summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/kvm/book3s_xics.c
blob: e48803e2918daeee099c7123fed00ec392b6d33f (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
/*
 * Copyright 2012 Michael Ellerman, IBM Corporation.
 * Copyright 2012 Benjamin Herrenschmidt, IBM Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 */

#include <linux/kernel.h>
#include <linux/kvm_host.h>
#include <linux/err.h>
#include <linux/gfp.h>
#include <linux/anon_inodes.h>
#include <linux/spinlock.h>

#include <linux/uaccess.h>
#include <asm/kvm_book3s.h>
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/xics.h>
#include <asm/debug.h>
#include <asm/time.h>

#include <linux/debugfs.h>
#include <linux/seq_file.h>

#include "book3s_xics.h"

#if 1
#define XICS_DBG(fmt...) do { } while (0)
#else
#define XICS_DBG(fmt...) trace_printk(fmt)
#endif

#define ENABLE_REALMODE	true
#define DEBUG_REALMODE	false

/*
 * LOCKING
 * =======
 *
 * Each ICS has a spin lock protecting the information about the IRQ
 * sources and avoiding simultaneous deliveries of the same interrupt.
 *
 * ICP operations are done via a single compare & swap transaction
 * (most ICP state fits in the union kvmppc_icp_state)
 */

/*
 * TODO
 * ====
 *
 * - To speed up resends, keep a bitmap of "resend" set bits in the
 *   ICS
 *
 * - Speed up server# -> ICP lookup (array ? hash table ?)
 *
 * - Make ICS lockless as well, or at least a per-interrupt lock or hashed
 *   locks array to improve scalability
 */

/* -- ICS routines -- */

static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
			    u32 new_irq, bool check_resend);

/*
 * Return value ideally indicates how the interrupt was handled, but no
 * callers look at it (given that we don't implement KVM_IRQ_LINE_STATUS),
 * so just return 0.
 */
static int ics_deliver_irq(struct kvmppc_xics *xics, u32 irq, u32 level)
{
	struct ics_irq_state *state;
	struct kvmppc_ics *ics;
	u16 src;
	u32 pq_old, pq_new;

	XICS_DBG("ics deliver %#x (level: %d)\n", irq, level);

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics) {
		XICS_DBG("ics_deliver_irq: IRQ 0x%06x not found !\n", irq);
		return -EINVAL;
	}
	state = &ics->irq_state[src];
	if (!state->exists)
		return -EINVAL;

	if (level == KVM_INTERRUPT_SET_LEVEL || level == KVM_INTERRUPT_SET)
		level = 1;
	else if (level == KVM_INTERRUPT_UNSET)
		level = 0;
	/*
	 * Take other values the same as 1, consistent with original code.
	 * maybe WARN here?
	 */

	if (!state->lsi && level == 0) /* noop for MSI */
		return 0;

	do {
		pq_old = state->pq_state;
		if (state->lsi) {
			if (level) {
				if (pq_old & PQ_PRESENTED)
					/* Setting already set LSI ... */
					return 0;

				pq_new = PQ_PRESENTED;
			} else
				pq_new = 0;
		} else
			pq_new = ((pq_old << 1) & 3) | PQ_PRESENTED;
	} while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old);

	/* Test P=1, Q=0, this is the only case where we present */
	if (pq_new == PQ_PRESENTED)
		icp_deliver_irq(xics, NULL, irq, false);

	/* Record which CPU this arrived on for passed-through interrupts */
	if (state->host_irq)
		state->intr_cpu = raw_smp_processor_id();

	return 0;
}

static void ics_check_resend(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
			     struct kvmppc_icp *icp)
{
	int i;

	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
		struct ics_irq_state *state = &ics->irq_state[i];
		if (state->resend) {
			XICS_DBG("resend %#x prio %#x\n", state->number,
				      state->priority);
			icp_deliver_irq(xics, icp, state->number, true);
		}
	}
}

static bool write_xive(struct kvmppc_xics *xics, struct kvmppc_ics *ics,
		       struct ics_irq_state *state,
		       u32 server, u32 priority, u32 saved_priority)
{
	bool deliver;
	unsigned long flags;

	local_irq_save(flags);
	arch_spin_lock(&ics->lock);

	state->server = server;
	state->priority = priority;
	state->saved_priority = saved_priority;
	deliver = false;
	if ((state->masked_pending || state->resend) && priority != MASKED) {
		state->masked_pending = 0;
		state->resend = 0;
		deliver = true;
	}

	arch_spin_unlock(&ics->lock);
	local_irq_restore(flags);

	return deliver;
}

int kvmppc_xics_set_xive(struct kvm *kvm, u32 irq, u32 server, u32 priority)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_icp *icp;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u16 src;

	if (!xics)
		return -ENODEV;

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics)
		return -EINVAL;
	state = &ics->irq_state[src];

	icp = kvmppc_xics_find_server(kvm, server);
	if (!icp)
		return -EINVAL;

	XICS_DBG("set_xive %#x server %#x prio %#x MP:%d RS:%d\n",
		 irq, server, priority,
		 state->masked_pending, state->resend);

	if (write_xive(xics, ics, state, server, priority, priority))
		icp_deliver_irq(xics, icp, irq, false);

	return 0;
}

int kvmppc_xics_get_xive(struct kvm *kvm, u32 irq, u32 *server, u32 *priority)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u16 src;
	unsigned long flags;

	if (!xics)
		return -ENODEV;

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics)
		return -EINVAL;
	state = &ics->irq_state[src];

	local_irq_save(flags);
	arch_spin_lock(&ics->lock);
	*server = state->server;
	*priority = state->priority;
	arch_spin_unlock(&ics->lock);
	local_irq_restore(flags);

	return 0;
}

int kvmppc_xics_int_on(struct kvm *kvm, u32 irq)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_icp *icp;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u16 src;

	if (!xics)
		return -ENODEV;

