aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm/lapic.c
blob: df8bcb0f66d8a2b996dc5b6626e117a8af7cac2b (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
/*
 * Local APIC virtualization
 *
 * Copyright (C) 2006 Qumranet, Inc.
 * Copyright (C) 2007 Novell
 * Copyright (C) 2007 Intel
 *
 * Authors:
 *   Dor Laor <dor.laor@qumranet.com>
 *   Gregory Haskins <ghaskins@novell.com>
 *   Yaozu (Eddie) Dong <eddie.dong@intel.com>
 *
 * Based on Xen 3.1 code, Copyright (c) 2004, Intel Corporation.
 *
 * This work is licensed under the terms of the GNU GPL, version 2.  See
 * the COPYING file in the top-level directory.
 */

#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/smp.h>
#include <linux/hrtimer.h>
#include <linux/io.h>
#include <linux/module.h>
#include <linux/math64.h>
#include <asm/processor.h>
#include <asm/msr.h>
#include <asm/page.h>
#include <asm/current.h>
#include <asm/apicdef.h>
#include <asm/atomic.h>
#include <asm/apicdef.h>
#include "kvm_cache_regs.h"
#include "irq.h"
#include "trace.h"
#include "x86.h"

#ifndef CONFIG_X86_64
#define mod_64(x, y) ((x) - (y) * div64_u64(x, y))
#else
#define mod_64(x, y) ((x) % (y))
#endif

#define PRId64 "d"
#define PRIx64 "llx"
#define PRIu64 "u"
#define PRIo64 "o"

#define APIC_BUS_CYCLE_NS 1

/* #define apic_debug(fmt,arg...) printk(KERN_WARNING fmt,##arg) */
#define apic_debug(fmt, arg...)

#define APIC_LVT_NUM			6
/* 14 is the version for Xeon and Pentium 8.4.8*/
#define APIC_VERSION			(0x14UL | ((APIC_LVT_NUM - 1) << 16))
#define LAPIC_MMIO_LENGTH		(1 << 12)
/* followed define is not in apicdef.h */
#define APIC_SHORT_MASK			0xc0000
#define APIC_DEST_NOSHORT		0x0
#define APIC_DEST_MASK			0x800
#define MAX_APIC_VECTOR			256

#define VEC_POS(v) ((v) & (32 - 1))
#define REG_POS(v) (((v) >> 5) << 4)

static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off)
{
	return *((u32 *) (apic->regs + reg_off));
}

static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
	*((u32 *) (apic->regs + reg_off)) = val;
}

static inline int apic_test_and_set_vector(int vec, void *bitmap)
{
	return test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}

static inline int apic_test_and_clear_vector(int vec, void *bitmap)
{
	return test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}

static inline void apic_set_vector(int vec, void *bitmap)
{
	set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}

static inline void apic_clear_vector(int vec, void *bitmap)
{
	clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
}

static inline int apic_hw_enabled(struct kvm_lapic *apic)
{
	return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
}

static inline int  apic_sw_enabled(struct kvm_lapic *apic)
{
	return apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED;
}

static inline int apic_enabled(struct kvm_lapic *apic)
{
	return apic_sw_enabled(apic) &&	apic_hw_enabled(apic);
}

#define LVT_MASK	\
	(APIC_LVT_MASKED | APIC_SEND_PENDING | APIC_VECTOR_MASK)

#define LINT_MASK	\
	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)

static inline int kvm_apic_id(struct kvm_lapic *apic)
{
	return (apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
}

static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
{
	return !(apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
}

static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type)
{
	return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
}

static inline int apic_lvtt_period(struct kvm_lapic *apic)
{
	return apic_get_reg(apic, APIC_LVTT) & APIC_LVT_TIMER_PERIODIC;
}

static inline int apic_lvt_nmi_mode(u32 lvt_val)
{
	return (lvt_val & (APIC_MODE_MASK | APIC_LVT_MASKED)) == APIC_DM_NMI;
}

void kvm_apic_set_version(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	struct kvm_cpuid_entry2 *feat;
	u32 v = APIC_VERSION;

	if (!irqchip_in_kernel(vcpu->kvm))
		return;

	feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
	if (feat && (feat->ecx & (1 << (X86_FEATURE_X2APIC & 31))))
		v |= APIC_LVR_DIRECTED_EOI;
	apic_set_reg(apic, APIC_LVR, v);
}

