forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathinterrupt.c
2339 lines (2047 loc) · 61.7 KB
/
interrupt.c
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
/*
* handling kvm guest interrupts
*
* Copyright IBM Corp. 2008, 2015
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License (version 2 only)
* as published by the Free Software Foundation.
*
* Author(s): Carsten Otte <[email protected]>
*/
#include <linux/interrupt.h>
#include <linux/kvm_host.h>
#include <linux/hrtimer.h>
#include <linux/mmu_context.h>
#include <linux/signal.h>
#include <linux/slab.h>
#include <linux/bitmap.h>
#include <linux/vmalloc.h>
#include <asm/asm-offsets.h>
#include <asm/dis.h>
#include <asm/uaccess.h>
#include <asm/sclp.h>
#include <asm/isc.h>
#include "kvm-s390.h"
#include "gaccess.h"
#include "trace-s390.h"
#define IOINT_SCHID_MASK 0x0000ffff
#define IOINT_SSID_MASK 0x00030000
#define IOINT_CSSID_MASK 0x03fc0000
#define PFAULT_INIT 0x0600
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
/* handle external calls via sigp interpretation facility */
static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
{
int c, scn;
if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
return 0;
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
union esca_sigp_ctrl sigp_ctrl =
sca->cpu[vcpu->vcpu_id].sigp_ctrl;
c = sigp_ctrl.c;
scn = sigp_ctrl.scn;
} else {
struct bsca_block *sca = vcpu->kvm->arch.sca;
union bsca_sigp_ctrl sigp_ctrl =
sca->cpu[vcpu->vcpu_id].sigp_ctrl;
c = sigp_ctrl.c;
scn = sigp_ctrl.scn;
}
read_unlock(&vcpu->kvm->arch.sca_lock);
if (src_id)
*src_id = scn;
return c;
}
static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
{
int expect, rc;
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
union esca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
new_val.scn = src_id;
new_val.c = 1;
old_val.c = 0;
expect = old_val.value;
rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
} else {
struct bsca_block *sca = vcpu->kvm->arch.sca;
union bsca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
new_val.scn = src_id;
new_val.c = 1;
old_val.c = 0;
expect = old_val.value;
rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
}
read_unlock(&vcpu->kvm->arch.sca_lock);
if (rc != expect) {
/* another external call is pending */
return -EBUSY;
}
atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
return 0;
}
static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc, expect;
atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
union esca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
union esca_sigp_ctrl old = *sigp_ctrl;
expect = old.value;
rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
} else {
struct bsca_block *sca = vcpu->kvm->arch.sca;
union bsca_sigp_ctrl *sigp_ctrl =
&(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
union bsca_sigp_ctrl old = *sigp_ctrl;
expect = old.value;
rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
}
read_unlock(&vcpu->kvm->arch.sca_lock);
WARN_ON(rc != expect); /* cannot clear? */
}
int psw_extint_disabled(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
}
static int psw_ioint_disabled(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_IO);
}
static int psw_mchk_disabled(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_MCHECK);
}
static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
{
return psw_extint_disabled(vcpu) &&
psw_ioint_disabled(vcpu) &&
psw_mchk_disabled(vcpu);
}
static int ckc_interrupts_enabled(struct kvm_vcpu *vcpu)
{
if (psw_extint_disabled(vcpu) ||
!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
return 0;
