forked from riscvarchive/riscv-qemu
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathkvm.c
2238 lines (1932 loc) · 60.7 KB
/
kvm.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
/*
* QEMU S390x KVM implementation
*
* Copyright (c) 2009 Alexander Graf <[email protected]>
* Copyright IBM Corp. 2012
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* Contributions after 2012-10-29 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*
* You should have received a copy of the GNU (Lesser) General Public
* License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <linux/kvm.h>
#include <asm/ptrace.h>
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/timer.h"
#include "sysemu/sysemu.h"
#include "sysemu/kvm.h"
#include "hw/hw.h"
#include "cpu.h"
#include "sysemu/device_tree.h"
#include "qapi/qmp/qjson.h"
#include "exec/gdbstub.h"
#include "exec/address-spaces.h"
#include "trace.h"
#include "qapi-event.h"
#include "hw/s390x/s390-pci-inst.h"
#include "hw/s390x/s390-pci-bus.h"
#include "hw/s390x/ipl.h"
#include "hw/s390x/ebcdic.h"
#include "exec/memattrs.h"
/* #define DEBUG_KVM */
#ifdef DEBUG_KVM
#define DPRINTF(fmt, ...) \
do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0)
#else
#define DPRINTF(fmt, ...) \
do { } while (0)
#endif
#define kvm_vm_check_mem_attr(s, attr) \
kvm_vm_check_attr(s, KVM_S390_VM_MEM_CTRL, attr)
#define IPA0_DIAG 0x8300
#define IPA0_SIGP 0xae00
#define IPA0_B2 0xb200
#define IPA0_B9 0xb900
#define IPA0_EB 0xeb00
#define IPA0_E3 0xe300
#define PRIV_B2_SCLP_CALL 0x20
#define PRIV_B2_CSCH 0x30
#define PRIV_B2_HSCH 0x31
#define PRIV_B2_MSCH 0x32
#define PRIV_B2_SSCH 0x33
#define PRIV_B2_STSCH 0x34
#define PRIV_B2_TSCH 0x35
#define PRIV_B2_TPI 0x36
#define PRIV_B2_SAL 0x37
#define PRIV_B2_RSCH 0x38
#define PRIV_B2_STCRW 0x39
#define PRIV_B2_STCPS 0x3a
#define PRIV_B2_RCHP 0x3b
#define PRIV_B2_SCHM 0x3c
#define PRIV_B2_CHSC 0x5f
#define PRIV_B2_SIGA 0x74
#define PRIV_B2_XSCH 0x76
#define PRIV_EB_SQBS 0x8a
#define PRIV_EB_PCISTB 0xd0
#define PRIV_EB_SIC 0xd1
#define PRIV_B9_EQBS 0x9c
#define PRIV_B9_CLP 0xa0
#define PRIV_B9_PCISTG 0xd0
#define PRIV_B9_PCILG 0xd2
#define PRIV_B9_RPCIT 0xd3
#define PRIV_E3_MPCIFC 0xd0
#define PRIV_E3_STPCIFC 0xd4
#define DIAG_TIMEREVENT 0x288
#define DIAG_IPL 0x308
#define DIAG_KVM_HYPERCALL 0x500
#define DIAG_KVM_BREAKPOINT 0x501
#define ICPT_INSTRUCTION 0x04
#define ICPT_PROGRAM 0x08
#define ICPT_EXT_INT 0x14
#define ICPT_WAITPSW 0x1c
#define ICPT_SOFT_INTERCEPT 0x24
#define ICPT_CPU_STOP 0x28
#define ICPT_IO 0x40
#define NR_LOCAL_IRQS 32
/*
* Needs to be big enough to contain max_cpus emergency signals
* and in addition NR_LOCAL_IRQS interrupts
*/
#define VCPU_IRQ_BUF_SIZE (sizeof(struct kvm_s390_irq) * \
(max_cpus + NR_LOCAL_IRQS))
static CPUWatchpoint hw_watchpoint;
/*
* We don't use a list because this structure is also used to transmit the
* hardware breakpoints to the kernel.