static inline int apic_x2apic_mode(struct kvm_lapic *apic)
{
	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
}

static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
	LVT_MASK | APIC_LVT_TIMER_PERIODIC,	/* LVTT */
	LVT_MASK | APIC_MODE_MASK,	/* LVTTHMR */
	LVT_MASK | APIC_MODE_MASK,	/* LVTPC */
	LINT_MASK, LINT_MASK,	/* LVT0-1 */
	LVT_MASK		/* LVTERR */
};

static int find_highest_vector(void *bitmap)
{
	u32 *word = bitmap;
	int word_offset = MAX_APIC_VECTOR >> 5;

	while ((word_offset != 0) && (word[(--word_offset) << 2] == 0))
		continue;

	if (likely(!word_offset && !word[0]))
		return -1;
	else
		return fls(word[word_offset << 2]) - 1 + (word_offset << 5);
}

static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
{
	apic->irr_pending = true;
	return apic_test_and_set_vector(vec, apic->regs + APIC_IRR);
}

static inline int apic_search_irr(struct kvm_lapic *apic)
{
	return find_highest_vector(apic->regs + APIC_IRR);
}

static inline int apic_find_highest_irr(struct kvm_lapic *apic)
{
	int result;

	if (!apic->irr_pending)
		return -1;

	result = apic_search_irr(apic);
	ASSERT(result == -1 || result >= 16);

	return result;
}

static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
{
	apic->irr_pending = false;
	apic_clear_vector(vec, apic->regs + APIC_IRR);
	if (apic_search_irr(apic) != -1)
		apic->irr_pending = true;
}

int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	int highest_irr;

	/* This may race with setting of irr in __apic_accept_irq() and
	 * value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq
	 * will cause vmexit immediately and the value will be recalculated
	 * on the next vmentry.
	 */
	if (!apic)
		return 0;
	highest_irr = apic_find_highest_irr(apic);

	return highest_irr;
}

static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
			     int vector, int level, int trig_mode);

int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq)
{
	struct kvm_lapic *apic = vcpu->arch.apic;

	return __apic_accept_irq(apic, irq->delivery_mode, irq->vector,
			irq->level, irq->trig_mode);
}

static inline int apic_find_highest_isr(struct kvm_lapic *apic)
{
	int result;

	result = find_highest_vector(apic->regs + APIC_ISR);
	ASSERT(result == -1 || result >= 16);

	return result;
}

static void apic_update_ppr(struct kvm_lapic *apic)
{
	u32 tpr, isrv, ppr;
	int isr;

	tpr = apic_get_reg(apic, APIC_TASKPRI);
	isr = apic_find_highest_isr(apic);
	isrv = (isr != -1) ? isr : 0;

	if ((tpr & 0xf0) >= (isrv & 0xf0))
		ppr = tpr & 0xff;
	else
		ppr = isrv & 0xf0;

	apic_debug("vlapic %p, ppr 0x%x, isr 0x%x, isrv 0x%x",
		   apic, ppr, isr, isrv);

	apic_set_reg(apic, APIC_PROCPRI, ppr);
}

static void apic_set_tpr(struct kvm_lapic *apic, u32 tpr)
{
	apic_set_reg(apic, APIC_TASKPRI, tpr);
	apic_update_ppr(apic);
}

int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest)
{
	return dest == 0xff || kvm_apic_id(apic) == dest;
}

int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
{
	int result = 0;
	u32 logical_id;

	if (apic_x2apic_mode(apic)) {
		logical_id = apic_get_reg(apic, APIC_LDR);
		return logical_id & mda;
	}

	logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR));

	switch (apic_get_reg(apic, APIC_DFR)) {
	case APIC_DFR_FLAT:
		if (logical_id & mda)
			result = 1;
		break;
	case APIC_DFR_CLUSTER:
		if (((logical_id >> 4) == (mda >> 0x4))
		    && (logical_id & mda & 0xf))
			result = 1;
		break;
	default:
		printk(KERN_WARNING "Bad DFR vcpu %d: %08x\n",
		       apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR));
		break;
	}

	return result;
}

int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
			   int short_hand, int dest, int dest_mode)
{
	int result = 0;
	struct kvm_lapic *target = vcpu->arch.apic;

	apic_debug("target %p, source %p, dest 0x%x, "
		   "dest_mode 0x%x, short_hand 0x%x\n",
		   target, source, dest, dest_mode, short_hand);