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics)
		return -EINVAL;
	state = &ics->irq_state[src];

	icp = kvmppc_xics_find_server(kvm, state->server);
	if (!icp)
		return -EINVAL;

	if (write_xive(xics, ics, state, state->server, state->saved_priority,
		       state->saved_priority))
		icp_deliver_irq(xics, icp, irq, false);

	return 0;
}

int kvmppc_xics_int_off(struct kvm *kvm, u32 irq)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u16 src;

	if (!xics)
		return -ENODEV;

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics)
		return -EINVAL;
	state = &ics->irq_state[src];

	write_xive(xics, ics, state, state->server, MASKED, state->priority);

	return 0;
}

/* -- ICP routines, including hcalls -- */

static inline bool icp_try_update(struct kvmppc_icp *icp,
				  union kvmppc_icp_state old,
				  union kvmppc_icp_state new,
				  bool change_self)
{
	bool success;

	/* Calculate new output value */
	new.out_ee = (new.xisr && (new.pending_pri < new.cppr));

	/* Attempt atomic update */
	success = cmpxchg64(&icp->state.raw, old.raw, new.raw) == old.raw;
	if (!success)
		goto bail;

	XICS_DBG("UPD [%04lx] - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n",
		 icp->server_num,
		 old.cppr, old.mfrr, old.pending_pri, old.xisr,
		 old.need_resend, old.out_ee);
	XICS_DBG("UPD        - C:%02x M:%02x PP: %02x PI:%06x R:%d O:%d\n",
		 new.cppr, new.mfrr, new.pending_pri, new.xisr,
		 new.need_resend, new.out_ee);
	/*
	 * Check for output state update
	 *
	 * Note that this is racy since another processor could be updating
	 * the state already. This is why we never clear the interrupt output
	 * here, we only ever set it. The clear only happens prior to doing
	 * an update and only by the processor itself. Currently we do it
	 * in Accept (H_XIRR) and Up_Cppr (H_XPPR).
	 *
	 * We also do not try to figure out whether the EE state has changed,
	 * we unconditionally set it if the new state calls for it. The reason
	 * for that is that we opportunistically remove the pending interrupt
	 * flag when raising CPPR, so we need to set it back here if an
	 * interrupt is still pending.
	 */
	if (new.out_ee) {
		kvmppc_book3s_queue_irqprio(icp->vcpu,
					    BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
		if (!change_self)
			kvmppc_fast_vcpu_kick(icp->vcpu);
	}
 bail:
	return success;
}

static void icp_check_resend(struct kvmppc_xics *xics,
			     struct kvmppc_icp *icp)
{
	u32 icsid;

	/* Order this load with the test for need_resend in the caller */
	smp_rmb();
	for_each_set_bit(icsid, icp->resend_map, xics->max_icsid + 1) {
		struct kvmppc_ics *ics = xics->ics[icsid];

		if (!test_and_clear_bit(icsid, icp->resend_map))
			continue;
		if (!ics)
			continue;
		ics_check_resend(xics, ics, icp);
	}
}

static bool icp_try_to_deliver(struct kvmppc_icp *icp, u32 irq, u8 priority,
			       u32 *reject)
{
	union kvmppc_icp_state old_state, new_state;
	bool success;

	XICS_DBG("try deliver %#x(P:%#x) to server %#lx\n", irq, priority,
		 icp->server_num);

	do {
		old_state = new_state = READ_ONCE(icp->state);

		*reject = 0;

		/* See if we can deliver */
		success = new_state.cppr > priority &&
			new_state.mfrr > priority &&
			new_state.pending_pri > priority;

		/*
		 * If we can, check for a rejection and perform the
		 * delivery
		 */
		if (success) {
			*reject = new_state.xisr;
			new_state.xisr = irq;
			new_state.pending_pri = priority;
		} else {
			/*
			 * If we failed to deliver we set need_resend
			 * so a subsequent CPPR state change causes us
			 * to try a new delivery.
			 */
			new_state.need_resend = true;
		}

	} while (!icp_try_update(icp, old_state, new_state, false));

	return success;
}

static void icp_deliver_irq(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
			    u32 new_irq, bool check_resend)
{
	struct ics_irq_state *state;
	struct kvmppc_ics *ics;
	u32 reject;
	u16 src;
	unsigned long flags;

	/*
	 * This is used both for initial delivery of an interrupt and
	 * for subsequent rejection.
	 *
	 * Rejection can be racy vs. resends. We have evaluated the
	 * rejection in an atomic ICP transaction which is now complete,
	 * so potentially the ICP can already accept the interrupt again.
	 *
	 * So we need to retry the delivery. Essentially the reject path
	 * boils down to a failed delivery. Always.
	 *
	 * Now the interrupt could also have moved to a different target,
	 * thus we may need to re-do the ICP lookup as well
	 */

 again:
	/* Get the ICS state and lock it */
	ics = kvmppc_xics_find_ics(xics, new_irq, &src);
	if (!ics) {
		XICS_DBG("icp_deliver_irq: IRQ 0x%06x not found !\n", new_irq);
		return;
	}
	state = &ics->irq_state[src];

	/* Get a lock on the ICS */
	local_irq_save(flags);
	arch_spin_lock(&ics->lock);

	/* Get our server */
	if (!icp || state->server != icp->server_num) {
		icp = kvmppc_xics_find_server(xics->kvm, state->server);
		if (!icp) {
			pr_warn("icp_deliver_irq: IRQ 0x%06x server 0x%x not found !\n",
				new_irq, state->server);
			goto out;
		}
	}

	if (check_resend)
		if (!state->resend)
			goto out;