*/
static struct kvm_hw_breakpoint *hw_breakpoints;
static int nb_hw_breakpoints;
const KVMCapabilityInfo kvm_arch_required_capabilities[] = {
KVM_CAP_LAST_INFO
};
static int cap_sync_regs;
static int cap_async_pf;
static int cap_mem_op;
static int cap_s390_irq;
static void *legacy_s390_alloc(size_t size, uint64_t *align);
static int kvm_s390_query_mem_limit(KVMState *s, uint64_t *memory_limit)
{
struct kvm_device_attr attr = {
.group = KVM_S390_VM_MEM_CTRL,
.attr = KVM_S390_VM_MEM_LIMIT_SIZE,
.addr = (uint64_t) memory_limit,
};
return kvm_vm_ioctl(s, KVM_GET_DEVICE_ATTR, &attr);
}
int kvm_s390_set_mem_limit(KVMState *s, uint64_t new_limit, uint64_t *hw_limit)
{
int rc;
struct kvm_device_attr attr = {
.group = KVM_S390_VM_MEM_CTRL,
.attr = KVM_S390_VM_MEM_LIMIT_SIZE,
.addr = (uint64_t) &new_limit,
};
if (!kvm_vm_check_mem_attr(s, KVM_S390_VM_MEM_LIMIT_SIZE)) {
return 0;
}
rc = kvm_s390_query_mem_limit(s, hw_limit);
if (rc) {
return rc;
} else if (*hw_limit < new_limit) {
return -E2BIG;
}
return kvm_vm_ioctl(s, KVM_SET_DEVICE_ATTR, &attr);
}
void kvm_s390_clear_cmma_callback(void *opaque)
{
int rc;
KVMState *s = opaque;
struct kvm_device_attr attr = {
.group = KVM_S390_VM_MEM_CTRL,
.attr = KVM_S390_VM_MEM_CLR_CMMA,
};
rc = kvm_vm_ioctl(s, KVM_SET_DEVICE_ATTR, &attr);
trace_kvm_clear_cmma(rc);
}
static void kvm_s390_enable_cmma(KVMState *s)
{
int rc;
struct kvm_device_attr attr = {
.group = KVM_S390_VM_MEM_CTRL,
.attr = KVM_S390_VM_MEM_ENABLE_CMMA,
};
if (!kvm_vm_check_mem_attr(s, KVM_S390_VM_MEM_ENABLE_CMMA) ||
!kvm_vm_check_mem_attr(s, KVM_S390_VM_MEM_CLR_CMMA)) {
return;
}
rc = kvm_vm_ioctl(s, KVM_SET_DEVICE_ATTR, &attr);
if (!rc) {
qemu_register_reset(kvm_s390_clear_cmma_callback, s);
}
trace_kvm_enable_cmma(rc);
}
static void kvm_s390_set_attr(uint64_t attr)
{
struct kvm_device_attr attribute = {
.group = KVM_S390_VM_CRYPTO,
.attr = attr,
};
int ret = kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attribute);
if (ret) {
error_report("Failed to set crypto device attribute %lu: %s",
attr, strerror(-ret));
}
}
static void kvm_s390_init_aes_kw(void)
{
uint64_t attr = KVM_S390_VM_CRYPTO_DISABLE_AES_KW;
if (object_property_get_bool(OBJECT(qdev_get_machine()), "aes-key-wrap",
NULL)) {
attr = KVM_S390_VM_CRYPTO_ENABLE_AES_KW;
}
if (kvm_vm_check_attr(kvm_state, KVM_S390_VM_CRYPTO, attr)) {
kvm_s390_set_attr(attr);
}
}
static void kvm_s390_init_dea_kw(void)
{
uint64_t attr = KVM_S390_VM_CRYPTO_DISABLE_DEA_KW;
if (object_property_get_bool(OBJECT(qdev_get_machine()), "dea-key-wrap",
NULL)) {
attr = KVM_S390_VM_CRYPTO_ENABLE_DEA_KW;
}
if (kvm_vm_check_attr(kvm_state, KVM_S390_VM_CRYPTO, attr)) {
kvm_s390_set_attr(attr);
}
}
static void kvm_s390_init_crypto(void)
{
kvm_s390_init_aes_kw();
kvm_s390_init_dea_kw();
}
int kvm_arch_init(MachineState *ms, KVMState *s)
{
cap_sync_regs = kvm_check_extension(s, KVM_CAP_SYNC_REGS);
cap_async_pf = kvm_check_extension(s, KVM_CAP_ASYNC_PF);