	ASSERT(!target);
	switch (short_hand) {
	case APIC_DEST_NOSHORT:
		if (dest_mode == 0)
			/* Physical mode. */
			result = kvm_apic_match_physical_addr(target, dest);
		else
			/* Logical mode. */
			result = kvm_apic_match_logical_addr(target, dest);
		break;
	case APIC_DEST_SELF:
		result = (target == source);
		break;
	case APIC_DEST_ALLINC:
		result = 1;
		break;
	case APIC_DEST_ALLBUT:
		result = (target != source);
		break;
	default:
		printk(KERN_WARNING "Bad dest shorthand value %x\n",
		       short_hand);
		break;
	}

	return result;
}

/*
 * Add a pending IRQ into lapic.
 * Return 1 if successfully added and 0 if discarded.
 */
static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
			     int vector, int level, int trig_mode)
{
	int result = 0;
	struct kvm_vcpu *vcpu = apic->vcpu;

	switch (delivery_mode) {
	case APIC_DM_LOWEST:
		vcpu->arch.apic_arb_prio++;
	case APIC_DM_FIXED:
		/* FIXME add logic for vcpu on reset */
		if (unlikely(!apic_enabled(apic)))
			break;

		result = !apic_test_and_set_irr(vector, apic);
		trace_kvm_apic_accept_irq(vcpu->vcpu_id, delivery_mode,
					  trig_mode, vector, !result);
		if (!result) {
			if (trig_mode)
				apic_debug("level trig mode repeatedly for "
						"vector %d", vector);
			break;
		}

		if (trig_mode) {
			apic_debug("level trig mode for vector %d", vector);
			apic_set_vector(vector, apic->regs + APIC_TMR);
		} else
			apic_clear_vector(vector, apic->regs + APIC_TMR);
		kvm_vcpu_kick(vcpu);
		break;

	case APIC_DM_REMRD:
		printk(KERN_DEBUG "Ignoring delivery mode 3\n");
		break;

	case APIC_DM_SMI:
		printk(KERN_DEBUG "Ignoring guest SMI\n");
		break;

	case APIC_DM_NMI:
		result = 1;
		kvm_inject_nmi(vcpu);
		kvm_vcpu_kick(vcpu);
		break;

	case APIC_DM_INIT:
		if (level) {
			result = 1;
			if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
				printk(KERN_DEBUG
				       "INIT on a runnable vcpu %d\n",
				       vcpu->vcpu_id);
			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
			kvm_vcpu_kick(vcpu);
		} else {
			apic_debug("Ignoring de-assert INIT to vcpu %d\n",
				   vcpu->vcpu_id);
		}
		break;

	case APIC_DM_STARTUP:
		apic_debug("SIPI to vcpu %d vector 0x%02x\n",
			   vcpu->vcpu_id, vector);
		if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
			result = 1;
			vcpu->arch.sipi_vector = vector;
			vcpu->arch.mp_state = KVM_MP_STATE_SIPI_RECEIVED;
			kvm_vcpu_kick(vcpu);
		}
		break;

	case APIC_DM_EXTINT:
		/*
		 * Should only be called by kvm_apic_local_deliver() with LVT0,
		 * before NMI watchdog was enabled. Already handled by
		 * kvm_apic_accept_pic_intr().
		 */
		break;

	default:
		printk(KERN_ERR "TODO: unsupported delivery mode %x\n",
		       delivery_mode);
		break;
	}
	return result;
}

int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
{
	return vcpu1->arch.apic_arb_prio - vcpu2->arch.apic_arb_prio;
}

static void apic_set_eoi(struct kvm_lapic *apic)
{
	int vector = apic_find_highest_isr(apic);
	int trigger_mode;
	/*
	 * Not every write EOI will has corresponding ISR,
	 * one example is when Kernel check timer on setup_IO_APIC
	 */
	if (vector == -1)
		return;

	apic_clear_vector(vector, apic->regs + APIC_ISR);
	apic_update_ppr(apic);

	if (apic_test_and_clear_vector(vector, apic->regs + APIC_TMR))
		trigger_mode = IOAPIC_LEVEL_TRIG;
	else
		trigger_mode = IOAPIC_EDGE_TRIG;
	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI))
		kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
}