	/* Clear the resend bit of that interrupt */
	state->resend = 0;

	/*
	 * If masked, bail out
	 *
	 * Note: PAPR doesn't mention anything about masked pending
	 * when doing a resend, only when doing a delivery.
	 *
	 * However that would have the effect of losing a masked
	 * interrupt that was rejected and isn't consistent with
	 * the whole masked_pending business which is about not
	 * losing interrupts that occur while masked.
	 *
	 * I don't differentiate normal deliveries and resends, this
	 * implementation will differ from PAPR and not lose such
	 * interrupts.
	 */
	if (state->priority == MASKED) {
		XICS_DBG("irq %#x masked pending\n", new_irq);
		state->masked_pending = 1;
		goto out;
	}

	/*
	 * Try the delivery, this will set the need_resend flag
	 * in the ICP as part of the atomic transaction if the
	 * delivery is not possible.
	 *
	 * Note that if successful, the new delivery might have itself
	 * rejected an interrupt that was "delivered" before we took the
	 * ics spin lock.
	 *
	 * In this case we do the whole sequence all over again for the
	 * new guy. We cannot assume that the rejected interrupt is less
	 * favored than the new one, and thus doesn't need to be delivered,
	 * because by the time we exit icp_try_to_deliver() the target
	 * processor may well have alrady consumed & completed it, and thus
	 * the rejected interrupt might actually be already acceptable.
	 */
	if (icp_try_to_deliver(icp, new_irq, state->priority, &reject)) {
		/*
		 * Delivery was successful, did we reject somebody else ?
		 */
		if (reject && reject != XICS_IPI) {
			arch_spin_unlock(&ics->lock);
			local_irq_restore(flags);
			new_irq = reject;
			check_resend = 0;
			goto again;
		}
	} else {
		/*
		 * We failed to deliver the interrupt we need to set the
		 * resend map bit and mark the ICS state as needing a resend
		 */
		state->resend = 1;

		/*
		 * Make sure when checking resend, we don't miss the resend
		 * if resend_map bit is seen and cleared.
		 */
		smp_wmb();
		set_bit(ics->icsid, icp->resend_map);

		/*
		 * If the need_resend flag got cleared in the ICP some time
		 * between icp_try_to_deliver() atomic update and now, then
		 * we know it might have missed the resend_map bit. So we
		 * retry
		 */
		smp_mb();
		if (!icp->state.need_resend) {
			state->resend = 0;
			arch_spin_unlock(&ics->lock);
			local_irq_restore(flags);
			check_resend = 0;
			goto again;
		}
	}
 out:
	arch_spin_unlock(&ics->lock);
	local_irq_restore(flags);
}

static void icp_down_cppr(struct kvmppc_xics *xics, struct kvmppc_icp *icp,
			  u8 new_cppr)
{
	union kvmppc_icp_state old_state, new_state;
	bool resend;

	/*
	 * This handles several related states in one operation:
	 *
	 * ICP State: Down_CPPR
	 *
	 * Load CPPR with new value and if the XISR is 0
	 * then check for resends:
	 *
	 * ICP State: Resend
	 *
	 * If MFRR is more favored than CPPR, check for IPIs
	 * and notify ICS of a potential resend. This is done
	 * asynchronously (when used in real mode, we will have
	 * to exit here).
	 *
	 * We do not handle the complete Check_IPI as documented
	 * here. In the PAPR, this state will be used for both
	 * Set_MFRR and Down_CPPR. However, we know that we aren't
	 * changing the MFRR state here so we don't need to handle
	 * the case of an MFRR causing a reject of a pending irq,
	 * this will have been handled when the MFRR was set in the
	 * first place.
	 *
	 * Thus we don't have to handle rejects, only resends.
	 *
	 * When implementing real mode for HV KVM, resend will lead to
	 * a H_TOO_HARD return and the whole transaction will be handled
	 * in virtual mode.
	 */
	do {
		old_state = new_state = READ_ONCE(icp->state);

		/* Down_CPPR */
		new_state.cppr = new_cppr;

		/*
		 * Cut down Resend / Check_IPI / IPI
		 *
		 * The logic is that we cannot have a pending interrupt
		 * trumped by an IPI at this point (see above), so we
		 * know that either the pending interrupt is already an
		 * IPI (in which case we don't care to override it) or
		 * it's either more favored than us or non existent
		 */
		if (new_state.mfrr < new_cppr &&
		    new_state.mfrr <= new_state.pending_pri) {
			WARN_ON(new_state.xisr != XICS_IPI &&
				new_state.xisr != 0);
			new_state.pending_pri = new_state.mfrr;
			new_state.xisr = XICS_IPI;
		}

		/* Latch/clear resend bit */
		resend = new_state.need_resend;
		new_state.need_resend = 0;

	} while (!icp_try_update(icp, old_state, new_state, true));

	/*
	 * Now handle resend checks. Those are asynchronous to the ICP
	 * state update in HW (ie bus transactions) so we can handle them
	 * separately here too
	 */
	if (resend)
		icp_check_resend(xics, icp);
}

static noinline unsigned long kvmppc_h_xirr(struct kvm_vcpu *vcpu)
{
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	u32 xirr;

	/* First, remove EE from the processor */
	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);

	/*
	 * ICP State: Accept_Interrupt
	 *
	 * Return the pending interrupt (if any) along with the
	 * current CPPR, then clear the XISR & set CPPR to the
	 * pending priority
	 */
	do {
		old_state = new_state = READ_ONCE(icp->state);

		xirr = old_state.xisr | (((u32)old_state.cppr) << 24);
		if (!old_state.xisr)
			break;
		new_state.cppr = new_state.pending_pri;
		new_state.pending_pri = 0xff;
		new_state.xisr = 0;

