summaryrefslogtreecommitdiff
path: root/arch/mips/kvm/emulate.c
blob: edaec93a1a1feb6737e0ba8467ff76d2d66c6893 (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
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
/*
 * This file is subject to the terms and conditions of the GNU General Public
 * License.  See the file "COPYING" in the main directory of this archive
 * for more details.
 *
 * KVM/MIPS: Instruction/Exception emulation
 *
 * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
 * Authors: Sanjay Lal <sanjayl@kymasys.com>
 */

#include <linux/errno.h>
#include <linux/err.h>
#include <linux/ktime.h>
#include <linux/kvm_host.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/memblock.h>
#include <linux/random.h>
#include <asm/page.h>
#include <asm/cacheflush.h>
#include <asm/cacheops.h>
#include <asm/cpu-info.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
#include <asm/inst.h>

#undef CONFIG_MIPS_MT
#include <asm/r4kcache.h>
#define CONFIG_MIPS_MT

#include "interrupt.h"

#include "trace.h"

/*
 * Compute the return address and do emulate branch simulation, if required.
 * This function should be called only in branch delay slot active.
 */
static int kvm_compute_return_epc(struct kvm_vcpu *vcpu, unsigned long instpc,
				  unsigned long *out)
{
	unsigned int dspcontrol;
	union mips_instruction insn;
	struct kvm_vcpu_arch *arch = &vcpu->arch;
	long epc = instpc;
	long nextpc;
	int err;

	if (epc & 3) {
		kvm_err("%s: unaligned epc\n", __func__);
		return -EINVAL;
	}

	/* Read the instruction */
	err = kvm_get_badinstrp((u32 *)epc, vcpu, &insn.word);
	if (err)
		return err;

	switch (insn.i_format.opcode) {
		/* jr and jalr are in r_format format. */
	case spec_op:
		switch (insn.r_format.func) {
		case jalr_op:
			arch->gprs[insn.r_format.rd] = epc + 8;
			fallthrough;
		case jr_op:
			nextpc = arch->gprs[insn.r_format.rs];
			break;
		default:
			return -EINVAL;
		}
		break;

		/*
		 * This group contains:
		 * bltz_op, bgez_op, bltzl_op, bgezl_op,
		 * bltzal_op, bgezal_op, bltzall_op, bgezall_op.
		 */
	case bcond_op:
		switch (insn.i_format.rt) {
		case bltz_op:
		case bltzl_op:
			if ((long)arch->gprs[insn.i_format.rs] < 0)
				epc = epc + 4 + (insn.i_format.simmediate << 2);
			else
				epc += 8;
			nextpc = epc;
			break;

		case bgez_op:
		case bgezl_op:
			if ((long)arch->gprs[insn.i_format.rs] >= 0)
				epc = epc + 4 + (insn.i_format.simmediate << 2);
			else
				epc += 8;
			nextpc = epc;
			break;

		case bltzal_op:
		case bltzall_op:
			arch->gprs[31] = epc + 8;
			if ((long)arch->gprs[insn.i_format.rs] < 0)
				epc = epc + 4 + (insn.i_format.simmediate << 2);
			else
				epc += 8;
			nextpc = epc;
			break;

		case bgezal_op:
		case bgezall_op:
			arch->gprs[31] = epc + 8;
			if ((long)arch->gprs[insn.i_format.rs] >= 0)
				epc = epc + 4 + (insn.i_format.simmediate << 2);
			else
				epc += 8;
			nextpc = epc;
			break;
		case bposge32_op:
			if (!cpu_has_dsp) {
				kvm_err("%s: DSP branch but not DSP ASE\n",
					__func__);
				return -EINVAL;
			}

			dspcontrol = rddsp(0x01);

			if (dspcontrol >= 32)
				epc = epc + 4 + (insn.i_format.simmediate << 2);
			else
				epc += 8;
			nextpc = epc;
			break;
		default:
			return -EINVAL;
		}
		break;

		/* These are unconditional and in j_format. */
	case jal_op:
		arch->gprs[31] = instpc + 8;
		fallthrough;
	case j_op:
		epc += 4;
		epc >>= 28;
		epc <<= 28;
		epc |= (insn.j_format.target << 2);
		nextpc = epc;
		break;

		/* These are conditional and in i_format. */
	case beq_op:
	case beql_op:
		if (arch->gprs[insn.i_format.rs] ==
		    arch->gprs[insn.i_format.rt])
			epc = epc + 4 + (insn.i_format.simmediate << 2);
		else
			epc += 8;
		nextpc = epc;
		break;

	case bne_op:
	case bnel_op:
		if (arch->gprs[insn.i_format.rs] !=
		    arch->gprs[insn.i_format.rt])
			epc = epc + 4 + (insn.i_format.simmediate << 2);
		else
			epc += 8;
		nextpc = epc;
		break;

	case blez_op:	/* POP06 */
#ifndef CONFIG_CPU_MIPSR6
	case blezl_op:	/* removed in R6 */
#endif
		if (insn.i_format.rt != 0)
			goto compact_branch;
		if ((long)arch->gprs[insn.i_format.rs] <= 0)
			epc = epc + 4 + (insn.i_format.simmediate << 2);
		else
			epc += 8;
		nextpc = epc;
		break;

	case bgtz_op:	/* POP07 */
#ifndef CONFIG_CPU_MIPSR6
	case bgtzl_op:	/* removed in R6 */
#endif
		if (insn.i_format.rt != 0)
			goto compact_branch;
		if ((long)arch->gprs[insn.i_format.rs] > 0)
			epc = epc + 4 + (insn.i_format.simmediate << 2);
		else
			epc += 8;
		nextpc = epc;
		break;

		/* And now the FPA/cp1 branch instructions. */
	case cop1_op:
		kvm_err("%s: unsupported cop1_op\n", __func__);
		return -EINVAL;

#ifdef CONFIG_CPU_MIPSR6
	/* R6 added the following compact branches with forbidden slots */
	case blezl_op:	/* POP26 */
	case bgtzl_op:	/* POP27 */
		/* only rt == 0 isn't compact branch */
		if (insn.i_format.rt != 0)
			goto compact_branch;
		return -EINVAL;
	case pop10_op:
	case pop30_op:
		/* only rs == rt == 0 is reserved, rest are compact branches */
		if (insn.i_format.rs != 0 || insn.i_format.rt != 0)
			goto compact_branch;
		return -EINVAL;
	case pop66_op:
	case pop76_op:
		/* only rs == 0 isn't compact branch */
		if (insn.i_format.rs != 0)
			goto compact_branch;
		return -EINVAL;
compact_branch:
		/*
		 * If we've hit an exception on the forbidden slot, then
		 * the branch must not have been taken.
		 */
		epc += 8;
		nextpc = epc;
		break;
#else
compact_branch:
		/* Fall through - Compact branches not supported before R6 */
#endif
	default:
		return -EINVAL;
	}