static void apic_send_ipi(struct kvm_lapic *apic)
{
	u32 icr_low = apic_get_reg(apic, APIC_ICR);
	u32 icr_high = apic_get_reg(apic, APIC_ICR2);
	struct kvm_lapic_irq irq;

	irq.vector = icr_low & APIC_VECTOR_MASK;
	irq.delivery_mode = icr_low & APIC_MODE_MASK;
	irq.dest_mode = icr_low & APIC_DEST_MASK;
	irq.level = icr_low & APIC_INT_ASSERT;
	irq.trig_mode = icr_low & APIC_INT_LEVELTRIG;
	irq.shorthand = icr_low & APIC_SHORT_MASK;
	if (apic_x2apic_mode(apic))
		irq.dest_id = icr_high;
	else
		irq.dest_id = GET_APIC_DEST_FIELD(icr_high);

	trace_kvm_apic_ipi(icr_low, irq.dest_id);

	apic_debug("icr_high 0x%x, icr_low 0x%x, "
		   "short_hand 0x%x, dest 0x%x, trig_mode 0x%x, level 0x%x, "
		   "dest_mode 0x%x, delivery_mode 0x%x, vector 0x%x\n",
		   icr_high, icr_low, irq.shorthand, irq.dest_id,
		   irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
		   irq.vector);

	mutex_lock(&apic->vcpu->kvm->irq_lock);
	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq);
	mutex_unlock(&apic->vcpu->kvm->irq_lock);
}

static u32 apic_get_tmcct(struct kvm_lapic *apic)
{
	ktime_t remaining;
	s64 ns;
	u32 tmcct;

	ASSERT(apic != NULL);

	/* if initial count is 0, current count should also be 0 */
	if (apic_get_reg(apic, APIC_TMICT) == 0)
		return 0;

	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
	if (ktime_to_ns(remaining) < 0)
		remaining = ktime_set(0, 0);

	ns = mod_64(ktime_to_ns(remaining), apic->lapic_timer.period);
	tmcct = div64_u64(ns,
			 (APIC_BUS_CYCLE_NS * apic->divide_count));

	return tmcct;
}

static void __report_tpr_access(struct kvm_lapic *apic, bool write)
{
	struct kvm_vcpu *vcpu = apic->vcpu;
	struct kvm_run *run = vcpu->run;

	set_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests);
	run->tpr_access.rip = kvm_rip_read(vcpu);
	run->tpr_access.is_write = write;
}

static inline void report_tpr_access(struct kvm_lapic *apic, bool write)
{
	if (apic->vcpu->arch.tpr_access_reporting)
		__report_tpr_access(apic, write);
}

static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
{
	u32 val = 0;

	if (offset >= LAPIC_MMIO_LENGTH)
		return 0;

	switch (offset) {
	case APIC_ID:
		if (apic_x2apic_mode(apic))
			val = kvm_apic_id(apic);
		else
			val = kvm_apic_id(apic) << 24;
		break;
	case APIC_ARBPRI:
		printk(KERN_WARNING "Access APIC ARBPRI register "
		       "which is for P6\n");
		break;

	case APIC_TMCCT:	/* Timer CCR */
		val = apic_get_tmcct(apic);
		break;

	case APIC_TASKPRI:
		report_tpr_access(apic, false);
		/* fall thru */
	default:
		apic_update_ppr(apic);
		val = apic_get_reg(apic, offset);
		break;
	}

	return val;
}

static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev)
{
	return container_of(dev, struct kvm_lapic, dev);
}

static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
		void *data)
{
	unsigned char alignment = offset & 0xf;
	u32 result;
	/* this bitmask has a bit cleared for each reserver register */
	static const u64 rmask = 0x43ff01ffffffe70cULL;

	if ((alignment + len) > 4) {
		apic_debug("KVM_APIC_READ: alignment error %x %d\n",
			   offset, len);
		return 1;
	}

	if (offset > 0x3f0 || !(rmask & (1ULL << (offset >> 4)))) {
		apic_debug("KVM_APIC_READ: read reserved register %x\n",
			   offset);
		return 1;
	}

	result = __apic_read(apic, offset & ~0xf);

	trace_kvm_apic_read(offset, result);

	switch (len) {
	case 1:
	case 2:
	case 4:
		memcpy(data, (char *)&result + alignment, len);
		break;
	default:
		printk(KERN_ERR "Local APIC read with len = %x, "
		       "should be 1,2, or 4 instead\n", len);
		break;
	}
	return 0;
}