	} while (!icp_try_update(icp, old_state, new_state, true));

	XICS_DBG("h_xirr vcpu %d xirr %#x\n", vcpu->vcpu_id, xirr);

	return xirr;
}

static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
				 unsigned long mfrr)
{
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp;
	u32 reject;
	bool resend;
	bool local;

	XICS_DBG("h_ipi vcpu %d to server %lu mfrr %#lx\n",
		 vcpu->vcpu_id, server, mfrr);

	icp = vcpu->arch.icp;
	local = icp->server_num == server;
	if (!local) {
		icp = kvmppc_xics_find_server(vcpu->kvm, server);
		if (!icp)
			return H_PARAMETER;
	}

	/*
	 * ICP state: Set_MFRR
	 *
	 * If the CPPR is more favored than the new MFRR, then
	 * nothing needs to be rejected as there can be no XISR to
	 * reject.  If the MFRR is being made less favored then
	 * there might be a previously-rejected interrupt needing
	 * to be resent.
	 *
	 * ICP state: Check_IPI
	 *
	 * If the CPPR is less favored, then we might be replacing
	 * an interrupt, and thus need to possibly reject it.
	 *
	 * ICP State: IPI
	 *
	 * Besides rejecting any pending interrupts, we also
	 * update XISR and pending_pri to mark IPI as pending.
	 *
	 * PAPR does not describe this state, but if the MFRR is being
	 * made less favored than its earlier value, there might be
	 * a previously-rejected interrupt needing to be resent.
	 * Ideally, we would want to resend only if
	 *	prio(pending_interrupt) < mfrr &&
	 *	prio(pending_interrupt) < cppr
	 * where pending interrupt is the one that was rejected. But
	 * we don't have that state, so we simply trigger a resend
	 * whenever the MFRR is made less favored.
	 */
	do {
		old_state = new_state = READ_ONCE(icp->state);

		/* Set_MFRR */
		new_state.mfrr = mfrr;

		/* Check_IPI */
		reject = 0;
		resend = false;
		if (mfrr < new_state.cppr) {
			/* Reject a pending interrupt if not an IPI */
			if (mfrr <= new_state.pending_pri) {
				reject = new_state.xisr;
				new_state.pending_pri = mfrr;
				new_state.xisr = XICS_IPI;
			}
		}

		if (mfrr > old_state.mfrr) {
			resend = new_state.need_resend;
			new_state.need_resend = 0;
		}
	} while (!icp_try_update(icp, old_state, new_state, local));

	/* Handle reject */
	if (reject && reject != XICS_IPI)
		icp_deliver_irq(xics, icp, reject, false);

	/* Handle resend */
	if (resend)
		icp_check_resend(xics, icp);

	return H_SUCCESS;
}

static int kvmppc_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
{
	union kvmppc_icp_state state;
	struct kvmppc_icp *icp;

	icp = vcpu->arch.icp;
	if (icp->server_num != server) {
		icp = kvmppc_xics_find_server(vcpu->kvm, server);
		if (!icp)
			return H_PARAMETER;
	}
	state = READ_ONCE(icp->state);
	kvmppc_set_gpr(vcpu, 4, ((u32)state.cppr << 24) | state.xisr);
	kvmppc_set_gpr(vcpu, 5, state.mfrr);
	return H_SUCCESS;
}

static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
{
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	u32 reject;

	XICS_DBG("h_cppr vcpu %d cppr %#lx\n", vcpu->vcpu_id, cppr);

	/*
	 * ICP State: Set_CPPR
	 *
	 * We can safely compare the new value with the current
	 * value outside of the transaction as the CPPR is only
	 * ever changed by the processor on itself
	 */
	if (cppr > icp->state.cppr)
		icp_down_cppr(xics, icp, cppr);
	else if (cppr == icp->state.cppr)
		return;

	/*
	 * ICP State: Up_CPPR
	 *
	 * The processor is raising its priority, this can result
	 * in a rejection of a pending interrupt:
	 *
	 * ICP State: Reject_Current
	 *
	 * We can remove EE from the current processor, the update
	 * transaction will set it again if needed
	 */
	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);

	do {
		old_state = new_state = READ_ONCE(icp->state);

		reject = 0;
		new_state.cppr = cppr;

		if (cppr <= new_state.pending_pri) {
			reject = new_state.xisr;
			new_state.xisr = 0;
			new_state.pending_pri = 0xff;
		}

	} while (!icp_try_update(icp, old_state, new_state, true));

	/*
	 * Check for rejects. They are handled by doing a new delivery
	 * attempt (see comments in icp_deliver_irq).
	 */
	if (reject && reject != XICS_IPI)
		icp_deliver_irq(xics, icp, reject, false);
}

static int ics_eoi(struct kvm_vcpu *vcpu, u32 irq)
{
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	struct kvmppc_ics *ics;
	struct ics_irq_state *state;
	u16 src;
	u32 pq_old, pq_new;

	/*
	 * ICS EOI handling: For LSI, if P bit is still set, we need to
	 * resend it.
	 *
	 * For MSI, we move Q bit into P (and clear Q). If it is set,
	 * resend it.
	 */

	ics = kvmppc_xics_find_ics(xics, irq, &src);
	if (!ics) {
		XICS_DBG("ios_eoi: IRQ 0x%06x not found !\n", irq);
		return H_PARAMETER;
	}
	state = &ics->irq_state[src];

	if (state->lsi)
		pq_new = state->pq_state;
	else
		do {
			pq_old = state->pq_state;
			pq_new = pq_old >> 1;
		} while (cmpxchg(&state->pq_state, pq_old, pq_new) != pq_old);

	if (pq_new & PQ_PRESENTED)
		icp_deliver_irq(xics, icp, irq, false);

	kvm_notify_acked_irq(vcpu->kvm, 0, irq);

	return H_SUCCESS;
}

static noinline int kvmppc_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
{
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;
	u32 irq = xirr & 0x00ffffff;