	*out = nextpc;
	return 0;
}

enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause)
{
	int err;

	if (cause & CAUSEF_BD) {
		err = kvm_compute_return_epc(vcpu, vcpu->arch.pc,
					     &vcpu->arch.pc);
		if (err)
			return EMULATE_FAIL;
	} else {
		vcpu->arch.pc += 4;
	}

	kvm_debug("update_pc(): New PC: %#lx\n", vcpu->arch.pc);

	return EMULATE_DONE;
}

/**
 * kvm_get_badinstr() - Get bad instruction encoding.
 * @opc:	Guest pointer to faulting instruction.
 * @vcpu:	KVM VCPU information.
 *
 * Gets the instruction encoding of the faulting instruction, using the saved
 * BadInstr register value if it exists, otherwise falling back to reading guest
 * memory at @opc.
 *
 * Returns:	The instruction encoding of the faulting instruction.
 */
int kvm_get_badinstr(u32 *opc, struct kvm_vcpu *vcpu, u32 *out)
{
	if (cpu_has_badinstr) {
		*out = vcpu->arch.host_cp0_badinstr;
		return 0;
	} else {
		WARN_ONCE(1, "CPU doesn't have BadInstr register\n");
		return -EINVAL;
	}
}

/**
 * kvm_get_badinstrp() - Get bad prior instruction encoding.
 * @opc:	Guest pointer to prior faulting instruction.
 * @vcpu:	KVM VCPU information.
 *
 * Gets the instruction encoding of the prior faulting instruction (the branch
 * containing the delay slot which faulted), using the saved BadInstrP register
 * value if it exists, otherwise falling back to reading guest memory at @opc.
 *
 * Returns:	The instruction encoding of the prior faulting instruction.
 */
int kvm_get_badinstrp(u32 *opc, struct kvm_vcpu *vcpu, u32 *out)
{
	if (cpu_has_badinstrp) {
		*out = vcpu->arch.host_cp0_badinstrp;
		return 0;
	} else {
		WARN_ONCE(1, "CPU doesn't have BadInstrp register\n");
		return -EINVAL;
	}
}

/**
 * kvm_mips_count_disabled() - Find whether the CP0_Count timer is disabled.
 * @vcpu:	Virtual CPU.
 *
 * Returns:	1 if the CP0_Count timer is disabled by either the guest
 *		CP0_Cause.DC bit or the count_ctl.DC bit.
 *		0 otherwise (in which case CP0_Count timer is running).
 */
int kvm_mips_count_disabled(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;

	return	(vcpu->arch.count_ctl & KVM_REG_MIPS_COUNT_CTL_DC) ||
		(kvm_read_c0_guest_cause(cop0) & CAUSEF_DC);
}

/**
 * kvm_mips_ktime_to_count() - Scale ktime_t to a 32-bit count.
 *
 * Caches the dynamic nanosecond bias in vcpu->arch.count_dyn_bias.
 *
 * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
 */
static u32 kvm_mips_ktime_to_count(struct kvm_vcpu *vcpu, ktime_t now)
{
	s64 now_ns, periods;
	u64 delta;

	now_ns = ktime_to_ns(now);
	delta = now_ns + vcpu->arch.count_dyn_bias;

	if (delta >= vcpu->arch.count_period) {
		/* If delta is out of safe range the bias needs adjusting */
		periods = div64_s64(now_ns, vcpu->arch.count_period);
		vcpu->arch.count_dyn_bias = -periods * vcpu->arch.count_period;
		/* Recalculate delta with new bias */
		delta = now_ns + vcpu->arch.count_dyn_bias;
	}

	/*
	 * We've ensured that:
	 *   delta < count_period
	 *
	 * Therefore the intermediate delta*count_hz will never overflow since
	 * at the boundary condition:
	 *   delta = count_period
	 *   delta = NSEC_PER_SEC * 2^32 / count_hz
	 *   delta * count_hz = NSEC_PER_SEC * 2^32
	 */
	return div_u64(delta * vcpu->arch.count_hz, NSEC_PER_SEC);
}

/**
 * kvm_mips_count_time() - Get effective current time.
 * @vcpu:	Virtual CPU.
 *
 * Get effective monotonic ktime. This is usually a straightforward ktime_get(),
 * except when the master disable bit is set in count_ctl, in which case it is
 * count_resume, i.e. the time that the count was disabled.
 *
 * Returns:	Effective monotonic ktime for CP0_Count.
 */
static inline ktime_t kvm_mips_count_time(struct kvm_vcpu *vcpu)
{
	if (unlikely(vcpu->arch.count_ctl & KVM_REG_MIPS_COUNT_CTL_DC))
		return vcpu->arch.count_resume;

	return ktime_get();
}

/**
 * kvm_mips_read_count_running() - Read the current count value as if running.
 * @vcpu:	Virtual CPU.
 * @now:	Kernel time to read CP0_Count at.
 *
 * Returns the current guest CP0_Count register at time @now and handles if the
 * timer interrupt is pending and hasn't been handled yet.
 *
 * Returns:	The current value of the guest CP0_Count register.
 */
static u32 kvm_mips_read_count_running(struct kvm_vcpu *vcpu, ktime_t now)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	ktime_t expires, threshold;
	u32 count, compare;
	int running;

	/* Calculate the biased and scaled guest CP0_Count */
	count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);
	compare = kvm_read_c0_guest_compare(cop0);

	/*
	 * Find whether CP0_Count has reached the closest timer interrupt. If
	 * not, we shouldn't inject it.
	 */
	if ((s32)(count - compare) < 0)
		return count;

	/*
	 * The CP0_Count we're going to return has already reached the closest
	 * timer interrupt. Quickly check if it really is a new interrupt by
	 * looking at whether the interval until the hrtimer expiry time is
	 * less than 1/4 of the timer period.
	 */
	expires = hrtimer_get_expires(&vcpu->arch.comparecount_timer);
	threshold = ktime_add_ns(now, vcpu->arch.count_period / 4);
	if (ktime_before(expires, threshold)) {
		/*
		 * Cancel it while we handle it so there's no chance of
		 * interference with the timeout handler.
		 */
		running = hrtimer_cancel(&vcpu->arch.comparecount_timer);

		/* Nothing should be waiting on the timeout */
		kvm_mips_callbacks->queue_timer_int(vcpu);

