forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
powerpc.c
2552 lines (2190 loc) · 57.6 KB
/
powerpc.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
// SPDX-License-Identifier: GPL-2.0-only
/*
*
* Copyright IBM Corp. 2007
*
* Authors: Hollis Blanchard <[email protected]>
* Christian Ehrhardt <[email protected]>
*/
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
#include <linux/vmalloc.h>
#include <linux/hrtimer.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/module.h>
#include <linux/irqbypass.h>
#include <linux/kvm_irqfd.h>
#include <linux/of.h>
#include <asm/cputable.h>
#include <linux/uaccess.h>
#include <asm/kvm_ppc.h>
#include <asm/cputhreads.h>
#include <asm/irqflags.h>
#include <asm/iommu.h>
#include <asm/switch_to.h>
#include <asm/xive.h>
#ifdef CONFIG_PPC_PSERIES
#include <asm/hvcall.h>
#include <asm/plpar_wrappers.h>
#endif
#include <asm/ultravisor.h>
#include "timing.h"
#include "irq.h"
#include "../mm/mmu_decl.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
struct kvmppc_ops *kvmppc_hv_ops;
EXPORT_SYMBOL_GPL(kvmppc_hv_ops);
struct kvmppc_ops *kvmppc_pr_ops;
EXPORT_SYMBOL_GPL(kvmppc_pr_ops);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
return !!(v->arch.pending_exceptions) || kvm_request_pending(v);
}
bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
{
return kvm_arch_vcpu_runnable(vcpu);
}
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
return false;
}
int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
return 1;
}
/*
* Common checks before entering the guest world. Call with interrupts
* disabled.
*
* returns:
*
* == 1 if we're ready to go into guest state
* <= 0 if we need to go back to the host with return value
*/
int kvmppc_prepare_to_enter(struct kvm_vcpu *vcpu)
{
int r;
WARN_ON(irqs_disabled());
hard_irq_disable();
while (true) {
if (need_resched()) {
local_irq_enable();
cond_resched();
hard_irq_disable();
continue;
}
if (signal_pending(current)) {
kvmppc_account_exit(vcpu, SIGNAL_EXITS);
vcpu->run->exit_reason = KVM_EXIT_INTR;
r = -EINTR;
break;
}
vcpu->mode = IN_GUEST_MODE;
/*
* Reading vcpu->requests must happen after setting vcpu->mode,
* so we don't miss a request because the requester sees
* OUTSIDE_GUEST_MODE and assumes we'll be checking requests
* before next entering the guest (and thus doesn't IPI).
* This also orders the write to mode from any reads
* to the page tables done while the VCPU is running.
* Please see the comment in kvm_flush_remote_tlbs.
*/
smp_mb();
if (kvm_request_pending(vcpu)) {
/* Make sure we process requests preemptable */
local_irq_enable();
trace_kvm_check_requests(vcpu);
r = kvmppc_core_check_requests(vcpu);
hard_irq_disable();
if (r > 0)
continue;
break;
}
if (kvmppc_core_prepare_to_enter(vcpu)) {
/* interrupts got enabled in between, so we
are back at square 1 */
continue;
}
guest_enter_irqoff();
return 1;
}
/* return to host */
local_irq_enable();
return r;
}
EXPORT_SYMBOL_GPL(kvmppc_prepare_to_enter);
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
static void kvmppc_swab_shared(struct kvm_vcpu *vcpu)
{
struct kvm_vcpu_arch_shared *shared = vcpu->arch.shared;
int i;
shared->sprg0 = swab64(shared->sprg0);
shared->sprg1 = swab64(shared->sprg1);
shared->sprg2 = swab64(shared->sprg2);
shared->sprg3 = swab64(shared->sprg3);
shared->srr0 = swab64(shared->srr0);
shared->srr1 = swab64(shared->srr1);
shared->dar = swab64(shared->dar);
shared->msr = swab64(shared->msr);
shared->dsisr = swab32(shared->dsisr);
shared->int_pending = swab32(shared->int_pending);
for (i = 0; i < ARRAY_SIZE(shared->sr); i++)
shared->sr[i] = swab32(shared->sr[i]);
}
#endif
int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
{
int nr = kvmppc_get_gpr(vcpu, 11);
int r;
unsigned long __maybe_unused param1 = kvmppc_get_gpr(vcpu, 3);
unsigned long __maybe_unused param2 = kvmppc_get_gpr(vcpu, 4);
unsigned long __maybe_unused param3 = kvmppc_get_gpr(vcpu, 5);
unsigned long __maybe_unused param4 = kvmppc_get_gpr(vcpu, 6);
unsigned long r2 = 0;
if (!(kvmppc_get_msr(vcpu) & MSR_SF)) {
/* 32 bit mode */
param1 &= 0xffffffff;
param2 &= 0xffffffff;
param3 &= 0xffffffff;
param4 &= 0xffffffff;
}
switch (nr) {
case KVM_HCALL_TOKEN(KVM_HC_PPC_MAP_MAGIC_PAGE):
{
#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_KVM_BOOK3S_PR_POSSIBLE)
/* Book3S can be little endian, find it out here */
int shared_big_endian = true;
if (vcpu->arch.intr_msr & MSR_LE)
shared_big_endian = false;
if (shared_big_endian != vcpu->arch.shared_big_endian)
kvmppc_swab_shared(vcpu);
vcpu->arch.shared_big_endian = shared_big_endian;
#endif
if (!(param2 & MAGIC_PAGE_FLAG_NOT_MAPPED_NX)) {
/*
* Older versions of the Linux magic page code had
* a bug where they would map their trampoline code
* NX. If that's the case, remove !PR NX capability.
*/
vcpu->arch.disable_kernel_nx = true;
kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
}
vcpu->arch.magic_page_pa = param1 & ~0xfffULL;
vcpu->arch.magic_page_ea = param2 & ~0xfffULL;
#ifdef CONFIG_PPC_64K_PAGES
/*
* Make sure our 4k magic page is in the same window of a 64k
* page within the guest and within the host's page.
*/
if ((vcpu->arch.magic_page_pa & 0xf000) !=
((ulong)vcpu->arch.shared & 0xf000)) {
void *old_shared = vcpu->arch.shared;
ulong shared = (ulong)vcpu->arch.shared;
void *new_shared;
shared &= PAGE_MASK;
shared |= vcpu->arch.magic_page_pa & 0xf000;
new_shared = (void*)shared;
memcpy(new_shared, old_shared, 0x1000);
vcpu->arch.shared = new_shared;
}
#endif
r2 = KVM_MAGIC_FEAT_SR | KVM_MAGIC_FEAT_MAS0_TO_SPRG7;
r = EV_SUCCESS;
break;
}
case KVM_HCALL_TOKEN(KVM_HC_FEATURES):
r = EV_SUCCESS;
#if defined(CONFIG_PPC_BOOK3S) || defined(CONFIG_KVM_E500V2)
r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
#endif
/* Second return value is in r4 */
break;
case EV_HCALL_TOKEN(EV_IDLE):
r = EV_SUCCESS;
kvm_vcpu_halt(vcpu);
kvm_clear_request(KVM_REQ_UNHALT, vcpu);
break;
default:
r = EV_UNIMPLEMENTED;
break;
}
kvmppc_set_gpr(vcpu, 4, r2);
return r;
}
EXPORT_SYMBOL_GPL(kvmppc_kvm_pv);
int kvmppc_sanity_check(struct kvm_vcpu *vcpu)
{
int r = false;
/* We have to know what CPU to virtualize */
if (!vcpu->arch.pvr)
goto out;
/* PAPR only works with book3s_64 */
if ((vcpu->arch.cpu_type != KVM_CPU_3S_64) && vcpu->arch.papr_enabled)
goto out;
/* HV KVM can only do PAPR mode for now */
if (!vcpu->arch.papr_enabled && is_kvmppc_hv_enabled(vcpu->kvm))
goto out;
#ifdef CONFIG_KVM_BOOKE_HV
if (!cpu_has_feature(CPU_FTR_EMB_HV))
goto out;
#endif
r = true;
out:
vcpu->arch.sane = r;
return r ? 0 : -EINVAL;
}
EXPORT_SYMBOL_GPL(kvmppc_sanity_check);
int kvmppc_emulate_mmio(struct kvm_vcpu *vcpu)
{
enum emulation_result er;
int r;
er = kvmppc_emulate_loadstore(vcpu);
switch (er) {
case EMULATE_DONE:
/* Future optimization: only reload non-volatiles if they were
* actually modified. */
r = RESUME_GUEST_NV;
break;
case EMULATE_AGAIN:
r = RESUME_GUEST;
break;
case EMULATE_DO_MMIO:
vcpu->run->exit_reason = KVM_EXIT_MMIO;
/* We must reload nonvolatiles because "update" load/store
* instructions modify register state. */
/* Future optimization: only reload non-volatiles if they were
* actually modified. */
r = RESUME_HOST_NV;
break;
case EMULATE_FAIL:
{
u32 last_inst;
kvmppc_get_last_inst(vcpu, INST_GENERIC, &last_inst);
kvm_debug_ratelimited("Guest access to device memory using unsupported instruction (opcode: %#08x)\n",
last_inst);
/*
* Injecting a Data Storage here is a bit more
* accurate since the instruction that caused the
* access could still be a valid one.
*/
if (!IS_ENABLED(CONFIG_BOOKE)) {
ulong dsisr = DSISR_BADACCESS;
if (vcpu->mmio_is_write)
dsisr |= DSISR_ISSTORE;
kvmppc_core_queue_data_storage(vcpu, vcpu->arch.vaddr_accessed, dsisr);
} else {
/*
* BookE does not send a SIGBUS on a bad
* fault, so use a Program interrupt instead
* to avoid a fault loop.
*/
kvmppc_core_queue_program(vcpu, 0);
}
r = RESUME_GUEST;
break;
}
default:
WARN_ON(1);
r = RESUME_GUEST;
}
return r;
}
EXPORT_SYMBOL_GPL(kvmppc_emulate_mmio);
int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
bool data)
{
ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
struct kvmppc_pte pte;
int r = -EINVAL;
vcpu->stat.st++;
if (vcpu->kvm->arch.kvm_ops && vcpu->kvm->arch.kvm_ops->store_to_eaddr)
r = vcpu->kvm->arch.kvm_ops->store_to_eaddr(vcpu, eaddr, ptr,
size);
if ((!r) || (r == -EAGAIN))
return r;
r = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
XLATE_WRITE, &pte);
if (r < 0)
return r;
*eaddr = pte.raddr;
if (!pte.may_write)
return -EPERM;
/* Magic page override */
if (kvmppc_supports_magic_page(vcpu) && mp_pa &&
((pte.raddr & KVM_PAM & PAGE_MASK) == mp_pa) &&
!(kvmppc_get_msr(vcpu) & MSR_PR)) {
void *magic = vcpu->arch.shared;
magic += pte.eaddr & 0xfff;
memcpy(magic, ptr, size);
return EMULATE_DONE;
}
if (kvm_write_guest(vcpu->kvm, pte.raddr, ptr, size))
return EMULATE_DO_MMIO;
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvmppc_st);
int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
bool data)
{
ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
struct kvmppc_pte pte;
int rc = -EINVAL;
vcpu->stat.ld++;
if (vcpu->kvm->arch.kvm_ops && vcpu->kvm->arch.kvm_ops->load_from_eaddr)
rc = vcpu->kvm->arch.kvm_ops->load_from_eaddr(vcpu, eaddr, ptr,
size);
if ((!rc) || (rc == -EAGAIN))
return rc;
rc = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
XLATE_READ, &pte);
if (rc)
return rc;
*eaddr = pte.raddr;
if (!pte.may_read)
return -EPERM;
if (!data && !pte.may_execute)
return -ENOEXEC;
/* Magic page override */
if (kvmppc_supports_magic_page(vcpu) && mp_pa &&
((pte.raddr & KVM_PAM & PAGE_MASK) == mp_pa) &&
!(kvmppc_get_msr(vcpu) & MSR_PR)) {
void *magic = vcpu->arch.shared;
magic += pte.eaddr & 0xfff;
memcpy(ptr, magic, size);
return EMULATE_DONE;
}
kvm_vcpu_srcu_read_lock(vcpu);
rc = kvm_read_guest(vcpu->kvm, pte.raddr, ptr, size);
kvm_vcpu_srcu_read_unlock(vcpu);
if (rc)
return EMULATE_DO_MMIO;
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvmppc_ld);
int kvm_arch_hardware_enable(void)
{
return 0;
}
int kvm_arch_hardware_setup(void *opaque)
{
return 0;
}
int kvm_arch_check_processor_compat(void *opaque)
{
return kvmppc_core_check_processor_compat();
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
struct kvmppc_ops *kvm_ops = NULL;
int r;
/*
* if we have both HV and PR enabled, default is HV
*/
if (type == 0) {
if (kvmppc_hv_ops)
kvm_ops = kvmppc_hv_ops;
else
kvm_ops = kvmppc_pr_ops;
if (!kvm_ops)
goto err_out;
} else if (type == KVM_VM_PPC_HV) {
if (!kvmppc_hv_ops)
goto err_out;
kvm_ops = kvmppc_hv_ops;
} else if (type == KVM_VM_PPC_PR) {
if (!kvmppc_pr_ops)
goto err_out;
kvm_ops = kvmppc_pr_ops;
} else
goto err_out;
if (!try_module_get(kvm_ops->owner))
return -ENOENT;
kvm->arch.kvm_ops = kvm_ops;
r = kvmppc_core_init_vm(kvm);
if (r)
module_put(kvm_ops->owner);
return r;
err_out:
return -EINVAL;
}
void kvm_arch_destroy_vm(struct kvm *kvm)
{
#ifdef CONFIG_KVM_XICS
/*
* We call kick_all_cpus_sync() to ensure that all
* CPUs have executed any pending IPIs before we
* continue and free VCPUs structures below.
*/
if (is_kvmppc_hv_enabled(kvm))
kick_all_cpus_sync();
#endif
kvm_destroy_vcpus(kvm);
mutex_lock(&kvm->lock);
kvmppc_core_destroy_vm(kvm);
mutex_unlock(&kvm->lock);
/* drop the module reference */
module_put(kvm->arch.kvm_ops->owner);
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
/* Assume we're using HV mode when the HV module is loaded */
int hv_enabled = kvmppc_hv_ops ? 1 : 0;
if (kvm) {
/*
* Hooray - we know which VM type we're running on. Depend on
* that rather than the guess above.
*/
hv_enabled = is_kvmppc_hv_enabled(kvm);
}
switch (ext) {
#ifdef CONFIG_BOOKE
case KVM_CAP_PPC_BOOKE_SREGS:
case KVM_CAP_PPC_BOOKE_WATCHDOG:
case KVM_CAP_PPC_EPR:
#else
case KVM_CAP_PPC_SEGSTATE:
case KVM_CAP_PPC_HIOR:
case KVM_CAP_PPC_PAPR:
#endif
case KVM_CAP_PPC_UNSET_IRQ:
case KVM_CAP_PPC_IRQ_LEVEL:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_ONE_REG:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_IMMEDIATE_EXIT:
case KVM_CAP_SET_GUEST_DEBUG:
r = 1;
break;
case KVM_CAP_PPC_GUEST_DEBUG_SSTEP:
case KVM_CAP_PPC_PAIRED_SINGLES:
case KVM_CAP_PPC_OSI:
case KVM_CAP_PPC_GET_PVINFO:
#if defined(CONFIG_KVM_E500V2) || defined(CONFIG_KVM_E500MC)
case KVM_CAP_SW_TLB:
#endif
/* We support this only for PR */
r = !hv_enabled;
break;
#ifdef CONFIG_KVM_MPIC
case KVM_CAP_IRQ_MPIC:
r = 1;
break;
#endif
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_SPAPR_TCE:
case KVM_CAP_SPAPR_TCE_64:
r = 1;
break;
case KVM_CAP_SPAPR_TCE_VFIO:
r = !!cpu_has_feature(CPU_FTR_HVMODE);
break;
case KVM_CAP_PPC_RTAS:
case KVM_CAP_PPC_FIXUP_HCALL:
case KVM_CAP_PPC_ENABLE_HCALL:
#ifdef CONFIG_KVM_XICS
case KVM_CAP_IRQ_XICS:
#endif
case KVM_CAP_PPC_GET_CPU_CHAR:
r = 1;
break;
#ifdef CONFIG_KVM_XIVE
case KVM_CAP_PPC_IRQ_XIVE:
/*
* We need XIVE to be enabled on the platform (implies
* a POWER9 processor) and the PowerNV platform, as
* nested is not yet supported.
*/
r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE) &&
kvmppc_xive_native_supported();
break;
#endif
case KVM_CAP_PPC_ALLOC_HTAB:
r = hv_enabled;
break;
#endif /* CONFIG_PPC_BOOK3S_64 */
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
case KVM_CAP_PPC_SMT:
r = 0;
if (kvm) {
if (kvm->arch.emul_smt_mode > 1)
r = kvm->arch.emul_smt_mode;
else
r = kvm->arch.smt_mode;
} else if (hv_enabled) {
if (cpu_has_feature(CPU_FTR_ARCH_300))
r = 1;
else
r = threads_per_subcore;
}
break;
case KVM_CAP_PPC_SMT_POSSIBLE:
r = 1;
if (hv_enabled) {
if (!cpu_has_feature(CPU_FTR_ARCH_300))
r = ((threads_per_subcore << 1) - 1);
else
/* P9 can emulate dbells, so allow any mode */
r = 8 | 4 | 2 | 1;
}
break;
case KVM_CAP_PPC_RMA:
r = 0;
break;
case KVM_CAP_PPC_HWRNG:
r = kvmppc_hwrng_present();
break;
case KVM_CAP_PPC_MMU_RADIX:
r = !!(hv_enabled && radix_enabled());
break;
case KVM_CAP_PPC_MMU_HASH_V3:
r = !!(hv_enabled && kvmppc_hv_ops->hash_v3_possible &&
kvmppc_hv_ops->hash_v3_possible());
break;
case KVM_CAP_PPC_NESTED_HV:
r = !!(hv_enabled && kvmppc_hv_ops->enable_nested &&
!kvmppc_hv_ops->enable_nested(NULL));
break;
#endif
case KVM_CAP_SYNC_MMU:
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
r = hv_enabled;
#elif defined(KVM_ARCH_WANT_MMU_NOTIFIER)
r = 1;
#else
r = 0;
#endif
break;
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
case KVM_CAP_PPC_HTAB_FD:
r = hv_enabled;
break;
#endif
case KVM_CAP_NR_VCPUS:
/*
* Recommending a number of CPUs is somewhat arbitrary; we
* return the number of present CPUs for -HV (since a host
* will have secondary threads "offline"), and for other KVM
* implementations just count online CPUs.
*/
if (hv_enabled)
r = min_t(unsigned int, num_present_cpus(), KVM_MAX_VCPUS);
else
r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS);
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
case KVM_CAP_MAX_VCPU_ID:
r = KVM_MAX_VCPU_IDS;
break;
#ifdef CONFIG_PPC_BOOK3S_64
case KVM_CAP_PPC_GET_SMMU_INFO:
r = 1;
break;
case KVM_CAP_SPAPR_MULTITCE:
r = 1;
break;
case KVM_CAP_SPAPR_RESIZE_HPT:
r = !!hv_enabled;
break;
#endif
#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
case KVM_CAP_PPC_FWNMI:
r = hv_enabled;
break;
#endif
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
case KVM_CAP_PPC_HTM:
r = !!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
(hv_enabled && cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
break;
#endif
#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
case KVM_CAP_PPC_SECURE_GUEST:
r = hv_enabled && kvmppc_hv_ops->enable_svm &&
!kvmppc_hv_ops->enable_svm(NULL);
break;
case KVM_CAP_PPC_DAWR1:
r = !!(hv_enabled && kvmppc_hv_ops->enable_dawr1 &&
!kvmppc_hv_ops->enable_dawr1(NULL));
break;
case KVM_CAP_PPC_RPT_INVALIDATE:
r = 1;
break;
#endif
case KVM_CAP_PPC_AIL_MODE_3:
r = 0;
/*
* KVM PR, POWER7, and some POWER9s don't support AIL=3 mode.
* The POWER9s can support it if the guest runs in hash mode,
* but QEMU doesn't necessarily query the capability in time.
*/
if (hv_enabled) {
if (kvmhv_on_pseries()) {
if (pseries_reloc_on_exception())
r = 1;
} else if (cpu_has_feature(CPU_FTR_ARCH_207S) &&
!cpu_has_feature(CPU_FTR_P9_RADIX_PREFETCH_BUG)) {
r = 1;
}
}
break;
default:
r = 0;
break;
}
return r;
}
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
return -EINVAL;
}
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot)
{
kvmppc_core_free_memslot(kvm, slot);
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
return kvmppc_core_prepare_memory_region(kvm, old, new, change);
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
kvmppc_core_commit_memory_region(kvm, old, new, change);
}
void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot)
{
kvmppc_core_flush_memslot(kvm, slot);
}
int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
{
return 0;
}
static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
{
struct kvm_vcpu *vcpu;
vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
kvmppc_decrementer_func(vcpu);
return HRTIMER_NORESTART;
}
int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
{
int err;
hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
vcpu->arch.dec_expires = get_tb();
#ifdef CONFIG_KVM_EXIT_TIMING
mutex_init(&vcpu->arch.exit_timing_lock);
#endif
err = kvmppc_subarch_vcpu_init(vcpu);
if (err)
return err;
err = kvmppc_core_vcpu_create(vcpu);
if (err)
goto out_vcpu_uninit;
rcuwait_init(&vcpu->arch.wait);
vcpu->arch.waitp = &vcpu->arch.wait;
return 0;
out_vcpu_uninit:
kvmppc_subarch_vcpu_uninit(vcpu);
return err;
}
void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
/* Make sure we're not using the vcpu anymore */
hrtimer_cancel(&vcpu->arch.dec_timer);
switch (vcpu->arch.irq_type) {
case KVMPPC_IRQ_MPIC:
kvmppc_mpic_disconnect_vcpu(vcpu->arch.mpic, vcpu);
break;
case KVMPPC_IRQ_XICS:
if (xics_on_xive())
kvmppc_xive_cleanup_vcpu(vcpu);
else
kvmppc_xics_free_icp(vcpu);
break;
case KVMPPC_IRQ_XIVE:
kvmppc_xive_native_cleanup_vcpu(vcpu);
break;
}
kvmppc_core_vcpu_free(vcpu);
kvmppc_subarch_vcpu_uninit(vcpu);
}
int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
return kvmppc_core_pending_dec(vcpu);
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
#ifdef CONFIG_BOOKE
/*
* vrsave (formerly usprg0) isn't used by Linux, but may
* be used by the guest.
*
* On non-booke this is associated with Altivec and
* is handled by code in book3s.c.
*/
mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
#endif
kvmppc_core_vcpu_load(vcpu, cpu);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
kvmppc_core_vcpu_put(vcpu);
#ifdef CONFIG_BOOKE
vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
#endif
}
/*
* irq_bypass_add_producer and irq_bypass_del_producer are only
* useful if the architecture supports PCI passthrough.
* irq_bypass_stop and irq_bypass_start are not needed and so
* kvm_ops are not defined for them.
*/
bool kvm_arch_has_irq_bypass(void)
{
return ((kvmppc_hv_ops && kvmppc_hv_ops->irq_bypass_add_producer) ||
(kvmppc_pr_ops && kvmppc_pr_ops->irq_bypass_add_producer));
}
int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
struct kvm *kvm = irqfd->kvm;
if (kvm->arch.kvm_ops->irq_bypass_add_producer)
return kvm->arch.kvm_ops->irq_bypass_add_producer(cons, prod);
return 0;
}
void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
struct irq_bypass_producer *prod)
{
struct kvm_kernel_irqfd *irqfd =
container_of(cons, struct kvm_kernel_irqfd, consumer);
struct kvm *kvm = irqfd->kvm;
if (kvm->arch.kvm_ops->irq_bypass_del_producer)
kvm->arch.kvm_ops->irq_bypass_del_producer(cons, prod);
}
#ifdef CONFIG_VSX
static inline int kvmppc_get_vsr_dword_offset(int index)
{
int offset;
if ((index != 0) && (index != 1))
return -1;
#ifdef __BIG_ENDIAN
offset = index;
#else
offset = 1 - index;
#endif
return offset;
}
static inline int kvmppc_get_vsr_word_offset(int index)
{
int offset;
if ((index > 3) || (index < 0))
return -1;
#ifdef __BIG_ENDIAN
offset = index;
#else
offset = 3 - index;
#endif
return offset;
}
static inline void kvmppc_set_vsr_dword(struct kvm_vcpu *vcpu,
u64 gpr)
{
union kvmppc_one_reg val;
int offset = kvmppc_get_vsr_dword_offset(vcpu->arch.mmio_vsx_offset);
int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
if (offset == -1)
return;
if (index >= 32) {
val.vval = VCPU_VSX_VR(vcpu, index - 32);
val.vsxval[offset] = gpr;
VCPU_VSX_VR(vcpu, index - 32) = val.vval;
} else {
VCPU_VSX_FPR(vcpu, index, offset) = gpr;
}
}
static inline void kvmppc_set_vsr_dword_dump(struct kvm_vcpu *vcpu,
u64 gpr)
{
union kvmppc_one_reg val;
int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
if (index >= 32) {
val.vval = VCPU_VSX_VR(vcpu, index - 32);
val.vsxval[0] = gpr;
val.vsxval[1] = gpr;
VCPU_VSX_VR(vcpu, index - 32) = val.vval;
} else {
VCPU_VSX_FPR(vcpu, index, 0) = gpr;
VCPU_VSX_FPR(vcpu, index, 1) = gpr;
}
}
static inline void kvmppc_set_vsr_word_dump(struct kvm_vcpu *vcpu,
u32 gpr)
{
union kvmppc_one_reg val;
int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
if (index >= 32) {
val.vsx32val[0] = gpr;
val.vsx32val[1] = gpr;
val.vsx32val[2] = gpr;
val.vsx32val[3] = gpr;
VCPU_VSX_VR(vcpu, index - 32) = val.vval;
} else {
val.vsx32val[0] = gpr;
val.vsx32val[1] = gpr;
VCPU_VSX_FPR(vcpu, index, 0) = val.vsxval[0];
VCPU_VSX_FPR(vcpu, index, 1) = val.vsxval[0];
}
}
static inline void kvmppc_set_vsr_word(struct kvm_vcpu *vcpu,
u32 gpr32)
{
union kvmppc_one_reg val;
int offset = kvmppc_get_vsr_word_offset(vcpu->arch.mmio_vsx_offset);
int index = vcpu->arch.io_gpr & KVM_MMIO_REG_MASK;
int dword_offset, word_offset;
if (offset == -1)
return;