	XICS_DBG("h_eoi vcpu %d eoi %#lx\n", vcpu->vcpu_id, xirr);

	/*
	 * ICP State: EOI
	 *
	 * Note: If EOI is incorrectly used by SW to lower the CPPR
	 * value (ie more favored), we do not check for rejection of
	 * a pending interrupt, this is a SW error and PAPR sepcifies
	 * that we don't have to deal with it.
	 *
	 * The sending of an EOI to the ICS is handled after the
	 * CPPR update
	 *
	 * ICP State: Down_CPPR which we handle
	 * in a separate function as it's shared with H_CPPR.
	 */
	icp_down_cppr(xics, icp, xirr >> 24);

	/* IPIs have no EOI */
	if (irq == XICS_IPI)
		return H_SUCCESS;

	return ics_eoi(vcpu, irq);
}

int kvmppc_xics_rm_complete(struct kvm_vcpu *vcpu, u32 hcall)
{
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	struct kvmppc_icp *icp = vcpu->arch.icp;

	XICS_DBG("XICS_RM: H_%x completing, act: %x state: %lx tgt: %p\n",
		 hcall, icp->rm_action, icp->rm_dbgstate.raw, icp->rm_dbgtgt);

	if (icp->rm_action & XICS_RM_KICK_VCPU) {
		icp->n_rm_kick_vcpu++;
		kvmppc_fast_vcpu_kick(icp->rm_kick_target);
	}
	if (icp->rm_action & XICS_RM_CHECK_RESEND) {
		icp->n_rm_check_resend++;
		icp_check_resend(xics, icp->rm_resend_icp);
	}
	if (icp->rm_action & XICS_RM_NOTIFY_EOI) {
		icp->n_rm_notify_eoi++;
		kvm_notify_acked_irq(vcpu->kvm, 0, icp->rm_eoied_irq);
	}

	icp->rm_action = 0;

	return H_SUCCESS;
}
EXPORT_SYMBOL_GPL(kvmppc_xics_rm_complete);

int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
{
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	unsigned long res;
	int rc = H_SUCCESS;

	/* Check if we have an ICP */
	if (!xics || !vcpu->arch.icp)
		return H_HARDWARE;

	/* These requests don't have real-mode implementations at present */
	switch (req) {
	case H_XIRR_X:
		res = kvmppc_h_xirr(vcpu);
		kvmppc_set_gpr(vcpu, 4, res);
		kvmppc_set_gpr(vcpu, 5, get_tb());
		return rc;
	case H_IPOLL:
		rc = kvmppc_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4));
		return rc;
	}

	/* Check for real mode returning too hard */
	if (xics->real_mode && is_kvmppc_hv_enabled(vcpu->kvm))
		return kvmppc_xics_rm_complete(vcpu, req);

	switch (req) {
	case H_XIRR:
		res = kvmppc_h_xirr(vcpu);
		kvmppc_set_gpr(vcpu, 4, res);
		break;
	case H_CPPR:
		kvmppc_h_cppr(vcpu, kvmppc_get_gpr(vcpu, 4));
		break;
	case H_EOI:
		rc = kvmppc_h_eoi(vcpu, kvmppc_get_gpr(vcpu, 4));
		break;
	case H_IPI:
		rc = kvmppc_h_ipi(vcpu, kvmppc_get_gpr(vcpu, 4),
				  kvmppc_get_gpr(vcpu, 5));
		break;
	}

	return rc;
}
EXPORT_SYMBOL_GPL(kvmppc_xics_hcall);


/* -- Initialisation code etc. -- */

static void xics_debugfs_irqmap(struct seq_file *m,
				struct kvmppc_passthru_irqmap *pimap)
{
	int i;

	if (!pimap)
		return;
	seq_printf(m, "========\nPIRQ mappings: %d maps\n===========\n",
				pimap->n_mapped);
	for (i = 0; i < pimap->n_mapped; i++)  {
		seq_printf(m, "r_hwirq=%x, v_hwirq=%x\n",
			pimap->mapped[i].r_hwirq, pimap->mapped[i].v_hwirq);
	}
}

static int xics_debug_show(struct seq_file *m, void *private)
{
	struct kvmppc_xics *xics = m->private;
	struct kvm *kvm = xics->kvm;
	struct kvm_vcpu *vcpu;
	int icsid, i;
	unsigned long flags;
	unsigned long t_rm_kick_vcpu, t_rm_check_resend;
	unsigned long t_rm_notify_eoi;
	unsigned long t_reject, t_check_resend;

	if (!kvm)
		return 0;

	t_rm_kick_vcpu = 0;
	t_rm_notify_eoi = 0;
	t_rm_check_resend = 0;
	t_check_resend = 0;
	t_reject = 0;

	xics_debugfs_irqmap(m, kvm->arch.pimap);

	seq_printf(m, "=========\nICP state\n=========\n");

	kvm_for_each_vcpu(i, vcpu, kvm) {
		struct kvmppc_icp *icp = vcpu->arch.icp;
		union kvmppc_icp_state state;

		if (!icp)
			continue;

