summaryrefslogtreecommitdiff
path: root/arch/powerpc/mm/book3s64/radix_tlb.c
blob: 631be42abd330611db0c8f67a7adc6a56dc0a57d (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
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * TLB flush routines for radix kernels.
 *
 * Copyright 2015-2016, Aneesh Kumar K.V, IBM Corporation.
 */

#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/memblock.h>
#include <linux/mmu_context.h>
#include <linux/sched/mm.h>

#include <asm/ppc-opcode.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/trace.h>
#include <asm/cputhreads.h>

#define RIC_FLUSH_TLB 0
#define RIC_FLUSH_PWC 1
#define RIC_FLUSH_ALL 2

/*
 * tlbiel instruction for radix, set invalidation
 * i.e., r=1 and is=01 or is=10 or is=11
 */
static __always_inline void tlbiel_radix_set_isa300(unsigned int set, unsigned int is,
					unsigned int pid,
					unsigned int ric, unsigned int prs)
{
	unsigned long rb;
	unsigned long rs;

	rb = (set << PPC_BITLSHIFT(51)) | (is << PPC_BITLSHIFT(53));
	rs = ((unsigned long)pid << PPC_BITLSHIFT(31));

	asm volatile(PPC_TLBIEL(%0, %1, %2, %3, 1)
		     : : "r"(rb), "r"(rs), "i"(ric), "i"(prs)
		     : "memory");
}

static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
{
	unsigned int set;

	asm volatile("ptesync": : :"memory");

	/*
	 * Flush the first set of the TLB, and the entire Page Walk Cache
	 * and partition table entries. Then flush the remaining sets of the
	 * TLB.
	 */

	if (early_cpu_has_feature(CPU_FTR_HVMODE)) {
		/* MSR[HV] should flush partition scope translations first. */
		tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
		for (set = 1; set < num_sets; set++)
			tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
	}

	/* Flush process scoped entries. */
	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1);
	for (set = 1; set < num_sets; set++)
		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);

	asm volatile("ptesync": : :"memory");
}

void radix__tlbiel_all(unsigned int action)
{
	unsigned int is;

	switch (action) {
	case TLB_INVAL_SCOPE_GLOBAL:
		is = 3;
		break;
	case TLB_INVAL_SCOPE_LPID:
		is = 2;
		break;
	default:
		BUG();
	}

	if (early_cpu_has_feature(CPU_FTR_ARCH_300))
		tlbiel_all_isa300(POWER9_TLB_SETS_RADIX, is);
	else
		WARN(1, "%s called on pre-POWER9 CPU\n", __func__);

	asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT "; isync" : : :"memory");
}

static __always_inline void __tlbiel_pid(unsigned long pid, int set,
				unsigned long ric)
{
	unsigned long rb,rs,prs,r;

	rb = PPC_BIT(53); /* IS = 1 */
	rb |= set << PPC_BITLSHIFT(51);
	rs = ((unsigned long)pid) << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* radix format */

	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	trace_tlbie(0, 1, rb, rs, ric, prs, r);
}

static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
{
	unsigned long rb,rs,prs,r;

	rb = PPC_BIT(53); /* IS = 1 */
	rs = pid << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* radix format */

	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	trace_tlbie(0, 0, rb, rs, ric, prs, r);
}

static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
{
	unsigned long rb,rs,prs,r;

	rb = PPC_BIT(52); /* IS = 2 */
	rs = lpid;
	prs = 0; /* partition scoped */
	r = 1;   /* radix format */

	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
}

static __always_inline void __tlbie_lpid_guest(unsigned long lpid, unsigned long ric)
{
	unsigned long rb,rs,prs,r;

	rb = PPC_BIT(52); /* IS = 2 */
	rs = lpid;
	prs = 1; /* process scoped */
	r = 1;   /* radix format */

	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
}

static __always_inline void __tlbiel_va(unsigned long va, unsigned long pid,
					unsigned long ap, unsigned long ric)
{
	unsigned long rb,rs,prs,r;

	rb = va & ~(PPC_BITMASK(52, 63));
	rb |= ap << PPC_BITLSHIFT(58);
	rs = pid << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* radix format */

	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	trace_tlbie(0, 1, rb, rs, ric, prs, r);
}

static __always_inline void __tlbie_va(unsigned long va, unsigned long pid,
				       unsigned long ap, unsigned long ric)
{
	unsigned long rb,rs,prs,r;

	rb = va & ~(PPC_BITMASK(52, 63));
	rb |= ap << PPC_BITLSHIFT(58);
	rs = pid << PPC_BITLSHIFT(31);
	prs = 1; /* process scoped */
	r = 1;   /* radix format */