static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
{
	return apic_hw_enabled(apic) &&
	    addr >= apic->base_address &&
	    addr < apic->base_address + LAPIC_MMIO_LENGTH;
}

static int apic_mmio_read(struct kvm_io_device *this,
			   gpa_t address, int len, void *data)
{
	struct kvm_lapic *apic = to_lapic(this);
	u32 offset = address - apic->base_address;

	if (!apic_mmio_in_range(apic, address))
		return -EOPNOTSUPP;

	apic_reg_read(apic, offset, len, data);

	return 0;
}

static void update_divide_count(struct kvm_lapic *apic)
{
	u32 tmp1, tmp2, tdcr;

	tdcr = apic_get_reg(apic, APIC_TDCR);
	tmp1 = tdcr & 0xf;
	tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
	apic->divide_count = 0x1 << (tmp2 & 0x7);

	apic_debug("timer divide count is 0x%x\n",
				   apic->divide_count);
}

static void start_apic_timer(struct kvm_lapic *apic)
{
	ktime_t now = apic->lapic_timer.timer.base->get_time();

	apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT) *
		    APIC_BUS_CYCLE_NS * apic->divide_count;
	atomic_set(&apic->lapic_timer.pending, 0);

	if (!apic->lapic_timer.period)
		return;
	/*
	 * Do not allow the guest to program periodic timers with small
	 * interval, since the hrtimers are not throttled by the host
	 * scheduler.
	 */
	if (apic_lvtt_period(apic)) {
		if (apic->lapic_timer.period < NSEC_PER_MSEC/2)
			apic->lapic_timer.period = NSEC_PER_MSEC/2;
	}

	hrtimer_start(&apic->lapic_timer.timer,
		      ktime_add_ns(now, apic->lapic_timer.period),
		      HRTIMER_MODE_ABS);

	apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
			   PRIx64 ", "
			   "timer initial count 0x%x, period %lldns, "
			   "expire @ 0x%016" PRIx64 ".\n", __func__,
			   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
			   apic_get_reg(apic, APIC_TMICT),
			   apic->lapic_timer.period,
			   ktime_to_ns(ktime_add_ns(now,
					apic->lapic_timer.period)));
}

static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
{
	int nmi_wd_enabled = apic_lvt_nmi_mode(apic_get_reg(apic, APIC_LVT0));

	if (apic_lvt_nmi_mode(lvt0_val)) {
		if (!nmi_wd_enabled) {
			apic_debug("Receive NMI setting on APIC_LVT0 "
				   "for cpu %d\n", apic->vcpu->vcpu_id);
			apic->vcpu->kvm->arch.vapics_in_nmi_mode++;
		}
	} else if (nmi_wd_enabled)
		apic->vcpu->kvm->arch.vapics_in_nmi_mode--;
}

static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
{
	int ret = 0;

	trace_kvm_apic_write(reg, val);

	switch (reg) {
	case APIC_ID:		/* Local APIC ID */
		if (!apic_x2apic_mode(apic))
			apic_set_reg(apic, APIC_ID, val);
		else
			ret = 1;
		break;

	case APIC_TASKPRI:
		report_tpr_access(apic, true);
		apic_set_tpr(apic, val & 0xff);
		break;

	case APIC_EOI:
		apic_set_eoi(apic);
		break;

	case APIC_LDR:
		if (!apic_x2apic_mode(apic))
			apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK);
		else
			ret = 1;
		break;

	case APIC_DFR:
		if (!apic_x2apic_mode(apic))
			apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
		else
			ret = 1;
		break;

	case APIC_SPIV: {
		u32 mask = 0x3ff;
		if (apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
			mask |= APIC_SPIV_DIRECTED_EOI;
		apic_set_reg(apic, APIC_SPIV, val & mask);
		if (!(val & APIC_SPIV_APIC_ENABLED)) {
			int i;
			u32 lvt_val;

			for (i = 0; i < APIC_LVT_NUM; i++) {
				lvt_val = apic_get_reg(apic,
						       APIC_LVTT + 0x10 * i);
				apic_set_reg(apic, APIC_LVTT + 0x10 * i,
					     lvt_val | APIC_LVT_MASKED);
			}
			atomic_set(&apic->lapic_timer.pending, 0);