		state.raw = READ_ONCE(icp->state.raw);
		seq_printf(m, "cpu server %#lx XIRR:%#x PPRI:%#x CPPR:%#x MFRR:%#x OUT:%d NR:%d\n",
			   icp->server_num, state.xisr,
			   state.pending_pri, state.cppr, state.mfrr,
			   state.out_ee, state.need_resend);
		t_rm_kick_vcpu += icp->n_rm_kick_vcpu;
		t_rm_notify_eoi += icp->n_rm_notify_eoi;
		t_rm_check_resend += icp->n_rm_check_resend;
		t_check_resend += icp->n_check_resend;
		t_reject += icp->n_reject;
	}

	seq_printf(m, "ICP Guest->Host totals: kick_vcpu=%lu check_resend=%lu notify_eoi=%lu\n",
			t_rm_kick_vcpu, t_rm_check_resend,
			t_rm_notify_eoi);
	seq_printf(m, "ICP Real Mode totals: check_resend=%lu resend=%lu\n",
			t_check_resend, t_reject);
	for (icsid = 0; icsid <= KVMPPC_XICS_MAX_ICS_ID; icsid++) {
		struct kvmppc_ics *ics = xics->ics[icsid];

		if (!ics)
			continue;

		seq_printf(m, "=========\nICS state for ICS 0x%x\n=========\n",
			   icsid);

		local_irq_save(flags);
		arch_spin_lock(&ics->lock);

		for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
			struct ics_irq_state *irq = &ics->irq_state[i];

			seq_printf(m, "irq 0x%06x: server %#x prio %#x save prio %#x pq_state %d resend %d masked pending %d\n",
				   irq->number, irq->server, irq->priority,
				   irq->saved_priority, irq->pq_state,
				   irq->resend, irq->masked_pending);

		}
		arch_spin_unlock(&ics->lock);
		local_irq_restore(flags);
	}
	return 0;
}

static int xics_debug_open(struct inode *inode, struct file *file)
{
	return single_open(file, xics_debug_show, inode->i_private);
}

static const struct file_operations xics_debug_fops = {
	.open = xics_debug_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

static void xics_debugfs_init(struct kvmppc_xics *xics)
{
	char *name;

	name = kasprintf(GFP_KERNEL, "kvm-xics-%p", xics);
	if (!name) {
		pr_err("%s: no memory for name\n", __func__);
		return;
	}

	xics->dentry = debugfs_create_file(name, S_IRUGO, powerpc_debugfs_root,
					   xics, &xics_debug_fops);

	pr_debug("%s: created %s\n", __func__, name);
	kfree(name);
}

static struct kvmppc_ics *kvmppc_xics_create_ics(struct kvm *kvm,
					struct kvmppc_xics *xics, int irq)
{
	struct kvmppc_ics *ics;
	int i, icsid;

	icsid = irq >> KVMPPC_XICS_ICS_SHIFT;

	mutex_lock(&kvm->lock);

	/* ICS already exists - somebody else got here first */
	if (xics->ics[icsid])
		goto out;

	/* Create the ICS */
	ics = kzalloc(sizeof(struct kvmppc_ics), GFP_KERNEL);
	if (!ics)
		goto out;

	ics->icsid = icsid;

	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
		ics->irq_state[i].number = (icsid << KVMPPC_XICS_ICS_SHIFT) | i;
		ics->irq_state[i].priority = MASKED;
		ics->irq_state[i].saved_priority = MASKED;
	}
	smp_wmb();
	xics->ics[icsid] = ics;

	if (icsid > xics->max_icsid)
		xics->max_icsid = icsid;

 out:
	mutex_unlock(&kvm->lock);
	return xics->ics[icsid];
}

int kvmppc_xics_create_icp(struct kvm_vcpu *vcpu, unsigned long server_num)
{
	struct kvmppc_icp *icp;

	if (!vcpu->kvm->arch.xics)
		return -ENODEV;

	if (kvmppc_xics_find_server(vcpu->kvm, server_num))
		return -EEXIST;

	icp = kzalloc(sizeof(struct kvmppc_icp), GFP_KERNEL);
	if (!icp)
		return -ENOMEM;

	icp->vcpu = vcpu;
	icp->server_num = server_num;
	icp->state.mfrr = MASKED;
	icp->state.pending_pri = MASKED;
	vcpu->arch.icp = icp;

	XICS_DBG("created server for vcpu %d\n", vcpu->vcpu_id);

	return 0;
}

u64 kvmppc_xics_get_icp(struct kvm_vcpu *vcpu)
{
	struct kvmppc_icp *icp = vcpu->arch.icp;
	union kvmppc_icp_state state;

	if (!icp)
		return 0;
	state = icp->state;
	return ((u64)state.cppr << KVM_REG_PPC_ICP_CPPR_SHIFT) |
		((u64)state.xisr << KVM_REG_PPC_ICP_XISR_SHIFT) |
		((u64)state.mfrr << KVM_REG_PPC_ICP_MFRR_SHIFT) |
		((u64)state.pending_pri << KVM_REG_PPC_ICP_PPRI_SHIFT);
}

int kvmppc_xics_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
{
	struct kvmppc_icp *icp = vcpu->arch.icp;
	struct kvmppc_xics *xics = vcpu->kvm->arch.xics;
	union kvmppc_icp_state old_state, new_state;
	struct kvmppc_ics *ics;
	u8 cppr, mfrr, pending_pri;
	u32 xisr;
	u16 src;
	bool resend;

	if (!icp || !xics)
		return -ENOENT;

	cppr = icpval >> KVM_REG_PPC_ICP_CPPR_SHIFT;
	xisr = (icpval >> KVM_REG_PPC_ICP_XISR_SHIFT) &
		KVM_REG_PPC_ICP_XISR_MASK;
	mfrr = icpval >> KVM_REG_PPC_ICP_MFRR_SHIFT;
	pending_pri = icpval >> KVM_REG_PPC_ICP_PPRI_SHIFT;