	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	trace_tlbie(0, 0, rb, rs, ric, prs, r);
}

static __always_inline void __tlbie_lpid_va(unsigned long va, unsigned long lpid,
					    unsigned long ap, unsigned long ric)
{
	unsigned long rb,rs,prs,r;

	rb = va & ~(PPC_BITMASK(52, 63));
	rb |= ap << PPC_BITLSHIFT(58);
	rs = lpid;
	prs = 0; /* partition scoped */
	r = 1;   /* radix format */

	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
}

static inline void fixup_tlbie(void)
{
	unsigned long pid = 0;
	unsigned long va = ((1UL << 52) - 1);

	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
		asm volatile("ptesync": : :"memory");
		__tlbie_va(va, pid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
	}
}

static inline void fixup_tlbie_lpid(unsigned long lpid)
{
	unsigned long va = ((1UL << 52) - 1);

	if (cpu_has_feature(CPU_FTR_P9_TLBIE_BUG)) {
		asm volatile("ptesync": : :"memory");
		__tlbie_lpid_va(va, lpid, mmu_get_ap(MMU_PAGE_64K), RIC_FLUSH_TLB);
	}
}

/*
 * We use 128 set in radix mode and 256 set in hpt mode.
 */
static __always_inline void _tlbiel_pid(unsigned long pid, unsigned long ric)
{
	int set;

	asm volatile("ptesync": : :"memory");

	/*
	 * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
	 * also flush the entire Page Walk Cache.
	 */
	__tlbiel_pid(pid, 0, ric);

	/* For PWC, only one flush is needed */
	if (ric == RIC_FLUSH_PWC) {
		asm volatile("ptesync": : :"memory");
		return;
	}

	/* For the remaining sets, just flush the TLB */
	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
		__tlbiel_pid(pid, set, RIC_FLUSH_TLB);

	asm volatile("ptesync": : :"memory");
	asm volatile(PPC_RADIX_INVALIDATE_ERAT_USER "; isync" : : :"memory");
}

static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
{
	asm volatile("ptesync": : :"memory");

	/*
	 * Workaround the fact that the "ric" argument to __tlbie_pid
	 * must be a compile-time contraint to match the "i" constraint
	 * in the asm statement.
	 */
	switch (ric) {
	case RIC_FLUSH_TLB:
		__tlbie_pid(pid, RIC_FLUSH_TLB);
		break;
	case RIC_FLUSH_PWC:
		__tlbie_pid(pid, RIC_FLUSH_PWC);
		break;
	case RIC_FLUSH_ALL:
	default:
		__tlbie_pid(pid, RIC_FLUSH_ALL);
	}
	fixup_tlbie();
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

struct tlbiel_pid {
	unsigned long pid;
	unsigned long ric;
};

static void do_tlbiel_pid(void *info)
{
	struct tlbiel_pid *t = info;

	if (t->ric == RIC_FLUSH_TLB)
		_tlbiel_pid(t->pid, RIC_FLUSH_TLB);
	else if (t->ric == RIC_FLUSH_PWC)
		_tlbiel_pid(t->pid, RIC_FLUSH_PWC);
	else
		_tlbiel_pid(t->pid, RIC_FLUSH_ALL);
}

static inline void _tlbiel_pid_multicast(struct mm_struct *mm,
				unsigned long pid, unsigned long ric)
{
	struct cpumask *cpus = mm_cpumask(mm);
	struct tlbiel_pid t = { .pid = pid, .ric = ric };

	on_each_cpu_mask(cpus, do_tlbiel_pid, &t, 1);
	/*
	 * Always want the CPU translations to be invalidated with tlbiel in
	 * these paths, so while coprocessors must use tlbie, we can not
	 * optimise away the tlbiel component.
	 */
	if (atomic_read(&mm->context.copros) > 0)
		_tlbie_pid(pid, RIC_FLUSH_ALL);
}

static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric)
{
	asm volatile("ptesync": : :"memory");