		/*
		 * Restart the timer if it was running based on the expiry time
		 * we read, so that we don't push it back 2 periods.
		 */
		if (running) {
			expires = ktime_add_ns(expires,
					       vcpu->arch.count_period);
			hrtimer_start(&vcpu->arch.comparecount_timer, expires,
				      HRTIMER_MODE_ABS);
		}
	}

	return count;
}

/**
 * kvm_mips_read_count() - Read the current count value.
 * @vcpu:	Virtual CPU.
 *
 * Read the current guest CP0_Count value, taking into account whether the timer
 * is stopped.
 *
 * Returns:	The current guest CP0_Count value.
 */
u32 kvm_mips_read_count(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;

	/* If count disabled just read static copy of count */
	if (kvm_mips_count_disabled(vcpu))
		return kvm_read_c0_guest_count(cop0);

	return kvm_mips_read_count_running(vcpu, ktime_get());
}

/**
 * kvm_mips_freeze_hrtimer() - Safely stop the hrtimer.
 * @vcpu:	Virtual CPU.
 * @count:	Output pointer for CP0_Count value at point of freeze.
 *
 * Freeze the hrtimer safely and return both the ktime and the CP0_Count value
 * at the point it was frozen. It is guaranteed that any pending interrupts at
 * the point it was frozen are handled, and none after that point.
 *
 * This is useful where the time/CP0_Count is needed in the calculation of the
 * new parameters.
 *
 * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
 *
 * Returns:	The ktime at the point of freeze.
 */
ktime_t kvm_mips_freeze_hrtimer(struct kvm_vcpu *vcpu, u32 *count)
{
	ktime_t now;

	/* stop hrtimer before finding time */
	hrtimer_cancel(&vcpu->arch.comparecount_timer);
	now = ktime_get();

	/* find count at this point and handle pending hrtimer */
	*count = kvm_mips_read_count_running(vcpu, now);

	return now;
}

/**
 * kvm_mips_resume_hrtimer() - Resume hrtimer, updating expiry.
 * @vcpu:	Virtual CPU.
 * @now:	ktime at point of resume.
 * @count:	CP0_Count at point of resume.
 *
 * Resumes the timer and updates the timer expiry based on @now and @count.
 * This can be used in conjunction with kvm_mips_freeze_timer() when timer
 * parameters need to be changed.
 *
 * It is guaranteed that a timer interrupt immediately after resume will be
 * handled, but not if CP_Compare is exactly at @count. That case is already
 * handled by kvm_mips_freeze_timer().
 *
 * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is running).
 */
static void kvm_mips_resume_hrtimer(struct kvm_vcpu *vcpu,
				    ktime_t now, u32 count)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	u32 compare;
	u64 delta;
	ktime_t expire;

	/* Calculate timeout (wrap 0 to 2^32) */
	compare = kvm_read_c0_guest_compare(cop0);
	delta = (u64)(u32)(compare - count - 1) + 1;
	delta = div_u64(delta * NSEC_PER_SEC, vcpu->arch.count_hz);
	expire = ktime_add_ns(now, delta);

	/* Update hrtimer to use new timeout */
	hrtimer_cancel(&vcpu->arch.comparecount_timer);
	hrtimer_start(&vcpu->arch.comparecount_timer, expire, HRTIMER_MODE_ABS);
}

/**
 * kvm_mips_restore_hrtimer() - Restore hrtimer after a gap, updating expiry.
 * @vcpu:	Virtual CPU.
 * @before:	Time before Count was saved, lower bound of drift calculation.
 * @count:	CP0_Count at point of restore.
 * @min_drift:	Minimum amount of drift permitted before correction.
 *		Must be <= 0.
 *
 * Restores the timer from a particular @count, accounting for drift. This can
 * be used in conjunction with kvm_mips_freeze_timer() when a hardware timer is
 * to be used for a period of time, but the exact ktime corresponding to the
 * final Count that must be restored is not known.
 *
 * It is gauranteed that a timer interrupt immediately after restore will be
 * handled, but not if CP0_Compare is exactly at @count. That case should
 * already be handled when the hardware timer state is saved.
 *
 * Assumes !kvm_mips_count_disabled(@vcpu) (guest CP0_Count timer is not
 * stopped).
 *
 * Returns:	Amount of correction to count_bias due to drift.
 */
int kvm_mips_restore_hrtimer(struct kvm_vcpu *vcpu, ktime_t before,
			     u32 count, int min_drift)
{
	ktime_t now, count_time;
	u32 now_count, before_count;
	u64 delta;
	int drift, ret = 0;

	/* Calculate expected count at before */
	before_count = vcpu->arch.count_bias +
			kvm_mips_ktime_to_count(vcpu, before);

	/*
	 * Detect significantly negative drift, where count is lower than
	 * expected. Some negative drift is expected when hardware counter is
	 * set after kvm_mips_freeze_timer(), and it is harmless to allow the
	 * time to jump forwards a little, within reason. If the drift is too
	 * significant, adjust the bias to avoid a big Guest.CP0_Count jump.
	 */
	drift = count - before_count;
	if (drift < min_drift) {
		count_time = before;
		vcpu->arch.count_bias += drift;
		ret = drift;
		goto resume;
	}

	/* Calculate expected count right now */
	now = ktime_get();
	now_count = vcpu->arch.count_bias + kvm_mips_ktime_to_count(vcpu, now);

	/*
	 * Detect positive drift, where count is higher than expected, and
	 * adjust the bias to avoid guest time going backwards.
	 */
	drift = count - now_count;
	if (drift > 0) {
		count_time = now;
		vcpu->arch.count_bias += drift;
		ret = drift;
		goto resume;
	}

	/* Subtract nanosecond delta to find ktime when count was read */
	delta = (u64)(u32)(now_count - count);
	delta = div_u64(delta * NSEC_PER_SEC, vcpu->arch.count_hz);
	count_time = ktime_sub_ns(now, delta);

resume:
	/* Resume using the calculated ktime */
	kvm_mips_resume_hrtimer(vcpu, count_time, count);
	return ret;
}

/**
 * kvm_mips_write_count() - Modify the count and update timer.
 * @vcpu:	Virtual CPU.
 * @count:	Guest CP0_Count value to set.
 *
 * Sets the CP0_Count value and updates the timer accordingly.
 */
void kvm_mips_write_count(struct kvm_vcpu *vcpu, u32 count)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	ktime_t now;

	/* Calculate bias */
	now = kvm_mips_count_time(vcpu);
	vcpu->arch.count_bias = count - kvm_mips_ktime_to_count(vcpu, now);

	if (kvm_mips_count_disabled(vcpu))
		/* The timer's disabled, adjust the static count */
		kvm_write_c0_guest_count(cop0, count);
	else
		/* Update timeout */
		kvm_mips_resume_hrtimer(vcpu, now, count);
}