	/* Require the new state to be internally consistent */
	if (xisr == 0) {
		if (pending_pri != 0xff)
			return -EINVAL;
	} else if (xisr == XICS_IPI) {
		if (pending_pri != mfrr || pending_pri >= cppr)
			return -EINVAL;
	} else {
		if (pending_pri >= mfrr || pending_pri >= cppr)
			return -EINVAL;
		ics = kvmppc_xics_find_ics(xics, xisr, &src);
		if (!ics)
			return -EINVAL;
	}

	new_state.raw = 0;
	new_state.cppr = cppr;
	new_state.xisr = xisr;
	new_state.mfrr = mfrr;
	new_state.pending_pri = pending_pri;

	/*
	 * Deassert the CPU interrupt request.
	 * icp_try_update will reassert it if necessary.
	 */
	kvmppc_book3s_dequeue_irqprio(icp->vcpu,
				      BOOK3S_INTERRUPT_EXTERNAL_LEVEL);

	/*
	 * Note that if we displace an interrupt from old_state.xisr,
	 * we don't mark it as rejected.  We expect userspace to set
	 * the state of the interrupt sources to be consistent with
	 * the ICP states (either before or afterwards, which doesn't
	 * matter).  We do handle resends due to CPPR becoming less
	 * favoured because that is necessary to end up with a
	 * consistent state in the situation where userspace restores
	 * the ICS states before the ICP states.
	 */
	do {
		old_state = READ_ONCE(icp->state);

		if (new_state.mfrr <= old_state.mfrr) {
			resend = false;
			new_state.need_resend = old_state.need_resend;
		} else {
			resend = old_state.need_resend;
			new_state.need_resend = 0;
		}
	} while (!icp_try_update(icp, old_state, new_state, false));

	if (resend)
		icp_check_resend(xics, icp);

	return 0;
}

static int xics_get_source(struct kvmppc_xics *xics, long irq, u64 addr)
{
	int ret;
	struct kvmppc_ics *ics;
	struct ics_irq_state *irqp;
	u64 __user *ubufp = (u64 __user *) addr;
	u16 idx;
	u64 val, prio;
	unsigned long flags;

	ics = kvmppc_xics_find_ics(xics, irq, &idx);
	if (!ics)
		return -ENOENT;

	irqp = &ics->irq_state[idx];
	local_irq_save(flags);
	arch_spin_lock(&ics->lock);
	ret = -ENOENT;
	if (irqp->exists) {
		val = irqp->server;
		prio = irqp->priority;
		if (prio == MASKED) {
			val |= KVM_XICS_MASKED;
			prio = irqp->saved_priority;
		}
		val |= prio << KVM_XICS_PRIORITY_SHIFT;
		if (irqp->lsi) {
			val |= KVM_XICS_LEVEL_SENSITIVE;
			if (irqp->pq_state & PQ_PRESENTED)
				val |= KVM_XICS_PENDING;
		} else if (irqp->masked_pending || irqp->resend)
			val |= KVM_XICS_PENDING;

		if (irqp->pq_state & PQ_PRESENTED)
			val |= KVM_XICS_PRESENTED;

		if (irqp->pq_state & PQ_QUEUED)
			val |= KVM_XICS_QUEUED;

		ret = 0;
	}
	arch_spin_unlock(&ics->lock);
	local_irq_restore(flags);

	if (!ret && put_user(val, ubufp))
		ret = -EFAULT;

	return ret;
}

static int xics_set_source(struct kvmppc_xics *xics, long irq, u64 addr)
{
	struct kvmppc_ics *ics;
	struct ics_irq_state *irqp;
	u64 __user *ubufp = (u64 __user *) addr;
	u16 idx;
	u64 val;
	u8 prio;
	u32 server;
	unsigned long flags;

	if (irq < KVMPPC_XICS_FIRST_IRQ || irq >= KVMPPC_XICS_NR_IRQS)
		return -ENOENT;

	ics = kvmppc_xics_find_ics(xics, irq, &idx);
	if (!ics) {
		ics = kvmppc_xics_create_ics(xics->kvm, xics, irq);
		if (!ics)
			return -ENOMEM;
	}
	irqp = &ics->irq_state[idx];
	if (get_user(val, ubufp))
		return -EFAULT;

	server = val & KVM_XICS_DESTINATION_MASK;
	prio = val >> KVM_XICS_PRIORITY_SHIFT;
	if (prio != MASKED &&
	    kvmppc_xics_find_server(xics->kvm, server) == NULL)
		return -EINVAL;

	local_irq_save(flags);
	arch_spin_lock(&ics->lock);
	irqp->server = server;
	irqp->saved_priority = prio;
	if (val & KVM_XICS_MASKED)
		prio = MASKED;
	irqp->priority = prio;
	irqp->resend = 0;
	irqp->masked_pending = 0;
	irqp->lsi = 0;
	irqp->pq_state = 0;
	if (val & KVM_XICS_LEVEL_SENSITIVE)
		irqp->lsi = 1;
	/* If PENDING, set P in case P is not saved because of old code */
	if (val & KVM_XICS_PRESENTED || val & KVM_XICS_PENDING)
		irqp->pq_state |= PQ_PRESENTED;
	if (val & KVM_XICS_QUEUED)
		irqp->pq_state |= PQ_QUEUED;
	irqp->exists = 1;
	arch_spin_unlock(&ics->lock);
	local_irq_restore(flags);

	if (val & KVM_XICS_PENDING)
		icp_deliver_irq(xics, NULL, irqp->number, false);