	/*
	 * Workaround the fact that the "ric" argument to __tlbie_pid
	 * must be a compile-time contraint to match the "i" constraint
	 * in the asm statement.
	 */
	switch (ric) {
	case RIC_FLUSH_TLB:
		__tlbie_lpid(lpid, RIC_FLUSH_TLB);
		break;
	case RIC_FLUSH_PWC:
		__tlbie_lpid(lpid, RIC_FLUSH_PWC);
		break;
	case RIC_FLUSH_ALL:
	default:
		__tlbie_lpid(lpid, RIC_FLUSH_ALL);
	}
	fixup_tlbie_lpid(lpid);
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

static __always_inline void _tlbie_lpid_guest(unsigned long lpid, unsigned long ric)
{
	/*
	 * Workaround the fact that the "ric" argument to __tlbie_pid
	 * must be a compile-time contraint to match the "i" constraint
	 * in the asm statement.
	 */
	switch (ric) {
	case RIC_FLUSH_TLB:
		__tlbie_lpid_guest(lpid, RIC_FLUSH_TLB);
		break;
	case RIC_FLUSH_PWC:
		__tlbie_lpid_guest(lpid, RIC_FLUSH_PWC);
		break;
	case RIC_FLUSH_ALL:
	default:
		__tlbie_lpid_guest(lpid, RIC_FLUSH_ALL);
	}
	fixup_tlbie_lpid(lpid);
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
				    unsigned long pid, unsigned long page_size,
				    unsigned long psize)
{
	unsigned long addr;
	unsigned long ap = mmu_get_ap(psize);

	for (addr = start; addr < end; addr += page_size)
		__tlbiel_va(addr, pid, ap, RIC_FLUSH_TLB);
}

static __always_inline void _tlbiel_va(unsigned long va, unsigned long pid,
				       unsigned long psize, unsigned long ric)
{
	unsigned long ap = mmu_get_ap(psize);

	asm volatile("ptesync": : :"memory");
	__tlbiel_va(va, pid, ap, ric);
	asm volatile("ptesync": : :"memory");
}

static inline void _tlbiel_va_range(unsigned long start, unsigned long end,
				    unsigned long pid, unsigned long page_size,
				    unsigned long psize, bool also_pwc)
{
	asm volatile("ptesync": : :"memory");
	if (also_pwc)
		__tlbiel_pid(pid, 0, RIC_FLUSH_PWC);
	__tlbiel_va_range(start, end, pid, page_size, psize);
	asm volatile("ptesync": : :"memory");
}

static inline void __tlbie_va_range(unsigned long start, unsigned long end,
				    unsigned long pid, unsigned long page_size,
				    unsigned long psize)
{
	unsigned long addr;
	unsigned long ap = mmu_get_ap(psize);

	for (addr = start; addr < end; addr += page_size)
		__tlbie_va(addr, pid, ap, RIC_FLUSH_TLB);
}

static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
				      unsigned long psize, unsigned long ric)
{
	unsigned long ap = mmu_get_ap(psize);

	asm volatile("ptesync": : :"memory");
	__tlbie_va(va, pid, ap, ric);
	fixup_tlbie();
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

struct tlbiel_va {
	unsigned long pid;
	unsigned long va;
	unsigned long psize;
	unsigned long ric;
};

static void do_tlbiel_va(void *info)
{
	struct tlbiel_va *t = info;

	if (t->ric == RIC_FLUSH_TLB)
		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_TLB);
	else if (t->ric == RIC_FLUSH_PWC)
		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_PWC);
	else
		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_ALL);
}

static inline void _tlbiel_va_multicast(struct mm_struct *mm,
				unsigned long va, unsigned long pid,
				unsigned long psize, unsigned long ric)
{
	struct cpumask *cpus = mm_cpumask(mm);
	struct tlbiel_va t = { .va = va, .pid = pid, .psize = psize, .ric = ric };
	on_each_cpu_mask(cpus, do_tlbiel_va, &t, 1);
	if (atomic_read(&mm->context.copros) > 0)
		_tlbie_va(va, pid, psize, RIC_FLUSH_TLB);
}

struct tlbiel_va_range {
	unsigned long pid;
	unsigned long start;
	unsigned long end;
	unsigned long page_size;
	unsigned long psize;
	bool also_pwc;
};

static void do_tlbiel_va_range(void *info)
{
	struct tlbiel_va_range *t = info;