		}
		break;
	}
	case APIC_ICR:
		/* No delay here, so we always clear the pending bit */
		apic_set_reg(apic, APIC_ICR, val & ~(1 << 12));
		apic_send_ipi(apic);
		break;

	case APIC_ICR2:
		if (!apic_x2apic_mode(apic))
			val &= 0xff000000;
		apic_set_reg(apic, APIC_ICR2, val);
		break;

	case APIC_LVT0:
		apic_manage_nmi_watchdog(apic, val);
	case APIC_LVTT:
	case APIC_LVTTHMR:
	case APIC_LVTPC:
	case APIC_LVT1:
	case APIC_LVTERR:
		/* TODO: Check vector */
		if (!apic_sw_enabled(apic))
			val |= APIC_LVT_MASKED;

		val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
		apic_set_reg(apic, reg, val);

		break;

	case APIC_TMICT:
		hrtimer_cancel(&apic->lapic_timer.timer);
		apic_set_reg(apic, APIC_TMICT, val);
		start_apic_timer(apic);
		break;

	case APIC_TDCR:
		if (val & 4)
			printk(KERN_ERR "KVM_WRITE:TDCR %x\n", val);
		apic_set_reg(apic, APIC_TDCR, val);
		update_divide_count(apic);
		break;

	case APIC_ESR:
		if (apic_x2apic_mode(apic) && val != 0) {
			printk(KERN_ERR "KVM_WRITE:ESR not zero %x\n", val);
			ret = 1;
		}
		break;

	case APIC_SELF_IPI:
		if (apic_x2apic_mode(apic)) {
			apic_reg_write(apic, APIC_ICR, 0x40000 | (val & 0xff));
		} else
			ret = 1;
		break;
	default:
		ret = 1;
		break;
	}
	if (ret)
		apic_debug("Local APIC Write to read-only register %x\n", reg);
	return ret;
}

static int apic_mmio_write(struct kvm_io_device *this,
			    gpa_t address, int len, const void *data)
{
	struct kvm_lapic *apic = to_lapic(this);
	unsigned int offset = address - apic->base_address;
	u32 val;

	if (!apic_mmio_in_range(apic, address))
		return -EOPNOTSUPP;

	/*
	 * APIC register must be aligned on 128-bits boundary.
	 * 32/64/128 bits registers must be accessed thru 32 bits.
	 * Refer SDM 8.4.1
	 */
	if (len != 4 || (offset & 0xf)) {
		/* Don't shout loud, $infamous_os would cause only noise. */
		apic_debug("apic write: bad size=%d %lx\n", len, (long)address);
		return 0;
	}

	val = *(u32*)data;

	/* too common printing */
	if (offset != APIC_EOI)
		apic_debug("%s: offset 0x%x with length 0x%x, and value is "
			   "0x%x\n", __func__, offset, len, val);

	apic_reg_write(apic, offset & 0xff0, val);

	return 0;
}

void kvm_free_lapic(struct kvm_vcpu *vcpu)
{
	if (!vcpu->arch.apic)
		return;

	hrtimer_cancel(&vcpu->arch.apic->lapic_timer.timer);

	if (vcpu->arch.apic->regs_page)
		__free_page(vcpu->arch.apic->regs_page);

	kfree(vcpu->arch.apic);
}

/*
 *----------------------------------------------------------------------
 * LAPIC interface
 *----------------------------------------------------------------------
 */

void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
{
	struct kvm_lapic *apic = vcpu->arch.apic;

	if (!apic)
		return;
	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
		     | (apic_get_reg(apic, APIC_TASKPRI) & 4));
}

u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	u64 tpr;

	if (!apic)
		return 0;
	tpr = (u64) apic_get_reg(apic, APIC_TASKPRI);

	return (tpr & 0xf0) >> 4;
}

void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
{
	struct kvm_lapic *apic = vcpu->arch.apic;

	if (!apic) {
		value |= MSR_IA32_APICBASE_BSP;
		vcpu->arch.apic_base = value;
		return;
	}

	if (!kvm_vcpu_is_bsp(apic->vcpu))
		value &= ~MSR_IA32_APICBASE_BSP;

	vcpu->arch.apic_base = value;
	if (apic_x2apic_mode(apic)) {
		u32 id = kvm_apic_id(apic);
		u32 ldr = ((id & ~0xf) << 16) | (1 << (id & 0xf));
		apic_set_reg(apic, APIC_LDR, ldr);
	}
	apic->base_address = apic->vcpu->arch.apic_base &
			     MSR_IA32_APICBASE_BASE;

	/* with FSB delivery interrupt, we can restart APIC functionality */
	apic_debug("apic base msr is 0x%016" PRIx64 ", and base address is "
		   "0x%lx.\n", apic->vcpu->arch.apic_base, apic->base_address);

}

void kvm_lapic_reset(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic;
	int i;

	apic_debug("%s\n", __func__);

	ASSERT(vcpu);
	apic = vcpu->arch.apic;
	ASSERT(apic != NULL);

	/* Stop the timer in case it's a reset to an active apic */
	hrtimer_cancel(&apic->lapic_timer.timer);

	apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24);
	kvm_apic_set_version(apic->vcpu);

	for (i = 0; i < APIC_LVT_NUM; i++)
		apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
	apic_set_reg(apic, APIC_LVT0,
		     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));

	apic_set_reg(apic, APIC_DFR, 0xffffffffU);
	apic_set_reg(apic, APIC_SPIV, 0xff);
	apic_set_reg(apic, APIC_TASKPRI, 0);
	apic_set_reg(apic, APIC_LDR, 0);
	apic_set_reg(apic, APIC_ESR, 0);
	apic_set_reg(apic, APIC_ICR, 0);
	apic_set_reg(apic, APIC_ICR2, 0);
	apic_set_reg(apic, APIC_TDCR, 0);
	apic_set_reg(apic, APIC_TMICT, 0);
	for (i = 0; i < 8; i++) {
		apic_set_reg(apic, APIC_IRR + 0x10 * i, 0);
		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
	}
	apic->irr_pending = false;
	update_divide_count(apic);
	atomic_set(&apic->lapic_timer.pending, 0);
	if (kvm_vcpu_is_bsp(vcpu))
		vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
	apic_update_ppr(apic);

	vcpu->arch.apic_arb_prio = 0;

	apic_debug(KERN_INFO "%s: vcpu=%p, id=%d, base_msr="
		   "0x%016" PRIx64 ", base_address=0x%0lx.\n", __func__,
		   vcpu, kvm_apic_id(apic),
		   vcpu->arch.apic_base, apic->base_address);
}

bool kvm_apic_present(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.apic && apic_hw_enabled(vcpu->arch.apic);
}

int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
{
	return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic);
}

/*
 *----------------------------------------------------------------------
 * timer interface
 *----------------------------------------------------------------------
 */

static bool lapic_is_periodic(struct kvm_timer *ktimer)
{
	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic,
					      lapic_timer);
	return apic_lvtt_period(apic);
}

int apic_has_pending_timer(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *lapic = vcpu->arch.apic;

	if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
		return atomic_read(&lapic->lapic_timer.pending);

	return 0;
}

static int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
{
	u32 reg = apic_get_reg(apic, lvt_type);
	int vector, mode, trig_mode;

	if (apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
		vector = reg & APIC_VECTOR_MASK;
		mode = reg & APIC_MODE_MASK;
		trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
		return __apic_accept_irq(apic, mode, vector, 1, trig_mode);
	}
	return 0;
}

void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;

	if (apic)
		kvm_apic_local_deliver(apic, APIC_LVT0);
}

static struct kvm_timer_ops lapic_timer_ops = {
	.is_periodic = lapic_is_periodic,
};

static const struct kvm_io_device_ops apic_mmio_ops = {
	.read     = apic_mmio_read,
	.write    = apic_mmio_write,
};

int kvm_create_lapic(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic;

	ASSERT(vcpu != NULL);
	apic_debug("apic_init %d\n", vcpu->vcpu_id);

	apic = kzalloc(sizeof(*apic), GFP_KERNEL);
	if (!apic)
		goto nomem;

	vcpu->arch.apic = apic;

	apic->regs_page = alloc_page(GFP_KERNEL);
	if (apic->regs_page == NULL) {
		printk(KERN_ERR "malloc apic regs error for vcpu %x\n",
		       vcpu->vcpu_id);
		goto nomem_free_apic;
	}
	apic->regs = page_address(apic->regs_page);
	memset(apic->regs, 0, PAGE_SIZE);
	apic->vcpu = vcpu;

