power ISA Version 3.1B.
		 */
	}
	/* See ptesync comment in radix__set_pte_at */
}

void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
				    unsigned long addr, pte_t *ptep,
				    pte_t old_pte, pte_t pte)
{
	struct mm_struct *mm = vma->vm_mm;

	/*
	 * POWER9 NMMU must flush the TLB after clearing the PTE before
	 * installing a PTE with more relaxed access permissions, see
	 * radix__ptep_set_access_flags.
	 */
	if (!cpu_has_feature(CPU_FTR_ARCH_31) &&
	    is_pte_rw_upgrade(pte_val(old_pte), pte_val(pte)) &&
	    (atomic_read(&mm->context.copros) > 0))
		radix__flush_tlb_page(vma, addr);

	set_pte_at(mm, addr, ptep, pte);
}

int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
{
	pte_t *ptep = (pte_t *)pud;
	pte_t new_pud = pfn_pte(__phys_to_pfn(addr), prot);

	if (!radix_enabled())
		return 0;

	set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pud);

	return 1;
}

int pud_clear_huge(pud_t *pud)
{
	if (pud_is_leaf(*pud)) {
		pud_clear(pud);
		return 1;
	}

	return 0;
}

int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
	pmd_t *pmd;
	int i;

	pmd = pud_pgtable(*pud);
	pud_clear(pud);

	flush_tlb_kernel_range(addr, addr + PUD_SIZE);

	for (i = 0; i < PTRS_PER_PMD; i++) {
		if (!pmd_none(pmd[i])) {
			pte_t *pte;
			pte = (pte_t *)pmd_page_vaddr(pmd[i]);

			pte_free_kernel(&init_mm, pte);
		}
	}

	pmd_free(&init_mm, pmd);

	return 1;
}

int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
{
	pte_t *ptep = (pte_t *)pmd;
	pte_t new_pmd = pfn_pte(__phys_to_pfn(addr), prot);

	if (!radix_enabled())
		return 0;

	set_pte_at(&init_mm, 0 /* radix unused */, ptep, new_pmd);

	return 1;
}

int pmd_clear_huge(pmd_t *pmd)
{
	if (pmd_is_leaf(*pmd)) {
		pmd_clear(pmd);
		return 1;
	}

	return 0;
}

int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
	pte_t *pte;

	pte = (pte_t *)pmd_page_vaddr(*pmd);
	pmd_clear(pmd);

	flush_tlb_kernel_range(addr, addr + PMD_SIZE);

	pte_free_kernel(&init_mm, pte);

	return 1;
}