cap_mem_op = kvm_check_extension(s, KVM_CAP_S390_MEM_OP);
cap_s390_irq = kvm_check_extension(s, KVM_CAP_S390_INJECT_IRQ);
kvm_s390_enable_cmma(s);
if (!kvm_check_extension(s, KVM_CAP_S390_GMAP)
|| !kvm_check_extension(s, KVM_CAP_S390_COW)) {
phys_mem_set_alloc(legacy_s390_alloc);
}
kvm_vm_enable_cap(s, KVM_CAP_S390_USER_SIGP, 0);
kvm_vm_enable_cap(s, KVM_CAP_S390_VECTOR_REGISTERS, 0);
kvm_vm_enable_cap(s, KVM_CAP_S390_USER_STSI, 0);
return 0;
}
unsigned long kvm_arch_vcpu_id(CPUState *cpu)
{
return cpu->cpu_index;
}
int kvm_arch_init_vcpu(CPUState *cs)
{
S390CPU *cpu = S390_CPU(cs);
kvm_s390_set_cpu_state(cpu, cpu->env.cpu_state);
cpu->irqstate = g_malloc0(VCPU_IRQ_BUF_SIZE);
return 0;
}
void kvm_s390_reset_vcpu(S390CPU *cpu)
{
CPUState *cs = CPU(cpu);
/* The initial reset call is needed here to reset in-kernel
* vcpu data that we can't access directly from QEMU
* (i.e. with older kernels which don't support sync_regs/ONE_REG).
* Before this ioctl cpu_synchronize_state() is called in common kvm
* code (kvm-all) */
if (kvm_vcpu_ioctl(cs, KVM_S390_INITIAL_RESET, NULL)) {
error_report("Initial CPU reset failed on CPU %i", cs->cpu_index);
}
kvm_s390_init_crypto();
}
static int can_sync_regs(CPUState *cs, int regs)
{
return cap_sync_regs && (cs->kvm_run->kvm_valid_regs & regs) == regs;
}
int kvm_arch_put_registers(CPUState *cs, int level)
{
S390CPU *cpu = S390_CPU(cs);
CPUS390XState *env = &cpu->env;
struct kvm_sregs sregs;
struct kvm_regs regs;
struct kvm_fpu fpu = {};
int r;
int i;
/* always save the PSW and the GPRS*/
cs->kvm_run->psw_addr = env->psw.addr;
cs->kvm_run->psw_mask = env->psw.mask;
if (can_sync_regs(cs, KVM_SYNC_GPRS)) {
for (i = 0; i < 16; i++) {
cs->kvm_run->s.regs.gprs[i] = env->regs[i];
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_GPRS;
}
} else {
for (i = 0; i < 16; i++) {
regs.gprs[i] = env->regs[i];
}
r = kvm_vcpu_ioctl(cs, KVM_SET_REGS, ®s);
if (r < 0) {
return r;
}
}
if (can_sync_regs(cs, KVM_SYNC_VRS)) {
for (i = 0; i < 32; i++) {
cs->kvm_run->s.regs.vrs[i][0] = env->vregs[i][0].ll;
cs->kvm_run->s.regs.vrs[i][1] = env->vregs[i][1].ll;
}
cs->kvm_run->s.regs.fpc = env->fpc;
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_VRS;
} else {
/* Floating point */
for (i = 0; i < 16; i++) {
fpu.fprs[i] = get_freg(env, i)->ll;
}
fpu.fpc = env->fpc;
r = kvm_vcpu_ioctl(cs, KVM_SET_FPU, &fpu);
if (r < 0) {
return r;
}
}
/* Do we need to save more than that? */
if (level == KVM_PUT_RUNTIME_STATE) {
return 0;
}
if (can_sync_regs(cs, KVM_SYNC_ARCH0)) {
cs->kvm_run->s.regs.cputm = env->cputm;
cs->kvm_run->s.regs.ckc = env->ckc;
cs->kvm_run->s.regs.todpr = env->todpr;
cs->kvm_run->s.regs.gbea = env->gbea;
cs->kvm_run->s.regs.pp = env->pp;
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_ARCH0;
} else {
/*
* These ONE_REGS are not protected by a capability. As they are only
* necessary for migration we just trace a possible error, but don't
* return with an error return code.