	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
		     HRTIMER_MODE_ABS);
	apic->lapic_timer.timer.function = kvm_timer_fn;
	apic->lapic_timer.t_ops = &lapic_timer_ops;
	apic->lapic_timer.kvm = vcpu->kvm;
	apic->lapic_timer.vcpu = vcpu;

	apic->base_address = APIC_DEFAULT_PHYS_BASE;
	vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;

	kvm_lapic_reset(vcpu);
	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);

	return 0;
nomem_free_apic:
	kfree(apic);
nomem:
	return -ENOMEM;
}

int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	int highest_irr;

	if (!apic || !apic_enabled(apic))
		return -1;

	apic_update_ppr(apic);
	highest_irr = apic_find_highest_irr(apic);
	if ((highest_irr == -1) ||
	    ((highest_irr & 0xF0) <= apic_get_reg(apic, APIC_PROCPRI)))
		return -1;
	return highest_irr;
}

int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu)
{
	u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0);
	int r = 0;

	if (kvm_vcpu_is_bsp(vcpu)) {
		if (!apic_hw_enabled(vcpu->arch.apic))
			r = 1;
		if ((lvt0 & APIC_LVT_MASKED) == 0 &&
		    GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT)
			r = 1;
	}
	return r;
}

void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;

	if (apic && atomic_read(&apic->lapic_timer.pending) > 0) {
		if (kvm_apic_local_deliver(apic, APIC_LVTT))
			atomic_dec(&apic->lapic_timer.pending);
	}
}

int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
{
	int vector = kvm_apic_has_interrupt(vcpu);
	struct kvm_lapic *apic = vcpu->arch.apic;

	if (vector == -1)
		return -1;

	apic_set_vector(vector, apic->regs + APIC_ISR);
	apic_update_ppr(apic);
	apic_clear_irr(vector, apic);
	return vector;
}

void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;

	apic->base_address = vcpu->arch.apic_base &
			     MSR_IA32_APICBASE_BASE;
	kvm_apic_set_version(vcpu);

	apic_update_ppr(apic);
	hrtimer_cancel(&apic->lapic_timer.timer);
	update_divide_count(apic);
	start_apic_timer(apic);
}

void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	struct hrtimer *timer;

	if (!apic)
		return;

	timer = &apic->lapic_timer.timer;
	if (hrtimer_cancel(timer))
		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
}

void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
{
	u32 data;
	void *vapic;

	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
		return;

	vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0);
	data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
	kunmap_atomic(vapic, KM_USER0);

	apic_set_tpr(vcpu->arch.apic, data & 0xff);
}

void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
{
	u32 data, tpr;
	int max_irr, max_isr;
	struct kvm_lapic *apic;
	void *vapic;

	if (!irqchip_in_kernel(vcpu->kvm) || !vcpu->arch.apic->vapic_addr)
		return;

	apic = vcpu->arch.apic;
	tpr = apic_get_reg(apic, APIC_TASKPRI) & 0xff;
	max_irr = apic_find_highest_irr(apic);
	if (max_irr < 0)
		max_irr = 0;
	max_isr = apic_find_highest_isr(apic);
	if (max_isr < 0)
		max_isr = 0;
	data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);

	vapic = kmap_atomic(vcpu->arch.apic->vapic_page, KM_USER0);
	*(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
	kunmap_atomic(vapic, KM_USER0);
}

void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
{
	if (!irqchip_in_kernel(vcpu->kvm))
		return;

	vcpu->arch.apic->vapic_addr = vapic_addr;
}

int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	u32 reg = (msr - APIC_BASE_MSR) << 4;

	if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
		return 1;

	/* if this is ICR write vector before command */
	if (msr == 0x830)
		apic_reg_write(apic, APIC_ICR2, (u32)(data >> 32));
	return apic_reg_write(apic, reg, (u32)data);
}

int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data)
{
	struct kvm_lapic *apic = vcpu->arch.apic;
	u32 reg = (msr - APIC_BASE_MSR) << 4, low, high = 0;

	if (!irqchip_in_kernel(vcpu->kvm) || !apic_x2apic_mode(apic))
		return 1;

	if (apic_reg_read(apic, reg, 4, &low))
		return 1;
	if (msr == 0x830)
		apic_reg_read(apic, APIC_ICR2, 4, &high);

	*data = (((u64)high) << 32) | low;

	return 0;
}