1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2017-2019, IBM Corporation.
*/
#define pr_fmt(fmt) "xive-kvm: " fmt
#include <linux/kernel.h>
#include <linux/kvm_host.h>
#include <linux/err.h>
#include <linux/gfp.h>
#include <linux/spinlock.h>
#include <linux/delay.h>
#include <linux/file.h>
#include <linux/irqdomain.h>
#include <asm/uaccess.h>
#include <asm/kvm_book3s.h>
#include <asm/kvm_ppc.h>
#include <asm/hvcall.h>
#include <asm/xive.h>
#include <asm/xive-regs.h>
#include <asm/debug.h>
#include <asm/opal.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include "book3s_xive.h"
static u8 xive_vm_esb_load(struct xive_irq_data *xd, u32 offset)
{
u64 val;
/*
* The KVM XIVE native device does not use the XIVE_ESB_SET_PQ_10
* load operation, so there is no need to enforce load-after-store
* ordering.
*/
val = in_be64(xd->eoi_mmio + offset);
return (u8)val;
}
static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
{
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
struct xive_q *q = &xc->queues[prio];
xive_native_disable_queue(xc->vp_id, q, prio);
if (q->qpage) {
put_page(virt_to_page(q->qpage));
q->qpage = NULL;
}
}
static int kvmppc_xive_native_configure_queue(u32 vp_id, struct xive_q *q,
u8 prio, __be32 *qpage,
u32 order, bool can_escalate)
{
int rc;
__be32 *qpage_prev = q->qpage;
rc = xive_native_configure_queue(vp_id, q, prio, qpage, order,
can_escalate);
if (rc)
return rc;
if (qpage_prev)
put_page(virt_to_page(qpage_prev));
return rc;
}
void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
{
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
int i;
if (!kvmppc_xive_enabled(vcpu))
return;
if (!xc)
return;
pr_devel("native_cleanup_vcpu(cpu=%d)\n", xc->server_num);
/* Ensure no interrupt is still routed to that VP */
xc->valid = false;
kvmppc_xive_disable_vcpu_interrupts(vcpu);
/* Free escalations */
for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
/* Free the escalation irq */
if (xc->esc_virq[i]) {
if (kvmppc_xive_has_single_escalation(xc->xive))
xive_cleanup_single_escalation(vcpu, xc->esc_virq[i]);
free_irq(xc->esc_virq[i], vcpu);
irq_dispose_mapping(xc->esc_virq[i]);
kfree(xc->esc_virq_names[i]);
xc->esc_virq[i] = 0;
}
}
/* Disable the VP */
xive_native_disable_vp(xc->vp_id);
/* Clear the cam word so guest entry won't try to push context */
vcpu->arch.xive_cam_word = 0;
/* Free the queues */
for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
kvmppc_xive_native_cleanup_queue(vcpu, i);
}
/* Free the VP */
kfree(xc);
/* Cleanup the vcpu */
vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
vcpu->arch.xive_vcpu = NULL;
}
int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
struct kvm_vcpu *vcpu, u32 server_num)
{
struct kvmppc_xive *xive = dev->private;
struct kvmppc_xive_vcpu *xc = NULL;
int rc;
u32 vp_id;
pr_devel("native_connect_vcpu(server=%d)\n", server_num);
if (dev->ops != &kvm_xive_native_ops) {
pr_devel("Wrong ops !\n");
return -EPERM;
}
if (xive->kvm != vcpu->kvm)
return -EPERM;
if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
return -EBUSY;
mutex_lock(&xive->lock);
rc = kvmppc_xive_compute_vp_id(xive, server_num, &vp_id);
if (rc)
goto bail;
xc = kzalloc(sizeof(*xc), GFP_KERNEL);
if (!xc) {
rc = -ENOMEM;
goto bail;
}
vcpu->arch.xive_vcpu = xc;
xc->xive = xive;
xc->vcpu = vcpu;
xc->server_num = server_num;
xc->vp_id = vp_id;
xc->valid = true;
vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
rc = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
if (rc) {
pr_err("Failed to get VP info from OPAL: %d\n", rc);
goto bail;
}
if (!kvmppc_xive_check_save_restore(vcpu)) {
pr_err("inconsistent save-restore setup for VCPU %d\n", server_num);
rc = -EIO;
goto bail;
}
/*
* Enable the VP first as the single escalation mode will