/**
 * kvm_mips_init_count() - Initialise timer.
 * @vcpu:	Virtual CPU.
 * @count_hz:	Frequency of timer.
 *
 * Initialise the timer to the specified frequency, zero it, and set it going if
 * it's enabled.
 */
void kvm_mips_init_count(struct kvm_vcpu *vcpu, unsigned long count_hz)
{
	vcpu->arch.count_hz = count_hz;
	vcpu->arch.count_period = div_u64((u64)NSEC_PER_SEC << 32, count_hz);
	vcpu->arch.count_dyn_bias = 0;

	/* Starting at 0 */
	kvm_mips_write_count(vcpu, 0);
}

/**
 * kvm_mips_set_count_hz() - Update the frequency of the timer.
 * @vcpu:	Virtual CPU.
 * @count_hz:	Frequency of CP0_Count timer in Hz.
 *
 * Change the frequency of the CP0_Count timer. This is done atomically so that
 * CP0_Count is continuous and no timer interrupt is lost.
 *
 * Returns:	-EINVAL if @count_hz is out of range.
 *		0 on success.
 */
int kvm_mips_set_count_hz(struct kvm_vcpu *vcpu, s64 count_hz)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	int dc;
	ktime_t now;
	u32 count;

	/* ensure the frequency is in a sensible range... */
	if (count_hz <= 0 || count_hz > NSEC_PER_SEC)
		return -EINVAL;
	/* ... and has actually changed */
	if (vcpu->arch.count_hz == count_hz)
		return 0;

	/* Safely freeze timer so we can keep it continuous */
	dc = kvm_mips_count_disabled(vcpu);
	if (dc) {
		now = kvm_mips_count_time(vcpu);
		count = kvm_read_c0_guest_count(cop0);
	} else {
		now = kvm_mips_freeze_hrtimer(vcpu, &count);
	}

	/* Update the frequency */
	vcpu->arch.count_hz = count_hz;
	vcpu->arch.count_period = div_u64((u64)NSEC_PER_SEC << 32, count_hz);
	vcpu->arch.count_dyn_bias = 0;

	/* Calculate adjusted bias so dynamic count is unchanged */
	vcpu->arch.count_bias = count - kvm_mips_ktime_to_count(vcpu, now);

	/* Update and resume hrtimer */
	if (!dc)
		kvm_mips_resume_hrtimer(vcpu, now, count);
	return 0;
}

/**
 * kvm_mips_write_compare() - Modify compare and update timer.
 * @vcpu:	Virtual CPU.
 * @compare:	New CP0_Compare value.
 * @ack:	Whether to acknowledge timer interrupt.
 *
 * Update CP0_Compare to a new value and update the timeout.
 * If @ack, atomically acknowledge any pending timer interrupt, otherwise ensure
 * any pending timer interrupt is preserved.
 */
void kvm_mips_write_compare(struct kvm_vcpu *vcpu, u32 compare, bool ack)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	int dc;
	u32 old_compare = kvm_read_c0_guest_compare(cop0);
	s32 delta = compare - old_compare;
	u32 cause;
	ktime_t now = ktime_set(0, 0); /* silence bogus GCC warning */
	u32 count;

	/* if unchanged, must just be an ack */
	if (old_compare == compare) {
		if (!ack)
			return;
		kvm_mips_callbacks->dequeue_timer_int(vcpu);
		kvm_write_c0_guest_compare(cop0, compare);
		return;
	}

	/*
	 * If guest CP0_Compare moves forward, CP0_GTOffset should be adjusted
	 * too to prevent guest CP0_Count hitting guest CP0_Compare.
	 *
	 * The new GTOffset corresponds to the new value of CP0_Compare, and is
	 * set prior to it being written into the guest context. We disable
	 * preemption until the new value is written to prevent restore of a
	 * GTOffset corresponding to the old CP0_Compare value.
	 */
	if (delta > 0) {
		preempt_disable();
		write_c0_gtoffset(compare - read_c0_count());
		back_to_back_c0_hazard();
	}

	/* freeze_hrtimer() takes care of timer interrupts <= count */
	dc = kvm_mips_count_disabled(vcpu);
	if (!dc)
		now = kvm_mips_freeze_hrtimer(vcpu, &count);

	if (ack)
		kvm_mips_callbacks->dequeue_timer_int(vcpu);
	else
		/*
		 * With VZ, writing CP0_Compare acks (clears) CP0_Cause.TI, so
		 * preserve guest CP0_Cause.TI if we don't want to ack it.
		 */
		cause = kvm_read_c0_guest_cause(cop0);

	kvm_write_c0_guest_compare(cop0, compare);

	if (delta > 0)
		preempt_enable();

	back_to_back_c0_hazard();

	if (!ack && cause & CAUSEF_TI)
		kvm_write_c0_guest_cause(cop0, cause);

	/* resume_hrtimer() takes care of timer interrupts > count */
	if (!dc)
		kvm_mips_resume_hrtimer(vcpu, now, count);

	/*
	 * If guest CP0_Compare is moving backward, we delay CP0_GTOffset change
	 * until after the new CP0_Compare is written, otherwise new guest
	 * CP0_Count could hit new guest CP0_Compare.
	 */
	if (delta <= 0)
		write_c0_gtoffset(compare - read_c0_count());
}

/**
 * kvm_mips_count_disable() - Disable count.
 * @vcpu:	Virtual CPU.
 *
 * Disable the CP0_Count timer. A timer interrupt on or before the final stop
 * time will be handled but not after.
 *
 * Assumes CP0_Count was previously enabled but now Guest.CP0_Cause.DC or
 * count_ctl.DC has been set (count disabled).
 *
 * Returns:	The time that the timer was stopped.
 */
static ktime_t kvm_mips_count_disable(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	u32 count;
	ktime_t now;

	/* Stop hrtimer */
	hrtimer_cancel(&vcpu->arch.comparecount_timer);

	/* Set the static count from the dynamic count, handling pending TI */
	now = ktime_get();
	count = kvm_mips_read_count_running(vcpu, now);
	kvm_write_c0_guest_count(cop0, count);

	return now;
}

/**
 * kvm_mips_count_disable_cause() - Disable count using CP0_Cause.DC.
 * @vcpu:	Virtual CPU.
 *
 * Disable the CP0_Count timer and set CP0_Cause.DC. A timer interrupt on or
 * before the final stop time will be handled if the timer isn't disabled by
 * count_ctl.DC, but not after.
 *
 * Assumes CP0_Cause.DC is clear (count enabled).
 */
void kvm_mips_count_disable_cause(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;

	kvm_set_c0_guest_cause(cop0, CAUSEF_DC);
	if (!(vcpu->arch.count_ctl & KVM_REG_MIPS_COUNT_CTL_DC))
		kvm_mips_count_disable(vcpu);
}