	_tlbiel_va_range(t->start, t->end, t->pid, t->page_size,
				    t->psize, t->also_pwc);
}

static __always_inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid,
			      unsigned long psize, unsigned long ric)
{
	unsigned long ap = mmu_get_ap(psize);

	asm volatile("ptesync": : :"memory");
	__tlbie_lpid_va(va, lpid, ap, ric);
	fixup_tlbie_lpid(lpid);
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

static inline void _tlbie_va_range(unsigned long start, unsigned long end,
				    unsigned long pid, unsigned long page_size,
				    unsigned long psize, bool also_pwc)
{
	asm volatile("ptesync": : :"memory");
	if (also_pwc)
		__tlbie_pid(pid, RIC_FLUSH_PWC);
	__tlbie_va_range(start, end, pid, page_size, psize);
	fixup_tlbie();
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
				unsigned long start, unsigned long end,
				unsigned long pid, unsigned long page_size,
				unsigned long psize, bool also_pwc)
{
	struct cpumask *cpus = mm_cpumask(mm);
	struct tlbiel_va_range t = { .start = start, .end = end,
				.pid = pid, .page_size = page_size,
				.psize = psize, .also_pwc = also_pwc };

	on_each_cpu_mask(cpus, do_tlbiel_va_range, &t, 1);
	if (atomic_read(&mm->context.copros) > 0)
		_tlbie_va_range(start, end, pid, page_size, psize, also_pwc);
}

/*
 * Base TLB flushing operations:
 *
 *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
 *  - flush_tlb_page(vma, vmaddr) flushes one page
 *  - flush_tlb_range(vma, start, end) flushes a range of pages
 *  - flush_tlb_kernel_range(start, end) flushes kernel pages
 *
 *  - local_* variants of page and mm only apply to the current
 *    processor
 */
void radix__local_flush_tlb_mm(struct mm_struct *mm)
{
	unsigned long pid;

	preempt_disable();
	pid = mm->context.id;
	if (pid != MMU_NO_CONTEXT)
		_tlbiel_pid(pid, RIC_FLUSH_TLB);
	preempt_enable();
}
EXPORT_SYMBOL(radix__local_flush_tlb_mm);

#ifndef CONFIG_SMP
void radix__local_flush_all_mm(struct mm_struct *mm)
{
	unsigned long pid;

	preempt_disable();
	pid = mm->context.id;
	if (pid != MMU_NO_CONTEXT)
		_tlbiel_pid(pid, RIC_FLUSH_ALL);
	preempt_enable();
}
EXPORT_SYMBOL(radix__local_flush_all_mm);
#endif /* CONFIG_SMP */

void radix__local_flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
				       int psize)
{
	unsigned long pid;

	preempt_disable();
	pid = mm->context.id;
	if (pid != MMU_NO_CONTEXT)
		_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
	preempt_enable();
}

void radix__local_flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
#ifdef CONFIG_HUGETLB_PAGE
	/* need the return fix for nohash.c */
	if (is_vm_hugetlb_page(vma))
		return radix__local_flush_hugetlb_page(vma, vmaddr);
#endif
	radix__local_flush_tlb_page_psize(vma->vm_mm, vmaddr, mmu_virtual_psize);
}
EXPORT_SYMBOL(radix__local_flush_tlb_page);

static bool mm_is_singlethreaded(struct mm_struct *mm)
{
	if (atomic_read(&mm->context.copros) > 0)
		return false;
	if (atomic_read(&mm->mm_users) <= 1 && current->mm == mm)
		return true;
	return false;
}

static bool mm_needs_flush_escalation(struct mm_struct *mm)
{
	/*
	 * P9 nest MMU has issues with the page walk cache
	 * caching PTEs and not flushing them properly when
	 * RIC = 0 for a PID/LPID invalidate
	 */
	if (atomic_read(&mm->context.copros) > 0)
		return true;
	return false;
}

#ifdef CONFIG_SMP
static void do_exit_flush_lazy_tlb(void *arg)
{
	struct mm_struct *mm = arg;
	unsigned long pid = mm->context.id;

	if (current->mm == mm)
		return; /* Local CPU */

	if (current->active_mm == mm) {
		/*
		 * Must be a kernel thread because sender is single-threaded.
		 */
		BUG_ON(current->mm);
		mmgrab(&init_mm);
		switch_mm(mm, &init_mm, current);
		current->active_mm = &init_mm;
		mmdrop(mm);
	}
	_tlbiel_pid(pid, RIC_FLUSH_ALL);
}

static void exit_flush_lazy_tlbs(struct mm_struct *mm)
{
	/*
	 * Would be nice if this was async so it could be run in
	 * parallel with our local flush, but generic code does not
	 * give a good API for it. Could extend the generic code or
	 * make a special powerpc IPI for flushing TLBs.
	 * For now it's not too performance critical.
	 */
	smp_call_function_many(mm_cpumask(mm), do_exit_flush_lazy_tlb,
				(void *)mm, 1);
	mm_reset_thread_local(mm);
}

void radix__flush_tlb_mm(struct mm_struct *mm)
{
	unsigned long pid;