* affect escalation interrupts numbering
*/
rc = xive_native_enable_vp(xc->vp_id, kvmppc_xive_has_single_escalation(xive));
if (rc) {
pr_err("Failed to enable VP in OPAL: %d\n", rc);
goto bail;
}
/* Configure VCPU fields for use by assembly push/pull */
vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
/* TODO: reset all queues to a clean state ? */
bail:
mutex_unlock(&xive->lock);
if (rc)
kvmppc_xive_native_cleanup_vcpu(vcpu);
return rc;
}
/*
* Device passthrough support
*/
static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq)
{
struct kvmppc_xive *xive = kvm->arch.xive;
pgoff_t esb_pgoff = KVM_XIVE_ESB_PAGE_OFFSET + irq * 2;
if (irq >= KVMPPC_XIVE_NR_IRQS)
return -EINVAL;
/*
* Clear the ESB pages of the IRQ number being mapped (or
* unmapped) into the guest and let the VM fault handler
* repopulate with the appropriate ESB pages (device or IC)
*/
pr_debug("clearing esb pages for girq 0x%lx\n", irq);
mutex_lock(&xive->mapping_lock);
if (xive->mapping)
unmap_mapping_range(xive->mapping,
esb_pgoff << PAGE_SHIFT,
2ull << PAGE_SHIFT, 1);
mutex_unlock(&xive->mapping_lock);
return 0;
}
static struct kvmppc_xive_ops kvmppc_xive_native_ops = {
.reset_mapped = kvmppc_xive_native_reset_mapped,
};
static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct kvm_device *dev = vma->vm_file->private_data;
struct kvmppc_xive *xive = dev->private;
struct kvmppc_xive_src_block *sb;
struct kvmppc_xive_irq_state *state;
struct xive_irq_data *xd;
u32 hw_num;
u16 src;
u64 page;
unsigned long irq;
u64 page_offset;
/*
* Linux/KVM uses a two pages ESB setting, one for trigger and
* one for EOI
*/
page_offset = vmf->pgoff - vma->vm_pgoff;
irq = page_offset / 2;
sb = kvmppc_xive_find_source(xive, irq, &src);
if (!sb) {
pr_devel("%s: source %lx not found !\n", __func__, irq);
return VM_FAULT_SIGBUS;
}
state = &sb->irq_state[src];
/* Some sanity checking */
if (!state->valid) {
pr_devel("%s: source %lx invalid !\n", __func__, irq);
return VM_FAULT_SIGBUS;
}
kvmppc_xive_select_irq(state, &hw_num, &xd);
arch_spin_lock(&sb->lock);
/*
* first/even page is for trigger
* second/odd page is for EOI and management.
*/
page = page_offset % 2 ? xd->eoi_page : xd->trig_page;
arch_spin_unlock(&sb->lock);
if (WARN_ON(!page)) {
pr_err("%s: accessing invalid ESB page for source %lx !\n",
__func__, irq);
return VM_FAULT_SIGBUS;
}
vmf_insert_pfn(vma, vmf->address, page >> PAGE_SHIFT);
return VM_FAULT_NOPAGE;
}
static const struct vm_operations_struct xive_native_esb_vmops = {
.fault = xive_native_esb_fault,
};
static vm_fault_t xive_native_tima_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
switch (vmf->pgoff - vma->vm_pgoff) {
case 0: /* HW - forbid access */
case 1: /* HV - forbid access */
return VM_FAULT_SIGBUS;
case 2: /* OS */
vmf_insert_pfn(vma, vmf->address, xive_tima_os >> PAGE_SHIFT);
return VM_FAULT_NOPAGE;
case 3: /* USER - TODO */
default:
return VM_FAULT_SIGBUS;
}
}
static const struct vm_operations_struct xive_native_tima_vmops = {
.fault = xive_native_tima_fault,
};
static int kvmppc_xive_native_mmap(struct kvm_device *dev,
struct vm_area_struct *vma)
{
struct kvmppc_xive *xive = dev->private;
/* We only allow mappings at fixed offset for now */
if (vma->vm_pgoff == KVM_XIVE_TIMA_PAGE_OFFSET) {
if (vma_pages(vma) > 4)
return -EINVAL;
vma->vm_ops = &xive_native_tima_vmops;
} else if (vma->vm_pgoff == KVM_XIVE_ESB_PAGE_OFFSET) {
if (vma_pages(vma) > KVMPPC_XIVE_NR_IRQS * 2)
return -EINVAL;
vma->vm_ops = &xive_native_esb_vmops;
} else {
return -EINVAL;
}
vma->vm_flags |= VM_IO | VM_PFNMAP;
vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
/*
* Grab the KVM device file address_space to be able to clear
* the ESB pages mapping when a device is passed-through into
* the guest.
*/
xive->mapping = vma->vm_file->f_mapping;
return 0;
}
static int kvmppc_xive_native_set_source(struct kvmppc_xive *xive, long irq,
u64 addr)
{
struct kvmppc_xive_src_block *sb;
struct kvmppc_xive_irq_state *state;
u64 __user *ubufp = (u64 __user *) addr;
u64 val;
u16 idx;
int rc;
pr_devel("%s irq=0x%lx\n", __func__, irq);
if (irq < KVMPPC_XIVE_FIRST_IRQ || irq >= KVMPPC_XIVE_NR_IRQS)
return -E2BIG;
sb = kvmppc_xive_find_source(xive, irq, &idx);
if (!sb) {
pr_debug("No source, creating source block...\n");
sb = kvmppc_xive_create_src_block(xive, irq);
if (!sb) {
pr_err("Failed to create block...\n");
return -ENOMEM;
}
}
state = &sb->irq_state[idx];
if (get_user(val, ubufp)) {
pr_err("fault getting user info !\n");
return -EFAULT;
}
arch_spin_lock(&sb->lock);
/*
* If the source doesn't already have an IPI, allocate
* one and get the corresponding data
*/
if (!state->ipi_number) {
state->ipi_number = xive_native_alloc_irq();
if (state->ipi_number == 0) {
pr_err("Failed to allocate IRQ !\n");
rc = -ENXIO;
goto unlock;
}
xive_native_populate_irq_data(state->ipi_number,
&state->ipi_data);
pr_debug("%s allocated hw_irq=0x%x for irq=0x%lx\n", __func__,
state->ipi_number, irq);
}
/* Restore LSI state */
if (val & KVM_XIVE_LEVEL_SENSITIVE) {
state->lsi = true;
if (val & KVM_XIVE_LEVEL_ASSERTED)
state->asserted = true;
pr_devel(" LSI ! Asserted=%d\n", state->asserted);
}
/* Mask IRQ to start with */
state->act_server = 0;
state->act_priority = MASKED;
xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
/* Increment the number of valid sources and mark this one valid */
if (!state->valid)
xive->src_count++;
state->valid = true;
rc = 0;
unlock:
arch_spin_unlock(&sb->lock);
return rc;
}
static int kvmppc_xive_native_update_source_config(struct kvmppc_xive *xive,
struct kvmppc_xive_src_block *sb,
struct kvmppc_xive_irq_state *state,
u32 server, u8 priority, bool masked,
u32 eisn)
{
struct kvm *kvm = xive->kvm;
u32 hw_num;
int rc = 0;
arch_spin_lock(&sb->lock);
if (state->act_server == server && state->act_priority == priority &&
state->eisn == eisn)
goto unlock;
pr_devel("new_act_prio=%d new_act_server=%d mask=%d act_server=%d act_prio=%d\n",
priority, server, masked, state->act_server,
state->act_priority);
kvmppc_xive_select_irq(state, &hw_num, NULL);
if (priority != MASKED && !masked) {
rc = kvmppc_xive_select_target(kvm, &server, priority);
if (rc)
goto unlock;
state->act_priority = priority;
state->act_server = server;
state->eisn = eisn;
rc = xive_native_configure_irq(hw_num,
kvmppc_xive_vp(xive, server),
priority, eisn);
} else {
state->act_priority = MASKED;
state->act_server = 0;
state->eisn = 0;
rc = xive_native_configure_irq(hw_num, 0, MASKED, 0);
}
unlock:
arch_spin_unlock(&sb->lock);
return rc;
}
static int kvmppc_xive_native_set_source_config(struct kvmppc_xive *xive,
long irq, u64 addr)
{
struct kvmppc_xive_src_block *sb;
struct kvmppc_xive_irq_state *state;
u64 __user *ubufp = (u64 __user *) addr;
u16 src;
u64 kvm_cfg;
u32 server;
u8 priority;
bool masked;
u32 eisn;
sb = kvmppc_xive_find_source(xive, irq, &src);
if (!sb)
return -ENOENT;
state = &sb->irq_state[src];
if (!state->valid)
return -EINVAL;
if (get_user(kvm_cfg, ubufp))
return -EFAULT;
pr_devel("%s irq=0x%lx cfg=%016llx\n", __func__, irq, kvm_cfg);
priority = (kvm_cfg & KVM_XIVE_SOURCE_PRIORITY_MASK) >>
KVM_XIVE_SOURCE_PRIORITY_SHIFT;
server = (kvm_cfg & KVM_XIVE_SOURCE_SERVER_MASK) >>
KVM_XIVE_SOURCE_SERVER_SHIFT;
masked = (kvm_cfg & KVM_XIVE_SOURCE_MASKED_MASK) >>
KVM_XIVE_SOURCE_MASKED_SHIFT;
eisn = (kvm_cfg & KVM_XIVE_SOURCE_EISN_MASK) >>
KVM_XIVE_SOURCE_EISN_SHIFT;
if (priority != xive_prio_from_guest(priority)) {
pr_err("invalid priority for queue %d for VCPU %d\n",
priority, server);
return -EINVAL;
}
return kvmppc_xive_native_update_source_config(xive, sb, state, server,
priority, masked, eisn);
}
static int kvmppc_xive_native_sync_source(struct kvmppc_xive *xive,
long irq, u64 addr)
{
struct kvmppc_xive_src_block *sb;
struct kvmppc_xive_irq_state *state;
struct xive_irq_data *xd;
u32 hw_num;
u16 src;
int rc = 0;
pr_devel("%s irq=0x%lx", __func__, irq);
sb = kvmppc_xive_find_source(xive, irq, &src);
if (!sb)
return -ENOENT;
state = &sb->irq_state[src];
rc = -EINVAL;
arch_spin_lock(&sb->lock);
if (state->valid) {
kvmppc_xive_select_irq(state, &hw_num, &xd);
xive_native_sync_source(hw_num);
rc = 0;
}
arch_spin_unlock(&sb->lock);
return rc;
}
static int xive_native_validate_queue_size(u32 qshift)
{
/*
* We only support 64K pages for the moment. This is also
* advertised in the DT property "ibm,xive-eq-sizes"
*/
switch (qshift) {
case 0: /* EQ reset */
case 16:
return 0;
case 12:
case 21:
case 24:
default:
return -EINVAL;
}
}
static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
long eq_idx, u64 addr)
{
struct kvm *kvm = xive->kvm;
struct kvm_vcpu *vcpu;
struct kvmppc_xive_vcpu *xc;
void __user *ubufp = (void __user *) addr;
u32 server;
u8 priority;
struct kvm_ppc_xive_eq kvm_eq;
int rc;
__be32 *qaddr = 0;
struct page *page;
struct xive_q *q;
gfn_t gfn;
unsigned long page_size;
int srcu_idx;
/*
* Demangle priority/server tuple from the EQ identifier
*/
priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
KVM_XIVE_EQ_PRIORITY_SHIFT;
server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
KVM_XIVE_EQ_SERVER_SHIFT;
if (copy_from_user(&kvm_eq, ubufp, sizeof(kvm_eq)))
return -EFAULT;
vcpu = kvmppc_xive_find_server(kvm, server);
if (!vcpu) {
pr_err("Can't find server %d\n", server);
return -ENOENT;
}
xc = vcpu->arch.xive_vcpu;
if (priority != xive_prio_from_guest(priority)) {
pr_err("Trying to restore invalid queue %d for VCPU %d\n",
priority, server);
return -EINVAL;
}
q = &xc->queues[priority];
pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
__func__, server, priority, kvm_eq.flags,
kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
/* reset queue and disable queueing */
if (!kvm_eq.qshift) {
q->guest_qaddr = 0;
q->guest_qshift = 0;
rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
NULL, 0, true);
if (rc) {
pr_err("Failed to reset queue %d for VCPU %d: %d\n",
priority, xc->server_num, rc);
return rc;
}
return 0;
}
/*
* sPAPR specifies a "Unconditional Notify (n) flag" for the
* H_INT_SET_QUEUE_CONFIG hcall which forces notification
* without using the coalescing mechanisms provided by the
* XIVE END ESBs. This is required on KVM as notification
* using the END ESBs is not supported.
*/
if (kvm_eq.flags != KVM_XIVE_EQ_ALWAYS_NOTIFY) {
pr_err("invalid flags %d\n", kvm_eq.flags);
return -EINVAL;
}
rc = xive_native_validate_queue_size(kvm_eq.qshift);
if (rc) {
pr_err("invalid queue size %d\n", kvm_eq.qshift);
return rc;
}
if (kvm_eq.qaddr & ((1ull << kvm_eq.qshift) - 1)) {
pr_err("queue page is not aligned %llx/%llx\n", kvm_eq.qaddr,
1ull << kvm_eq.qshift);
return -EINVAL;
}
srcu_idx = srcu_read_lock(&kvm->srcu);
gfn = gpa_to_gfn(kvm_eq.qaddr);
page_size = kvm_host_page_size(vcpu, gfn);
if (1ull << kvm_eq.qshift > page_size) {
srcu_read_unlock(&kvm->srcu, srcu_idx);
pr_warn("Incompatible host page size %lx!\n", page_size);
return -EINVAL;
}
page = gfn_to_page(kvm, gfn);
if (is_error_page(page)) {
srcu_read_unlock(&kvm->srcu, srcu_idx);
pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
return -EINVAL;
}
qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK);
srcu_read_unlock(&kvm->srcu, srcu_idx);
/*
* Backup the queue page guest address to the mark EQ page
* dirty for migration.
*/
q->guest_qaddr = kvm_eq.qaddr;
q->guest_qshift = kvm_eq.qshift;
/*
* Unconditional Notification is forced by default at the
* OPAL level because the use of END ESBs is not supported by
* Linux.
*/
rc = kvmppc_xive_native_configure_queue(xc->vp_id, q, priority,
(__be32 *) qaddr, kvm_eq.qshift, true);
if (rc) {
pr_err("Failed to configure queue %d for VCPU %d: %d\n",
priority, xc->server_num, rc);
put_page(page);
return rc;
}
/*
* Only restore the queue state when needed. When doing the
* H_INT_SET_SOURCE_CONFIG hcall, it should not.
*/
if (kvm_eq.qtoggle != 1 || kvm_eq.qindex != 0) {
rc = xive_native_set_queue_state(xc->vp_id, priority,
kvm_eq.qtoggle,
kvm_eq.qindex);
if (rc)
goto error;
}
rc = kvmppc_xive_attach_escalation(vcpu, priority,
kvmppc_xive_has_single_escalation(xive));
error:
if (rc)
kvmppc_xive_native_cleanup_queue(vcpu, priority);
return rc;
}
static int kvmppc_xive_native_get_queue_config(struct kvmppc_xive *xive,
long eq_idx, u64 addr)
{
struct kvm *kvm = xive->kvm;
struct kvm_vcpu *vcpu;
struct kvmppc_xive_vcpu *xc;
struct xive_q *q;
void __user *ubufp = (u64 __user *) addr;
u32 server;
u8 priority;
struct kvm_ppc_xive_eq kvm_eq;
u64 qaddr;
u64 qshift;
u64 qeoi_page;
u32 escalate_irq;
u64 qflags;
int rc;
/*
* Demangle priority/server tuple from the EQ identifier
*/
priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
KVM_XIVE_EQ_PRIORITY_SHIFT;
server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
KVM_XIVE_EQ_SERVER_SHIFT;
vcpu = kvmppc_xive_find_server(kvm, server);
if (!vcpu) {
pr_err("Can't find server %d\n", server);
return -ENOENT;
}
xc = vcpu->arch.xive_vcpu;
if (priority != xive_prio_from_guest(priority)) {
pr_err("invalid priority for queue %d for VCPU %d\n",
priority, server);
return -EINVAL;
}
q = &xc->queues[priority];
memset(&kvm_eq, 0, sizeof(kvm_eq));
if (!q->qpage)
return 0;
rc = xive_native_get_queue_info(xc->vp_id, priority, &qaddr, &qshift,
&qeoi_page, &escalate_irq, &qflags);
if (rc)
return rc;
kvm_eq.flags = 0;
if (qflags & OPAL_XIVE_EQ_ALWAYS_NOTIFY)
kvm_eq.flags |= KVM_XIVE_EQ_ALWAYS_NOTIFY;
kvm_eq.qshift = q->guest_qshift;
kvm_eq.qaddr = q->guest_qaddr;
rc = xive_native_get_queue_state(xc->vp_id, priority, &kvm_eq.qtoggle,
&kvm_eq.qindex);
if (rc)
return rc;
pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
__func__, server, priority, kvm_eq.flags,
kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
if (copy_to_user(ubufp, &kvm_eq, sizeof(kvm_eq)))
return -EFAULT;
return 0;
}
static void kvmppc_xive_reset_sources(struct kvmppc_xive_src_block *sb)
{
int i;
for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
if (!state->valid)
continue;
if (state->act_priority == MASKED)
continue;
state->eisn = 0;
state->act_server = 0;
state->act_priority = MASKED;
xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
if (state->pt_number) {
xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_01);
xive_native_configure_irq(state->pt_number,
0, MASKED, 0);
}
}
}
static int kvmppc_xive_reset(struct kvmppc_xive *xive)
{
struct kvm *kvm = xive->kvm;
struct kvm_vcpu *vcpu;
unsigned long i;
pr_devel("%s\n", __func__);
mutex_lock(&xive->lock);
kvm_for_each_vcpu(i, vcpu, kvm) {
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
unsigned int prio;
if (!xc)
continue;
kvmppc_xive_disable_vcpu_interrupts(vcpu);
for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
/* Single escalation, no queue 7 */
if (prio == 7 && kvmppc_xive_has_single_escalation(xive))
break;
if (xc->esc_virq[prio]) {
free_irq(xc->esc_virq[prio], vcpu);
irq_dispose_mapping(xc->esc_virq[prio]);
kfree(xc->esc_virq_names[prio]);
xc->esc_virq[prio] = 0;
}
kvmppc_xive_native_cleanup_queue(vcpu, prio);
}
}
for (i = 0; i <= xive->max_sbid; i++) {
struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
if (sb) {
arch_spin_lock(&sb->lock);
kvmppc_xive_reset_sources(sb);
arch_spin_unlock(&sb->lock);
}
}
mutex_unlock(&xive->lock);
return 0;
}
static void kvmppc_xive_native_sync_sources(struct kvmppc_xive_src_block *sb)
{
int j;
for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++) {
struct kvmppc_xive_irq_state *state = &sb->irq_state[j];
struct xive_irq_data *xd;
u32 hw_num;
if (!state->valid)
continue;
/*
* The struct kvmppc_xive_irq_state reflects the state
* of the EAS configuration and not the state of the
* source. The source is masked setting the PQ bits to
* '-Q', which is what is being done before calling
* the KVM_DEV_XIVE_EQ_SYNC control.
*
* If a source EAS is configured, OPAL syncs the XIVE
* IC of the source and the XIVE IC of the previous
* target if any.
*
* So it should be fine ignoring MASKED sources as
* they have been synced already.
*/
if (state->act_priority == MASKED)
continue;
kvmppc_xive_select_irq(state, &hw_num, &xd);
xive_native_sync_source(hw_num);
xive_native_sync_queue(hw_num);
}
}
static int kvmppc_xive_native_vcpu_eq_sync(struct kvm_vcpu *vcpu)
{
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
unsigned int prio;
int srcu_idx;
if (!xc)
return -ENOENT;
for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
struct xive_q *q = &xc->queues[prio];
if (!q->qpage)
continue;
/* Mark EQ page dirty for migration */
srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
mark_page_dirty(vcpu->kvm, gpa_to_gfn(q->guest_qaddr));
srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
}
return 0;
}
static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive)
{
struct kvm *kvm = xive->kvm;
struct kvm_vcpu *vcpu;
unsigned long i;
pr_devel("%s\n", __func__);
mutex_lock(&xive->lock);
for (i = 0; i <= xive->max_sbid; i++) {
struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
if (sb) {
arch_spin_lock(&sb->lock);
kvmppc_xive_native_sync_sources(sb);
arch_spin_unlock(&sb->lock);
}
}
kvm_for_each_vcpu(i, vcpu, kvm) {
kvmppc_xive_native_vcpu_eq_sync(vcpu);
}
mutex_unlock(&xive->lock);
return 0;
}
static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
struct kvmppc_xive *xive = dev->private;
switch (attr->group) {
case KVM_DEV_XIVE_GRP_CTRL:
switch (attr->attr) {
case KVM_DEV_XIVE_RESET:
return kvmppc_xive_reset(xive);
case KVM_DEV_XIVE_EQ_SYNC:
return kvmppc_xive_native_eq_sync(xive);
case KVM_DEV_XIVE_NR_SERVERS:
return kvmppc_xive_set_nr_servers(xive, attr->addr);
}
break;
case KVM_DEV_XIVE_GRP_SOURCE:
return kvmppc_xive_native_set_source(xive, attr->attr,
attr->addr);
case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
return kvmppc_xive_native_set_source_config(xive, attr->attr,
attr->addr);
case KVM_DEV_XIVE_GRP_EQ_CONFIG:
return kvmppc_xive_native_set_queue_config(xive, attr->attr,
attr->addr);
case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
return kvmppc_xive_native_sync_source(xive, attr->attr,
attr->addr);
}
return -ENXIO;
}
static int kvmppc_xive_native_get_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
struct kvmppc_xive *xive = dev->private;
switch (attr->group) {
case KVM_DEV_XIVE_GRP_EQ_CONFIG:
return kvmppc_xive_native_get_queue_config(xive, attr->attr,
attr->addr);
}
return -ENXIO;
}
static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
struct kvm_device_attr *attr)
{
switch (attr->group) {
case KVM_DEV_XIVE_GRP_CTRL:
switch (attr->attr) {
case KVM_DEV_XIVE_RESET:
case KVM_DEV_XIVE_EQ_SYNC:
case KVM_DEV_XIVE_NR_SERVERS:
return 0;
}
break;
case KVM_DEV_XIVE_GRP_SOURCE:
case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
if (attr->attr >= KVMPPC_XIVE_FIRST_IRQ &&
attr->attr < KVMPPC_XIVE_NR_IRQS)
return 0;
break;
case KVM_DEV_XIVE_GRP_EQ_CONFIG:
return 0;
}
return -ENXIO;
}
/*
* Called when device fd is closed. kvm->lock is held.
*/
static void kvmppc_xive_native_release(struct kvm_device *dev)
{
struct kvmppc_xive *xive = dev->private;
struct kvm *kvm = xive->kvm;
struct kvm_vcpu *vcpu;
unsigned long i;
pr_devel("Releasing xive native device\n");
/*
* Clear the KVM device file address_space which is used to
* unmap the ESB pages when a device is passed-through.
*/
mutex_lock(&xive->mapping_lock);
xive->mapping = NULL;
mutex_unlock(&xive->mapping_lock);
/*
* Since this is the device release function, we know that
* userspace does not have any open fd or mmap referring to
* the device. Therefore there can not be any of the
* device attribute set/get, mmap, or page fault functions
* being executed concurrently, and similarly, the
* connect_vcpu and set/clr_mapped functions also cannot
* be being executed.
*/
debugfs_remove(xive->dentry);
/*
* We should clean up the vCPU interrupt presenters first.
*/
kvm_for_each_vcpu(i, vcpu, kvm) {
/*
* Take vcpu->mutex to ensure that no one_reg get/set ioctl
* (i.e. kvmppc_xive_native_[gs]et_vp) can be being done.
* Holding the vcpu->mutex also means that the vcpu cannot
* be executing the KVM_RUN ioctl, and therefore it cannot
* be executing the XIVE push or pull code or accessing
* the XIVE MMIO regions.
*/
mutex_lock(&vcpu->mutex);
kvmppc_xive_native_cleanup_vcpu(vcpu);
mutex_unlock(&vcpu->mutex);
}
/*
* Now that we have cleared vcpu->arch.xive_vcpu, vcpu->arch.irq_type
* and vcpu->arch.xive_esc_[vr]addr on each vcpu, we are safe
* against xive code getting called during vcpu execution or
* set/get one_reg operations.
*/
kvm->arch.xive = NULL;
for (i = 0; i <= xive->max_sbid; i++) {
if (xive->src_blocks[i])
kvmppc_xive_free_sources(xive->src_blocks[i]);
kfree(xive->src_blocks[i]);
xive->src_blocks[i] = NULL;
}
if (xive->vp_base != XIVE_INVALID_VP)
xive_native_free_vp_block(xive->vp_base);
/*
* A reference of the kvmppc_xive pointer is now kept under
* the xive_devices struct of the machine for reuse. It is
* freed when the VM is destroyed for now until we fix all the
* execution paths.
*/
kfree(dev);
}
/*
* Create a XIVE device. kvm->lock is held.
*/
static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
{
struct kvmppc_xive *xive;
struct kvm *kvm = dev->kvm;
pr_devel("Creating xive native device\n");
if (kvm->arch.xive)
return -EEXIST;
xive = kvmppc_xive_get_device(kvm, type);
if (!xive)
return -ENOMEM;
dev->private = xive;
xive->dev = dev;
xive->kvm = kvm;
mutex_init(&xive->mapping_lock);
mutex_init(&xive->lock);
/* VP allocation is delayed to the first call to connect_vcpu */
xive->vp_base = XIVE_INVALID_VP;
/* KVM_MAX_VCPUS limits the number of VMs to roughly 64 per sockets
* on a POWER9 system.
*/
xive->nr_servers = KVM_MAX_VCPUS;
if (xive_native_has_single_escalation())
xive->flags |= KVMPPC_XIVE_FLAG_SINGLE_ESCALATION;
if (xive_native_has_save_restore())
xive->flags |= KVMPPC_XIVE_FLAG_SAVE_RESTORE;
xive->ops = &kvmppc_xive_native_ops;
kvm->arch.xive = xive;
return 0;
}
/*
* Interrupt Pending Buffer (IPB) offset
*/
#define TM_IPB_SHIFT 40
#define TM_IPB_MASK (((u64) 0xFF) << TM_IPB_SHIFT)
int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
{
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
u64 opal_state;
int rc;
if (!kvmppc_xive_enabled(vcpu))
return -EPERM;
if (!xc)
return -ENOENT;
/* Thread context registers. We only care about IPB and CPPR */
val->xive_timaval[0] = vcpu->arch.xive_saved_state.w01;
/* Get the VP state from OPAL */
rc = xive_native_get_vp_state(xc->vp_id, &opal_state);
if (rc)
return rc;
/*
* Capture the backup of IPB register in the NVT structure and
* merge it in our KVM VP state.
*/
val->xive_timaval[0] |= cpu_to_be64(opal_state & TM_IPB_MASK);
pr_devel("%s NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x opal=%016llx\n",
__func__,
vcpu->arch.xive_saved_state.nsr,
vcpu->arch.xive_saved_state.cppr,
vcpu->arch.xive_saved_state.ipb,
vcpu->arch.xive_saved_state.pipr,
vcpu->arch.xive_saved_state.w01,
(u32) vcpu->arch.xive_cam_word, opal_state);
return 0;
}
int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
{
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
pr_devel("%s w01=%016llx vp=%016llx\n", __func__,
val->xive_timaval[0], val->xive_timaval[1]);
if (!kvmppc_xive_enabled(vcpu))
return -EPERM;
if (!xc || !xive)
return -ENOENT;
/* We can't update the state of a "pushed" VCPU */
if (WARN_ON(vcpu->arch.xive_pushed))
return -EBUSY;
/*
* Restore the thread context registers. IPB and CPPR should
* be the only ones that matter.
*/
vcpu->arch.xive_saved_state.w01 = val->xive_timaval[0];
/*
* There is no need to restore the XIVE internal state (IPB
* stored in the NVT) as the IPB register was merged in KVM VP
* state when captured.
*/
return 0;
}
bool kvmppc_xive_native_supported(void)
{
return xive_native_has_queue_state_support();
}
static int xive_native_debug_show(struct seq_file *m, void *private)
{
struct kvmppc_xive *xive = m->private;
struct kvm *kvm = xive->kvm;
struct kvm_vcpu *vcpu;
unsigned long i;
if (!kvm)
return 0;
seq_puts(m, "=========\nVCPU state\n=========\n");
kvm_for_each_vcpu(i, vcpu, kvm) {
struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
if (!xc)
continue;
seq_printf(m, "VCPU %d: VP=%#x/%02x\n"
" NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
xc->server_num, xc->vp_id, xc->vp_chip_id,
vcpu->arch.xive_saved_state.nsr,
vcpu->arch.xive_saved_state.cppr,
vcpu->arch.xive_saved_state.ipb,
vcpu->arch.xive_saved_state.pipr,
be64_to_cpu(vcpu->arch.xive_saved_state.w01),
be32_to_cpu(vcpu->arch.xive_cam_word));
kvmppc_xive_debug_show_queues(m, vcpu);
}
seq_puts(m, "=========\nSources\n=========\n");
for (i = 0; i <= xive->max_sbid; i++) {
struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
if (sb) {
arch_spin_lock(&sb->lock);
kvmppc_xive_debug_show_sources(m, sb);
arch_spin_unlock(&sb->lock);
}
}
return 0;
}
DEFINE_SHOW_ATTRIBUTE(xive_native_debug);
static void xive_native_debugfs_init(struct kvmppc_xive *xive)
{
xive->dentry = debugfs_create_file("xive", 0444, xive->kvm->debugfs_dentry,
xive, &xive_native_debug_fops);
pr_debug("%s: created\n", __func__);
}
static void kvmppc_xive_native_init(struct kvm_device *dev)
{
struct kvmppc_xive *xive = dev->private;
/* Register some debug interfaces */
xive_native_debugfs_init(xive);
}
struct kvm_device_ops kvm_xive_native_ops = {
.name = "kvm-xive-native",
.create = kvmppc_xive_native_create,
.init = kvmppc_xive_native_init,
.release = kvmppc_xive_native_release,
.set_attr = kvmppc_xive_native_set_attr,
.get_attr = kvmppc_xive_native_get_attr,
.has_attr = kvmppc_xive_native_has_attr,
.mmap = kvmppc_xive_native_mmap,
};
|