/**
 * kvm_mips_count_enable_cause() - Enable count using CP0_Cause.DC.
 * @vcpu:	Virtual CPU.
 *
 * Enable the CP0_Count timer and clear CP0_Cause.DC. A timer interrupt after
 * the start time will be handled if the timer isn't disabled by count_ctl.DC,
 * potentially before even returning, so the caller should be careful with
 * ordering of CP0_Cause modifications so as not to lose it.
 *
 * Assumes CP0_Cause.DC is set (count disabled).
 */
void kvm_mips_count_enable_cause(struct kvm_vcpu *vcpu)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	u32 count;

	kvm_clear_c0_guest_cause(cop0, CAUSEF_DC);

	/*
	 * Set the dynamic count to match the static count.
	 * This starts the hrtimer if count_ctl.DC allows it.
	 * Otherwise it conveniently updates the biases.
	 */
	count = kvm_read_c0_guest_count(cop0);
	kvm_mips_write_count(vcpu, count);
}

/**
 * kvm_mips_set_count_ctl() - Update the count control KVM register.
 * @vcpu:	Virtual CPU.
 * @count_ctl:	Count control register new value.
 *
 * Set the count control KVM register. The timer is updated accordingly.
 *
 * Returns:	-EINVAL if reserved bits are set.
 *		0 on success.
 */
int kvm_mips_set_count_ctl(struct kvm_vcpu *vcpu, s64 count_ctl)
{
	struct mips_coproc *cop0 = vcpu->arch.cop0;
	s64 changed = count_ctl ^ vcpu->arch.count_ctl;
	s64 delta;
	ktime_t expire, now;
	u32 count, compare;

	/* Only allow defined bits to be changed */
	if (changed & ~(s64)(KVM_REG_MIPS_COUNT_CTL_DC))
		return -EINVAL;

	/* Apply new value */
	vcpu->arch.count_ctl = count_ctl;

	/* Master CP0_Count disable */
	if (changed & KVM_REG_MIPS_COUNT_CTL_DC) {
		/* Is CP0_Cause.DC already disabling CP0_Count? */
		if (kvm_read_c0_guest_cause(cop0) & CAUSEF_DC) {
			if (count_ctl & KVM_REG_MIPS_COUNT_CTL_DC)
				/* Just record the current time */
				vcpu->arch.count_resume = ktime_get();
		} else if (count_ctl & KVM_REG_MIPS_COUNT_CTL_DC) {
			/* disable timer and record current time */
			vcpu->arch.count_resume = kvm_mips_count_disable(vcpu);
		} else {
			/*
			 * Calculate timeout relative to static count at resume
			 * time (wrap 0 to 2^32).
			 */
			count = kvm_read_c0_guest_count(cop0);
			compare = kvm_read_c0_guest_compare(cop0);
			delta = (u64)(u32)(compare - count - 1) + 1;
			delta = div_u64(delta * NSEC_PER_SEC,
					vcpu->arch.count_hz);
			expire = ktime_add_ns(vcpu->arch.count_resume, delta);

			/* Handle pending interrupt */
			now = ktime_get();
			if (ktime_compare(now, expire) >= 0)
				/* Nothing should be waiting on the timeout */
				kvm_mips_callbacks->queue_timer_int(vcpu);

			/* Resume hrtimer without changing bias */
			count = kvm_mips_read_count_running(vcpu, now);
			kvm_mips_resume_hrtimer(vcpu, now, count);
		}
	}

	return 0;
}

/**
 * kvm_mips_set_count_resume() - Update the count resume KVM register.
 * @vcpu:		Virtual CPU.
 * @count_resume:	Count resume register new value.
 *
 * Set the count resume KVM register.
 *
 * Returns:	-EINVAL if out of valid range (0..now).
 *		0 on success.
 */
int kvm_mips_set_count_resume(struct kvm_vcpu *vcpu, s64 count_resume)
{
	/*
	 * It doesn't make sense for the resume time to be in the future, as it
	 * would be possible for the next interrupt to be more than a full
	 * period in the future.
	 */
	if (count_resume < 0 || count_resume > ktime_to_ns(ktime_get()))
		return -EINVAL;

	vcpu->arch.count_resume = ns_to_ktime(count_resume);
	return 0;
}

/**
 * kvm_mips_count_timeout() - Push timer forward on timeout.
 * @vcpu:	Virtual CPU.
 *
 * Handle an hrtimer event by push the hrtimer forward a period.
 *
 * Returns:	The hrtimer_restart value to return to the hrtimer subsystem.
 */
enum hrtimer_restart kvm_mips_count_timeout(struct kvm_vcpu *vcpu)
{
	/* Add the Count period to the current expiry time */
	hrtimer_add_expires_ns(&vcpu->arch.comparecount_timer,
			       vcpu->arch.count_period);
	return HRTIMER_RESTART;
}

enum emulation_result kvm_mips_emul_wait(struct kvm_vcpu *vcpu)
{
	kvm_debug("[%#lx] !!!WAIT!!! (%#lx)\n", vcpu->arch.pc,
		  vcpu->arch.pending_exceptions);

	++vcpu->stat.wait_exits;
	trace_kvm_exit(vcpu, KVM_TRACE_EXIT_WAIT);
	if (!vcpu->arch.pending_exceptions) {
		kvm_vz_lose_htimer(vcpu);
		vcpu->arch.wait = 1;
		kvm_vcpu_halt(vcpu);

		/*
		 * We are runnable, then definitely go off to user space to
		 * check if any I/O interrupts are pending.
		 */
		if (kvm_arch_vcpu_runnable(vcpu))
			vcpu->run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
	}

	return EMULATE_DONE;
}

enum emulation_result kvm_mips_emulate_store(union mips_instruction inst,
					     u32 cause,
					     struct kvm_vcpu *vcpu)
{
	int r;
	enum emulation_result er;
	u32 rt;
	struct kvm_run *run = vcpu->run;
	void *data = run->mmio.data;
	unsigned int imme;
	unsigned long curr_pc;

	/*
	 * Update PC and hold onto current PC in case there is
	 * an error and we want to rollback the PC
	 */
	curr_pc = vcpu->arch.pc;
	er = update_pc(vcpu, cause);
	if (er == EMULATE_FAIL)
		return er;

	rt = inst.i_format.rt;

	run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
						vcpu->arch.host_cp0_badvaddr);
	if (run->mmio.phys_addr == KVM_INVALID_ADDR)
		goto out_fail;

	switch (inst.i_format.opcode) {
#if defined(CONFIG_64BIT)
	case sd_op:
		run->mmio.len = 8;
		*(u64 *)data = vcpu->arch.gprs[rt];

		kvm_debug("[%#lx] OP_SD: eaddr: %#lx, gpr: %#lx, data: %#llx\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u64 *)data);
		break;
#endif

	case sw_op:
		run->mmio.len = 4;
		*(u32 *)data = vcpu->arch.gprs[rt];

		kvm_debug("[%#lx] OP_SW: eaddr: %#lx, gpr: %#lx, data: %#x\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u32 *)data);
		break;

	case sh_op:
		run->mmio.len = 2;
		*(u16 *)data = vcpu->arch.gprs[rt];

		kvm_debug("[%#lx] OP_SH: eaddr: %#lx, gpr: %#lx, data: %#x\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u16 *)data);
		break;

	case sb_op:
		run->mmio.len = 1;
		*(u8 *)data = vcpu->arch.gprs[rt];

		kvm_debug("[%#lx] OP_SB: eaddr: %#lx, gpr: %#lx, data: %#x\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u8 *)data);
		break;

	case swl_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x3);
		run->mmio.len = 4;
		imme = vcpu->arch.host_cp0_badvaddr & 0x3;
		switch (imme) {
		case 0:
			*(u32 *)data = ((*(u32 *)data) & 0xffffff00) |
					(vcpu->arch.gprs[rt] >> 24);
			break;
		case 1:
			*(u32 *)data = ((*(u32 *)data) & 0xffff0000) |
					(vcpu->arch.gprs[rt] >> 16);
			break;
		case 2:
			*(u32 *)data = ((*(u32 *)data) & 0xff000000) |
					(vcpu->arch.gprs[rt] >> 8);
			break;
		case 3:
			*(u32 *)data = vcpu->arch.gprs[rt];
			break;
		default:
			break;
		}

		kvm_debug("[%#lx] OP_SWL: eaddr: %#lx, gpr: %#lx, data: %#x\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u32 *)data);
		break;

	case swr_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x3);
		run->mmio.len = 4;
		imme = vcpu->arch.host_cp0_badvaddr & 0x3;
		switch (imme) {
		case 0:
			*(u32 *)data = vcpu->arch.gprs[rt];
			break;
		case 1:
			*(u32 *)data = ((*(u32 *)data) & 0xff) |
					(vcpu->arch.gprs[rt] << 8);
			break;
		case 2:
			*(u32 *)data = ((*(u32 *)data) & 0xffff) |
					(vcpu->arch.gprs[rt] << 16);
			break;
		case 3:
			*(u32 *)data = ((*(u32 *)data) & 0xffffff) |
					(vcpu->arch.gprs[rt] << 24);
			break;
		default:
			break;
		}

		kvm_debug("[%#lx] OP_SWR: eaddr: %#lx, gpr: %#lx, data: %#x\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u32 *)data);
		break;

#if defined(CONFIG_64BIT)
	case sdl_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x7);

		run->mmio.len = 8;
		imme = vcpu->arch.host_cp0_badvaddr & 0x7;
		switch (imme) {
		case 0:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffffffffff00) |
					((vcpu->arch.gprs[rt] >> 56) & 0xff);
			break;
		case 1:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffffffff0000) |
					((vcpu->arch.gprs[rt] >> 48) & 0xffff);
			break;
		case 2:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffffff000000) |
					((vcpu->arch.gprs[rt] >> 40) & 0xffffff);
			break;
		case 3:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffff00000000) |
					((vcpu->arch.gprs[rt] >> 32) & 0xffffffff);
			break;
		case 4:
			*(u64 *)data = ((*(u64 *)data) & 0xffffff0000000000) |
					((vcpu->arch.gprs[rt] >> 24) & 0xffffffffff);
			break;
		case 5:
			*(u64 *)data = ((*(u64 *)data) & 0xffff000000000000) |
					((vcpu->arch.gprs[rt] >> 16) & 0xffffffffffff);
			break;
		case 6:
			*(u64 *)data = ((*(u64 *)data) & 0xff00000000000000) |
					((vcpu->arch.gprs[rt] >> 8) & 0xffffffffffffff);
			break;
		case 7:
			*(u64 *)data = vcpu->arch.gprs[rt];
			break;
		default:
			break;
		}

		kvm_debug("[%#lx] OP_SDL: eaddr: %#lx, gpr: %#lx, data: %llx\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u64 *)data);
		break;

	case sdr_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x7);

		run->mmio.len = 8;
		imme = vcpu->arch.host_cp0_badvaddr & 0x7;
		switch (imme) {
		case 0:
			*(u64 *)data = vcpu->arch.gprs[rt];
			break;
		case 1:
			*(u64 *)data = ((*(u64 *)data) & 0xff) |
					(vcpu->arch.gprs[rt] << 8);
			break;
		case 2:
			*(u64 *)data = ((*(u64 *)data) & 0xffff) |
					(vcpu->arch.gprs[rt] << 16);
			break;
		case 3:
			*(u64 *)data = ((*(u64 *)data) & 0xffffff) |
					(vcpu->arch.gprs[rt] << 24);
			break;
		case 4:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffff) |
					(vcpu->arch.gprs[rt] << 32);
			break;
		case 5:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffffff) |
					(vcpu->arch.gprs[rt] << 40);
			break;
		case 6:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffffffff) |
					(vcpu->arch.gprs[rt] << 48);
			break;
		case 7:
			*(u64 *)data = ((*(u64 *)data) & 0xffffffffffffff) |
					(vcpu->arch.gprs[rt] << 56);
			break;
		default:
			break;
		}

		kvm_debug("[%#lx] OP_SDR: eaddr: %#lx, gpr: %#lx, data: %llx\n",
			  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
			  vcpu->arch.gprs[rt], *(u64 *)data);
		break;
#endif

#ifdef CONFIG_CPU_LOONGSON64
	case sdc2_op:
		rt = inst.loongson3_lsdc2_format.rt;
		switch (inst.loongson3_lsdc2_format.opcode1) {
		/*
		 * Loongson-3 overridden sdc2 instructions.
		 * opcode1              instruction
		 *   0x0          gssbx: store 1 bytes from GPR
		 *   0x1          gsshx: store 2 bytes from GPR
		 *   0x2          gsswx: store 4 bytes from GPR
		 *   0x3          gssdx: store 8 bytes from GPR
		 */
		case 0x0:
			run->mmio.len = 1;
			*(u8 *)data = vcpu->arch.gprs[rt];

			kvm_debug("[%#lx] OP_GSSBX: eaddr: %#lx, gpr: %#lx, data: %#x\n",
				  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
				  vcpu->arch.gprs[rt], *(u8 *)data);
			break;
		case 0x1:
			run->mmio.len = 2;
			*(u16 *)data = vcpu->arch.gprs[rt];

			kvm_debug("[%#lx] OP_GSSSHX: eaddr: %#lx, gpr: %#lx, data: %#x\n",
				  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
				  vcpu->arch.gprs[rt], *(u16 *)data);
			break;
		case 0x2:
			run->mmio.len = 4;
			*(u32 *)data = vcpu->arch.gprs[rt];

			kvm_debug("[%#lx] OP_GSSWX: eaddr: %#lx, gpr: %#lx, data: %#x\n",
				  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
				  vcpu->arch.gprs[rt], *(u32 *)data);
			break;
		case 0x3:
			run->mmio.len = 8;
			*(u64 *)data = vcpu->arch.gprs[rt];

			kvm_debug("[%#lx] OP_GSSDX: eaddr: %#lx, gpr: %#lx, data: %#llx\n",
				  vcpu->arch.pc, vcpu->arch.host_cp0_badvaddr,
				  vcpu->arch.gprs[rt], *(u64 *)data);
			break;
		default:
			kvm_err("Godson Extended GS-Store not yet supported (inst=0x%08x)\n",
				inst.word);
			break;
		}
		break;
#endif
	default:
		kvm_err("Store not yet supported (inst=0x%08x)\n",
			inst.word);
		goto out_fail;
	}

	vcpu->mmio_needed = 1;
	run->mmio.is_write = 1;
	vcpu->mmio_is_write = 1;

	r = kvm_io_bus_write(vcpu, KVM_MMIO_BUS,
			run->mmio.phys_addr, run->mmio.len, data);

	if (!r) {
		vcpu->mmio_needed = 0;
		return EMULATE_DONE;
	}

	return EMULATE_DO_MMIO;

out_fail:
	/* Rollback PC if emulation was unsuccessful */
	vcpu->arch.pc = curr_pc;
	return EMULATE_FAIL;
}

enum emulation_result kvm_mips_emulate_load(union mips_instruction inst,
					    u32 cause, struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	int r;
	enum emulation_result er;
	unsigned long curr_pc;
	u32 op, rt;
	unsigned int imme;

	rt = inst.i_format.rt;
	op = inst.i_format.opcode;

	/*
	 * Find the resume PC now while we have safe and easy access to the
	 * prior branch instruction, and save it for
	 * kvm_mips_complete_mmio_load() to restore later.
	 */
	curr_pc = vcpu->arch.pc;
	er = update_pc(vcpu, cause);
	if (er == EMULATE_FAIL)
		return er;
	vcpu->arch.io_pc = vcpu->arch.pc;
	vcpu->arch.pc = curr_pc;

	vcpu->arch.io_gpr = rt;

	run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
						vcpu->arch.host_cp0_badvaddr);
	if (run->mmio.phys_addr == KVM_INVALID_ADDR)
		return EMULATE_FAIL;

	vcpu->mmio_needed = 2;	/* signed */
	switch (op) {
#if defined(CONFIG_64BIT)
	case ld_op:
		run->mmio.len = 8;
		break;

	case lwu_op:
		vcpu->mmio_needed = 1;	/* unsigned */
		fallthrough;
#endif
	case lw_op:
		run->mmio.len = 4;
		break;

	case lhu_op:
		vcpu->mmio_needed = 1;	/* unsigned */
		fallthrough;
	case lh_op:
		run->mmio.len = 2;
		break;

	case lbu_op:
		vcpu->mmio_needed = 1;	/* unsigned */
		fallthrough;
	case lb_op:
		run->mmio.len = 1;
		break;

	case lwl_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x3);

		run->mmio.len = 4;
		imme = vcpu->arch.host_cp0_badvaddr & 0x3;
		switch (imme) {
		case 0:
			vcpu->mmio_needed = 3;	/* 1 byte */
			break;
		case 1:
			vcpu->mmio_needed = 4;	/* 2 bytes */
			break;
		case 2:
			vcpu->mmio_needed = 5;	/* 3 bytes */
			break;
		case 3:
			vcpu->mmio_needed = 6;	/* 4 bytes */
			break;
		default:
			break;
		}
		break;

	case lwr_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x3);

		run->mmio.len = 4;
		imme = vcpu->arch.host_cp0_badvaddr & 0x3;
		switch (imme) {
		case 0:
			vcpu->mmio_needed = 7;	/* 4 bytes */
			break;
		case 1:
			vcpu->mmio_needed = 8;	/* 3 bytes */
			break;
		case 2:
			vcpu->mmio_needed = 9;	/* 2 bytes */
			break;
		case 3:
			vcpu->mmio_needed = 10;	/* 1 byte */
			break;
		default:
			break;
		}
		break;

#if defined(CONFIG_64BIT)
	case ldl_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x7);

		run->mmio.len = 8;
		imme = vcpu->arch.host_cp0_badvaddr & 0x7;
		switch (imme) {
		case 0:
			vcpu->mmio_needed = 11;	/* 1 byte */
			break;
		case 1:
			vcpu->mmio_needed = 12;	/* 2 bytes */
			break;
		case 2:
			vcpu->mmio_needed = 13;	/* 3 bytes */
			break;
		case 3:
			vcpu->mmio_needed = 14;	/* 4 bytes */
			break;
		case 4:
			vcpu->mmio_needed = 15;	/* 5 bytes */
			break;
		case 5:
			vcpu->mmio_needed = 16;	/* 6 bytes */
			break;
		case 6:
			vcpu->mmio_needed = 17;	/* 7 bytes */
			break;
		case 7:
			vcpu->mmio_needed = 18;	/* 8 bytes */
			break;
		default:
			break;
		}
		break;

	case ldr_op:
		run->mmio.phys_addr = kvm_mips_callbacks->gva_to_gpa(
					vcpu->arch.host_cp0_badvaddr) & (~0x7);

		run->mmio.len = 8;
		imme = vcpu->arch.host_cp0_badvaddr & 0x7;
		switch (imme) {
		case 0:
			vcpu->mmio_needed = 19;	/* 8 bytes */
			break;
		case 1:
			vcpu->mmio_needed = 20;	/* 7 bytes */
			break;
		case 2:
			vcpu->mmio_needed = 21;	/* 6 bytes */
			break;
		case 3:
			vcpu->mmio_needed = 22;	/* 5 bytes */
			break;
		case 4:
			vcpu->mmio_needed = 23;	/* 4 bytes */
			break;
		case 5:
			vcpu->mmio_needed = 24;	/* 3 bytes */
			break;
		case 6:
			vcpu->mmio_needed = 25;	/* 2 bytes */
			break;
		case 7:
			vcpu->mmio_needed = 26;	/* 1 byte */
			break;
		default:
			break;
		}
		break;
#endif

#ifdef CONFIG_CPU_LOONGSON64
	case ldc2_op:
		rt = inst.loongson3_lsdc2_format.rt;
		switch (inst.loongson3_lsdc2_format.opcode1) {
		/*
		 * Loongson-3 overridden ldc2 instructions.
		 * opcode1              instruction
		 *   0x0          gslbx: store 1 bytes from GPR
		 *   0x1          gslhx: store 2 bytes from GPR
		 *   0x2          gslwx: store 4 bytes from GPR
		 *   0x3          gsldx: store 8 bytes from GPR
		 */
		case 0x0:
			run->mmio.len = 1;
			vcpu->mmio_needed = 27;	/* signed */
			break;
		case 0x1:
			run->mmio.len = 2;
			vcpu->mmio_needed = 28;	/* signed */
			break;
		case 0x2:
			run->mmio.len = 4;
			vcpu->mmio_needed = 29;	/* signed */
			break;
		case 0x3:
			run->mmio.len = 8;
			vcpu->mmio_needed = 30;	/* signed */
			break;
		default:
			kvm_err("Godson Extended GS-Load for float not yet supported (inst=0x%08x)\n",
				inst.word);
			break;
		}
		break;
#endif

	default:
		kvm_err("Load not yet supported (inst=0x%08x)\n",
			inst.word);
		vcpu->mmio_needed = 0;
		return EMULATE_FAIL;
	}

	run->mmio.is_write = 0;
	vcpu->mmio_is_write = 0;

	r = kvm_io_bus_read(vcpu, KVM_MMIO_BUS,
			run->mmio.phys_addr, run->mmio.len, run->mmio.data);

	if (!r) {
		kvm_mips_complete_mmio_load(vcpu);
		vcpu->mmio_needed = 0;
		return EMULATE_DONE;
	}

	return EMULATE_DO_MMIO;
}

enum emulation_result kvm_mips_complete_mmio_load(struct kvm_vcpu *vcpu)
{
	struct kvm_run *run = vcpu->run;
	unsigned long *gpr = &vcpu->arch.gprs[vcpu->arch.io_gpr];
	enum emulation_result er = EMULATE_DONE;

	if (run->mmio.len > sizeof(*gpr)) {
		kvm_err("Bad MMIO length: %d", run->mmio.len);
		er = EMULATE_FAIL;
		goto done;
	}

	/* Restore saved resume PC */
	vcpu->arch.pc = vcpu->arch.io_pc;

	switch (run->mmio.len) {
	case 8:
		switch (vcpu->mmio_needed) {
		case 11:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffffffffff) |
				(((*(s64 *)run->mmio.data) & 0xff) << 56);
			break;
		case 12:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffffffff) |
				(((*(s64 *)run->mmio.data) & 0xffff) << 48);
			break;
		case 13:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffffff) |
				(((*(s64 *)run->mmio.data) & 0xffffff) << 40);
			break;
		case 14:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffff) |
				(((*(s64 *)run->mmio.data) & 0xffffffff) << 32);
			break;
		case 15:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffff) |
				(((*(s64 *)run->mmio.data) & 0xffffffffff) << 24);
			break;
		case 16:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffff) |
				(((*(s64 *)run->mmio.data) & 0xffffffffffff) << 16);
			break;
		case 17:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xff) |
				(((*(s64 *)run->mmio.data) & 0xffffffffffffff) << 8);
			break;
		case 18:
		case 19:
			*gpr = *(s64 *)run->mmio.data;
			break;
		case 20:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xff00000000000000) |
				((((*(s64 *)run->mmio.data)) >> 8) & 0xffffffffffffff);
			break;
		case 21:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffff000000000000) |
				((((*(s64 *)run->mmio.data)) >> 16) & 0xffffffffffff);
			break;
		case 22:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffff0000000000) |
				((((*(s64 *)run->mmio.data)) >> 24) & 0xffffffffff);
			break;
		case 23:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffff00000000) |
				((((*(s64 *)run->mmio.data)) >> 32) & 0xffffffff);
			break;
		case 24:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffffff000000) |
				((((*(s64 *)run->mmio.data)) >> 40) & 0xffffff);
			break;
		case 25:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffffffff0000) |
				((((*(s64 *)run->mmio.data)) >> 48) & 0xffff);
			break;
		case 26:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffffffffffff00) |
				((((*(s64 *)run->mmio.data)) >> 56) & 0xff);
			break;
		default:
			*gpr = *(s64 *)run->mmio.data;
		}
		break;

	case 4:
		switch (vcpu->mmio_needed) {
		case 1:
			*gpr = *(u32 *)run->mmio.data;
			break;
		case 2:
			*gpr = *(s32 *)run->mmio.data;
			break;
		case 3:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffff) |
				(((*(s32 *)run->mmio.data) & 0xff) << 24);
			break;
		case 4:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffff) |
				(((*(s32 *)run->mmio.data) & 0xffff) << 16);
			break;
		case 5:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xff) |
				(((*(s32 *)run->mmio.data) & 0xffffff) << 8);
			break;
		case 6:
		case 7:
			*gpr = *(s32 *)run->mmio.data;
			break;
		case 8:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xff000000) |
				((((*(s32 *)run->mmio.data)) >> 8) & 0xffffff);
			break;
		case 9:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffff0000) |
				((((*(s32 *)run->mmio.data)) >> 16) & 0xffff);
			break;
		case 10:
			*gpr = (vcpu->arch.gprs[vcpu->arch.io_gpr] & 0xffffff00) |
				((((*(s32 *)run->mmio.data)) >> 24) & 0xff);
			break;
		default:
			*gpr = *(s32 *)run->mmio.data;
		}
		break;

	case 2:
		if (vcpu->mmio_needed == 1)
			*gpr = *(u16 *)run->mmio.data;
		else
			*gpr = *(s16 *)run->mmio.data;

		break;
	case 1:
		if (vcpu->mmio_needed == 1)
			*gpr = *(u8 *)run->mmio.data;
		else
			*gpr = *(s8 *)run->mmio.data;
		break;
	}

done:
	return er;
}