	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		return;

	preempt_disable();
	/*
	 * Order loads of mm_cpumask vs previous stores to clear ptes before
	 * the invalidate. See barrier in switch_mm_irqs_off
	 */
	smp_mb();
	if (!mm_is_thread_local(mm)) {
		if (unlikely(mm_is_singlethreaded(mm))) {
			exit_flush_lazy_tlbs(mm);
			goto local;
		}

		if (cputlb_use_tlbie()) {
			if (mm_needs_flush_escalation(mm))
				_tlbie_pid(pid, RIC_FLUSH_ALL);
			else
				_tlbie_pid(pid, RIC_FLUSH_TLB);
		} else {
			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB);
		}
	} else {
local:
		_tlbiel_pid(pid, RIC_FLUSH_TLB);
	}
	preempt_enable();
}
EXPORT_SYMBOL(radix__flush_tlb_mm);

static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
{
	unsigned long pid;

	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		return;

	preempt_disable();
	smp_mb(); /* see radix__flush_tlb_mm */
	if (!mm_is_thread_local(mm)) {
		if (unlikely(mm_is_singlethreaded(mm))) {
			if (!fullmm) {
				exit_flush_lazy_tlbs(mm);
				goto local;
			}
		}
		if (cputlb_use_tlbie())
			_tlbie_pid(pid, RIC_FLUSH_ALL);
		else
			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
	} else {
local:
		_tlbiel_pid(pid, RIC_FLUSH_ALL);
	}
	preempt_enable();
}
void radix__flush_all_mm(struct mm_struct *mm)
{
	__flush_all_mm(mm, false);
}
EXPORT_SYMBOL(radix__flush_all_mm);

void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr)
{
	tlb->need_flush_all = 1;
}
EXPORT_SYMBOL(radix__flush_tlb_pwc);

void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
				 int psize)
{
	unsigned long pid;

	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		return;

	preempt_disable();
	smp_mb(); /* see radix__flush_tlb_mm */
	if (!mm_is_thread_local(mm)) {
		if (unlikely(mm_is_singlethreaded(mm))) {
			exit_flush_lazy_tlbs(mm);
			goto local;
		}
		if (cputlb_use_tlbie())
			_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
		else
			_tlbiel_va_multicast(mm, vmaddr, pid, psize, RIC_FLUSH_TLB);
	} else {
local:
		_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
	}
	preempt_enable();
}

void radix__flush_tlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
{
#ifdef CONFIG_HUGETLB_PAGE
	if (is_vm_hugetlb_page(vma))
		return radix__flush_hugetlb_page(vma, vmaddr);
#endif
	radix__flush_tlb_page_psize(vma->vm_mm, vmaddr, mmu_virtual_psize);
}
EXPORT_SYMBOL(radix__flush_tlb_page);

#else /* CONFIG_SMP */
#define radix__flush_all_mm radix__local_flush_all_mm
#endif /* CONFIG_SMP */

static void do_tlbiel_kernel(void *info)
{
	_tlbiel_pid(0, RIC_FLUSH_ALL);
}

static inline void _tlbiel_kernel_broadcast(void)
{
	on_each_cpu(do_tlbiel_kernel, NULL, 1);
	if (tlbie_capable) {
		/*
		 * Coherent accelerators don't refcount kernel memory mappings,
		 * so have to always issue a tlbie for them. This is quite a
		 * slow path anyway.
		 */
		_tlbie_pid(0, RIC_FLUSH_ALL);
	}
}

/*
 * If kernel TLBIs ever become local rather than global, then
 * drivers/misc/ocxl/link.c:ocxl_link_add_pe will need some work, as it
 * assumes kernel TLBIs are global.
 */
void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
{
	if (cputlb_use_tlbie())
		_tlbie_pid(0, RIC_FLUSH_ALL);
	else
		_tlbiel_kernel_broadcast();
}
EXPORT_SYMBOL(radix__flush_tlb_kernel_range);

#define TLB_FLUSH_ALL -1UL

/*
 * Number of pages above which we invalidate the entire PID rather than
 * flush individual pages, for local and global flushes respectively.
 *
 * tlbie goes out to the interconnect and individual ops are more costly.
 * It also does not iterate over sets like the local tlbiel variant when
 * invalidating a full PID, so it has a far lower threshold to change from
 * individual page flushes to full-pid flushes.
 */
static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33;
static unsigned long tlb_local_single_page_flush_ceiling __read_mostly = POWER9_TLB_SETS_RADIX * 2;

static inline void __radix__flush_tlb_range(struct mm_struct *mm,
					unsigned long start, unsigned long end,
					bool flush_all_sizes)