*/
kvm_set_one_reg(cs, KVM_REG_S390_CPU_TIMER, &env->cputm);
kvm_set_one_reg(cs, KVM_REG_S390_CLOCK_COMP, &env->ckc);
kvm_set_one_reg(cs, KVM_REG_S390_TODPR, &env->todpr);
kvm_set_one_reg(cs, KVM_REG_S390_GBEA, &env->gbea);
kvm_set_one_reg(cs, KVM_REG_S390_PP, &env->pp);
}
/* pfault parameters */
if (can_sync_regs(cs, KVM_SYNC_PFAULT)) {
cs->kvm_run->s.regs.pft = env->pfault_token;
cs->kvm_run->s.regs.pfs = env->pfault_select;
cs->kvm_run->s.regs.pfc = env->pfault_compare;
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_PFAULT;
} else if (cap_async_pf) {
r = kvm_set_one_reg(cs, KVM_REG_S390_PFTOKEN, &env->pfault_token);
if (r < 0) {
return r;
}
r = kvm_set_one_reg(cs, KVM_REG_S390_PFCOMPARE, &env->pfault_compare);
if (r < 0) {
return r;
}
r = kvm_set_one_reg(cs, KVM_REG_S390_PFSELECT, &env->pfault_select);
if (r < 0) {
return r;
}
}
/* access registers and control registers*/
if (can_sync_regs(cs, KVM_SYNC_ACRS | KVM_SYNC_CRS)) {
for (i = 0; i < 16; i++) {
cs->kvm_run->s.regs.acrs[i] = env->aregs[i];
cs->kvm_run->s.regs.crs[i] = env->cregs[i];
}
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_ACRS;
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_CRS;
} else {
for (i = 0; i < 16; i++) {
sregs.acrs[i] = env->aregs[i];
sregs.crs[i] = env->cregs[i];
}
r = kvm_vcpu_ioctl(cs, KVM_SET_SREGS, &sregs);
if (r < 0) {
return r;
}
}
/* Finally the prefix */
if (can_sync_regs(cs, KVM_SYNC_PREFIX)) {
cs->kvm_run->s.regs.prefix = env->psa;
cs->kvm_run->kvm_dirty_regs |= KVM_SYNC_PREFIX;
} else {
/* prefix is only supported via sync regs */
}
return 0;
}
int kvm_arch_get_registers(CPUState *cs)
{
S390CPU *cpu = S390_CPU(cs);
CPUS390XState *env = &cpu->env;
struct kvm_sregs sregs;
struct kvm_regs regs;
struct kvm_fpu fpu;
int i, r;
/* get the PSW */
env->psw.addr = cs->kvm_run->psw_addr;
env->psw.mask = cs->kvm_run->psw_mask;
/* the GPRS */
if (can_sync_regs(cs, KVM_SYNC_GPRS)) {
for (i = 0; i < 16; i++) {
env->regs[i] = cs->kvm_run->s.regs.gprs[i];
}
} else {
r = kvm_vcpu_ioctl(cs, KVM_GET_REGS, ®s);
if (r < 0) {
return r;
}
for (i = 0; i < 16; i++) {
env->regs[i] = regs.gprs[i];
}
}
/* The ACRS and CRS */
if (can_sync_regs(cs, KVM_SYNC_ACRS | KVM_SYNC_CRS)) {
for (i = 0; i < 16; i++) {
env->aregs[i] = cs->kvm_run->s.regs.acrs[i];
env->cregs[i] = cs->kvm_run->s.regs.crs[i];
}
} else {
r = kvm_vcpu_ioctl(cs, KVM_GET_SREGS, &sregs);
if (r < 0) {
return r;
}
for (i = 0; i < 16; i++) {
env->aregs[i] = sregs.acrs[i];
env->cregs[i] = sregs.crs[i];
}
}
/* Floating point and vector registers */
if (can_sync_regs(cs, KVM_SYNC_VRS)) {
for (i = 0; i < 32; i++) {
env->vregs[i][0].ll = cs->kvm_run->s.regs.vrs[i][0];
env->vregs[i][1].ll = cs->kvm_run->s.regs.vrs[i][1];
}
env->fpc = cs->kvm_run->s.regs.fpc;
} else {
r = kvm_vcpu_ioctl(cs, KVM_GET_FPU, &fpu);
if (r < 0) {
return r;
}
for (i = 0; i < 16; i++) {
get_freg(env, i)->ll = fpu.fprs[i];
}
env->fpc = fpu.fpc;
}
/* The prefix */
if (can_sync_regs(cs, KVM_SYNC_PREFIX)) {
env->psa = cs->kvm_run->s.regs.prefix;
}
if (can_sync_regs(cs, KVM_SYNC_ARCH0)) {
env->cputm = cs->kvm_run->s.regs.cputm;
env->ckc = cs->kvm_run->s.regs.ckc;
env->todpr = cs->kvm_run->s.regs.todpr;
env->gbea = cs->kvm_run->s.regs.gbea;
env->pp = cs->kvm_run->s.regs.pp;
} else {
/*
* These ONE_REGS are not protected by a capability. As they are only
* necessary for migration we just trace a possible error, but don't
* return with an error return code.
*/
kvm_get_one_reg(cs, KVM_REG_S390_CPU_TIMER, &env->cputm);
kvm_get_one_reg(cs, KVM_REG_S390_CLOCK_COMP, &env->ckc);
kvm_get_one_reg(cs, KVM_REG_S390_TODPR, &env->todpr);
kvm_get_one_reg(cs, KVM_REG_S390_GBEA, &env->gbea);
kvm_get_one_reg(cs, KVM_REG_S390_PP, &env->pp);
}
/* pfault parameters */
if (can_sync_regs(cs, KVM_SYNC_PFAULT)) {
env->pfault_token = cs->kvm_run->s.regs.pft;
env->pfault_select = cs->kvm_run->s.regs.pfs;
env->pfault_compare = cs->kvm_run->s.regs.pfc;
} else if (cap_async_pf) {
r = kvm_get_one_reg(cs, KVM_REG_S390_PFTOKEN, &env->pfault_token);
if (r < 0) {
return r;
}
r = kvm_get_one_reg(cs, KVM_REG_S390_PFCOMPARE, &env->pfault_compare);
if (r < 0) {
return r;
}
r = kvm_get_one_reg(cs, KVM_REG_S390_PFSELECT, &env->pfault_select);
if (r < 0) {
return r;
}
}
return 0;
}
int kvm_s390_get_clock(uint8_t *tod_high, uint64_t *tod_low)
{
int r;
struct kvm_device_attr attr = {
.group = KVM_S390_VM_TOD,
.attr = KVM_S390_VM_TOD_LOW,
.addr = (uint64_t)tod_low,
};
r = kvm_vm_ioctl(kvm_state, KVM_GET_DEVICE_ATTR, &attr);
if (r) {
return r;
}
attr.attr = KVM_S390_VM_TOD_HIGH;
attr.addr = (uint64_t)tod_high;
return kvm_vm_ioctl(kvm_state, KVM_GET_DEVICE_ATTR, &attr);
}
int kvm_s390_set_clock(uint8_t *tod_high, uint64_t *tod_low)
{
int r;
struct kvm_device_attr attr = {
.group = KVM_S390_VM_TOD,
.attr = KVM_S390_VM_TOD_LOW,
.addr = (uint64_t)tod_low,
};
r = kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
if (r) {
return r;
}
attr.attr = KVM_S390_VM_TOD_HIGH;
attr.addr = (uint64_t)tod_high;
return kvm_vm_ioctl(kvm_state, KVM_SET_DEVICE_ATTR, &attr);
}
/**
* kvm_s390_mem_op:
* @addr: the logical start address in guest memory
* @ar: the access register number
* @hostbuf: buffer in host memory. NULL = do only checks w/o copying
* @len: length that should be transferred
* @is_write: true = write, false = read
* Returns: 0 on success, non-zero if an exception or error occurred
*
* Use KVM ioctl to read/write from/to guest memory. An access exception
* is injected into the vCPU in case of translation errors.
*/
int kvm_s390_mem_op(S390CPU *cpu, vaddr addr, uint8_t ar, void *hostbuf,
int len, bool is_write)
{
struct kvm_s390_mem_op mem_op = {
.gaddr = addr,
.flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION,
.size = len,
.op = is_write ? KVM_S390_MEMOP_LOGICAL_WRITE
: KVM_S390_MEMOP_LOGICAL_READ,
.buf = (uint64_t)hostbuf,
.ar = ar,
};
int ret;
if (!cap_mem_op) {
return -ENOSYS;
}
if (!hostbuf) {
mem_op.flags |= KVM_S390_MEMOP_F_CHECK_ONLY;
}
ret = kvm_vcpu_ioctl(CPU(cpu), KVM_S390_MEM_OP, &mem_op);
if (ret < 0) {
error_printf("KVM_S390_MEM_OP failed: %s\n", strerror(-ret));
}
return ret;
}
/*
* Legacy layout for s390:
* Older S390 KVM requires the topmost vma of the RAM to be
* smaller than an system defined value, which is at least 256GB.
* Larger systems have larger values. We put the guest between
* the end of data segment (system break) and this value. We
* use 32GB as a base to have enough room for the system break
* to grow. We also have to use MAP parameters that avoid
* read-only mapping of guest pages.
*/
static void *legacy_s390_alloc(size_t size, uint64_t *align)
{
void *mem;
mem = mmap((void *) 0x800000000ULL, size,
PROT_EXEC|PROT_READ|PROT_WRITE,
MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
return mem == MAP_FAILED ? NULL : mem;
}
/* DIAG 501 is used for sw breakpoints */
static const uint8_t diag_501[] = {0x83, 0x24, 0x05, 0x01};
int kvm_arch_insert_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp)
{
if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn,
sizeof(diag_501), 0) ||
cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)diag_501,
sizeof(diag_501), 1)) {
return -EINVAL;
}
return 0;
}
int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp)
{
uint8_t t[sizeof(diag_501)];
if (cpu_memory_rw_debug(cs, bp->pc, t, sizeof(diag_501), 0)) {
return -EINVAL;
} else if (memcmp(t, diag_501, sizeof(diag_501))) {
return -EINVAL;
} else if (cpu_memory_rw_debug(cs, bp->pc, (uint8_t *)&bp->saved_insn,
sizeof(diag_501), 1)) {
return -EINVAL;
}
return 0;
}
static struct kvm_hw_breakpoint *find_hw_breakpoint(target_ulong addr,
int len, int type)
{
int n;
for (n = 0; n < nb_hw_breakpoints; n++) {
if (hw_breakpoints[n].addr == addr && hw_breakpoints[n].type == type &&
(hw_breakpoints[n].len == len || len == -1)) {
return &hw_breakpoints[n];
}
}
return NULL;
}
static int insert_hw_breakpoint(target_ulong addr, int len, int type)
{
int size;
if (find_hw_breakpoint(addr, len, type)) {
return -EEXIST;
}
size = (nb_hw_breakpoints + 1) * sizeof(struct kvm_hw_breakpoint);
if (!hw_breakpoints) {
nb_hw_breakpoints = 0;
hw_breakpoints = (struct kvm_hw_breakpoint *)g_try_malloc(size);
} else {
hw_breakpoints =
(struct kvm_hw_breakpoint *)g_try_realloc(hw_breakpoints, size);
}
if (!hw_breakpoints) {
nb_hw_breakpoints = 0;
return -ENOMEM;
}
hw_breakpoints[nb_hw_breakpoints].addr = addr;
hw_breakpoints[nb_hw_breakpoints].len = len;
hw_breakpoints[nb_hw_breakpoints].type = type;
nb_hw_breakpoints++;
return 0;
}
int kvm_arch_insert_hw_breakpoint(target_ulong addr,
target_ulong len, int type)
{
switch (type) {
case GDB_BREAKPOINT_HW:
type = KVM_HW_BP;
break;
case GDB_WATCHPOINT_WRITE:
if (len < 1) {
return -EINVAL;
}
type = KVM_HW_WP_WRITE;
break;
default:
return -ENOSYS;
}
return insert_hw_breakpoint(addr, len, type);
}
int kvm_arch_remove_hw_breakpoint(target_ulong addr,
target_ulong len, int type)
{
int size;
struct kvm_hw_breakpoint *bp = find_hw_breakpoint(addr, len, type);
if (bp == NULL) {
return -ENOENT;
}
nb_hw_breakpoints--;
if (nb_hw_breakpoints > 0) {
/*
* In order to trim the array, move the last element to the position to
* be removed - if necessary.
*/
if (bp != &hw_breakpoints[nb_hw_breakpoints]) {
*bp = hw_breakpoints[nb_hw_breakpoints];
}
size = nb_hw_breakpoints * sizeof(struct kvm_hw_breakpoint);
hw_breakpoints =
(struct kvm_hw_breakpoint *)g_realloc(hw_breakpoints, size);
} else {
g_free(hw_breakpoints);
hw_breakpoints = NULL;
}
return 0;
}
void kvm_arch_remove_all_hw_breakpoints(void)
{
nb_hw_breakpoints = 0;
g_free(hw_breakpoints);
hw_breakpoints = NULL;
}
void kvm_arch_update_guest_debug(CPUState *cpu, struct kvm_guest_debug *dbg)
{
int i;
if (nb_hw_breakpoints > 0) {
dbg->arch.nr_hw_bp = nb_hw_breakpoints;
dbg->arch.hw_bp = hw_breakpoints;
for (i = 0; i < nb_hw_breakpoints; ++i) {
hw_breakpoints[i].phys_addr = s390_cpu_get_phys_addr_debug(cpu,
hw_breakpoints[i].addr);
}
dbg->control |= KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP;
} else {
dbg->arch.nr_hw_bp = 0;
dbg->arch.hw_bp = NULL;
}
}
void kvm_arch_pre_run(CPUState *cpu, struct kvm_run *run)
{
}
MemTxAttrs kvm_arch_post_run(CPUState *cs, struct kvm_run *run)
{
return MEMTXATTRS_UNSPECIFIED;
}
int kvm_arch_process_async_events(CPUState *cs)
{
return cs->halted;
}
static int s390_kvm_irq_to_interrupt(struct kvm_s390_irq *irq,
struct kvm_s390_interrupt *interrupt)
{
int r = 0;
interrupt->type = irq->type;
switch (irq->type) {
case KVM_S390_INT_VIRTIO:
interrupt->parm = irq->u.ext.ext_params;
/* fall through */
case KVM_S390_INT_PFAULT_INIT:
case KVM_S390_INT_PFAULT_DONE:
interrupt->parm64 = irq->u.ext.ext_params2;
break;
case KVM_S390_PROGRAM_INT:
interrupt->parm = irq->u.pgm.code;
break;
case KVM_S390_SIGP_SET_PREFIX:
interrupt->parm = irq->u.prefix.address;
break;
case KVM_S390_INT_SERVICE:
interrupt->parm = irq->u.ext.ext_params;
break;
case KVM_S390_MCHK:
interrupt->parm = irq->u.mchk.cr14;
interrupt->parm64 = irq->u.mchk.mcic;
break;
case KVM_S390_INT_EXTERNAL_CALL:
interrupt->parm = irq->u.extcall.code;
break;
case KVM_S390_INT_EMERGENCY:
interrupt->parm = irq->u.emerg.code;
break;
case KVM_S390_SIGP_STOP:
case KVM_S390_RESTART:
break; /* These types have no parameters */
case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
interrupt->parm = irq->u.io.subchannel_id << 16;
interrupt->parm |= irq->u.io.subchannel_nr;
interrupt->parm64 = (uint64_t)irq->u.io.io_int_parm << 32;
interrupt->parm64 |= irq->u.io.io_int_word;
break;
default:
r = -EINVAL;
break;
}
return r;
}
static void inject_vcpu_irq_legacy(CPUState *cs, struct kvm_s390_irq *irq)
{
struct kvm_s390_interrupt kvmint = {};
int r;
r = s390_kvm_irq_to_interrupt(irq, &kvmint);