	return 0;
}

int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level,
		bool line_status)
{
	struct kvmppc_xics *xics = kvm->arch.xics;

	if (!xics)
		return -ENODEV;
	return ics_deliver_irq(xics, irq, level);
}

int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *irq_entry,
			      struct kvm *kvm, int irq_source_id,
			      int level, bool line_status)
{
	return kvm_set_irq(kvm, irq_source_id, irq_entry->gsi,
			   level, line_status);
}

static int xics_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	struct kvmppc_xics *xics = dev->private;

	switch (attr->group) {
	case KVM_DEV_XICS_GRP_SOURCES:
		return xics_set_source(xics, attr->attr, attr->addr);
	}
	return -ENXIO;
}

static int xics_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	struct kvmppc_xics *xics = dev->private;

	switch (attr->group) {
	case KVM_DEV_XICS_GRP_SOURCES:
		return xics_get_source(xics, attr->attr, attr->addr);
	}
	return -ENXIO;
}

static int xics_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	switch (attr->group) {
	case KVM_DEV_XICS_GRP_SOURCES:
		if (attr->attr >= KVMPPC_XICS_FIRST_IRQ &&
		    attr->attr < KVMPPC_XICS_NR_IRQS)
			return 0;
		break;
	}
	return -ENXIO;
}

static void kvmppc_xics_free(struct kvm_device *dev)
{
	struct kvmppc_xics *xics = dev->private;
	int i;
	struct kvm *kvm = xics->kvm;

	debugfs_remove(xics->dentry);

	if (kvm)
		kvm->arch.xics = NULL;

	for (i = 0; i <= xics->max_icsid; i++)
		kfree(xics->ics[i]);
	kfree(xics);
	kfree(dev);
}

static int kvmppc_xics_create(struct kvm_device *dev, u32 type)
{
	struct kvmppc_xics *xics;
	struct kvm *kvm = dev->kvm;
	int ret = 0;

	xics = kzalloc(sizeof(*xics), GFP_KERNEL);
	if (!xics)
		return -ENOMEM;

	dev->private = xics;
	xics->dev = dev;
	xics->kvm = kvm;

	/* Already there ? */
	if (kvm->arch.xics)
		ret = -EEXIST;
	else
		kvm->arch.xics = xics;

	if (ret) {
		kfree(xics);
		return ret;
	}

#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
	if (cpu_has_feature(CPU_FTR_ARCH_206)) {
		/* Enable real mode support */
		xics->real_mode = ENABLE_REALMODE;
		xics->real_mode_dbg = DEBUG_REALMODE;
	}
#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */

	return 0;
}

static void kvmppc_xics_init(struct kvm_device *dev)
{
	struct kvmppc_xics *xics = (struct kvmppc_xics *)dev->private;

	xics_debugfs_init(xics);
}

struct kvm_device_ops kvm_xics_ops = {
	.name = "kvm-xics",
	.create = kvmppc_xics_create,
	.init = kvmppc_xics_init,
	.destroy = kvmppc_xics_free,
	.set_attr = xics_set_attr,
	.get_attr = xics_get_attr,
	.has_attr = xics_has_attr,
};

int kvmppc_xics_connect_vcpu(struct kvm_device *dev, struct kvm_vcpu *vcpu,
			     u32 xcpu)
{
	struct kvmppc_xics *xics = dev->private;
	int r = -EBUSY;

	if (dev->ops != &kvm_xics_ops)
		return -EPERM;
	if (xics->kvm != vcpu->kvm)
		return -EPERM;
	if (vcpu->arch.irq_type)
		return -EBUSY;

	r = kvmppc_xics_create_icp(vcpu, xcpu);
	if (!r)
		vcpu->arch.irq_type = KVMPPC_IRQ_XICS;

	return r;
}

void kvmppc_xics_free_icp(struct kvm_vcpu *vcpu)
{
	if (!vcpu->arch.icp)
		return;
	kfree(vcpu->arch.icp);
	vcpu->arch.icp = NULL;
	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
}

static int xics_set_irq(struct kvm_kernel_irq_routing_entry *e,
			struct kvm *kvm, int irq_source_id, int level,
			bool line_status)
{
	return kvm_set_irq(kvm, irq_source_id, e->gsi, level, line_status);
}

int kvm_irq_map_gsi(struct kvm *kvm,
		    struct kvm_kernel_irq_routing_entry *entries, int gsi)
{
	entries->gsi = gsi;
	entries->type = KVM_IRQ_ROUTING_IRQCHIP;
	entries->set = xics_set_irq;
	entries->irqchip.irqchip = 0;
	entries->irqchip.pin = gsi;
	return 1;
}

int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
	return pin;
}

void kvmppc_xics_set_mapped(struct kvm *kvm, unsigned long irq,
			    unsigned long host_irq)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_ics *ics;
	u16 idx;

	ics = kvmppc_xics_find_ics(xics, irq, &idx);
	if (!ics)
		return;

	ics->irq_state[idx].host_irq = host_irq;
	ics->irq_state[idx].intr_cpu = -1;
}
EXPORT_SYMBOL_GPL(kvmppc_xics_set_mapped);

void kvmppc_xics_clr_mapped(struct kvm *kvm, unsigned long irq,
			    unsigned long host_irq)
{
	struct kvmppc_xics *xics = kvm->arch.xics;
	struct kvmppc_ics *ics;
	u16 idx;

	ics = kvmppc_xics_find_ics(xics, irq, &idx);
	if (!ics)
		return;

	ics->irq_state[idx].host_irq = 0;
}
EXPORT_SYMBOL_GPL(kvmppc_xics_clr_mapped);