{
	unsigned long pid;
	unsigned int page_shift = mmu_psize_defs[mmu_virtual_psize].shift;
	unsigned long page_size = 1UL << page_shift;
	unsigned long nr_pages = (end - start) >> page_shift;
	bool local, full;

	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		return;

	preempt_disable();
	smp_mb(); /* see radix__flush_tlb_mm */
	if (!mm_is_thread_local(mm)) {
		if (unlikely(mm_is_singlethreaded(mm))) {
			if (end != TLB_FLUSH_ALL) {
				exit_flush_lazy_tlbs(mm);
				goto is_local;
			}
		}
		local = false;
		full = (end == TLB_FLUSH_ALL ||
				nr_pages > tlb_single_page_flush_ceiling);
	} else {
is_local:
		local = true;
		full = (end == TLB_FLUSH_ALL ||
				nr_pages > tlb_local_single_page_flush_ceiling);
	}

	if (full) {
		if (local) {
			_tlbiel_pid(pid, RIC_FLUSH_TLB);
		} else {
			if (cputlb_use_tlbie()) {
				if (mm_needs_flush_escalation(mm))
					_tlbie_pid(pid, RIC_FLUSH_ALL);
				else
					_tlbie_pid(pid, RIC_FLUSH_TLB);
			} else {
				_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB);
			}
		}
	} else {
		bool hflush = flush_all_sizes;
		bool gflush = flush_all_sizes;
		unsigned long hstart, hend;
		unsigned long gstart, gend;

		if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
			hflush = true;

		if (hflush) {
			hstart = (start + PMD_SIZE - 1) & PMD_MASK;
			hend = end & PMD_MASK;
			if (hstart == hend)
				hflush = false;
		}

		if (gflush) {
			gstart = (start + PUD_SIZE - 1) & PUD_MASK;
			gend = end & PUD_MASK;
			if (gstart == gend)
				gflush = false;
		}

		if (local) {
			asm volatile("ptesync": : :"memory");
			__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
			if (hflush)
				__tlbiel_va_range(hstart, hend, pid,
						PMD_SIZE, MMU_PAGE_2M);
			if (gflush)
				__tlbiel_va_range(gstart, gend, pid,
						PUD_SIZE, MMU_PAGE_1G);
			asm volatile("ptesync": : :"memory");
		} else if (cputlb_use_tlbie()) {
			asm volatile("ptesync": : :"memory");
			__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
			if (hflush)
				__tlbie_va_range(hstart, hend, pid,
						PMD_SIZE, MMU_PAGE_2M);
			if (gflush)
				__tlbie_va_range(gstart, gend, pid,
						PUD_SIZE, MMU_PAGE_1G);
			fixup_tlbie();
			asm volatile("eieio; tlbsync; ptesync": : :"memory");
		} else {
			_tlbiel_va_range_multicast(mm,
					start, end, pid, page_size, mmu_virtual_psize, false);
			if (hflush)
				_tlbiel_va_range_multicast(mm,
					hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, false);
			if (gflush)
				_tlbiel_va_range_multicast(mm,
					gstart, gend, pid, PUD_SIZE, MMU_PAGE_1G, false);
		}
	}
	preempt_enable();
}

void radix__flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
		     unsigned long end)

{
#ifdef CONFIG_HUGETLB_PAGE
	if (is_vm_hugetlb_page(vma))
		return radix__flush_hugetlb_tlb_range(vma, start, end);
#endif

	__radix__flush_tlb_range(vma->vm_mm, start, end, false);
}
EXPORT_SYMBOL(radix__flush_tlb_range);

static int radix_get_mmu_psize(int page_size)
{
	int psize;

	if (page_size == (1UL << mmu_psize_defs[mmu_virtual_psize].shift))
		psize = mmu_virtual_psize;
	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_2M].shift))
		psize = MMU_PAGE_2M;
	else if (page_size == (1UL << mmu_psize_defs[MMU_PAGE_1G].shift))
		psize = MMU_PAGE_1G;
	else
		return -1;
	return psize;
}

/*
 * Flush partition scoped LPID address translation for all CPUs.
 */
void radix__flush_tlb_lpid_page(unsigned int lpid,
					unsigned long addr,
					unsigned long page_size)
{
	int psize = radix_get_mmu_psize(page_size);

	_tlbie_lpid_va(addr, lpid, psize, RIC_FLUSH_TLB);
}
EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid_page);