if (r < 0) {
fprintf(stderr, "%s called with bogus interrupt\n", __func__);
exit(1);
}
r = kvm_vcpu_ioctl(cs, KVM_S390_INTERRUPT, &kvmint);
if (r < 0) {
fprintf(stderr, "KVM failed to inject interrupt\n");
exit(1);
}
}
void kvm_s390_vcpu_interrupt(S390CPU *cpu, struct kvm_s390_irq *irq)
{
CPUState *cs = CPU(cpu);
int r;
if (cap_s390_irq) {
r = kvm_vcpu_ioctl(cs, KVM_S390_IRQ, irq);
if (!r) {
return;
}
error_report("KVM failed to inject interrupt %llx", irq->type);
exit(1);
}
inject_vcpu_irq_legacy(cs, irq);
}
static void __kvm_s390_floating_interrupt(struct kvm_s390_irq *irq)
{
struct kvm_s390_interrupt kvmint = {};
int r;
r = s390_kvm_irq_to_interrupt(irq, &kvmint);
if (r < 0) {
fprintf(stderr, "%s called with bogus interrupt\n", __func__);
exit(1);
}
r = kvm_vm_ioctl(kvm_state, KVM_S390_INTERRUPT, &kvmint);
if (r < 0) {
fprintf(stderr, "KVM failed to inject interrupt\n");
exit(1);
}
}
void kvm_s390_floating_interrupt(struct kvm_s390_irq *irq)
{
static bool use_flic = true;
int r;
if (use_flic) {
r = kvm_s390_inject_flic(irq);
if (r == -ENOSYS) {
use_flic = false;
}
if (!r) {
return;
}
}
__kvm_s390_floating_interrupt(irq);
}
void kvm_s390_virtio_irq(int config_change, uint64_t token)
{
struct kvm_s390_irq irq = {
.type = KVM_S390_INT_VIRTIO,
.u.ext.ext_params = config_change,
.u.ext.ext_params2 = token,
};
kvm_s390_floating_interrupt(&irq);
}
void kvm_s390_service_interrupt(uint32_t parm)
{
struct kvm_s390_irq irq = {
.type = KVM_S390_INT_SERVICE,
.u.ext.ext_params = parm,
};
kvm_s390_floating_interrupt(&irq);
}
static void enter_pgmcheck(S390CPU *cpu, uint16_t code)
{
struct kvm_s390_irq irq = {
.type = KVM_S390_PROGRAM_INT,
.u.pgm.code = code,
};
kvm_s390_vcpu_interrupt(cpu, &irq);
}
void kvm_s390_access_exception(S390CPU *cpu, uint16_t code, uint64_t te_code)
{
struct kvm_s390_irq irq = {
.type = KVM_S390_PROGRAM_INT,
.u.pgm.code = code,
.u.pgm.trans_exc_code = te_code,
.u.pgm.exc_access_id = te_code & 3,
};
kvm_s390_vcpu_interrupt(cpu, &irq);
}
static int kvm_sclp_service_call(S390CPU *cpu, struct kvm_run *run,
uint16_t ipbh0)
{
CPUS390XState *env = &cpu->env;
uint64_t sccb;
uint32_t code;
int r = 0;
cpu_synchronize_state(CPU(cpu));
sccb = env->regs[ipbh0 & 0xf];
code = env->regs[(ipbh0 & 0xf0) >> 4];
r = sclp_service_call(env, sccb, code);
if (r < 0) {
enter_pgmcheck(cpu, -r);
} else {
setcc(cpu, r);
}
return 0;
}
static int handle_b2(S390CPU *cpu, struct kvm_run *run, uint8_t ipa1)
{
CPUS390XState *env = &cpu->env;
int rc = 0;