if (guestdbg_enabled(vcpu) && guestdbg_sstep_enabled(vcpu))
/* No timer interrupts when single stepping */
return 0;
return 1;
}
static int ckc_irq_pending(struct kvm_vcpu *vcpu)
{
if (vcpu->arch.sie_block->ckc >= kvm_s390_get_tod_clock_fast(vcpu->kvm))
return 0;
return ckc_interrupts_enabled(vcpu);
}
static int cpu_timer_interrupts_enabled(struct kvm_vcpu *vcpu)
{
return !psw_extint_disabled(vcpu) &&
(vcpu->arch.sie_block->gcr[0] & 0x400ul);
}
static int cpu_timer_irq_pending(struct kvm_vcpu *vcpu)
{
return (vcpu->arch.sie_block->cputm >> 63) &&
cpu_timer_interrupts_enabled(vcpu);
}
static inline int is_ioirq(unsigned long irq_type)
{
return ((irq_type >= IRQ_PEND_IO_ISC_0) &&
(irq_type <= IRQ_PEND_IO_ISC_7));
}
static uint64_t isc_to_isc_bits(int isc)
{
return (0x80 >> isc) << 24;
}
static inline u8 int_word_to_isc(u32 int_word)
{
return (int_word & 0x38000000) >> 27;
}
static inline unsigned long pending_irqs(struct kvm_vcpu *vcpu)
{
return vcpu->kvm->arch.float_int.pending_irqs |
vcpu->arch.local_int.pending_irqs;
}
static unsigned long disable_iscs(struct kvm_vcpu *vcpu,
unsigned long active_mask)
{
int i;
for (i = 0; i <= MAX_ISC; i++)
if (!(vcpu->arch.sie_block->gcr[6] & isc_to_isc_bits(i)))
active_mask &= ~(1UL << (IRQ_PEND_IO_ISC_0 + i));
return active_mask;
}
static unsigned long deliverable_irqs(struct kvm_vcpu *vcpu)
{
unsigned long active_mask;
active_mask = pending_irqs(vcpu);
if (!active_mask)
return 0;
if (psw_extint_disabled(vcpu))
active_mask &= ~IRQ_PEND_EXT_MASK;
if (psw_ioint_disabled(vcpu))
active_mask &= ~IRQ_PEND_IO_MASK;
else
active_mask = disable_iscs(vcpu, active_mask);
if (!(vcpu->arch.sie_block->gcr[0] & 0x2000ul))
__clear_bit(IRQ_PEND_EXT_EXTERNAL, &active_mask);
if (!(vcpu->arch.sie_block->gcr[0] & 0x4000ul))
__clear_bit(IRQ_PEND_EXT_EMERGENCY, &active_mask);
if (!(vcpu->arch.sie_block->gcr[0] & 0x800ul))
__clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &active_mask);
if (!(vcpu->arch.sie_block->gcr[0] & 0x400ul))
__clear_bit(IRQ_PEND_EXT_CPU_TIMER, &active_mask);
if (!(vcpu->arch.sie_block->gcr[0] & 0x200ul))
__clear_bit(IRQ_PEND_EXT_SERVICE, &active_mask);
if (psw_mchk_disabled(vcpu))
active_mask &= ~IRQ_PEND_MCHK_MASK;
if (!(vcpu->arch.sie_block->gcr[14] &
vcpu->kvm->arch.float_int.mchk.cr14))
__clear_bit(IRQ_PEND_MCHK_REP, &active_mask);
/*
* STOP irqs will never be actively delivered. They are triggered via
* intercept requests and cleared when the stop intercept is performed.
*/
__clear_bit(IRQ_PEND_SIGP_STOP, &active_mask);
return active_mask;
}
static void __set_cpu_idle(struct kvm_vcpu *vcpu)
{
atomic_or(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
set_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}
static void __unset_cpu_idle(struct kvm_vcpu *vcpu)
{
atomic_andnot(CPUSTAT_WAIT, &vcpu->arch.sie_block->cpuflags);
clear_bit(vcpu->vcpu_id, vcpu->arch.local_int.float_int->idle_mask);
}
static void __reset_intercept_indicators(struct kvm_vcpu *vcpu)
{
atomic_andnot(CPUSTAT_IO_INT | CPUSTAT_EXT_INT | CPUSTAT_STOP_INT,
&vcpu->arch.sie_block->cpuflags);
vcpu->arch.sie_block->lctl = 0x0000;
vcpu->arch.sie_block->ictl &= ~(ICTL_LPSW | ICTL_STCTL | ICTL_PINT);
if (guestdbg_enabled(vcpu)) {
vcpu->arch.sie_block->lctl |= (LCTL_CR0 | LCTL_CR9 |
LCTL_CR10 | LCTL_CR11);
vcpu->arch.sie_block->ictl |= (ICTL_STCTL | ICTL_PINT);
}
}
static void __set_cpuflag(struct kvm_vcpu *vcpu, u32 flag)
{
atomic_or(flag, &vcpu->arch.sie_block->cpuflags);
}
static void set_intercept_indicators_io(struct kvm_vcpu *vcpu)
{
if (!(pending_irqs(vcpu) & IRQ_PEND_IO_MASK))
return;
else if (psw_ioint_disabled(vcpu))
__set_cpuflag(vcpu, CPUSTAT_IO_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR6;
}
static void set_intercept_indicators_ext(struct kvm_vcpu *vcpu)
{
if (!(pending_irqs(vcpu) & IRQ_PEND_EXT_MASK))
return;
if (psw_extint_disabled(vcpu))
__set_cpuflag(vcpu, CPUSTAT_EXT_INT);
else
vcpu->arch.sie_block->lctl |= LCTL_CR0;
}
static void set_intercept_indicators_mchk(struct kvm_vcpu *vcpu)
{
if (!(pending_irqs(vcpu) & IRQ_PEND_MCHK_MASK))
return;
if (psw_mchk_disabled(vcpu))
vcpu->arch.sie_block->ictl |= ICTL_LPSW;
else
vcpu->arch.sie_block->lctl |= LCTL_CR14;
}
static void set_intercept_indicators_stop(struct kvm_vcpu *vcpu)
{
if (kvm_s390_is_stop_irq_pending(vcpu))
__set_cpuflag(vcpu, CPUSTAT_STOP_INT);
}
/* Set interception request for non-deliverable interrupts */
static void set_intercept_indicators(struct kvm_vcpu *vcpu)
{
set_intercept_indicators_io(vcpu);
set_intercept_indicators_ext(vcpu);
set_intercept_indicators_mchk(vcpu);
set_intercept_indicators_stop(vcpu);
}
static u16 get_ilc(struct kvm_vcpu *vcpu)
{
switch (vcpu->arch.sie_block->icptcode) {
case ICPT_INST:
case ICPT_INSTPROGI:
case ICPT_OPEREXC:
case ICPT_PARTEXEC:
case ICPT_IOINST:
/* last instruction only stored for these icptcodes */
return insn_length(vcpu->arch.sie_block->ipa >> 8);
case ICPT_PROGI:
return vcpu->arch.sie_block->pgmilc;
default:
return 0;
}
}
static int __must_check __deliver_cpu_timer(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CPU_TIMER,
0, 0);
rc = put_guest_lc(vcpu, EXT_IRQ_CPU_TIMER,
(u16 *)__LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
clear_bit(IRQ_PEND_EXT_CPU_TIMER, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_ckc(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_CLOCK_COMP,
0, 0);
rc = put_guest_lc(vcpu, EXT_IRQ_CLK_COMP,
(u16 __user *)__LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
clear_bit(IRQ_PEND_EXT_CLOCK_COMP, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_pfault_init(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_ext_info ext;
int rc;
spin_lock(&li->lock);
ext = li->irq.ext;
clear_bit(IRQ_PEND_PFAULT_INIT, &li->pending_irqs);
li->irq.ext.ext_params2 = 0;
spin_unlock(&li->lock);
VCPU_EVENT(vcpu, 4, "deliver: pfault init token 0x%llx",
ext.ext_params2);
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_INT_PFAULT_INIT,
0, ext.ext_params2);
rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE, (u16 *) __LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, PFAULT_INIT, (u16 *) __LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= put_guest_lc(vcpu, ext.ext_params2, (u64 *) __LC_EXT_PARAMS2);
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_machine_check(struct kvm_vcpu *vcpu)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_mchk_info mchk = {};
unsigned long adtl_status_addr;
int deliver = 0;
int rc = 0;
spin_lock(&fi->lock);
spin_lock(&li->lock);
if (test_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs) ||
test_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs)) {
/*
* If there was an exigent machine check pending, then any
* repressible machine checks that might have been pending
* are indicated along with it, so always clear bits for
* repressible and exigent interrupts
*/
mchk = li->irq.mchk;
clear_bit(IRQ_PEND_MCHK_EX, &li->pending_irqs);
clear_bit(IRQ_PEND_MCHK_REP, &li->pending_irqs);
memset(&li->irq.mchk, 0, sizeof(mchk));
deliver = 1;
}
/*
* We indicate floating repressible conditions along with
* other pending conditions. Channel Report Pending and Channel
* Subsystem damage are the only two and and are indicated by
* bits in mcic and masked in cr14.
*/
if (test_and_clear_bit(IRQ_PEND_MCHK_REP, &fi->pending_irqs)) {
mchk.mcic |= fi->mchk.mcic;
mchk.cr14 |= fi->mchk.cr14;
memset(&fi->mchk, 0, sizeof(mchk));
deliver = 1;
}
spin_unlock(&li->lock);
spin_unlock(&fi->lock);
if (deliver) {
VCPU_EVENT(vcpu, 3, "deliver: machine check mcic 0x%llx",
mchk.mcic);
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_MCHK,
mchk.cr14, mchk.mcic);
rc = kvm_s390_vcpu_store_status(vcpu,
KVM_S390_STORE_STATUS_PREFIXED);
rc |= read_guest_lc(vcpu, __LC_VX_SAVE_AREA_ADDR,
&adtl_status_addr,
sizeof(unsigned long));
rc |= kvm_s390_vcpu_store_adtl_status(vcpu,
adtl_status_addr);
rc |= put_guest_lc(vcpu, mchk.mcic,
(u64 __user *) __LC_MCCK_CODE);
rc |= put_guest_lc(vcpu, mchk.failing_storage_address,
(u64 __user *) __LC_MCCK_FAIL_STOR_ADDR);
rc |= write_guest_lc(vcpu, __LC_PSW_SAVE_AREA,
&mchk.fixed_logout,
sizeof(mchk.fixed_logout));
rc |= write_guest_lc(vcpu, __LC_MCK_OLD_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_MCK_NEW_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
}
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc;
VCPU_EVENT(vcpu, 3, "%s", "deliver: cpu restart");
vcpu->stat.deliver_restart_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
rc = write_guest_lc(vcpu,
offsetof(struct lowcore, restart_old_psw),
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_set_prefix(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_prefix_info prefix;
spin_lock(&li->lock);
prefix = li->irq.prefix;
li->irq.prefix.address = 0;
clear_bit(IRQ_PEND_SET_PREFIX, &li->pending_irqs);
spin_unlock(&li->lock);
vcpu->stat.deliver_prefix_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_SIGP_SET_PREFIX,
prefix.address, 0);
kvm_s390_set_prefix(vcpu, prefix.address);
return 0;
}
static int __must_check __deliver_emergency_signal(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
int rc;
int cpu_addr;
spin_lock(&li->lock);
cpu_addr = find_first_bit(li->sigp_emerg_pending, KVM_MAX_VCPUS);
clear_bit(cpu_addr, li->sigp_emerg_pending);
if (bitmap_empty(li->sigp_emerg_pending, KVM_MAX_VCPUS))
clear_bit(IRQ_PEND_EXT_EMERGENCY, &li->pending_irqs);
spin_unlock(&li->lock);
VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp emerg");
vcpu->stat.deliver_emergency_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_EMERGENCY,
cpu_addr, 0);
rc = put_guest_lc(vcpu, EXT_IRQ_EMERGENCY_SIG,
(u16 *)__LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, cpu_addr, (u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_external_call(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_extcall_info extcall;
int rc;
spin_lock(&li->lock);
extcall = li->irq.extcall;
li->irq.extcall.code = 0;
clear_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
spin_unlock(&li->lock);
VCPU_EVENT(vcpu, 4, "%s", "deliver: sigp ext call");
vcpu->stat.deliver_external_call++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_INT_EXTERNAL_CALL,
extcall.code, 0);
rc = put_guest_lc(vcpu, EXT_IRQ_EXTERNAL_CALL,
(u16 *)__LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, extcall.code, (u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW, &vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_prog(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_pgm_info pgm_info;
int rc = 0, nullifying = false;
u16 ilc = get_ilc(vcpu);
spin_lock(&li->lock);
pgm_info = li->irq.pgm;
clear_bit(IRQ_PEND_PROG, &li->pending_irqs);
memset(&li->irq.pgm, 0, sizeof(pgm_info));
spin_unlock(&li->lock);
VCPU_EVENT(vcpu, 3, "deliver: program irq code 0x%x, ilc:%d",
pgm_info.code, ilc);
vcpu->stat.deliver_program_int++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_PROGRAM_INT,
pgm_info.code, 0);
switch (pgm_info.code & ~PGM_PER) {
case PGM_AFX_TRANSLATION:
case PGM_ASX_TRANSLATION:
case PGM_EX_TRANSLATION:
case PGM_LFX_TRANSLATION:
case PGM_LSTE_SEQUENCE:
case PGM_LSX_TRANSLATION:
case PGM_LX_TRANSLATION:
case PGM_PRIMARY_AUTHORITY:
case PGM_SECONDARY_AUTHORITY:
nullifying = true;
/* fall through */
case PGM_SPACE_SWITCH:
rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
(u64 *)__LC_TRANS_EXC_CODE);
break;
case PGM_ALEN_TRANSLATION:
case PGM_ALE_SEQUENCE:
case PGM_ASTE_INSTANCE:
case PGM_ASTE_SEQUENCE:
case PGM_ASTE_VALIDITY:
case PGM_EXTENDED_AUTHORITY:
rc = put_guest_lc(vcpu, pgm_info.exc_access_id,
(u8 *)__LC_EXC_ACCESS_ID);
nullifying = true;
break;
case PGM_ASCE_TYPE:
case PGM_PAGE_TRANSLATION:
case PGM_REGION_FIRST_TRANS:
case PGM_REGION_SECOND_TRANS:
case PGM_REGION_THIRD_TRANS:
case PGM_SEGMENT_TRANSLATION:
rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
(u64 *)__LC_TRANS_EXC_CODE);
rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
(u8 *)__LC_EXC_ACCESS_ID);
rc |= put_guest_lc(vcpu, pgm_info.op_access_id,
(u8 *)__LC_OP_ACCESS_ID);
nullifying = true;
break;
case PGM_MONITOR:
rc = put_guest_lc(vcpu, pgm_info.mon_class_nr,
(u16 *)__LC_MON_CLASS_NR);
rc |= put_guest_lc(vcpu, pgm_info.mon_code,
(u64 *)__LC_MON_CODE);
break;
case PGM_VECTOR_PROCESSING:
case PGM_DATA:
rc = put_guest_lc(vcpu, pgm_info.data_exc_code,
(u32 *)__LC_DATA_EXC_CODE);
break;
case PGM_PROTECTION:
rc = put_guest_lc(vcpu, pgm_info.trans_exc_code,
(u64 *)__LC_TRANS_EXC_CODE);
rc |= put_guest_lc(vcpu, pgm_info.exc_access_id,
(u8 *)__LC_EXC_ACCESS_ID);
break;
case PGM_STACK_FULL:
case PGM_STACK_EMPTY:
case PGM_STACK_SPECIFICATION:
case PGM_STACK_TYPE:
case PGM_STACK_OPERATION:
case PGM_TRACE_TABEL:
case PGM_CRYPTO_OPERATION:
nullifying = true;
break;
}
if (pgm_info.code & PGM_PER) {
rc |= put_guest_lc(vcpu, pgm_info.per_code,
(u8 *) __LC_PER_CODE);
rc |= put_guest_lc(vcpu, pgm_info.per_atmid,
(u8 *)__LC_PER_ATMID);
rc |= put_guest_lc(vcpu, pgm_info.per_address,
(u64 *) __LC_PER_ADDRESS);
rc |= put_guest_lc(vcpu, pgm_info.per_access_id,
(u8 *) __LC_PER_ACCESS_ID);
}
if (nullifying && vcpu->arch.sie_block->icptcode == ICPT_INST)
kvm_s390_rewind_psw(vcpu, ilc);
rc |= put_guest_lc(vcpu, ilc, (u16 *) __LC_PGM_ILC);
rc |= put_guest_lc(vcpu, vcpu->arch.sie_block->gbea,
(u64 *) __LC_LAST_BREAK);
rc |= put_guest_lc(vcpu, pgm_info.code,
(u16 *)__LC_PGM_INT_CODE);
rc |= write_guest_lc(vcpu, __LC_PGM_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_PGM_NEW_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_service(struct kvm_vcpu *vcpu)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_ext_info ext;
int rc = 0;
spin_lock(&fi->lock);
if (!(test_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs))) {
spin_unlock(&fi->lock);
return 0;
}
ext = fi->srv_signal;
memset(&fi->srv_signal, 0, sizeof(ext));
clear_bit(IRQ_PEND_EXT_SERVICE, &fi->pending_irqs);
spin_unlock(&fi->lock);
VCPU_EVENT(vcpu, 4, "deliver: sclp parameter 0x%x",
ext.ext_params);
vcpu->stat.deliver_service_signal++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_INT_SERVICE,
ext.ext_params, 0);
rc = put_guest_lc(vcpu, EXT_IRQ_SERVICE_SIG, (u16 *)__LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, 0, (u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
rc |= put_guest_lc(vcpu, ext.ext_params,
(u32 *)__LC_EXT_PARAMS);
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_pfault_done(struct kvm_vcpu *vcpu)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_interrupt_info *inti;
int rc = 0;
spin_lock(&fi->lock);
inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_PFAULT],
struct kvm_s390_interrupt_info,
list);
if (inti) {
list_del(&inti->list);
fi->counters[FIRQ_CNTR_PFAULT] -= 1;
}
if (list_empty(&fi->lists[FIRQ_LIST_PFAULT]))
clear_bit(IRQ_PEND_PFAULT_DONE, &fi->pending_irqs);
spin_unlock(&fi->lock);
if (inti) {
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
KVM_S390_INT_PFAULT_DONE, 0,
inti->ext.ext_params2);
VCPU_EVENT(vcpu, 4, "deliver: pfault done token 0x%llx",
inti->ext.ext_params2);
rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE,
(u16 *)__LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, PFAULT_DONE,
(u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
(u64 *)__LC_EXT_PARAMS2);
kfree(inti);
}
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_virtio(struct kvm_vcpu *vcpu)
{
struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
struct kvm_s390_interrupt_info *inti;
int rc = 0;
spin_lock(&fi->lock);
inti = list_first_entry_or_null(&fi->lists[FIRQ_LIST_VIRTIO],
struct kvm_s390_interrupt_info,
list);
if (inti) {
VCPU_EVENT(vcpu, 4,
"deliver: virtio parm: 0x%x,parm64: 0x%llx",
inti->ext.ext_params, inti->ext.ext_params2);
vcpu->stat.deliver_virtio_interrupt++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
inti->type,
inti->ext.ext_params,
inti->ext.ext_params2);
list_del(&inti->list);
fi->counters[FIRQ_CNTR_VIRTIO] -= 1;
}
if (list_empty(&fi->lists[FIRQ_LIST_VIRTIO]))
clear_bit(IRQ_PEND_VIRTIO, &fi->pending_irqs);
spin_unlock(&fi->lock);
if (inti) {
rc = put_guest_lc(vcpu, EXT_IRQ_CP_SERVICE,
(u16 *)__LC_EXT_INT_CODE);
rc |= put_guest_lc(vcpu, VIRTIO_PARAM,
(u16 *)__LC_EXT_CPU_ADDR);
rc |= write_guest_lc(vcpu, __LC_EXT_OLD_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_EXT_NEW_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
rc |= put_guest_lc(vcpu, inti->ext.ext_params,
(u32 *)__LC_EXT_PARAMS);
rc |= put_guest_lc(vcpu, inti->ext.ext_params2,
(u64 *)__LC_EXT_PARAMS2);
kfree(inti);
}
return rc ? -EFAULT : 0;
}
static int __must_check __deliver_io(struct kvm_vcpu *vcpu,
unsigned long irq_type)
{
struct list_head *isc_list;
struct kvm_s390_float_interrupt *fi;
struct kvm_s390_interrupt_info *inti = NULL;
int rc = 0;
fi = &vcpu->kvm->arch.float_int;
spin_lock(&fi->lock);
isc_list = &fi->lists[irq_type - IRQ_PEND_IO_ISC_0];
inti = list_first_entry_or_null(isc_list,
struct kvm_s390_interrupt_info,
list);
if (inti) {
VCPU_EVENT(vcpu, 4, "deliver: I/O 0x%llx", inti->type);
vcpu->stat.deliver_io_int++;
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id,
inti->type,
((__u32)inti->io.subchannel_id << 16) |
inti->io.subchannel_nr,
((__u64)inti->io.io_int_parm << 32) |
inti->io.io_int_word);
list_del(&inti->list);
fi->counters[FIRQ_CNTR_IO] -= 1;
}
if (list_empty(isc_list))
clear_bit(irq_type, &fi->pending_irqs);
spin_unlock(&fi->lock);
if (inti) {
rc = put_guest_lc(vcpu, inti->io.subchannel_id,
(u16 *)__LC_SUBCHANNEL_ID);
rc |= put_guest_lc(vcpu, inti->io.subchannel_nr,
(u16 *)__LC_SUBCHANNEL_NR);
rc |= put_guest_lc(vcpu, inti->io.io_int_parm,
(u32 *)__LC_IO_INT_PARM);
rc |= put_guest_lc(vcpu, inti->io.io_int_word,
(u32 *)__LC_IO_INT_WORD);
rc |= write_guest_lc(vcpu, __LC_IO_OLD_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
rc |= read_guest_lc(vcpu, __LC_IO_NEW_PSW,
&vcpu->arch.sie_block->gpsw,
sizeof(psw_t));
kfree(inti);
}
return rc ? -EFAULT : 0;
}
typedef int (*deliver_irq_t)(struct kvm_vcpu *vcpu);
static const deliver_irq_t deliver_irq_funcs[] = {
[IRQ_PEND_MCHK_EX] = __deliver_machine_check,
[IRQ_PEND_MCHK_REP] = __deliver_machine_check,
[IRQ_PEND_PROG] = __deliver_prog,
[IRQ_PEND_EXT_EMERGENCY] = __deliver_emergency_signal,
[IRQ_PEND_EXT_EXTERNAL] = __deliver_external_call,
[IRQ_PEND_EXT_CLOCK_COMP] = __deliver_ckc,
[IRQ_PEND_EXT_CPU_TIMER] = __deliver_cpu_timer,
[IRQ_PEND_RESTART] = __deliver_restart,
[IRQ_PEND_SET_PREFIX] = __deliver_set_prefix,
[IRQ_PEND_PFAULT_INIT] = __deliver_pfault_init,
[IRQ_PEND_EXT_SERVICE] = __deliver_service,
[IRQ_PEND_PFAULT_DONE] = __deliver_pfault_done,
[IRQ_PEND_VIRTIO] = __deliver_virtio,
};
/* Check whether an external call is pending (deliverable or not) */
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
if (!sclp.has_sigpif)
return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
return sca_ext_call_pending(vcpu, NULL);
}
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
{
if (deliverable_irqs(vcpu))
return 1;
if (kvm_cpu_has_pending_timer(vcpu))
return 1;
/* external call pending and deliverable */
if (kvm_s390_ext_call_pending(vcpu) &&
!psw_extint_disabled(vcpu) &&
(vcpu->arch.sie_block->gcr[0] & 0x2000ul))
return 1;
if (!exclude_stop && kvm_s390_is_stop_irq_pending(vcpu))
return 1;
return 0;
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
return ckc_irq_pending(vcpu) || cpu_timer_irq_pending(vcpu);
}
int kvm_s390_handle_wait(struct kvm_vcpu *vcpu)
{
u64 now, sltime;
vcpu->stat.exit_wait_state++;
/* fast path */
if (kvm_arch_vcpu_runnable(vcpu))
return 0;
if (psw_interrupts_disabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "disabled wait");
return -EOPNOTSUPP; /* disabled wait */
}
if (!ckc_interrupts_enabled(vcpu)) {
VCPU_EVENT(vcpu, 3, "%s", "enabled wait w/o timer");
__set_cpu_idle(vcpu);
goto no_timer;
}
now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
/* underflow */
if (vcpu->arch.sie_block->ckc < now)
return 0;
__set_cpu_idle(vcpu);
hrtimer_start(&vcpu->arch.ckc_timer, ktime_set (0, sltime) , HRTIMER_MODE_REL);
VCPU_EVENT(vcpu, 4, "enabled wait via clock comparator: %llu ns", sltime);
no_timer:
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
kvm_vcpu_block(vcpu);
__unset_cpu_idle(vcpu);
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
hrtimer_cancel(&vcpu->arch.ckc_timer);
return 0;
}
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
if (swait_active(&vcpu->wq)) {
/*
* The vcpu gave up the cpu voluntarily, mark it as a good
* yield-candidate.
*/
vcpu->preempted = true;
swake_up(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
enum hrtimer_restart kvm_s390_idle_wakeup(struct hrtimer *timer)
{
struct kvm_vcpu *vcpu;
u64 now, sltime;
vcpu = container_of(timer, struct kvm_vcpu, arch.ckc_timer);
now = kvm_s390_get_tod_clock_fast(vcpu->kvm);
sltime = tod_to_ns(vcpu->arch.sie_block->ckc - now);
/*
* If the monotonic clock runs faster than the tod clock we might be
* woken up too early and have to go back to sleep to avoid deadlocks.
*/
if (vcpu->arch.sie_block->ckc > now &&
hrtimer_forward_now(timer, ns_to_ktime(sltime)))
return HRTIMER_RESTART;
kvm_s390_vcpu_wakeup(vcpu);
return HRTIMER_NORESTART;
}
void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)