/*
 * Flush partition scoped PWC from LPID for all CPUs.
 */
void radix__flush_pwc_lpid(unsigned int lpid)
{
	_tlbie_lpid(lpid, RIC_FLUSH_PWC);
}
EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid);

/*
 * Flush partition scoped translations from LPID (=LPIDR)
 */
void radix__flush_all_lpid(unsigned int lpid)
{
	_tlbie_lpid(lpid, RIC_FLUSH_ALL);
}
EXPORT_SYMBOL_GPL(radix__flush_all_lpid);

/*
 * Flush process scoped translations from LPID (=LPIDR)
 */
void radix__flush_all_lpid_guest(unsigned int lpid)
{
	_tlbie_lpid_guest(lpid, RIC_FLUSH_ALL);
}

static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
				  unsigned long end, int psize);

void radix__tlb_flush(struct mmu_gather *tlb)
{
	int psize = 0;
	struct mm_struct *mm = tlb->mm;
	int page_size = tlb->page_size;
	unsigned long start = tlb->start;
	unsigned long end = tlb->end;

	/*
	 * if page size is not something we understand, do a full mm flush
	 *
	 * A "fullmm" flush must always do a flush_all_mm (RIC=2) flush
	 * that flushes the process table entry cache upon process teardown.
	 * See the comment for radix in arch_exit_mmap().
	 */
	if (tlb->fullmm) {
		__flush_all_mm(mm, true);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLB_PAGE)
	} else if (mm_tlb_flush_nested(mm)) {
		/*
		 * If there is a concurrent invalidation that is clearing ptes,
		 * then it's possible this invalidation will miss one of those
		 * cleared ptes and miss flushing the TLB. If this invalidate
		 * returns before the other one flushes TLBs, that can result
		 * in it returning while there are still valid TLBs inside the
		 * range to be invalidated.
		 *
		 * See mm/memory.c:tlb_finish_mmu() for more details.
		 *
		 * The solution to this is ensure the entire range is always
		 * flushed here. The problem for powerpc is that the flushes
		 * are page size specific, so this "forced flush" would not
		 * do the right thing if there are a mix of page sizes in
		 * the range to be invalidated. So use __flush_tlb_range
		 * which invalidates all possible page sizes in the range.
		 *
		 * PWC flush probably is not be required because the core code
		 * shouldn't free page tables in this path, but accounting
		 * for the possibility makes us a bit more robust.
		 *
		 * need_flush_all is an uncommon case because page table
		 * teardown should be done with exclusive locks held (but
		 * after locks are dropped another invalidate could come
		 * in), it could be optimized further if necessary.
		 */
		if (!tlb->need_flush_all)
			__radix__flush_tlb_range(mm, start, end, true);
		else
			radix__flush_all_mm(mm);
#endif
	} else if ( (psize = radix_get_mmu_psize(page_size)) == -1) {
		if (!tlb->need_flush_all)
			radix__flush_tlb_mm(mm);
		else
			radix__flush_all_mm(mm);
	} else {
		if (!tlb->need_flush_all)
			radix__flush_tlb_range_psize(mm, start, end, psize);
		else
			radix__flush_tlb_pwc_range_psize(mm, start, end, psize);
	}
	tlb->need_flush_all = 0;
}

static __always_inline void __radix__flush_tlb_range_psize(struct mm_struct *mm,
				unsigned long start, unsigned long end,
				int psize, bool also_pwc)
{
	unsigned long pid;
	unsigned int page_shift = mmu_psize_defs[psize].shift;
	unsigned long page_size = 1UL << page_shift;
	unsigned long nr_pages = (end - start) >> page_shift;
	bool local, full;

	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		return;

	preempt_disable();
	smp_mb(); /* see radix__flush_tlb_mm */
	if (!mm_is_thread_local(mm)) {
		if (unlikely(mm_is_singlethreaded(mm))) {
			if (end != TLB_FLUSH_ALL) {
				exit_flush_lazy_tlbs(mm);
				goto is_local;
			}
		}
		local = false;
		full = (end == TLB_FLUSH_ALL ||
				nr_pages > tlb_single_page_flush_ceiling);
	} else {
is_local:
		local = true;
		full = (end == TLB_FLUSH_ALL ||
				nr_pages > tlb_local_single_page_flush_ceiling);
	}

	if (full) {
		if (local) {
			_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
		} else {
			if (cputlb_use_tlbie()) {
				if (mm_needs_flush_escalation(mm))
					also_pwc = true;

				_tlbie_pid(pid,
					also_pwc ?  RIC_FLUSH_ALL : RIC_FLUSH_TLB);
			} else {
				_tlbiel_pid_multicast(mm, pid,
					also_pwc ?  RIC_FLUSH_ALL : RIC_FLUSH_TLB);
			}

		}
	} else {
		if (local)
			_tlbiel_va_range(start, end, pid, page_size, psize, also_pwc);
		else if (cputlb_use_tlbie())
			_tlbie_va_range(start, end, pid, page_size, psize, also_pwc);
		else
			_tlbiel_va_range_multicast(mm,
					start, end, pid, page_size, psize, also_pwc);
	}
	preempt_enable();
}

void radix__flush_tlb_range_psize(struct mm_struct *mm, unsigned long start,
				  unsigned long end, int psize)
{
	return __radix__flush_tlb_range_psize(mm, start, end, psize, false);
}

static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
				  unsigned long end, int psize)
{
	__radix__flush_tlb_range_psize(mm, start, end, psize, true);
}

#ifdef CONFIG_TRANSPARENT_HUGEPAGE
void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
{
	unsigned long pid, end;

	pid = mm->context.id;
	if (unlikely(pid == MMU_NO_CONTEXT))
		return;

	/* 4k page size, just blow the world */
	if (PAGE_SIZE == 0x1000) {
		radix__flush_all_mm(mm);
		return;
	}

	end = addr + HPAGE_PMD_SIZE;

	/* Otherwise first do the PWC, then iterate the pages. */
	preempt_disable();
	smp_mb(); /* see radix__flush_tlb_mm */
	if (!mm_is_thread_local(mm)) {
		if (unlikely(mm_is_singlethreaded(mm))) {
			exit_flush_lazy_tlbs(mm);
			goto local;
		}
		if (cputlb_use_tlbie())
			_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
		else
			_tlbiel_va_range_multicast(mm,
					addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
	} else {
local:
		_tlbiel_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
	}

	preempt_enable();
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */

void radix__flush_pmd_tlb_range(struct vm_area_struct *vma,
				unsigned long start, unsigned long end)
{
	radix__flush_tlb_range_psize(vma->vm_mm, start, end, MMU_PAGE_2M);
}
EXPORT_SYMBOL(radix__flush_pmd_tlb_range);

void radix__flush_tlb_all(void)
{
	unsigned long rb,prs,r,rs;
	unsigned long ric = RIC_FLUSH_ALL;

	rb = 0x3 << PPC_BITLSHIFT(53); /* IS = 3 */
	prs = 0; /* partition scoped */
	r = 1;   /* radix format */
	rs = 1 & ((1UL << 32) - 1); /* any LPID value to flush guest mappings */

	asm volatile("ptesync": : :"memory");
	/*
	 * now flush guest entries by passing PRS = 1 and LPID != 0
	 */
	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(1), "i"(ric), "r"(rs) : "memory");
	/*
	 * now flush host entires by passing PRS = 0 and LPID == 0
	 */
	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(0) : "memory");
	asm volatile("eieio; tlbsync; ptesync": : :"memory");
}

#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
{
	unsigned long pid = mm->context.id;

	if (unlikely(pid == MMU_NO_CONTEXT))
		return;

	/*
	 * If this context hasn't run on that CPU before and KVM is
	 * around, there's a slim chance that the guest on another
	 * CPU just brought in obsolete translation into the TLB of
	 * this CPU due to a bad prefetch using the guest PID on
	 * the way into the hypervisor.
	 *
	 * We work around this here. If KVM is possible, we check if
	 * any sibling thread is in KVM. If it is, the window may exist
	 * and thus we flush that PID from the core.
	 *
	 * A potential future improvement would be to mark which PIDs
	 * have never been used on the system and avoid it if the PID
	 * is new and the process has no other cpumask bit set.
	 */
	if (cpu_has_feature(CPU_FTR_HVMODE) && radix_enabled()) {
		int cpu = smp_processor_id();
		int sib = cpu_first_thread_sibling(cpu);
		bool flush = false;

		for (; sib <= cpu_last_thread_sibling(cpu) && !flush; sib++) {
			if (sib == cpu)
				continue;
			if (!cpu_possible(sib))
				continue;
			if (paca_ptrs[sib]->kvm_hstate.kvm_vcpu)
				flush = true;
		}
		if (flush)
			_tlbiel_pid(pid, RIC_FLUSH_ALL);
	}
}
EXPORT_SYMBOL_GPL(radix_kvm_prefetch_workaround);
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */